CN111707908A - Method, device and storage medium for detecting arc fault in series with multiple load circuits - Google Patents
Method, device and storage medium for detecting arc fault in series with multiple load circuitsDownload PDFInfo
- Publication number
- CN111707908A CN111707908ACN202010748868.5ACN202010748868ACN111707908ACN 111707908 ACN111707908 ACN 111707908ACN 202010748868 ACN202010748868 ACN 202010748868ACN 111707908 ACN111707908 ACN 111707908A
- Authority
- CN
- China
- Prior art keywords
- fault
- wavelet coefficients
- series
- arc
- fault indication
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及电弧检测领域，尤其涉及一种多负载回路串联故障电弧检测方法、装置以及存储介质。The invention relates to the field of arc detection, in particular to a method, device and storage medium for detecting arc faults in series with multiple load loops.
背景技术Background technique
电弧放电是穿过绝缘介质的发光放电，通常伴随着电极的部分挥发的现象，而故障电弧则是“电路中无意的电弧放电状态”。电弧的中心温度高达5000K到15000K，如果周围有可燃材料，极有可能会引起火灾。Arc discharge is a luminous discharge through an insulating medium, usually accompanied by partial volatilization of an electrode, while a fault arc is an "unintentional arcing state in a circuit". The temperature of the center of the arc is as high as 5000K to 15000K, and if there are combustible materials around, it is very likely to cause a fire.
在家庭住宅、办公楼、大型商场等配电系统中，由于电线老化、接触不良等原因，经常出现串联故障电弧，继而引发电气火灾，为用户带来难以估量的损失。目前，针对串联故障电弧的研究，多集中在某一确定的单一负载回路。然而，在真实的用电网络中，线路非常复杂，且负载呈多元化，有些线路甚至非常隐蔽，很难保证在每一个负载回路中安装一个故障电弧探测器。In power distribution systems such as family residences, office buildings, and large shopping malls, due to aging wires and poor contact, series fault arcs often occur, which in turn lead to electrical fires, bringing incalculable losses to users. At present, the research on series arc faults mostly focuses on a certain single load circuit. However, in the real power consumption network, the lines are very complex, and the loads are diversified, and some lines are even very concealed. It is difficult to ensure that a fault arc detector is installed in each load circuit.
另外当故障电弧发生在某一支线回路上时，尤其该回路负载功率相对较小时，故障电流变化不明显，由故障电弧引起的电流畸变很容易被其它回路的大电流和背景噪声所淹没，这极大地增加了检测故障电弧的难度。In addition, when the fault arc occurs on a branch circuit, especially when the load power of the circuit is relatively small, the change of the fault current is not obvious, and the current distortion caused by the fault arc is easily overwhelmed by the large current and background noise of other circuits. Greatly increases the difficulty of detecting arc faults.
发明内容SUMMARY OF THE INVENTION
本申请实施例通过提供一种多负载回路串联故障电弧检测方法、装置以及存储介质，旨在解决现有技术中只能检测单一负载回路中的故障电弧，但无法对多负载回路进行故障电弧检测的问题。By providing a method, device and storage medium for detecting arc faults in series with multiple load circuits, the embodiments of the present application aim to solve the problem that in the prior art, arc faults in a single load circuit can only be detected, but arc fault detection cannot be performed on multiple load circuits. The problem.
本申请实施例提供了一种多负载回路串联故障电弧检测方法，其包括：The embodiment of the present application provides a method for detecting arc faults in series with multiple load loops, which includes:
采集多负载回路中的干路电流信号；Collect main circuit current signals in multiple load circuits;
对所述干路电流信号进行小波变换，获取小波系数；performing wavelet transformation on the mains current signal to obtain wavelet coefficients;
对所述小波系数进行处理获取至少两个故障指示特征；其中，所述故障指示特征满足：当产生故障电弧时，所述故障指示特征不受非故障支路的干扰，且能够用于判断故障支路是否发生故障；The wavelet coefficients are processed to obtain at least two fault indication features; wherein, the fault indication features satisfy: when a fault arc occurs, the fault indication features are not disturbed by non-faulty branches, and can be used to judge the fault Whether the branch circuit is faulty;
若所述至少两个故障指示特征满足预设判断条件，则判定多负载回路出现故障电弧。If the at least two fault indication features satisfy the preset judgment condition, it is judged that a fault arc occurs in the multi-load circuit.
在一些实施例中，采用神经网络模型判断所述至少两个故障指示特征是否满足预设判断条件；其中，所述神经网络模型以所述至少两个故障指示特征为输入，以是否发生电弧故障为输出。In some embodiments, a neural network model is used to determine whether the at least two fault-indicating features satisfy a preset judgment condition; wherein, the neural network model takes the at least two fault-indicating features as input to determine whether an arc fault occurs for output.
在一些实施例中，还包括训练得到所述神经网络模型的步骤，包括：In some embodiments, it also includes the step of obtaining the neural network model through training, including:
搭建多负载回路串联故障电弧仿真模型；Build a multi-load circuit series arc fault simulation model;
基于所述多负载回路串联故障电弧仿真模型，根据应用场景生成训练数据；其中，所述训练数据所包含的特征与所述至少两个故障指示特征对应，且具有对应的故障标签；Based on the multi-load loop series arc fault simulation model, training data is generated according to an application scenario; wherein the features included in the training data correspond to the at least two fault indication features and have corresponding fault labels;
采用所述训练数据对所述神经网络模型进行训练。The neural network model is trained using the training data.
在一些实施例中，所述对所述干路电流信号进行小波变换，获取小波系数的步骤，包括：In some embodiments, the step of performing wavelet transform on the mains current signal to obtain wavelet coefficients includes:
对所述干路电流信号以多贝西小波系列中的db4小波函数为基函数进行四层分解，获取各层小波系数在一些实施例中，所述对所述小波系数进行处理获取至少两个故障指示特征，包括：The main circuit current signal is decomposed in four layers using the db4 wavelet function in the Dobessie wavelet series as the basis function, and the wavelet coefficients of each layer are obtained. In some embodiments, the wavelet coefficients are processed to obtain at least two Fault-indicating characteristics, including:
计算
在一些实施例中，所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：In some embodiments, the step of processing the wavelet coefficients to obtain at least two fault indication features includes:
计算
在一些实施例中，所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：In some embodiments, the step of processing the wavelet coefficients to obtain at least two fault indication features includes:
计算
在一些实施例中，所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：In some embodiments, the step of processing the wavelet coefficients to obtain at least two fault indication features includes:
计算
本申请还提出一种串联故障电弧检测装置，所述串联故障电弧检测装置包括电流检测装置、与所述电流检测装置通信连接的处理器、存储器和存储在所述存储器上并可在所述处理器上运行的串联故障电弧检测程序，所述串联故障电弧检测程序被所述处理器执行时实现所述多负载回路串联故障电弧检测方法的各个步骤。The present application also proposes a series arc fault detection device, the series arc fault detection device includes a current detection device, a processor communicatively connected to the current detection device, a memory, and a storage device stored on the memory and available in the processing A series arc fault detection program running on the processor, when the series arc fault detection program is executed by the processor, implements each step of the multi-load circuit series arc fault detection method.
本申请还提出一种计算机可读存储介质，所述计算机可读存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现所述多负载回路串联故障电弧检测方法中的步骤。The present application also proposes a computer-readable storage medium, where one or more programs are stored in the computer-readable storage medium, and the one or more programs can be executed by one or more processors to realize the multi-load Steps in a loop series arc fault detection method.
本申请通过采集多负载回路的干路电流，并对干路电流进行小波变换，得到小波系数，再对所述小波系数进行处理获取至少两个故障指示特征，所述故障指示特征不受非故障支路的干扰，因此可避免受到多负载回路中其他大功率支路电流的干扰，再测试至少两个故障指示特征是否满足预设判断条件，从而得出检测结果。从而本申请更可靠地从多负载回路的干路电流中提取并识别出任意支路所发生的串联故障电弧。本实施例可解决现有方法只能对某单一负载回路检测故障电弧的缺陷，适用于放置在线路复杂、且负载呈多元化、甚至有些线路非常隐蔽的家庭住宅、办公楼、大型商场用电网络的配电进线处，而不必再需要为线路中的每个负载配置一台故障电弧探测器，起到节省故障电弧探测器成本的作用，同时还能有效地预防因故障电弧导致的火灾的发生。In the present application, the main circuit currents of multiple load circuits are collected, and the main circuit current is subjected to wavelet transformation to obtain wavelet coefficients, and then the wavelet coefficients are processed to obtain at least two fault indication features, which are not affected by non-fault indications. Therefore, it can avoid the interference of other high-power branch currents in the multi-load circuit, and then test whether at least two fault indication characteristics meet the preset judgment conditions, so as to obtain the detection result. Therefore, the present application can more reliably extract and identify the series fault arc occurred in any branch circuit from the main circuit current of multiple load circuits. This embodiment can solve the defect that the existing method can only detect a fault arc for a single load circuit, and is suitable for power consumption in family houses, office buildings, and large shopping malls where the lines are complex, the loads are diversified, and even some lines are very concealed. At the power distribution inlet of the network, it is no longer necessary to configure a fault arc detector for each load in the line, which can save the cost of the fault arc detector and effectively prevent the fire caused by the fault arc. happened.
附图说明Description of drawings
图1为本申请的串联故障电弧检测装置的一实施例的硬件结构示意图；FIG. 1 is a schematic diagram of the hardware structure of an embodiment of the series arc fault detection device of the present application;
图2为本申请的多负载回路串联故障电弧检测方法的实施例一的流程框图；FIG. 2 is a flowchart of
图3在仿真平台MATLAD中构建的多负载回路串联故障电弧仿真模型的的结构示意图；Figure 3 is a schematic structural diagram of a multi-load loop series arc fault simulation model constructed in the simulation platform MATLAD;
图4表示在图3中的电路连接不同数量的负载时，干路电流的第一层小波系数的示意图；Fig. 4 shows the schematic diagram of the first-layer wavelet coefficients of the main circuit current when the circuit in Fig. 3 is connected with different numbers of loads;
图5为本申请的多负载回路串联故障电弧检测方法的实施例一的至少两个故障指示特征是第一故障指示特征和第二故障指示特征的流程框图；FIG. 5 is a flow chart of the first embodiment of the method for detecting arc faults in series with multiple load circuits of the present application, in which at least two fault indication features are a first fault indication feature and a second fault indication feature;
图6表示有故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第一故障指示特征与正常状态下的正常参数的对比图；Fig. 6 shows the comparison diagram of the first fault indication feature in the wavelet coefficients of each layer and the normal parameters in the normal state after the four-layer wavelet decomposition is performed on the main circuit current with the db4 wavelet function as the basis function when an arc fault occurs;
图7表示有故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第二故障指示特征与正常状态下的正常参数的对比图；Fig. 7 shows the comparison diagram of the second fault indication feature in the wavelet coefficients of each layer and the normal parameters in the normal state after the four-layer wavelet decomposition is performed on the main circuit current with the db4 wavelet function as the basis function when an arc fault occurs;
图8为本申请的多负载回路串联故障电弧检测方法的实施例二的流程框图；FIG. 8 is a flowchart of
图9表示有故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第三故障指示特征与正常状态下的正常参数的对比图；Fig. 9 is a graph showing the comparison of the third fault indication feature in the wavelet coefficients of each layer and the normal parameters in the normal state after four-layer wavelet decomposition is performed on the main circuit current with the db4 wavelet function as the basis function when an arc fault occurs;
图10为本申请的多负载回路串联故障电弧检测方法的实施例三的流程框图；FIG. 10 is a flowchart of Embodiment 3 of the method for detecting arc faults in series with multiple load loops of the present application;
图11为本申请的多负载回路串联故障电弧检测方法的实施例四的流程框图。FIG. 11 is a flowchart of Embodiment 4 of the method for detecting arc faults in series with multiple load circuits of the present application.
具体实施方式Detailed ways
为了更好的理解上述技术方案，下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。For better understanding of the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.
在家庭住宅、办公楼、大型商场等配电系统中，由于电线老化、接触不良等原因，经常出现串联故障电弧，继而引发电气火灾，为用户带来难以估量的损失。目前，针对串联故障电弧的研究，多集中在某一确定的单一负载回路。然而，在真实的用电网络中，线路非常复杂，且负载呈多元化，有些线路甚至非常隐蔽，很难保证在每一个负载回路中安装一个故障电弧探测器。因此，故障电弧探测器往往放置在用户配电进线处。In power distribution systems such as family residences, office buildings, and large shopping malls, due to aging wires and poor contact, series fault arcs often occur, which in turn lead to electrical fires, bringing incalculable losses to users. At present, the research on series arc faults mostly focuses on a certain single load circuit. However, in the real power consumption network, the lines are very complex, and the loads are diversified, and some lines are even very concealed. It is difficult to ensure that a fault arc detector is installed in each load circuit. Therefore, arc fault detectors are often placed at the user's power distribution inlet.
当故障电弧发生在某一支线回路上时，尤其该回路负载功率相对较小时，故障电流变化不明显，由故障电弧引起的电流畸变很容易被其它回路的大电流和背景噪声所淹没，这极大地增加了检测故障电弧的难度。所以，当串联故障电弧发生时，如何从配电进线处测得的电流信号中识别出故障信号成了故障电弧检测技术的关键。鉴于此，本申请提出一种多负载回路串联故障电弧检测方法、装置以及存储介质。When a fault arc occurs on a branch circuit, especially when the load power of the circuit is relatively small, the fault current does not change significantly, and the current distortion caused by the fault arc is easily overwhelmed by the large current and background noise of other circuits. Greatly increases the difficulty of detecting arc faults. Therefore, when a series fault arc occurs, how to identify the fault signal from the current signal measured at the power distribution inlet becomes the key to the fault arc detection technology. In view of this, the present application proposes a method, device and storage medium for detecting arc faults in series with multiple load circuits.
下面介绍串联故障电弧检测装置，请参照图1，本申请的实施例提出一种串联故障电弧检测装置，所述串联故障电弧检测装置包括：电流检测装置104，处理器101，存储器102以及通信总线103。其中，通信总线103用于实现这些组件之间的连接通信。A series arc fault detection device will be introduced below. Please refer to FIG. 1. An embodiment of the present application proposes a series arc fault detection device. The series arc fault detection device includes: a
所述电流检测装置104上设置于多负载回路的干路上，用于对干路电流进行采集。所述电流检测装置104可以采用各种市面上的各种交流电流检测装置。The
处理器101可以是中央处理单元(CPU)，该处理器还可以是其他通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。The
存储器102可以是高速RAM存储器，也可以是稳定的存储器(non-volatilememory)，例如磁盘存储器。如图1所示，作为一种计算机存储介质的存储器103中可以包括串联故障电弧检测程序；而处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：The
在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：In one embodiment, the
采用神经网络模型判断所述至少两个故障指示特征是否满足预设判断条件；其中，所述神经网络模型以所述至少两个故障指示特征为输入，以是否发生电弧故障为输出。A neural network model is used to judge whether the at least two fault indication features satisfy the preset judgment condition; wherein, the neural network model takes the at least two fault indication features as input, and takes whether an arc fault occurs as an output.
在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：In one embodiment, the
还包括训练得到所述神经网络模型的步骤，其包括：搭建多负载回路串联故障电弧仿真模型；基于所述仿真模型，根据应用场景开展仿真并获取训练数据；其中，所述训练数据所包含的特征与所述至少两个故障指示特征对应，且具有对应的故障标签；采用所述训练数据对所述神经网络模型进行训练。It also includes the step of training to obtain the neural network model, which includes: building a multi-load loop series fault arc simulation model; based on the simulation model, carrying out simulation and obtaining training data according to application scenarios; wherein, the training data includes The features correspond to the at least two fault indication features and have corresponding fault labels; the neural network model is trained by using the training data.
在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：In one embodiment, the
所述对所述干路电流信号进行小波变换，获取小波系数的步骤，包括：The step of performing wavelet transformation on the mains current signal to obtain wavelet coefficients includes:
对所述干路电流信号以多贝西小波系列中的db4小波函数为基函数进行四层分解，获取各层小波系数在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：The main circuit current signal is decomposed in four layers using the db4 wavelet function in the Dobessie wavelet series as the basis function, and the wavelet coefficients of each layer are obtained. Arc fault detection procedure, and do the following:
所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：The step of processing the wavelet coefficients to obtain at least two fault indication features includes:
计算
在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：In one embodiment, the
所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：The step of processing the wavelet coefficients to obtain at least two fault indication features includes:
计算
在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：In one embodiment, the
计算
在一实施例中，处理器101可以用于调用存储器102中存储的串联故障电弧检测程序，并执行以下操作：所述对所述小波系数进行处理获取至少两个故障指示特征的步骤，包括：In one embodiment, the
计算
本实施例通过采集多负载回路的干路电流，并对干路电流进行小波变换，得到小波系数，再对所述小波系数进行处理获取至少两个故障指示特征，所述故障指示特征不受非故障支路的干扰，因此可避免受到多负载回路中其他大功率支路电流的干扰，再测试至少两个故障指示特征是否满足预设判断条件，从而得出检测结果。从而本申请更可靠地从多负载回路的干路电流中提取并识别出任意支路所发生的串联故障电弧。本实施例可解决现有方法只能对某单一负载回路检测故障电弧的缺陷，适用于放置在线路复杂、且负载呈多元化、甚至有些线路非常隐蔽的家庭住宅、办公楼、大型商场用电网络的配电进线处，而不必再需要为线路中的每个负载配置一台故障电弧探测器，起到节省故障电弧探测器成本的作用，同时还能有效地预防因故障电弧导致的火灾的发生。In this embodiment, the main circuit currents of multiple load circuits are collected, and the main circuit current is subjected to wavelet transformation to obtain wavelet coefficients, and then the wavelet coefficients are processed to obtain at least two fault indication features. Therefore, it can avoid the interference of other high-power branch currents in the multi-load circuit, and then test whether at least two fault indication characteristics meet the preset judgment conditions, so as to obtain the detection result. Therefore, the present application can more reliably extract and identify the series fault arc occurred in any branch circuit from the main circuit current of multiple load circuits. This embodiment can solve the defect that the existing method can only detect a fault arc for a single load circuit, and is suitable for power consumption in family houses, office buildings, and large shopping malls where the lines are complex, the loads are diversified, and even some lines are very concealed. At the power distribution inlet of the network, it is no longer necessary to configure a fault arc detector for each load in the line, which can save the cost of the fault arc detector and effectively prevent the fire caused by the fault arc. happened.
基于上述串联故障电弧检测装置的硬件构架，提出本申请的多负载回路串联故障电弧检测方法的实施例。Based on the hardware structure of the above-mentioned serial arc fault detection device, an embodiment of the multi-load loop serial fault arc detection method of the present application is proposed.
参照图2，图2为本申请多负载回路串联故障电弧检测方法的实施例一，所述多负载回路串联故障电弧检测方法包括以下步骤：Referring to FIG. 2, FIG. 2 is the first embodiment of the multi-load circuit series arc fault detection method of the present application. The multi-load circuit series series arc fault detection method includes the following steps:
S110、采集多负载回路中的干路电流信号；S110. Collect the main circuit current signal in the multi-load circuit;
通过在多负载回路的干路中设置电流检测装置104对干路电流进行检测，而在实际应用中，通常在用户配电进线处设置电流检测装置104，以实现对干路电流的检测。需要说明的是，由于多负载回路中多个的负载之间的关系为并联，本文的术语“干路”指的是所有负载电流经过的回路的重合部分的电路。换句话说，即是与电源直接相连的电路。The main circuit current is detected by arranging the
S120、对所述干路电流信号进行小波变换，获取小波系数；S120, performing wavelet transformation on the mains current signal to obtain wavelet coefficients;
如背景技术所述，现实环境中的线路非常复杂，且负载呈多元化，当故障电弧发生在某一支线回路上时，尤其该回路负载功率相对较小时，故障电流变化不明显，由故障电弧引起的电流畸变很容易被其它回路的大电流和背景噪声所淹没，导致检测故障电弧的难度加大。因此需要找到一个不受多负载电路的支路电路影响的“相对稳定量”，以此作为故障电弧判断的基础。本申请通过利用MATLAD对多负载回路进行故障电弧仿真，申请人发现干路电流的小波系数基本不受其它大功率支路电流的影响。故而，在本申请中，对所述干路电流信号进行小波变换，获取小波系数再进行后续的故障电弧判断。As mentioned in the background art, the lines in the real environment are very complex and the loads are diversified. When a fault arc occurs on a branch circuit, especially when the load power of the circuit is relatively small, the fault current does not change significantly. The induced current distortion is easily overwhelmed by the large currents and background noise of other circuits, making it more difficult to detect arc faults. Therefore, it is necessary to find a "relatively stable quantity" that is not affected by the branch circuit of the multi-load circuit, as the basis for the judgment of the fault arc. In the present application, by using MATLAD to simulate arc faults on multiple load circuits, the applicant finds that the wavelet coefficient of the main circuit current is basically not affected by other high-power branch currents. Therefore, in the present application, wavelet transform is performed on the mains current signal, wavelet coefficients are obtained, and subsequent arc fault judgment is performed.
具体地，对所述干路电流信号以多贝西小波系列中的db4小波函数为基函数进行四层分解，获取各层小波系数。申请人在多次的实验中发现，当小波变换的基函数为db4小波函数，且进行四层分解时，能获得不受其余负载支路干扰且能明显区分故障状态与正常状态的小波系数，故在本申请中选用db4小波函数为基函数，对干路电流进行四层小波变换。Specifically, four-layer decomposition is performed on the main circuit current signal using the db4 wavelet function in the Dobessie wavelet series as a basis function, and the wavelet coefficients of each layer are obtained. The applicant has found in many experiments that when the basis function of the wavelet transform is the db4 wavelet function and the four-layer decomposition is performed, the wavelet coefficients that are not disturbed by the rest of the load branches and can clearly distinguish the fault state from the normal state can be obtained. Therefore, in this application, the db4 wavelet function is selected as the basis function, and the four-layer wavelet transform is performed on the main circuit current.
请参照图3，在仿真平台MATLAD中构建多个不同负载(即图中的阻性负载，阻感负载和阻容负载)并联组成多负载回路，故障电弧发生模块与任一负载连接，故障电弧发生模块用于产生故障电弧，电流检测装置则设置在干路上对干路电流进行检测。其中，阻性负载指的是单一电阻负载，阻感负载指的是电阻和电感串联而成的组合负载，阻容负载指的是电阻和电容串联而成的组合负载。图4表示在图3中的电路连接不同数量的负载时，干路电流的第一层小波系数的情况。例如，当电路中只存在一个阻性负载，电弧发生模块与阻性负载串联组成单负载回路；在上述单负载回路的基础上，再并联一个阻感负载组成双负载回路；在上述双负载回路的基础上，再并联一个阻容负载组成三负载回路；三负载回路以上的多负载回路的组成原理可以此类推。Please refer to Figure 3. In the simulation platform MATLAD, construct multiple different loads (that is, resistive loads, resistive-inductive loads and resistive-capacitive loads in the figure) in parallel to form a multi-load loop. The fault arc generation module is connected to any load, and the fault arc The generating module is used to generate the fault arc, and the current detection device is arranged on the main road to detect the main circuit current. Among them, resistive load refers to a single resistive load, resistive-inductive load refers to a combined load formed by a resistor and an inductor in series, and a resistive-capacitive load refers to a combined load formed by a resistor and a capacitor in series. Figure 4 shows the wavelet coefficients of the first layer of the mains current when the circuit in Figure 3 is connected to different numbers of loads. For example, when there is only one resistive load in the circuit, the arc generating module and the resistive load are connected in series to form a single-load loop; on the basis of the above single-load loop, a resistive-inductive load is connected in parallel to form a double-load loop; in the above-mentioned double-load loop On the basis of , a resistance-capacitance load is connected in parallel to form three load circuits;
从图4中可看出，单负载回路的小波系数的波形与双负载回路的小波系数的波形及三负载回路的小波系数的波形近乎相同。也就是说，对干路电流进行小波变换后得到的小波系数不受实际中并联的负载数量的影响，即干路电流的小波系数基本不受其它大功率支路电流(即非故障支路)的影响。因此可将干路电流的小波系数作为故障电弧的研究基础。It can be seen from Fig. 4 that the waveforms of the wavelet coefficients of the single-load loop are almost the same as the waveforms of the wavelet coefficients of the double-load loop and the wavelet coefficients of the three-load loop. That is to say, the wavelet coefficient obtained by the wavelet transformation of the main circuit current is not affected by the number of loads connected in parallel in practice, that is, the wavelet coefficient of the main circuit current is basically not affected by the currents of other high-power branches (ie, non-faulty branches). Impact. Therefore, the wavelet coefficient of main circuit current can be used as the research basis of fault arc.
在找到多负载电路中不受其它大功率支路电流的影响的小波系数的情况下，通过小波系数寻找到区分故障电弧产生状态与正常状态的故障指示特征，即可得到判断电路中是否发生故障电弧的判断依据，从而实现多负载回路中的故障电弧判断。In the case of finding the wavelet coefficients in the multi-load circuit that are not affected by the current of other high-power branches, the fault indication features that distinguish the fault arc generation state and the normal state can be found through the wavelet coefficients, and then the judgment of whether a fault occurs in the circuit can be obtained. The judgment basis of the arc, so as to realize the judgment of the fault arc in the multi-load circuit.
S130、对所述小波系数进行处理获取至少两个故障指示特征；其中，所述故障指示特征满足：当产生故障电弧时，所述故障指示特征不受非故障支路的干扰，且能够用于判断故障支路是否发生故障。S130. Process the wavelet coefficients to obtain at least two fault indication features; wherein, the fault indication features satisfy: when a fault arc occurs, the fault indication features are not disturbed by non-faulty branches, and can be used for Determine whether the faulty branch is faulty.
需要说明的是，由于所述小波系数不受其它大功率支路电流的影响，通过小波系数求得的故障指示特征必然也不受其它大功率支路电流(非故障支路)的影响。可以理解的是，上述的“不受影响”并非绝对不受到任何影响，而是指影响处于非常微小的程度，基本上可以忽略。It should be noted that, since the wavelet coefficients are not affected by the currents of other high-power branches, the fault indication feature obtained by the wavelet coefficients must also not be affected by the currents of other high-power branches (non-faulty branches). It can be understood that the above-mentioned "not affected" does not mean that it is not affected at all, but means that the impact is at a very small level and can be basically ignored.
在本实施例中，请参照图5，对所述小波系数进行处理获取至少两个故障指示特征的步骤包括：S131、计算
具体地，请参照图6，图6表示有故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第一故障指示特征与正常状态下的正常参数的对比图。其中，横坐标表示为实验组别，纵坐标表示为第一故障指示特征的数值。a1表示第一层小波系数的第一故障指示特征与正常状态下的正常参数的对比图，a2至a4的含义可以此类推。Specifically, please refer to FIG. 6. FIG. 6 shows the first fault indication feature in each layer of wavelet coefficients and the normal state of A comparison chart of the parameters. Among them, the abscissa represents the experimental group, and the ordinate represents the value of the first fault indication feature. a1 represents a comparison diagram of the first fault indication feature of the wavelet coefficients of the first layer and the normal parameters in a normal state, and the meanings of a2 to a4 can be deduced by analogy.
通过观察图6可发现，在故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第一故障指示特征与正常参数存在明显的差异，且进一步观察可发现，第一层小波系数至第四层小波系数求得的第一故障指示特征的数值均在10以上，且正常参数均在0附近。By observing Fig. 6, it can be found that when the fault arc is generated, the first fault indication feature in the wavelet coefficients of each layer is significantly different from the normal parameters after the four-layer wavelet decomposition is performed on the main circuit current with the db4 wavelet function as the basis function, and further It can be found by observation that the values of the first fault indication feature obtained from the wavelet coefficients of the first layer to the wavelet coefficients of the fourth layer are all above 10, and the normal parameters are all around 0.
需要说明的是，由于第一层小波系数的第一故障指示特征的波动性较强，不够稳定，在实际中，可求取第二层小波系数至第四层小波系数的第一故障指示特征进行故障电弧的验证。可以理解的是，可以求取第二层小波系数至第四层小波系数的任一层的第一故障指示特征，或者求取第二层小波系数至第四层小波系数的任一层的第一故障指示特征中任两层的第一故障指示特征，求取小波系数所在层数的第一故障指示特征愈多，对实验结果的验证越充分且越具说服力。It should be noted that since the first fault indication feature of the first layer of wavelet coefficients has strong volatility and is not stable enough, in practice, the first fault indication features of the second layer to the fourth layer of wavelet coefficients can be obtained. Verify the arc fault. It can be understood that the first fault indication feature of any layer from the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained, or the first fault indication feature of any layer of the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained. For the first fault-indicating features of any two layers in a fault-indicating feature, the more first-fault-indicating features in the layers where the wavelet coefficients are obtained, the more sufficient and convincing the experimental results are to verify.
另外，计算
具体地，请参照图7，图7表示有故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第二故障指示特征与正常状态下的正常参数的对比图。其中，横坐标表示为实验组别，纵坐标表示为第二故障指示特征的数值。a1表示第一层小波系数的第二故障指示特征与正常状态下的正常参数的对比图，a2至a4的含义可以此类推。Specifically, please refer to FIG. 7. FIG. 7 shows the second fault indication feature in each layer of wavelet coefficients and the normal state of A comparison chart of the parameters. Among them, the abscissa represents the experimental group, and the ordinate represents the value of the second fault indication feature. a1 represents a comparison diagram of the second fault indication feature of the wavelet coefficients of the first layer and the normal parameters in a normal state, and the meanings of a2 to a4 can be deduced by analogy.
通过观察图7可发现，在故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第二故障指示特征与正常参数存在明显的差异，且进一步观察可发现，第一层小波系数至第四层小波系数求得的第二故障指示特征的数值均在10以上，且正常参数均在[0，10]的区间内。By observing Fig. 7, it can be found that when the fault arc is generated, the second fault indication features in the wavelet coefficients of each layer are significantly different from the normal parameters after the four-layer wavelet decomposition of the main circuit current using the db4 wavelet function as the basis function, and further It can be found by observation that the values of the second fault indication feature obtained from the wavelet coefficients of the first layer to the wavelet coefficients of the fourth layer are all above 10, and the normal parameters are all in the interval of [0, 10].
同理，由于第一层小波系数的第二故障指示特征的波动性较强，不够稳定，在实际中，可求取第二层小波系数至第四层小波系数的第二故障指示特征进行故障电弧的验证。可以理解的是，可以求取第二层小波系数至第四层小波系数的任一层的第二故障指示特征，或者求取第二层小波系数至第四层小波系数的任一层的第二故障指示特征中任两层的第二故障指示特征，求取干路电流各层小波系数的第二故障指示特征愈多，对实验结果的验证越充分且越具说服力。Similarly, since the second fault indication feature of the first-layer wavelet coefficients has strong volatility and is not stable enough, in practice, the second fault-indicating features from the second-layer wavelet coefficients to the fourth-layer wavelet coefficients can be obtained for fault detection. Validation of the arc. It can be understood that the second fault indication feature of any layer from the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained, or the first layer of the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained. For the second fault indication features of any two layers in the two fault indication features, the more second fault indication features of the wavelet coefficients of each layer of the main circuit current are obtained, the more sufficient and convincing the experimental results are to be verified.
S140、若所述至少两个故障指示特征满足预设判断条件，则判定多负载回路出现故障电弧。S140. If the at least two fault indication characteristics satisfy the preset judgment condition, it is judged that a fault arc occurs in the multi-load circuit.
本实施例中采用神经网络模型判断所述至少两个故障指示特征是否满足预设判断条件；其中，所述神经网络模型以第一故障指示特征和第二故障指示特征为输入，以是否产生故障电弧为输出。In this embodiment, a neural network model is used to judge whether the at least two fault indication features meet the preset judgment conditions; wherein, the neural network model takes the first fault indication characteristic and the second fault indication characteristic as input to determine whether a fault occurs Arc is the output.
进一步地，本实施例还包括训练得到所述神经网络模型的步骤，其包括：搭建多负载回路串联故障电弧仿真模型；基于所述多负载回路串联故障电弧仿真模型，根据应用场景生成训练数据；其中，所述训练数据所包含的特征与所述至少两个故障指示特征对应，且具有对应的故障标签；采用所述训练数据对所述神经网络模型进行训练。可以理解的，在构建电路模型的步骤中构建多负载的电路模型。将故障电弧数据以及正常数据输入，并标定好故障电弧数据以及正常数据，经过大量的迭代运算，得到较可靠的训练数据。并且，所述训练数据所包含的特征与所述至少两个故障指示特征对应，且具有对应的故障标签。Further, this embodiment also includes the step of obtaining the neural network model through training, which includes: building a multi-load circuit series arc fault simulation model; based on the multi-load circuit series series arc fault simulation model, generating training data according to an application scenario; The features included in the training data correspond to the at least two fault indication features and have corresponding fault labels; the training data is used to train the neural network model. It can be understood that a multi-load circuit model is constructed in the step of constructing the circuit model. The fault arc data and normal data are input, and the fault arc data and normal data are calibrated. After a large number of iterative operations, more reliable training data is obtained. Moreover, the features included in the training data correspond to the at least two fault indication features, and have corresponding fault labels.
例如，在一些实施例中，经过所述神经网络模型的训练，得到第一故障特征的训练数据为10，第二故障特征的训练数据为10，当输入的第一故障特征大于等于10且第二故障特征大于等于10时，则判定产生故障电弧，所述神经网络模型输出产生故障电弧的信号。For example, in some embodiments, after the training of the neural network model, the obtained training data of the first fault feature is 10, and the training data of the second fault feature is 10. When the inputted first fault feature is greater than or equal to 10 and the When the second fault characteristic is greater than or equal to 10, it is determined that a fault arc is generated, and the neural network model outputs a signal for generating a fault arc.
从而，输入第一故障指示特征和第二故障指示特征进入所述神经网络模型，所述神经网络模型可得出产生故障电弧的输出信号，告知所检测的多回路负载中出现故障电弧。Thus, the first fault indication feature and the second fault indication feature are input into the neural network model, and the neural network model can derive an output signal for generating a fault arc, informing the detected multi-circuit load that an arc fault occurs.
并且本实施例中通过求得第一故障指示特征和第二故障指示特征作为双特征组合并输入神经网路进行检测，可提高检测结果的可靠性。In addition, in this embodiment, the reliability of the detection result can be improved by obtaining the first fault indication feature and the second fault indication feature as a combination of dual features and inputting them into the neural network for detection.
需要说明的是，使用单一的第一故障指示特征或第二故障指示特征均能够达到检测多负载回路串联故障电弧的效果。本实施例采用第一故障指示特征和第二故障指示特征相结合进行多负载回路串联故障电弧检测，有利于提高多负载回路故障电弧检测的准确性和可靠性。It should be noted that using a single first fault indication feature or a single second fault indication feature can achieve the effect of detecting arc faults in multiple load circuits in series. This embodiment adopts the combination of the first fault indication feature and the second fault indication feature to detect arc faults in series of multiple load circuits, which is beneficial to improve the accuracy and reliability of arc fault detection of multiple load circuits.
本实施例通过采集多负载回路的干路电流，并对干路电流进行小波变换，得到小波系数，再对所述小波系数进行处理获取至少两个故障指示特征，所述故障指示特征不受非故障支路的干扰，因此可避免受到多负载回路中其他大功率支路电流的干扰，再测试至少两个故障指示特征是否满足预设判断条件，从而得出检测结果。从而本申请更可靠地从多负载回路的干路电流中提取并识别出任意支路所发生的串联故障电弧。本实施例可解决现有方法只能对某单一负载回路检测故障电弧的缺陷，适用于放置在线路复杂、且负载呈多元化、甚至有些线路非常隐蔽的家庭住宅、办公楼、大型商场用电网络的配电进线处，而不必再需要为线路中的每个负载配置一台故障电弧探测器，起到节省故障电弧探测器成本的作用，同时还能有效地预防因故障电弧导致的火灾的发生。In this embodiment, the main circuit currents of multiple load circuits are collected, and the main circuit current is subjected to wavelet transformation to obtain wavelet coefficients, and then the wavelet coefficients are processed to obtain at least two fault indication features. Therefore, it can avoid the interference of other high-power branch currents in the multi-load circuit, and then test whether at least two fault indication characteristics meet the preset judgment conditions, so as to obtain the detection result. Therefore, the present application can more reliably extract and identify the series fault arc occurred in any branch circuit from the main circuit current of multiple load circuits. This embodiment can solve the defect that the existing method can only detect a fault arc for a single load circuit, and is suitable for power consumption in family houses, office buildings, and large shopping malls where the lines are complex, the loads are diversified, and even some lines are very concealed. At the power distribution inlet of the network, it is no longer necessary to configure a fault arc detector for each load in the line, which can save the cost of the fault arc detector and effectively prevent the fire caused by the fault arc. happened.
参照图8，图8为本申请的多负载回路串联故障电弧检测方法的第二实施例，所述本申请的多负载回路串联故障电弧检测方法包括以下步骤：Referring to FIG. 8, FIG. 8 is a second embodiment of the method for detecting arc faults in series with multiple load circuits of the present application. The method for detecting arc faults in series with multiple load circuits of the present application includes the following steps:
S210、采集多负载回路中的干路电流信号；S210. Collect the main circuit current signal in the multi-load circuit;
S220、对所述干路电流信号进行小波变换，获取小波系数；S220, performing wavelet transformation on the mains current signal to obtain wavelet coefficients;
S230、计算
具体地，请参照图9，图9表示有故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第三故障指示特征与正常状态下的正常参数的对比图。其中，横坐标表示为实验组别，纵坐标表示为第三故障指示特征的数值。a1表示第一层小波系数的第三故障指示特征与正常状态下的正常参数的对比图，a2至a4的含义可以此类推。Specifically, please refer to FIG. 9. FIG. 9 shows the third fault indication feature in each layer of wavelet coefficients and the normal state of A comparison chart of the parameters. Among them, the abscissa represents the experimental group, and the ordinate represents the value of the third fault indication feature. a1 represents the comparison diagram of the third fault indication feature of the wavelet coefficients of the first layer and the normal parameters in the normal state, and the meanings of a2 to a4 can be deduced by analogy.
通过观察图9可发现，在故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第三故障指示特征与正常参数存在明显的差异，且进一步观察可发现，第一层小波系数至第四层小波系数求得的第三故障指示特征的数值均在9以下，且正常参数均在10附近。By observing Fig. 9, it can be found that when the fault arc is generated, the third fault indication feature in the wavelet coefficients of each layer is significantly different from the normal parameters after the four-layer wavelet decomposition is performed on the main circuit current with the db4 wavelet function as the basis function, and further It can be found by observation that the values of the third fault indication feature obtained from the wavelet coefficients of the first layer to the wavelet coefficients of the fourth layer are all below 9, and the normal parameters are all around 10.
需要说明的是，由于第一层小波系数的第三故障指示特征的波动性较强，不够稳定，在实际中，可求取第二层小波系数至第四层小波系数的第三故障指示特征进行故障电弧的验证。可以理解的是，可以求取第二层小波系数至第四层小波系数的任一层的第三故障指示特征，或者求取第二层小波系数至第四层小波系数的任一层的第三故障指示特征中任两层的第三故障指示特征，求取小波系数所在层数的第三故障指示特征愈多，对实验结果的验证越充分且越具说服力。It should be noted that, since the third fault indication feature of the wavelet coefficients of the first layer has strong volatility and is not stable enough, in practice, the third fault indication features of the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained. Verify the arc fault. It can be understood that the third fault indication feature of any layer from the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained, or the third fault indication feature of any layer of the wavelet coefficients of the second layer to the wavelet coefficients of the fourth layer can be obtained. For the third fault indicating features of any two layers among the three fault indicating features, the more third fault indicating features of the layers where the wavelet coefficients are located, the more sufficient and convincing the experimental results are to be verified.
S240、若所述第一故障指示特征和所述第三故障指示特征满足预设判断条件，则判定多负载回路出现故障电弧。S240. If the first fault indication feature and the third fault indication feature satisfy a preset judgment condition, determine that a fault arc occurs in the multi-load circuit.
本实施例中采用神经网络模型判断所述至少两个故障指示特征是否满足预设判断条件；其中，所述神经网络模型以第一故障指示特征和第三故障指示特征为输入，以是否产生故障电弧为输出。In this embodiment, a neural network model is used to judge whether the at least two fault indication features meet the preset judgment conditions; wherein, the neural network model takes the first fault indication characteristic and the third fault indication characteristic as input to determine whether a fault occurs Arc is the output.
例如，在一些实施例中，经过所述神经网络模型的训练，得到第一故障特征的训练数据为10，第三故障指示特征的训练数据为9，当输入的第一故障特征大于等于10且第三故障特征小于等于9时，则判定产生故障电弧，所述神经网络模型输出产生故障电弧的信号。For example, in some embodiments, after the training of the neural network model, the obtained training data of the first fault feature is 10, and the training data of the third fault indication feature is 9. When the inputted first fault feature is greater than or equal to 10 and When the third fault feature is less than or equal to 9, it is determined that an arc fault is generated, and the neural network model outputs a signal for generating an arc fault.
本实施例中通过求得第一故障指示特征和第三故障指示特征作为双特征组合输入神经网路进行检测，可提高检测结果的可靠性。In this embodiment, the reliability of the detection result can be improved by obtaining the first fault indication feature and the third fault indication feature as a dual-feature combination and inputting the neural network for detection.
本实施例通过采集多负载回路的干路电流，并对干路电流进行小波变换，得到小波系数，再对所述小波系数进行处理获取至少两个故障指示特征，所述故障指示特征不受非故障支路的干扰，因此可避免受到多负载回路中其他大功率支路电流的干扰，再测试至少两个故障指示特征是否满足预设判断条件，从而得出检测结果。从而本申请更可靠地从多负载回路的干路电流中提取并识别出任意支路所发生的串联故障电弧。本实施例可解决现有方法只能对某单一负载回路检测故障电弧的缺陷，适用于放置在线路复杂、且负载呈多元化、甚至有些线路非常隐蔽的家庭住宅、办公楼、大型商场用电网络的配电进线处，而不必再需要为线路中的每个负载配置一台故障电弧探测器，起到节省故障电弧探测器成本的作用，同时还能有效地预防因故障电弧导致的火灾的发生。In this embodiment, the main circuit currents of multiple load circuits are collected, and the main circuit current is subjected to wavelet transformation to obtain wavelet coefficients, and then the wavelet coefficients are processed to obtain at least two fault indication features. Therefore, it can avoid the interference of other high-power branch currents in the multi-load circuit, and then test whether at least two fault indication characteristics meet the preset judgment conditions, so as to obtain the detection result. Therefore, the present application can more reliably extract and identify the series fault arc occurred in any branch circuit from the main circuit current of multiple load circuits. This embodiment can solve the defect that the existing method can only detect a fault arc for a single load circuit, and is suitable for power consumption in family houses, office buildings, and large shopping malls where the lines are complex, the loads are diversified, and even some lines are very concealed. At the power distribution inlet of the network, it is no longer necessary to configure a fault arc detector for each load in the line, which can save the cost of the fault arc detector and effectively prevent the fire caused by the fault arc. happened.
参照图10，图10为本申请的多负载回路串联故障电弧检测方法的第三实施例，所述本申请的多负载回路串联故障电弧检测方法包括以下步骤：Referring to FIG. 10 , FIG. 10 is a third embodiment of the method for detecting arc faults in series with multiple load circuits of the present application. The method for detecting arc faults in series with multiple load circuits in the present application includes the following steps:
S310、采集多负载回路中的干路电流信号；S310. Collect the main circuit current signal in the multi-load circuit;
S320、对所述干路电流信号进行小波变换，获取小波系数；S320, performing wavelet transformation on the mains current signal to obtain wavelet coefficients;
S330、计算
本实施例中使用第二故障指示特征和第三故障指示特征作为双特征组合，参照图7和图9，在故障电弧产生时对干路电流以db4小波函数为基函数进行四层小波分解后各层小波系数中的第二故障指示特征和第三故障指示特征与正常参数均存在明显的差异。通过使用第二故障指示特征和第三故障指示特征作为双特征组合输入神经网路进行检测，可提高检测结果可靠性。In this embodiment, the second fault indication feature and the third fault indication feature are used as a dual feature combination. Referring to FIG. 7 and FIG. 9 , when the fault arc is generated, the main circuit current is subjected to four-layer wavelet decomposition using the db4 wavelet function as the basis function. There are obvious differences between the second fault indication feature and the third fault indication feature in the wavelet coefficients of each layer and the normal parameters. By using the second fault-indicating feature and the third fault-indicating feature as a dual-feature combination to input the neural network for detection, the reliability of the detection result can be improved.
S340、若第二故障指示特征和第三故障指示特征满足预设判断条件，则判定多负载回路出现故障电弧。S340. If the second fault indication feature and the third fault indication feature satisfy the preset judgment condition, it is judged that a fault arc occurs in the multi-load circuit.
本实施例通过采集多负载回路的干路电流，并对干路电流进行小波变换，得到小波系数，再对所述小波系数进行处理获取至少两个故障指示特征，所述故障指示特征不受非故障支路的干扰，因此可避免受到多负载回路中其他大功率支路电流的干扰，再测试至少两个故障指示特征是否满足预设判断条件，从而得出检测结果。从而本申请更可靠地从多负载回路的干路电流中提取并识别出任意支路所发生的串联故障电弧。本实施例可解决现有方法只能对某单一负载回路检测故障电弧的缺陷，适用于放置在线路复杂、且负载呈多元化、甚至有些线路非常隐蔽的家庭住宅、办公楼、大型商场用电网络的配电进线处，而不必再需要为线路中的每个负载配置一台故障电弧探测器，起到节省故障电弧探测器成本的作用，同时还能有效地预防因故障电弧导致的火灾的发生。In this embodiment, the main circuit currents of multiple load circuits are collected, and the main circuit current is subjected to wavelet transformation to obtain wavelet coefficients, and then the wavelet coefficients are processed to obtain at least two fault indication features. Therefore, it can avoid the interference of other high-power branch currents in the multi-load circuit, and then test whether at least two fault indication characteristics meet the preset judgment conditions, so as to obtain the detection result. Therefore, the present application can more reliably extract and identify the series fault arc occurred in any branch circuit from the main circuit current of multiple load circuits. This embodiment can solve the defect that the existing method can only detect a fault arc for a single load circuit, and is suitable for power consumption in family houses, office buildings, and large shopping malls where the lines are complex, the loads are diversified, and even some lines are very concealed. At the power distribution inlet of the network, it is no longer necessary to configure a fault arc detector for each load in the line, which can save the cost of the fault arc detector and effectively prevent the fire caused by the fault arc. happened.
参照图11，图11为本申请的多负载回路串联故障电弧检测方法的第四实施例，所述本申请的多负载回路串联故障电弧检测方法包括以下步骤：Referring to FIG. 11, FIG. 11 is a fourth embodiment of the method for detecting arc faults in series with multiple load circuits of the present application. The method for detecting arc faults in series with multiple load circuits of the present application includes the following steps:
S410、采集多负载回路中的干路电流信号；S410. Collect the main circuit current signal in the multi-load circuit;
S420、对所述干路电流信号进行小波变换，获取小波系数；S420, performing wavelet transformation on the main circuit current signal to obtain wavelet coefficients;
S430、计算
本实施例中使用第一故障指示特征、第二故障指示特征和第三故障指示特征作为三特征组合，参照图6、图7和图9，在故障电弧产生时对干路电流以多贝西小波函数为基函数进行四层小波分解后各层小波系数中的第一故障指示特征、第二故障指示特征和第三故障指示特征与正常参数均存在明显的差异。通过使用第一故障指示特征、第二故障指示特征和第三故障指示特征作为三特征组合并输入神经网路进行检测，相比使用双特征组合进一步提高检测结果的可靠性。In this embodiment, the first fault indication feature, the second fault indication feature and the third fault indication feature are used as a combination of three features. Referring to FIG. 6, FIG. 7 and FIG. There are obvious differences between the first fault indication feature, the second fault indication feature and the third fault indication feature in the wavelet coefficients of each layer after the wavelet function is the basis function for the four-layer wavelet decomposition and the normal parameters. By using the first fault-indicating feature, the second fault-indicating feature and the third fault-indicating feature as a three-feature combination and inputting it into a neural network for detection, the reliability of the detection result is further improved compared to using a dual-feature combination.
S440、若所述第一故障指示特征、第二故障指示特征和第三故障指示特征满足预设判断条件，则判定多负载回路出现故障电弧。S440. If the first fault indication feature, the second fault indication feature and the third fault indication feature satisfy the preset judgment condition, it is judged that a fault arc occurs in the multi-load circuit.
本实施例通过采集多负载回路的干路电流，并对干路电流进行小波变换，得到小波系数，再对所述小波系数进行处理获取至少两个故障指示特征，所述故障指示特征不受非故障支路的干扰，因此可避免受到多负载回路中其他大功率支路电流的干扰，再测试至少两个故障指示特征是否满足预设判断条件，从而得出检测结果。从而本申请更可靠地从多负载回路的干路电流中提取并识别出任意支路所发生的串联故障电弧。本实施例可解决现有方法只能对某单一负载回路检测故障电弧的缺陷，适用于放置在线路复杂、且负载呈多元化、甚至有些线路非常隐蔽的家庭住宅、办公楼、大型商场用电网络的配电进线处，而不必再需要为线路中的每个负载配置一台故障电弧探测器，起到节省故障电弧探测器成本的作用，同时还能有效地预防因故障电弧导致的火灾的发生。In this embodiment, the main circuit currents of multiple load circuits are collected, and the main circuit current is subjected to wavelet transformation to obtain wavelet coefficients, and then the wavelet coefficients are processed to obtain at least two fault indication features. Therefore, it can avoid the interference of other high-power branch currents in the multi-load circuit, and then test whether at least two fault indication characteristics meet the preset judgment conditions, so as to obtain the detection result. Therefore, the present application can more reliably extract and identify the series fault arc occurred in any branch circuit from the main circuit current of multiple load circuits. This embodiment can solve the defect that the existing method can only detect a fault arc for a single load circuit, and is suitable for power consumption in family houses, office buildings, and large shopping malls where the lines are complex, the loads are diversified, and even some lines are very concealed. At the power distribution inlet of the network, it is no longer necessary to configure a fault arc detector for each load in the line, which can save the cost of the fault arc detector and effectively prevent the fire caused by the fault arc. happened.
本申请还提出一种计算机可读存储介质，所述计算机可读存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现所述的多负载回路串联故障电弧检测方法中的步骤。The present application also proposes a computer-readable storage medium, where one or more programs are stored in the computer-readable storage medium, and the one or more programs can be executed by one or more processors to realize the multiple Steps in a load circuit series arc fault detection method.
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.
应当注意的是，在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的部件或步骤。位于部件之前的单词“一”或“一个”不排除存在多个这样的部件。本发明可以借助于包括有若干不同部件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。It should be noted that, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not preclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. do not denote any order. These words can be interpreted as names.
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。Although the preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of the present invention.
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims (10)
Translated fromChinese
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010748868.5ACN111707908B (en) | 2020-07-29 | 2020-07-29 | Method, device and storage medium for detecting arc fault in series with multiple load circuits |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010748868.5ACN111707908B (en) | 2020-07-29 | 2020-07-29 | Method, device and storage medium for detecting arc fault in series with multiple load circuits |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111707908Atrue CN111707908A (en) | 2020-09-25 |
| CN111707908B CN111707908B (en) | 2022-05-17 |
Family
ID=72548078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010748868.5AActiveCN111707908B (en) | 2020-07-29 | 2020-07-29 | Method, device and storage medium for detecting arc fault in series with multiple load circuits |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111707908B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112583000A (en)* | 2020-11-25 | 2021-03-30 | 中国科学技术大学先进技术研究院 | Fault arc identification tripping device |
| CN113311227A (en)* | 2021-06-10 | 2021-08-27 | 中国科学技术大学先进技术研究院 | Current signal noise reduction method for fault arc diagnosis technology |
| CN113468704A (en)* | 2021-07-23 | 2021-10-01 | 南方电网科学研究院有限责任公司 | Intermittent arc fault detection method and related device |
| CN113514724A (en)* | 2021-07-15 | 2021-10-19 | 阳光电源股份有限公司 | Photovoltaic system and arc detection method and device thereof |
| CN114236203A (en)* | 2021-11-29 | 2022-03-25 | 国网北京市电力公司 | Load control system, load control method, storage medium, and electronic device |
| CN115616364A (en)* | 2022-12-16 | 2023-01-17 | 中国科学技术大学先进技术研究院 | Arc fault detection method, device, equipment and storage medium |
| CN115792316A (en)* | 2022-11-14 | 2023-03-14 | 国网重庆市电力公司电力科学研究院 | Fault arc simulation signal generating device based on multi-load virtual load |
| CN118534240A (en)* | 2024-07-22 | 2024-08-23 | 安徽中科易能科技有限公司 | A non-intrusive electric bicycle battery identification technology |
| US12230953B2 (en) | 2021-06-15 | 2025-02-18 | Leviton Manufacturing Co., Inc. | Arc fault detection using machine learning |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323518A (en)* | 2011-05-19 | 2012-01-18 | 西南交通大学 | A Partial Discharge Signal Recognition Method Based on Spectral Kurtosis |
| CN103543375A (en)* | 2013-08-26 | 2014-01-29 | 上海交通大学 | Method for detecting alternating-current fault arcs on basis of wavelet transformation and time-domain hybrid features |
| CN103926509A (en)* | 2014-04-01 | 2014-07-16 | 河南理工大学 | Power distribution network fault step type line section method based on spectral kurtosis relative energy entropies |
| CN105223482A (en)* | 2015-10-22 | 2016-01-06 | 西安交通大学 | The wavelet decomposition two-value denoising method of partial-discharge ultrahigh-frequency signal waveform |
| CN106771898A (en)* | 2016-11-27 | 2017-05-31 | 福州大学 | Series fault arc detection device and its method based on Higher Order Cumulants identification |
| CN107064752A (en)* | 2017-03-22 | 2017-08-18 | 北京航空航天大学 | A kind of distinguished number of aviation fault electric arc detection |
| CN108535636A (en)* | 2018-05-16 | 2018-09-14 | 武汉大学 | A kind of analog circuit is distributed the neighbouring embedded fault signature extracting method that the victor is a king based on stochastic parameter |
| CN108885237A (en)* | 2016-03-03 | 2018-11-23 | Abb瑞士股份有限公司 | Method and apparatus for detecting arc faults in electrical systems |
| CN110118900A (en)* | 2019-03-27 | 2019-08-13 | 南京航空航天大学 | A kind of remained capacity and power frequency series arc faults detection method |
| CN110488161A (en)* | 2019-07-23 | 2019-11-22 | 南京航空航天大学 | A kind of detection of multi-load series arc faults and localization method |
| JP2019211447A (en)* | 2018-06-08 | 2019-12-12 | 株式会社東芝 | Partial discharge detector, method for detecting partial discharge, partial discharge detection system, and computer program |
| CN110717472A (en)* | 2019-10-17 | 2020-01-21 | 齐鲁工业大学 | Fault diagnosis method and system based on improved wavelet threshold denoising |
| CN110969194A (en)* | 2019-11-21 | 2020-04-07 | 国网辽宁省电力有限公司电力科学研究院 | Cable early fault positioning method based on improved convolutional neural network |
- 2020
- 2020-07-29CNCN202010748868.5Apatent/CN111707908B/enactiveActive
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323518A (en)* | 2011-05-19 | 2012-01-18 | 西南交通大学 | A Partial Discharge Signal Recognition Method Based on Spectral Kurtosis |
| CN103543375A (en)* | 2013-08-26 | 2014-01-29 | 上海交通大学 | Method for detecting alternating-current fault arcs on basis of wavelet transformation and time-domain hybrid features |
| CN103926509A (en)* | 2014-04-01 | 2014-07-16 | 河南理工大学 | Power distribution network fault step type line section method based on spectral kurtosis relative energy entropies |
| CN105223482A (en)* | 2015-10-22 | 2016-01-06 | 西安交通大学 | The wavelet decomposition two-value denoising method of partial-discharge ultrahigh-frequency signal waveform |
| CN108885237A (en)* | 2016-03-03 | 2018-11-23 | Abb瑞士股份有限公司 | Method and apparatus for detecting arc faults in electrical systems |
| CN106771898A (en)* | 2016-11-27 | 2017-05-31 | 福州大学 | Series fault arc detection device and its method based on Higher Order Cumulants identification |
| CN107064752A (en)* | 2017-03-22 | 2017-08-18 | 北京航空航天大学 | A kind of distinguished number of aviation fault electric arc detection |
| CN108535636A (en)* | 2018-05-16 | 2018-09-14 | 武汉大学 | A kind of analog circuit is distributed the neighbouring embedded fault signature extracting method that the victor is a king based on stochastic parameter |
| JP2019211447A (en)* | 2018-06-08 | 2019-12-12 | 株式会社東芝 | Partial discharge detector, method for detecting partial discharge, partial discharge detection system, and computer program |
| CN110118900A (en)* | 2019-03-27 | 2019-08-13 | 南京航空航天大学 | A kind of remained capacity and power frequency series arc faults detection method |
| CN110488161A (en)* | 2019-07-23 | 2019-11-22 | 南京航空航天大学 | A kind of detection of multi-load series arc faults and localization method |
| CN110717472A (en)* | 2019-10-17 | 2020-01-21 | 齐鲁工业大学 | Fault diagnosis method and system based on improved wavelet threshold denoising |
| CN110969194A (en)* | 2019-11-21 | 2020-04-07 | 国网辽宁省电力有限公司电力科学研究院 | Cable early fault positioning method based on improved convolutional neural network |
Non-Patent Citations (3)
| Title |
|---|
| JUN JIANG ET AL: "《Series Arc Detection and Complex Load Recognition Based on Principal Component Analysis and Support Vector Machine》", 《IEEE ACCESS》* |
| 游江龙: "《多负载回路串联型故障电弧特性研究》", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》* |
| 王中华: "《基于小波分析和神经网络的模拟故障诊断方法研究》", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》* |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112583000A (en)* | 2020-11-25 | 2021-03-30 | 中国科学技术大学先进技术研究院 | Fault arc identification tripping device |
| CN113311227A (en)* | 2021-06-10 | 2021-08-27 | 中国科学技术大学先进技术研究院 | Current signal noise reduction method for fault arc diagnosis technology |
| CN113311227B (en)* | 2021-06-10 | 2022-06-24 | 中国科学技术大学先进技术研究院 | Current signal noise reduction method for fault arc diagnosis technology |
| US12230953B2 (en) | 2021-06-15 | 2025-02-18 | Leviton Manufacturing Co., Inc. | Arc fault detection using machine learning |
| CN113514724A (en)* | 2021-07-15 | 2021-10-19 | 阳光电源股份有限公司 | Photovoltaic system and arc detection method and device thereof |
| CN113468704A (en)* | 2021-07-23 | 2021-10-01 | 南方电网科学研究院有限责任公司 | Intermittent arc fault detection method and related device |
| CN113468704B (en)* | 2021-07-23 | 2024-02-02 | 南方电网科学研究院有限责任公司 | An intermittent arc fault detection method and related devices |
| CN114236203B (en)* | 2021-11-29 | 2023-10-24 | 国网北京市电力公司 | Load control system, method, storage medium and electronic device |
| CN114236203A (en)* | 2021-11-29 | 2022-03-25 | 国网北京市电力公司 | Load control system, load control method, storage medium, and electronic device |
| CN115792316A (en)* | 2022-11-14 | 2023-03-14 | 国网重庆市电力公司电力科学研究院 | Fault arc simulation signal generating device based on multi-load virtual load |
| CN115616364B (en)* | 2022-12-16 | 2023-03-17 | 中国科学技术大学先进技术研究院 | Arc fault detection method, device, equipment and storage medium |
| CN115616364A (en)* | 2022-12-16 | 2023-01-17 | 中国科学技术大学先进技术研究院 | Arc fault detection method, device, equipment and storage medium |
| CN118534240A (en)* | 2024-07-22 | 2024-08-23 | 安徽中科易能科技有限公司 | A non-intrusive electric bicycle battery identification technology |
| CN118534240B (en)* | 2024-07-22 | 2024-11-22 | 安徽中科易能科技有限公司 | A non-intrusive electric bicycle battery identification technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111707908B (en) | 2022-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111707908B (en) | Method, device and storage medium for detecting arc fault in series with multiple load circuits | |
| Zhao et al. | Series arc fault detection based on current fluctuation and zero-current features | |
| CN105425118B (en) | A kind of Multi-information acquisition fault arc detection method and device | |
| CN108646149A (en) | Fault electric arc recognition methods based on current characteristic extraction | |
| CN111610416B (en) | Series arc fault intelligent circuit breaker | |
| CN110543921A (en) | A method for early fault identification of cables based on waveform learning | |
| CN103197230A (en) | Integrated circuit fault detection method based on feature extraction | |
| CN102916427A (en) | Method for calculating integrated three-phase imbalance degree of multi-circuit transmission lines | |
| CN110212503B (en) | High-resistance grounding protection method suitable for small-resistance grounding system | |
| CN115166424B (en) | A method for arc fault detection and location based on system modeling analysis | |
| CN106771798A (en) | A kind of fault arc detection method based on the equal difference of wavelet coefficient | |
| CN109920193A (en) | Intelligent detection method, system, equipment and medium for electrical fire hazard | |
| CN108510147B (en) | Electric energy quality comprehensive evaluation method based on residual error fluctuation model | |
| CN110398669A (en) | Arc fault detection method | |
| Zhang et al. | Lightweight AC arc fault detection method by integration of event-based load classification | |
| CN112305319A (en) | Method and system for online monitoring of converter transformer valve side sleeve parameters | |
| CN110764027A (en) | Electric connector intermittent fault diagnosis method based on frequency spectrum characteristic change | |
| CN109633357B (en) | Monitoring method and monitoring device for grounding insulation of multiple busbars among three busbars | |
| CN101782625A (en) | Power electronic system fault diagnostic method based on Gradation-boosting algorithm | |
| CN116990648A (en) | Fault arc detection method based on one-dimensional cavity convolutional neural network | |
| CN114707553A (en) | Step-by-step fault arc detection method and device, electronic equipment and storage medium | |
| CN116047237A (en) | Online detection method and device for series arc faults of three-phase frequency converter circuit | |
| CN110703149A (en) | A method and system for detecting vibration and sound of transformer operating state using character spacing | |
| CN118673303A (en) | Electric bicycle charging load identification method, system, equipment and storage medium | |
| CN118671524A (en) | Method, system, equipment and storage medium for detecting alternating current fault arc under multi-load condition based on double-tree complex wavelet transformation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right | Effective date of registration:20250320 Address after:230000 No. 800 Wangjiang West Road, Hefei, Anhui Province Patentee after:INSTITUTE OF ADVANCED TECHNOLOGY University OF SCIENCE AND TECHNOLOGY OF CHINA Country or region after:China Patentee after:University of Science and Technology of China Address before:230000 no.5089 Wangjiang West Road, hi tech Zone, Hefei City, Anhui Province Patentee before:INSTITUTE OF ADVANCED TECHNOLOGY University OF SCIENCE AND TECHNOLOGY OF CHINA Country or region before:China |