Movatterモバイル変換


[0]ホーム

URL:


CN117761423A - Power distribution network fault prediction method - Google Patents

Power distribution network fault prediction method
Download PDF

Info

Publication number
CN117761423A
CN117761423ACN202311611662.8ACN202311611662ACN117761423ACN 117761423 ACN117761423 ACN 117761423ACN 202311611662 ACN202311611662 ACN 202311611662ACN 117761423 ACN117761423 ACN 117761423A
Authority
CN
China
Prior art keywords
voltage
fault
distribution network
intersection
time
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.)
Pending
Application number
CN202311611662.8A
Other languages
Chinese (zh)
Inventor
赵建军
刘珅
李洋
郝世诚
杨小龙
靳康萌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Smart Distribution Network Center of State Grid Jibei Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Smart Distribution Network Center of State Grid Jibei Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Smart Distribution Network Center of State Grid Jibei Electric Power Co LtdfiledCriticalState Grid Corp of China SGCC
Priority to CN202311611662.8ApriorityCriticalpatent/CN117761423A/en
Publication of CN117761423ApublicationCriticalpatent/CN117761423A/en
Pendinglegal-statusCriticalCurrent

Links

Landscapes

Abstract

Translated fromChinese

本发明公开了一种配电网故障预测的方法,本发明涉及配电网故障预测技术领域,解决了针对出现的异常数据没有进行合理的分析,其次没有结合故障原因进行合理预测的技术问题,本发明通过对历史故障数据进行分析,并以故障原因中的电压为例进行分析,通过将电压进行正常电压和故障电压分类,进一步的来判断二者之间是否存在交集,针对存在交集的情况通过获取到实时电压的变化情况来分析配电网整体的工作状态,从而达到预测的目的,针对不存在交集的情况,通过获取到实时电压的数值,并将其与对应的区间值进行比较来对配电网整体的工作状态进行分析,通过数据分析,可以及时发现异常情况,并进行预警和处理,减少故障的发生。

The invention discloses a method for predicting distribution network faults. The invention relates to the technical field of distribution network fault prediction, and solves the technical problem of not conducting reasonable analysis on abnormal data that occurs, and secondly, not making reasonable predictions based on the causes of the faults. This invention analyzes historical fault data and takes the voltage in the cause of the fault as an example. By classifying the voltage into normal voltage and fault voltage, it further determines whether there is an intersection between the two. In the case where there is an intersection, the present invention By obtaining the changes in real-time voltage, the overall working status of the distribution network is analyzed to achieve the purpose of prediction. For situations where there is no intersection, the real-time voltage value is obtained and compared with the corresponding interval value. Analyze the overall working status of the distribution network. Through data analysis, abnormal situations can be discovered in time, and early warning and processing can be carried out to reduce the occurrence of faults.

Description

Translated fromChinese
一种配电网故障预测的方法A method for predicting distribution network faults

技术领域Technical field

本发明涉及配电网故障预测技术领域,具体为一种配电网故障预测的方法。The invention relates to the technical field of distribution network fault prediction, specifically a method for distribution network fault prediction.

背景技术Background technique

配电网是电力系统中的重要组成部分,随着智能电网的快速发展,分布式电源的大量的不确定接入,使得配电网故障信息越发复杂,故障的准确快速分析变得越发困难。The distribution network is an important part of the power system. With the rapid development of smart grids, a large number of uncertain access to distributed power sources has made the fault information of the distribution network more and more complex, and the accurate and rapid analysis of faults has become more and more difficult.

根据申请号为CN201810866754.3的专利显示,该专利的方法包括:对所需预测的配电网区段内的故障录波数据提取距前时间、数据密度、降采样波形和局部波形;将距前时间、数据密度、降采样波形和局部波形输入故障预测模型获得预测结果,所述故障预测模型包括深度卷积神经网络、掩蔽单元及长短时期记忆网络单元。According to the patent application number CN201810866754.3, the method of the patent includes: extracting the previous time, data density, downsampling waveform and local waveform from the fault recording data in the distribution network section to be predicted; The previous time, data density, downsampling waveform and local waveform are input into the fault prediction model to obtain the prediction results. The fault prediction model includes a deep convolutional neural network, a masking unit and a long and short-term memory network unit.

上述专利通过对故障录波数据进行分析,从而来达到预测的目的,但是针对配电网中出现的异常数据上述专利没有对其进行很好的处理,在工作过程中电压、电流和功率这些因素会直接影响到配电网的正常工作,因此需要对其进行合理的数据分析,从而根据数据来得到故障原因,并根据故障原因来进行及时的预测和预警处理。The above-mentioned patent achieves the purpose of prediction by analyzing fault recording data. However, the above-mentioned patent does not deal with the abnormal data that appears in the distribution network well. During the work process, factors such as voltage, current and power It will directly affect the normal operation of the distribution network, so it is necessary to conduct reasonable data analysis to obtain the cause of the fault based on the data, and to conduct timely prediction and early warning processing based on the cause of the fault.

发明内容Contents of the invention

针对现有技术的不足,本发明提供了一种配电网故障预测的方法,解决了针对出现的异常数据没有进行合理的分析,其次没有结合故障原因进行合理预测的问题。In view of the shortcomings of the existing technology, the present invention provides a method for predicting distribution network faults, which solves the problem of no reasonable analysis of abnormal data that occurs, and secondly, no reasonable prediction based on the cause of the fault.

为实现以上目的,本发明通过以下技术方案予以实现:一种配电网故障预测的方法,该方法具体包括以下步骤:In order to achieve the above objectives, the present invention is implemented through the following technical solutions: a method for predicting distribution network faults, which specifically includes the following steps:

步骤一:首先获取配电网的历史故障数据,且历史故障数据的时间周期为T,其中历史故障数据包括:故障次数、故障原因和故障设备,然后根据故障原因判断是否存在多次故障的设备得到判断结果,判断结果包括存在结果和不存在结果;具体的,多次故障设备表示为该设备出现故障的次数存在两次及以上的情况。Step 1: First obtain the historical fault data of the distribution network, and the time period of the historical fault data is T. The historical fault data includes: the number of faults, the cause of the fault and the faulty equipment. Then based on the fault cause, determine whether there are multiple faulty equipment. The judgment result is obtained, and the judgment result includes an existence result and a non-existence result; specifically, a multiple-failure device indicates that the device has failed twice or more.

步骤二:接着获取到不存在结果并对故障原因进行获取,且故障原因具体可以包括:电压、电流和功率,同时获取到电压、电流和功率对应故障原因的故障次数,并选取故障次数最多对应的故障原因进行分析,在本申请中以电压出现的故障次数最多为例进行分析;Step 2: Then obtain the non-existent result and obtain the cause of the fault, and the cause of the failure can specifically include: voltage, current and power. At the same time, obtain the number of faults corresponding to the voltage, current and power of the fault cause, and select the one with the highest number of faults. The cause of the failure is analyzed. In this application, the voltage with the highest number of failures is used as an example for analysis;

步骤三:获取到历史数据中所有的电压数据,并根据电压数据判断得到正常电压和故障电压,同时根据正常电压和故障电压之间是否存在交集得到交集判断结果,接着根据交集判断结果得到电压故障比较结果,且对电压变化情况的分析方式如下:Step 3: Obtain all voltage data in the historical data, and determine the normal voltage and fault voltage based on the voltage data. At the same time, obtain the intersection judgment result based on whether there is an intersection between the normal voltage and the fault voltage, and then obtain the voltage fault based on the intersection judgment result. Compare the results and analyze the voltage changes as follows:

S1:对所有的电压数据进行标号处理且记作U i,且i=1、2、…、j,j表示为故障次数标号,其中j的具体数值根据实际情况取值,接着根据故障原因将电压数据进行正常电压和故障电压分类,同时将正常电压记作Uzk,k=1、2、…、o,将故障电压记作Ugh,h=1、2、…、f,;具体表示为:如果出现的故障原因显示是电压异常导致整体故障,则将对应的电压标记为故障电压,反之如果不是电压导致则将对应的电压标记为正常电压。S1: Label all the voltage data and record it as U i, and i = 1, 2, ..., j, j represents the number of faults, where the specific value of j is determined according to the actual situation, and then the value is determined according to the cause of the fault. The voltage data is classified into normal voltage and fault voltage. At the same time, the normal voltage is recorded as Uzk, k=1, 2,...,o, and the fault voltage is recorded as Ugh, h=1, 2,..., f,; the specific expression is: If the cause of the fault shows that abnormal voltage causes the overall fault, the corresponding voltage will be marked as the fault voltage. On the contrary, if it is not caused by voltage, the corresponding voltage will be marked as the normal voltage.

S2:获取到所有正常电压Uzk和故障电压Ugh并判断二者是否存在交集得到交集判断结果,交集判断结果包括:存在交集结果和不存在交集结果,此处的交集表示相同数值的电压可能为正常电压,也可能会故障电压,如果正常电压和故障电压均存在相同数值的电压,则表示二者存在交集,反之如果正常电压和故障电压不存在相同数值电压,则表示二者不存在交集S2: Obtain all normal voltages Uzk and fault voltage Ugh and determine whether there is an intersection between the two to obtain the intersection judgment result. The intersection judgment result includes: there is an intersection result and there is no intersection result. The intersection here means that voltages with the same value may be normal. voltage, and may also be fault voltage. If the normal voltage and fault voltage have the same value, it means that there is an intersection between the two. On the contrary, if the normal voltage and the fault voltage do not have the same value, it means that there is no intersection between the two.

S3:当交集判断结果为不存在交集结果时,获取到正常电压的最大值和最小值,并以最小值和最大值生成正常电压区间范围,同理获取到故障电压区间范围;此处得到的正常电压区间范围和故障电压区间范围用来对产生的实时电压进行比较,从而来判断配电网整体的运行状态,从而达到预测的目的,同时不存在交集还表示为正常电压最大值和最小值得到的区间值不包括故障电压中的任一电压值,也就表示得到的两个区间为互不干扰的两个区间,举例表示正常电压区间为[37,45],故障电压区间为[50,60]。S3: When the intersection judgment result is that there is no intersection result, obtain the maximum and minimum values of the normal voltage, and use the minimum and maximum values to generate the normal voltage range, and obtain the fault voltage range in the same way; obtained here The normal voltage interval range and the fault voltage interval range are used to compare the generated real-time voltages to judge the overall operating status of the distribution network to achieve the purpose of prediction. At the same time, if there is no intersection, it is also expressed as the maximum and minimum normal voltage values. The obtained interval value does not include any voltage value in the fault voltage, which means that the two obtained intervals are two intervals that do not interfere with each other. For example, the normal voltage interval is [37, 45] and the fault voltage interval is [50 , 60].

S4:当交集判断结果为存在交集结果时,获取到存在相同数值的电压并将其作为交集电压,接着以产生交集电压的时间为终点,获取终点之前t时间内正常电压的变化情况和故障电压的变化情况。且此处默认产生的交集电压个数只有一个。S4: When the intersection judgment result is that there is an intersection result, obtain the voltage with the same value and use it as the intersection voltage. Then, taking the time when the intersection voltage is generated as the end point, obtain the changes in the normal voltage and the fault voltage within t time before the end point. changes. And there is only one intersection voltage generated by default here.

步骤四:根据高精度传感器获取到配电网的实时数据,且高精度传感器具体指电压表,并测量得到配电网的实时电压,接着将实时电压与电压比对结果进行匹配得到配电网预测结果,且具体的匹配方式如下:Step 4: Obtain the real-time data of the distribution network based on the high-precision sensor, and the high-precision sensor specifically refers to the voltmeter, and measure the real-time voltage of the distribution network, and then match the real-time voltage with the voltage comparison result to obtain the distribution network Prediction results, and the specific matching method is as follows:

P1:当获取到的为不存在交集结果时,将实时电压与正常电压区间范围和故障电压区间范围进行比较,具体的比较方式为:P1: When the obtained result is that there is no intersection, compare the real-time voltage with the normal voltage range and the fault voltage range. The specific comparison method is:

获取到正常电压区间范围最大值和故障电压区间范围最小值,并将二者分别记作Uzmax和Ugmin,当实时电压大于Uzmax生成预警信号,或实时电压大于Ugmin生成预警信号;此处表示为任意一种情况满足都生成预警信号,只有当实时电压位于正常电压区间范围内时表示正常。Obtain the maximum value of the normal voltage range and the minimum value of the fault voltage range, and record them as Uzmax and Ugmin respectively. When the real-time voltage is greater than Uzmax, an early warning signal is generated, or when the real-time voltage is greater than Ugmin, an early warning signal is generated; here expressed as any A warning signal will be generated if any one condition is met, and it means normal only when the real-time voltage is within the normal voltage range.

P2:当获取到的为存在结果时,获取到实时电压并判断时间t内的变化情况,若实时电压为稳定变化则表示正常同时对配电网持续监测,若实时电压为上升变化则表示异常同时生成预警信号。此处获取到的实时电压为存在交集的情况,针对存在交集的情况通过判断电压的变化情况来进行预警。P2: When the obtained result is existence, obtain the real-time voltage and determine the change within time t. If the real-time voltage changes steadily, it means it is normal. At the same time, the distribution network is continuously monitored. If the real-time voltage changes upward, it means it is abnormal. At the same time, an early warning signal is generated. The real-time voltage obtained here is the situation where there is an intersection. For the situation where there is an intersection, an early warning is provided by judging the change of the voltage.

本发明提供了一种配电网故障预测的方法。与现有技术相比具备以下有益效果:The invention provides a method for predicting distribution network faults. Compared with existing technology, it has the following beneficial effects:

本发明通过对历史故障数据进行分析,并以故障原因中的电压为例进行分析,通过将电压进行正常电压和故障电压分类,进一步的来判断二者之间是否存在交集,针对存在交集的情况通过获取到实时电压的变化情况来分析配电网整体的工作状态,从而达到预测的目的,针对不存在交集的情况,通过获取到实时电压的数值,并将其与对应的区间值进行比较来对配电网整体的工作状态进行分析,从而达到预测的目的,数据化的分析能够提高整体预测的精准度,可以及时发现异常情况,并进行预警和处理,减少故障的发生。The present invention analyzes historical fault data and takes the voltage in the cause of the fault as an example. By classifying the voltage into normal voltage and fault voltage, it further determines whether there is an intersection between the two. In the case of intersection, the present invention By obtaining the changes in real-time voltage, the overall working status of the distribution network is analyzed to achieve the purpose of prediction. For situations where there is no intersection, the real-time voltage value is obtained and compared with the corresponding interval value. Analyze the overall working status of the distribution network to achieve the purpose of prediction. Data-based analysis can improve the accuracy of the overall prediction, detect abnormal situations in a timely manner, and provide early warning and processing to reduce the occurrence of faults.

附图说明Description of drawings

图1为本发明方法图;Figure 1 is a method diagram of the present invention;

图2为本发明流程图;Figure 2 is a flow chart of the present invention;

图3为本发明交集示意图。Figure 3 is a schematic diagram of the intersection of the present invention.

具体实施方式Detailed ways

下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

实施例一,请参阅图1至图3,本申请提供了一种配电网故障预测的方法,该方法具体包括以下步骤:Embodiment 1. Please refer to Figures 1 to 3. This application provides a method for predicting distribution network faults. The method specifically includes the following steps:

步骤一:首先获取配电网的历史故障数据,且历史故障数据的时间周期为T,其中历史故障数据包括:故障次数、故障原因和故障设备,然后根据故障原因判断是否存在多次故障的设备得到判断结果,判断结果包括存在结果和不存在结果;具体的,多次故障设备表示为该设备出现故障的次数存在两次及以上的情况。Step 1: First obtain the historical fault data of the distribution network, and the time period of the historical fault data is T. The historical fault data includes: the number of faults, the cause of the fault and the faulty equipment. Then based on the fault cause, determine whether there are multiple faulty equipment. The judgment result is obtained, and the judgment result includes an existence result and a non-existence result; specifically, a multiple-failure device indicates that the device has failed twice or more.

步骤二:接着获取到不存在结果并对故障原因进行获取,且故障原因具体可以包括:电压、电流和功率,同时获取到电压、电流和功率对应故障原因的故障次数,并选取故障次数最多对应的故障原因进行分析,在本申请中以电压出现的故障次数最多为例进行分析;Step 2: Then obtain the non-existent result and obtain the cause of the fault, and the cause of the failure can specifically include: voltage, current and power. At the same time, obtain the number of faults corresponding to the voltage, current and power of the fault cause, and select the one with the highest number of faults. The cause of the failure is analyzed. In this application, the voltage with the highest number of failures is used as an example for analysis;

步骤三:获取到历史数据中所有的电压数据,并根据电压数据判断得到正常电压和故障电压,同时根据正常电压和故障电压之间是否存在交集得到交集判断结果,接着根据交集判断结果得到电压故障比较结果,且对电压变化情况的分析方式如下:Step 3: Obtain all voltage data in the historical data, and determine the normal voltage and fault voltage based on the voltage data. At the same time, obtain the intersection judgment result based on whether there is an intersection between the normal voltage and the fault voltage, and then obtain the voltage fault based on the intersection judgment result. Compare the results and analyze the voltage changes as follows:

S1:对所有的电压数据进行标号处理且记作Ui,且i=1、2、…、j,j表示为故障次数标号,其中j的具体数值根据实际情况取值,接着根据故障原因将电压数据进行正常电压和故障电压分类,同时将正常电压记作Uzk,k=1、2、…、o,将故障电压记作Ugh,h=1、2、…、f,;具体表示为:如果出现的故障原因显示是电压异常导致整体故障,则将对应的电压标记为故障电压,反之如果不是电压导致则将对应的电压标记为正常电压。S1: Label all the voltage data and record it as Ui, and i=1, 2,...,j, j represents the number of faults, where the specific value of j is based on the actual situation, and then the voltage is calculated according to the cause of the fault. The data is classified into normal voltage and fault voltage. At the same time, the normal voltage is recorded as Uzk, k=1, 2,..., o, and the fault voltage is recorded as Ugh, h=1, 2,..., f,; the specific expression is: if If the cause of the fault appears to be abnormal voltage causing the overall fault, the corresponding voltage will be marked as the fault voltage. On the contrary, if it is not caused by voltage, the corresponding voltage will be marked as the normal voltage.

S2:获取到所有正常电压Uzk和故障电压Ugh并判断二者是否存在交集得到交集判断结果,交集判断结果包括:存在交集结果和不存在交集结果,此处的交集表示相同数值的电压可能为正常电压,也可能会故障电压,如果正常电压和故障电压均存在相同数值的电压,则表示二者存在交集,反之如果正常电压和故障电压不存在相同数值电压,则表示二者不存在交集S2: Obtain all normal voltages Uzk and fault voltage Ugh and determine whether there is an intersection between the two to obtain the intersection judgment result. The intersection judgment result includes: there is an intersection result and there is no intersection result. The intersection here means that voltages with the same value may be normal. voltage, and may also be fault voltage. If the normal voltage and fault voltage have the same value, it means that there is an intersection between the two. On the contrary, if the normal voltage and the fault voltage do not have the same value, it means that there is no intersection between the two.

S3:当交集判断结果为不存在交集结果时,获取到正常电压的最大值和最小值,并以最小值和最大值生成正常电压区间范围,同理获取到故障电压区间范围;此处得到的正常电压区间范围和故障电压区间范围用来对产生的实时电压进行比较,从而来判断配电网整体的运行状态,从而达到预测的目的,同时不存在交集还表示为正常电压最大值和最小值得到的区间值不包括故障电压中的任一电压值,也就表示得到的两个区间为互不干扰的两个区间,举例表示正常电压区间为[37,45],故障电压区间为[50,60]。S3: When the intersection judgment result is that there is no intersection result, obtain the maximum and minimum values of the normal voltage, and use the minimum and maximum values to generate the normal voltage range, and obtain the fault voltage range in the same way; obtained here The normal voltage interval range and the fault voltage interval range are used to compare the generated real-time voltages to judge the overall operating status of the distribution network to achieve the purpose of prediction. At the same time, if there is no intersection, it is also expressed as the maximum and minimum normal voltage values. The obtained interval value does not include any voltage value in the fault voltage, which means that the two obtained intervals are two intervals that do not interfere with each other. For example, the normal voltage interval is [37, 45] and the fault voltage interval is [50 , 60].

S4:当交集判断结果为存在交集结果时,获取到存在相同数值的电压并将其作为交集电压,接着以产生交集电压的时间为终点,获取终点之前t时间内正常电压的变化情况和故障电压的变化情况。且此处默认产生的交集电压个数只有一个。S4: When the intersection judgment result is that there is an intersection result, obtain the voltage with the same value and use it as the intersection voltage. Then, taking the time when the intersection voltage is generated as the end point, obtain the changes in the normal voltage and the fault voltage within t time before the end point. changes. And there is only one intersection voltage generated by default here.

结合实际情况分析,正常电压变化情况和故障电压变化情况通过计算t时间内电压值的变化得到,其中变化情况包括:稳定和上升,根据实际情况分析得到,正常电压变化情况在t时间内为持续稳定不变的,而针对故障电压的变化情况则为上升的,因此通过二者的区别来进行判断预测。Based on the analysis of the actual situation, the normal voltage changes and the fault voltage changes are obtained by calculating the changes in the voltage value within t time. The changes include: stability and rising. According to the actual situation analysis, the normal voltage change situation is continuous within t time. It is stable and unchanged, while the change of fault voltage is rising, so judgment and prediction can be made based on the difference between the two.

步骤四:根据高精度传感器获取到配电网的实时数据,且高精度传感器具体指电压表,并测量得到配电网的实时电压,接着将实时电压与电压比对结果进行匹配得到配电网预测结果,且具体的匹配方式如下:Step 4: Obtain the real-time data of the distribution network based on the high-precision sensor, and the high-precision sensor specifically refers to the voltmeter, and measure the real-time voltage of the distribution network, and then match the real-time voltage with the voltage comparison result to obtain the distribution network Prediction results, and the specific matching method is as follows:

P1:当获取到的为不存在交集结果时,将实时电压与正常电压区间范围和故障电压区间范围进行比较,具体的比较方式为:P1: When the obtained result is that there is no intersection, compare the real-time voltage with the normal voltage range and the fault voltage range. The specific comparison method is:

获取到正常电压区间范围最大值和故障电压区间范围最小值,并将二者分别记作Uzmax和Ugmin,当实时电压大于Uzmax生成预警信号,或实时电压大于Ugmin生成预警信号;此处表示为任意一种情况满足都生成预警信号,只有当实时电压位于正常电压区间范围内时表示正常。Obtain the maximum value of the normal voltage range and the minimum value of the fault voltage range, and record them as Uzmax and Ugmin respectively. When the real-time voltage is greater than Uzmax, an early warning signal is generated, or when the real-time voltage is greater than Ugmin, an early warning signal is generated; here expressed as any A warning signal will be generated if any one condition is met, and it means normal only when the real-time voltage is within the normal voltage range.

P2:当获取到的为存在结果时,获取到实时电压并判断时间t内的变化情况,若实时电压为稳定变化则表示正常同时对配电网持续监测,若实时电压为上升变化则表示异常同时生成预警信号。此处获取到的实时电压为存在交集的情况,针对存在交集的情况通过判断电压的变化情况来进行预警。P2: When the obtained result is existence, obtain the real-time voltage and determine the change within time t. If the real-time voltage changes steadily, it means it is normal. At the same time, the distribution network is continuously monitored. If the real-time voltage changes upward, it means it is abnormal. At the same time, an early warning signal is generated. The real-time voltage obtained here is the situation where there is an intersection. For the situation where there is an intersection, an early warning is provided by judging the change of the voltage.

实施例二,本实施例在实施例一的基础上实施,本实施例与实施例一的区别之处在于,本实施例是对判断结果为存在结果进行分析。Embodiment 2: This embodiment is implemented on the basis of Embodiment 1. The difference between this embodiment and Embodiment 1 is that this embodiment analyzes the judgment result as an existence result.

获取到存在结果并对故障原因进行获取,故障原因具体可以包括:电压、电流和功率,同时获取到历史故障原因中的故障设备,且此处的故障设备表示为存在结果对应的故障设备,具体表示为出现多次故障原因的故障设备,接着对故障设备的故障原因进行分类得到分类故障原因,并以分类故障原因中的电压为例进行分析,且具体的分析方式如下:Obtain the existence result and obtain the fault cause. The fault cause can specifically include: voltage, current and power. At the same time, the faulty device in the historical fault cause is obtained, and the faulty device here is represented as the faulty device corresponding to the existence result. Specifically Represented as a faulty device with multiple fault causes, the fault causes of the faulty device are then classified to obtain the classified fault causes, and the voltage in the classified fault causes is used as an example for analysis, and the specific analysis method is as follows:

A1:获取到所有的故障电压并对将其记作U1 a,且a=1、2、…、b,同时获取到故障电压中最小电压记作U1min,并对最小电压对应的电流和功率进行分析;且此处故障电压最小值表示的为非正常工作状态下电压值,结合实际分析,最小电压也超过正常工作下的电压。A1: Obtain all fault voltages and record them as U1 a, and a=1, 2,...,b. At the same time, obtain the minimum voltage among the fault voltages and record them as U1min, and conduct the current and power corresponding to the minimum voltage. Analysis; and the minimum value of the fault voltage here represents the voltage value under abnormal working conditions. Based on actual analysis, the minimum voltage also exceeds the voltage under normal working conditions.

A2:若最小电压对应的电流和功率正常,则表示电压异常,并将最小电压作为异常判断标准,同时获取到实时电压并将二者进行比较,若实时电压未超过U1min,则表示正常并对其进行持续监测,且未超过不包括等于U1min的情况,反之若实时电压超过U1min,则表示异常并生成预警信号,且超过包括等于U1mind的情况;A2: If the current and power corresponding to the minimum voltage are normal, it indicates that the voltage is abnormal, and the minimum voltage is used as the abnormality judgment standard. At the same time, the real-time voltage is obtained and the two are compared. If the real-time voltage does not exceed U1min, it indicates that it is normal and is continuously monitored, and it does not exceed, including or equal to U1min. On the contrary, if the real-time voltage exceeds U1min, it indicates an abnormality and generates a warning signal, and it exceeds, including or equal to U1mind.

A3:若最小电压对应的电流和功率异常,且存在的异常表示二者中存在任一异常的情况,则对出现异常的电流和功率进行分析,并根据获取到的实时电流和实时功率来对整体状态进行分析,若均正常则进行持续监测,若二者任一存在异常则生成预警信号。A3: If the current and power corresponding to the minimum voltage are abnormal, and the existing abnormality indicates that either of the two is abnormal, analyze the abnormal current and power, and make corrections based on the obtained real-time current and real-time power. The overall status is analyzed, and if both are normal, continuous monitoring is performed. If any of the two is abnormal, an early warning signal is generated.

实施例三,作为本发明的实施例三,重点在于将实施例一和实施例二的实施过程结合实施。Embodiment 3, as Embodiment 3 of the present invention, focuses on combining the implementation processes of Embodiment 1 and Embodiment 2.

上述公式中的部分数据均是去其纲量进行数值计算,同时本说明书中未作详细描述的内容均属于本领域技术人员公知的现有技术。Some of the data in the above formulas are numerically calculated without their dimensions. At the same time, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

以上实施例仅用以说明本发明的技术方法而非限制,尽管参照较佳实施例对本发明进行了详细说明,本领域的普通技术人员应当理解,可以对本发明的技术方法进行修改或等同替换,而不脱离本发明技术方法的精神和范围。The above embodiments are only used to illustrate the technical methods of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical methods of the present invention can be modified or equivalently substituted. without departing from the spirit and scope of the technical method of the present invention.

Claims (8)

Translated fromChinese
1.一种配电网故障预测的方法,其特征在于,该方法具体包括以下步骤:1. A method for predicting distribution network faults, characterized in that the method specifically includes the following steps:步骤一:根据历史故障数据对设备是否存在多次故障进行判断得到判断结果,判断结果包括存在结果和不存在结果,历史故障数据包括:故障次数、故障原因和故障设备;Step 1: Based on the historical fault data, judge whether the equipment has multiple faults and obtain the judgment result. The judgment result includes the existence result and the non-existence result. The historical fault data includes: the number of faults, the cause of the fault and the faulty equipment;步骤二:对不存在结果对应的故障原因进行获取,并对故障原因为电压的情况进行分析,同时将电压分类为正常电压和故障电压;Step 2: Obtain the fault cause corresponding to the non-existent result, analyze the situation where the fault cause is voltage, and classify the voltage into normal voltage and fault voltage;步骤三:根据正常电压和故障电压是否存在交集得到交集判断结果,交集判断结果包括存在交集结果和不存在交集结果;Step 3: Obtain the intersection judgment result based on whether there is an intersection between the normal voltage and the fault voltage. The intersection judgment result includes the existence of intersection result and the non-existence of intersection result;步骤四:针对不存在交集结果获取到正常电压区间范围和故障电压区间范围,并获取到实时电压与二者进行比较得到配电网预测结果;Step 4: Obtain the normal voltage range and the fault voltage range for the non-intersection result, and obtain the real-time voltage and compare it with the two to obtain the distribution network prediction result;步骤五:针对存在交集结果获取到二者对应的电压变化情况,同时获取到实时电压变化情况,并将实时电压变化情况与二者变化情况匹配得到配电网预测结果;Step 5: Obtain the voltage changes corresponding to the intersection results and obtain the real-time voltage changes at the same time, and match the real-time voltage changes with the changes of the two to obtain the distribution network prediction results;步骤六:对存在结果对应的故障原因进行获取,并对故障原因为电压的情况进行分析,同时获取到实时电压并将其与故障原因对应的电压进行比较得到配电网预测结果。Step 6: Obtain the fault cause corresponding to the existing result, and analyze the situation where the fault cause is voltage. At the same time, obtain the real-time voltage and compare it with the voltage corresponding to the fault cause to obtain the distribution network prediction result.2.根据权利要求1所述的一种配电网故障预测的方法,其特征在于,所述步骤三中交集判断结果的具体分析方式为:2. A method for predicting distribution network faults according to claim 1, characterized in that the specific analysis method of the intersection judgment result in step three is:S1:将所有的电压数据进行标号处理且记作Ui,且i=1、2、…、j,并根据故障原因将电压数据进行正常电压Uzk和故障电压Ugh分类,且k=1、2、…、o,h=1、2、…、f;S1: Label all voltage data and record them as Ui, and i=1, 2,...,j, and classify the voltage data into normal voltage Uzk and fault voltage Ugh according to the cause of the fault, and k=1, 2, ..., o, h = 1, 2, ..., f;S2:当正常电压Uzk与故障电压Ugh存在相同电压值时,则生成存在交集结果,反之则生成不存在交集结果。S2: When the normal voltage Uzk and the fault voltage Ugh have the same voltage value, an intersection result is generated, and vice versa, an intersection result is generated.3.根据权利要求1所述的一种配电网故障预测的方法,其特征在于,所述步骤四中针对不存在交集结果得到配电网预测结果的方式为:3. A method for predicting distribution network faults according to claim 1, characterized in that, in step 4, the method for obtaining distribution network prediction results for non-existent intersection results is:P1:获取到正常电压和故障电压对应的最大值和最小值,并以最小值和最大值分别生成正常电压区间范围和故障电压区间范围;P1: Obtain the maximum and minimum values corresponding to the normal voltage and fault voltage, and generate the normal voltage range and fault voltage range using the minimum and maximum values respectively;P2:获取到正常电压区间范围最大值Uzmax和故障电压区间范围最小值Ugmin,当实时电压大于Uzmax或实时电压大于Ugmin任一一项满足时生成预警信号。P2: Obtain the maximum value Uzmax of the normal voltage range and the minimum value Ugmin of the fault voltage range. When either the real-time voltage is greater than Uzmax or the real-time voltage is greater than Ugmin, an early warning signal is generated.4.根据权利要求1所述的一种配电网故障预测的方法,其特征在于,所述步骤五中针对存在交集记过得到配电网预测结果的方式为:4. A method for predicting distribution network faults according to claim 1, characterized in that, in the step five, the method for obtaining the distribution network prediction results by recording demerits for the existence of intersections is:A1:将正常电压区间范围和故障电压区间范围存在相同数值的电压记作交集电压,获取交集电压之前t时间内正常电压和故障电压对应的变化情况,变化情况对应为:稳定和上升;A1: The voltage with the same value in the normal voltage range and the fault voltage range is recorded as the intersection voltage, and the corresponding changes in the normal voltage and the fault voltage within t time before the intersection voltage are obtained. The changes are corresponding to: stable and rising;A2:获取到实时电压并判断时间t内的变化情况,若实时电压为稳定变化则表示正常同时对配电网持续监测,若实时电压为上升变化则表示异常同时生成预警信号。A2: Obtain the real-time voltage and determine the changes within time t. If the real-time voltage changes steadily, it means it is normal and the distribution network will be continuously monitored. If the real-time voltage changes upward, it means it is abnormal and an early warning signal will be generated.5.根据权利要求1所述的一种配电网故障预测的方法,其特征在于,所述步骤六中对存在结果进行分析得到配电网预测结果的方式为:5. A method for predicting distribution network faults according to claim 1, characterized in that the method of analyzing the existing results in step 6 to obtain distribution network prediction results is:获取到存在结果并对故障原因进行获取,故障原因具体可以包括:电压、电流和功率,同时获取到历史故障原因中的故障设备,并对故障设备的故障原因进行分类得到分类故障原因。Obtain the existence result and obtain the fault cause. The fault cause can specifically include: voltage, current and power. At the same time, the faulty equipment in the historical fault causes is obtained, and the fault cause of the faulty equipment is classified to obtain the classified fault cause.6.根据权利要求5所述的一种配电网故障预测的方法,其特征在于,所述根据分类故障原因对电压的分析方式为:6. A method for predicting distribution network faults according to claim 5, characterized in that the method of analyzing voltage according to classified fault causes is:将所有的故障电压进行标号处理记作U1 a,且a=1、2、…、b,同时获取到故障电压中最小电压记作U1min,并对最小电压对应的电流和功率进行分析判断电流和功率是否正常得到电压异常和电压正常。Label all fault voltages and record them as U1 a, and a = 1, 2,..., b. At the same time, obtain the minimum voltage among the fault voltages and record them as U1min. Analyze the current and power corresponding to the minimum voltage to determine the current and Whether the power is normal or not means the voltage is abnormal and the voltage is normal.7.根据权利要求6所述的一种配电网故障预测的方法,其特征在于,所述当分析得到电压异常时得到配电网预测结果的方式为:7. A method for predicting distribution network faults according to claim 6, characterized in that the method for obtaining distribution network prediction results when analysis results in abnormal voltage is:将故障电压对应的最小电压作为异常判断标准,同时获取到实时电压并将二者进行比较,若实时电压未超过U1min,则表示正常并对其进行持续监测,反之若实时电压超过U1min,则表示异常并生成预警信号。The minimum voltage corresponding to the fault voltage is used as the abnormality judgment standard, and the real-time voltage is obtained at the same time and compared with the two. If the real-time voltage does not exceed U1min, it means it is normal and it will be continuously monitored. On the contrary, if the real-time voltage exceeds U1min, it means exception and generate early warning signals.8.根据权利要求6所述的一种配电网故障预测的方法,其特征在于,所述当分析得到电压正常时得到配电网预测结果的方式为:8. A method for predicting distribution network faults according to claim 6, characterized in that the method for obtaining the distribution network prediction result when the voltage is analyzed to be normal is:获取到异常的电流和功率,同时根据获取到的实时电流和实时功率来对整体状态进行分析,若均正常则进行持续监测,若二者任一存在异常则生成预警信号。Abnormal current and power are obtained, and the overall status is analyzed based on the obtained real-time current and real-time power. If both are normal, continuous monitoring will be performed. If any of the two is abnormal, an early warning signal will be generated.
CN202311611662.8A2023-11-292023-11-29Power distribution network fault prediction methodPendingCN117761423A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202311611662.8ACN117761423A (en)2023-11-292023-11-29Power distribution network fault prediction method

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202311611662.8ACN117761423A (en)2023-11-292023-11-29Power distribution network fault prediction method

Publications (1)

Publication NumberPublication Date
CN117761423Atrue CN117761423A (en)2024-03-26

Family

ID=90313715

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202311611662.8APendingCN117761423A (en)2023-11-292023-11-29Power distribution network fault prediction method

Country Status (1)

CountryLink
CN (1)CN117761423A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN118381650A (en)*2024-05-102024-07-23华能广西清洁能源有限公司Network security situation awareness system suitable for power system
CN119093569A (en)*2024-08-292024-12-06扬州华平电力设备有限公司 An intelligent integrated uninterruptible AC/DC power supply system for rail transit

Cited By (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN118381650A (en)*2024-05-102024-07-23华能广西清洁能源有限公司Network security situation awareness system suitable for power system
CN119093569A (en)*2024-08-292024-12-06扬州华平电力设备有限公司 An intelligent integrated uninterruptible AC/DC power supply system for rail transit

Similar Documents

PublicationPublication DateTitle
CN108460144B (en)Coal equipment fault early warning system and method based on machine learning
CN111459700B (en)Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium
WO2023071217A1 (en)Multi-working-condition process industrial fault detection and diagnosis method based on deep transfer learning
CN117114454B (en)DC sleeve state evaluation method and system based on Apriori algorithm
CN117761423A (en)Power distribution network fault prediction method
CN110008565B (en) Prediction method of abnormal working condition of industrial process based on correlation analysis of operating parameters
CN109186813A (en) A temperature sensor self-checking device and method
CN118261584B (en)Transformer state evaluation method and system based on multi-parameter data
CN118395358B (en)Intelligent anti-misoperation topology analysis method for transformer substation
CN112861350B (en)Temperature overheating defect early warning method for stator winding of water-cooled steam turbine generator
CN119293664A (en) A device operation evaluation method based on multi-source data fusion
CN119004303A (en)Power plant equipment fault diagnosis method and system based on artificial intelligence and automation
CN114664063B (en) A device classification alarm method based on general indicator trend analysis
CN114781476B (en)System and method for analyzing faults of measuring equipment
CN118690306B (en)Digital twin-based heat accumulating type thermal incinerator system fault prediction method and system
CN117560300B (en)Intelligent internet of things flow prediction and optimization system
CN115495274B (en)Exception handling method based on time sequence data, network equipment and readable storage medium
CN116430272A (en)Electrical disturbance-based coal mine equipment abnormality diagnosis method and system and electronic equipment
CN111262750A (en)Method and system for evaluating baseline model
CN116720091A (en) A motor fault analysis method
CN114356621A (en) Method and device for bus exit based on information entropy analysis
CN111783856B (en) A manufacturing-oriented equipment fault auxiliary diagnosis method and system
CN119846518A (en)Short-circuit parameter measurement algorithm development method and system
CN118585917B (en) A solenoid valve fault online diagnosis method based on time-frequency domain characteristic analysis
CN115238929A (en) Method and system for predictive maintenance of petroleum refining system

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp