CN113837596A - Fault determination method and device, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the application discloses a fault determination method, a fault determination device, electronic equipment and a storage medium, wherein the fault determination method comprises the following steps: analyzing historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment; determining a load prediction score of the target device by analyzing historical fault data of the at least one historical fault device and historical operation and maintenance data of the target device; analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm, and determining a three-phase unbalance degree prediction score of the target equipment; and determining the probability of the target equipment failing according to the failure prediction score, the load prediction score and the three-phase unbalance prediction score. The application can avoid excessive overhaul of the equipment and reduce the maintenance cost of the equipment.

Description

Fault determination method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of equipment fault detection, in particular to a fault determination method and device, electronic equipment and a storage medium.

Background

In an enterprise, equipment is equipped for meeting the process requirements of a certain production object or completing the expected functions of an engineering project, and is the value embodiment in the production activity and the important guarantee for the production, however, the frequent failure of the equipment and the maintenance of the equipment not only affect the data and the quality of the enterprise products, but also increase the maintenance cost of the equipment.

In the prior art, under the condition of limited resources such as manpower, financial resources and the like, the increase of the workload and difficulty of equipment maintenance can lead to blind, repeated and excessive maintenance. Therefore, it is necessary to design a method for determining equipment failure, which can avoid excessive overhaul of the equipment and reduce the maintenance cost of the equipment.

Disclosure of Invention

The embodiment of the application provides a fault determination method and device, electronic equipment and a storage medium, which can avoid excessive overhaul of the equipment and reduce the maintenance cost of the equipment.

In a first aspect, an embodiment of the present application provides a fault determination method, where the method includes:

analyzing historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment;

determining a load prediction score of the target device by analyzing historical fault data of the at least one historical fault device and historical operation and maintenance data of the target device;

analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm, and determining a three-phase unbalance degree prediction score of the target equipment;

and determining the probability of the target equipment failing according to the failure prediction score, the load prediction score and the three-phase unbalance prediction score.

In a second aspect, an embodiment of the present application provides a fault determination apparatus, including:

the fault scoring prediction module is used for analyzing historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment;

the load score prediction module is used for determining a load prediction score of the target equipment by analyzing historical fault data of the at least one piece of historical fault equipment and historical operation and maintenance data of the target equipment;

the unbalance degree score prediction module is used for analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm and determining a three-phase unbalance degree prediction score of the target equipment;

and the fault probability determination module is used for determining the probability of the target equipment fault according to the fault prediction score, the load prediction score and the three-phase unbalance degree prediction score.

In a third aspect, an embodiment of the present application provides an electronic device, including:

one or more processors;

storage means for storing one or more programs;

when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the fault determination method of any embodiment of the present application.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the fault determination method according to any embodiment of the present application.

The embodiment of the application provides a fault determination method and device, electronic equipment and a storage medium, wherein historical fault data of at least one piece of historical fault equipment is analyzed through a preset clustering algorithm to obtain an analysis result of the historical fault equipment; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment; determining a load prediction score of the target device by analyzing historical fault data of the at least one historical fault device and historical operation and maintenance data of the target device; analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm, and determining a three-phase unbalance degree prediction score of the target equipment; and determining the probability of the target equipment failing according to the failure prediction score, the load prediction score and the three-phase unbalance prediction score. The technical scheme of this application can avoid excessively overhauing equipment, reduces equipment maintenance cost.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a first flowchart of a fault determination method according to an embodiment of the present disclosure;

fig. 2 is a second flowchart of a fault determination method according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of a fault determination apparatus according to an embodiment of the present application;

fig. 4 is a block diagram of an electronic device for implementing a fault determination method according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Example one

Fig. 1 is a first flowchart of a fault determination method according to an embodiment of the present application, which is applicable to a case where a fault probability of a device is evaluated. The fault determination method provided by this embodiment may be executed by the fault determination apparatus provided by this embodiment, which may be implemented by software and/or hardware and integrated in an electronic device executing this method.

Referring to fig. 1, the method of the present embodiment includes, but is not limited to, the following steps:

s110, analyzing historical fault data of at least one piece of historical fault equipment through a preset clustering algorithm to obtain an analysis result of the historical fault equipment; and determining the failure prediction score of the target equipment according to the analysis result and the attribute information of the target equipment.

The historical fault data can comprise attribute information and fault data of the equipment; the attribute information at least comprises manufacturer information and first commissioning time; the fault data includes at least an equipment fault occurrence time; the product types of the at least one historical fault device and the target device are the same; at least one historical failure device is from at least two vendors. For example, the historical failure device and the target device may be transformers.

In the embodiment of the application, after the electronic device obtains the manufacturer information, the first commissioning time and the device failure occurrence time of at least one piece of historical failure device, the electronic device analyzes the manufacturer information, the first commissioning time and the device failure occurrence time to obtain an analysis result of the device failure, and analyzes the probability of the failure of the target device according to the analysis result. Specifically, first, the equipment commissioning time is calculated according to the first commissioning time of the at least one historical faulty equipment and the equipment fault occurrence time. And then, analyzing the relation between the equipment commissioning time and the manufacturers according to a preset clustering algorithm to obtain the average commissioning time of the equipment manufactured by each manufacturer. And finally, judging the time point of possible failure of the target equipment according to the manufacturer information and the first commissioning time of the target equipment, and further evaluating the failure prediction score of the target equipment.

It should be noted that a large amount of historical fault data of historical fault equipment of different manufacturers in a certain city of a certain year at different commissioning times can be acquired, so that the analysis result of the historical fault equipment obtained through analysis can be more accurate, and the fault prediction score of the target equipment is more accurate.

And S120, analyzing the historical fault data of at least one piece of historical fault equipment and the historical operation and maintenance data of the target equipment, and determining the load prediction score of the target equipment.

The historical fault data can also comprise load data and fault times; the historical operation and maintenance data at least comprises load data.

In the embodiment of the application, because the user does not replace the equipment accessories in time according to the natural increase of the equipment load, the equipment runs in an overload mode, the temperature of the equipment continuously rises, and finally the equipment is in a fault or burnt out. Thus, heavy equipment overload is a significant cause of equipment failure. Optionally, in this step, a linear regression method may be used to analyze the correlation between the heavy overload of the device and the device failure according to the load data and the failure times of the at least one historical failure device. And determining the load prediction score of the target equipment by combining the load data of the target equipment.

S130, analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm, and determining a three-phase unbalance degree prediction score of the target equipment.

If the target device is a transformer, the historical operation and maintenance data may further include voltage data and current data.

In the embodiment of the application, the three-phase current and voltage data updating frequency is that current data and voltage data are uploaded once every 15 minutes, and the voltage unbalance and the current unbalance of the voltage data and the current data uploaded by the target device are determined according to accurate judgment in the three-phase voltage/current allowable unbalance. And then analyzing the characteristics of the voltage unbalance degree and the current unbalance degree of the target equipment within a preset time period (such as within one month) through a preset clustering algorithm, and further determining the three-phase unbalance degree prediction score of the target equipment. Wherein, the three-phase voltage/current allowable unbalance is stipulated as follows: the allowable value of the normal voltage unbalance of the common connection point of the power system is 2%, and meanwhile, the short-time voltage unbalance is regulated to be not more than 4%; the current imbalance must not exceed 10%.

And S140, determining the probability of the target equipment having faults according to the fault prediction score, the load prediction score and the three-phase unbalance prediction score.

In the embodiment of the application, the scores of the three scoring indexes of the target device are determined through the steps as follows: fault prediction scoring, load prediction scoring, and three-phase imbalance prediction scoring. Weights are set for the three scoring indexes of the fault prediction scoring, the load prediction scoring and the three-phase unbalance prediction scoring according to expert experience, and the scoring indexes are multiplied by the corresponding weights and then accumulated to obtain the probability of the target equipment having faults. Alternatively, the weight of the score index may be determined by a method for determining the weight in the prior art, such as a factor analysis method, an entropy method, and the like.

According to the technical scheme provided by the embodiment, historical fault data of at least one piece of historical fault equipment is analyzed through a preset clustering algorithm to obtain an analysis result of the historical fault equipment; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment; determining a load prediction score of the target equipment by analyzing historical fault data of at least one piece of historical fault equipment and historical operation and maintenance data of the target equipment; analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm, and determining a three-phase unbalance degree prediction score of the target equipment; and determining the probability of the target equipment failing according to the failure prediction score, the load prediction score and the three-phase unbalance prediction score. The method comprises the steps of setting three scoring indexes for target equipment, analyzing historical fault data of at least one piece of historical fault equipment and historical operation and maintenance data of the target equipment, determining scores of the three-phase scoring indexes, and finally determining the probability of the target equipment failing. The technical scheme of this application can avoid excessively overhauing equipment, reduces equipment maintenance cost.

Example two

Fig. 2 is a second flowchart of a fault determination method according to an embodiment of the present application. The embodiment of the application is optimized on the basis of the embodiment, and specifically optimized as follows: the determination process of the fault prediction score, the load prediction score and the three-phase unbalance prediction score is added with a detailed explanation.

Referring to fig. 2, the method of the present embodiment includes, but is not limited to, the following steps:

s210, determining the commissioning time of at least one historical fault device according to the historical fault data of the at least one historical fault device; and determining the equipment failure number of each manufacturer according to the manufacturer information of at least one piece of historical failure equipment.

In the embodiment of the application, after the electronic equipment acquires the manufacturer information, the first commissioning time and the equipment fault occurrence time of at least one piece of historical fault equipment, the commissioning time of the at least one piece of historical fault equipment is determined according to the first commissioning time and the equipment fault occurrence time; and determining the equipment failure number of each manufacturer according to the manufacturer information of at least one piece of historical failure equipment.

S220, according to the operation time of each historical fault device and the device fault number of each manufacturer, respectively adopting a K-Means Clustering algorithm and a Noise-Based Density Clustering algorithm (DBSCAN) to perform data iteration, and respectively obtaining the analysis results of at least one historical fault device in the operation time dimension and the device fault number dimension.

In the embodiment of the present application, after the commissioning time of each historical faulty device and the device fault number of each manufacturer are determined through step S210, the device fault number of a certain manufacturer that has a fault in a certain commissioning time is counted, then the commissioning time is taken as an abscissa and the device fault number is taken as an ordinate, and the data of each historical faulty device is plotted on a two-dimensional coordinate system, so as to obtain a scatter diagram of the device fault numbers of different manufacturers in different commissioning times. For example: a (4, 2) indicates that a total of two devices in four years of operation of the manufacturer A have failed.

In the embodiment of the application, a K-Means clustering algorithm is adopted to perform data iteration on the scatter diagram in the dimension of the operation time length to obtain the fault condition of at least one historical fault device in different operation time lengths; and performing data iteration on the scatter diagram on the dimension of the equipment fault number by adopting a DBSCAN clustering algorithm to obtain at least one manufacturer with higher fault rate and lower fault rate corresponding to the historical fault equipment.

And S230, determining the failure prediction score of the target equipment according to the analysis result and the attribute information of the target equipment.

S240, analyzing the load data in the historical operation and maintenance data of the target equipment through a pre-trained load evaluation model to obtain a load prediction score.

The load evaluation model is trained through historical fault data and historical operation and maintenance data of at least one piece of historical fault equipment; the load data includes at least overload information and overload information.

In the embodiment of the application, load data in historical operation and maintenance data of target equipment in a preset time period (such as in the last three months) is obtained, and the load data is input into a pre-trained load evaluation model to obtain a load prediction score of the target equipment.

Optionally, the model training process of the load assessment model includes: acquiring load data of at least one historical fault device within a preset time (such as within three months of the approximate fault) close to the fault; determining an initial load evaluation model by adopting a logistic regression algorithm on the load data of at least one historical fault device; and training the initial load evaluation model to obtain the trained load evaluation model.

Exemplarily, firstly, a logistic regression algorithm is adopted to determine an initial load evaluation model; and acquiring overload information and overload information of at least one historical fault device within three months close to the fault, and using the overload information and the overload information as sample data. Then dividing the sample data into training set and testing set according to the ratio of 8:2, and supplementing missing value by mean value. And finally, training the initial load evaluation model by adopting a training set and a testing set to obtain the trained load evaluation model.

S250, respectively calculating the voltage three-phase unbalance degree and the current three-phase unbalance degree according to the voltage data and the current data in the historical operation and maintenance data of the target equipment; and determining the average value of the three-phase unbalance, the test abnormal rate and the abnormal occurrence days in the preset time according to the voltage three-phase unbalance and the current three-phase unbalance.

In the embodiment of the application, the three-phase current and voltage data updating frequency is that current data and voltage data are uploaded every 15 minutes, after the electronic device obtains multiple pieces of voltage data and multiple pieces of current data of the target device within a preset time period (for example, within one month), the imbalance of the voltage data and the current data is calculated through a voltage/current three-phase imbalance calculation formula, and then the average value of the voltage/current three-phase imbalance within a preset time pair, the test anomaly rate and the number of abnormal occurrence days are calculated. Then, the mean value is used as an x axis, the test abnormality rate is used as a y axis, the number of days of abnormality occurrence is used as a z axis, and a scatter diagram of the voltage three-phase unbalance degree and a scatter diagram of the current three-phase unbalance degree are respectively drawn.

And S260, carrying out data iteration on the mean value of the three-phase unbalance, the test abnormal rate and the abnormal occurrence days by adopting a K-Means clustering algorithm to obtain the three-phase unbalance prediction score of the target equipment.

In this embodiment, after the voltage three-phase imbalance scatter diagram and the current three-phase imbalance scatter diagram are obtained in step S250, data iteration is performed on data points in the voltage three-phase imbalance scatter diagram and the current three-phase imbalance scatter diagram respectively by using a K-Means clustering algorithm, a voltage three-phase imbalance prediction score and a current three-phase imbalance prediction score of the target device are obtained respectively, and then the three-phase imbalance prediction scores are obtained according to respective weighted values of the voltage three-phase imbalance prediction score and the current three-phase imbalance prediction score.

And S270, determining the probability of the target equipment having faults according to the fault prediction score, the load prediction score and the three-phase unbalance prediction score.

According to the technical scheme provided by the embodiment, the determined commissioning time of each piece of historical fault equipment and the determined equipment fault number of each manufacturer are subjected to data iteration by adopting a K-Means clustering algorithm and a DBSCAN clustering algorithm respectively, so that the analysis results of at least one piece of historical fault equipment on the commissioning time dimension and the equipment fault number dimension are obtained respectively, and further the fault prediction score of the target equipment is determined; analyzing load data in the historical operation and maintenance data of the target equipment through a load evaluation model to obtain a load prediction score; determining the mean value of the three-phase unbalance, the test abnormal rate and the abnormal occurrence days within a preset time according to the predetermined voltage three-phase unbalance and current three-phase unbalance, and performing data iteration on the three-phase unbalance by adopting a K-Means clustering algorithm to obtain the three-phase unbalance prediction score of the target equipment; and determining the probability of the target equipment failing according to the failure prediction score, the load prediction score and the three-phase unbalance prediction score. The method comprises the steps of setting three scoring indexes for target equipment, analyzing historical fault data of at least one piece of historical fault equipment and historical operation and maintenance data of the target equipment, determining scores of the three-phase scoring indexes, and finally determining the probability of the target equipment failing. The technical scheme of this application can avoid excessively overhauing equipment, reduces equipment maintenance cost.

EXAMPLE III

Fig. 3 is a schematic structural diagram of a fault determination apparatus according to an embodiment of the present application, and as shown in fig. 3, theapparatus 300 may include:

the faultscoring prediction module 310 is configured to analyze historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device; and determining the failure prediction score of the target equipment according to the analysis result and the attribute information of the target equipment.

And a loadscore prediction module 320, configured to determine a load prediction score of the target device by analyzing the historical fault data of the at least one historical fault device and the historical operation and maintenance data of the target device.

And the unbalance degreescore prediction module 330 is configured to analyze historical operation and maintenance data of the target device through a preset clustering algorithm, and determine a three-phase unbalance degree prediction score of the target device.

And the failureprobability determination module 340 is configured to determine the probability of failure of the target device according to the failure prediction score, the load prediction score and the three-phase imbalance prediction score.

Further, the failurescore prediction module 310 is specifically configured to: determining the commissioning time of the at least one historical fault device according to the historical fault data of the at least one historical fault device; determining the equipment fault number of each manufacturer according to the manufacturer information of the at least one historical fault equipment; and performing data iteration by respectively adopting a K-Means clustering algorithm and a DBSCAN clustering algorithm according to the commissioning time of each historical fault device and the device fault number of each manufacturer to respectively obtain the analysis results of the at least one historical fault device on the commissioning time dimension and the device fault number dimension.

Further, the imbalance degreescore prediction module 330 is specifically configured to: respectively calculating the voltage three-phase unbalance degree and the current three-phase unbalance degree according to the voltage data and the current data in the historical operation and maintenance data of the target equipment; determining the mean value of the three-phase unbalance, the test abnormal rate and the abnormal occurrence days within a preset time according to the voltage three-phase unbalance and the current three-phase unbalance; and performing data iteration on the mean value of the three-phase unbalance degrees, the test abnormal rate and the abnormal occurrence days by adopting a K-Means clustering algorithm to obtain the three-phase unbalance degree prediction score of the target equipment.

Further, the loadscore prediction module 320 is specifically configured to: analyzing load data in the historical operation and maintenance data of the target equipment through a pre-trained load evaluation model to obtain a load prediction score; wherein the load evaluation model is trained by historical fault data and historical operation and maintenance data of at least one historical fault device.

Optionally, the model training process of the load assessment model includes: acquiring load data of the at least one historical fault device within preset time close to the fault; determining an initial load evaluation model by adopting a logistic regression algorithm on the load data of the at least one historical fault device; and training the initial load evaluation model to obtain a trained load evaluation model.

Optionally, the at least one historical failure device and the target device are of the same product type.

The fault determination device provided by the embodiment can be applied to the fault determination method provided by any embodiment, and has corresponding functions and beneficial effects.

Example four

Fig. 4 is a block diagram of an electronic device used to implement a fault determination method according to an embodiment of the present application, and fig. 4 shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present application. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application. The electronic device can be a smart phone, a tablet computer, a notebook computer, a vehicle-mounted terminal, a wearable device and the like.

As shown in fig. 4,electronic device 400 is embodied in the form of a general purpose computing device. The components ofelectronic device 400 may include, but are not limited to: one or more processors orprocessing units 416, amemory 428, and abus 418 that couples the various system components including thememory 428 and theprocessing unit 416.

Bus 418 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 400 typically includes a variety of computer system readable media. Such media may be any available media that is accessible byelectronic device 400 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 428 can include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)430 and/orcache memory 432. Theelectronic device 400 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only,storage system 434 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected tobus 418 by one or more data media interfaces.Memory 428 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.

A program/utility 440 having a set (at least one) ofprogram modules 442 may be stored, for instance, inmemory 428,such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment.Program modules 442 generally perform the functions and/or methodologies of embodiments described herein.

Theelectronic device 400 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device,display 424, etc.), with one or more devices that enable a user to interact with theelectronic device 400, and/or with any devices (e.g., network card, modem, etc.) that enable theelectronic device 400 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 422. Also,electronic device 400 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) throughnetwork adapter 420. As shown in FIG. 4,network adapter 420 communicates with the other modules ofelectronic device 400 overbus 418. It should be appreciated that although not shown in FIG. 4, other hardware and/or software modules may be used in conjunction withelectronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Theprocessing unit 416 executes various functional applications and data processing by executing programs stored in thememory 428, for example, to implement the fault determination method provided in any embodiment of the present application.

EXAMPLE five

A fifth embodiment of the present application further provides a computer-readable storage medium, on which a computer program (or referred to as computer-executable instructions) is stored, where the computer program, when executed by a processor, can be used to execute the fault determination method provided in any of the above embodiments of the present application.

The computer storage media of the embodiments of the present application may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for embodiments of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the embodiments of the present application have been described in more detail through the above embodiments, the embodiments of the present application are not limited to the above embodiments, and many other equivalent embodiments may be included without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims (10)

1. A method of fault determination, the method comprising:

analyzing historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment;

determining a load prediction score of the target device by analyzing historical fault data of the at least one historical fault device and historical operation and maintenance data of the target device;

analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm, and determining a three-phase unbalance degree prediction score of the target equipment;

and determining the probability of the target equipment failing according to the failure prediction score, the load prediction score and the three-phase unbalance prediction score.

2. The method according to claim 1, wherein the analyzing historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device comprises:

determining the commissioning time of the at least one historical fault device according to the historical fault data of the at least one historical fault device; determining the equipment fault number of each manufacturer according to the manufacturer information of the at least one historical fault equipment;

and performing data iteration by respectively adopting a K-Means clustering algorithm and a noise-based density clustering algorithm DBSCAN according to the commissioning time of the at least one historical fault device and the device fault number of each manufacturer, and respectively obtaining the analysis results of the at least one historical fault device on the commissioning time dimension and the device fault number dimension.

3. The method of claim 1, wherein the analyzing the historical operation and maintenance data of the target device through a preset clustering algorithm to determine a three-phase imbalance degree prediction score of the target device comprises:

respectively calculating the voltage three-phase unbalance degree and the current three-phase unbalance degree according to the voltage data and the current data in the historical operation and maintenance data of the target equipment;

determining the mean value of the three-phase unbalance, the test abnormal rate and the abnormal occurrence days within a preset time according to the voltage three-phase unbalance and the current three-phase unbalance;

and performing data iteration on the mean value of the three-phase unbalance degrees, the test abnormal rate and the abnormal occurrence days by adopting a K-Means clustering algorithm to obtain the three-phase unbalance degree prediction score of the target equipment.

4. The method of claim 1, wherein determining the load prediction score of the target device by analyzing historical fault data of the at least one historical fault device and historical operation and maintenance data of the target device comprises:

analyzing load data in the historical operation and maintenance data of the target equipment through a pre-trained load evaluation model to obtain a load prediction score; wherein the load evaluation model is trained by historical fault data and historical operation and maintenance data of at least one historical fault device.

5. The method of claim 4, wherein the model training process of the load assessment model comprises:

acquiring load data of the at least one historical fault device within preset time close to the fault;

determining an initial load evaluation model by adopting a logistic regression algorithm on the load data of the at least one historical fault device;

and training the initial load evaluation model to obtain a trained load evaluation model.

6. The method of claim 1, wherein the at least one historically failed device and the target device are of the same product type.

7. A fault determination device, characterized in that the device comprises:

the fault scoring prediction module is used for analyzing historical fault data of at least one historical fault device through a preset clustering algorithm to obtain an analysis result of the historical fault device; determining a fault prediction score of the target equipment according to the analysis result and the attribute information of the target equipment;

the load score prediction module is used for determining a load prediction score of the target equipment by analyzing historical fault data of the at least one piece of historical fault equipment and historical operation and maintenance data of the target equipment;

the unbalance degree score prediction module is used for analyzing historical operation and maintenance data of the target equipment through a preset clustering algorithm and determining a three-phase unbalance degree prediction score of the target equipment;

and the fault probability determination module is used for determining the probability of the target equipment fault according to the fault prediction score, the load prediction score and the three-phase unbalance degree prediction score.

8. The method of claim 7, wherein the failure score prediction module is specifically configured to:

determining the commissioning time of the at least one historical fault device according to the historical fault data of the at least one historical fault device; determining the equipment fault number of each manufacturer according to the manufacturer information of the at least one historical fault equipment;

and performing data iteration by respectively adopting a K-Means clustering algorithm and a DBSCAN clustering algorithm according to the commissioning time of the at least one historical fault device and the device fault number of each manufacturer to respectively obtain the analysis results of the at least one historical fault device on the commissioning time dimension and the device fault number dimension.

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

storage means for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the fault determination method of any one of claims 1-6.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method of fault determination according to any one of claims 1-6.

Images