A bird damage fault diagnosis method, device, equipment and storage medium

Abstract

The present invention discloses a bird damage fault diagnosis method, device, equipment and storage medium. The method includes: determining fault correlation information, where the fault correlation information includes a plurality of first fault factors associated with the occurrence of bird damage faults; determining the probability of the bird damage fault to be determined according to the current state of the first fault factor and the corresponding first preset weight; if the probability of the bird damage fault to be determined is less than a preset threshold, determining the target bird damage fault probability according to the current fault traveling wave and the probability of the bird damage fault to be determined. The technical solution of the embodiment of the present invention accurately determines the probability of the current occurrence of bird damage faults, without requiring a large amount of economic costs, and is less restricted by weather and terrain.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission, and particularly to a method, device, equipment and storage medium for diagnosing bird damage faults. Background Art

[0002] Currently, transmission lines are facing serious bird damage problems. Birds such as magpies and crows often perch on transmission lines. They not only build nests on the wires but may also cause short - circuit accidents. These birds damage transmission lines in various ways, including pecking through the wire insulation layer and then the bird carcass causing a short - circuit, etc.

[0003] Installing physical isolation facilities such as anti - bird spines and anti - bird nets often has limitations and cannot completely solve the bird damage problem. Currently, common methods include visual inspection, infrared thermal imaging, and acoustic monitoring, etc. Visual inspection relies on manual or drone patrols of the line, and can intuitively detect faults caused by bird nests or dead birds. Detecting abnormal hot spots on the line through infrared thermal imaging technology to identify bird damage problems is suitable for inspections at night or in bad weather. The acoustic monitoring system can capture the sounds of bird activities in real - time and analyze their impact on transmission equipment, and has the characteristics of high efficiency and all - weather.

[0004] However, visual inspection has low efficiency and is greatly restricted by weather and terrain. Infrared thermal imaging technology has high costs, and the initial installation and maintenance costs of the acoustic monitoring system are not low. These methods all have their own limitations. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for diagnosing bird damage faults to solve the limitations of traditional bird damage diagnosis methods.

[0006] In a first aspect, the present invention provides a method for diagnosing bird damage faults, including:

[0007] Determine fault - related information, where the fault - related information includes a plurality of first fault factors associated with the occurrence of bird damage faults;

[0008] Determine the probability of the bird damage fault to be determined according to the current state of the first fault factor and the corresponding first preset weight;

[0009] If the probability of the bird damage fault to be determined is less than a preset threshold, then determine the target bird damage fault probability according to the current fault traveling wave and the probability of the bird damage fault to be determined.

[0010] In a second aspect, the present invention provides a device for diagnosing bird damage faults, including:

[0011] A fault - related information determination module, configured to determine fault - related information, where the fault - related information includes a plurality of first fault factors associated with the occurrence of bird damage faults;

[0012] An undetermined fault probability determination module, configured to determine an undetermined bird damage fault probability according to the current state of the first fault factor and the corresponding first preset weight;

[0013] A target fault probability determination module, configured to determine a target bird damage fault probability according to the current fault traveling wave and the undetermined bird damage fault probability if the undetermined bird damage fault probability is less than a preset threshold.

[0014] In a third aspect, the present invention provides an electronic device, which includes:

[0015] At least one processor;

[0016] And a memory communicatively connected to at least one processor;

[0017] Wherein, the memory stores a computer program executable by at least one processor, and the computer program is executed by at least one processor so that at least one processor can execute the bird damage fault diagnosis method in the first aspect above.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores computer instructions for causing a processor to implement the bird damage fault diagnosis method in the first aspect above when executed.

[0019] The bird damage fault diagnosis solution provided by the present invention determines fault association information, where the fault association information includes a plurality of first fault factors associated with the occurrence of bird damage faults. According to the current state of the first fault factor and the corresponding first preset weight, an undetermined bird damage fault probability is determined. If the undetermined bird damage fault probability is less than a preset threshold, a target bird damage fault probability is determined according to the current fault traveling wave and the undetermined bird damage fault probability. By adopting the above technical solution, the factors associated with the occurrence of bird damage faults are excavated to initially determine the probability of the current occurrence of bird damage faults. When the probability is small, the probability of the current occurrence of bird damage faults is accurately judged according to the characteristics of the fault traveling wave and the probability, without investing a large amount of economic costs and being less restricted by weather and terrain.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0022] Figure 1 is a flowchart of a bird damage fault diagnosis method provided in Embodiment 1 of the present invention;

[0023] Figure 2 is a flowchart of a bird damage fault diagnosis method provided in Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of a bird damage fault diagnosis device provided in Embodiment 3 of the present invention;

[0025] Figure 4 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed implementation manners

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In the description of the present invention, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. In addition, the terms "comprising" and "having" and any of their deformations are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0028] Embodiment 1

[0029] Figure 1 The figure is a flowchart of a bird damage fault diagnosis method provided by Embodiment 1 of the present invention. This embodiment is applicable to determining the probability of a bird damage fault occurring in a transmission line. This method can be executed by a bird damage fault diagnosis device, which can be implemented in the form of hardware and / or software. The bird damage fault diagnosis device can be configured in an electronic device, which can be composed of two or more physical entities or one physical entity.

[0030] As Figure 1 shown, a bird damage fault diagnosis method provided by Embodiment 1 of the present invention specifically includes the following steps:

[0031] S101. Determine fault correlation information, where the fault correlation information includes a plurality of first fault factors associated with the occurrence of a bird damage fault.

[0032] In this embodiment, the causes of bird damage faults and the characteristics after the occurrence of bird damage faults can be studied in advance. According to expert experience or prior knowledge, factors associated with the occurrence of bird damage faults, that is, first fault factors, are excavated. For example, weather conditions and the bird distribution in the current area, etc. Among them, the first fault factors include cause factors that are likely to cause bird damage faults and characteristic factors after the occurrence of bird damage faults.

[0033] S102. Determine the probability of the to-be-determined bird damage fault according to the current state of the first fault factor and the corresponding first preset weight.

[0034] In this embodiment, corresponding weights can be set in advance for different states of the first fault factor, that is, the first preset weight is set. Then, according to the current state of each first fault factor and the preset weight corresponding to each state, the probability of the to-be-determined bird damage fault can be calculated. For example, the numerical values of these weights can be added, and the result obtained is the probability of the to-be-determined bird damage fault. Among them, the first preset weight is usually less than 1.

[0035] S103. If the probability of the to-be-determined bird damage fault is less than the preset threshold, determine the target bird damage fault probability according to the current fault traveling wave and the probability of the to-be-determined bird damage fault.

[0036] In this embodiment, if the probability of bird damage fault to be determined is less than the preset threshold, it means that the states of the first fault factors do not all meet the states that should be possessed when a bird damage fault occurs. The target bird damage fault probability can be determined comprehensively based on the current fault traveling wave and the probability of bird damage fault to be determined. For example, the probability of a bird damage fault occurring can be predicted based on the current fault traveling wave, and then the predicted probability and the probability of bird damage fault to be determined are processed to obtain the target bird damage fault probability. For example, the predicted probability and the probability of bird damage fault to be determined are weighted and summed to obtain the target bird damage fault probability.

[0037] The bird damage fault diagnosis method provided by the embodiment of the present invention determines fault correlation information, where the fault correlation information includes a plurality of first fault factors associated with the occurrence of bird damage faults. According to the current states of the first fault factors and the corresponding first preset weights, the probability of bird damage fault to be determined is determined. If the probability of bird damage fault to be determined is less than the preset threshold, the target bird damage fault probability is determined based on the current fault traveling wave and the probability of bird damage fault to be determined. The technical solution of the embodiment of the present invention uses the factors excavated and associated with the occurrence of bird damage faults to initially determine the probability of a current bird damage fault. When this probability is relatively small, the probability of a current bird damage fault is accurately judged based on the characteristics of the fault traveling wave and this probability, without investing a large amount of economic costs and being less restricted by weather and terrain.

[0038] Optionally, before determining the probability of bird damage fault to be determined according to the current states of the first fault factors and the corresponding first preset weights, it further includes: obtaining the current states of the first fault factors and determining whether there are failures and / or omissions in the states; if so, receiving input information and using the input information to correct and / or supplement the states to obtain the updated current states of the first fault factors, where the input information contains the failed and / or missing states.

[0039] Specifically, when the state of the first fault factor fails and / or is missing, input information manually entered can be accepted to complete and / or correct the state of the first fault factor.

[0040] Optionally, the first fault factors in the fault correlation information include time, reclosing information after a fault, phase fault information of the transmission line, visualization information, preset bird damage level of the current area, meteorological information, and line voltage level; where the preset bird damage level of the current area is the risk level of a bird damage fault occurring in the current area, and the visualization information is the bird situation in the current area.

[0041] Specifically, through statistics and analysis, it can be found that:

[0042] 1) Due to the habits of birds, certain time periods are frequent bird damage fault time periods.

[0043] 2) After a bird damage fault occurs, there is a certain pattern in the reclosing situation of the transmission line.

[0044] 3) Under bird damage faults, there is a certain pattern in the fault conditions of the transmission line phases.

[0045] 4) Under certain specific meteorological conditions, bird damage faults are likely to occur, such as when there are no typhoons, heavy rains, and strong winds, and the weather is good.

[0046] 5) For lines of certain voltage levels, bird damage faults are likely to occur.

[0047] 6) In areas with a large number of birds, the risk level of bird damage faults is usually relatively high, and bird damage faults are likely to occur.

[0048] 7) When bird nests and other bird-related situations are captured around the transmission line, bird damage faults are usually likely to occur.

[0049] Therefore, the current time, the reclosing situation after the current fault occurs, the fault conditions of the transmission line phases, the visual information collected by the camera, the preset bird damage level in the area where the transmission line tower is located, the meteorological situation, and the voltage level of the transmission line, etc. are all related to whether a bird damage fault occurs.

[0050] Embodiment 2

[0051] Figure 2 It is a flowchart of a bird damage fault diagnosis method provided by Embodiment 2 of the present invention. The technical solution of the embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions, and a specific method for judging bird damage faults is given.

[0052] Optionally, determining the probability of the to-be-determined bird damage fault according to the state of the current first fault factor and the corresponding first preset weight includes: determining the first sum value of the first preset weights corresponding to the state of the current first fault factor, and determining the fault exclusion information, where the fault exclusion information includes a plurality of second fault factors associated with excluding bird damage faults; determining the second sum value of the second preset weights corresponding to the state of the current second fault factor, and determining the sum value of the first sum value and the second sum value as the probability of the to-be-determined bird damage fault. The advantage of such a setting is that the probability of the bird damage fault determined according to the weight of the fault association information (i.e., the first sum value) is corrected by using the fault exclusion information, further ensuring the accuracy and reliability of the line fault diagnosis.

[0053] Optionally, determining the target bird damage fault probability based on the current fault traveling wave and the to-be-determined bird damage fault probability includes: using a preset bird damage fault waveform identification model to output a predicted bird damage fault probability according to the current fault traveling wave; and obtaining the target bird damage fault probability through performing a preset operation on the predicted bird damage fault probability and the to-be-determined bird damage fault probability. The advantage of such a setting is that the predicted bird damage fault probability under the current fault traveling wave is quickly predicted by using the preset bird damage fault waveform identification model, and combined with the to-be-determined bird damage fault probability, the probability of the current line having a bird damage fault is accurately analyzed.

[0054] Optionally, after determining the to-be-determined bird damage fault probability according to the state of the current first fault factor and the corresponding first preset weight, it includes: if the to-be-determined bird damage fault probability is greater than or equal to a preset threshold, then determining the to-be-determined bird damage fault probability as the target bird damage fault probability.

[0055] As Figure 2 shown, a bird damage fault diagnosis method provided in Embodiment 2 of the present invention specifically includes the following steps:

[0056] S201. Determine fault-related information, where the fault-related information includes time, reclosing information after a fault, transmission line phase fault information, visualization information, a preset bird damage level of the current area, meteorological information, and line voltage level.

[0057] Among them, the preset bird damage level of the current area is the risk level of a bird damage fault occurring in the current area, and the visualization information is the bird situation in the current area.

[0058] S202. Obtain the state of the current first fault factor, and determine whether the state has a failure and / or is missing. If so, execute step 203; if not, execute step 204.

[0059] S203. Receive input information, and use the input information to correct and / or supplement the state to obtain the updated state of the current first fault factor, where the input information includes the failed and / or missing state.

[0060] S204. Determine the first sum value of the first preset weight corresponding to the state of the current first fault factor, and determine fault exclusion information, where the fault exclusion information includes a plurality of second fault factors associated with excluding bird damage faults.

[0061] Exemplarily, if the state of the first fault factor is:

[0062] The fault time is within the interval from 4 to 8 o'clock or from 17 to 22 o'clock, the reclosing is successful, the phase of the transmission line where the fault occurs is the upper phase or the middle phase, the visual information indicates the presence of birds or no abnormality, the fault tower is located in a bird damage area of level 2 or above, there is no typhoon, heavy rain or strong wind disaster at present, and the voltage level of the transmission line with the fault is not ±800 kV or ±1000 kV. The first preset weight corresponding to "the fault time is within the interval from 4 to 8 o'clock or from 17 to 22 o'clock" is a, the first preset weight corresponding to "the reclosing is successful" is b, the first preset weight corresponding to "the phase of the transmission line where the fault occurs is the upper phase or the middle phase" is c, the first preset weight corresponding to "the visual information indicates the presence of birds or no abnormality" is d, the first preset weight corresponding to "the fault tower is located in a bird damage area of level 2 or above" is e, the first preset weight corresponding to "there is no typhoon, heavy rain or strong wind disaster at present" is f, and the first preset weight corresponding to "the voltage level of the transmission line with the fault is not ±800 kV or ±1000 kV" is g. Among them, if a + b + c + d + e + f = X%, then the first sum value is X%. The second fault factors in the fault troubleshooting information may include the line voltage level, meteorological information, post-fault reclosing information, phase-to-phase fault information, and high-resistance fault information.

[0063] S205. Determine the second sum value of the second preset weights corresponding to the states of the current second fault factors, and determine the sum value of the first sum value and the second sum value as the bird damage fault probability to be determined.

[0064] Specifically, the preset weights corresponding to the states of the fault factors are usually negative.

[0065] Exemplarily, if the state of the second fault factor is at least one of the following:

[0066] The voltage level of the fault line is ±800 kV or ±1000 kV, a typhoon, heavy rain or strong wind disaster occurs, the reclosing is unsuccessful, a phase-to-phase fault occurs, and a high-resistance fault occurs. If the second preset weight corresponding to "the voltage level of the fault line is ±800 kV or ±1000 kV" is A, the second preset weight corresponding to "a typhoon, heavy rain or strong wind disaster occurs" is B, the second preset weight corresponding to "the reclosing is unsuccessful" is C, the second preset weight corresponding to "a phase-to-phase fault occurs" is D, and the second preset weight corresponding to "a high-resistance fault occurs" is E. Among them, if A + B + C + D + E = -Y% < 0, then the second sum value is -Y%. If the first sum value is Z%, the bird damage fault probability to be determined is the value of Z% - Y%.

[0067] S206. Determine whether the bird damage fault probability to be determined is less than the preset threshold. If so, execute step 207; if not, execute step 209.

[0068] Exemplarily, the preset threshold may be the X% described above.

[0069] S207. Output a predicted bird damage fault probability according to the current fault traveling wave by using a preset bird damage fault waveform identification model.

[0070] Specifically, the current fault traveling wave can be input into the preset bird damage fault waveform identification model to obtain the predicted bird damage fault probability.

[0071] S208. Obtain a target bird damage fault probability through a preset operation on the predicted bird damage fault probability and the to-be-determined bird damage fault probability.

[0072] Exemplarily, a preset operation such as weighted summation, direct summation, or averaging can be performed on the predicted bird damage fault probability and the bird damage fault probability to obtain the target bird damage fault probability.

[0073] Optionally, the determination method of the preset bird damage fault waveform identification model includes:

[0074] Obtain historical power grid fault data, where the historical power grid fault data includes time-domain feature data and frequency-domain feature data of bird damage fault traveling waves under multiple bird damage fault types; use oversampling technology to supplement the historical power grid fault data to obtain balanced training sample data; use the balanced training sample data and the deep forest algorithm to train an initial deep learning model to obtain a preset bird damage fault waveform identification model.

[0075] Specifically, historical fault information can be collected first, and a line fault transient waveform database can be established using this information. Multiple characteristic parameters of the fault traveling wave are extracted from the time domain and the frequency domain, and a bird damage fault waveform identification model is established using these parameters. The time-domain feature data and frequency-domain feature data of bird damage fault traveling waves under multiple bird damage fault types included in the historical power grid fault data may be unbalanced data. Therefore, the SMOTE oversampling technology can be used to supplement the historical power grid fault data to obtain balanced training sample data. The initial deep learning model can be a multi-granularity cascade forest model. The multi-granularity cascade forest model includes multi-granularity scanning and cascade forest. The multi-granularity scanning part filters features and generates feature quantities that are more closely related to the classification relationship. The role of the cascade forest is to process the sample features layer by layer to enhance the accuracy of the algorithm's pattern recognition. Each layer is provided with 1 random forest and 1 completely random forest. The input data of the first layer of the cascade forest is a multi-dimensional vector spliced by the multi-dimensional class vector passing through the random forest and the multi-dimensional vector passing through the completely random forest. After classification processing, 2 two-dimensional class vectors are obtained. Then, these 2 two-dimensional class vectors are spliced with the multi-dimensional initial feature vector to form a multi-dimensional new feature vector as the input of the second layer, and so on. Finally, the average value of the class vectors output by the Nth layer is calculated, and the maximum value in the average value is output, and this maximum value is the output predicted bird damage fault probability.

[0076] S209. Determine the to-be-determined bird damage fault probability as the target bird damage fault probability.

[0077] Exemplarily, when the to-be-determined bird damage fault probability = X%, it indicates that the states of the first fault factors all meet the states when a bird damage fault occurs. Therefore, the to-be-determined bird damage fault probability can be directly determined as the target bird damage fault probability.

[0078] The bird damage fault diagnosis method provided by the embodiments of the present invention corrects the bird damage fault probability determined according to the weight of the fault association information by using the fault exclusion information, further ensuring the accuracy and reliability of the line fault diagnosis. When the probability is small, the predicted bird damage fault probability under the current fault traveling wave is quickly predicted by using the preset bird damage fault waveform identification model, and combined with the to-be-determined bird damage fault probability, the probability of the current line having a bird damage fault is accurately analyzed.

[0079] Embodiment III

[0080] Figure 3 It is a schematic structural diagram of a bird damage fault diagnosis device provided by Embodiment III of the present invention. As Figure 3 shown, the device includes: a fault association information determination module 301, a to-be-determined fault probability determination module 302, and a target fault probability determination module 303, where:

[0081] The fault association information determination module is used to determine the fault association information, where the fault association information includes a plurality of first fault factors associated with the occurrence of a bird damage fault;

[0082] The to-be-determined fault probability determination module is used to determine the to-be-determined bird damage fault probability according to the state of the current first fault factor and the corresponding first preset weight;

[0083] The target fault probability determination module is used to, if the to-be-determined bird damage fault probability is less than a preset threshold, determine the target bird damage fault probability according to the current fault traveling wave and the to-be-determined bird damage fault probability.

[0084] The bird damage fault diagnosis device provided by the embodiments of the present invention preliminarily determines the probability of the current occurrence of a bird damage fault by using the excavated factors associated with the occurrence of a bird damage fault. When the probability is small, the probability of the current occurrence of a bird damage fault is accurately judged according to the characteristics of the fault traveling wave and the probability, without investing a large amount of economic cost and being less restricted by weather and terrain.

[0085] Optionally, the to-be-determined fault probability determination module includes:

[0086] A summation and exclusion information determination unit is configured to determine a first sum value of a first preset weight corresponding to the state of the current first fault factor, and determine troubleshooting information, where the troubleshooting information includes a plurality of second fault factors associated with troubleshooting bird damage faults;

[0087] A to-be-determined fault probability determination unit is configured to determine a second sum value of a second preset weight corresponding to the state of the current second fault factor, and determine the sum value of the first sum value and the second sum value as the to-be-determined bird damage fault probability.

[0088] Optionally, the device further includes:

[0089] A judgment module is configured to, before determining the to-be-determined bird damage fault probability according to the state of the current first fault factor and the corresponding first preset weight, obtain the state of the current first fault factor, and judge whether the state has a failure and / or a missing;

[0090] An update module is configured to, if the information returned by the judgment module is yes, receive input information, and use the input information to correct and / or supplement the state to obtain the updated state of the current first fault factor, where the input information includes the state of failure and / or missing.

[0091] Optionally, the target fault probability determination module includes:

[0092] A probability output unit is configured to output a predicted bird damage fault probability according to the current fault traveling wave by using a preset bird damage fault waveform identification model;

[0093] A target fault probability determination unit is configured to obtain a target bird damage fault probability through a preset operation on the predicted bird damage fault probability and the to-be-determined bird damage fault probability.

[0094] Furthermore, the determination method of the preset bird damage fault waveform identification model includes: obtaining historical power grid fault data, where the historical power grid fault data includes time-domain characteristic data and frequency-domain characteristic data of bird damage fault traveling waves under a plurality of bird damage fault types; using an oversampling technique to supplement the historical power grid fault data to obtain balanced training sample data; using the balanced training sample data and a deep forest algorithm to train an initial deep learning model to obtain a preset bird damage fault waveform identification model.

[0095] Furthermore, the first fault factor in the fault association information includes time, reclosing information after a fault, transmission line phase fault information, visualization information, a preset bird damage level in the current area, meteorological information, and line voltage level; where the preset bird damage level in the current area is the risk level of bird damage faults occurring in the current area, and the visualization information is the bird situation in the current area.

[0096] Optionally, the device further includes:

[0097] A bird damage fault probability determination module, configured to, after determining the to-be-determined bird damage fault probability according to the state of the current first fault factor and the corresponding first preset weight, if the to-be-determined bird damage fault probability is greater than or equal to a preset threshold, determine the to-be-determined bird damage fault probability as the target bird damage fault probability.

[0098] The bird damage fault diagnosis device provided by the embodiments of the present invention can execute the bird damage fault diagnosis method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0099] Embodiment 4

[0100] Figure 4 FIG. shows a schematic structural diagram of an electronic device 40 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0101] As Figure 4 shown, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc. The memory stores a computer program executable by at least one processor. The processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. The input / output (I / O) interface 45 is also connected to the bus 44.

[0102] Multiple components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disc, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0103] The processor 41 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the bird damage fault diagnosis method.

[0104] In some embodiments, the bird damage fault diagnosis method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the bird damage fault diagnosis method described above can be executed. Alternatively, in other embodiments, the processor 41 can be configured to execute the bird damage fault diagnosis method by any other suitable means (e.g., by means of firmware).

[0105] The various embodiments of the systems and technologies described above in this article can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0107] The computer device provided above can be used to execute the bird damage fault diagnosis method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0108] Embodiment Five

[0109] In the context of the present invention, a computer-readable storage medium can be a tangible medium, and the computer-executable instructions are used to execute the bird damage fault diagnosis method when executed by a computer processor. The method includes:

[0110] Determine fault correlation information, where the fault correlation information includes a plurality of first fault factors associated with the occurrence of bird damage faults;

[0111] Determine the probability of the bird damage fault to be determined according to the current state of the first fault factor and the corresponding first preset weight;

[0112] If the probability of the bird damage fault to be determined is less than a preset threshold, then determine the target bird damage fault probability according to the current fault traveling wave and the probability of the bird damage fault to be determined.

[0113] In the context of the present invention, a computer-readable storage medium can be a tangible medium, which can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] The computer device provided above can be used to execute the bird damage fault diagnosis method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0115] It should be noted that in the embodiments of the above bird damage fault diagnosis device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0116] Note that the above is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A bird damage fault diagnosis method, characterized in that: include: Determining fault association information, wherein the fault association information includes a plurality of first fault factors associated with the bird damage fault; Determine the probability of a bird damage failure to be determined according to the current state of the first fault factor and the corresponding first preset weight; If the to-be-determined bird damage fault probability is less than a preset threshold, determining the target bird damage fault probability according to the current fault traveling wave and the to-be-determined bird damage fault probability; The determining of the probability of a bird damage failure to be determined according to the current state of the first fault factor and the corresponding first preset weight includes: Determine a first sum value of a first preset weight corresponding to the current state of the first fault factor, and determine fault elimination information, wherein the fault elimination information includes a plurality of second fault factors associated with eliminating the bird damage fault; A second sum value of a second preset weight corresponding to the current state of the second fault factor is determined, and a sum value of the first sum value and the second sum value is determined as the bird damage fault probability to be determined.

2. The method according to claim 1, characterized in that: Before determining the to-be-determined probability of bird damage failure according to the current state of the first fault factor and the corresponding first preset weight, the method further includes: Obtaining the current state of the first fault factor, and determining whether the state is invalid and / or missing; If so, receiving input information, and using the input information to correct and / or supplement the state to obtain an updated current state of the first fault factor, wherein the input information includes a failed and / or missing state.

3. The method according to any one of claims 1 to 2, characterized in that: The step of determining the target bird damage fault probability according to the current fault traveling wave and the to-be-determined bird damage fault probability includes: The preset bird damage fault waveform identification model is used to output the predicted probability of bird damage fault according to the current fault traveling wave; By performing a preset operation on the predicted bird damage failure probability and the to-be-determined bird damage failure probability, a target bird damage failure probability is obtained.

4. The method according to claim 3, characterized in that The method for determining the preset bird damage fault waveform identification model includes: Acquire historical power grid fault data, wherein the historical power grid fault data includes time domain characteristic data and frequency domain characteristic data of bird damage fault traveling waves under multiple bird damage fault types; Supplementing the historical power grid fault data by using oversampling technology to obtain balanced training sample data; The initial deep learning model is trained using balanced training sample data and the deep forest algorithm to obtain a preset bird damage fault waveform recognition model.

5. The method according to claim 1, characterized in that The first fault factor in the fault-related information includes time, post-fault reclosing information, transmission line phase fault information, visualization information, preset bird damage level in the current area, meteorological information and line voltage level; The preset bird damage level of the current area is the risk level of bird damage failure in the current area, and the visualization information is the bird situation in the current area.

6. The method according to claim 1, characterized in that After determining the probability of bird damage failure to be determined according to the current state of the first fault factor and the corresponding first preset weight, the method includes: If the to-be-determined bird damage failure probability is greater than or equal to a preset threshold, the to-be-determined bird damage failure probability is determined as a target bird damage failure probability.

7. A bird damage fault diagnosis device, characterized in that: include: A fault-related information determination module, used to determine fault-related information, wherein the fault-related information includes a plurality of first fault factors associated with the bird damage fault; A failure probability determination module to be determined, used to determine the failure probability of bird damage to be determined according to the current state of the first failure factor and the corresponding first preset weight; A target fault probability determination module is used to determine a target bird damage fault probability according to a current fault traveling wave and the bird damage fault probability to be determined if the to-be-determined bird damage fault probability is less than a preset threshold; The module for determining the failure probability to be determined includes: A summing and elimination information determination unit, configured to determine a first sum value of a first preset weight corresponding to the current state of the first fault factor, and determine fault elimination information, wherein the fault elimination information includes a plurality of second fault factors associated with eliminating the bird damage fault; The to-be-determined fault probability determination unit is used to determine a second sum value of a second preset weight corresponding to the current state of the second fault factor, and determine the sum of the first sum value and the second sum value as the to-be-determined bird damage fault probability.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the bird damage fault diagnosis method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the bird damage fault diagnosis method according to any one of claims 1 to 6 when executed.

Images