A method, device, equipment and storage medium for diagnosing external damage faults during construction

Abstract

The present invention discloses a construction external failure fault diagnosis method, device, equipment and storage medium; the method comprises: acquiring fault information, identifying the fault information through a fault identification model to obtain identification result information, and determining the fault type based on the identification result information and first environmental monitoring information; when the fault type belongs to a non-lightning fault, determining whether the fault type belongs to a metallic fault by performing feature analysis on the fault waveform information in the fault information, and determining whether the fault type belongs to a non-natural disaster fault through second environmental monitoring information; when the fault type belongs to a metallic fault and a non-natural disaster fault, determining the probability of the fault being a construction external failure fault based on the fault information and the second environmental monitoring information according to a preset construction external failure fault correlation factor analysis rule, so as to accurately analyze and determine the probability of the occurrence of a construction external failure fault, and improve the accuracy and reliability of line fault diagnosis.

Description

Technical Field

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

[0002] As an important part of the power system, the operating state of transmission lines is directly related to the stability and reliability of the power grid. However, during actual operation, transmission lines will inevitably be affected by various external factors, leading to faults. Therefore, effective fault diagnosis of transmission lines is of great significance.

[0003] In the current field of diagnosing external damage faults in transmission line construction, the technical status presents a diversified development trend. Commonly used technical means include infrared thermal imaging, UAV inspection, and intelligent sensor monitoring, etc. These technologies have played an active role in improving the efficiency and accuracy of fault detection. However, in the face of the increasingly complex power grid environment and diverse fault types, the existing diagnostic technologies still face many challenges. First, at present, some online monitoring devices have not fully covered the extraction and application of typical characteristic parameters of external damage faults in line construction, and further exploration is still needed. Second, the common factors causing external damage faults in construction have not been clearly and uniformly divided, which is likely to result in a low accuracy rate of judging external damage faults in construction. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for diagnosing external damage faults in construction to solve the problem of low accuracy rate in diagnosing external damage faults in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides a method for diagnosing external damage faults in construction, including:

[0006] Obtaining fault information, identifying the fault information through a fault identification model to obtain identification result information, and determining the fault type based on the identification result information and first environmental monitoring information;

[0007] When the fault type belongs to non-lightning strike faults, determining whether the fault type belongs to metallic faults by analyzing the fault waveform information in the fault information, and determining whether the fault type belongs to non-natural disaster faults through second environmental monitoring information;

[0008] When the fault type belongs to metallic faults and non-natural disaster faults, then based on the fault information and the second environmental monitoring information, according to the preset judgment rule of construction external damage fault correlation factors, determining the probability that the fault is an external damage fault in construction.

[0009] Optionally, the obtaining of the fault information and the identification of the fault information through a fault identification model to obtain identification result information include:

[0010] When the protection action information is detected, obtain the fault information;

[0011] Extract and analyze the time-frequency domain characteristics of the fault waveform information in the fault information based on the fault identification model to determine the identification result information.

[0012] Optionally, the method further includes:

[0013] Construct a fault identification model based on the SMOTE (Synthetic Minority Oversampling Technique) algorithm and the deep forest algorithm;

[0014] Train the initial fault identification model through a historical fault data set to obtain the trained fault identification model.

[0015] Optionally, the construction external damage correlation factors include at least one of the following: visualization information, fault phase information, fault time, and meteorological information, where the visualization information and the fault time are determined through the fault information, the fault phase information is determined through the fault waveform information, and the meteorological information is determined through the second environmental monitoring information;

[0016] The preset construction external damage fault correlation factor judgment rules include: key factor judgment rules, coupling factor judgment rules, and exclusion factor judgment rules.

[0017] Optionally, based on the fault information and the second environmental monitoring information, according to the preset construction external damage fault correlation factor judgment rules, determine the probability of a construction external damage fault diagnosis, including:

[0018] Based on the fault information and the second environmental monitoring information, determine the construction external damage correlation factor information corresponding to the fault;

[0019] Judge whether the construction external damage correlation factor information conforms to the key factor judgment rules;

[0020] If it conforms, determine that the fault is a construction external damage fault;

[0021] If it does not conform, based on the construction external damage correlation factor information, through the coupling factor judgment rules, determine the first probability value that the fault is a construction external damage fault;

[0022] Based on the construction external damage correlation factor information, update the first probability value through the exclusion factor judgment rule to determine the second probability value that the fault is a construction external damage fault;

[0023] Determine the probability value that the fault is a construction external damage fault based on the second probability value.

[0024] Optionally, determining the probability value that the fault is a construction external damage fault based on the second probability value includes:

[0025] Based on the fault identification model, obtain the third probability value that the fault is a construction external damage fault;

[0026] Based on the third probability value and the second probability value, determine the probability value that the fault is a construction external damage fault.

[0027] In a second aspect, an embodiment of the present invention provides a construction external damage fault diagnosis device, including:

[0028] An acquisition module, configured to acquire fault information, identify the fault information through a fault identification model to obtain identification result information, and determine the fault type based on the identification result information and the first environmental monitoring information;

[0029] A judgment module, configured to, when the fault type belongs to non-lightning strike faults, determine whether the fault type belongs to metallic faults by performing feature analysis on the fault waveform information in the fault information, and determine whether the fault type belongs to non-natural disaster faults through the second environmental monitoring information;

[0030] A determination module, configured to, when the fault type belongs to metallic faults and non-natural disaster faults, then determine the probability that the fault is a construction external damage fault based on the fault information and the second environmental monitoring information according to a preset construction external damage fault correlation factor judgment rule.

[0031] Optionally, the determination module is specifically configured to:

[0032] Based on the fault information and the second environmental monitoring information, determine the construction external damage correlation factor information corresponding to the fault;

[0033] Judge whether the construction external damage correlation factor information conforms to the key factor judgment rule;

[0034] If it conforms, determine that the fault is a construction external damage fault;

[0035] If it does not conform, based on the construction external damage correlation factor information, determine the first probability value that the fault is a construction external damage fault through the coupling factor judgment rule;

[0036] Based on the information of the construction external damage related factors, through the exclusion factor research and judgment rules, update the first probability value to determine the second probability value that the fault is a construction external damage fault;

[0037] Based on the second probability value, determine the probability value that the fault is a construction external damage fault.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device, and the electronic device includes:

[0039] At least one processor; and a memory communicatively connected to the at least one processor;

[0040] 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 construction external damage fault diagnosis method according to any embodiment of the present invention.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium, and the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the construction external damage fault diagnosis method according to any embodiment of the present invention when executed by a processor.

[0042] The technical solution of the embodiment of the present invention obtains fault information, identifies the fault information through a fault identification model to obtain identification result information, determines the fault type based on the identification result information and the first environmental monitoring information; when the fault type belongs to a non-lightning strike type fault, determines whether the fault type belongs to a metallic fault by performing feature analysis on the fault waveform information in the fault information, and determines whether the fault type belongs to a non-natural disaster fault through the second environmental monitoring information; when the fault type belongs to a metallic fault and a non-natural disaster fault, then based on the fault information and the second environmental monitoring information, according to the preset research and judgment rules of the construction external damage fault related factors, determines the probability that the fault is a construction external damage fault, solves the problem of low accuracy in diagnosing construction external damage faults in the prior art, can accurately analyze and determine the probability of occurrence of construction external damage faults, and improves the accuracy and reliability of line fault diagnosis.

[0043] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for description in the embodiments. Obviously, the 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 drawings can be obtained based on these drawings.

[0045] Figure 1 It is a flowchart of a method for diagnosing construction external damage faults provided in Embodiment 1 of the present invention;

[0046] Figure 2 It is a flowchart of a method for diagnosing construction external damage faults provided in Embodiment 2 of the present invention;

[0047] Figure 3 It is an overall flowchart of a method for diagnosing construction external damage faults provided in Embodiment 2 of the present invention;

[0048] Figure 4 It is a schematic structural diagram of a device for diagnosing construction external damage faults provided in Embodiment 3 of the present invention;

[0049] Figure 5 It shows a schematic structural diagram of an electronic device that can be used to implement the embodiments of the present invention. Detailed implementation manners

[0050] In order to enable those skilled in the art of the present technology 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 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.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above 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 used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes 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.

[0052] Embodiment 1

[0053] Figure 1 The figure is a flowchart of a construction external damage fault diagnosis method provided in the first embodiment of the present invention. This embodiment is applicable to the situation of power transmission line fault diagnosis. This method can be executed by a construction external damage fault diagnosis device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. As Figure 1 shown, the method includes:

[0054] S110. Obtain fault information, identify the fault information through a fault identification model to obtain identification result information, and determine the fault type based on the identification result information and the first environmental monitoring information.

[0055] Among them, the fault information may refer to the information generated when a fault occurs in a power transmission line. For example, the fault waveform generated when a fault occurs in a power transmission line, the time when the power transmission line fails, etc. The fault identification model may refer to a model that determines the fault type by analyzing and identifying the fault waveform. The identification result information may refer to the fault type to which the fault belongs. Currently, the fault types of power transmission lines can be divided into two categories: lightning strike and non-lightning strike; among them, the non-lightning strike category includes: construction external damage faults, bird damage, wildfire faults, wind deviation faults, etc. The first environmental monitoring information may refer to lightning monitoring information.

[0056] Specifically, when a fault occurs in a power transmission line, the fault waveform, fault time, etc. of the fault can be obtained through a dispatching device. Inputting the fault waveform into the fault identification model for analysis and identification can determine the fault type to which the fault belongs. Determine whether the fault type is a lightning strike or a non-lightning strike based on the fault type output by the fault identification model and the lightning monitoring information; for example, if the fault type output by the fault identification model is non-lightning strike and the lightning monitoring information is that there is no lightning, it is determined that the fault type is 100% a non-lightning strike fault. If the fault type output by the fault identification model is lightning strike and the lightning monitoring information is that there is lightning, it is determined that the fault type is 100% a lightning strike fault. Ignore the situation where the fault type output by the fault identification model is inconsistent with the lightning monitoring information.

[0057] In this embodiment, by obtaining fault information, inputting the fault waveform in the fault information into the fault identification model for identification, outputting the fault type to which the fault belongs, and determining whether the fault type is a lightning strike or a non-lightning strike based on the fault type output by the fault identification model and the lightning monitoring information, the accuracy and reliability of the output line fault diagnosis are effectively improved.

[0058] S120. When the fault type belongs to the non-lightning strike fault category, determine whether the fault type belongs to a metallic fault by performing feature analysis on the fault waveform information in the fault information, and determine whether the fault type belongs to a non-natural disaster fault through the second environmental monitoring information.

[0059] Among them, the second environmental monitoring information may refer to meteorological monitoring information such as heavy rain, typhoon, and strong wind disasters.

[0060] Specifically, when it is determined that the fault type belongs to non-lightning strike faults, feature extraction can be performed on the fault waveform information in the fault information, for example, amplitude characteristics, phase characteristics, and frequency characteristics; then transient component analysis and traveling wave characteristic analysis are carried out. Finally, through a preset judgment rule, for example, if the amplitude of the fault phase voltage is lower than a certain threshold, and the phase difference between the fault phase and the non-fault phase exceeds a certain angle, and at the same time the transient component decay time constant is less than a certain value, it can be preliminarily judged as a metallic fault. Or, through a pre-trained recognition model, it can be directly determined whether the fault type belongs to a metallic fault, for example, a fault identification model. If the second environmental monitoring information indicates the existence of heavy rain, typhoon, and strong wind disasters, it is determined that the fault type belongs to a natural disaster fault; if the second environmental monitoring information indicates the non-existence of heavy rain, typhoon, and strong wind disasters, it is determined that the fault type belongs to a non-natural disaster fault.

[0061] In this embodiment, by performing feature analysis on the fault waveform information in the fault information again, it can be determined whether the fault type belongs to a metallic fault, and by using the second environmental monitoring information, it can be determined whether the fault type belongs to a non-natural disaster fault. Through precise analysis, the accuracy and reliability of line fault diagnosis are further improved.

[0062] S130: When the fault type belongs to a metallic fault and a non-natural disaster fault, then based on the fault information and the second environmental monitoring information, according to the preset research and judgment rule of the construction external damage fault correlation factor, determine the probability that the fault is a construction external damage fault.

[0063] Among them, the preset research and judgment rule of the construction external damage fault correlation factor may refer to the weight calculation rule for the correlation factor of the construction external damage fault type set in advance according to historical operation and maintenance data. Further, this research and judgment rule can be dynamically adjusted according to the update of historical operation and maintenance data.

[0064] Specifically, more than 90 correlation factors related to the fault type are sorted out in advance, and for the construction external damage fault type, a typical fault factor library is established, and the research and judgment rule of the construction external damage fault correlation factor is set based on historical operation and maintenance data. When the fault type belongs to a metallic fault and a non-natural disaster fault, then according to the preset research and judgment rule of the correlation factor for the construction external damage fault type, by calculating different weight values for the fault waveform, fault time, visualization information, and meteorological monitoring information, etc., determine the probability value that the fault is a construction external damage fault, realizing precise analysis and determination of the probability of occurrence of a construction external damage fault, and effectively improving the accuracy and reliability of line fault diagnosis.

[0065] In this embodiment, by obtaining fault information, identifying the fault information through a fault identification model to obtain identification result information, and determining the fault type based on the identification result information and first environmental monitoring information; when the fault type belongs to non-lightning strike faults, determining whether the fault type belongs to metallic faults by performing feature analysis on the fault waveform information in the fault information, and determining whether the fault type belongs to non-natural disaster faults through second environmental monitoring information; by sorting out and refining the judgment factors for construction external damage and setting the judgment rules for the associated factors of construction external damage faults based on historical operation and maintenance data, when the fault type belongs to metallic faults and non-natural disaster faults, different weight values can be calculated for the fault information and the second environmental monitoring information according to the preset judgment rules for the associated factors of construction external damage faults, so as to obtain the probability value of the fault being a construction external damage fault, solving the problem of low diagnostic accuracy of construction external damage faults in the prior art, being able to accurately analyze and determine the probability of occurrence of construction external damage faults, and improving the accuracy and reliability of line fault diagnosis.

[0066] Optionally, the obtaining of the fault information and identifying the fault information through a fault identification model to obtain identification result information includes:

[0067] When detecting protection action information, obtaining the fault information;

[0068] Performing time-frequency domain feature extraction and analysis on the fault waveform information in the fault information based on the fault identification model to determine the identification result information.

[0069] Among them, the protection action information may refer to the fault signal sent by the protection device; the time-frequency domain features of the fault waveform may include: 16 time domain features, 13 frequency domain features, 6 EWF component information entropies, weighted energy entropy, EWF4 sample entropy, and EWF1 root mean square value, etc., a total of 38 features.

[0070] Specifically, when a fault occurs in the transmission line, the protection device will send a fault signal to the dispatching device, and the dispatching device will receive and obtain the fault information of the fault. Input the fault waveform information in the fault information into the fault identification model, and through the time-frequency domain feature extraction of the fault waveform by the fault identification model, 38 feature values including 16 time domain features, 13 frequency domain features, 6 EWF component information entropies, weighted energy entropy, EWF4 sample entropy, and EWF1 root mean square value can be obtained; by comparing and analyzing each feature value with the historical fault data set, the fault type to which the fault belongs is determined.

[0071] In this embodiment, when the protection action information is detected, the dispatching device is used to receive and obtain the fault information; based on the fault identification model, the time-frequency domain features of the fault waveform information in the fault information are extracted, and each extracted feature value is compared and analyzed with the historical fault data set to determine the fault type to which the fault belongs. Through precise analysis, the accuracy and reliability of the output line fault diagnosis are effectively improved.

[0072] Optionally, this embodiment may further include:

[0073] Construct an initial fault identification model based on the SMOTE algorithm and the deep forest algorithm;

[0074] Train the initial fault identification model with the historical fault data set to obtain the trained fault identification model.

[0075] Among them, the SMOTE algorithm can refer to solving the problem of data class imbalance by synthesizing new minority class samples. The deep forest algorithm can refer to simulating the hierarchical feature extraction ability of deep learning and realizing hierarchical feature extraction by constructing a multi-layer random forest structure. The historical fault data set can refer to a fault transient waveform data set established based on historical output line fault information.

[0076] Specifically, the time-frequency features of the voltage and current waveforms in the historical fault data set can be extracted, and the fault classification can be performed according to the extracted time-frequency features to form a fault waveform data set of different fault types: the unbalanced data set in the fault waveform data set is clustered by the clustering algorithm, and the unbalanced data set after clustering is data-expanded by SMOTE sampling; the fault sub-data set is formed according to the balanced data set and the expanded unbalanced data set: the trained fault identification model is obtained through the fault sub-data set and based on the deep forest algorithm for model training.

[0077] In this embodiment, an initial fault identification model is constructed based on the SMOTE algorithm and the deep forest algorithm; the initial fault identification model is trained with the historical fault data set to obtain the trained fault identification model; the trained fault identification model is used to diagnose the fault type, which has good accuracy and effectiveness, and provides a high-accuracy and high-coverage diagnosis for transmission line faults.

[0078] Optionally, the construction external damage correlation factors include at least one of the following: visualization information, fault phase information, fault time, and meteorological information, where the visualization information and the fault time are determined by the fault information, the fault phase information is determined by the fault waveform information, and the meteorological information is determined by the second environmental monitoring information;

[0079] The preset judgment rules for construction external damage fault correlation factors include: key factor judgment rules, coupling factor judgment rules, and exclusion factor judgment rules.

[0080] Among them, the visual information can refer to the information on whether construction machinery alarms are displayed in the visual interface; the fault phase information can refer to the information that the fault phase is the lower phase or the side phase; the fault time can refer to the time when the construction external damage fault occurs, for example, 5 o'clock - 23 o'clock; the meteorological information can refer to heavy rain, typhoon, and strong wind disaster information. The key factor judgment rule can refer to the judgment rule that can determine with 100% certainty that a construction external damage fault has occurred; the coupling factor judgment rule can refer to the judgment rule that can determine the probability value of the occurrence of a construction external damage fault, and this probability value is greater than 0% and less than 100%; the exclusion factor judgment rule can refer to the judgment rule for excluding other faults, and other faults can refer to other faults except for construction external damage faults.

[0081] Specifically, the visual information and the fault time can be directly determined through the fault information, the fault phase information is determined by analyzing the fault waveform in the fault information, and the meteorological information can be directly determined through the second environmental monitoring information. By pre-combing more than 90 correlation factors related to the fault type, and for the construction external damage fault type, establishing its typical fault factor library, and setting the key factor judgment rule, coupling factor judgment rule, and exclusion factor judgment rule for construction external damage faults based on historical operation and maintenance data.

[0082] Exemplarily, the key factor judgment rule can be: Visualization shows construction machinery alarm + Fault phase is the lower phase or the side phase + Meteorological information does not have heavy rain, typhoon, strong wind disaster warnings + Fault time: 5 o'clock - 23 o'clock (100% certain that the fault is a construction external damage fault)

[0083] The coupling factor judgment rule can be:

[0084] Visualization shows construction machinery alarm + Meteorological information does not have heavy rain, typhoon, strong wind disaster warnings + Fault phase is the lower phase / side phase (the probability value of determining that the fault is a construction external damage fault is 80%);

[0085] Visualization shows construction machinery alarm + Meteorological information does not have heavy rain, typhoon, strong wind disaster warnings + Fault time: 5 o'clock - 23 o'clock (the probability value of determining that the fault is a construction external damage fault is 80%);

[0086] Fault phase is the lower phase or the side phase + Meteorological information does not have heavy rain, typhoon, strong wind disaster warnings + Fault time: 5 o'clock - 23 o'clock (the probability value of determining that the fault is a construction external damage fault is 50%);

[0087] Visualization shows construction machinery alarm + Meteorological information does not have heavy rain, typhoon, strong wind disaster warnings (the probability value of determining that the fault is a construction external damage fault is 50%);

[0088] Visualization shows construction machinery alarms (the probability value of determining the fault as an external damage fault during construction is 40%), the fault phase or side phase (the probability value of determining the fault as an external damage fault during construction is 15%), the fault time: 5 o'clock - 23 o'clock (the probability value of determining the fault as an external damage fault during construction is 15%), potential hazards exist at construction hazard points (the probability value of determining the fault as an external damage fault during construction is 20%), the same-tower line is out of service for maintenance (the probability value of determining the fault as an external damage fault during construction is 30%), the reclosing is unsuccessful (the probability value of determining the fault as an external damage fault during construction is 25%), and a metallic grounding fault (the probability value of determining the fault as an external damage fault during construction is 15%);

[0089] The exclusion factor judgment rule can be: disaster warning: typhoon, heavy rain, strong wind (-100%, that is, it is determined that the fault must not be an external damage fault during construction), phase-to-phase fault (-80%, that is, it is determined that the fault is not an external damage fault during construction with a probability of 80%), successful reclosing (-60%, that is, it is determined that the fault is not an external damage fault during construction with a probability of 60%), the fault line is ±800 kV or 1000 kV (-10%, that is, it is determined that the fault is not an external damage fault during construction with a probability of 10%).

[0090] In this embodiment, through the fault information and the second environmental monitoring information, the construction external damage associated factor information corresponding to the fault is determined; according to the preset key factor judgment rule, coupling factor judgment rule, and exclusion factor judgment rule for construction external damage faults, the probability of diagnosing a construction external damage fault is determined, which has good accuracy and provides a highly accurate and efficient diagnosis for transmission line faults.

[0091] Embodiment 2

[0092] Figure 2 It is a flowchart of a method for diagnosing construction external damage faults provided by Embodiment 2 of the present invention. The technical solution of this embodiment is further refined on the basis of the above embodiment. As Figure 2 shown, the method includes:

[0093] S210. Obtain fault information, identify the fault information through a fault identification model to obtain identification result information, and determine the fault type based on the identification result information and the first environmental monitoring information.

[0094] S220. When the fault type belongs to non-lightning strike faults, determine whether the fault type belongs to a metallic fault by performing feature analysis on the fault waveform information in the fault information, and determine whether the fault type belongs to non-natural disaster faults through the second environmental monitoring information.

[0095] S230. Based on the fault information and the second environmental monitoring information, determine the construction external damage associated factor information corresponding to the fault.

[0096] Among them, the information on the associated factors of construction external damage can refer to the information on the associated factors that affect the judgment of construction external damage faults.

[0097] Specifically, the information on the associated factors of construction external damage can include: fault waveform information, reclosing information, visualization information, meteorological information, fault phase information, terrain environment information, fault time season, historical fault information, hidden danger situation, etc. Among them, some information on the associated factors of construction external damage can be determined through fault information and the second environmental monitoring information. For example, fault waveform information, meteorological information, etc.; some information on the associated factors of construction external damage can be manually input, such as terrain environment information, hidden danger situation, etc.

[0098] In this embodiment, all the information on the associated factors of construction external damage corresponding to the fault can be determined through fault information, the second environmental monitoring information, and manually input information, effectively improving the coverage rate of the associated factors of construction external damage and further improving the accuracy and reliability of line fault diagnosis.

[0099] S240. Judge whether the information on the associated factors of construction external damage conforms to the key factor research and judgment rule.

[0100] Specifically, according to the visualization information, fault phase information, fault time, and meteorological information, judge whether it conforms to the situation that there is a construction machinery warning in the visualization + the fault phase is the lower phase or the side phase + there is no rainstorm, typhoon, or strong wind disaster warning in the meteorological information + the fault time: 5 o'clock - 23 o'clock.

[0101] In this embodiment, by judging the information on the associated factors of construction external damage through the key factor research and judgment rule, it can be determined whether the fault is 100% a construction external damage fault, improving the judgment coverage rate of the associated factors of construction external damage and the accuracy of construction external damage fault diagnosis.

[0102] S250. If it conforms, determine that the fault is a construction external damage fault.

[0103] In this embodiment, if the information on the associated factors of construction external damage conforms to the key factor research and judgment rule, it is directly determined that the fault is 100% a construction external damage fault.

[0104] S260. If it does not conform, based on the information on the associated factors of construction external damage, through the coupling factor research and judgment rule, determine the first probability value that the fault is a construction external damage fault.

[0105] Among them, the first probability value can refer to the probability determined through the coupling factor research and judgment rule.

[0106] In this embodiment, all the construction external damage associated factor information corresponding to the fault can be determined through fault information, second environmental monitoring information, and manually input information. The coupling factor research and judgment rule is used to research and judge all the construction external damage associated factor information corresponding to the fault to determine the first probability value that the fault is a construction external damage fault, improving the judgment coverage rate of the construction external damage associated factors and the accuracy of the construction external damage fault diagnosis.

[0107] S270. Based on the construction external damage associated factor information, through the exclusion factor research and judgment rule, update the first probability value to determine the second probability value that the fault is a construction external damage fault.

[0108] Among them, the second probability value can refer to the updated first probability value.

[0109] Specifically, after determining the first probability value, the construction external damage associated factor information can be continuously researched and judged through the exclusion factor research and judgment rule. If the construction external damage associated factor information meets the exclusion factor research and judgment rule, the corresponding negative probability is determined. The negative probability is superimposed on the first probability value to determine the second probability value that the fault is a construction external damage fault. Exemplarily, if the first probability value is 80% and the negative probability obtained through the exclusion factor research and judgment rule is -60%, the obtained second probability value is 20%. If the construction external damage associated factor information does not meet the exclusion factor research and judgment rule, the corresponding negative probability is determined to be 0.

[0110] In this embodiment, after determining the first probability value, through the exclusion factor research and judgment rule, the first probability value is updated to determine the second probability value that the fault is a construction external damage fault. By accurately analyzing and determining the probability of the construction external damage fault occurring, the accuracy and reliability of the line fault diagnosis are effectively improved.

[0111] S280. Based on the second probability value, determine the probability value that the fault is a construction external damage fault.

[0112] In this embodiment, by obtaining fault information, identifying the fault information through a fault identification model to obtain identification result information, and determining the fault type based on the identification result information and first environmental monitoring information; when the fault type belongs to non-lightning strike faults, by performing feature analysis on the fault waveform information in the fault information to determine whether the fault type belongs to metallic faults, and determining whether the fault type belongs to non-natural disaster faults through second environmental monitoring information; by sorting out and refining the judgment factors for external damage caused by construction, and setting the judgment rules for the associated factors of external damage faults caused by construction based on historical operation and maintenance data, when the fault type belongs to metallic faults and non-natural disaster faults, it is possible to judge the fault information and second environmental monitoring information according to the key factor judgment rule, coupling factor judgment rule, and exclusion factor judgment rule included in the preset judgment rules for the associated factors of external damage faults caused by construction, and then obtain the probability value of the fault being an external damage fault caused by construction. By accurately analyzing and determining the probability of an external damage fault caused by construction, the accuracy and reliability of line fault diagnosis are effectively improved.

[0113] Optionally, the determining the probability value of the fault being an external damage fault caused by construction based on the second probability value includes:

[0114] Based on the fault identification model, obtaining a third probability value that the fault is an external damage fault caused by construction;

[0115] Based on the third probability value and the second probability value, determining the probability value of the fault being an external damage fault caused by construction.

[0116] Among them, the third probability may refer to the probability value corresponding to the fault type output after the fault identification model analyzes and identifies the fault waveform.

[0117] Specifically, the weights of the third probability value and the second probability value can be preset; for example, the weight ratio of the third probability value can be preset as α, the weight ratio of the second probability value can be preset as β, the third probability value is A, the second probability value is B, then the finally obtained probability value C of the fault being an external damage fault caused by construction is C = α×A + β×B, where α + β = 1. Exemplarily, if α = 50%, β = 50%, A = 70%, B = 80%, then the finally obtained probability value of this fault being an external damage fault caused by construction is 75%.

[0118] In this embodiment, based on the fault identification model, obtaining a third probability value that the fault is an external damage fault caused by construction; by comprehensively considering the third probability value and the second probability value, determining the probability value of the fault being an external damage fault caused by construction, realizing accurate analysis and determination of the probability of an external damage fault caused by construction, and effectively improving the accuracy and reliability of line fault diagnosis.

[0119] Exemplarily, Figure 3This is the overall flowchart of a construction external break fault diagnosis method provided in the second embodiment of the present invention. As Figure 3 shown, the specific steps for performing construction external break fault diagnosis include:

[0120] 1. When protection action information is detected.

[0121] 2. Obtain distributed fault information (i.e., fault information).

[0122] 3. Based on the comprehensive distributed waveform identification result information (i.e., identification result information) and lightning monitoring information (i.e., the first environmental monitoring information), determine whether it is a non-lightning strike fault.

[0123] 4. If the fault type belongs to non-lightning strike faults, then analyze the characteristics of the distributed / replay waveforms (fault waveform information) to determine whether the fault belongs to a metallic fault, and determine whether the fault belongs to a non-natural disaster fault through the early warning and monitored meteorological disaster information (i.e., the second environmental monitoring information).

[0124] 5. If the fault type belongs to metallic faults and non-natural disaster faults, then determine the construction external break associated factor information corresponding to the fault through the fault information and the second environmental monitoring information.

[0125] 6. Determine whether the construction external break associated factor information conforms to the key factor judgment rule; if it conforms, then determine that the fault is a construction external break fault.

[0126] 7. If it does not conform, then based on the construction external break regular factor (i.e., the construction external break associated factor information corresponding to the fault determined by the fault information and the second environmental monitoring information), and the manually entered fault factor (i.e., the manually entered construction external break associated factor information), determine the first probability value of the fault being a construction external break fault through the coupling factor judgment rule.

[0127] 8. After determining the first probability value, the construction external break associated factor information can be continuously judged through the construction external break negative factor (i.e., the exclusion factor judgment rule), and the first probability value can be updated to determine the second probability value of the fault being a construction external break fault.

[0128] 9. Determine the final probability value of the fault being a construction external break fault through the construction external break distributed probability (i.e., the third probability value) determined by the distributed waveform and the second probability value.

[0129] In this embodiment, when the protection action information is detected, the distributed fault information is obtained, and whether it is a non-lightning strike fault is determined by integrating the distributed waveform identification result information and the lightning monitoring information. If the fault type belongs to the non-lightning strike fault type, then the distributed / replay waveform characteristics are analyzed to determine whether the fault belongs to a metallic fault, and whether the fault belongs to a non-natural disaster fault is determined through the early warning and monitored meteorological disaster information. If the fault type belongs to the metallic fault and non-natural disaster fault types, then the construction external damage correlation factor information corresponding to the fault is determined through the fault information and the second environmental monitoring information. It is judged whether the construction external damage correlation factor information conforms to the key factor research and judgment rule; if it conforms, it is determined that the fault is a construction external damage fault. If it does not conform, then based on the construction external damage law factor and the manually input fault factor, through the coupling factor research and judgment rule, the first probability value that the fault is a construction external damage fault is determined. After the first probability value is determined, the construction external damage correlation factor information can be further studied and judged through the construction external damage negation factor, and the first probability value is updated to determine the second probability value that the fault is a construction external damage fault. The final probability value that the fault is a construction external damage fault is determined through the construction external damage distributed probability determined by the distributed waveform and the second probability value, and by accurately analyzing and determining the probability of the occurrence of the construction external damage fault, the accuracy and reliability of the line fault diagnosis are effectively improved.

[0130] Embodiment III

[0131] Figure 4 It is a structural schematic diagram of a construction external damage fault diagnosis device provided by Embodiment III of the present invention. As Figure 4 shown, the device includes:

[0132] An acquisition module 310, configured to acquire fault information, identify the fault information through a fault identification model to obtain identification result information, and determine a fault type based on the identification result information and the first environmental monitoring information;

[0133] A judgment module 320, configured to, when the fault type belongs to the non-lightning strike fault type, determine whether the fault type belongs to a metallic fault by performing feature analysis on the fault waveform information in the fault information, and determine whether the fault type belongs to a non-natural disaster fault through the second environmental monitoring information;

[0134] A determination module 330, configured to, when the fault type belongs to the metallic fault and non-natural disaster fault types, based on the fault information and the second environmental monitoring information, determine the probability that the fault is a construction external damage fault according to a preset construction external damage fault correlation factor research and judgment rule.

[0135] Optionally, the acquisition module 310 is specifically configured to:

[0136] When the protection action information is detected, obtain the fault information;

[0137] Based on the fault identification model, extract and analyze the time-frequency domain features of the fault waveform information in the fault information to determine the identification result information.

[0138] Optionally, the device further includes: a training module, and the training module is specifically used for:

[0139] Construct an initial fault identification model based on the SMOTE algorithm and the deep forest algorithm;

[0140] Train the initial fault identification model through the historical fault data set to obtain the trained fault identification model.

[0141] Optionally, the construction external damage correlation factors include at least one of the following: visualization information, fault phase information, fault time, and meteorological information, where the visualization information and the fault time are determined through the fault information, the fault phase information is determined through the fault waveform information, and the meteorological information is determined through the second environmental monitoring information;

[0142] The preset construction external damage fault correlation factor judgment rules include: key factor judgment rules, coupling factor judgment rules, and exclusion factor judgment rules.

[0143] Optionally, the determination module 330 is specifically used for:

[0144] Based on the fault information and the second environmental monitoring information, determine the construction external damage correlation factor information corresponding to the fault;

[0145] Judge whether the construction external damage correlation factor information conforms to the key factor judgment rules;

[0146] If it conforms, determine that the fault is a construction external damage fault;

[0147] If it does not conform, based on the construction external damage correlation factor information, through the coupling factor judgment rules, determine the first probability value that the fault is a construction external damage fault;

[0148] Based on the construction external damage correlation factor information, through the exclusion factor judgment rules, update the first probability value to determine the second probability value that the fault is a construction external damage fault;

[0149] Based on the second probability value, determine the probability value that the fault is a construction external damage fault.

[0150] Optionally, the determination module 330 is specifically used for:

[0151] Based on the fault identification model, obtain a third probability value that the fault is a construction external damage fault;

[0152] Based on the third probability value and the second probability value, determine the probability value that the fault is a construction external damage fault.

[0153] The construction external damage fault diagnosis device provided by the embodiments of the present invention can execute the construction external damage fault diagnosis method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0154] Embodiment 4

[0155] Figure 5 The structural schematic diagram of an electronic device that can be used to implement the embodiments of the present invention is shown. The electronic device 10 is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0156] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by at least one processor 11, and the computer program is executed by the at least one processor 11 so that the at least one processor 11 can execute the method provided by the present invention.

[0157] The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0158] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0159] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 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 11 executes the various methods and processes described above, such as the construction external damage fault diagnosis method.

[0160] In some embodiments, the construction external 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 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the construction external damage fault diagnosis method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the construction external damage fault diagnosis method by any other suitable means (e.g., by means of firmware).

[0161] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chip (SOC) systems, 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 are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0162] The computer programs for implementing the methods 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, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0163] In the context of the present invention, a computer-readable storage medium stores computer instructions that, when executed by a processor, implement the construction external damage fault diagnosis method provided by the present invention. The computer-readable storage medium may be a tangible medium that 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 may 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 may 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, a portable computer disk, 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.

[0164] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0165] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), blockchain network, and the Internet.

[0166] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and Virtual Private Server (VPS) services.

[0167] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0168] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A construction external failure diagnosis method, characterized in that: include: Acquire fault information, identify the fault information through a fault identification model to obtain identification result information, and determine the fault type based on the identification result information and the first environment monitoring information; When the fault type belongs to a non-lightning fault, determining whether the fault type belongs to a metallic fault by performing feature analysis on the fault waveform information in the fault information, and determining whether the fault type belongs to a non-natural disaster fault by using the second environmental monitoring information; When the fault type belongs to a metallic fault and a non-natural disaster fault, based on the fault information and the second environmental monitoring information, according to the preset construction external failure fault correlation factor analysis rule, the probability that the fault is a construction external failure fault is determined, and the preset construction external failure fault correlation factor analysis rule includes: a key factor analysis rule, a coupling factor analysis rule, and an exclusion factor analysis rule; Wherein, based on the fault information and the second environmental monitoring information, according to the preset construction external failure fault correlation factor analysis rule, determining the probability that the fault is a construction external failure fault includes: Based on the fault information and the second environment monitoring information, determining the construction external damage correlation factor information corresponding to the fault; Determine whether the construction external failure correlation factor information complies with the key factor analysis rules; If it is true, it is determined that the fault is a construction failure; If not, based on the construction external failure correlation factor information and through the coupling factor analysis rule, determine the first probability value of the fault being a construction external failure fault; Based on the construction external failure associated factor information, the first probability value is updated through the exclusion factor analysis rule to determine a second probability value that the fault is a construction external failure fault; A probability value that the fault is a construction failure fault is determined based on the second probability value.

2. The method according to claim 1, characterized in that The acquiring of fault information and identifying the fault information by a fault identification model to obtain identification result information includes: When protection action information is detected, obtaining the fault information; Based on the fault identification model, time-frequency domain features of the fault waveform information in the fault information are extracted and analyzed to determine the identification result information.

3. The method according to claim 1, characterized in that Also includes: Construct an initial fault identification model based on the SMOTE algorithm and deep forest algorithm; The initial fault identification model is trained by using a historical fault data set to obtain the trained fault identification model.

4. The method according to claim 1, characterized in that: The construction external failure correlation factors include at least one of the following: visualization information, fault phase information, fault time and meteorological information, wherein the visualization information and the fault time are determined by the fault information, the fault phase information is determined by the fault waveform information, and the meteorological information is determined by the second environment monitoring information.

5. The method according to claim 1, characterized in that The determining, based on the second probability value, a probability value of the fault being a construction failure fault includes: Based on the fault identification model, obtaining a third probability value that the fault is a construction failure; Based on the third probability value and the second probability value, a probability value that the fault is a construction failure is determined.

6. A construction external failure diagnosis device, characterized in that: include: An acquisition module, used to acquire fault information, identify the fault information through a fault identification model to obtain identification result information, and determine the fault type based on the identification result information and the first environment monitoring information; A judgment module, used for determining whether the fault type is a metallic fault by performing feature analysis on the fault waveform information in the fault information when the fault type is a non-lightning fault, and determining whether the fault type is a non-natural disaster fault by using the second environmental monitoring information; A determination module, for determining the probability that the fault is a construction external failure fault based on the fault information and the second environmental monitoring information and according to a preset construction external failure fault correlation factor judgment rule when the fault type belongs to a metallic fault and a non-natural disaster fault, wherein the preset construction external failure fault correlation factor judgment rule includes: a key factor judgment rule, a coupling factor judgment rule, and an exclusion factor judgment rule; Identify modules, specifically for: Based on the fault information and the second environment monitoring information, determining the construction external damage correlation factor information corresponding to the fault; Determine whether the construction external failure correlation factor information complies with the key factor analysis rules; If it is true, it is determined that the fault is a construction failure; If not, based on the construction external failure correlation factor information and through the coupling factor analysis rule, determine the first probability value of the fault being a construction external failure fault; Based on the construction external failure associated factor information, the first probability value is updated through the exclusion factor analysis rule to determine a second probability value that the fault is a construction external failure fault; A probability value that the fault is a construction failure fault is determined based on the second probability value.

7. The device according to claim 6, characterized in that The determination module is specifically used for: Based on the fault information and the second environment monitoring information, determining the construction external damage correlation factor information corresponding to the fault; Determine whether the construction external failure correlation factor information complies with the key factor analysis rules; If it is true, it is determined that the fault is a construction failure; If not, based on the construction external failure correlation factor information, a first probability value of the fault being a construction external failure is determined through a coupling factor analysis rule; Based on the construction external failure associated factor information, the first probability value is updated by excluding factor analysis rules to determine a second probability value that the fault is a construction external failure fault; A probability value that the fault is a construction failure fault is determined based on the second probability value.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled 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 construction external failure fault diagnosis method described in any one of claims 1-5.

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 construction external failure fault diagnosis method described in any one of claims 1-5 when executed.

Images