Power transformation equipment monitoring system
Through real-time monitoring of substation equipment monitoring system and machine learning model prediction, the leakage risk caused by monitoring delay in wet weather is solved, and the grid stability and power supply continuity are improved.
Patent Information
- Application Number
- CN202410980989.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-08
AI Technical Summary
In humid weather, the monitoring delay of substation equipment leads to an increase in the risk of leakage, which in turn affects the stability of power supply.
A substation equipment monitoring system was designed, including substation equipment information collection module, historical data collection module, historical data analysis module and real-time information collection module. Through machine learning models, the impact of faults is predicted, humidity and environmental parameters are monitored in real time, and faults are generated. Analyze the model, predict potential failures and develop maintenance strategies.
It effectively reduces the possibility of equipment failure, reduces power outage time, improves grid stability and power supply continuity, and reduces the risk of power outage accidents.
Smart Images

Figure CN118920696A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of substation equipment monitoring, and in particular to a substation equipment monitoring system. Background Art
[0002] Substations provide an indispensable source of electricity for human life. Their function is similar to that of the human heart, responsible for converting the high-voltage electricity generated by power plants into low-voltage electricity suitable for transmission to users. Substation equipment is a key node in the power system, responsible for the transmission, distribution and conversion of electricity. It is the basis for power supply for various production, life and service facilities in modern society. It is responsible for the reasonable distribution and regulation of the electricity transmitted from power plants to ensure that the electricity needs of different regions are met. Whether it is industrial production, commercial services or family life, it depends on a stable and reliable power supply.
[0003] However, in the current humid weather, most of the monitoring of discharge impact in humid environments is carried out through real-time water immersion detection, which has a monitoring delay on the substation equipment. In particular, the impact on substation equipment is greater in humid weather. Delayed detection will cause a more serious leakage risk in the equipment, which will lead to instability in the power supply stability of the substation in humid weather. Summary of the invention
[0004] The purpose of the present invention is to provide a substation monitoring system to solve the shortcomings of the background technology.
[0005] In order to achieve the above-mentioned purpose, the substation equipment monitoring system includes a substation equipment information collection module, a substation historical data collection module, a substation historical data analysis module, a real-time information collection module and a substation equipment status monitoring module;
[0006] Substation equipment information collection module: mainly used to pre-collect the equipment information of each monitoring line set in the substation, and send the equipment information to the substation historical data collection module;
[0007] Substation historical data collection module: used to collect historical data of equipment information of each substation equipment on the monitoring line, and send the collected historical data of equipment information to the substation historical data analysis module;
[0008] Substation historical data analysis module: used to generate a fault analysis model for evaluating the impact of substation equipment failures based on the historical data of each device information, and send the trained fault analysis model to the substation equipment status monitoring module;
[0009] Real-time information collection module: used to collect the fault cause data of each device in real time and send the fault cause data to the substation equipment status monitoring module;
[0010] Substation equipment status monitoring module: used to predict future fault impacts based on the attribute values of real-time fault cause data.
[0011] In a preferred embodiment, the monitoring line is a line of substation equipment with sensors inside the substation, and the equipment information includes equipment identification, function, fault condition and fault impact range of each substation equipment on the monitoring line.
[0012] In a preferred embodiment, the device identifier is a unique identifier or number of each substation, which is used to uniquely distinguish the substation; the functions include but are not limited to raising and lowering the voltage to achieve power transmission and distribution, controlling the current flow in the circuit, cutting off the current when a fault occurs, isolating the equipment and cutting off the current when the circuit is operating normally, improving the power factor of the system, measuring current and voltage and converting them into signals suitable for measuring and protecting the equipment, overcurrent protection, overvoltage protection, undervoltage protection, real-time monitoring and remote control of the system; the fault conditions include but are not limited to the operating status, health status and known fault information of the equipment; the fault impact range is the impact range of the equipment failure on the operation of the substation, including but not limited to the affected areas, equipment, functions, and the safety hazards or production risks caused.
[0013] In a preferred embodiment, the step of collecting historical data of the device information includes:
[0014] Step S101: sorting the device information according to the function, and numbering the substation equipment according to the sorting information, and marking the number as k, k = 1, 2, 3 ... K, K is the number of the device information;
[0015] Step S102: according to the device information k, all fault cause data of the device information k and the device information k-1 in wet weather are collected, and for each fault cause data, the fault impact on the device information k caused by the fault cause data is collected, and a determination rule before the fault impact is generated is set in advance according to the relationship between the fault impact and the fault cause data;
[0016] Step S103: collecting attribute values of each fault cause and fault impact caused by each piece of equipment information k and using them as historical data of the equipment information.
[0017] In a preferred embodiment, the sorting logic of the sorting information is:
[0018] The sorting information is sorted in the order of function - equipment location line - equipment setting, and the equipment location line is classified in alphabetical order.
[0019] In a preferred embodiment, the determination rule before the fault impact is generated is:
[0020] Each fault cause includes humidity, temperature and discharge intensity around the substation equipment in humid weather, and analysis constants α, β and γ are set. A fault cause coefficient H is generated based on the analysis constants α, β and γ. The generation formula of the fault cause coefficient H is H=α*(Sc-Sj)+β*(Tc-Tj)+γ*(Qc-Qj), wherein Sc is the humidity around the substation equipment, Sj is the standard value of humidity around the substation equipment, Tc is the temperature around the substation equipment, Tj is the standard value of temperature around the substation equipment, Qc is the discharge intensity around the substation equipment, Qj is the standard value of discharge intensity around the substation equipment, and α, β and γ are respectively the influence analysis parameters of humidity, temperature and discharge intensity around the substation equipment;
[0021] An analysis threshold Hy is set, and the fault cause coefficient H is compared with the analysis threshold Hy. If the fault cause coefficient H is greater than or equal to the analysis threshold Hy, a determination of the fault impact is generated; if the fault cause coefficient H is less than the analysis threshold Hy, no determination of the fault impact is generated.
[0022] Step S103: collecting attribute values of each fault cause and fault impact caused by each piece of equipment information k and using them as historical data of the equipment information.
[0023] In a preferred embodiment, the step of generating the fault analysis module includes:
[0024] Step S201: Based on each device information k, the attribute value of the fault cause data in the historical data of the device information is used as the input of the fault analysis model, the attribute value of the fault impact is used as the output of the fault analysis model, the fault impact occurring in each device information is used as the prediction target, and the prediction accuracy of the machine learning model is used as the training target. The fault impact is the location, impact range and functional impact of the affected substation equipment;
[0025] Step S202: setting a prediction accuracy threshold ky, and training a fault analysis model for each device information k;
[0026] Step S203: When the prediction accuracy of the fault analysis model reaches the prediction accuracy threshold ky, stop training, and mark the fault analysis model of the trained device information k as Mk. The machine learning model can be a support vector machine, a linear model or a decision tree.
[0027] In a preferred embodiment, the fault cause data is data on the impact of failure of each device information in wet weather, including but not limited to the surrounding temperature, humidity and discharge intensity of the substation equipment;
[0028] The generation step of the fault analysis module includes:
[0029] Step S201: Based on each device information k, the attribute value of the fault cause data in the historical data of the device information is used as the input of the fault analysis model, the attribute value of the fault impact is used as the output of the fault analysis model, the fault impact occurring in each device information is used as the prediction target, and the prediction accuracy of the machine learning model is used as the training target. The fault impact is the location, impact range and functional impact of the affected substation equipment;
[0030] Step S202: setting a prediction accuracy threshold ky, and training a fault analysis model for each device information k;
[0031] Step S203: When the prediction accuracy of the fault analysis model reaches the prediction accuracy threshold ky, stop training, and mark the fault analysis model of the trained device information k as Mk. The machine learning model can be a support vector machine, a linear model or a decision tree.
[0032] Furthermore, the real-time information collection module is used to collect the fault cause data of each device information in real time;
[0033] The fault cause data is data on the impact of failure of each device in wet weather, including but not limited to the surrounding temperature, humidity and discharge intensity of the substation equipment;
[0034] Preferably, the real-time information collection module collects data on the impact of failures of various equipment in wet weather, including:
[0035] Step S301: collecting and determining fault impact data according to the determination rule set in step 102 before the fault impact is generated;
[0036] Step S302: Compare the fault cause coefficient H with the analysis threshold Hy. If the fault cause coefficient H is greater than or equal to the analysis threshold Hy, the fault impact is determined and generated, and step S303 is performed. If the fault cause coefficient H is less than the analysis threshold Hy, the fault impact is not determined and generated, and no data processing is performed.
[0037] Step S303: Based on the device information k, collect the attribute values of the real-time fault cause data.
[0038] Furthermore, the substation equipment status monitoring module analyzes the attribute values of the received fault cause data, inputs the attribute values of the fault cause data into a fault analysis model, and the fault analysis model outputs a predicted fault impact.
[0039] In the above technical solution, the technical effects and advantages provided by the present invention are:
[0040] By real-time monitoring of the humidity and other environmental parameters around the substation equipment, the present invention can promptly discover potential failure risks caused by humid weather, take corresponding preventive measures, and reduce the possibility of equipment failure. In combination with historical data and machine learning models, it can analyze the failure mode and impact range of equipment in humid weather and formulate targeted maintenance strategies, so that the equipment can be maintained and serviced in a timely manner to reduce the damage to the equipment caused by humid weather. Through fault prediction and preventive maintenance, the power outage time caused by equipment failure can be reduced, the stability and reliability of the power grid can be improved, the continuity and stability of power supply can be guaranteed, and the risk of power outage accidents can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0042] Figure 1 The module flow chart of a substation equipment monitoring system of the present invention is shown in FIG. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0044] See also Figure 1 As shown, this embodiment proposes a substation equipment monitoring system, which includes a substation equipment information collection module, a substation historical data collection module, a substation historical data analysis module, a real-time information collection module and a substation equipment status monitoring module, and each module is connected by an electrical and / or wireless network;
[0045] The substation equipment information collection module is mainly used to pre-collect equipment information of each monitoring line set in the substation;
[0046] The monitoring line is a line of a substation equipment equipped with sensors in the substation;
[0047] The equipment information includes the equipment identification, function, fault condition and fault impact range of each substation equipment on the monitoring line;
[0048] Preferably, the device identifier is a unique identifier or number of each substation device, which is used to uniquely distinguish the substation device;
[0049] The functions include but are not limited to raising and lowering voltage to achieve power transmission and distribution, controlling the flow of current in the circuit, cutting off the current when a fault occurs, isolating the equipment and cutting off the current when the circuit is operating normally, improving the power factor of the system, measuring current and voltage and converting them into signals suitable for measuring and protecting equipment, overcurrent protection, overvoltage protection, undervoltage protection, real-time monitoring and remote control of the system;
[0050] The fault condition includes but is not limited to the operating status, health status and known fault information of the equipment;
[0051] The fault impact scope refers to the impact of the equipment failure on the substation operation, including but not limited to the affected area, equipment, functions, and the resulting safety hazards or production risks.
[0052] The substation equipment information collection module sends each equipment information to the substation historical data collection module;
[0053] The substation historical data collection module is used to collect historical data of equipment information of each substation equipment on the monitoring line;
[0054] The step of collecting the historical data of the device information includes:
[0055] Step S101: sorting the device information according to the function, and numbering the substation equipment according to the sorting information, and marking the number as k, k = 1, 2, 3 ... K, K is the number of the device information;
[0056] Preferably, the sorting logic of the sorting information is:
[0057] The sorting information is sorted in the order of function - equipment location line - equipment setting, and the equipment location line is classified in alphabetical order;
[0058] For example, the sorting information of the equipment No. 001 of the first arrangement line transformer is TA001;
[0059] It should be noted that: T is used to represent transformers, which are devices used to raise and lower voltages in substations; CB is used to represent circuit breakers, which are devices that control the flow of current in circuits and are also often used to represent switchgear; DS is used to represent disconnectors, which are devices that isolate circuits for maintenance, overhaul or switching operations; CT is used to represent current transformers, which are used to measure current and convert it into signals suitable for measuring and protecting equipment; VT is used to represent voltage transformers, which are used to measure voltage and convert it into signals suitable for measuring and protecting equipment; CAP is used to represent capacitors, which are used to adjust the power factor in power systems; REAC is used to represent reactors, which are used to adjust voltage stability in power systems.
[0060] Step S102: according to the device information k, all fault cause data of the device information k and the device information k-1 in wet weather are collected, and for each fault cause data, the fault impact on the device information k caused by the fault cause data is collected, and a determination rule before the fault impact is generated is set in advance according to the relationship between the fault impact and the fault cause data;
[0061] Preferably, the determination rule before the fault impact is generated is:
[0062] Each fault cause includes humidity, temperature and discharge intensity around the substation equipment in humid weather, and analysis constants α, β and γ are set. A fault cause coefficient H is generated based on the analysis constants α, β and γ. The generation formula of the fault cause coefficient H is H=α*(Sc-Sj)+β*(Tc-Tj)+γ*(Qc-Qj), wherein Sc is the humidity around the substation equipment, Sj is the standard value of humidity around the substation equipment, Tc is the temperature around the substation equipment, Tj is the standard value of temperature around the substation equipment, Qc is the discharge intensity around the substation equipment, Qj is the standard value of discharge intensity around the substation equipment, and α, β and γ are respectively the influence analysis parameters of humidity, temperature and discharge intensity around the substation equipment;
[0063] An analysis threshold Hy is set, and the fault cause coefficient H is compared with the analysis threshold Hy. If the fault cause coefficient H is greater than or equal to the analysis threshold Hy, a determination of the fault impact is generated; if the fault cause coefficient H is less than the analysis threshold Hy, no determination of the fault impact is generated.
[0064] Step S103: collecting attribute values of each fault cause and fault impact caused by each piece of equipment information k and using them as historical data of the equipment information.
[0065] It should be noted that the equipment used for the functions of the various devices described include but are not limited to transformers, circuit breakers, disconnectors, capacitors, reactors, current transformers, voltage transformers, protection devices and control devices, and automation equipment, among which transformers are used to raise and lower voltages to achieve power transmission and distribution; circuit breakers are used to control the flow of current in a circuit and quickly cut off the circuit when a circuit fails; disconnectors isolate the circuit to facilitate equipment inspection, maintenance or switching operations; capacitors and reactors adjust the power factor and voltage stability in the power system; current transformers and voltage transformers are used to measure current and voltage and convert them into signals suitable for measuring and protecting equipment; protection devices and control devices are used to achieve protection and control functions of the power system, including overcurrent protection, overvoltage protection, undervoltage protection, etc.; automation equipment includes automation protection devices, telecontrol devices, communication equipment, etc., which are used to achieve automated monitoring, control and protection of the power system.
[0066] The substation historical data collection module sends the collected historical data of the equipment information to the substation historical data analysis module;
[0067] The substation historical data analysis module is used to generate a fault analysis model for evaluating the impact of substation equipment failures based on the historical data of each device information;
[0068] The generation step of the fault analysis module includes:
[0069] Step S201: Based on each device information k, the attribute value of the fault cause data in the historical data of the device information is used as the input of the fault analysis model, the attribute value of the fault impact is used as the output of the fault analysis model, the fault impact occurring in each device information is used as the prediction target, and the prediction accuracy of the machine learning model is used as the training target. The fault impact is the location, impact range and functional impact of the affected substation equipment;
[0070] Step S202: setting a prediction accuracy threshold ky, and training a fault analysis model for each device information k;
[0071] Step S203: When the prediction accuracy of the fault analysis model reaches the prediction accuracy threshold ky, stop training, and mark the fault analysis model of the trained device information k as Mk. The machine learning model can be a support vector machine, a linear model or a decision tree.
[0072] The substation historical data collection module sends the trained fault analysis model Mk to the substation equipment status monitoring module.
[0073] The real-time information collection module is used to collect the fault cause data of each device information in real time;
[0074] The fault cause data is data on the impact of failure of each device in wet weather, including but not limited to the surrounding temperature, humidity and discharge intensity of the substation equipment;
[0075] Preferably, the real-time information collection module collects data on the impact of failures of various devices in wet weather, including:
[0076] Step S301: collecting and determining fault impact data according to the determination rule set in step 102 before the fault impact is generated;
[0077] Step S302: Compare the fault cause coefficient H with the analysis threshold Hy. If the fault cause coefficient H is greater than or equal to the analysis threshold Hy, the fault impact is determined and generated, and step S303 is performed. If the fault cause coefficient H is less than the analysis threshold Hy, the fault impact is not determined and generated, and no data processing is performed.
[0078] Step S303: Based on the device information k, collect the attribute values of the real-time fault cause data.
[0079] The real-time information collection module sends the fault cause data to the substation equipment status monitoring module
[0080] The substation equipment status monitoring module is used to predict future fault impacts based on the attribute values of real-time fault cause data;
[0081] Preferably, the substation equipment status monitoring module analyzes the attribute values of the received fault cause data, inputs the attribute values of the fault cause data into the fault analysis model Mk, and the fault analysis model Mk outputs the predicted fault impact;
[0082] It can be understood as predicting the location, impact range and functional impact of substation equipment that will be affected by future faults through fault cause data.
[0083] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0084] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.
[0085] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple;
[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0087] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A substation equipment monitoring system, It is characterized in that The substation equipment monitoring system includes a substation equipment information collection module, a substation historical data collection module, a substation historical data analysis module, a real-time information collection module and a substation equipment status monitoring module; Substation equipment information collection module: mainly used to pre-collect the equipment information of each monitoring line set in the substation, and send the equipment information to the substation historical data collection module; Substation historical data collection module: used to collect historical data of equipment information of each substation equipment on the monitoring line, and send the collected historical data of equipment information to the substation historical data analysis module; Substation historical data analysis module: used to generate a fault analysis model for evaluating the impact of substation equipment failures based on the historical data of each device information, and send the trained fault analysis model to the substation equipment status monitoring module; Real-time information collection module: used to collect the fault cause data of each device in real time and send the fault cause data to the substation equipment status monitoring module; Substation equipment status monitoring module: used to predict future fault impacts based on the attribute values of real-time fault cause data.
2. A substation equipment monitoring system according to claim 1, It is characterized in that The monitoring line is a line of substation equipment equipped with sensors in the substation, and the equipment information includes equipment identification, function, fault condition and fault impact range of each substation equipment on the monitoring line.
3. A substation equipment monitoring system according to claim 2, It is characterized in that The device identifier is a unique identifier or number for each substation, which is used to uniquely distinguish the substation; the functions include but are not limited to raising and lowering voltage to achieve power transmission and distribution, controlling current flow in the circuit, cutting off current when a fault occurs, isolating equipment and cutting off current when the circuit is operating normally, improving the power factor of the system, measuring current and voltage and converting them into signals suitable for measuring and protecting equipment, overcurrent protection, overvoltage protection, undervoltage protection, real-time monitoring and remote control of the system; the fault conditions include but are not limited to the operating status, health status and known fault information of the equipment; the fault impact range is the impact range of the equipment failure on the operation of the substation, including but not limited to the affected areas, equipment, functions, and the resulting safety hazards or production risks.
4. A substation equipment monitoring system according to claim 3, It is characterized in that The step of collecting the historical data of the device information includes: Step S101: sorting the device information according to the function, and numbering the substation equipment according to the sorting information, and marking the number as k, k = 1, 2, 3 ... K, K is the number of the device information; Step S102: according to the device information k, all fault cause data of the device information k and the device information k-1 in wet weather are collected, and for each fault cause data, the fault impact on the device information k caused by the fault cause data is collected, and a determination rule before the fault impact is generated is set in advance according to the relationship between the fault impact and the fault cause data; Step S103: collecting attribute values of each fault cause and fault impact caused by each piece of equipment information k and using them as historical data of the equipment information.
5. A substation equipment monitoring system according to claim 4, It is characterized in that The sorting logic of the sorting information is: The sorting information is sorted in the order of function - device location line - device setting, and the device location line is classified in alphabetical order.
6. A substation equipment monitoring system according to claim 5, It is characterized in that The judgment rule before the fault impact is generated is: Each fault cause includes humidity, temperature and discharge intensity around the substation equipment in humid weather, and analysis constants α, β and γ are set. A fault cause coefficient H is generated based on the analysis constants α, β and γ. The generation formula of the fault cause coefficient H is H=α*(Sc-Sj)+β*(Tc-Tj)+γ*(Qc-Qj), wherein Sc is the humidity around the substation equipment, Sj is the standard value of humidity around the substation equipment, Tc is the temperature around the substation equipment, Tj is the standard value of temperature around the substation equipment, Qc is the discharge intensity around the substation equipment, Qj is the standard value of discharge intensity around the substation equipment, and α, β and γ are respectively the influence analysis parameters of humidity, temperature and discharge intensity around the substation equipment; An analysis threshold value Hy is set, and the fault cause coefficient H is compared with the analysis threshold value Hy. If the fault cause coefficient H is greater than or equal to the analysis threshold value Hy, a determination of the fault impact is generated; if the fault cause coefficient H is less than the analysis threshold value Hy, a determination of the fault impact is not generated; Step S103: collecting attribute values of each fault cause and fault impact caused by each piece of equipment information k and using them as historical data of the equipment information.
7. A substation equipment monitoring system according to claim 6, It is characterized in that The generation step of the fault analysis module includes: Step S201: Based on each device information k, the attribute value of the fault cause data in the historical data of the device information is used as the input of the fault analysis model, the attribute value of the fault impact is used as the output of the fault analysis model, the fault impact occurring in each device information is used as the prediction target, and the prediction accuracy of the machine learning model is used as the training target. The fault impact is the location, impact range and functional impact of the affected substation equipment; Step S202: setting a prediction accuracy threshold ky, and training a fault analysis model for each device information k; Step S203: When the prediction accuracy of the fault analysis model reaches the prediction accuracy threshold ky, stop training, and mark the fault analysis model of the device information k after training as Mk. The machine learning model can be a support vector machine, a linear model or a decision tree.
8. A substation equipment monitoring system according to claim 7, It is characterized in that The fault cause data is data on the impact of failure of each device in wet weather, including but not limited to the surrounding temperature, humidity and discharge intensity of the substation equipment; The generation step of the fault analysis module includes: Step S201: Based on each device information k, the attribute value of the fault cause data in the historical data of the device information is used as the input of the fault analysis model, the attribute value of the fault impact is used as the output of the fault analysis model, the fault impact occurring in each device information is used as the prediction target, and the prediction accuracy of the machine learning model is used as the training target. The fault impact is the location, impact range and functional impact of the affected substation equipment; Step S202: setting a prediction accuracy threshold ky, and training a fault analysis model for each device information k; Step S203: When the prediction accuracy of the fault analysis model reaches the prediction accuracy threshold ky, stop training, and mark the fault analysis model of the device information k after training as Mk. The machine learning model can be a support vector machine, a linear model or a decision tree.
9. A substation equipment monitoring system according to claim 8, It is characterized in that The real-time information collection module is used to collect the fault cause data of each device information in real time; The fault cause data is data on the impact of failure of each device in wet weather, including but not limited to the surrounding temperature, humidity and discharge intensity of the substation equipment; Preferably, the real-time information collection module collects data on the impact of failures of various equipment in wet weather, including: Step S301: collecting and determining fault impact data according to the determination rule set in step 102 before the fault impact is generated; Step S302: Compare the fault cause coefficient H with the analysis threshold Hy. If the fault cause coefficient H is greater than or equal to the analysis threshold Hy, the fault impact is determined and generated, and step S303 is performed. If the fault cause coefficient H is less than the analysis threshold Hy, the fault impact is not determined and generated, and no data processing is performed. Step S303: Based on the device information k, collect the attribute values of the real-time fault cause data.
10. A substation equipment monitoring system according to claim 9, It is characterized in that The substation equipment status monitoring module analyzes the attribute values of the received fault cause data, inputs the attribute values of the fault cause data into a fault analysis model, and the fault analysis model outputs a predicted fault impact.
