Transformer production fault management system based on big data analysis

Abstract

The invention relates to the technical field of electrical equipment manufacturing, and particularly discloses a transformer production fault management system based on big data analysis. Comprising a region division module, a transformer data acquisition module, a data preprocessing module, a transformer power data analysis module, a transformer winding temperature data analysis module, a production equipment health data analysis module, a transformer comprehensive analysis module, a transformer fault judgment module, a transformer fault early warning module and an AR display terminal module. Through a big data analysis technology, accurate recognition of faults can be realized, potential faults can be found in time, and the influence of the faults on production is reduced; through automatic and intelligent fault management, the workload of manual inspection and troubleshooting can be remarkably reduced, the operation and maintenance cost is reduced, and meanwhile, due to improvement of the fault processing efficiency and accuracy, the production loss and the maintenance cost caused by faults can also be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment manufacturing, and in particular to a transformer production fault management system based on big data analysis. Background Art

[0002] As power systems continue to expand and become more intelligent, the stability and reliability of transformers, key components of power transmission, are becoming increasingly important. Transformer production is complex, involving the assembly and testing of numerous precision components. Oversights in any step can lead to equipment failures, impacting the safe and stable operation of the entire power grid.

[0003] In existing technologies, the management of transformer production failures primarily relies on traditional quality control and troubleshooting methods. First, strict production processes and quality standards are established to ensure transformer quality control during production. Second, when a failure occurs, manual inspections, equipment testing, and data analysis are used to locate and troubleshoot the fault. Finally, appropriate repair measures are implemented based on the fault type and cause to restore the transformer to normal operation.

[0004] However, it still has some shortcomings in actual use. First, fault detection and repair usually require manual participation, and the ability to analyze fault data is limited, resulting in untimely fault handling, which may pose a threat to the stable operation of the power grid; second, although regular maintenance is safe, it often leads to over-maintenance or insufficient maintenance, which not only increases maintenance costs, but may also cause more serious faults due to failure to discover hidden dangers in time; in addition, the process of fault identification and diagnosis is cumbersome and time-consuming, which cannot meet the needs of rapid response and handling of faults, and it is difficult to accurately identify and diagnose complex and hidden faults, which may lead to untimely fault handling and affect production efficiency and product quality. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a transformer production fault management system based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: a transformer production fault management system based on big data analysis, comprising a regional division module, a transformer data acquisition module, a data preprocessing module, a transformer power data analysis module, a transformer winding temperature data analysis module, a production equipment health data analysis module, a transformer comprehensive analysis module, a transformer fault judgment module, a transformer fault warning module, and an AR display terminal module.

[0007] Area division module: used to determine the transformer production line as the target area, divide the target area into monitoring sub-areas according to the equal time division method, and number each monitoring sub-area in sequence as 1, 2, ..., i, ..., n;

[0008] Transformer data acquisition module: used to collect comprehensive transformer parameters of each monitoring sub-area and transmit the collected comprehensive transformer parameters to the data preprocessing module;

[0009] Data preprocessing module: used to preprocess the transformer comprehensive parameters collected by the transformer data acquisition module, and transmit the preprocessed data to the transformer power data analysis module, the transformer winding temperature data analysis module, and the production equipment health data analysis module respectively;

[0010] Transformer power data analysis module: used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer power abnormality coefficient, calculate the transformer power abnormality coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module;

[0011] Transformer winding temperature data analysis module: used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer winding temperature deviation coefficient, calculate the transformer winding temperature deviation coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module;

[0012] Production equipment health data analysis module: used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer production equipment health coefficient, calculate the transformer production equipment health coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module;

[0013] Transformer comprehensive analysis module: used to establish a comprehensive analysis model, import the data transmitted by the transformer power data analysis module, the transformer winding temperature data analysis module, and the production equipment health data analysis module into the comprehensive analysis model, calculate the comprehensive index of transformer production failures in the target area, and transmit it to the transformer fault judgment module;

[0014] Transformer fault judgment module: used to compare the transformer production fault comprehensive index calculated by the transformer comprehensive analysis module with the transformer production fault comprehensive index threshold, obtain a judgment result, and transmit the judgment result to the transformer fault early warning module;

[0015] Transformer fault warning module: Based on the analysis and judgment results of the transformer fault judgment module, it warns of transformer production failures and generates fault handling suggestions;

[0016] AR display terminal module: used to receive and display real-time dynamic data of transformer production and transformer fault analysis reports, and form an intuitive three-dimensional visualization interface for operators or managers to conduct real-time monitoring, decision-making and guidance.

[0017] Preferably, the transformer production equipment configured in each monitoring sub-area all adopts a unified equipment model, and the transformers produced in the production line all have a unified parameter model.

[0018] Preferably, the comprehensive transformer parameters include transformer power parameters, transformer winding temperature parameters, and transformer production equipment parameters; wherein the transformer power parameters include the unit loss of the core material, the core mass, the current density, the wire mass, the no-load current, the transformer rated capacity, and the transformer short-circuit voltage; the transformer winding temperature parameters include the ambient temperature, the load current, the transformer winding resistance, and the transformer core loss heat; the transformer production equipment parameters include the vibration amplitude of the transformer production equipment, the average load value of the transformer, the rated capacity of the transformer, the initial temperature of the transformer, and the temperature of the transformer after the running time t.

[0019] Preferably, the data preprocessing module preprocesses the collected data by performing noise reduction processing on the data, identifying missing values ​​and outliers, outlier detection, and outlier processing through existing filtering technology.

[0020] Preferably, the calculation steps of the transformer power anomaly coefficient of each monitoring sub-area are as follows:

[0021] Step S01: Calculate the no-load loss of the transformer. The calculation model is as follows:

[0022] P 0i =Kc×Pc i ×Gc i , where P 0i It is represented as the no-load loss of the transformer in the ith monitoring sub-area, Kc is the process coefficient, and Pc i It is represented as the unit loss of the core material in the ith monitoring sub-area, and Gc is represented as the core mass in the ith monitoring sub-area;

[0023] Step S02: Calculate the load loss of the transformer. The calculation model is as follows:

[0024] Pk i =Km×J i 2 ×Gm i , where Pk i is the load loss of the transformer in the ith monitoring sub-area, Km is the conductivity coefficient, J iExpressed as the current density of the ith monitoring sub-area, Gm i It is represented as the conductor quality of the i-th monitoring sub-area;

[0025] Step S03: Calculate the reactive power on the power supply side of the transformer during the no-load test. The calculation model is as follows:

[0026] Among them, Q 0i It is expressed as the reactive power of the transformer in the i-th monitoring sub-area when it is unloaded, I 0i It is represented as the no-load current of the i-th monitoring sub-area, I 0i % is expressed as the percentage of no-load current in the i-th monitoring sub-area, S N Expressed as transformer rated capacity, P 0i It is represented as the no-load loss of the transformer in the i-th monitoring sub-area;

[0027] Step S04: Calculate the transformer power abnormality coefficient. The calculation model is as follows:

[0028] Among them, TPC i Expressed as the transformer power anomaly coefficient of the i-th monitoring sub-area, Q 0i It is expressed as the reactive power of the transformer in the ith monitoring sub-area when it is unloaded, Uk i Expressed as the transformer short-circuit voltage of the ith monitoring sub-area, Uk i % is expressed as the percentage of short pedal voltage in the i-th monitoring sub-area, S N Expressed as transformer rated capacity, Pk i It is represented as the load loss of the transformer in the i-th monitoring sub-area.

[0029] Preferably, the calculation model of the transformer winding temperature deviation coefficient of each monitoring sub-area is as follows:

[0030] Among them, WTDC i Expressed as the transformer winding temperature deviation coefficient of the i-th monitoring sub-area, Ten i It is represented as the ambient temperature of the i-th monitoring sub-area, Ilo i Expressed as the load current of the ith monitoring sub-area, Rw i Expressed as the transformer winding resistance of the i-th monitoring sub-area, Q_loss i It represents the heat loss of the transformer core in the i-th monitoring sub-area, WT_ideal represents the ideal temperature of the transformer winding, and k represents the heat dissipation coefficient.

[0031] Preferably, the calculation model of the transformer production equipment health factor of each monitoring sub-area is specifically as follows:

[0032] Among them, EPEC i Expressed as the health factor of transformer production equipment in the ith monitoring sub-area, Va i It is represented by the vibration amplitude of the transformer production equipment in the i-th monitoring sub-area, Va max It is expressed as the maximum value allowed for the vibration amplitude of transformer production equipment, Tal i It is expressed as the average transformer load value of the i-th monitoring sub-area, Trc i It is represented by the rated capacity of the transformer in the ith monitoring sub-area, Ta i Expressed as the initial temperature of the transformer in the ith monitoring sub-area, Tt i It is represented as the transformer temperature of the i-th monitoring sub-area after the operating time t.

[0033] Preferably, the target area transformer production failure comprehensive index calculation model is as follows:

[0034] Among them, PMCI represents the comprehensive index of transformer production failure in the target area, TPC i Expressed as the transformer power anomaly coefficient of the i-th monitoring sub-area, WTDC i It is expressed as the transformer winding temperature deviation coefficient of the i-th monitoring sub-area, EPEC i It is expressed as the health factor of transformer production equipment in the ith monitoring sub-area, and k1, k2 and k3 are constants.

[0035] Preferably, the transformer production failure comprehensive index threshold is expressed as λ. When PMCI>λ, it means that the target area transformer production failure comprehensive index is greater than the transformer production failure comprehensive index threshold, indicating that there is no abnormality in transformer production. When PMCI<λ, it means that the target area transformer production failure comprehensive index is less than the transformer production failure comprehensive index threshold, indicating that there is an abnormality in transformer production. In this case, an analysis report is generated for the transformer production abnormality data and an early warning signal is issued.

[0036] Technical effects and advantages of the present invention:

[0037] 1. Through big data analysis technology, the system of the present invention can comprehensively collect data from the transformer production process and conduct in-depth mining and analysis, thereby achieving accurate fault identification, helping to timely discover potential faults and reduce the impact of faults on production;

[0038] 2. Through automated and intelligent fault management, the present invention can significantly reduce the workload of manual inspections and troubleshooting, lowering operation and maintenance costs. At the same time, due to the improved efficiency and accuracy of fault handling, it can also reduce production losses and maintenance costs caused by faults.

[0039] 3. The present invention can provide a visual management interface to intuitively display various fault analysis results, assisting management to make more accurate and efficient decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0041] Figure 1 Schematic diagram of the overall structure of the system of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of the present invention.

[0043] See also Figure 1 As shown, the present invention provides a transformer production fault management system based on big data analysis, including a region division module, a transformer data acquisition module, a data preprocessing module, a transformer power data analysis module, a transformer winding temperature data analysis module, a production equipment health data analysis module, a transformer comprehensive analysis module, a transformer fault judgment module, a transformer fault early warning module, and an AR display terminal module.

[0044] The output end of the area division module is telecom connected to the input end of the transformer data acquisition module, the output end of the transformer data acquisition module is telecom connected to the input end of the data preprocessing module, the output end of the data preprocessing module is telecom connected to the input end of the transformer power data analysis module, the input end of the transformer winding temperature data analysis module, and the input end of the production equipment health data analysis module respectively, the output end of the transformer power data analysis module is telecom connected to the input end of the transformer comprehensive analysis module, the output end of the transformer power data analysis module is telecom connected to the input end of the transformer comprehensive analysis module, the output end of the transformer winding temperature data analysis module is telecom connected to the input end of the transformer comprehensive analysis module, the output end of the transformer comprehensive analysis module is telecom connected to the input end of the transformer fault judgment module, the output end of the transformer fault judgment module is telecom connected to the input end of the transformer fault early warning module and the input end of the AR display terminal module respectively, and the output end of the transformer fault early warning module is telecom connected to the input end of the AR display terminal module.

[0045] The area division module is used to determine the transformer production line as the target area, divide the target area into monitoring sub-areas in an equal time division manner, and number the monitoring sub-areas in sequence as 1, 2, ..., i, ..., n;

[0046] In this embodiment, it should be specifically explained that the transformer production equipment configured in each monitoring sub-area all adopts a unified equipment model, and the transformers produced in the production line all have a unified parameter model.

[0047] The transformer data acquisition module is used to collect the comprehensive parameters of the transformers in each monitoring sub-area and transmit the collected comprehensive parameters of the transformers to the data preprocessing module;

[0048] In this embodiment, it should be specifically explained that the comprehensive transformer parameters include transformer power parameters, transformer winding temperature parameters, and transformer production equipment parameters; wherein the transformer power parameters include the unit loss of the core material, the core mass, the current density, the wire mass, the no-load current, the transformer rated capacity, and the transformer short-circuit voltage; the transformer winding temperature parameters include the ambient temperature, the load current, the transformer winding resistance, and the transformer core loss heat; the transformer production equipment parameters include the vibration amplitude of the transformer production equipment, the average load value of the transformer, the rated capacity of the transformer, the initial temperature of the transformer, and the temperature of the transformer after the operating time t.

[0049] The data preprocessing module is used to preprocess the transformer comprehensive parameters collected by the transformer data acquisition module, and transmit the preprocessed data to the transformer power data analysis module, the transformer winding temperature data analysis module, and the production equipment health data analysis module respectively;

[0050] In this embodiment, it should be specifically explained that the data preprocessing module preprocesses the collected data by performing noise reduction processing on the data, identifying missing values ​​and outliers, outlier detection, and outlier processing through existing filtering technology.

[0051] In this embodiment, it should be specifically explained that the noise reduction process is to remove noise from transformer monitoring data to improve data quality and analysis accuracy; commonly used noise reduction methods include smoothing filtering, wavelet transform and empirical mode decomposition; smoothing filtering can remove high-frequency noise, wavelet transform can remove local noise, and empirical mode decomposition can remove non-stationary noise;

[0052] The missing values ​​and outliers are identified, and the missing values ​​can be filled using the mean, median or interpolation method; and the outliers can be deleted or corrected.

[0053] The transformer power data analysis module is used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer power abnormality coefficient, calculate the transformer power abnormality coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module;

[0054] In this embodiment, it should be specifically explained that the calculation steps of the transformer power abnormality coefficient of each monitoring sub-area are as follows:

[0055] Step S01: Calculate the no-load loss of the transformer. The calculation model is as follows:

[0056] P 0i =Kc×Pc i ×Gc i , where P 0i It is represented as the no-load loss of the transformer in the ith monitoring sub-area, Kc is the process coefficient, and Pc i It is represented as the unit loss of the core material in the ith monitoring sub-area, and Gc is represented as the core mass in the ith monitoring sub-area;

[0057] Step S02: Calculate the load loss of the transformer. The calculation model is as follows:

[0058] Among them, Pk i is the load loss of the transformer in the ith monitoring sub-area, Km is the conductivity coefficient, J i Expressed as the current density of the ith monitoring sub-area, Gm i It is represented as the conductor quality of the i-th monitoring sub-area;

[0059] Step S03: Calculate the reactive power on the power supply side of the transformer during the no-load test. The calculation model is as follows:

[0060] Among them, Q 0i It is expressed as the reactive power of the transformer in the i-th monitoring sub-area when it is unloaded, I 0i It is represented as the no-load current of the i-th monitoring sub-area, I 0i % is expressed as the percentage of no-load current in the i-th monitoring sub-area, S N Expressed as transformer rated capacity, P 0i It is represented as the no-load loss of the transformer in the i-th monitoring sub-area;

[0061] Step S04: Calculate the transformer power abnormality coefficient. The calculation model is as follows:

[0062] Among them, TPC i Expressed as the transformer power anomaly coefficient of the i-th monitoring sub-area, Q 0iIt is expressed as the reactive power of the transformer in the ith monitoring sub-area when it is unloaded, Uk i Expressed as the transformer short-circuit voltage of the ith monitoring sub-area, Uk i % is expressed as the percentage of short pedal voltage in the i-th monitoring sub-area, S N Expressed as transformer rated capacity, Pk i It is represented as the load loss of the transformer in the i-th monitoring sub-area.

[0063] The transformer winding temperature data analysis module is used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer winding temperature deviation coefficient, calculate the transformer winding temperature deviation coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module;

[0064] In this embodiment, it should be specifically explained that the calculation model of the transformer winding temperature deviation coefficient of each monitoring sub-area is as follows:

[0065] Among them, WTDC i Expressed as the transformer winding temperature deviation coefficient of the i-th monitoring sub-area, Ten i It is represented as the ambient temperature of the i-th monitoring sub-area, Ilo i Expressed as the load current of the ith monitoring sub-area, Rw i Expressed as the transformer winding resistance of the i-th monitoring sub-area, Q_loss i It represents the heat loss of the transformer core in the i-th monitoring sub-area, WT_ideal represents the ideal temperature of the transformer winding, and k represents the heat dissipation coefficient.

[0066] The production equipment health data analysis module is used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer production equipment health coefficient, calculate the transformer production equipment health coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module;

[0067] In this embodiment, it should be specifically explained that the calculation model of the transformer production equipment health factor of each monitoring sub-area is as follows:

[0068] Among them, EPEC i Expressed as the health factor of transformer production equipment in the ith monitoring sub-area, Va i It is represented by the vibration amplitude of the transformer production equipment in the i-th monitoring sub-area, Va max It is expressed as the maximum value allowed for the vibration amplitude of transformer production equipment, Tal i It is expressed as the average transformer load value of the i-th monitoring sub-area, Trc iIt is represented by the rated capacity of the transformer in the ith monitoring sub-area, Ta i Expressed as the initial temperature of the transformer in the ith monitoring sub-area, Tt i It is represented as the transformer temperature of the i-th monitoring sub-area after the operating time t.

[0069] The transformer comprehensive analysis module is used to establish a comprehensive analysis model, import the data transmitted by the transformer power data analysis module, the transformer winding temperature data analysis module, and the production equipment health data analysis module into the comprehensive analysis model, calculate the comprehensive index of transformer production failures in the target area, and transmit it to the transformer fault judgment module;

[0070] In this embodiment, it should be specifically explained that the calculation model of the target area transformer production failure comprehensive index is as follows:

[0071] Among them, PMCI represents the comprehensive index of transformer production failure in the target area, TPC i Expressed as the transformer power anomaly coefficient of the i-th monitoring sub-area, WTDC i It is expressed as the transformer winding temperature deviation coefficient of the i-th monitoring sub-area, EPEC i It is expressed as the health factor of transformer production equipment in the ith monitoring sub-area, and k1, k2 and k3 are constants.

[0072] The transformer fault judgment module is used to compare the transformer production fault comprehensive index calculated by the transformer comprehensive analysis module with the transformer production fault comprehensive index threshold, obtain a judgment result, and transmit the judgment result to the transformer fault early warning module;

[0073] In this embodiment, it should be specifically explained that the transformer production failure comprehensive index threshold is expressed as λ. When PMCI>λ, it means that the target area transformer production failure comprehensive index is greater than the transformer production failure comprehensive index threshold, indicating that there is no abnormality in transformer production. When PMCI<λ, it means that the target area transformer production failure comprehensive index is less than the transformer production failure comprehensive index threshold, indicating that there is an abnormality in transformer production. In this case, an analysis report is generated for the transformer production abnormality data and an early warning signal is issued.

[0074] The transformer fault early warning module issues early warnings for transformer production faults based on the analysis and judgment results of the transformer fault judgment module and generates fault handling suggestions;

[0075] The AR display terminal module is used to receive and display real-time dynamic data of transformer production and transformer fault analysis reports, and form an intuitive three-dimensional visualization interface for operators or managers to conduct real-time monitoring, decision-making and guidance.

[0076] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0077] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A transformer production fault management system based on big data analysis, characterized in that: include: Area division module: used to determine the transformer production line as the target area, divide the target area into monitoring sub-areas in an equal time division manner, and number each monitoring sub-area in sequence as 1, 2, ..., i, ..., n; Transformer data acquisition module: used to collect the comprehensive parameters of the transformers in each monitoring sub-area, and transmit the collected comprehensive parameters of the transformers to the data preprocessing module; Data preprocessing module: used to preprocess the transformer comprehensive parameters collected by the transformer data acquisition module, and transmit the preprocessed data to the transformer power data analysis module, the transformer winding temperature data analysis module, and the production equipment health data analysis module respectively; Transformer power data analysis module: used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer power abnormality coefficient, calculate the transformer power abnormality coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module; Transformer winding temperature data analysis module: used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer winding temperature deviation coefficient, calculate the transformer winding temperature deviation coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module; Production equipment health data analysis module: used to import the data preprocessed by the data preprocessing module into the mathematical model of the transformer production equipment health coefficient, calculate the transformer production equipment health coefficient of each monitoring sub-area, and transmit it to the transformer comprehensive analysis module; Transformer comprehensive analysis module: used to establish a comprehensive analysis model, import the data transmitted by the transformer power data analysis module, the transformer winding temperature data analysis module, and the production equipment health data analysis module into the comprehensive analysis model, calculate the comprehensive index of transformer production failures in the target area, and transmit it to the transformer fault judgment module; Transformer fault judgment module: used to compare the transformer production fault comprehensive index calculated by the transformer comprehensive analysis module with the transformer production fault comprehensive index threshold, obtain a judgment result, and transmit the judgment result to the transformer fault early warning module; Transformer fault early warning module: according to the analysis and judgment results of the transformer fault judgment module, early warning is given for transformer production faults, and fault handling suggestions are generated; AR display terminal module: used to receive and display real-time dynamic data of transformer production and transformer fault analysis reports, and form an intuitive three-dimensional visualization interface for operators or managers to conduct real-time monitoring, decision-making and guidance.

2. According to claim 1, a transformer production fault management system based on big data analysis is characterized in that: The transformer production equipment configured in each monitoring sub-area adopts a unified equipment model, and the transformers produced by the production line are all of a unified parameter model.

3. According to claim 1, a transformer production fault management system based on big data analysis is characterized in that: The comprehensive parameters of the transformer include transformer power parameters, transformer winding temperature parameters, and transformer production equipment parameters; wherein the transformer power parameters include unit loss of core material, core mass, current density, wire mass, no-load current, transformer rated capacity, and transformer short-circuit voltage; the transformer winding temperature parameters include ambient temperature, load current, transformer winding resistance, and transformer core loss heat; the transformer production equipment parameters include transformer production equipment vibration amplitude, transformer average load value, transformer rated capacity, transformer initial temperature, and transformer temperature after running time t.

4. The transformer production fault management system based on big data analysis according to claim 1 is characterized in that: The data preprocessing module preprocesses the collected data by performing noise reduction, identifying missing values ​​and outliers, outlier detection, and outlier processing on the data through existing filtering technology.

5. The transformer production fault management system based on big data analysis according to claim 1 is characterized in that: The calculation steps of the transformer power abnormality coefficient of each monitoring sub-area are as follows: Step S01: Calculate the no-load loss of the transformer. The calculation model is as follows: P 0i =Kc×Pc i ×Gc i , where P 0i It is represented as the no-load loss of the transformer in the ith monitoring sub-area, Kc is represented as the process coefficient, and Pc i It is represented as the unit loss of the core material in the ith monitoring sub-area, and Gc is represented as the core mass in the ith monitoring sub-area; Step S02: Calculate the load loss of the transformer. The calculation model is as follows: Among them, Pk i is represented by the load loss of the transformer in the ith monitoring sub-area, Km is represented by the conductivity coefficient, J i It is expressed as the current density of the ith monitoring sub-area, Gm i It is represented as the wire quality of the ith monitoring sub-area; Step S03: Calculate the reactive power of the power supply side of the transformer during the no-load test. The calculation model is as follows: Among them, Q 0i It is expressed as the reactive power of the transformer in the ith monitoring sub-area when it is unloaded, I 0i It is represented as the no-load current of the ith monitoring sub-area, I 0i % represents the no-load current percentage of the i-th monitoring sub-area, S N Expressed as transformer rated capacity, P 0i It is represented as the no-load loss of the transformer in the ith monitoring sub-area; Step S04: Calculate the transformer power abnormality coefficient, the calculation model is as follows: Among them, TPC i It is expressed as the transformer power anomaly coefficient of the ith monitoring sub-area, Q 0i It is represented by the reactive power of the transformer in the ith monitoring sub-area when it is unloaded, Uk i It is represented by the transformer short-circuit voltage of the ith monitoring sub-area, Uk i % represents the short pedal voltage percentage of the i-th monitoring sub-area, S N Expressed as transformer rated capacity, Pk i It is represented as the load loss of the transformer in the i-th monitoring sub-area.

6. A transformer production fault management system based on big data analysis according to claim 1, characterized in that: The calculation model of the transformer winding temperature deviation coefficient of each monitoring sub-area is as follows: Among them, WTDC i It is expressed as the transformer winding temperature deviation coefficient of the ith monitoring sub-area, Ten i It is represented as the ambient temperature of the ith monitoring sub-area, Ilo i Represented as the load current of the ith monitoring sub-area, Rw i Expressed as the transformer winding resistance of the ith monitoring sub-area, Q_loss i It is represented as the transformer core loss heat of the ith monitoring sub-area, WT_ideal is represented as the ideal temperature of the transformer winding, and k is represented as the heat dissipation coefficient.

7. The transformer production fault management system based on big data analysis according to claim 1 is characterized in that: The calculation model of the transformer production equipment health factor of each monitoring sub-area is specifically as follows: Among them, EPEC i It is expressed as the health factor of transformer production equipment in the ith monitoring sub-area, Va i It is represented by the vibration amplitude of the transformer production equipment in the ith monitoring sub-area, Va max It is expressed as the maximum allowable vibration amplitude of transformer production equipment, Tal i It is expressed as the average transformer load value of the ith monitoring sub-area, Trc i It is represented by the rated capacity of the transformer in the ith monitoring sub-area, Ta i It is represented as the initial temperature of the transformer in the ith monitoring sub-area, Tt i It is represented as the transformer temperature of the i-th monitoring sub-area after the operating time t.

8. The transformer production fault management system based on big data analysis according to claim 1 is characterized in that: The calculation model of the comprehensive index of transformer production failure in the target area is as follows: Among them, PMCI represents the comprehensive index of transformer production failure in the target area, TPC i It is expressed as the transformer power anomaly coefficient of the ith monitoring sub-area, WTDC i It is expressed as the transformer winding temperature deviation coefficient of the ith monitoring sub-area, EPEC i It is represented as the health coefficient of transformer production equipment in the ith monitoring sub-area, and k1, k2 and k3 represent constants.

9. The transformer production fault management system based on big data analysis according to claim 1 is characterized in that: The transformer production failure comprehensive index threshold is expressed as λ. When PMCI>λ, it means that the transformer production failure comprehensive index of the target area is greater than the transformer production failure comprehensive index threshold, indicating that there is no abnormality in the transformer production. When PMCI<λ, it means that the transformer production failure comprehensive index of the target area is less than the transformer production failure comprehensive index threshold, indicating that there is an abnormality in the transformer production. In this case, an analysis report is generated for the transformer production abnormality data and an early warning signal is issued.

Images