Method for calculating field strength of transformer insulation under influence of moisture and temperature distribution

Abstract

This invention discloses a method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution, relating to the field of power engineering technology. The method includes: constructing a multiphysics coupled simulation platform for monitoring and analyzing the temperature, humidity, and electric field distribution inside the transformer; setting up a humidity-sensitive element array to collect humidity data and transmitting the data to a central processing unit for processing; constructing an insulation prediction model using a deep neural network algorithm, training the model based on historical humidity, historical temperature, and insulation state data to predict the changing trend of the insulation field strength under specific operating conditions; processing real-time data and inputting it into the insulation prediction model to obtain real-time insulation state prediction values, and dynamically adjusting the parameters of the insulation prediction model; and establishing an anomaly early warning mechanism based on the real-time insulation state prediction values. Once an insulation state anomaly is detected, the system immediately activates an early warning, notifying maintenance personnel to conduct inspections and maintenance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power engineering, and particularly relates to a transformer insulation field strength calculation method under the influence of moisture and temperature distribution. BACKGROUND

[0002] In the field of electric power engineering, as a key component of the power system, the safe and stable operation of the transformer is crucial for the reliability of the power grid. In recent years, with the rapid development of smart grids, the demand for transformer state monitoring and health assessment has been growing. Traditional transformer monitoring technology mainly relies on periodic manual inspection and offline testing. This method is not only inefficient, but also difficult to capture early signs of failure in real time, especially in the face of complex and changing operating environments. The influence of humidity and temperature fluctuations on the insulation state of the transformer is often overlooked, leading to misjudgment and missed judgment of faults.

[0003] The existing transformer state monitoring technology has deficiencies in dealing with the complexity of the influence of humidity and temperature on the insulation state. On the one hand, the lack of multi-physical field coupling effect makes it difficult for the monitoring system to comprehensively evaluate the dynamic changes in the insulation aging process, especially the performance degradation of insulation materials caused by humidity and temperature changes, which directly affects the safe operation of the transformer. On the other hand, the lack of effective data processing and analysis tools limits the application of deep learning models in the monitoring system, making it difficult to mine valuable information from massive data, especially in predicting the evolution trend of the insulation state, which is limited in terms of early warning of potential fault risks. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a transformer insulation field strength calculation method under the influence of moisture and temperature distribution to solve the problem of the lack of multi-physical field coupling effect, which makes it difficult for the monitoring system to comprehensively evaluate the dynamic changes in the insulation aging process, especially the performance degradation of insulation materials caused by humidity and temperature changes, which directly affects the safe operation of the transformer. On the other hand, the lack of effective data processing and analysis tools limits the application of deep learning models in the monitoring system, making it difficult to mine valuable information from massive data, especially in predicting the evolution trend of the insulation state, which is limited in terms of early warning of potential fault risks.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a transformer insulation field strength calculation method under the influence of moisture and temperature distribution, which includes,

[0008] A multi-physics coupling simulation platform is constructed for monitoring and analyzing the temperature, humidity and electric field distribution inside the transformer;

[0009] The humidity sensitive element array is set, humidity data is collected, and the humidity data is transmitted to the central processor for processing;

[0010] An insulation prediction model is constructed through a deep neural network algorithm, historical humidity, historical temperature and insulation state data are input into the insulation prediction model for training, and the change trend of the insulation field strength under specific working conditions is predicted;

[0011] Real-time data is processed and input into the insulation prediction model to obtain real-time insulation state prediction values, and the parameters of the insulation prediction model are dynamically adjusted;

[0012] An abnormal early warning mechanism is established based on the real-time insulation state prediction values, and once the insulation state is abnormal, the system immediately starts the early warning and notifies the operation and maintenance personnel to check and maintain.

[0013] As a preferred scheme of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, wherein: the multi-physics coupling simulation platform is constructed for monitoring and analyzing the temperature, humidity and electric field distribution inside the transformer, and the specific steps are:

[0014] A multi-physics coupling model is constructed based on partial differential equations PDEs for describing the dynamic changes of temperature T, humidity and electric field, and the core equations of the multi-physics coupling model include temperature diffusion equation, humidity diffusion equation and electric field distribution equation;

[0015] Particle swarm optimization algorithm is used to dynamically update the thermal conductivity, humidity diffusion coefficient and charge density of PSO;

[0016] The central processor, sensor network, wireless communication module, data preprocessing algorithm and multi-physics coupling model are integrated to obtain a multi-physics coupling simulation platform, wherein the central processor is used to coordinate the processing of data flow and the operation of the multi-physics coupling model.

[0017] As a preferred scheme of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, wherein: the humidity sensitive element array is set, humidity data is collected, and the humidity data is transmitted to the central processor for processing, and the specific steps are:

[0018] In the transformer, the selected parts include windings, cores and oil tank walls, and temperature sensors, humidity sensors and electric field sensors are integrated;

[0019] The selected parts are divided into uniform grids, and each grid unit represents a potential monitoring point;

[0020] The distance between the computing elements is calculated, and a humidity sensitive element is placed at the center of each grid unit to form a two-dimensional array;

[0021] A microcontroller is built into each humidity sensitive element to continuously collect humidity data at a sampling frequency f s = 10 Hz;

[0022] The humidity data is encoded using Manchester encoding;

[0023] After completing the Manchester encoding of the humidity data, it is packaged into a data packet;

[0024] After the central processing unit receives the data, it first decodes the data packet, and then uses a Kalman filter to preprocess the humidity data to eliminate noise and improve data quality;

[0025] A distributed Kalman filter algorithm is used to fuse the data from multiple elements in the same area;

[0026] Based on the real-time humidity data collected by the humidity sensitive element array, an anomaly detection algorithm is used to detect outliers, and when the humidity in a certain area is detected to be outside the normal range, a warning is triggered immediately;

[0027] According to the real-time humidity data, the humidity diffusion coefficient function in the multi-physical field coupling model is dynamically adjusted to ensure that the model parameters are consistent with the actual working conditions.

[0028] As a preferred scheme of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, the specific steps of constructing the insulation prediction model through the deep neural network algorithm are:

[0029] Selecting a long short-term memory network (LSTM) as the basis of the insulation prediction model;

[0030] The insulation prediction model includes an input layer, a plurality of LSTM layers, a full connection layer, and an output layer.

[0031] As a preferred scheme of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, the specific steps of constructing the insulation prediction model through the deep neural network algorithm are:

[0032] Extracting humidity, temperature, and insulation state data related to the insulation state of the transformer from the historical data set;

[0033] Using an interpolation method to fill in missing data, and using Z-score standardization to normalize the data;

[0034] Based on the original humidity and temperature, the cross features most affecting the insulation state prediction are extracted by principal component analysis (PCA) to capture the interaction of humidity and temperature on the insulation state;

[0035] The cross features are input into the insulation prediction model to output the predicted value of the insulation state.

[0036] As a preferred scheme of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, the real-time data is processed and input into the insulation prediction model to obtain a real-time insulation state prediction value, and the parameters of the insulation prediction model are dynamically adjusted.

[0037] The humidity, temperature and electric field data inside the transformer are collected in real time through a sensor network;

[0038] Before the data is transmitted to the central processor, Manchester encoding and Kalman filter are used to process the real-time data to improve the data quality and the robustness of transmission;

[0039] The processed real-time data is input into the insulation prediction model, and the model parameters are updated at the same time;

[0040] The thermal conductivity, humidity diffusion coefficient and charge density are dynamically updated using the PSO algorithm;

[0041] After the real-time data is input into the insulation prediction model, the real-time insulation state prediction value is output;

[0042] The mean square error (MSE) is selected as the loss function to measure the difference between the predicted value of the insulation prediction model and the actual insulation state;

[0043] A threshold value LO is set;

[0044] When the MSE value exceeds the pre-set threshold value, it indicates that there is a large deviation between the model prediction and the actual state, and the model parameters need to be adjusted through the back propagation algorithm to optimize the model, thereby reducing the MSE and improving the prediction accuracy.

[0045] As a preferred scheme of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, an abnormal warning mechanism is established based on the real-time insulation state prediction value, and once the insulation state is abnormal, the system immediately starts the warning to notify the operation and maintenance personnel to check and maintain.

[0046] An abnormal detection algorithm is used to identify the abnormal fluctuations of the real-time insulation state prediction value;

[0047] The insulation state prediction value is monitored in real time, and once the prediction value deviates from the normal range, the warning mechanism is triggered immediately;

[0048] Upon detecting an anomaly, the central processing unit immediately sends an alarm to the maintenance personnel and initiates a self-diagnostic program to find potential causes of the fault and take timely measures to prevent the insulation condition from deteriorating.

[0049] As a preferred embodiment of the transformer insulation field strength calculation method under the influence of moisture and temperature distribution described in this invention, the real-time monitoring of the predicted insulation state value triggers an early warning mechanism immediately upon detecting a deviation from the normal range, specifically as follows:

[0050] The dynamic threshold is compared with the real-time insulation status prediction value, and then the normal range, warning range, slightly abnormal range and severely abnormal range are divided.

[0051] A certain safety margin is set as △;

[0052] when When the system is in normal working condition, basic maintenance is performed regularly, including cleaning, lubrication, tightening, and functional testing, based on the equipment's usage frequency and historical maintenance records.

[0053] when When the system enters an early warning state, in addition to routine maintenance, it is necessary to increase the frequency of online monitoring, conduct remote diagnostics, and arrange professional personnel to conduct on-site inspections to ensure that any potential problems can be detected and dealt with in a timely manner.

[0054] when When the system detects a minor anomaly, it immediately notifies the operations and maintenance personnel to conduct an on-site inspection, while simultaneously initiating a self-diagnostic program to locate possible sources of failure and implement preliminary repair and adjustment measures.

[0055] when If the system is facing a serious anomaly and a major malfunction is imminent, immediately shut down the system for inspection to avoid further damage. At the same time, initiate a high-level troubleshooting process and replace damaged components if necessary.

[0056] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in the first aspect of the present invention.

[0057] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in the first aspect of the present invention.

[0058] The present application has the beneficial effects that: the present application realizes comprehensive monitoring and analysis of the temperature, humidity and electric field distribution inside the transformer by constructing a multi-physical field coupling simulation platform, in particular, the present application uses deep neural network technology to construct an insulation prediction model, dynamically adjusts the model parameters combined with real-time data, can not only accurately predict the change trend of the insulation state, but also quickly start the early warning mechanism when abnormal situation occurs, provides timely fault diagnosis information for the operation and maintenance personnel, the present application focuses on the intelligent analysis and early warning of the influence of humidity and temperature on the insulation state, provides a new solution for the health management of the transformer, and helps to improve the operation safety and economy of the power system. BRIEF DESCRIPTION OF DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0060] Figure 1 Flow chart of the transformer insulation field strength calculation method under the influence of water content and temperature distribution in embodiment 1.

[0061] Figure 2 Flow chart of the transformer insulation field strength calculation method under the influence of water content and temperature distribution in embodiment 1. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0063] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0064] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0065] Embodiment 1, reference Figure 1 and Figure 2 , the first embodiment of the present application, the embodiment provides a transformer insulation field strength calculation method under the influence of water content and temperature distribution, including the following steps:

[0066] S1 constructs a multi-physics coupling simulation platform for monitoring and analyzing the temperature, humidity and electric field distribution inside the transformer;

[0067] Based on the partial differential equation PDEs, a multi-physics coupling model is constructed for describing the dynamic changes of temperature T, humidity and electric field, and the core equations of the multi-physics coupling model include temperature diffusion equation, humidity diffusion equation and electric field distribution equation;

[0068] The temperature diffusion equation is expressed as:

[0069]

[0070] wherein, represents the rate of change of the temperature field with time, is a gradient operator for calculating the spatial gradient of the temperature field, k represents the thermal conductivity dependent on temperature and humidity, T represents the temperature, H represents the humidity, T(x, y, z, t) represents the temperature field, Q loss represents the heat loss function;

[0071] The humidity diffusion equation is expressed as:

[0072]

[0073] wherein, represents the rate of change of the humidity field with time, D(H) represents the humidity diffusion coefficient function, H(x, y, z, t) represents the humidity field, S m represents the humidity change;

[0074] The electric field distribution equation is expressed as:

[0075]

[0076] wherein, E(x, y, z, t) represents the electric field distribution, p is the charge density function, and represents the charge distribution affected by the temperature field, humidity field and electric field distribution;

[0077] The particle swarm optimization algorithm is adopted to dynamically update the PSO thermal conductivity, humidity diffusion coefficient and charge density, and the PSO algorithm can adjust these parameters according to real-time data, so that the model is more consistent with the actual working condition;

[0078] The central processing unit, sensor network, wireless communication module, data preprocessing algorithm and multi-physics coupling model are integrated to obtain a multi-physics coupling simulation platform, wherein the central processing unit is used to coordinate the processing of data flow and the operation of the multi-physics coupling model.

[0079] The heat loss function, the main source of heat loss is the resistance loss, and the resistance loss expression is:

[0080] Q loss (T,E)=σ(T)|E| 2 ;

[0081] where σ represents the electrical conductivity;

[0082] The humidity diffusion coefficient function represents the diffusion rate of water molecules in the medium, and the humidity diffusion coefficient usually changes with the increase of humidity, and the expression is:

[0083]

[0084] where D0 represents the diffusion coefficient of humidity, E a represents the activation energy, which represents the difficulty of water diffusion, and is related to the chemical properties of the medium, and R represents the universal gas constant;

[0085] The charge density function, in the transformer insulation material, the charge density is mainly generated by the polarization charge and ion migration, and the expression is:

[0086] ρ(T,H,E)=ρ p (T,H)+ρ m (E);

[0087] where p p (T,H) represents the temperature and humidity dependent polarization charge density, which reflects the polarization degree of the material at different temperatures and humidities, and p m (E) represents the electric field dependent migration charge density, which describes the degree of charge migration caused by the electric field.

[0088] S2 sets the humidity sensitive element array, collects humidity data, and transmits the humidity data to the central processor for processing;

[0089] Select the humidity sensitive element based on the principle of dielectric constant change. This element reflects the change of humidity by measuring the change of dielectric constant of the medium, and has the characteristics of high precision and fast response;

[0090] Use the gold electrode structure on the polyimide substrate, because polyimide has stable dielectric properties in a wide humidity range, and gold electrode is sensitive to humidity change, which can be effectively converted into electrical signal;

[0091] Adopt LoRa technology for wireless data transmission, because of its long distance and low power consumption characteristics, it is very suitable for use in such a closed environment inside the transformer;

[0092] Inside the transformer, the selected parts include winding, core and oil tank wall, integrated temperature sensor, humidity sensor and electric field sensor;

[0093] The selected site is divided into a uniform grid, with each grid cell representing a potential monitoring point. The size of the grid should take into account the expected gradient of humidity change and the required data resolution.

[0094] The distance between the computational elements is calculated, and a humidity-sensitive element is placed at the center of each grid cell to form a two-dimensional array, ensuring that each area is covered by at least one element. This avoids excessive overlap between elements and reduces data redundancy.

[0095] Each humidity-sensitive element is equipped with a microcontroller to continuously collect humidity data at a sampling frequency f s = 10 Hz.

[0096] The humidity data is encoded using Manchester encoding to improve the robustness and anti-interference ability of wireless transmission.

[0097] After Manchester encoding of the humidity data, it is packaged into data packets, each containing the element ID, encoded humidity data, timestamp, and CRC check code.

[0098] After receiving the data, the central processor first decodes the data packets and then uses a Kalman filter to preprocess the humidity data to eliminate noise and improve data quality.

[0099] A distributed Kalman filter algorithm is used to fuse data from multiple elements in the same area to obtain more accurate humidity estimates.

[0100] Based on real-time humidity data collected by the humidity-sensitive element array, an anomaly detection algorithm is used to detect outliers. When the humidity in a certain area exceeds the normal range, an early warning is triggered. Once an anomaly is detected, the central processor immediately sends an alert to the maintenance personnel and starts a self-diagnosis program to find potential fault causes.

[0101] The humidity diffusion coefficient function in the multi-physical field coupling model is dynamically adjusted based on real-time humidity data to ensure that the model parameters are consistent with the actual working conditions.

[0102] The distance between the computational elements is calculated as follows:

[0103] Set the target coverage C, which represents the proportion of the area effectively monitored by a single element to the total area. The maximum distance between elements is expressed as:

[0104]

[0105] where d represents the maximum distance between elements, and r represents the monitoring radius of each humidity-sensitive element.

[0106] Manchester coding is used to encode the humidity data, and the specific steps are as follows:

[0107] The humidity data is converted into binary format, and the humidity data is set as a 16-bit number. After quantization and encoding, it is converted into a binary string;

[0108] Manchester coding is used to convert each bit 0 and 1 into two pulse signals, and each pulse signal has a duration of half a bit period. Bit 0 is represented by a pulse from low to high, and bit 1 is represented by a pulse from high to low.

[0109] When the bit is 0, the signal remains low in the first half of the bit period, and rises to high in the second half;

[0110] When the bit is 1, the signal remains high in the first half of the bit period, and falls to low in the second half;

[0111] According to the sampling frequency, the bit period is calculated, which is equal to 1 divided by twice the sampling frequency.

[0112] S3 builds an insulation prediction model through a deep neural network algorithm, and inputs the historical humidity, historical temperature and insulation state data into the insulation prediction model to complete the training, and predicts the change trend of the insulation field strength under specific working conditions;

[0113] Insulation state data is collected through regular inspection of the transformer, including insulation resistance and dielectric spectrum;

[0114] Long short-term memory network (LSTM) is selected as the basis of the insulation prediction model because it is good at processing time series data and can capture long-term dependencies in data;

[0115] The insulation prediction model includes an input layer, several LSTM layers, a fully connected layer, and an output layer;

[0116] The LSTM layer is used to capture time series features, the fully connected layer is used for feature fusion, and the output layer gives the insulation state prediction;

[0117] The insulation prediction model is expressed as:

[0118]

[0119] Where, △I(t) represents the change of insulation state at time point t, α is a positive coefficient for adjusting the influence of temperature on the change of insulation state, e -λ(t) is a temperature-based exponential decay function, and β is another positive coefficient for adjusting the influence of humidity on the change of insulation state, represents that with the increase of humidity, the function value gradually increases from -0.5 to close to 0.5, indicating that the negative impact of humidity increase on the insulation state is enhanced, μ is a positive number, controlling the steepness of the humidity effect, γ is a positive coefficient, used to adjust the strength of the comprehensive influence of other physical parameters, w k represents the weight factor of k(T, H), w D represents the weight factor of D(H), w p represents the weight factor of P(T, H, E);

[0120] The insulation prediction model output layer is expressed as:

[0121]

[0122] wherein, represents the predicted value of the insulation state at time point t, I(t-1) represents the actual insulation state value at the previous time;

[0123] Extract the humidity, temperature and insulation state data related to the insulation state of the transformer from the historical data set;

[0124] Fill in the missing data by interpolation method to ensure the integrity and consistency of the data set, and use Z-score standardization to normalize the data, so that features of different scales are in the same order of magnitude, and improve the model training efficiency;

[0125] Based on the original humidity and temperature, use principal component analysis PCA to extract the cross features most influential to the insulation state prediction, which are used to capture the interaction between humidity and temperature on the insulation state;

[0126] Input the cross features into the insulation prediction model to output the predicted value of the insulation state, i.e. the change trend of the insulation field strength;

[0127] The specific steps of extracting cross features are as follows:

[0128] Set the standardized data matrix as X;

[0129] Calculate the covariance matrix C of X, expressed as:

[0130]

[0131] wherein, N represents the number of samples;

[0132] Calculate the eigenvalues and eigenvectors of the covariance matrix C, expressed as:

[0133] Cv = λv;

[0134] wherein, V represents the eigenvector, and λ represents the eigenvector;

[0135] The characteristic vectors are arranged in descending order of characteristic values, and the principal component represented by the characteristic vector with a larger characteristic value is more important.

[0136] The proportion of each characteristic value in the total characteristic value is accumulated, and the principal components whose cumulative contribution rate reaches 80% are selected as the final feature set.

[0137] The characteristic vector matrix is projected into the matrix composed of the selected first k characteristic vectors.

[0138] The projection formula is:

[0139] Y=XV k ;

[0140] Where V k represents the matrix composed of the first k characteristic vectors, and Y represents the projected data matrix.

[0141] S4 processes the real-time data and inputs it into the insulation prediction model to obtain the real-time insulation state prediction value, and dynamically adjusts the parameters of the insulation prediction model;

[0142] The humidity, temperature and electric field data inside the transformer are collected in real time through the sensor network;

[0143] Before the data is transmitted to the central processor, Manchester coding and Kalman filter are used to process the real-time data, improving the data quality and the robustness of transmission;

[0144] The processed real-time data is input into the insulation prediction model, and the model parameters are updated, especially those parameters that depend on temperature, humidity and electric field, humidity diffusion coefficient and charge density, which are dynamically adjusted according to real-time data to reflect the current working condition;

[0145] The thermal conductivity, humidity diffusion coefficient and charge density are dynamically updated using PSO algorithm to ensure that the model parameters are consistent with the actual working condition and improve the prediction accuracy;

[0146] After the real-time data is input into the insulation prediction model, the real-time insulation state prediction value is output;

[0147] The mean square error MSE is selected as the loss function to measure the difference between the prediction value of the insulation prediction model and the actual insulation state, and the expression is:

[0148]

[0149] Where N represents the number of samples, y i represents the true insulation state value of the i-th sample, represents the predicted insulation state value of the i-th sample;

[0150] Set threshold value LO;

[0151] When the MSE value exceeds the pre-set threshold value, it indicates that there is a large deviation between the model prediction and the actual state, and the model parameters need to be adjusted through the back propagation algorithm to optimize the model, thereby reducing the MSE and improving the prediction accuracy;

[0152] The continuous input of real-time data and the dynamic adjustment of model parameters form a closed loop, which continuously optimizes the prediction ability of the model, ensuring the real-time and accuracy of the insulation state evaluation.

[0153] S5 Based on the real-time insulation state prediction value, an abnormal warning mechanism is established. Once the insulation state is abnormal, the system immediately starts the warning and notifies the operation and maintenance personnel to check and maintain;

[0154] An abnormal detection algorithm is used to identify the abnormal fluctuations of the real-time insulation state prediction value, and the expression is:

[0155]

[0156] Where Θ(t) is the dynamic threshold value for judging whether the real-time insulation state is abnormal or not. When the real-time insulation state value exceeds this threshold value, the system will determine that it is an abnormal situation, represents the average insulation state value, σ t represents the standard deviation, Φ -1 represents the inverse cumulative distribution function, and p represents the abnormal occurrence probability threshold value, which can be set by oneself;

[0157] Real-time monitoring of the insulation state prediction value, once the prediction value deviates from the normal range, immediately trigger the warning mechanism;

[0158] The central processing unit immediately sends an alarm to the operation and maintenance personnel after detecting the abnormality, and starts the self-diagnosis program to find the potential fault cause, and takes timely measures to prevent the insulation state from deteriorating;

[0159] Compare the dynamic threshold value with the real-time insulation state prediction value, and then divide it into normal interval, warning interval, slight abnormal interval and serious abnormal interval;

[0160] Set a certain safety margin as Δ;

[0161] When , the system is in normal working state, and according to the use frequency and historical maintenance record of the equipment, regular cleaning, lubrication, tightening and function test basic maintenance are carried out;

[0162] When , the system enters the warning state, in addition to the regular maintenance, the online monitoring frequency needs to be increased, the remote diagnosis is carried out, and the professional personnel are arranged to carry out the on-site inspection, so as to ensure that any potential problem can be found and handled in time;

[0163] When a slight abnormality is determined, at this time, the operation and maintenance personnel are immediately notified to carry out on-site inspection, and at the same time, the self-diagnosis program is started to find the possible fault source and perform preliminary repair and adjustment measures;

[0164] When a serious abnormality is faced, there is a major fault about to occur, and immediate shutdown inspection is carried out to avoid greater damage, and at the same time, the high-level troubleshooting process is started, and the damaged parts are replaced if necessary.

[0165] The embodiment also provides a computer device suitable for the transformer insulation field strength calculation method under the influence of moisture and temperature distribution, which comprises a memory and a processor.

[0166] The computer device can be a terminal, and the computer device comprises a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0167] The embodiment also provides a storage medium on which a computer program is stored, the program being executed by a processor to implement the method for calculating the field strength of transformer insulation under the influence of moisture and temperature distribution as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0168] To sum up, the present application achieves comprehensive monitoring and analysis of the temperature, humidity and electric field distribution inside the transformer by constructing a multi-physics field coupling simulation platform. In particular, the present application uses deep neural network technology to construct an insulation prediction model and dynamically adjusts the model parameters in combination with real-time data, which not only accurately predicts the trend of the change in the insulation state, but also quickly starts the early warning mechanism in the event of an abnormal situation, thereby providing timely fault diagnosis information for the operation and maintenance personnel. The present application focuses particularly on the intelligent analysis and early warning of the influence of humidity and temperature on the insulation state, thereby providing a new solution for the health management of the transformer and helping to improve the operational safety and economy of the power system.

[0169] Embodiment 2

[0170] Referring to Table 1, the second embodiment of the present application is given, and experimental simulation data of the method for calculating the field strength of transformer insulation under the influence of moisture and temperature distribution are given to further verify the advancement of the present application.

[0171] To verify the effectiveness and innovation of the invention, a series of experiments were conducted to simulate the effects of humidity, temperature, and electric field distribution on the insulation state of the transformer under different operating conditions. The experiments were conducted in a laboratory environment using a multi-physics coupling simulation platform that integrated temperature, humidity, and electric field sensors, as well as an insulation prediction model based on deep neural networks. In the experiment, an array of 100 humidity-sensitive elements was first constructed, with a maximum distance of 0.5 meters between elements to ensure effective coverage of the entire transformer interior space. The elements collected data at a frequency of 10 Hz and transmitted it to the central processor for processing via LoRa wireless communication technology. In addition, various operating conditions were set, including different temperatures (20°C to 80°C), humidity (30% RH to 90% RH), and electric field intensity (0 V / m to 1000 V / m) to comprehensively evaluate the changing trend of the insulation state.

[0172] During the experiment, an insulation prediction model based on long short-term memory networks (LSTM) was constructed and trained based on historical data sets, including humidity, temperature, and insulation state data of the transformer under various operating conditions over the past year, totaling 10,000 records. After the model was trained, real-time data was used for testing to verify its prediction performance. To evaluate the prediction accuracy of the model, the mean squared error (MSE) was set as the loss function, with the goal of controlling the MSE within 0.01. In the experiment, an abnormal warning mechanism was also designed based on real-time insulation state predictions. When the deviation of the predicted value from the average value exceeds three times the standard deviation, the system will automatically start the warning and notify the operation and maintenance personnel for inspection.

[0173] Specifically as shown in Table 1:

[0174] Table 1 Experimental Record Table

[0175]

[0176]

[0177] Through analysis of the experimental data, it can be observed that as the temperature, humidity, and electric field intensity increase, the insulation state of the transformer shows a clear downward trend, for example, in operating conditions 001 to 100, the insulation state decreases from 0.98 to 0.65, which is consistent with the expected theoretical analysis. More importantly, the insulation prediction model based on deep neural networks shows excellent prediction ability. In all test operating conditions, the mean squared error (MSE) of the model's predicted insulation state and the actual value is less than 0.01, indicating that the model can accurately capture the dynamic trend of the insulation state as the operating conditions change.

[0178] Especially noteworthy is that the model can still maintain a low MSE under extreme working conditions of high temperature, high humidity and high electric field intensity, which reflects the robustness and stability of the model under complex environments. For example, in working condition 100, although the actual insulation state has dropped to 0.65, the model predicts a value of 0.66, and the MSE is only 0.001, which fully proves the prediction accuracy of the model. In addition, the abnormal warning mechanism also played a key role in the experiment, successfully identifying all cases where the predicted value deviated from the average value by more than 3 times the standard deviation, ensuring the safe operation of the system.

[0179] In summary, the multi-physics coupling simulation platform and insulation prediction model based on deep neural network proposed by the present application can not only accurately monitor and predict the insulation state change of the transformer under different working conditions, but also timely warn potential insulation faults, significantly improving the operation safety and reliability of the power system. This achievement has important innovative significance and broad application prospects in the field of electric power engineering.

[0180] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and they should be included in the scope of the claims of the present application.

Claims

1. A method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution, characterized in that: include, A multiphysics coupled simulation platform was constructed to monitor and analyze the temperature, humidity, and electric field distribution inside the transformer. Set up a humidity-sensitive element array to collect humidity data and transmit the humidity data to the central processing unit for processing; An insulation prediction model is constructed using a deep neural network algorithm. The model is trained by inputting historical humidity and temperature data along with insulation state data to predict the trend of insulation field strength under specific working conditions. Real-time data is processed and input into the insulation prediction model to obtain real-time insulation state prediction values, and the parameters of the insulation prediction model are dynamically adjusted. An anomaly early warning mechanism is established based on real-time insulation status prediction values. Once an insulation status anomaly is detected, the system immediately activates the early warning and notifies maintenance personnel to conduct inspections and maintenance. The insulation prediction model consists of an input layer, several LSTM layers, a fully connected layer, and an output layer. The LSTM layer is used to capture time series features, the fully connected layer is used for feature fusion, and the output layer provides an insulation state prediction. The insulation prediction model is expressed as follows: Where ΔI(t) represents the change in insulation state at time t, α is a positive coefficient used to adjust the degree of influence of temperature on the change in insulation state, and e -λT(t) This is a temperature-based exponential decay function, where β is another positive coefficient used to adjust the degree of influence of humidity on insulation state changes. This indicates that as humidity increases, the function value gradually increases from -0.5 to close to 0.5, signifying that the negative impact of humidity on insulation intensifies. μ is a positive number that controls the steepness of the humidity effect, γ is a positive coefficient used to adjust the intensity of the combined influence of other physical parameters, and wk represents the weighting factor of k(T,H). D w represents the weighting factor of D(H). ρ Represents the weighting factor of P(T,H,E); The output layer of the insulation prediction model is expressed as follows: in, I(t-1) represents the predicted value of the insulation state at time t, and I(t-1) represents the actual insulation state value at the previous time. Extract humidity, temperature, and insulation condition data related to transformer insulation condition from historical datasets; Interpolation methods were used to fill in missing data, and Z-score standardization was used to normalize the data. Based on the original humidity and temperature, principal component analysis (PCA) is used to extract the most influential cross features for insulation state prediction, which are used to capture the interaction between humidity and temperature on insulation state. The cross-features are input into the insulation prediction model, which outputs the predicted value of the insulation state, i.e. the trend of the change of the insulation field strength.

2. The method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in claim 1, characterized in that: The construction of a multiphysics coupled simulation platform for monitoring and analyzing the temperature, humidity, and electric field distribution inside the transformer involves the following steps: A multiphysics coupling model is constructed based on partial differential equations (PDEs) to describe the dynamic changes of temperature, humidity and electric field. The core equations of the multiphysics coupling model include the temperature diffusion equation, the humidity diffusion equation and the electric field distribution equation. The thermal conductivity, humidity diffusion coefficient, and charge density of PSO are dynamically updated using a particle swarm optimization algorithm. By integrating a central processing unit, sensor network, wireless communication module, data preprocessing algorithm, and multiphysics coupling model, a multiphysics coupling simulation platform is obtained. The central processing unit is used to coordinate the processing of data streams and the operation of the multiphysics coupling model.

3. The method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in claim 2, characterized in that: The set humidity-sensitive element array collects humidity data and transmits the humidity data to the central processing unit for processing. The specific steps are as follows: Inside the transformer, temperature sensors, humidity sensors, and electric field sensors are integrated into selected locations including the windings, core, and tank walls. Divide the selected area into a uniform grid, with each grid cell representing a potential monitoring point. The grid size should take into account the expected gradient of humidity changes and the required data resolution. The distance between the elements is calculated, and a humidity-sensitive element is placed at the center of each grid cell to form a two-dimensional array; Each humidity-sensitive element has a built-in microcontroller with a sampling frequency f s =Continuous collection of humidity data at 10Hz; The humidity data is encoded using Manchester encoding. After completing the Manchester encoding of the humidity data, it is encapsulated into a data packet; After receiving the data, the central processing unit first decodes the data packet, and then uses a Kalman filter to preprocess the humidity data to eliminate noise and improve data quality. A distributed Kalman filter algorithm is used to fuse data from multiple components in the same region; Based on real-time humidity data collected by a humidity-sensitive element array, an anomaly detection algorithm is used to detect outliers. When the humidity in a certain area exceeds the normal range, an early warning is immediately triggered. The humidity diffusion coefficient function in the multiphysics coupling model is dynamically adjusted based on real-time humidity data to ensure that the model parameters are consistent with the actual working conditions.

4. The method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in claim 1, characterized in that: The process of processing real-time data and inputting it into the insulation prediction model to obtain real-time insulation state prediction values, and dynamically adjusting the parameters of the insulation prediction model, specifically involves the following steps: Real-time data on humidity, temperature, and electric field inside the transformer are collected via a sensor network. Before the data is transmitted to the central processing unit, Manchester encoding and Kalman filtering are used to process the real-time data to improve data quality and transmission robustness. The processed real-time data is fed into the insulation prediction model, and the model parameters are updated simultaneously. The PSO algorithm is used to dynamically update thermal conductivity, humidity diffusion coefficient, and charge density. After real-time data is input into the insulation prediction model, the real-time insulation state prediction value is output. The mean squared error (MSE) is chosen as the loss function to measure the difference between the predicted values ​​of the insulation prediction model and the actual insulation state. Set the threshold LO; When the MSE value exceeds the preset threshold, it indicates that there is a large deviation between the model prediction and the actual state. It is necessary to adjust the model parameters and optimize the model through the backpropagation algorithm to reduce the MSE and improve the prediction accuracy.

5. The method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in claim 1, characterized in that: The aforementioned anomaly early warning mechanism, based on real-time insulation status prediction values, will immediately activate an early warning system upon detecting an insulation status anomaly, notifying maintenance personnel to conduct inspections and maintenance. The specific steps are as follows: Anomaly detection algorithms are used to identify abnormal fluctuations in real-time insulation status prediction values; Real-time monitoring of insulation status prediction values; once a prediction value deviates from the normal range, an early warning mechanism is immediately triggered. Upon detecting an anomaly, the central processing unit immediately sends an alarm to the maintenance personnel and initiates a self-diagnostic program to find potential causes of the fault and take timely measures to prevent the insulation condition from deteriorating.

6. The method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in claim 5, characterized in that: The real-time monitoring of the insulation status prediction value will trigger an early warning mechanism immediately if the prediction value deviates from the normal range. Specifically: The dynamic threshold is compared with the real-time insulation status prediction value, and then the normal range, warning range, slightly abnormal range and severely abnormal range are divided. A certain safety margin is set as △; when When the system is in normal working condition, basic maintenance is performed regularly, including cleaning, lubrication, tightening, and functional testing, based on the equipment's usage frequency and historical maintenance records. when When the system enters an early warning state, in addition to routine maintenance, it is necessary to increase the frequency of online monitoring, conduct remote diagnostics, and arrange professional personnel to conduct on-site inspections to ensure that any potential problems can be detected and dealt with in a timely manner. when When the system detects a minor anomaly, it immediately notifies the operations and maintenance personnel to conduct an on-site inspection, while simultaneously initiating a self-diagnostic program to locate possible sources of failure and implement preliminary repair and adjustment measures. when If the system is facing a serious anomaly and a major malfunction is imminent, immediately shut down the system for inspection to avoid further damage. At the same time, initiate a high-level troubleshooting process and replace damaged components if necessary.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for calculating the transformer insulation field strength under the influence of moisture and temperature distribution as described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for calculating the insulation field strength of a transformer under the influence of moisture and temperature distribution as described in any one of claims 1 to 6.

Images