Insulator simulation icing test method and system

Abstract

The invention relates to the technical field of environment simulation and electrical insulation, in particular to an insulator simulation icing test method and system. Collecting icing environment data, and deploying insulator icing simulation equipment; an insulator simulation icing environment is constructed, a control unit is used for adjustment, and the icing process in the natural environment is simulated; the icing condition is monitored, voltage distribution and current data of the insulator under different icing conditions are tested, and a deep learning model is used for adjustment; and analyzing an icing result by using the optimized deep learning model, and evaluating the performance of the insulator under the icing condition. Through natural icing environment simulation, real-time data monitoring, automatic parameter adjustment and deep learning optimization, the defects of a traditional method in the aspects of accurate simulation, data acquisition and performance evaluation are overcome, and the accuracy and efficiency of insulator ice resistance research are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental simulation and electrical insulation, and in particular to an insulator simulated icing test method and system. Background Art

[0002] In the field of electrical engineering, the performance of insulators is crucial to ensure the safe operation of power systems. However, it is difficult to test the icing performance of insulators in actual environments. Because the structure and shape of insulators are relatively complex, it is extremely difficult to predict their icing. At present, most methods are to conduct artificial icing experiments in artificial climate laboratories. The common method at home and abroad is to monitor the icing of insulators by the thickness of ice on a rotating cylinder. This is only a method to qualitatively judge the quality of insulator icing, and the establishment of an artificial climate laboratory has many requirements and high professional level.

[0003] Therefore, developing a test device and test method that can simulate a real icing environment, is easy to carry, and can accurately test the performance of insulators is of great significance for improving the design level of insulators and ensuring the stable operation of power systems. Summary of the invention

[0004] In view of the above problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the present invention provides an insulator simulated icing test method, which can solve the problems that traditional methods are difficult to accurately simulate the icing process in the natural environment, the insulator performance evaluation under icing conditions is incomplete, and the adjustment of environmental parameters and the simulation of the icing process usually rely on manual operation, which is inefficient and has large errors.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an insulator simulated icing test method, comprising: collecting icing environment data and deploying insulator simulated icing equipment; constructing an insulator simulated icing environment, using a control unit to adjust, and simulating the icing process in a natural environment; monitoring the icing condition, testing the voltage distribution and current data of the insulator under different icing conditions, and using a deep learning model to adjust; using an optimized deep learning model to analyze the icing results and evaluate the insulator performance under icing conditions.

[0007] As a preferred solution of the insulator simulation icing test method described in the present invention, the insulator simulation icing equipment includes: the left side of the test equipment is the control end, which includes a temperature control device, a humidity control device and a fan control device; the middle is the insulator part, and insulators of various materials are used according to the test needs. A monitoring sensor device, a voltage and current measuring device are configured; the right side is the simulated precipitation control device and the signal end, which are responsible for monitoring the data transmission and receiving function; the transmission module collects and analyzes the signal, and transmits it to the host computer through the transmission module to complete the signal processing and transmission; the insulator part is configured with a wire interface section to connect an external test transformer.

[0008] As a preferred embodiment of the insulator simulated icing test method of the present invention, the construction of the simulated icing environment of the insulator includes lowering the temperature of the test environment to the icing temperature through a temperature control device, starting a humidity control device to adjust the humidity, and setting the wind speed through a fan control device to simulate the meteorological conditions in the natural environment, applying an icing solution to the insulator through a spray system to simulate the precipitation process;

[0009] A fluid dynamics model for the ice-covered simulation environment is established, taking into account the flow of air and water droplets. The continuity equation is expressed as:

[0010]

[0011] Where ρ is the fluid density, u is the fluid velocity vector, f(ρ, u, t) is the coupled source term of water droplet deposition and air flow, is the gradient, t is the time, For partial guidance;

[0012] Considering the water droplet deposition and ice growth, the momentum equation is expressed as,

[0013]

[0014] Where g(ρ, T) is the coupled source term of ice growth and temperature change, η is the fluid dynamic viscosity, F is the volume force, and P is the fluid pressure;

[0015] Considering the growth and melting of ice, the energy equation is expressed as,

[0016]

[0017] Among them, λ is thermal conductivity, q is heat source term, e is energy density, T is temperature, and h(ρ, T) is the energy source term for ice growth and melting.

[0018] As a preferred solution of the insulator simulated icing test method of the present invention, the simulating icing process in the natural environment includes controlling the operation of the simulated temperature control device, the simulated precipitation control device and the fan device, simulating the icing growth process under different conditions, and during the icing growth process, the monitoring device monitors the icing state of the insulator in real time;

[0019] The ice growth rate is used to describe the growth of ice in unit time. The formula is:

[0020] R i =α·(RH-RH start )·(T ice -T)·v

[0021] Among them, R i is the ice growth rate, α is the ice growth coefficient, RH is the relative humidity, RH start is the relative humidity threshold for ice formation, T ice is the freezing temperature, V is the wind speed;

[0022] The ice thickness is calculated by time-integrating the ice growth rate, and the formula is expressed as:

[0023]

[0024] Where H(t) is the ice thickness at time t, H 0 is the initial ice thickness;

[0025] Monitor the icing condition and test the voltage distribution and current data of insulators under different icing conditions.

[0026] In the process of simulating ice coating, voltage is applied to the insulator, and the voltage distribution of the insulator is monitored in real time by a voltage measuring device, and the current data flowing through the insulator is measured and recorded in real time by a current measuring device;

[0027] The voltage distribution of the insulator under ice conditions is described by the potential gradient along the length of the insulator, which is expressed as follows:

[0028]

[0029] Where V(x, t) is the voltage at position x at time t, V 0 is the initial voltage, L is the total length of the insulator, and f(H(t)) is the function of the influence of ice thickness on voltage distribution;

[0030] The current formula of the insulator under ice conditions is expressed as:

[0031]

[0032] R(H(t))=R 0 ·(1+γ·H(t))

[0033] Where I(t) is the current at time t, R(H(t)) is the resistance that changes with ice thickness, and R 0 is the initial resistance, and γ is the influence coefficient of ice coverage on resistance.

[0034] As a preferred solution of the insulator simulation icing test method described in the present invention, the control unit adjustment includes: after building the insulator icing simulation environment, the signal end collects and analyzes the signal, and transmits it to the control unit of the host computer through the transmission module, and the control unit analyzes the difference, which is described by the weighted Euclidean distance, and the formula is expressed as follows:

[0035]

[0036] Among them, Δ is the difference, w T 、w RH and w v are the weights of temperature, humidity and wind speed respectively, T o RH o and V o They are target temperature, target humidity and target wind speed respectively;

[0037] If Δ≥α, the system determines that the icing state is a high-difference state, uses the automated adjustment model to adjust the environmental parameters, checks whether there are faults or configuration errors, and strengthens real-time data monitoring to ensure the effectiveness of the adjustment measures;

[0038] If β≤Δ<α, the system determines that the icing state is a medium difference state. According to the specific value of the difference, the environmental control parameters are adjusted. The system regularly feeds back the adjustment effect and evaluates whether a secondary adjustment is needed.

[0039] If Δ<β, the system determines that the icing state is a low-difference state, maintains the current environmental settings without adjustment, and regularly evaluates insulator performance to ensure long-term stability;

[0040] Among them, α and β are high difference and low difference thresholds respectively;

[0041] The automatic adjustment model formula is expressed as:

[0042] Δ ad =A·Δ+B·Δ′

[0043] Among them, Δ ad is the adjustment amount, A and B are different adjustment coefficients, Δ′ is the parameter of ice coverage, voltage distribution and current conditions. When optimizing the insulator performance, the deep learning model is used for tuning;

[0044] The temperature control device, the simulated precipitation control device and the fan control device are controlled to make adjustments until the target parameter values ​​are met.

[0045] As a preferred solution of the insulator simulation icing test method described in the present invention, the deep learning model includes learning the relationship between insulator performance and icing state, and predicting the insulator performance under different icing conditions;

[0046] The deep learning model includes an input layer, a hidden layer and an output layer;

[0047] The input layer, input feature X = [T, RH, v , H, R i , I, V];

[0048] The hidden layer includes multiple fully connected layers, and the calculation formula of each layer is H l =f(W l ·H l-1 +b 1 );

[0049] Among them, H l is the output of the first layer, W l , b 1 are the weight and bias of the first layer respectively, and f is the activation function;

[0050] The output layer outputs the predicted electrical performance of the insulator under ice-covered conditions, and the formula is expressed as:

[0051] Y=[V drop , I leak , Z]

[0052] Among them, Y is the predicted value of insulator performance, V drop is the voltage drop under ice conditions, I leak is the leakage current under ice-covered state, Z is the insulation impedance;

[0053] According to the insulator performance that needs to be tested and the predicted environmental parameters, the transmission control unit is regulated.

[0054] As a preferred embodiment of the insulator simulation icing test method of the present invention, the insulator performance evaluation under icing conditions includes evaluating the insulator performance under icing conditions, analyzing the data collected during the test, including the growth state of icing on the insulator, voltage distribution and current data, studying the icing law of the insulator through data analysis, evaluating the anti-icing ability of the insulator, comparing the test results with the standard values, and optimizing the anti-icing performance of the insulator according to the evaluation results;

[0055] The optimization of the deep learning model includes initializing the deep learning model, and the deep learning model prediction function formula is expressed as:

[0056] Y i =f(X i ; Θ)

[0057] Among them, Yi is the predicted value of the i-th input data, X i is the i-th input data, Θ is the model parameter;

[0058] Use the preset icing environment data for training, initialize the population of the insulator performance optimization algorithm, including icing conditions, voltage distribution, and current conditions, use the parameter combination in the current population to adjust the environmental conditions, and collect new data. Use the optimized deep learning model to predict the insulator performance and evaluate the prediction performance of the model. The evaluation formula is expressed as:

[0059]

[0060] Where E is the total error, τ is the time step, K is the number of performance parameters, and w k is the weight of the kth performance parameter, Y pred,tk、 Y actual, tk are the predicted value and actual value of the kth performance parameter at time t, respectively;

[0061] like The system judges that the model prediction is close to the actual performance, the insulator performance is good and the model is accurate. The system determines that the model and the insulator test device need to be adjusted, among which, is the error threshold;

[0062] The evaluation results are used to optimize the model. The optimization content includes temperature control, humidity control, wind speed control, and adjustment of current and voltage regulation parameters. According to the results of the optimization selection, the environmental condition parameters are adjusted, and the output is adjusted through the control unit to adjust the insulator characteristics. New data is collected in the adjusted environment for training the deep learning model. The environmental parameters and insulator data are repeatedly updated until the stopping conditions are met to obtain the optimization direction of the insulator performance.

[0063] Another object of the present invention is to provide an insulator simulated icing test system to solve the shortcomings of traditional methods in simulating the icing process in the natural environment, real-time monitoring data, environmental parameter adjustment and performance evaluation. By constructing an accurate icing environment, the natural icing process is simulated using a temperature, humidity, wind speed control system and a spray system. Monitoring sensors, voltage and current measuring devices are configured to achieve real-time data collection and analysis. Through the automated adjustment model, environmental parameters are adjusted according to real-time data to ensure the accuracy of the test conditions. At the same time, a deep learning model is applied to comprehensively evaluate and optimize the electrical performance of insulators under different icing conditions. This invention not only improves the accuracy and efficiency of icing tests, but also provides reliable data support and technical means for the research and optimization of the anti-icing performance of insulators.

[0064] As a preferred solution of the insulator simulation icing test system described in the present invention, it includes: an environment construction module, an icing detection module, a data analysis module and a performance evaluation and optimization module;

[0065] The environment construction module collects icing environment data of the target area, deploys insulator icing simulation equipment, adjusts parameters through the control unit, simulates the icing process in the natural environment, and constructs an icing environment that meets the experimental requirements;

[0066] The icing detection module, the monitoring device monitors the icing state of the insulator in real time, tests the voltage distribution and current data of the insulator under different icing conditions, and transmits the data to the host computer through the transmission module for processing and analysis;

[0067] The data analysis module studies the icing law of insulators through data analysis, evaluates the anti-icing ability of insulators, establishes and trains a deep learning model, learns the relationship between insulator performance and icing state, and predicts insulator performance under different icing conditions;

[0068] The performance evaluation and optimization module evaluates the electrical performance of the insulator based on the prediction results of the deep learning model, optimizes and adjusts the anti-icing performance of the insulator, continuously adjusts the environmental parameters and experimental conditions based on the analysis and evaluation results, optimizes the deep learning model, and repeats the optimization cycle until the experimental requirements are met.

[0069] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of any one of the methods for simulating icing test of insulators are implemented.

[0070] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of any one of the methods of a simulated icing test for an insulator are implemented.

[0071] Beneficial effects of the present invention: The method of the present invention can simulate the icing conditions in the real environment and accurately test the performance of the conductor. The method can be used to study the parameters of the pollution accumulation characteristics and flashover voltage of the insulator, and provide a basis for the optimal design of the insulator. The method is simple to operate, safe and reliable, and has high practical value and application prospects. Through technical means such as temperature control, spraying precipitation, and fans, the method can truly simulate the process and conditions of icing of the insulator in the actual environment. This makes the test results more reference-worthy and practical. The method simultaneously measures multiple parameters, including conductor voltage, current, etc., during the simulated icing process. The synchronous measurement of these parameters can more comprehensively evaluate the performance of the insulator and provide a more accurate basis for the optimal design of the insulator. The method uses an automated control system to control and monitor the test process, which greatly improves the accuracy and reliability of the test. At the same time, it reduces the errors and inconveniences of manual operation and improves the test efficiency. Through the signal transmission module, the method can realize remote monitoring and data sharing of the test process. The remote monitoring center can obtain test data and monitoring information in real time, remotely control and guide the test process, and greatly improve the flexibility and convenience of the test. At the same time, data sharing can promote academic exchanges and technical cooperation, and promote the research and development of conductor anti-icing technology. The insulator simulation icing test equipment of the present invention can simulate icing conditions in a real environment, and provides an effective means for studying the performance of insulators. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0073] Figure 1 A block diagram of an insulator simulated icing test device for an insulator simulated icing test method provided by an embodiment of the present invention.

[0074] Figure 2 A diagram of a natural environment insulator icing test platform for an insulator simulation icing test method provided by an embodiment of the present invention.

[0075] Figure 3 A flowchart of an icing test procedure for an insulator simulation icing test method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0077] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides an insulator simulated icing test method, comprising:

[0078] S1: Collect icing environment data and deploy insulator simulation icing equipment.

[0079] It should be noted that if Figure 1 As shown, the insulator simulation icing equipment includes: the left side of the test equipment is the control end, which includes a temperature control device, a humidity control device and a fan control device; the middle is the insulator part, and insulators of various materials are used according to the test needs. A monitoring sensor device, a voltage and current measuring device are configured; the right side is the simulated precipitation control device and the signal end, which are responsible for monitoring the data transmission and receiving function. The transmission module collects and analyzes the signal, and transmits it to the host computer through the transmission module to complete the signal processing and transmission. The insulator part is configured with a wire interface section to connect an external test transformer.

[0080] S2: Construct an insulator to simulate the icing environment and use the control unit to adjust and simulate the icing process in the natural environment.

[0081] It should be noted that the construction of the simulated icing environment for the insulator includes lowering the temperature of the test environment to the icing temperature through a temperature control device, starting a humidity control device to adjust the humidity, and setting the wind speed through a fan control device to simulate the meteorological conditions in the natural environment, applying an icing solution to the insulator through a spray system to simulate the precipitation process;

[0082] A fluid dynamics model for the ice-covered simulation environment is established, taking into account the flow of air and water droplets. The continuity equation is expressed as:

[0083]

[0084] Where ρ is the fluid density, u is the fluid velocity vector, f(ρ, u, t) is the coupled source term of water droplet deposition and air flow, is the gradient, t is the time, For partial guidance;

[0085] Considering the water droplet deposition and ice growth, the momentum equation is expressed as,

[0086]

[0087] Where g(ρ, T) is the coupled source term of ice growth and temperature change, η is the fluid dynamic viscosity, F is the volume force, and P is the fluid pressure;

[0088] Considering the growth and melting of ice, the energy equation is expressed as,

[0089]

[0090] Among them, λ is thermal conductivity, q is heat source term, e is energy density, T is temperature, and h(ρ, T) is the energy source term for ice growth and melting.

[0091] It should be noted that fluid dynamics models are extremely important in simulating insulator icing tests, and can accurately simulate the physical phenomena in the ice formation process, including fluid flow, heat transfer, and material conversion. By solving these equations, the icing process can be predicted and controlled, thereby achieving higher accuracy and reliability in design and testing.

[0092] Furthermore, the simulation of the icing process in the natural environment includes controlling the operation of the simulated temperature control device, the simulated precipitation control device and the fan device, simulating the icing growth process under different conditions, and during the icing growth process, the monitoring device monitors the icing state of the insulator in real time;

[0093] The ice growth rate is used to describe the growth of ice in unit time. The formula is:

[0094] R i =α·(RH-RH start )·(T ice -T)·v

[0095] Among them, R i is the ice growth rate, α is the ice growth coefficient, RH is the relative humidity, RH start is the relative humidity threshold for ice formation, T ice is the freezing temperature, V is the wind speed;

[0096] The ice thickness is calculated by time-integrating the ice growth rate, and the formula is expressed as:

[0097]

[0098] Where H(t) is the ice thickness at time t, H 0 is the initial ice thickness;

[0099] Monitor the icing condition and test the voltage distribution and current data of insulators under different icing conditions.

[0100] In the process of simulating ice coating, voltage is applied to the insulator, and the voltage distribution of the insulator is monitored in real time by a voltage measuring device, and the current data flowing through the insulator is measured and recorded in real time by a current measuring device;

[0101] The voltage distribution of the insulator under ice conditions is described by the potential gradient along the length of the insulator, which is expressed as follows:

[0102]

[0103] Where V(x, t) is the voltage at position x at time t, V 0 is the initial voltage, L is the total length of the insulator, and f(H(t)) is the function of the influence of ice thickness on voltage distribution;

[0104] The current formula of the insulator under ice conditions is expressed as:

[0105]

[0106] R(H(t))=R 0 ·(1+γ·H(t))

[0107] Where I(t) is the current at time t, R(H(t)) is the resistance that changes with ice thickness, and R 0 is the initial resistance, and γ is the influence coefficient of ice coverage on resistance.

[0108] S3: Monitor the icing condition, test the voltage distribution and current data of insulators under different icing conditions, and make adjustments using a deep learning model.

[0109] It should be noted that the control unit adjustment includes, after building the insulator ice coating simulation environment, the signal end collects and analyzes the signal, and transmits it to the control unit of the host computer through the transmission module, and the control unit analyzes the difference, which is described by the weighted Euclidean distance, and the formula is expressed as follows:

[0110]

[0111] Among them, Δ is the difference, w T 、w RH and w v are the weights of temperature, humidity and wind speed respectively, T o RH o and v o They are target temperature, target humidity and target wind speed respectively;

[0112] If Δ≥α, the system determines that the icing state is a high-difference state, uses an automated adjustment model to adjust environmental parameters, checks whether there are faults or configuration errors, strengthens real-time data monitoring, and ensures that the performance of insulators in a simulated icing environment is stable and reliable.

[0113] If β≤Δ<α, the system determines that the icing state is a medium difference state. According to the specific value of the difference, the environmental control parameters are adjusted. The system regularly feeds back the adjustment effect and evaluates whether a secondary adjustment is needed.

[0114] If Δ<β, the system determines that the icing state is a low-difference state, maintains the current environmental settings without adjustment, and regularly evaluates insulator performance to ensure long-term stability.

[0115] Among them, α and β are high difference and low difference thresholds respectively;

[0116] The automatic adjustment model formula is expressed as:

[0117] Δ ad =A·Δ+B·Δ

[0118] Among them, Δ ad is the adjustment amount, A and B are different adjustment coefficients, Δ is the parameter of ice coverage, voltage distribution and current conditions. When optimizing the insulator performance, the deep learning model is used for tuning;

[0119] The temperature control device, the simulated precipitation control device and the fan control device are controlled to make adjustments until the target parameter values ​​are met.

[0120] Furthermore, the deep learning model includes learning the relationship between insulator performance and icing conditions, and predicting insulator performance under different icing conditions;

[0121] The deep learning model includes an input layer, a hidden layer and an output layer;

[0122] The input layer, input feature X = [T, RH, V , H, R i , I, V];

[0123] The hidden layer includes multiple fully connected layers, and the calculation formula of each layer is H l =f(W l ·H l-1 +b l );

[0124] Among them, H l is the output of the first layer, W l 、b l are the weight and bias of the first layer respectively, and f is the activation function;

[0125] The output layer outputs the predicted electrical performance of the insulator under ice-covered conditions, and the formula is expressed as:

[0126] Y=[V drop , I leak, Z]

[0127] Among them, Y is the predicted value of insulator performance, V drop is the voltage drop under ice conditions, I leak is the leakage current under ice-covered state, Z is the insulation impedance;

[0128] According to the insulator performance that needs to be tested and the predicted environmental parameters, the transmission control unit is regulated.

[0129] It should be noted that this test method uses an insulator icing simulation device to simulate the ice coverage on the surface of the insulator in the natural environment. By adjusting the temperature and humidity in the laboratory, the performance of the insulator under freezing conditions is simulated, providing a scientific basis for evaluating the reliability of the insulator in the actual environment. The test conditions can also be adjusted to simulate ice coverage under different meteorological conditions, explore the performance of the insulator under various climatic conditions, and ensure the accuracy and reliability of the simulated ice layer during the test.

[0130] S4: Analyze icing results using an optimized deep learning model and evaluate insulator performance under icing conditions.

[0131] It should be noted that the evaluation of the insulator performance under icing conditions includes evaluating the insulator performance under icing conditions, analyzing the data collected during the test, including the growth state of ice on the insulator, voltage distribution and current data, studying the icing law of the insulator through data analysis, evaluating the anti-icing ability of the insulator, comparing the test results with the standard values, and optimizing the anti-icing performance of the insulator according to the evaluation results;

[0132] The optimization of the deep learning model includes initializing the deep learning model, and the deep learning model prediction function formula is expressed as:

[0133] Y i =f(X i ; Θ)

[0134] Among them, Yi is the predicted value of the i-th input data, X i is the i-th input data, Θ is the model parameter;

[0135] Use the preset icing environment data for training, initialize the population of the insulator performance optimization algorithm, including icing conditions, voltage distribution, and current conditions, use the parameter combination in the current population to adjust the environmental conditions, and collect new data. Use the optimized deep learning model to predict the insulator performance and evaluate the prediction performance of the model. The evaluation formula is expressed as:

[0136]

[0137] Where E is the total error, τ is the time step, K is the number of performance parameters, and w k is the weight of the kth performance parameter, Y pred，tk , Y actual，tk are the predicted value and actual value of the kth performance parameter at time t, respectively;

[0138] like The system judges that the model prediction is close to the actual performance, the insulator performance is good and the model is accurate. The system determines that the model and the insulator test device need to be adjusted, among which, is the error threshold;

[0139] The evaluation results are used to optimize the model. The optimization content includes temperature control, humidity control, wind speed control, and adjustment of current and voltage regulation parameters. According to the results of the optimization selection, the environmental condition parameters are adjusted, and the output is adjusted through the control unit to adjust the insulator characteristics. New data is collected in the adjusted environment for training the deep learning model. The environmental parameters and insulator data are repeatedly updated until the stopping conditions are met to obtain the optimization direction of the insulator performance.

[0140] The above is a schematic scheme of an insulator simulated icing test method of this embodiment. It should be noted that the technical scheme of the insulator simulated icing test system and the technical scheme of the insulator simulated icing test method described above belong to the same concept, and the details of the technical scheme of the insulator simulated icing test system not described in detail in this embodiment can be referred to the description of the technical scheme of the insulator simulated icing test method described above.

[0141] The insulator simulation icing test system in this embodiment includes: an environment construction module, an icing detection module, a data analysis module and a performance evaluation and optimization module;

[0142] The environment construction module collects icing environment data of the target area, deploys insulator icing simulation equipment, adjusts parameters through the control unit, simulates the icing process in the natural environment, and constructs an icing environment that meets the experimental requirements;

[0143] The icing detection module, the monitoring device monitors the icing state of the insulator in real time, tests the voltage distribution and current data of the insulator under different icing conditions, and transmits the data to the host computer through the transmission module for processing and analysis;

[0144] The data analysis module studies the icing law of insulators through data analysis, evaluates the anti-icing ability of insulators, establishes and trains a deep learning model, learns the relationship between insulator performance and icing state, and predicts insulator performance under different icing conditions;

[0145] The performance evaluation and optimization module evaluates the electrical performance of the insulator based on the prediction results of the deep learning model, optimizes and adjusts the anti-icing performance of the insulator, continuously adjusts the environmental parameters and experimental conditions based on the analysis and evaluation results, optimizes the deep learning model, and repeats the optimization cycle until the experimental requirements are met.

[0146] This embodiment further provides a computing device, which is applicable to the case of the insulator simulated icing test method, including:

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0148] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0149] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0150] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0151] Example 2, reference Figure 2 and Figure 3 , which is the second embodiment of the present invention, provides an insulator simulated icing test method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0152] Build a research platform, such as Figure 2 As shown in the figure, various live tests on iced insulators are carried out, such as live iced state, flashover research, etc. The test power supply can be provided by a 150kV / 150kVA test transformer, and the technical parameters meet the research of discharge test on iced insulators. The nozzle of the precipitation simulation device is made according to the recommendation of the International Electrotechnical Commission (IEC), and the air and water intake of the nozzle are adjusted to effectively control the diameter of the water droplets. The wind speed control system has an adjustment range of 1-12m / s, and the relative humidity can be controlled at 10%-100%, which can simulate the ice condition in different environments.

[0153] Two test areas are set up in the laboratory, one is equipped with the insulator icing test platform of the present invention, and the other is equipped with a traditional artificial climate simulation system. The test samples are selected from the same type of transmission line materials and insulators for the two test areas.

[0154] The insulator icing test method of the present invention is as follows Figure 3As shown, first, an external test transformer is connected as needed to apply voltage to a predetermined value; second, the test environment is simulated, and the control system simulates the set temperature, humidity, wind speed and other meteorological conditions to build a test environment similar to the actual icing environment. Then, the insulator icing simulation is carried out. In the set test environment, the icing solution is applied to the insulator through the spray system to simulate the icing process of the insulator in the natural environment; whether the icing is completed in the judgment stage, if it is, the voltage distribution of the insulator is monitored in real time through the voltage measuring device, and the current data of the insulator is measured and recorded in real time through the current measuring device. Carry out test data collection and analysis. During the entire simulated icing process, the system automatically collects voltage, current and other data, and processes and analyzes various monitoring data through the signal end. After the test, the test results are evaluated and compared. According to the collected data, the performance of the insulator in the simulated icing environment is evaluated, and the results are compared with the standard value. The automatic control of the test process is to automatically control the test environment simulation, insulator icing simulation, voltage application and measurement, current measurement and recording steps through the control system. The final step is to optimize the ice formation process. According to the test results and data analysis, the ice formation process is optimized to improve the accuracy and reliability of the simulation. The various modules are managed in a unified manner through the integrated control system, and the test process and the operating status of the equipment are monitored in real time through the monitoring system.

[0155] Before setting up the experiment, the operator of the traditional artificial climate simulation system manually adjusts various environmental equipment in the laboratory, including temperature, humidity controllers and fans, to build a test environment similar to the actual icing environment. At the beginning of the icing experiment, the sprinkler system is manually turned on, and the water pressure and sprinkler are adjusted to simulate the icing process of natural rain and snow. The icing process is monitored and recorded, and the thickness and state of the icing are manually measured. After the data is collected, the data is manually processed and analyzed. After the experiment is completed, the experimental equipment is manually turned off, and the data is sorted and analyzed to produce the final report. The experimental results are shown in Table 1.

[0156] Table 1. Experimental data comparison table

[0157] parameter Our technical solution Traditional technical solutions Ice coating rate (mm / h) 5 4.6 Final ice thickness (mm) 10.55 9.76 Operation automation level 92％ 75％ Response time (t) 2 3 Voltage drop(V) 0.8 1.1 Leakage current (mA) 5.2 5.8

[0158] The icing rate of our technical solution is slightly higher than that of the traditional solution, and it can form the target icing thickness faster. The formed icing thickness is slightly higher than that of the traditional solution, indicating that it is more effective in simulating the natural icing environment.

[0159] The degree of automation of our technical solution is significantly higher than that of traditional solutions, which reduces manual intervention, improves the accuracy and efficiency of the experiment, and the response time of our technical solution is also shorter than that of traditional solutions. The overall performance is better and can more effectively simulate the natural ice environment.

[0160] The voltage drop and leakage current of our technical solution are also lower than those of the traditional solution, indicating that our technical solution has more advantages in maintaining insulation performance.

[0161] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention 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 invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An insulator simulated icing test method, characterized in that: include, Collect icing environment data and deploy insulator icing simulation equipment; Construct an insulator to simulate the icing environment, and use the control unit to adjust and simulate the icing process in the natural environment; Monitor icing conditions, test the voltage distribution and current data of insulators under different icing conditions, and use deep learning models to make adjustments; The icing results were analyzed using an optimized deep learning model to evaluate the performance of insulators under icing conditions.

2. The insulator simulated icing test method according to claim 1, characterized in that: The insulator simulation icing equipment includes: the left side of the test equipment is the control end, which includes a temperature control device, a humidity control device and a fan control device; the middle is the insulator part, and insulators of various materials are used according to the test needs. A monitoring sensor device, a voltage and current measuring device are configured; the right side is the simulated precipitation control device and the signal end, which are responsible for monitoring the data transmission and receiving function. The transmission module collects and analyzes signals, and transmits them to the host computer through the transmission module to complete signal processing and transmission. The insulator part is configured with a wire interface section to connect an external test transformer.

3. The insulator simulated icing test method according to claim 2, characterized in that: The construction of the simulated icing environment for the insulator includes lowering the temperature of the test environment to an icing temperature by a temperature control device, starting a humidity control device to adjust the humidity, and setting a wind speed by a fan control device to simulate meteorological conditions in a natural environment, applying an icing solution to the insulator by a spray system to simulate a precipitation process; A fluid dynamics model for the ice-covered simulation environment is established, taking into account the flow of air and water droplets. The continuity equation is expressed as: Where ρ is the fluid density, u is the fluid velocity vector, and f(ρ,u,t) is the coupled source term of water droplet deposition and air flow. is the gradient, t is the time, For partial guidance; Considering the water droplet deposition and ice growth, the momentum equation is expressed as, Where g(ρ,T) is the coupled source term of ice growth and temperature change, η is the fluid dynamic viscosity, F is the volume force, and P is the fluid pressure; Considering the growth and melting of ice, the energy equation is expressed as, Among them, λ is the thermal conductivity, q is the heat source term, e is the energy density, T is the temperature, and h(ρ,T) is the energy source term for ice growth and melting.

4. The insulator simulated icing test method according to claim 3, characterized in that: The simulation of the icing process in the natural environment includes controlling the operation of the simulated temperature control device, the simulated precipitation control device and the fan device, simulating the icing growth process under different conditions, and during the icing growth process, the monitoring device monitors the icing state of the insulator in real time; The ice growth rate is used to describe the growth of ice in unit time. The formula is: R i =α·(RH-RH start )·(T ice -TV Among them, R i is the ice growth rate, α is the ice growth coefficient, RH is the relative humidity, RH start is the relative humidity threshold for ice formation, T ice is the freezing point temperature, T is the temperature, and v is the wind speed; The ice thickness is calculated by integrating the ice growth rate over time, and the formula is: Where H(t) is the ice thickness at time t, and H0 is the initial ice thickness; Monitor the icing condition, test the voltage distribution and current data of the insulator under different icing conditions. In the process of simulating icing, apply voltage to the insulator, monitor the voltage distribution of the insulator in real time through the voltage measuring device, and measure and record the current data flowing through the insulator in real time through the current measuring device; The voltage distribution of the insulator under ice conditions is described by the potential gradient along the length of the insulator, which is expressed as follows: Where V(x,t) is the voltage at position x at time t, V0 is the initial voltage, L is the total length of the insulator, and f(H(t)) is the function of the influence of ice thickness on voltage distribution; The current formula of the insulator under ice conditions is expressed as: R(H(t))=R0·(1+γ·H(t)) Where I(t) is the current at time t, R(H(t)) is the resistance that changes with the thickness of ice, R0 is the initial resistance, and γ is the influence coefficient of ice on resistance.

5. The insulator simulated icing test method according to claim 4, characterized in that: The control unit adjustment includes, after building the insulator ice coating simulation environment, the signal end collects and analyzes the signal, and transmits it to the control unit of the host computer through the transmission module, and the control unit analyzes the difference, which is described by the weighted Euclidean distance, and the formula is expressed as follows: Among them, Δ is the difference, w T 、w RH and w v are the weights of temperature, humidity and wind speed respectively, T o RH o and v o They are target temperature, target humidity and target wind speed respectively; If Δ≥α, the system determines that the icing state is a high-difference state, uses the automated adjustment model to adjust the environmental parameters, checks whether there are faults or configuration errors, and strengthens real-time data monitoring to ensure the effectiveness of the adjustment measures; If β≤Δ<α, the system determines that the icing state is a medium difference state. According to the specific value of the difference, the environmental control parameters are adjusted. The system regularly feeds back the adjustment effect and evaluates whether a secondary adjustment is needed. If Δ<β, the system determines that the icing state is a low-difference state, maintains the current environmental settings without adjustment, and regularly evaluates insulator performance to ensure long-term stability; Among them, α and β are high difference and low difference thresholds respectively; The automatic adjustment model formula is expressed as: D ad =A·Δ+B·Δ′ Among them, Δ ad is the adjustment amount, A and B are different adjustment coefficients, Δ′ is the parameter of ice coverage, voltage distribution and current conditions. When optimizing the insulator performance, the deep learning model is used for tuning; The temperature control device, the simulated precipitation control device and the fan control device are controlled to make adjustments until the target parameter values ​​are met.

6. The insulator simulated icing test method according to claim 5, characterized in that: The deep learning model includes learning the relationship between insulator performance and icing state, and predicting insulator performance under different icing conditions; The deep learning model includes an input layer, a hidden layer and an output layer; The input layer, input feature X = [T, RH, v, H, R i ,I,V]; The hidden layer includes multiple fully connected layers, and the calculation formula of each layer is H l =f(W l ·H l-1 +b l ); Among them, H l is the output of the lth layer, W l 、b l are the weight and bias of the lth layer respectively, and f is the activation function; The output layer outputs the predicted electrical performance of the insulator under ice-covered conditions, and the formula is expressed as: Y=[V drop ,I leak ,Z] Among them, Y is the predicted value of insulator performance, V drop is the voltage drop under ice conditions, I leak is the leakage current under ice-covered state, Z is the insulation impedance; According to the insulator performance that needs to be tested and the predicted environmental parameters, the transmission control unit is regulated.

7. The insulator simulated icing test method according to claim 6, characterized in that: The evaluation of the insulator performance under icing conditions includes evaluating the insulator performance under icing conditions, analyzing the data collected during the test, including the icing state of the insulator, voltage distribution and current data, studying the icing law of the insulator through data analysis, evaluating the anti-icing ability of the insulator, comparing the test results with the standard values, and optimizing the anti-icing performance of the insulator according to the evaluation results; The optimization of the deep learning model includes initializing the deep learning model, and the deep learning model prediction function formula is expressed as: Y i =f(X i ;I) Among them, Y i is the predicted value of the i-th input data, X i is the i-th input data, Θ is the model parameter; Use the preset icing environment data for training, initialize the population of the insulator performance optimization algorithm, including icing conditions, voltage distribution, and current conditions, use the parameter combination in the current population to adjust the environmental conditions, and collect new data. Use the optimized deep learning model to predict the insulator performance and evaluate the prediction performance of the model. The evaluation formula is expressed as: Where E is the total error, τ is the time step, K is the number of performance parameters, and w k is the weight of the kth performance parameter, Y pred,tk , Y actual,tk are the predicted value and actual value of the kth performance parameter at time t, respectively; like The system judges that the insulator performance is good and the model is accurate. The system determines that the model and the insulator test device need to be adjusted, among which, is the error threshold; Use the evaluation results to optimize the model. According to the results of the optimization selection, adjust the environmental condition parameters, output and adjust through the control unit, adjust the insulator characteristics, collect new data in the adjusted environment for deep learning model training, repeatedly update the environmental parameters and insulator data until the stop condition is met, and obtain the optimization direction of the insulator performance.

8. A system based on the insulator simulated icing test method according to any one of claims 1 to 7, characterized in that: It includes environment construction module, ice detection module, data analysis module and performance evaluation and optimization module; The environment construction module collects icing environment data of the target area, deploys insulator icing simulation equipment, adjusts parameters through the control unit, simulates the icing process in the natural environment, and constructs an icing environment that meets the experimental requirements; The icing detection module, the monitoring device monitors the icing state of the insulator in real time, tests the voltage distribution and current data of the insulator under different icing conditions, and transmits the data to the host computer through the transmission module for processing and analysis; The data analysis module studies the icing law of insulators through data analysis, evaluates the anti-icing ability of insulators, establishes and trains a deep learning model, learns the relationship between insulator performance and icing state, and predicts insulator performance under different icing conditions; The performance evaluation and optimization module evaluates the electrical performance of the insulator based on the prediction results of the deep learning model, optimizes and adjusts the anti-icing performance of the insulator, continuously adjusts the environmental parameters and experimental conditions based on the analysis and evaluation results, optimizes the deep learning model, and repeats the optimization cycle until the experimental requirements are met.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images