High-altitude environment simulation test platform control method, test platform and storage medium

Abstract

The present invention relates to the field of test platform control technology, and discloses a high-altitude environment simulation test platform control method, test platform, and storage medium. During the environmental simulation process, the deviation value of the environmental data is obtained based on the real-time value of the environmental data of the simulation area and the theoretical value of the environmental data of the altitude to be simulated; the deviation value is processed using a pre-trained fuzzy logic network model to obtain a first control instruction corresponding to temperature, humidity, and air pressure; the real-time value and the real-time temperature rise data of the reactor are input into a pre-constructed environmental coupling model, and the first control instruction is used as a constraint. The environmental coupling model is optimized and solved using a model predictive control algorithm to obtain a second control instruction corresponding to temperature, humidity, and air pressure to control the high-altitude environment simulation test platform. The method of the present application performs multi-physics field coupling modeling on temperature, humidity, and air pressure to improve the accuracy of control of the high-altitude environment simulation test platform.

Description

Technical Field

[0001] The present invention relates to the technical field of test platform control, and in particular to a high-altitude environment simulation test platform control method, a test platform and a storage medium. Background Art

[0002] In the field of power systems, dry-type air-core reactors are key devices for reactive power compensation and current limiting, and their reliable performance is crucial to the stable operation of power systems. The unique geographical environment of high altitudes (thin air, low air pressure, and large temperature fluctuations) causes the temperature rise characteristics of dry-type air-core reactors to differ significantly from those at lower altitudes. On the one hand, the low air pressure environment weakens the air's convective heat dissipation capacity, making it difficult for the dry-type air-core reactor to effectively dissipate heat. On the other hand, drastic temperature fluctuations affect the performance of the reactor's insulation material and internal electromagnetic properties, thereby altering its temperature rise pattern. Therefore, studying the temperature rise characteristics of dry-type air-core reactors at high altitudes is of great significance for ensuring the safe operation of power equipment and optimizing power system design.

[0003] Currently, research on the temperature-rise characteristics of dry-type air-core reactors in high-altitude environments primarily relies on high-altitude environment simulation test platforms. However, existing control methods for high-altitude environment simulation test platforms have technical flaws: they use independent control modes for temperature, humidity, and air pressure. Under these independent control modes, the simulated environment cannot accurately reproduce the coupling relationship between environmental parameters at high altitudes, resulting in significant deviations from the actual high-altitude environment and low accuracy.

[0004] It can be seen that how to improve the accuracy of the simulated environment of the high-altitude environment simulation test platform has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] The present invention provides a high-altitude environment simulation test platform control method, test platform and storage medium to solve the technical problem of how to improve the accuracy of the simulated environment of the high-altitude environment simulation test platform, thereby achieving the effect of improving the accuracy of the simulated environment of the high-altitude environment simulation test platform.

[0006] In a first aspect, the present invention provides a method for controlling a high-altitude environment simulation test platform, which is applied to a temperature rise test of a dry-type air-core reactor, and comprises:

[0007] Determine the theoretical value of the environmental data for the altitude to be simulated;

[0008] In the process of performing environmental simulation at the altitude to be simulated using the high-altitude environmental simulation test platform, respectively collecting real-time values ​​of the environmental data and real-time temperature rise data of the reactor in the environmental simulation area, and obtaining a deviation value of the environmental data based on the theoretical value and the real-time value;

[0009] Processing the deviation value using a pre-trained fuzzy logic network model to obtain a first temperature control instruction, a first humidity control instruction, and a first air pressure control instruction;

[0010] Inputting the real-time value and the real-time temperature rise data of the reactor into a pre-constructed environmental coupling model, optimizing and solving the environmental coupling model using a model predictive control algorithm with the first temperature control instruction, the first humidity control instruction, and the first air pressure control instruction as constraints to obtain a second temperature control instruction, a second humidity control instruction, and a second air pressure control instruction, wherein the environmental coupling model reflects the coupling relationship between temperature, humidity, and air pressure through a first correlation relationship of the environmental data, a temperature field dynamic equation, and a second correlation relationship under a saturated state of the environmental data;

[0011] The high-altitude environment simulation test platform is controlled according to the second temperature control instruction, the second humidity control instruction, and the second air pressure control instruction.

[0012] Preferably, the use of a pre-trained fuzzy logic network model to process the deviation value to obtain a first temperature control instruction, a first humidity control instruction, and a first air pressure control instruction includes:

[0013] According to the control objectives, the temperature deviation membership function, humidity deviation membership function and pressure deviation membership function are defined, and an expert rule base is constructed based on expert knowledge and experience;

[0014] Based on the temperature deviation value membership function, the humidity deviation value membership function, the air pressure deviation value membership function and the expert rule base, a fuzzy logic network model is constructed using a neural network model;

[0015] According to the temperature deviation value in the deviation value, a first temperature control instruction is obtained using the trained fuzzy logic network model;

[0016] According to the humidity deviation value in the deviation value, a first humidity control instruction is obtained using the trained fuzzy logic network model;

[0017] According to the air pressure deviation value in the deviation value, the first air pressure control instruction is obtained by using the trained fuzzy logic network model.

[0018] Preferably, the construction of the environmental coupling model includes:

[0019] Analyzing the first historical temperature data, the first historical humidity data, the first historical air pressure data, and the historical air density data of the altitude to be simulated to obtain a first correlation relationship of the environmental data;

[0020] Analyze the second historical temperature data, the second historical humidity data, and the second historical air pressure data of the altitude to be simulated in a saturated state to obtain a second correlation relationship of the environmental data in a saturated state;

[0021] Constructing a temperature field dynamic equation according to the temperature time variation law of the altitude to be simulated;

[0022] The environmental coupling model is constructed according to the first association relationship, the second association relationship and the temperature field dynamic equation.

[0023] Preferably, the functional relationship of the environmental coupling model is:

[0024]

[0025] in, Indicates air pressure, Indicates temperature, Indicates humidity, represents the air density, The functional relationship between temperature, humidity and air density is expressed as follows: Indicates time, represents the first empirical correction coefficient, represents the second empirical correction factor for humidity, Represents the third empirical correction coefficient for air pressure and temperature, represents the Laplace operator, Indicates the heat generated by the reactor. Indicates saturated humidity.

[0026] Preferably, the use of a model predictive control algorithm to optimize and solve the environmental coupling model to obtain a second temperature control instruction, a second humidity control instruction, and a second air pressure control instruction includes:

[0027] Analyzing the real-time value and the real-time temperature rise data of the reactor to obtain key characteristic data, wherein the key characteristic data at least includes a temperature rise rate, an air pressure change gradient, and a humidity saturation deviation value;

[0028] Inputting the key feature data into a pre-trained neural network prediction model to obtain a temperature prediction value, a humidity prediction value, an air pressure prediction value, and a predicted temperature rise trend of the reactor;

[0029] The environmental coupling model is solved by using a model predictive control algorithm to obtain theoretical temperature rise data of the reactor;

[0030] Analyzing the temperature prediction value, the humidity prediction value, the air pressure prediction value, the reactor predicted temperature rise trend, and the reactor theoretical temperature rise data, and dynamically adjusting the set initial temperature control instruction weight coefficient, initial humidity control instruction weight coefficient, and initial air pressure control instruction weight coefficient based on a preset weight dynamic adjustment rule according to the obtained analysis results to obtain a dynamic temperature control instruction weight coefficient, a dynamic humidity control instruction weight coefficient, and a dynamic air pressure control instruction weight coefficient;

[0031] According to the dynamic temperature control instruction weight coefficient, the dynamic humidity control instruction weight coefficient and the dynamic air pressure control instruction weight coefficient, the model predictive control algorithm is used to determine a second temperature control instruction, a second humidity control instruction and a second air pressure control instruction.

[0032] Preferably, the determining of the second temperature control instruction, the second humidity control instruction, and the second air pressure control instruction using the model predictive control algorithm according to the dynamic temperature control instruction weight coefficient, the dynamic humidity control instruction weight coefficient, and the dynamic air pressure control instruction weight coefficient includes:

[0033] The temperature adjustment amount is obtained according to the dynamic temperature control instruction weight coefficient, the humidity adjustment amount is obtained according to the dynamic humidity control instruction weight coefficient, and the air pressure adjustment amount is obtained according to the dynamic air pressure control instruction weight coefficient;

[0034] Obtain adjusted temperature data according to the temperature adjustment amount, obtain adjusted humidity data according to the humidity adjustment amount, and obtain adjusted air pressure data according to the air pressure adjustment amount;

[0035] Calculating a first deviation between the adjusted temperature data and the theoretical temperature data in the theoretical value, a second deviation between the adjusted humidity data and the theoretical humidity data in the theoretical value, and a third deviation between the adjusted air pressure data and the theoretical air pressure data in the theoretical value;

[0036] The square of the first deviation, the square of the second deviation and the sum of the square of the third deviation are used as the optimization objective function of the model predictive control algorithm, and the temperature adjustment amount, the humidity adjustment amount and the air pressure adjustment amount are optimized according to the optimization objective function to obtain a second temperature control instruction, a second humidity control instruction and a second air pressure control instruction.

[0037] Preferably, the method further comprises:

[0038] The first empirical correction coefficient, the second empirical correction coefficient, and the third empirical correction coefficient of the environmental coupling model are corrected according to the real-time temperature rise data of the reactor and the theoretical temperature rise data of the reactor to obtain the corrected environmental coupling model.

[0039] In a second aspect, the present invention further provides a high-altitude environment simulation test platform control system, which is controlled by the above-mentioned high-altitude environment simulation test platform control method, wherein the test platform comprises at least: an environment simulation device, a data acquisition device, and a control device;

[0040] The environmental simulation device is connected to the data acquisition device and the control device respectively, and includes a temperature regulating device, a humidity regulating device and an air pressure regulating device;

[0041] The data acquisition device includes an optical fiber temperature measuring device, a temperature sensor, a humidity sensor and a vacuum gauge;

[0042] The control device controls the environment simulation device according to the high-altitude environment simulation test platform control method.

[0043] Preferably, the optical fiber temperature measuring device is arranged at a temperature measuring point of each encapsulation layer on the top of the dry-type air-core reactor winding to be tested, and the temperature measuring points include a first type of temperature measuring point and a second type of temperature measuring point;

[0044] The first type of temperature measuring points are located in the circumferential direction of the dry-type air-core reactor to be tested, and the number of the first type of temperature measuring points arranged on each of the encapsulation layers is 2;

[0045] The second type of temperature measuring points are located in the axial direction of the dry-type air-core reactor to be tested, and the number of the second type of temperature measuring points arranged in each of the encapsulation layers is 7;

[0046] The temperature interval of the first type of temperature measuring points is 180°C, and the distance interval of the second type of temperature measuring points is 150mm.

[0047] In a third aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed, the above-mentioned high-altitude environment simulation test platform control method is implemented.

[0048] This application provides a high-altitude environment simulation test platform control method, test platform, and storage medium. Compared with the existing technology, the embodiments of this application have the following beneficial effects:

[0049] The control method for a high-altitude environmental simulation test platform disclosed in this application performs multi-physics field coupling modeling on temperature, humidity, and air pressure to improve the accuracy of control of the high-altitude environmental simulation test platform, making the simulated environment of the high-altitude environmental simulation test platform closer to the real environment. The method combines a fuzzy logic network model with a model predictive control algorithm to enhance the adaptive capability of the control of the high-altitude environmental simulation test platform, improve the accuracy of environmental simulation of the high-altitude environmental simulation test platform, and obtain accurate data for temperature rise tests of dry-type air-core reactors. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of the steps of a high-altitude environment simulation test platform control method provided by a preferred embodiment of the present invention;

[0051] Figure 2 This is a schematic diagram of the first type of temperature measurement points provided by a preferred embodiment of the present invention;

[0052] Figure 3 This is a schematic diagram of the second type of temperature measurement points provided by a preferred embodiment of the present invention;

[0053] Reference numerals:

[0054] 1- Dry-type air-core reactor winding to be tested, 2- First type of temperature measurement point, 2- Second type of temperature measurement point. DETAILED DESCRIPTION

[0055] The following is a detailed explanation of the embodiments of the present invention in conjunction with the accompanying drawings. The embodiments are provided for illustrative purposes only and cannot be understood as limitations on the present invention. The accompanying drawings are for reference and illustration purposes only and do not constitute a limitation on the scope of patent protection of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In the description of the present invention, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, the meaning of "multiple" is two or more.

[0056] In the description of the present invention, it should be noted that, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] In describing the present invention, it should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. Those skilled in the art will understand the specific meanings of the above terms in the present invention in specific circumstances.

[0058] At high altitudes, parameters such as air pressure, temperature, and humidity are interrelated and influence each other. A decrease in air pressure not only directly affects the air's heat dissipation capacity, but also changes the saturation state of water vapor, thereby affecting the effect of humidity on equipment. Temperature changes also work together with air pressure and humidity to exacerbate the impact on the temperature rise characteristics of the reactor.

[0059] In view of this, in an embodiment of the present invention, a control method for a high altitude environment simulation test platform is provided, which is applied to a temperature rise test of a dry-type air-core reactor. Figure 1 The figure shows a schematic diagram of a control method for a high-altitude environment simulation test platform, the method comprising:

[0060] S1. Determine the theoretical value of the environmental data for the altitude to be simulated. For the determination of the theoretical value of the environmental data for the altitude to be simulated, in a preferred embodiment of the present application, the international standard atmosphere model is used to calculate the theoretical value of the environmental data corresponding to the altitude to be simulated, and the theoretical value includes theoretical temperature data, theoretical humidity data, and theoretical air pressure data. The international standard atmosphere model is a mathematical model that standardizes the changes of atmospheric parameters such as temperature, pressure, density, and humidity with altitude based on the average state and physical properties of the atmosphere. In another embodiment of the present application, an empirical formula is used to calculate the theoretical value of the environmental data for the altitude to be simulated. For obtaining the empirical formula, an existing empirical formula can be used, or historical environmental data for the altitude to be simulated can be analyzed and fitted to obtain the corresponding temperature empirical formula, humidity empirical formula, and air pressure empirical formula, respectively.

[0061] S2. During the process of performing environmental simulation at the altitude to be simulated using the high-altitude environmental simulation test platform, real-time values ​​of environmental data in the environmental simulation area and real-time temperature rise data of the reactor are respectively collected, and a deviation value of the environmental data is obtained based on the theoretical value and the real-time values. A dry-type air-core reactor is placed in the high-altitude environmental simulation test platform. During the process of performing environmental simulation at the altitude to be simulated, a data acquisition device of the high-altitude environmental simulation test platform collects real-time values ​​of environmental data in the environmental simulation area of ​​the high-altitude environmental simulation test platform and real-time temperature rise data of the reactor in real time. The real-time values ​​include real-time temperature data, real-time humidity data, and real-time air pressure data. The data acquisition devices arranged in the high-altitude environmental simulation test platform include a temperature data acquisition device, a humidity data acquisition device, an air pressure data acquisition device, and a dry-type air-core reactor temperature rise data acquisition device. Specifically, the temperature data acquisition device uses a temperature sensor to measure the real-time temperature data of the high-altitude environment simulation test platform. The humidity data acquisition device uses a humidity sensor to measure the real-time humidity data of the high-altitude environment simulation test platform. The air pressure data acquisition device uses a vacuum gauge to measure the real-time air pressure data of the high-altitude environment simulation test platform. The dry-type air-core reactor temperature rise data acquisition device uses an optical fiber temperature measurement device to measure the real-time temperature rise data of the dry-type air-core reactor. The temperature difference between the theoretical temperature data and the real-time temperature data is calculated to obtain a temperature deviation value. The humidity difference between the theoretical humidity data and the real-time humidity data is calculated to obtain a humidity deviation value. The air pressure difference between the theoretical air pressure data and the real-time air pressure data is calculated to obtain an air pressure deviation value.

[0062] S3. Use a pre-trained fuzzy logic network model to process the deviation value to obtain a first temperature control instruction, a first humidity control instruction, and a first air pressure control instruction; the fuzzy neural network (FNN) model is an intelligent algorithm model that combines fuzzy logic and neural networks. It integrates the advantages of both and has powerful nonlinear mapping capabilities, self-learning capabilities, and the ability to process fuzzy information.

[0063] Fuzzy neural network models use membership functions to convert precise input data into membership values ​​within a fuzzy set. For example, physical quantities like temperature and humidity can be converted into membership values ​​for fuzzy concepts like "high," "medium," and "low," thus accounting for the uncertainty and ambiguity of the data. In this application, membership functions for temperature deviation, humidity deviation, and air pressure deviation are defined based on the control objectives.

[0064] Furthermore, an expert rule base is established based on expert knowledge and / or experience, for example, “if the temperature is high and the humidity is low, then the control strategy is to increase ventilation”. These rules describe the fuzzy relationship between input variables and output variables.

[0065] A neural network model usually consists of an input layer, a hidden layer, and an output layer. The input layer receives fuzzified input data, the hidden layer performs fuzzy reasoning and feature extraction, and the output layer produces the final fuzzy or precise output. Learning and optimization are achieved by adjusting the connection weights to adapt to different input-output relationships.

[0066] During the training process of the fuzzy logic network model, the back propagation algorithm is used for training. By calculating the error between the actual output and the expected output, the error is back propagated to each layer of the fuzzy logic network model, and the connection weights of the neurons are adjusted so that the output of the fuzzy logic network model gradually approaches the expected output, thereby realizing the learning and optimization of the fuzzy logic network model.

[0067] According to the temperature deviation value in the deviation value, the trained fuzzy logic network model is used to obtain the first temperature control instruction; according to the humidity deviation value in the deviation value, the trained fuzzy logic network model is used to obtain the first humidity control instruction; according to the air pressure deviation value in the deviation value, the trained fuzzy logic network model is used to obtain the first air pressure control instruction.

[0068] The fuzzy logic network model used in this application can directly process information with ambiguity and uncertainty, which is more consistent with human thinking and the language description of practical problems. By learning through training data, it can automatically adjust the parameters and structure of the network to adapt to different input-output relationships, and has good adaptability and generalization capabilities. Compared with traditional neural network models, the fuzzy rule base of the fuzzy logic network model has a certain degree of interpretability and can provide an intuitive understanding of the input-output relationship.

[0069] S4. Input the real-time value and the real-time temperature rise data of the reactor into a pre-constructed environmental coupling model, and use the first temperature control instruction, the first humidity control instruction and the first air pressure control instruction as constraints, and use a model predictive control algorithm to optimize and solve the environmental coupling model to obtain a second temperature control instruction, a second humidity control instruction and a second air pressure control instruction. The environmental coupling model reflects the coupling relationship between temperature, humidity and air pressure through the first correlation relationship of the environmental data, the dynamic equation of the temperature field and the second correlation relationship under the saturation state of the environmental data. In a preferred embodiment of the present application, according to the correlation relationship between pressure, temperature and humidity, as well as thermodynamics, fluid mechanics and mass transfer theory, a multi-physical field environmental coupling model is constructed, and the environmental coupling model includes the first correlation relationship of the environmental data, the dynamic equation of the temperature field and the second correlation relationship under the saturation state of the environmental data.

[0070] At high altitudes, the air pressure is low, the air is thin, and the atmospheric insulation is weak. The frequency of collisions between air molecules is low, resulting in easy heat loss and a drop in temperature. When air pressure drops, the air's ability to hold water vapor decreases. On the one hand, the water vapor pressure decreases as the total air pressure decreases, lowering the saturated vapor pressure of water. On the other hand, the air expands and cools, causing water vapor to condense and humidity to change. Therefore, air density is introduced to address the deviation problem of the traditional ideal gas equation at high altitudes and low air pressure. In a preferred embodiment of this application, the first historical temperature data, first historical humidity data, first historical air pressure data, and historical air density data for the altitude to be simulated are analyzed and fitted to obtain a first correlation between air pressure, temperature, and humidity.

[0071] According to the ideal gas equation and the principle of phase equilibrium, when air pressure decreases at high altitudes, the air becomes thinner, and the water vapor pressure and saturated vapor pressure of water also decrease. This is because the air's capacity to hold water vapor decreases as total air pressure decreases, making it easier for water vapor to reach saturation at lower pressures. Temperature is another key factor influencing saturated vapor pressure. According to the Clausius-Clapeyron equation, as temperature increases, the saturated vapor pressure of water increases exponentially, significantly increasing the air's capacity to hold water vapor. As temperature decreases, the saturated vapor pressure decreases sharply. At high altitudes, both air pressure and temperature affect humidity. For example, when temperature decreases at high altitudes, air pressure increases, increasing the air's capacity to hold water vapor. However, decreasing temperature decreases the saturated vapor pressure, weakening the air's capacity to hold water vapor. If the air contains a high amount of water vapor at this time, the effect of decreasing temperature becomes dominant, making it easier for the air to reach saturation, resulting in precipitation or condensation. Conversely, when temperature increases at high altitudes, air pressure decreases, increasing the saturated vapor pressure, increasing the air's capacity to hold water vapor, and decreasing relative humidity, making it more difficult for the air to reach saturation. In a preferred embodiment of the present application, the second historical temperature data, the second historical humidity data and the second historical air pressure data at the saturated state at the simulated altitude are analyzed and fitted to obtain a second correlation relationship among air pressure, temperature and humidity.

[0072] The temperature field dynamic equation is a heat conduction equation, which is used to describe the variation of temperature in space and time. In this application, the temperature field dynamic equation is constructed based on the characteristics of high-altitude areas.

[0073] According to the first correlation relationship, the second correlation relationship and the temperature field dynamic equation, an environmental coupling model is constructed. The functional relationship of the constructed environmental coupling model is expressed as follows:

[0074]

[0075] in, Indicates air pressure, Indicates temperature, Indicates humidity, represents the air density, The functional relationship between temperature, humidity and air density is expressed as follows: Indicates time, represents the first empirical correction coefficient, represents the second empirical correction factor for humidity, Represents the third empirical correction coefficient for air pressure and temperature, represents the Laplace operator, Indicates the heat generated by the reactor. Indicates saturated humidity.

[0076] In a preferred embodiment of the present application, multi-physics field coupling modeling is performed on temperature, humidity, and air pressure to truly restore the coupling relationship between environmental parameters in high-altitude areas, improve the accuracy of control of the high-altitude environment simulation test platform, and make the simulated environment of the high-altitude environment simulation test platform closer to the real environment.

[0077] The model predictive control algorithm is an advanced model-based control algorithm that uses a system's dynamic model to predict the system's output response over a period of time. By solving an optimization problem, it calculates a control sequence that optimizes the system's performance. At each sampling moment, only the first control variable in the control sequence is applied to the system. At the next sampling moment, the above process is repeated, re-predicting and optimizing based on the new system state, thereby achieving real-time control of the system. In a preferred embodiment of the present application, a model predictive control algorithm is used to optimize and solve an environmental coupling model to dynamically adjust and control the temperature, humidity, and air pressure of a high-altitude environmental simulation test platform. The environmental coupling model serves as the dynamic model of the high-altitude environmental simulation test platform. The model predictive control algorithm is used to predict the changes in the temperature, humidity, and air pressure of the high-altitude environmental simulation test platform over a period of time. Using the first temperature control instruction, the first humidity control instruction, and the first pressure control instruction as constraints, the optimal temperature control sequence, humidity control sequence, and pressure control sequence for the high-altitude environmental simulation test platform are calculated to obtain the second temperature control instruction, the second humidity control instruction, and the second pressure control instruction.

[0078] Specifically, the real-time values ​​of the collected environmental data and the real-time temperature rise data of the reactor are subjected to wavelet denoising and normalization. Through mathematical calculations and statistical analysis, high-level key feature data are obtained. These key feature data include at least the temperature rise rate, the air pressure gradient, and the humidity saturation deviation. The temperature rise rate is the rate of change of the real-time temperature rise of the reactor per unit time, the air pressure gradient is the fluctuation trend of air pressure over time, and the humidity saturation deviation is the difference between the actual humidity and the theoretical saturated humidity at the current air pressure and temperature. Furthermore, the temperature rise rate, air pressure gradient, and humidity saturation deviation are input into a pre-trained neural network prediction model to predict future changes in environmental data and the temperature rise trend of the dry-type air-core reactor, obtaining predicted values ​​for temperature, humidity, air pressure, and the predicted temperature rise trend of the reactor. A model predictive control algorithm is used to solve the environmental coupling model to obtain theoretical reactor temperature rise data, stabilizing the temperature rise of the dry-type air-core reactor within the target range. The current flowing through the windings of a dry-type air-core reactor generates heat, which is dissipated through convection and radiation. This heat is strongly correlated with the ambient temperature, humidity, and air pressure. Ambient temperature affects heat dissipation efficiency; higher temperatures reduce the dry-type air-core reactor's heat dissipation capacity. Humidity affects air thermal conductivity and can also cause condensation. However, before condensation occurs, the higher the humidity, the better the dry-type air-core reactor's heat dissipation capacity. Ambient pressure affects air density; lower pressure reduces the dry-type air-core reactor's heat dissipation capacity. By solving the environmental coupling model using a model predictive control algorithm, dynamic predictions for ambient temperature, humidity, and pressure are obtained. Therefore, the formula for solving the reactor's theoretical temperature rise data is as follows:

[0079]

[0080] in, Indicates the theoretical temperature rise data of the reactor, represents the heat dissipation coefficient, The functional relationship of the environmental coupling model is represented by: Represents the dynamic prediction value of ambient temperature, Represents the dynamic prediction value of ambient humidity, Represents the dynamic prediction value of ambient air pressure, Indicates the real-time value of the ambient temperature.

[0081] Furthermore, by combining the temperature prediction value, humidity prediction value, air pressure prediction value, reactor predicted temperature rise trend and reactor theoretical temperature rise data, the dynamic temperature control instruction weight coefficient, dynamic humidity control instruction weight coefficient and dynamic air pressure control instruction weight coefficient are obtained to provide dynamic weight coefficients for the model predictive control algorithm.

[0082] In a preferred embodiment of the present application, original weights are assigned to temperature regulation, humidity regulation, and air pressure regulation. Based on the sensitivity of the reactor temperature rise to environmental parameters, the initial temperature control instruction weight coefficient, initial humidity control instruction weight coefficient, and initial air pressure control instruction weight coefficient are respectively used. If the reactor temperature rise is most sensitive to changes in ambient temperature, the initial temperature control instruction weight coefficient is the largest. If ambient humidity can bidirectionally affect the reactor temperature rise, the initial humidity control instruction weight coefficient is medium. If ambient air pressure changes slowly and has little effect on the reactor temperature rise, the initial air pressure control instruction weight coefficient is the smallest. The predicted temperature values, predicted humidity values, predicted air pressure values, predicted reactor temperature rise trends, and theoretical reactor temperature rise data are analyzed. Based on the analysis results, the set initial temperature control instruction weight coefficient, initial humidity control instruction weight coefficient, and initial air pressure control instruction weight coefficient are dynamically adjusted based on preset weight dynamic adjustment rules to obtain dynamic temperature control instruction weight coefficients, dynamic humidity control instruction weight coefficients, and dynamic air pressure control instruction weight coefficients. The preset weight dynamic adjustment rules are also set based on the sensitivity of the reactor temperature rise to environmental parameters, including but not limited to the following rules: Rule 1. If the temperature prediction value exceeds the temperature threshold, the initial temperature control instruction weight coefficient is increased, and the initial humidity control instruction weight coefficient and the initial air pressure control instruction weight coefficient are correspondingly reduced according to the preset first ratio; Rule 2. If the humidity prediction value shows condensation risk, the initial humidity control instruction weight coefficient is increased, and the initial temperature control instruction weight coefficient and the initial air pressure control instruction weight coefficient are reduced according to the preset second ratio; Rule 3. If the air pressure prediction value suddenly decreases, the initial air pressure control instruction weight coefficient is increased, and the initial temperature control instruction weight coefficient and the initial humidity control instruction weight coefficient are reduced according to the third preset ratio; Rule 4. If there is a strong correlation between the humidity prediction value and the air pressure prediction value, the preset collaborative weight allocation strategy is adopted to adjust the initial humidity control instruction weight coefficient and the initial air pressure control instruction weight coefficient; Rule 5. If the difference between the reactor predicted temperature rise trend and the reactor theoretical temperature rise data exceeds the difference threshold, the initial temperature control instruction weight coefficient is adjusted according to the difference threshold. The adjustment priority is in the order of temperature control instruction weight coefficient, humidity control instruction weight coefficient, and air pressure control instruction weight coefficient. That is, if the temperature forecast value exceeds the threshold, the humidity forecast value shows condensation risk, and the air pressure forecast value suddenly decreases at the same time, the temperature control instruction weight coefficient is adjusted first.

[0083] Finally, a model predictive control algorithm is used to determine the second temperature control instruction, the second humidity control instruction, and the second pressure control instruction based on the dynamic temperature control instruction weight coefficient, the dynamic humidity control instruction weight coefficient, and the dynamic pressure control instruction weight coefficient. Specifically, a temperature adjustment amount is obtained based on the dynamic temperature control instruction weight coefficient, a humidity adjustment amount is obtained based on the dynamic humidity control instruction weight coefficient, and a pressure adjustment amount is obtained based on the dynamic pressure control instruction weight coefficient; adjusted temperature data is obtained based on the temperature adjustment amount, adjusted humidity data is obtained based on the humidity adjustment amount, and adjusted pressure adjustment amount is obtained based on the pressure adjustment amount; a first deviation between the adjusted temperature data and the theoretical temperature data in the theoretical value, a second deviation between the adjusted humidity data and the theoretical humidity data in the theoretical value, and a third deviation between the adjusted pressure data and the theoretical pressure data in the theoretical value are calculated; the square of the first deviation, the square of the second deviation, and the sum of the square of the third deviation are used as the optimization objective function of the model predictive control algorithm, and the temperature adjustment amount, the humidity adjustment amount, and the pressure adjustment amount are optimized based on minimizing the optimization objective function as the optimization target, to obtain the second temperature control instruction, the second humidity control instruction, and the second pressure control instruction.

[0084] In a preferred embodiment of the present application, multi-physics field coupling modeling is performed on temperature, humidity, and air pressure to improve the accuracy of control of the high-altitude environment simulation test platform, making the simulated environment of the high-altitude environment simulation test platform closer to the real environment, and combining the fuzzy logic network model and the model predictive control algorithm to enhance the adaptive ability of the high-altitude environment simulation test platform control, so as to obtain accurate data for the temperature rise test of the dry-type air-core reactor.

[0085] S5. Control the high-altitude environment simulation test platform according to the second temperature control instruction, the second humidity control instruction, and the second air pressure control instruction; control the temperature adjustment device of the high-altitude environment simulation test platform according to the second temperature control instruction to obtain a more accurate simulated temperature; control the humidity adjustment device of the high-altitude environment simulation test platform according to the second humidity control instruction to obtain a more accurate simulated humidity; and control the air pressure adjustment device of the high-altitude environment simulation test platform according to the second air pressure control instruction to obtain a more accurate simulated air pressure.

[0086] In a preferred embodiment of the present application, a data update period is set for the high-altitude environment simulation test platform to adapt to dynamic changes of the high-altitude environment simulation test platform.

[0087] Furthermore, based on the actual temperature rise data of the reactor and the theoretical temperature rise data of the reactor, the temperature rise deviation data is calculated. When the temperature rise deviation data exceeds the temperature rise deviation threshold, the first empirical correction coefficient, the second empirical correction coefficient and the third empirical correction coefficient of the environmental coupling model are corrected to obtain a corrected environmental coupling model to adapt to the dynamic changes of environmental parameters in the environmental simulation area of ​​the high-altitude environmental simulation test platform, thereby obtaining a more accurate simulation of the environment.

[0088] In a preferred embodiment of the present invention, theoretical values ​​of environmental data for an altitude to be simulated are determined; in the process of performing environmental simulation for the altitude to be simulated using a high-altitude environmental simulation test platform, real-time values ​​of environmental data in the environmental simulation area and real-time temperature rise data of the reactor are respectively collected, and deviation values ​​of the environmental data are obtained based on the theoretical values ​​and the real-time values; the deviation values ​​are processed using a pre-trained fuzzy logic network model to obtain a first temperature control instruction, a first humidity control instruction, and a first air pressure control instruction; the real-time values ​​and the real-time temperature rise data of the reactor are input into a pre-constructed environmental coupling model, and the environmental coupling model is optimized and solved using a model predictive control algorithm with the first temperature control instruction, the first humidity control instruction, and the first air pressure control instruction as constraints to obtain a second temperature control instruction, a second humidity control instruction, and a second air pressure control instruction. The environmental coupling model reflects the coupling relationship between temperature, humidity, and air pressure through a constructed first correlation relationship of the environmental data, a temperature field dynamic equation, and a second correlation relationship under a saturated state of the environmental data; and the high-altitude environmental simulation test platform is controlled based on the second temperature control instruction, the second humidity control instruction, and the second air pressure control instruction. The control method for a high-altitude environmental simulation test platform disclosed in this application performs multi-physics field coupling modeling on temperature, humidity, and air pressure to improve the accuracy of control of the high-altitude environmental simulation test platform, making the simulated environment of the high-altitude environmental simulation test platform closer to the real environment. The method combines a fuzzy logic network model with a model predictive control algorithm to enhance the adaptive capability of the control of the high-altitude environmental simulation test platform, improve the accuracy of environmental simulation of the high-altitude environmental simulation test platform, and obtain accurate data for temperature rise tests of dry-type air-core reactors.

[0089] Accordingly, based on a high-altitude environment simulation test platform control method, an embodiment of the present invention further provides a high-altitude environment simulation test platform, which is controlled by the high-altitude environment simulation test platform control method provided in this application. The test platform at least includes: an environment simulation device, a data acquisition device, and a control device;

[0090] The environmental simulation device is connected to the data acquisition device and the control device respectively, and includes a temperature regulating device, a humidity regulating device and an air pressure regulating device;

[0091] The data acquisition device includes an optical fiber temperature measuring device, a temperature sensor, a humidity sensor and a vacuum gauge;

[0092] The control device controls the environment simulation device according to the high-altitude environment simulation test platform control method.

[0093] The high-altitude environmental simulation test platform further includes an environmental simulation cabin for accommodating the dry-type air-core reactor to be tested.

[0094] The temperature regulating device includes a heating device and a refrigeration device to achieve precise control of the temperature in the environmental simulation cabin.

[0095] The humidity regulating device includes a humidifier and a dehumidifier. The humidifier is used to increase the humidity in the environmental simulation chamber, and the dehumidifier is used to reduce the humidity in the environmental simulation chamber to achieve precise control of the humidity in the environmental simulation chamber.

[0096] The air pressure regulating device includes a vacuum pump and an air inlet valve. The vacuum pump extracts the gas in the environmental simulation chamber to reduce the air pressure in the environmental simulation chamber. The air inlet valve is used to control the air intake volume in the environmental simulation chamber to maintain the air pressure in the environmental simulation chamber stable.

[0097] The high-altitude environment simulation test platform also includes an electrical measurement system, including a voltmeter and an ammeter, which are used to measure the voltage and current values ​​of the dry-type air-core reactor.

[0098] The control device includes a controller, a touch screen and a computer. The controller is used to receive signals from the data acquisition device and control the operation of the environmental simulation device according to the control method of the high-altitude environmental simulation test platform. The touch screen is used for human-computer interaction, and the computer is used for data processing, storage and analysis.

[0099] In the preferred embodiment of the present application, the optical fiber temperature measuring device is arranged at the temperature measuring point of each envelope layer on the top of the dry-type air-core reactor winding 1 to be tested, and the temperature measuring points include the first type of temperature measuring point 2 and the second type of temperature measuring point 3, such as Figure 2 The first type of temperature measurement point schematic diagram and Figure 3 Schematic diagram of the second type of temperature measuring points shown; the first type of temperature measuring points 2 are located in the circumferential direction of the dry-type air-core reactor to be tested, and the number of first type temperature measuring points 2 arranged in each encapsulation layer is 2; the second type of temperature measuring points 3 are located in the axial direction of the dry-type air-core reactor to be tested, and the number of second type temperature measuring points 3 arranged in each encapsulation layer is 7; the temperature interval of the first type of temperature measuring points 2 is 180°C, and the distance interval of the second type of temperature measuring points 3 is 150mm.

[0100] By reasonably setting the temperature measuring points of the optical fiber temperature measuring device, the temperature rise value of the dry-type air-core reactor can be accurately measured, providing accurate data for the temperature rise test of the dry-type air-core reactor.

[0101] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to perform the steps in the control of the high-altitude environment simulation test platform in the above embodiment, for example Figure 1 Steps S1 to S5 described in .

[0102] In summary, the embodiments of the present application provide a high-altitude environment simulation test platform control method, test platform and storage medium, which solve the technical problem of how to improve the accuracy of the simulated environment of the high-altitude environment simulation test platform. The method includes: determining the theoretical value of the environmental data of the altitude to be simulated; in the process of using the high-altitude environment simulation test platform to simulate the environment at the altitude to be simulated, respectively collecting the real-time value of the environmental data of the environmental simulation area and the real-time temperature rise data of the reactor, and obtaining the deviation value of the environmental data based on the theoretical value and the real-time value; using a pre-trained fuzzy logic network model to process the deviation value, and obtaining a first temperature control instruction, a first humidity control instruction and a first air flow control instruction. The high-altitude environment simulation test platform is controlled according to the second temperature control instruction, the second humidity control instruction, and the second pressure control instruction. The high-altitude environment simulation test platform is controlled according to the second temperature control instruction, the second humidity control instruction, and the second pressure control instruction. The high-altitude environment simulation test platform control method disclosed in the present application performs multi-physics field coupling modeling on temperature, humidity, and pressure to improve the accuracy of the control of the high-altitude environment simulation test platform, making the simulated environment of the high-altitude environment simulation test platform closer to the real environment, combining the fuzzy logic network model with the model predictive control algorithm to enhance the adaptive ability of the high-altitude environment simulation test platform control, improve the accuracy of the environmental simulation of the high-altitude environment simulation test platform, and obtain accurate data for the temperature rise test of the dry-type air-core reactor.

[0103] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0104] The above-described embodiments merely represent several preferred implementations of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art could make several improvements and substitutions without departing from the technical principles of the present application, and such improvements and substitutions should also be considered within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the scope of protection of the claims.

Claims

1. A high altitude environment simulation test platform control method, characterized in that: The method is applied to a temperature rise test of a dry-type air-core reactor, and the method comprises: Determine the theoretical value of the environmental data for the altitude to be simulated; In the process of performing environmental simulation at the altitude to be simulated using the high-altitude environmental simulation test platform, respectively collecting real-time values ​​of the environmental data and real-time temperature rise data of the reactor in the environmental simulation area, and obtaining a deviation value of the environmental data based on the theoretical value and the real-time value; Processing the deviation value using a pre-trained fuzzy logic network model to obtain a first temperature control instruction, a first humidity control instruction, and a first air pressure control instruction; Inputting the real-time value and the real-time temperature rise data of the reactor into a pre-constructed environmental coupling model, optimizing and solving the environmental coupling model using a model predictive control algorithm with the first temperature control instruction, the first humidity control instruction, and the first air pressure control instruction as constraints to obtain a second temperature control instruction, a second humidity control instruction, and a second air pressure control instruction, wherein the environmental coupling model reflects the coupling relationship between temperature, humidity, and air pressure through a first correlation relationship of the environmental data, a temperature field dynamic equation, and a second correlation relationship under a saturated state of the environmental data; The high-altitude environment simulation test platform is controlled according to the second temperature control instruction, the second humidity control instruction, and the second air pressure control instruction.

2. The high altitude environment simulation test platform control method according to claim 1, characterized in that: The method of using a pre-trained fuzzy logic network model to process the deviation value to obtain a first temperature control instruction, a first humidity control instruction, and a first air pressure control instruction includes: According to the control objectives, the temperature deviation membership function, humidity deviation membership function and pressure deviation membership function are defined, and an expert rule base is constructed based on expert knowledge and experience; Based on the temperature deviation value membership function, the humidity deviation value membership function, the air pressure deviation value membership function and the expert rule base, a fuzzy logic network model is constructed using a neural network model; According to the temperature deviation value in the deviation value, a first temperature control instruction is obtained using the trained fuzzy logic network model; According to the humidity deviation value in the deviation value, a first humidity control instruction is obtained using the trained fuzzy logic network model; According to the air pressure deviation value in the deviation value, the first air pressure control instruction is obtained by using the trained fuzzy logic network model.

3. The high altitude environment simulation test platform control method according to claim 1, characterized in that: The construction of the environmental coupling model includes: Analyzing the first historical temperature data, the first historical humidity data, the first historical air pressure data, and the historical air density data of the altitude to be simulated to obtain a first correlation relationship of the environmental data; Analyze the second historical temperature data, the second historical humidity data, and the second historical air pressure data of the altitude to be simulated in a saturated state to obtain a second correlation relationship of the environmental data in a saturated state; Constructing a temperature field dynamic equation according to the temperature time variation law of the altitude to be simulated; The environmental coupling model is constructed according to the first association relationship, the second association relationship and the temperature field dynamic equation.

4. The high altitude environment simulation test platform control method according to claim 3, characterized in that: The functional relationship of the environmental coupling model is: in, Indicates air pressure, Indicates temperature, Indicates humidity, represents the air density, The functional relationship between temperature, humidity and air density is expressed as follows: Indicates time, represents the first empirical correction coefficient, represents the second empirical correction factor for humidity, Represents the third empirical correction coefficient for air pressure and temperature, represents the Laplace operator, Indicates the heat generated by the reactor. Indicates saturated humidity.

5. The high altitude environment simulation test platform control method according to claim 4, characterized in that: The method of optimizing and solving the environmental coupling model using a model predictive control algorithm to obtain a second temperature control instruction, a second humidity control instruction, and a second air pressure control instruction includes: Analyzing the real-time value and the real-time temperature rise data of the reactor to obtain key characteristic data, wherein the key characteristic data at least includes a temperature rise rate, an air pressure change gradient, and a humidity saturation deviation value; Inputting the key feature data into a pre-trained neural network prediction model to obtain a temperature prediction value, a humidity prediction value, an air pressure prediction value, and a predicted temperature rise trend of the reactor; The environmental coupling model is solved by using a model predictive control algorithm to obtain theoretical temperature rise data of the reactor; Analyzing the temperature prediction value, the humidity prediction value, the air pressure prediction value, the reactor predicted temperature rise trend, and the reactor theoretical temperature rise data, and dynamically adjusting the set initial temperature control instruction weight coefficient, initial humidity control instruction weight coefficient, and initial air pressure control instruction weight coefficient based on a preset weight dynamic adjustment rule according to the obtained analysis results to obtain a dynamic temperature control instruction weight coefficient, a dynamic humidity control instruction weight coefficient, and a dynamic air pressure control instruction weight coefficient; According to the dynamic temperature control instruction weight coefficient, the dynamic humidity control instruction weight coefficient and the dynamic air pressure control instruction weight coefficient, the model predictive control algorithm is used to determine a second temperature control instruction, a second humidity control instruction and a second air pressure control instruction.

6. The high altitude environment simulation test platform control method according to claim 5, characterized in that: The method of determining a second temperature control instruction, a second humidity control instruction, and a second air pressure control instruction using the model predictive control algorithm according to the dynamic temperature control instruction weight coefficient, the dynamic humidity control instruction weight coefficient, and the dynamic air pressure control instruction weight coefficient includes: The temperature adjustment amount is obtained according to the dynamic temperature control instruction weight coefficient, the humidity adjustment amount is obtained according to the dynamic humidity control instruction weight coefficient, and the air pressure adjustment amount is obtained according to the dynamic air pressure control instruction weight coefficient; Obtain adjusted temperature data according to the temperature adjustment amount, obtain adjusted humidity data according to the humidity adjustment amount, and obtain adjusted air pressure data according to the air pressure adjustment amount; Calculating a first deviation between the adjusted temperature data and the theoretical temperature data in the theoretical value, a second deviation between the adjusted humidity data and the theoretical humidity data in the theoretical value, and a third deviation between the adjusted air pressure data and the theoretical air pressure data in the theoretical value; The square of the first deviation, the square of the second deviation and the sum of the square of the third deviation are used as the optimization objective function of the model predictive control algorithm, and the temperature adjustment amount, the humidity adjustment amount and the air pressure adjustment amount are optimized according to the optimization objective function to obtain a second temperature control instruction, a second humidity control instruction and a second air pressure control instruction.

7. The high altitude environment simulation test platform control method according to claim 5, characterized in that: The method further comprises: The first empirical correction coefficient, the second empirical correction coefficient, and the third empirical correction coefficient of the environmental coupling model are corrected according to the real-time temperature rise data of the reactor and the theoretical temperature rise data of the reactor to obtain the corrected environmental coupling model.

8. A high-altitude environment simulation test platform, controlled by the high-altitude environment simulation test platform control method according to any one of claims 1 to 7, characterized in that: The test platform at least includes: an environmental simulation device, a data acquisition device and a control device; The environmental simulation device is connected to the data acquisition device and the control device respectively, and includes a temperature regulating device, a humidity regulating device and an air pressure regulating device; The data acquisition device includes an optical fiber temperature measuring device, a temperature sensor, a humidity sensor and a vacuum gauge; The control device controls the environment simulation device according to the high-altitude environment simulation test platform control method.

9. The high altitude environment simulation test platform according to claim 8, characterized in that: The optical fiber temperature measuring device is arranged on the temperature measuring point of each encapsulation layer on the top of the dry-type air-core reactor winding to be tested, and the temperature measuring points include first-type temperature measuring points and second-type temperature measuring points; The first type of temperature measuring points are located in the circumferential direction of the dry-type air-core reactor to be tested, and the number of the first type of temperature measuring points arranged on each of the encapsulation layers is 2; The second type of temperature measuring points are located in the axial direction of the dry-type air-core reactor to be tested, and the number of the second type of temperature measuring points arranged in each of the encapsulation layers is 7; The temperature interval of the first type of temperature measuring points is 180°C, and the distance interval of the second type of temperature measuring points is 150mm.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the high-altitude environment simulation test platform control method according to any one of claims 1 to 7 is implemented.

Images