Energy-saving thermal management method and system for energy storage cabinet of phase change material

Abstract

The invention discloses an energy-saving thermal management method and system for an energy storage cabinet of a phase-change material, and belongs to the technical field of thermal management of energy storage equipment, and the method specifically comprises the steps: collecting temperature data in the energy storage cabinet through a temperature sensor, and predicting a temperature change trend through a neural network model after the temperature data is subjected to Kalman filtering processing; according to the prediction result, a fuzzy logic algorithm is adopted to judge the temperature state, and a PID control algorithm is combined to adjust the operation parameters of the auxiliary heat dissipation device; and meanwhile, the phase change material automatically absorbs or releases heat according to actual temperature change and works cooperatively with the auxiliary heat dissipation device, and the system also regularly collects real-time operation data and optimizes and updates a neural network model and a fuzzy logic rule so as to improve the temperature management efficiency and realize intelligent and accurate control of the temperature in the energy storage cabinet.

Description

Technical Field

[0001] The present invention belongs to the technical field of thermal management of energy storage equipment, and specifically relates to an energy-saving thermal management method and system for an energy storage cabinet made of a phase change material. Background Art

[0002] During the operation of the energy storage cabinet, heat is generated. If the temperature cannot be effectively managed, the performance and life of the energy storage equipment will be affected. At present, the common heat dissipation methods of energy storage cabinets mainly include air cooling and liquid cooling. Although the air cooling method has a simple structure and low cost, the heat dissipation efficiency is limited and it is difficult to meet the heat dissipation requirements of high-power energy storage cabinets. The liquid cooling method has a higher heat dissipation efficiency, but the system is complex, the cost is high, and there is a risk of leakage. In addition, traditional heat dissipation methods often have high energy consumption and it is difficult to accurately control the temperature, which affects the operating efficiency and stability of the energy storage cabinet.

[0003] For example, a Chinese patent with the authorization announcement number CN118248999B discloses a thermal management method and system for a network-type energy storage cabinet, including: collecting signal sources, performing preprocessing to determine whether the operating equipment is in heating mode; further determining whether the operating equipment is in cooling mode; and stopping cooling when the threshold is reached. Compared with the liquid cooling system, this technical solution reduces one heat exchange process, one heat exchange thermal resistance, reduces the heat exchange temperature difference, has good heat transfer performance, and the refrigerant undergoes phase change heat exchange in the battery cold plate, the second heat exchange unit, and the H-bridge cold plate, and the heat exchange capacity is significantly enhanced. This technology reduces the battery cold plate coolant circuit, the H-bridge coolant circuit, and the energy storage cabinet air conditioner in the liquid cooling system. The system is simple and compact in structure, greatly reducing the system cost. This technical solution avoids the flow of coolants such as ethylene glycol in the energy storage cabinet, avoids the risk of coolant leakage into the battery and the H-bridge, and is safer and more reliable.

[0004] The above existing technologies all have the following problems: low intelligence and adaptability; lack of flexibility and scalability. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes an energy-saving thermal management method and system for an energy storage cabinet using phase change materials. The temperature data in the energy storage cabinet is collected by a temperature sensor, and after being processed by Kalman filtering, a neural network model is used to predict the temperature change trend; according to the prediction result, a fuzzy logic algorithm is used to judge the temperature state, and the operating parameters of the auxiliary heat dissipation device are adjusted in combination with a PID control algorithm; at the same time, the phase change material automatically absorbs or releases heat according to the actual temperature change, and works in coordination with the auxiliary heat dissipation device. The system also regularly collects real-time operating data, optimizes and updates the neural network model and fuzzy logic rules to improve the temperature management efficiency, thereby realizing intelligent and precise control of the temperature in the energy storage cabinet.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A phase change material energy storage cabinet energy-saving thermal management method, comprising:

[0008] The temperature sensor collects the temperature data in the energy storage cabinet, and the temperature data is processed by the Kalman filter algorithm and then transmitted to the control system;

[0009] The control system uses a neural network model to predict temperature changes on the temperature data after Kalman filtering to obtain a temperature change trend prediction result;

[0010] According to the temperature change trend prediction result, a fuzzy logic algorithm is used to determine the current temperature state in the energy storage cabinet;

[0011] According to the temperature state determined by fuzzy logic and combined with PID control algorithm, the operating parameters of the auxiliary heat dissipation device are calculated and adjusted;

[0012] The phase change material automatically absorbs or releases heat according to the actual temperature change in the energy storage cabinet, and works in coordination with the auxiliary heat dissipation device;

[0013] Regularly collect the real-time operation data of the energy storage cabinet, and optimize and update the neural network model and fuzzy logic rules based on the real-time operation data of the energy storage cabinet.

[0014] Specifically, the temperature data is processed by the Kalman filter algorithm and then transmitted to the control system, including:

[0015] A1: Obtain the temperature data in the energy storage cabinet and set the initial parameters of the Kalman filter algorithm; the initial parameters of the Kalman filter algorithm include the state transfer matrix , observation matrix , process noise covariance matrix , observation noise covariance matrix , initial state estimate C and initial error covariance matrix ;

[0016] A2: Based on the estimated value of the state at time t-1 and the state transition matrix , predict the current state estimate , where t represents the current time;

[0017] A3: According to the error covariance matrix at time t-1 , state transfer matrix and the process noise covariance matrix , predict the error covariance matrix at the current moment , and introduces uncertainty quantification methods to Correction is performed to obtain the corrected error covariance matrix .

[0018] Specifically, the temperature data is processed by the Kalman filter algorithm and then transmitted to the control system, which also includes:

[0019] A4: Utilization , observation matrix and the observation noise covariance matrix at the current moment , calculate the Kalman gain At the same time, an observation fusion strategy is introduced to calculate the weighted Kalman gain based on the observation values ​​of multiple temperature sensors. ;

[0020] A5: Based on the current observation value, and , update the current state estimate ;

[0021] A6: Exploitation , , and the identity matrix , update the error covariance matrix at the current moment ;

[0022] A7: Update the estimated state value and the error covariance matrix As the initial value of the next moment, repeat steps A2 to A6 until all temperature data are processed;

[0023] A8: Transmit the processed temperature data X to the control system.

[0024] Specifically, judging the current temperature state in the energy storage cabinet by using a fuzzy logic algorithm according to the temperature change trend prediction result includes:

[0025] B1: Predict results based on temperature change trend , combining with a preset dynamic temperature threshold, defining the temperature state in the energy storage cabinet and determining the domain of temperature data; the temperature state in the energy storage cabinet includes low temperature, medium temperature and high temperature;

[0026] B2: For each temperature state in the energy storage cabinet, establish a fuzzy set and use A Gaussian membership function is defined for each fuzzy set, and a genetic algorithm is used to optimize the Gaussian membership function, where: represents the exponential function, express Corresponding Gaussian membership function; the fuzzy set includes a low temperature fuzzy set , medium temperature fuzzy set and high temperature fuzzy set , represents the mean, represents variance;

[0027] B3: Obtain optimized Gaussian membership function , for each predicted temperature data point , using the optimized Gaussian membership function Calculate its membership in different fuzzy sets, where .

[0028] Specifically, judging the current temperature state in the energy storage cabinet by using a fuzzy logic algorithm according to the temperature change trend prediction result also includes:

[0029] B4: According to the management requirements of the energy storage cabinet and the temperature status judgment criteria, an intelligent fuzzy rule base based on the knowledge graph is constructed;

[0030] B5: According to The membership degree and intelligent fuzzy rule base of each fuzzy set are inferred by the fuzzy logic reasoning method based on deep learning;

[0031] B6: According to the result of fuzzy logic reasoning, determine the temperature state in the current energy storage cabinet and output the temperature state.

[0032] Specifically, the temperature state determined by fuzzy logic is combined with a PID control algorithm to calculate and adjust the operating parameters of the auxiliary heat dissipation device, including:

[0033] C1: Obtain the temperature state in the current energy storage cabinet determined by fuzzy logic in B6;

[0034] C2: Set the target temperature value of the PID controller according to the temperature state determined by fuzzy logic;

[0035] C3: Calculate the current temperature error based on the target temperature value and the real-time temperature data collected by the temperature sensor, and execute the PID control algorithm to obtain the control output;

[0036] C4: Calculating the operating parameters of the auxiliary heat dissipation device according to the control output; the operating parameters refer to power;

[0037] C5: According to the operating parameters, adjust the working state of the auxiliary heat dissipation device, monitor the actual operating effect and make adjustments.

[0038] Specifically, the phase change material automatically absorbs or releases heat according to the actual temperature change in the energy storage cabinet, and works in coordination with the auxiliary heat dissipation device, including:

[0039] D1: The control system determines the temperature state in the energy storage cabinet based on the signal from the temperature sensor. When the temperature exceeds the phase change point of the phase change material, the phase change material begins to absorb heat and changes from solid to liquid. When the temperature is lower than the phase change point, the phase change material begins to release heat and changes from liquid to solid.

[0040] D2: When the temperature inside the energy storage cabinet exceeds the preset maximum temperature threshold and the heat absorption value of the phase change material is less than the heat dissipation temperature value of the energy storage cabinet, the control system starts the auxiliary heat dissipation device. While the phase change material absorbs heat, the auxiliary heat dissipation device also works according to the adjusted operating parameters to maintain the temperature inside the energy storage cabinet within the set range.

[0041] Specifically, the real-time operating data of the energy storage cabinet includes temperature data, operating status of an auxiliary heat dissipation device, and heat absorption / exothermic status of a phase change material.

[0042] An energy-saving thermal management system for energy storage cabinets of phase change materials, comprising: a data processing module, a temperature change prediction module, a temperature state judgment module, a heat dissipation control module, a phase change material collaborative heat dissipation module, and an optimization and update module;

[0043] The data processing module is used to collect temperature data in the energy storage cabinet and perform Kalman filtering;

[0044] The temperature change prediction module is used to predict the temperature data after Kalman filtering using a neural network model to obtain a temperature change trend prediction result;

[0045] The temperature state judgment module is used to judge the temperature state in the current energy storage cabinet using a fuzzy logic algorithm according to the temperature change trend prediction result;

[0046] The heat dissipation control module is used to calculate and adjust the operating parameters of the auxiliary heat dissipation device according to the judgment result of the temperature state in combination with the PID control algorithm;

[0047] The phase change material cooperative heat dissipation module is used to automatically absorb or release heat according to the actual temperature change in the energy storage cabinet, and work in coordination with the auxiliary heat dissipation device;

[0048] The optimization and update module is used to regularly collect real-time operation data of the energy storage cabinet, and optimize and update the neural network model and fuzzy logic rules according to the real-time operation data.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1. The present invention proposes an energy-saving thermal management method for a phase change material energy storage cabinet, which adjusts the operating parameters of an auxiliary heat dissipation device in real time according to temperature changes to avoid unnecessary energy consumption, and at the same time utilizes the heat absorption or heat release characteristics of the phase change material to further reduce energy consumption.

[0051] 2. The present invention proposes an energy-saving thermal management method for a phase change material energy storage cabinet. The temperature data in the energy storage cabinet is collected by a temperature sensor and processed by a Kalman filter algorithm to improve the accuracy and reliability of the data. Subsequently, a neural network model is used to predict the temperature data. Combined with a fuzzy logic algorithm and a PID control algorithm, accurate judgment of the temperature state in the energy storage cabinet and intelligent adjustment of the operating parameters of the auxiliary heat dissipation device are achieved, which not only improves the temperature control capability of the energy storage cabinet, but also ensures its stable operation under various working conditions, thereby extending the service life of the energy storage cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of an energy-saving thermal management method for a phase change material energy storage cabinet of the present invention;

[0053] Figure 2 A thermal management intelligent control flow chart of an energy-saving thermal management method for a phase change material energy storage cabinet of the present invention;

[0054] Figure 3 This is a physical picture of the phase change material energy storage cabinet;

[0055] Figure 4 This is a schematic diagram of an energy-saving thermal management system for a phase change material energy storage cabinet of the present invention. DETAILED DESCRIPTION

[0056] Example 1

[0057] See also Figure 1-Figure 3 , an embodiment of the present invention provides: a phase change material energy storage cabinet energy saving thermal management method, the method includes steps S101~S106, including the following steps:

[0058] S101: A temperature sensor collects temperature data in the energy storage cabinet, and the temperature data is processed by a Kalman filter algorithm and then transmitted to a control system;

[0059] S102: The control system uses a neural network model to predict temperature changes on the temperature data after Kalman filtering to obtain a temperature change trend prediction result;

[0060] Furthermore, the specific steps of S102 include:

[0061] (1) Use the temperature data after Kalman filtering as the input data of the neural network;

[0062] (2) Load the multi-layer perceptron neural network architecture and determine the number of nodes in the input layer, hidden layer, and output layer of the neural network, as well as the activation function and optimization algorithm parameters;

[0063] (3) Use the historical temperature data processed by Kalman filtering as the training set, input it into the multi-layer perceptron neural network model, and set the target output to the temperature value predicted by the model;

[0064] Among them, the multilayer perceptron neural network model uses the forward propagation algorithm when outputting. Specifically, for each neuron, its output can be expressed as: ,in, represents the temperature value predicted by the model, x represents the input vector, W represents the weight matrix, b represents the bias vector, and f represents the activation function;

[0065] (4) Adjust the weights and biases of the multilayer perceptron neural network through the back propagation algorithm to minimize the prediction error of the multilayer perceptron neural network model and generate a trained neural network model;

[0066] Among them, the backpropagation algorithm is used to calculate the gradient of the neural network weights and update the weights, and the gradient calculation involves the chain rule and the derivative of the activation function. The specific calculation formulas of the chain rule and the activation function are the prior art content in this field, which is not the inventive solution of this application and will not be elaborated here.

[0067] Furthermore, the present invention uses a mean square error loss function to measure the prediction error of the multilayer perceptron neural network model, and the formula is: ,in, represents the jth true temperature value, represents the j-th predicted temperature value, n represents the number of samples, and MSE represents the mean square error;

[0068] Furthermore, the weight update formula is: ,in, represents the learning rate, represents the gradient of the weight, represents partial derivative, represents the updated weight, Represents the weight before updating.

[0069] (5) Input the new Kalman filtered temperature data into the trained neural network model. At the same time, the trained neural network model outputs the temperature change trend prediction results. .

[0070] S103: judging the current temperature state in the energy storage cabinet by using a fuzzy logic algorithm according to the temperature change trend prediction result;

[0071] S104: Calculate and adjust the operating parameters of the auxiliary heat dissipation device according to the temperature state determined by fuzzy logic and in combination with a PID control algorithm;

[0072] S105: The phase change material automatically absorbs or releases heat according to the actual temperature change in the energy storage cabinet, and works in coordination with the auxiliary heat dissipation device;

[0073] S106: Regularly collect real-time operation data of the energy storage cabinet, and optimize and update the neural network model and fuzzy logic rules according to the real-time operation data of the energy storage cabinet.

[0074] The real-time operation data of the energy storage cabinet includes temperature data, the operation status of the auxiliary heat dissipation device, and the heat absorption / release status of the phase change material.

[0075] Exemplarily, multiple temperature sensors are installed in the energy storage cabinet to ensure that temperature data can be collected comprehensively and accurately. The temperature sensors collect temperature data at certain time intervals and transmit the temperature data to the data processing module; in the data processing module, the collected temperature data is processed using the Kalman filter algorithm, and the Kalman filter parameters are set according to the characteristics of the temperature data and the noise model, and the temperature data is predicted and updated to obtain accurate temperature data; the historical temperature data of the energy storage cabinet is collected, and the neural network model is trained according to the historical temperature data. After the training is completed, the temperature data after the Kalman filter is input into the neural network model to obtain the temperature change trend prediction result; according to the temperature change trend prediction result, combined with the pre-set fuzzy logic rules, the temperature state in the current energy storage cabinet is judged, and the fuzzy temperature change is converted into a fixed value through the steps of fuzzification, reasoning and defuzzification. The information is converted into a clear judgment of the temperature state; according to the temperature state judged by fuzzy logic, the PID control algorithm is used to calculate the adjustment value of the operating parameters of the auxiliary heat dissipation device, and according to the adjustment value, the power, speed and other parameters of the auxiliary heat dissipation device are controlled to achieve precise heat dissipation; in addition, phase change materials are installed in the energy storage cabinet. The phase change materials automatically absorb or release heat according to the actual temperature changes in the energy storage cabinet. When the temperature rises, the phase change material absorbs heat and slows down the temperature rise rate. When the temperature drops, the phase change material releases heat to keep the temperature in the energy storage cabinet stable. At the same time, the phase change material works with the auxiliary heat dissipation device to improve the heat dissipation effect; the real-time operation data of the energy storage cabinet is regularly collected and stored in the database. The real-time operation data is analyzed using data analysis tools. The neural network model and fuzzy logic rules are optimized and updated according to the analysis results to improve the performance and adaptability of the system.

[0076] The temperature data is processed by the Kalman filter algorithm and transmitted to the control system, including:

[0077] A1: Obtain the temperature data in the energy storage cabinet and set the initial parameters of the Kalman filter algorithm; the initial parameters of the Kalman filter algorithm include the state transfer matrix , observation matrix , process noise covariance matrix , observation noise covariance matrix , initial state estimate C and initial error covariance matrix ;

[0078] A2: Based on the estimated value of the state at time t-1 and the state transition matrix , through the formula Predict the current state estimate, where t represents the current time, represents the control matrix, Represents the control input at the current moment;

[0079] A3: According to the error covariance matrix at time t-1 , state transfer matrix and the process noise covariance matrix , calculate the prediction error covariance matrix at the current moment , and introduces uncertainty quantification methods to Correction is performed to obtain the corrected error covariance matrix ;

[0080] Furthermore, the specific steps of A3 include:

[0081] (1) Use the error covariance matrix at time t-1 , state transfer matrix and the process noise covariance matrix , according to the formula Calculate the prediction error covariance matrix at the current moment, where express The transpose of

[0082] (2) Using the Bayesian method to evaluate the uncertainty of the prediction error covariance matrix, and identifying the uncertainty or error in the prediction error covariance matrix based on the uncertainty analysis results, wherein the Bayesian method reflects new information by updating the probability distribution, and the Bayesian method is the prior art content in this field, and is not the inventive solution of the present application, and will not be described in detail here;

[0083] (3) According to the recognition results, the prediction error covariance matrix is ​​corrected.

[0084] A4: Utilization , observation matrix and the observation noise covariance matrix at the current moment , calculate the Kalman gain At the same time, an observation fusion strategy is introduced to calculate the weighted Kalman gain based on the observation values ​​of multiple temperature sensors. , the Kalman gain calculation formula is: ,in, express The transpose of

[0085] Among them, when calculating the weighted Kalman gain, the Kalman gain of each temperature sensor is The corresponding weights are weighted summed, and the selection of weights can be determined according to the inverse of the observation noise covariance matrix, because the smaller the observation noise, the more reliable the observation value of the temperature sensor, and the corresponding Kalman gain should be given greater weight.

[0086] A5: Based on the current observation value , and , update the current state estimate , the formula is: ,in, Indicates the real state value at the current moment, represents the observation noise at the current moment;

[0087] A6: Exploitation , , and the identity matrix , update the error covariance matrix at the current moment , the formula is: ;

[0088] A7: Update the estimated state value and the error covariance matrix As the initial value of the next moment, repeat steps A2 to A6 until all temperature data are processed;

[0089] A8: Transmit the processed temperature data X to the control system.

[0090] According to the temperature change trend prediction result, the fuzzy logic algorithm is used to judge the current temperature state in the energy storage cabinet, including:

[0091] B1: Predict results based on temperature change trend , combining with a preset dynamic temperature threshold, defining the temperature state in the energy storage cabinet and determining the domain of temperature data; the temperature state in the energy storage cabinet includes low temperature, medium temperature and high temperature;

[0092] The domain of temperature data refers to the value range of temperature data.

[0093] Furthermore, the temperature state classification or definition rules in the energy storage cabinet are as follows:

[0094] (1) Setting the low temperature threshold and high temperature threshold ;

[0095] (2) If , the temperature state is low temperature;

[0096] like , then the temperature state is medium temperature;

[0097] like , the temperature state is high temperature;

[0098] (3) Loading a pre-trained decision tree model, and using the pre-trained decision tree model to dynamically adjust the temperature threshold according to historical data and real-time prediction results to adapt to different environments and working conditions, wherein the decision tree model is the prior art content in this field and is not the inventive solution of the present application, and is not elaborated here.

[0099] B2: For each temperature state in the energy storage cabinet, establish a fuzzy set and use A Gaussian membership function is defined for each fuzzy set, and a genetic algorithm is used to optimize the Gaussian membership function, where: represents the exponential function, express Corresponding Gaussian membership function; the fuzzy set includes a low temperature fuzzy set , medium temperature fuzzy set and high temperature fuzzy set , represents the mean, represents variance;

[0100] Furthermore, the specific steps of defining a Gaussian membership function for each fuzzy set include:

[0101] (1) Obtain the fuzzy set of each temperature state in the energy storage cabinet, including the low temperature fuzzy set , medium temperature fuzzy set and high temperature fuzzy set ;

[0102] (2) For each fuzzy set, determine the two key parameters of the Gaussian membership function: mean and standard deviation ;

[0103] (3) Use the formula Construct a Gaussian membership function for each fuzzy set, where represents the exponential function, express The corresponding Gaussian membership function.

[0104] It should be noted that, on the one hand, the Gaussian membership function can accurately describe the fuzziness of the temperature state in the energy storage cabinet through the two parameters of mean and standard deviation, where the mean reflects the central value of the temperature state, that is, the most typical temperature, and the standard deviation describes the degree of dispersion of the temperature value around the central value, that is, the degree of fuzziness of the temperature value belonging to the fuzzy set. This representation method not only retains the core characteristics of the temperature state, but also takes into account its uncertainty, making the description of the temperature state more comprehensive and accurate. On the other hand, by defining the Gaussian membership function, the division of the temperature state can be adjusted according to actual needs. For example, the boundary and shape of the fuzzy set can be changed by changing the values ​​of the mean and standard deviation to adapt to different monitoring needs and temperature changes. This flexibility makes temperature monitoring more adaptable to actual conditions and improves the practicality and adaptability of the monitoring system.

[0105] Furthermore, the specific steps of optimizing the Gaussian membership function using the genetic algorithm include:

[0106] (1) Set the population size, genetic generation, crossover probability, and mutation probability parameters of the genetic algorithm;

[0107] (2) Determine the fitness function based on the control requirements and performance indicators of the temperature state in the energy storage cabinet , where the fitness function is used to evaluate the quality of each individual; the control requirement of the temperature state in the energy storage cabinet is the specific condition or range that the temperature state in the energy storage cabinet should reach or maintain, including temperature range control, temperature fluctuation control and thermal runaway prevention; the performance index is used to quantitatively evaluate the control effect of the temperature state in the energy storage cabinet, including temperature accuracy, temperature stability and energy efficiency ratio;

[0108] (3) Determine the parameter mean of the Gaussian membership function and standard deviation , the parameters of the membership functions are encoded as individual genes in the genetic algorithm;

[0109] The specific steps of encoding the parameters of the membership function into individual genes in the genetic algorithm include:

[0110] Setting the mean and standard deviation The initial value of

[0111] Set the length of the individual vector ;

[0112] Use real number encoding to convert the mean and standard deviation Directly as two elements in the individual vector, the individual vector is [ μ , σ ] , the first element corresponds to the mean and the second element corresponds to the standard deviation.

[0113] (4) According to the coding rules, a set of membership function parameters is randomly generated as the initial population;

[0114] (5) Use the fitness function to evaluate the fitness of each individual in the initial population and calculate the performance of its corresponding membership function on the temperature data. The formula is: , where I represents the individual index, represents the i-th predicted temperature data point, N represents the number of predicted temperature data, and are the mean and standard deviation of individual I, represents the expected output value corresponding to the i-th predicted temperature data point, represents Gaussian membership function;

[0115] (6) Genetic manipulation:

[0116] Selection: Select excellent individuals as parents according to their fitness values;

[0117] Crossover: Perform a crossover operation on the parent individuals to generate offspring individuals;

[0118] Mutation: Perform mutation operations on offspring individuals to increase the diversity of the population;

[0119] (7) Replace the parent individuals with the offspring individuals to form a new population;

[0120] (8) Repeat steps (5) to (7) until the preset genetic generation number is reached;

[0121] (9) Select the individual with the highest fitness value from the final population, decode the parameters of the optimized membership function, and generate the optimized Gaussian membership function .

[0122] It should be noted that by optimizing the parameters of the Gaussian membership function through genetic algorithms, the temperature range and control accuracy of each fuzzy set can be accurately adjusted. This optimization ensures that the temperature state in the energy storage cabinet can accurately reach or be maintained within a specific condition or range, meeting the requirements of temperature range control, temperature fluctuation control, and thermal runaway prevention. Moreover, the optimized Gaussian membership function can improve the performance indicators of the temperature monitoring system, such as temperature accuracy, temperature stability, and energy efficiency ratio, which means that the system can more accurately monitor and control the temperature state in the energy storage cabinet, reduce temperature fluctuations, and improve the stability and efficiency of the system.

[0123] In summary, genetic algorithms can automatically search and find the optimal membership function parameters in a complex temperature control environment by simulating natural selection and genetic mechanisms. This adaptive ability enables the system to cope with various uncertain factors, such as changes in ambient temperature and changes in the internal heat load of the energy storage cabinet, thereby maintaining a stable temperature control effect; the parameters of the Gaussian membership function are encoded as individual genes in the genetic algorithm and directly used as elements in the individual vector through real number encoding, which simplifies the parameter adjustment process, so that users do not need to adjust the parameters manually, but can automatically search for the optimal solution through the genetic algorithm, reducing the complexity of system debugging and maintenance. Combining the optimization of the genetic algorithm with the Gaussian membership function defined for each fuzzy set can significantly improve the performance and control accuracy of the energy storage cabinet temperature control system, enhance the adaptability and robustness of the system, simplify the parameter adjustment process, and promote the intelligence and automation of the system.

[0124] B3: Obtain optimized Gaussian membership function , for each predicted temperature data point , using the optimized Gaussian membership function Calculate its membership in different fuzzy sets, where ;

[0125] in, The result represents the predicted temperature data point The degree of membership in the corresponding fuzzy set.

[0126] B4: According to the management requirements of the energy storage cabinet and the temperature status judgment criteria, an intelligent fuzzy rule base based on the knowledge graph is constructed;

[0127] Furthermore, the specific steps of B4 include:

[0128] (1) Clarify the energy storage cabinet management requirements. For example, determine the temperature safety range of the energy storage cabinet under different operating conditions, such as charging, discharging, and idle;

[0129] (2) Obtain the temperature state judgment standard in B1;

[0130] (3) Extract the entities, attributes, and relationships of energy storage cabinet temperature management and construct a knowledge graph, where entities include energy storage cabinet, temperature sensor, and temperature status; attributes include temperature value and status description; and relationships include belonging to and affecting;

[0131] (4) Based on the temperature status judgment criteria, fuzzy rules are designed to describe the relationship between the temperature status and the energy storage cabinet management decision. The fuzzy rules include the conversion of temperature status, the triggering of alarm conditions, and the generation of maintenance recommendations.

[0132] (5) Encode the designed fuzzy rules into computer-executable logic and build an intelligent fuzzy rule base. The rule base should be able to receive real-time data from the temperature sensor and make inferences and decisions based on the fuzzy rules.

[0133] B5: According to The membership degree and intelligent fuzzy rule base of each fuzzy set are inferred by a fuzzy logic reasoning method based on deep learning, wherein the fuzzy logic reasoning method based on deep learning adopts a neural network model, and the deep learning model is trained by using a labeled training data set to obtain a trained neural network model, and a new temperature value is input into the trained neural network model, and reasoning is performed according to the membership degree and intelligent fuzzy rule base of the fuzzy set of the input temperature value, and the neural network model is the prior art content in this field, and is not the inventive solution of the present application, and will not be described in detail here;

[0134] B6: According to the result of fuzzy logic reasoning, determine the temperature state in the current energy storage cabinet and output the temperature state.

[0135] The temperature state determined by fuzzy logic, combined with the PID control algorithm, calculates and adjusts the operating parameters of the auxiliary heat dissipation device, including:

[0136] C1: Obtain the temperature state in the current energy storage cabinet determined by fuzzy logic in B6;

[0137] C2: Set the target temperature value of the PID controller according to the temperature state determined by fuzzy logic;

[0138] C3: Calculate the current temperature error based on the target temperature value and the real-time temperature data collected by the temperature sensor, and execute the PID control algorithm to obtain the control output;

[0139] Furthermore, the specific steps of executing the PID control algorithm include:

[0140] (1) Converting the target temperature value and the real-time temperature data collected by the temperature sensor into electrical signals, and then converting the electrical signals into digital signals through an analog-to-digital converter for subsequent calculation and processing. The analog-to-digital converter is a prior art in the art and is not an inventive solution of the present application, and is not described in detail here.

[0141] (2) Calculate the current temperature error based on the converted digital signal ,in, Indicates the temperature error at the current moment, Indicates the target temperature value, Indicates real-time temperature data;

[0142] (3) The calculated temperature error The three links of the PID controller, including proportion, integration and differentiation, are processed. The specific operation is: and PID coefficient , , Multiply them, and then add the product to the temperature error at the previous moment, and finally get the control output signal at the current moment. The formula is: ,in, Indicates the output control signal;

[0143] (4) The calculated control output signal is transmitted to the controlled object, thereby realizing precise control of the temperature, wherein the controlled object is a refrigeration device.

[0144] C4: Calculating the operating parameters of the auxiliary heat dissipation device according to the control output; the operating parameters refer to power;

[0145] Furthermore, the specific steps of C4 include:

[0146] (1) Obtain the corresponding relationship between the control output and the power of the auxiliary heat dissipation device through experiments or by referring to the equipment manual;

[0147] (2) Use sensors to collect control signals output by PID controller;

[0148] (3) converting the collected control output signal into a parameter associated with the power of the auxiliary heat dissipation device;

[0149] The process of converting the collected control output signal into a parameter associated with the power of the auxiliary heat dissipation device includes:

[0150] Clarify the type of control signal output by the PID controller and its output range;

[0151] Consult the technical manual or specification of the auxiliary heat sink to understand the corresponding relationship between its power and input signal;

[0152] The parameter conversion is completed according to the characteristics of the auxiliary heat dissipation device and the corresponding relationship between the power and the input signal.

[0153] (4) Based on the converted parameters and the characteristics of the auxiliary heat dissipation device, use the formula Calculate the required power value P, where represents the corresponding relationship function between the control output signal and the power, and u represents the control output signal;

[0154] (5) Verify the calculated power value to ensure that it meets the operating requirements and safety standards of the auxiliary heat dissipation device.

[0155] C5: According to the operating parameters, adjust the working state of the auxiliary heat dissipation device, monitor the actual operating effect and make adjustments, wherein an adaptive PID control algorithm is used to fine-tune the PID controller parameters during the adjustment. Specifically, the application of the adaptive PID control algorithm in the PID controller is mainly through real-time monitoring of parameters such as system error, control output and system response, and then dynamically adjusting the proportional, integral and differential parameters of the PID controller according to the changes in these parameters. In this way, the PID controller can maintain optimal control performance under different working conditions, thereby improving the heat dissipation effect and reducing abnormal temperature fluctuations. For example, when it is found that the heat dissipation effect is not ideal or the temperature fluctuates abnormally, the adaptive PID control algorithm will start the parameter fine-tuning mechanism, make subtle adjustments to the parameters of the PID controller, and return to step C3 to recalculate the control output to achieve more precise control of the heat dissipation system.

[0156] The phase change material automatically absorbs or releases heat according to the actual temperature change in the energy storage cabinet, and works in coordination with the auxiliary heat dissipation device, including:

[0157] D1: The control system determines the temperature state in the energy storage cabinet based on the signal from the temperature sensor. When the temperature exceeds the phase change point of the phase change material, the phase change material begins to absorb heat and changes from solid to liquid. When the temperature is lower than the phase change point, the phase change material begins to release heat and changes from liquid to solid.

[0158] D2: When the temperature inside the energy storage cabinet exceeds the preset maximum temperature threshold and the heat absorption value of the phase change material is less than the heat dissipation temperature value of the energy storage cabinet, the control system starts the auxiliary heat dissipation device. While the phase change material absorbs heat, the auxiliary heat dissipation device also works according to the adjusted operating parameters to maintain the temperature inside the energy storage cabinet within the set range.

[0159] Example 2

[0160] See also Figure 4 Another embodiment provided by the present invention is an energy storage cabinet energy-saving thermal management system of a phase change material, comprising:

[0161] Data processing module, temperature change prediction module, temperature state judgment module, heat dissipation control module, phase change material collaborative heat dissipation module, optimization and update module;

[0162] The data processing module is used to collect the temperature data in the energy storage cabinet and perform Kalman filtering;

[0163] The temperature change prediction module is used to use the neural network model to predict the temperature data after Kalman filtering to obtain the temperature change trend prediction result;

[0164] The temperature status judgment module is used to judge the temperature status in the current energy storage cabinet based on the prediction results of the temperature change trend and the fuzzy logic algorithm;

[0165] The heat dissipation control module is used to calculate and adjust the operating parameters of the auxiliary heat dissipation device according to the judgment result of the temperature state in combination with the PID control algorithm;

[0166] Phase change material collaborative heat dissipation module, which is used to automatically absorb or release heat according to the actual temperature changes in the energy storage cabinet, and work in conjunction with the auxiliary heat dissipation device;

[0167] The optimization and update module is used to regularly collect the real-time operation data of the energy storage cabinet, and optimize and update the neural network model and fuzzy logic rules based on the real-time operation data.

[0168] The data processing module includes: a sensor unit and a filter unit;

[0169] The sensor unit is used to collect temperature data in the energy storage cabinet in real time and provide original temperature information, which is the basis for subsequent processing and analysis;

[0170] The filtering unit is used to perform Kalman filtering on the temperature data collected by the temperature sensor to remove noise, smooth the data, and improve the accuracy and stability of the data.

[0171] The heat dissipation control module includes: a PID control unit and an auxiliary heat dissipation device unit;

[0172] The PID control unit is used to receive the judgment result of the temperature state, calculate the operating parameters of the auxiliary heat dissipation device, and adjust the auxiliary heat dissipation device, such as the speed and power parameters of the fan and heat sink, according to the temperature state through the PID control algorithm to achieve accurate temperature control;

[0173] The auxiliary heat dissipation device unit is used to execute the calculation results of the PID control unit, adjust the heat dissipation effect, and adjust the temperature inside the energy storage cabinet by adjusting its own operating state, such as speed, power, etc.

[0174] The optimization and updating module includes: a data collection unit and a model optimization unit;

[0175] The data collection unit is used to regularly collect the real-time operating data of the energy storage cabinet. By collecting real-time data including temperature data, the operating status of the auxiliary heat dissipation device, the heat absorption / exothermic status of the phase change material, etc., it provides a basis for subsequent optimization and updating;

[0176] The model optimization unit is used to optimize and update the neural network model and fuzzy logic rules according to real-time operating data, so as to improve the prediction accuracy of the neural network model and the judgment ability of the fuzzy logic rules through learning and training, thereby optimizing the performance of the entire thermal management system.

[0177] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. A phase change material energy storage cabinet energy saving thermal management method, characterized in that: include: The temperature sensor collects the temperature data in the energy storage cabinet, and the temperature data is processed by the Kalman filter algorithm and then transmitted to the control system; The control system uses a neural network model to predict temperature changes on the temperature data after Kalman filtering to obtain a temperature change trend prediction result; According to the temperature change trend prediction result, a fuzzy logic algorithm is used to determine the current temperature state in the energy storage cabinet; According to the temperature state determined by fuzzy logic and combined with PID control algorithm, the operating parameters of the auxiliary heat dissipation device are calculated and adjusted; The phase change material automatically absorbs or releases heat according to the actual temperature change in the energy storage cabinet, and works in coordination with the auxiliary heat dissipation device; Regularly collect the real-time operation data of the energy storage cabinet, and optimize and update the neural network model and fuzzy logic rules based on the real-time operation data of the energy storage cabinet.

2. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 1, characterized in that: The temperature data is processed by the Kalman filter algorithm and transmitted to the control system, including: A1: Obtain the temperature data in the energy storage cabinet and set the initial parameters of the Kalman filter algorithm; the initial parameters of the Kalman filter algorithm include the state transfer matrix , observation matrix , process noise covariance matrix , observation noise covariance matrix , initial state estimate C and initial error covariance matrix ; A2: Based on the estimated value of the state at time t-1 and the state transition matrix , predict the current state estimate , where t represents the current time; A3: According to the error covariance matrix at time t-1 , state transfer matrix and the process noise covariance matrix , predict the error covariance matrix at the current moment , and introduces uncertainty quantification methods to Correction is performed to obtain the corrected error covariance matrix .

3. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 2, characterized in that: The temperature data is processed by the Kalman filter algorithm and then transmitted to the control system, which also includes: A4: Utilization , observation matrix and the observation noise covariance matrix at the current moment , calculate the Kalman gain At the same time, an observation fusion strategy is introduced to calculate the weighted Kalman gain based on the observation values ​​of multiple temperature sensors. ; A5: Based on the current observation value, and , update the current state estimate ; A6: Utilization , , and the identity matrix , update the error covariance matrix at the current moment ; A7: Update the estimated state value and the error covariance matrix As the initial value of the next moment, repeat steps A2 to A6 until all temperature data are processed; A8: Transmit the processed temperature data X to the control system.

4. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 3, characterized in that: The method of determining the current temperature state in the energy storage cabinet by using a fuzzy logic algorithm according to the temperature change trend prediction result includes: B1: Predict results based on temperature change trend , combined with a preset dynamic temperature threshold, define the temperature state in the energy storage cabinet and determine the domain of temperature data; the temperature state in the energy storage cabinet includes low temperature, medium temperature and high temperature; B2: For each temperature state in the energy storage cabinet, establish a fuzzy set and use A Gaussian membership function is defined for each fuzzy set, and a genetic algorithm is used to optimize the Gaussian membership function, where: represents the exponential function, express Corresponding Gaussian membership function; the fuzzy set includes a low temperature fuzzy set , medium temperature fuzzy set and high temperature fuzzy set , represents the mean, represents variance; B3: Obtain optimized Gaussian membership function , for each predicted temperature data point , using the optimized Gaussian membership function Calculate its membership in different fuzzy sets, where .

5. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 4, characterized in that: The method of using a fuzzy logic algorithm to judge the current temperature state in the energy storage cabinet according to the temperature change trend prediction result also includes: B4: According to the management requirements of the energy storage cabinet and the temperature status judgment criteria, an intelligent fuzzy rule base based on the knowledge graph is constructed; B5: According to The membership degree and intelligent fuzzy rule base of each fuzzy set are inferred by the fuzzy logic reasoning method based on deep learning; B6: According to the result of fuzzy logic reasoning, determine the temperature state in the current energy storage cabinet and output the temperature state.

6. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 5, characterized in that: The temperature state determined by fuzzy logic, combined with the PID control algorithm, calculates and adjusts the operating parameters of the auxiliary heat dissipation device, including: C1: Obtain the temperature state in the current energy storage cabinet determined by fuzzy logic in B6; C2: Set the target temperature value of the PID controller according to the temperature state determined by fuzzy logic; C3: Calculate the current temperature error based on the target temperature value and the real-time temperature data collected by the temperature sensor, and execute the PID control algorithm to obtain the control output; C4: Calculating the operating parameters of the auxiliary heat dissipation device according to the control output; the operating parameters refer to power; C5: According to the operating parameters, adjust the working state of the auxiliary heat dissipation device, monitor the actual operating effect and make adjustments.

7. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 6, characterized in that: The phase change material automatically absorbs or releases heat according to the actual temperature change in the energy storage cabinet, and works in coordination with the auxiliary heat dissipation device, including: D1: The control system determines the temperature state in the energy storage cabinet based on the signal from the temperature sensor. When the temperature exceeds the phase change point of the phase change material, the phase change material begins to absorb heat and changes from solid to liquid. When the temperature is lower than the phase change point, the phase change material begins to release heat and changes from liquid to solid. D2: When the temperature inside the energy storage cabinet exceeds the preset maximum temperature threshold and the heat absorption value of the phase change material is less than the heat dissipation temperature value of the energy storage cabinet, the control system starts the auxiliary heat dissipation device. While the phase change material absorbs heat, the auxiliary heat dissipation device also works according to the adjusted operating parameters to maintain the temperature inside the energy storage cabinet within the set range.

8. The energy-saving thermal management method of a phase change material energy storage cabinet according to claim 7, characterized in that: The real-time operation data of the energy storage cabinet includes temperature data, the operation status of the auxiliary heat dissipation device, and the heat absorption / exothermic status of the phase change material.

9. An energy-saving thermal management system for energy storage cabinets made of phase change materials, which is used to implement an energy-saving thermal management method for energy storage cabinets made of phase change materials according to any one of claims 1 to 8, characterized in that: include: Data processing module, temperature change prediction module, temperature state judgment module, heat dissipation control module, phase change material collaborative heat dissipation module, optimization and update module; The data processing module is used to collect temperature data in the energy storage cabinet and perform Kalman filtering; The temperature change prediction module is used to predict the temperature data after Kalman filtering using a neural network model to obtain a temperature change trend prediction result; The temperature state judgment module is used to judge the temperature state in the current energy storage cabinet using a fuzzy logic algorithm according to the temperature change trend prediction result; The heat dissipation control module is used to calculate and adjust the operating parameters of the auxiliary heat dissipation device according to the judgment result of the temperature state in combination with the PID control algorithm; The phase change material cooperative heat dissipation module is used to automatically absorb or release heat according to the actual temperature change in the energy storage cabinet, and work in coordination with the auxiliary heat dissipation device; The optimization and update module is used to regularly collect real-time operation data of the energy storage cabinet, and optimize and update the neural network model and fuzzy logic rules according to the real-time operation data.

Images