Semi-superconducting motor adaptive heat dissipation control method and system

Abstract

The present invention belongs to the field of motor heat dissipation, and specifically relates to a semi-superconducting motor adaptive heat dissipation control method and system, which aims to solve the problems of insufficient real-time performance, complex models, high difficulty in optimizing control strategies, and poor adaptability in the prior art. The present invention includes: obtaining real-time temperature data of the motor; inputting the real-time temperature data and motor load data as input data into a fuzzy control algorithm optimized based on a genetic algorithm; the fuzzy control algorithm calculates control parameters based on fuzzy rules, and adjusts the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters. The present invention can flexibly change the search strategy of the genetic algorithm according to the individual's fitness, improve the search efficiency and optimization results, can accurately control and adapt to a variety of systems, increase the service life of the motor, and simplify design and debugging.

Description

Background Art

[0002] The semi-superconducting energy-saving motor adaptive cooling system is a system that adjusts the cooling method and controls the temperature in real time according to the working state of the motor. It mainly includes two parts: cooling device and control system.

[0003] The heat dissipation device generally consists of a radiator, a fan and a temperature sensor. The radiator is usually made of aluminum or copper and has good thermal conductivity. The fan accelerates the heat dissipation by generating airflow. The temperature sensor is used to monitor the motor temperature in real time and transmit the temperature data to the control system.

[0004] The control system controls the cooling effect by adjusting the fan speed and the cooling area of ​​the radiator according to the motor temperature data and the preset temperature range. When the motor temperature exceeds the preset range, the control system will increase the fan speed and the cooling area of ​​the radiator to speed up the cooling speed; when the motor temperature is lower than the preset range, the control system will reduce the fan speed and the cooling area of ​​the radiator to reduce energy consumption.

[0005] In addition, the semi-superconducting energy-saving motor adaptive cooling system can also be adaptively adjusted according to changes in the motor's workload. When the motor load increases, the control system will increase the radiator cooling area and fan speed accordingly to keep the motor temperature within a reasonable range; when the motor load decreases, the control system will reduce the radiator cooling area and fan speed accordingly to reduce energy consumption.

[0006] In general, the semi-superconducting energy-saving motor adaptive cooling system can effectively protect the motor and save energy consumption by adjusting the cooling method and controlling the temperature in real time.

[0007] In the prior art semi-superconducting energy-saving motor adaptive heat dissipation system, there are the following disadvantages:

[0008] High real-time requirements: The adaptive cooling algorithm needs to analyze and respond to changes in the motor's working state in real time. If the algorithm processing speed is slow or there is a delay, it may cause the motor to overheat or overcool, affecting the overall performance and efficiency.

[0009] Model complexity: Motor heating is related to many factors such as environment, load, speed, etc. It is relatively complex to build a physical model that accurately reflects these relationships. If the algorithm is too simplified, it may not be able to effectively adapt to all operating conditions, while an overly complex model may lead to high consumption of computing resources and low execution efficiency.

[0010] Difficulty in optimizing control strategies: The cooling system needs to design efficient control logic to dynamically adjust cooling measures such as fan speed and pump flow. However, the design of the optimal control strategy often involves multi-objective optimization problems. How to balance cooling effect, energy consumption, noise, and equipment life is a challenge.

[0011] Adaptability and scalability: As the motor's operating environment and load conditions change, the heat dissipation requirements will also change. The ideal adaptive heat dissipation algorithm should have good adaptability and scalability, and be able to maintain good performance under a variety of unknown or unforeseen conditions.

[0012] Based on this, the present invention proposes a semi-superconducting motor adaptive heat dissipation control method and system. Summary of the invention

[0013] In order to solve the above problems in the prior art, namely, the problems of insufficient real-time performance, complex models, high difficulty in optimizing control strategies and poor adaptability in the prior art, the present invention provides a semi-superconducting motor adaptive heat dissipation control method and system.

[0014] In a first aspect, the present invention provides a method for adaptive heat dissipation control of a semi-superconducting electric motor, the method comprising:

[0015] Get the real-time temperature data of the motor;

[0016] The real-time temperature data and the motor load data are input as input data into a fuzzy control algorithm based on genetic algorithm optimization;

[0017] The fuzzy control algorithm calculates control parameters based on fuzzy rules, and adjusts the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters.

[0018] In some preferred embodiments, the control parameter is calculated as follows:

[0019] The input data is fuzzified using a membership function, wherein the membership function includes preset membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature;

[0020] Based on the membership function and the preset rule weight, the inference result corresponding to the preset fuzzy rule is calculated, the inference result is defuzzified to obtain the defuzzified result, and converted into the control parameter.

[0021] In some preferred embodiments, the membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature are:

[0022] μ1(x1)=trimf(x1,[0,0,0.5]);

[0023] μ2(x1)=trimf(x1,[0,0.5,1]);

[0024] μ3(x1)=trimf(x1,[0.5,1,1]);

[0025] μ4(x2)=trimf(x2,[0,0,50]);

[0026] μ5(x2)=trimf(x2,[0,50,100]);

[0027] μ6(x2)=trimf(x2,[50,100,100]);

[0028] Among them, μ1(x1) is the membership function of light load; μ2(x1) is the membership function of moderate load; μ3(x1) is the membership function of heavy load; μ4(x2) is the membership function of low temperature; μ5(x2) is the membership function of moderate temperature; μ6(x2) is the membership function of high temperature; x1 is the load data; x2 is the real-time temperature data, and trimf is the representation of the membership function.

[0029] In some preferred implementations, the preset fuzzy rules are:

[0030] The first rule: light load and low temperature correspond to a small heat dissipation area of ​​the radiator; the second rule: moderate load and moderate temperature correspond to a moderate heat dissipation area of ​​the radiator; the third rule: heavy load and high temperature correspond to a large heat dissipation area of ​​the radiator.

[0031] In some preferred implementations, the inference result corresponding to the preset fuzzy rule is:

[0032] The inference result corresponding to the first rule = a×(μ1(x1)×μ4(x2));

[0033] The inference result corresponding to the second rule = b×(μ2(x1)×μ5(x2));

[0034] The inference result corresponding to the third rule = c × (μ3 (x1) × μ6 (x2));

[0035] Among them, a, b, and c are all preset rule weights.

[0036] In some preferred implementations, the inference result is defuzzified to obtain a defuzzified result, and the method is:

[0037] Defuzzification result = (the reasoning result corresponding to the first rule × a + the reasoning result corresponding to the second rule × b + the reasoning result corresponding to the third rule × c) / (a ​​+ b + c).

[0038] In some preferred implementations, the fuzzy control algorithm based on genetic algorithm optimization is obtained by:

[0039] Step S10, randomly generating an initial population P according to a set parameter range; the initial population P includes a plurality of individuals Pi, each of the individuals Pi includes three fuzzy rules and six membership function parameters;

[0040] Step S20, for each individual Pi, according to the current fuzzy rules and membership function parameters, use the fuzzy inference system to perform inference to obtain an output result, wherein the output result is the radiator area and temperature deviation;

[0041] Step S30, calculating the sum of fitness of all individuals according to the output result and the preset weight coefficient, and calculating the selection probability of each individual, and calculating the adaptive mutation probability according to the selection probability;

[0042] Step S40, calculating the fitness value of each individual, performing a selection operation on the individuals in the population to generate a parent set P', selecting two individuals from the parent set P' as the father and the mother, performing a crossover operation, and generating a child set C;

[0043] Step S50, for each individual Pi in the offspring set C, a gene is selected for mutation operation with a set probability according to the adaptive mutation probability; the parent set P' and the offspring set C are merged to obtain a new population P;

[0044] Steps S20-S50 are executed cyclically until the maximum number of iterations is reached or the convergence condition is met, and the loop is terminated;

[0045] Step S60, after the cycle ends, the individual with the best fitness is selected as the optimal solution, the optimal solution is the optimal fuzzy rule and membership function parameters, and the fuzzy control algorithm is optimized based on the optimal solution.

[0046] In some preferred embodiments, the sum of fitness of all individuals is calculated as follows:

[0047] The preset fitness function is F(Pi)=A(Pi)×w1+E(Pi)×w2;

[0048] Where w1 and w2 are weight coefficients used to balance the importance of heat sink area and temperature deviation; A(Pi) represents the heat sink area of ​​individual Pi, and E(Pi) represents the temperature deviation of individual Pi;

[0049] Fsum=ΣF(Pi);

[0050] Among them, Fsum is the sum of fitness of all individuals.

[0051] In some preferred embodiments, the heat sink area and the temperature deviation are calculated as follows:

[0052] A = p × load + q;

[0053] E = f × (target temperature - actual temperature) + d;

[0054] Among them, p and q are two parameters of the membership function of the radiator area; f and d are two parameters of the membership function of the temperature deviation; load is the load input of the motor, the target temperature is the center value of the preset safe temperature range, and the actual temperature is the temperature value calculated according to the current fuzzy rules and membership function parameters; A is the radiator area; E is the temperature deviation.

[0055] Another aspect of the present invention provides a semi-superconducting electric motor adaptive heat dissipation control system, based on a semi-superconducting electric motor adaptive heat dissipation control method, the system comprises:

[0056] A temperature acquisition module configured to acquire real-time temperature data of the motor;

[0057] An input module configured to input the real-time temperature data and motor load data as input data into a fuzzy control algorithm optimized based on a genetic algorithm;

[0058] An adjustment module, configured to calculate control parameters using the fuzzy control algorithm based on fuzzy rules, and adjust the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters;

[0059] The control parameter is calculated as follows:

[0060] The input data is fuzzified using a membership function, wherein the membership function includes preset membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature;

[0061] Based on the membership function and the preset rule weight, the inference result corresponding to the preset fuzzy rule is calculated, the inference result is defuzzified to obtain the defuzzified result, and converted into the control parameter.

[0062] Beneficial effects of the present invention:

[0063] Adaptability: Fuzzy control can handle nonlinear and uncertain systems. Through fuzzy logic reasoning, it can automatically adjust the fan speed and radiator working status according to the system's real-time temperature, load changes and other parameters. This means that the system can dynamically optimize the cooling strategy according to different working conditions and environmental changes, thereby improving cooling efficiency and ensuring stable hardware operation.

[0064] Precise control: Traditional on-off or proportional control may be too simplistic and crude when dealing with complex and changing cooling requirements. Fuzzy control can adjust the fan speed more finely, while keeping the CPU or other heating components at a safe operating temperature, while minimizing unnecessary noise and power consumption.

[0065] Energy saving and noise reduction: Fuzzy control can increase or decrease the fan speed appropriately according to actual needs, avoiding the high energy consumption and noise problems caused by long-term full-speed operation. When the device temperature is low, the fan speed can be reduced to achieve silent operation; when the temperature rises, the speed can be quickly increased to effectively dissipate heat.

[0066] Prolong service life: By properly regulating the working state of the fan, it is not only helpful to prevent hardware damage caused by overheating, but also to reduce excessive wear of the fan, thereby extending the service life of the radiator and the entire system.

[0067] Simplified design and debugging: Compared with complex traditional PID control or other advanced control algorithms, fuzzy control rules are relatively intuitive and easy to understand, making it easier for engineers to formulate and modify control strategies, and can reduce the need for precise mathematical models to a certain extent.

[0068] Flexible response: Fuzzy control can quickly respond to various complex working conditions according to the preset fuzzy logic rule set, which is especially suitable for those occasions where it is difficult to establish an accurate mathematical model or the working conditions switch frequently.

[0069] Optimization effect: By adaptively adjusting the mutation probability, the search strategy of the genetic algorithm can be flexibly changed according to the fitness of the individual, thereby improving the search efficiency and optimization results. Individuals with lower fitness will have a higher mutation probability, which can introduce more randomness and avoid premature convergence to the local optimal solution. Individuals with higher fitness will have a lower mutation probability, which can maintain the stability and convergence of the population and avoid excessive randomness affecting the optimization results. Through continuous iteration, the genetic algorithm can adaptively adjust the mutation probability according to the complexity and evolution of the problem to obtain better optimization results. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0071] Figure 1 It is a flow chart of a method for adaptive heat dissipation control of a semi-superconducting electric motor of the present invention;

[0072] Figure 2 It is a structural diagram of a computer system of a server for implementing the method, system, and device embodiments of the present application. DETAILED DESCRIPTION

[0073] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0074] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0075] A first embodiment of the present invention provides a method for adaptive heat dissipation control of a semi-superconducting electric motor, the method comprising:

[0076] Get the real-time temperature data of the motor;

[0077] The real-time temperature data and the motor load data are input as input data into a fuzzy control algorithm based on genetic algorithm optimization;

[0078] The fuzzy control algorithm calculates control parameters based on fuzzy rules, and adjusts the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters.

[0079] Among them, in the semi-superconducting energy-saving motor adaptive cooling system, the motor temperature can be used as a feedback signal and a target temperature can be set as a set value. According to the change of motor load, the control system monitors the motor temperature in real time and calculates the appropriate fan speed and radiator cooling area according to the PID algorithm.

[0080] The present invention is based on our understanding that the semi-superconducting energy-saving motor adaptive heat dissipation system can also be adaptively adjusted according to the changes in the motor workload. When the motor load increases, the control system will increase the heat dissipation area of ​​the radiator and the fan speed accordingly to keep the motor temperature within a reasonable range; when the motor load decreases, the control system will reduce the heat dissipation area of ​​the radiator and the fan speed accordingly to reduce energy consumption. In this process, the research on innovative algorithms is integrated, and then steps 1-5 below are introduced.

[0081] 1. Set the target temperature: Set a reasonable target temperature according to the motor working requirements and heat dissipation requirements.

[0082] 2. Measure motor temperature: Use temperature sensors to monitor motor temperature in real time and feed back temperature data to the control system.

[0083] 3. Calculate the control signal: According to the PID control algorithm, calculate the control signal, that is, the adjustment of the fan speed and the heat dissipation area of ​​the radiator. The PID algorithm calculates the proportional term, integral term and differential term based on the difference between the current temperature and the target temperature, and sums them up to get the final control signal.

[0084] 4. Adjust the fan speed and radiator cooling area: According to the calculated control signal, adjust the fan speed and radiator cooling area. When the motor load increases, increase the fan speed and radiator cooling area to increase the cooling effect; when the motor load decreases, reduce the fan speed and radiator cooling area to reduce energy consumption.

[0085] 5. Real-time monitoring and adjustment: Continuously monitor the motor temperature, and adjust the fan speed and radiator cooling area in real time according to the actual situation to keep the motor temperature within a reasonable range.

[0086] In summary, this is our basic research and development background. If we want to innovate algorithms, we can consider the following directions:

[0087] Intelligent algorithm: Using intelligent algorithms such as machine learning or deep learning, the parameters of the cooling system are automatically adjusted through learning and analysis of large amounts of data to achieve more precise temperature control.

[0088] Fuzzy control algorithm: Considering that there is a certain fuzzy relationship between motor load and temperature, a fuzzy control algorithm can be used to adjust the fan speed and radiator cooling area according to fuzzy rules to achieve more flexible heat dissipation control.

[0089] Predictive control algorithm: By predicting the motor load, the parameters of the cooling system can be adjusted in advance to avoid over- or under-temperature. The predictive control algorithm can combine historical data and load prediction models to predict future loads and perform cooling control accordingly.

[0090] Among them, as mentioned in the article, we selected the fuzzy control algorithm: Considering that there is a certain fuzzy relationship between motor load and temperature, the fuzzy control algorithm can be used to adjust the fan speed and radiator cooling area according to fuzzy rules to achieve more flexible cooling control. In the fuzzy control algorithm, input variables, output variables and fuzzy rules need to be defined. For the superconducting energy-saving motor adaptive cooling system, the motor load and motor temperature can be selected as input variables, and the fan speed and radiator cooling area can be selected as output variables.

[0091] In order to more clearly explain the self-adaptive heat dissipation control method of a semi-superconducting electric machine of the present invention, Figure 1 The embodiments of the present invention are described in detail:

[0092] The real-time temperature data and the motor load data are input as input data into a fuzzy control algorithm based on genetic algorithm optimization;

[0093] In the present invention, the control parameter is calculated as follows:

[0094] The input data is fuzzified using a membership function, wherein the membership function includes preset membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature;

[0095] Based on the membership function and the preset rule weight, the inference result corresponding to the preset fuzzy rule is calculated, the inference result is defuzzified to obtain the defuzzified result, and converted into the control parameter.

[0096] In this embodiment, the membership function selects a triangular membership function.

[0097] After obtaining the defuzzification results, it is necessary to convert them into actual control parameters through certain conversion methods to achieve more flexible heat dissipation control. The specific conversion method can be designed and optimized according to the actual problem. Some commonly used methods are given below:

[0098] Linear mapping method:

[0099] The defuzzification result is mapped to the value range of the actual control parameter, using a linear proportional relationship, that is:

[0100] Control parameter = a*defuzzification result + b

[0101] Where a and b are constants, which are adjusted according to the actual situation. This method is simple and easy to understand, but may have the problem of low accuracy.

[0102] Inversion method:

[0103] The defuzzification result is used as input, and the value of the control parameter is obtained through the inversion function, that is:

[0104] Control parameter = inversion function (defuzzification result)

[0105] The inversion function can be designed and optimized according to the actual problem, for example, polynomial function, exponential function, etc. can be used.

[0106] Static mapping table method:

[0107] A static mapping table is established between the defuzzification results and the control parameters to achieve discrete control, namely:

[0108] Control parameter = mapping table [defuzzification result]

[0109] The mapping table can be designed and optimized according to actual problems, for example, a lookup table, a hash table, etc. can be used.

[0110] Dynamic mapping table method:

[0111] A dynamic mapping table is established between the defuzzification results and the control parameters to achieve continuous control, namely:

[0112] Control parameter = interpolation function (defuzzification result)

[0113] The interpolation function can be designed and optimized according to the actual problem, for example, linear interpolation, spline interpolation, etc. can be used.

[0114] Through the above method, the defuzzification results can be converted into actual control parameters to achieve more flexible heat dissipation control.

[0115] As a further explanation of the present invention, the membership functions of light load, moderate load, heavy load and low temperature, moderate temperature, and high temperature are respectively:

[0116] μ1(x1)=trimf(x1,[0,0,0.5]);

[0117] μ2(x1)=trimf(x1,[0,0.5,1]);

[0118] μ3(x1)=trimf(x1,[0.5,1,1]);

[0119] μ4(x2)=trimf(x2,[0,0,50]);

[0120] μ5(x2)=trimf(x2,[0,50,100]);

[0121] μ6(x2)=trimf(x2,[50,100,100]);

[0122] Among them, μ1(x1) is the membership function of light load; μ2(x1) is the membership function of moderate load; μ3(x1) is the membership function of heavy load; μ4(x2) is the membership function of low temperature; μ5(x2) is the membership function of moderate temperature; μ6(x2) is the membership function of high temperature; x1 is the load data; x2 is the real-time temperature data, and trimf is the representation of the membership function.

[0123] The real-time temperature data and motor load data of the input data are illustrated as follows:

[0124] x1=[0.2, 0.4, 0.6, 0.8, 1.0];

[0125] x2=[30, 40, 50, 60, 70];

[0126] An example of the heat sink area of ​​the output data is given below:

[0127] y=[0.3, 0.5, 0.6, 0.8, 1.0].

[0128] As a further explanation of the present invention, the preset fuzzy rules are:

[0129] The first rule: light load and low temperature correspond to a small heat dissipation area of ​​the radiator; the second rule: moderate load and moderate temperature correspond to a moderate heat dissipation area of ​​the radiator; the third rule: heavy load and high temperature correspond to a large heat dissipation area of ​​the radiator.

[0130] According to fuzzy rules, fuzzy reasoning is performed. The fuzzy relationship matrix method is used for reasoning, and the formula is as follows:

[0131] Inference result = rule weight × (membership 1 × membership 2 × ... × membership n).

[0132] As a further explanation of the present invention, the reasoning result corresponding to the preset fuzzy rule is:

[0133] The inference result corresponding to the first rule = a×(μ1(x1)×μ4(x2));

[0134] The inference result corresponding to the second rule = b×(μ2(x1)×μ5(x2));

[0135] The inference result corresponding to the third rule = c × (μ3 (x1) × μ6 (x2));

[0136] Among them, a, b, and c are all preset rule weights, and a, b, and c are preferably 0.3, 0.5, and 0.4 in this embodiment.

[0137] As a further explanation of the present invention, the inference result is defuzzified to obtain a defuzzified result, and the method is as follows:

[0138] Defuzzification result = ∑(xi×Ai) / ∑Ai;

[0139] Among them, xi is the central value of the fuzzy set; Ai is the membership degree of the fuzzy set.

[0140] As a further explanation of the present invention, the inference result is defuzzified to obtain a defuzzified result, and the method is as follows:

[0141] Defuzzification result = (the inference result corresponding to the first rule × a + the inference result corresponding to the second rule × b + the inference result corresponding to the third rule × c) / (a ​​+ b + c);

[0142] In this embodiment, preferably, the defuzzification result = (the reasoning result corresponding to the first rule × 0.3 + the reasoning result corresponding to the second rule × 0.5 + the reasoning result corresponding to the third rule × 0.4) / (0.3 + 0.5 + 0.4).

[0143] In this process, known input and output data are used to adjust the parameters of fuzzy rules and membership functions through optimization algorithms, so that the output of the fuzzy inference system is as close to the actual output as possible.

[0144] Optimization algorithms, such as genetic algorithm, particle swarm optimization or gradient descent algorithm, can be used to search for the optimal fuzzy rules and membership function parameters.

[0145] Through the iterative optimization process, the parameters of fuzzy rules and membership functions are continuously adjusted to make the output of the model as close as possible to the actual output.

[0146] It should be noted that in practical applications, the specific steps and parameters of model training and optimization need to be adjusted and optimized according to actual conditions to achieve better modeling effects.

[0147] Genetic algorithm is a commonly used optimization algorithm, which has good results in searching for optimal fuzzy rules and membership function parameters. However, for complex problems, genetic algorithm may fall into local optimal solution, so it can be combined with other optimization algorithms or heuristic search algorithms to further improve the search effect.

[0148] Based on this, in the field of semi-superconducting energy-saving motor adaptive cooling system and cooling control:

[0149] The following is a complete example, combining the field of semi-superconducting energy-saving motor adaptive cooling system and cooling control, to demonstrate how to use genetic algorithms to search for optimal fuzzy rules and membership function parameters.

[0150] Suppose we need to design an adaptive cooling system to control the heat dissipation area of ​​the radiator of a semi-superconducting energy-saving motor. We hope to automatically adjust the heat dissipation area of ​​the radiator according to the motor load and temperature input to keep the motor temperature within a safe range.

[0151] Among them, in the field of semi-superconducting energy-saving motor adaptive cooling system and cooling control, the search process of genetic algorithm can be further improved to improve the search effect and optimize the results. The following are some possible improvement measures:

[0152] Multi-objective optimization: Introducing multiple objectives into fitness evaluation, such as minimizing temperature deviation and minimizing heat sink area. Using multi-objective optimization algorithms (such as NSGA-II, MOEA / D, etc.) can obtain a set of non-inferior solutions, providing more options.

[0153] Elite retention strategy: retain individuals with higher fitness, ensure that excellent genes are retained in the population, and avoid premature convergence.

[0154] Parameter adaptation: Dynamically adjust the parameters of the genetic algorithm (such as crossover probability, mutation probability, population size, etc.) according to the complexity and evolution of the problem. Adaptive genetic algorithms (such as adaptive crossover and mutation algorithms) can be used to automatically adjust these parameters.

[0155] Multi-population strategy: Divide the population into multiple sub-populations and conduct information exchange and gene flow between sub-populations to increase global search capabilities.

[0156] Local search: In each generation of the genetic algorithm, local search operators (such as simulated annealing, particle swarm optimization, etc.) are introduced to further optimize individuals.

[0157] Constraint processing: For the constraints of the superconducting energy-saving motor cooling system (such as radiator area limitation), a constraint processing mechanism is introduced to ensure that the generated solution meets the constraints.

[0158] Parallel computing: Utilize multi-core or distributed computing resources to parallelize the genetic algorithm calculation process and speed up the search process.

[0159] Through the application of the above improvement measures, the search effect and optimization results of genetic algorithms in the field of superconducting energy-saving motor adaptive cooling system and cooling control can be further improved. At the same time, according to specific problems and system characteristics, other optimization algorithms or heuristic search algorithms can be combined to further improve and optimize the search process.

[0160] Based on this idea, in order to more specifically illustrate how to implement the improved genetic algorithm, we will take the optimization of the superconducting energy-saving motor cooling system with the goal of minimizing the radiator area and minimizing the temperature deviation as an example. Assume that our goal is to find the optimal fuzzy rules and membership function parameters to minimize the radiator area (A) and minimize the temperature deviation (E).

[0161] In the present invention, the fuzzy control algorithm based on genetic algorithm optimization is obtained by:

[0162] Step S10, randomly generating an initial population P according to a set parameter range; the initial population P includes a plurality of individuals Pi, each of the individuals Pi includes three fuzzy rules and six membership function parameters;

[0163] Step S20, for each individual Pi, according to the current fuzzy rules and membership function parameters, use the fuzzy inference system to perform inference to obtain an output result, wherein the output result is the radiator area and temperature deviation;

[0164] Step S30, calculating the sum of fitness of all individuals according to the output result and the preset weight coefficient, and calculating the selection probability of each individual, and calculating the adaptive mutation probability according to the selection probability;

[0165] Step S40, calculating the fitness value of each individual, performing a selection operation on the individuals in the population to generate a parent set P', selecting two individuals from the parent set P' as the father and the mother, performing a crossover operation, and generating a child set C;

[0166] Step S50, for each individual Pi in the offspring set C, a gene is selected for mutation operation with a set probability according to the adaptive mutation probability; the parent set P' and the offspring set C are merged to obtain a new population P;

[0167] Steps S20-S50 are executed cyclically until the maximum number of iterations is reached or the convergence condition is met, and the loop is terminated;

[0168] Step S60, after the cycle ends, the individual with the best fitness is selected as the optimal solution, the optimal solution is the optimal fuzzy rule and membership function parameters, and the fuzzy control algorithm is optimized based on the optimal solution.

[0169] It should be noted that the specific genetic algorithm parameter settings and operation process need to be adjusted and optimized according to the actual situation. In practical applications, appropriate parameters can be selected through experiments and adjustments to achieve better search results.

[0170] As a further explanation of the present invention, the sum of fitness of all individuals is calculated as follows:

[0171] The preset fitness function is F(Pi)=A(Pi)×w1+E(Pi)×w2;

[0172] Where w1 and w2 are weight coefficients used to balance the importance of heat sink area and temperature deviation; A(Pi) represents the heat sink area of ​​individual Pi, and E(Pi) represents the temperature deviation of individual Pi;

[0173] Fsum=ΣF(Pi);

[0174] Among them, Fsum is the sum of fitness of all individuals.

[0175] As a further explanation of the present invention, the heat sink area and the temperature deviation are calculated as follows:

[0176] A = p × load + q;

[0177] E = f × (target temperature - actual temperature) + d;

[0178] Among them, p and q are two parameters of the membership function of the radiator area; f and d are two parameters of the membership function of the temperature deviation; load is the load input of the motor, the target temperature is the center value of the preset safe temperature range, and the actual temperature is the temperature value calculated according to the current fuzzy rules and membership function parameters; A is the radiator area; E is the temperature deviation.

[0179] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0180] A semi-superconducting electric motor adaptive heat dissipation system and heat dissipation control system according to a second embodiment of the present invention is based on a semi-superconducting electric motor adaptive heat dissipation control method, and the system comprises:

[0181] A temperature acquisition module configured to acquire real-time temperature data of the motor;

[0182] An input module configured to input the real-time temperature data and motor load data as input data into a fuzzy control algorithm optimized based on a genetic algorithm;

[0183] The adjustment module is configured to obtain control parameters by calculating the fuzzy control algorithm based on fuzzy rules, and adjust the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters. The control parameters are calculated by:

[0184] The input data is fuzzified using a membership function, wherein the membership function includes preset membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature;

[0185] Based on the membership function and the preset rule weight, the inference result corresponding to the preset fuzzy rule is calculated, the inference result is defuzzified to obtain the defuzzified result, and converted into the control parameter.

[0186] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0187] It should be noted that the above-mentioned embodiment provides a semi-superconducting electric motor adaptive heat dissipation system and heat dissipation control system, and only uses the division of the above-mentioned functional modules as an example. In practical applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above-mentioned embodiments can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0188] An electronic device according to a third embodiment of the present invention includes:

[0189] at least one processor; and

[0190] a memory communicatively connected to at least one of the processors; wherein,

[0191] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned semi-superconducting electric motor adaptive heat dissipation control method.

[0192] A computer-readable storage medium according to a fourth embodiment of the present invention stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned method for adaptive heat dissipation control of a semi-superconducting electric motor.

[0193] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0194] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0195] Reference below Figure 2 , which shows a schematic diagram of the structure of a computer system of a server for implementing the method, system, and device embodiments of the present application. Figure 2 The server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0196] like Figure 2 As shown, the computer system includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 202 or the program loaded from the storage part 208 to the random access memory (RAM) 203. Various programs and data required for system operation are also stored in the RAM 203. The CPU 201, ROM 202 and RAM 203 are connected to each other through a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0197] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, etc.; an output section 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 210 as needed so that a computer program read therefrom is installed into the storage section 208 as needed.

[0198] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 209, and / or installed from the removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0199] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0200] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0201] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0202] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0203] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for adaptive heat dissipation control of a semi-superconducting electric motor, characterized in that: The method includes: Get the real-time temperature data of the motor; The real-time temperature data and the motor load data are input as input data into a fuzzy control algorithm based on genetic algorithm optimization; The fuzzy control algorithm calculates control parameters based on fuzzy rules, and adjusts the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters; The control parameter is calculated as follows: The input data is fuzzified using a membership function, wherein the membership function includes preset membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature; Based on the membership function and the preset rule weight, the inference result corresponding to the preset fuzzy rule is calculated, the inference result is defuzzified to obtain the defuzzified result, and converted into the control parameter; The preset fuzzy rules are: The first rule: light load and low temperature correspond to a small heat dissipation area of ​​the radiator; the second rule: moderate load and moderate temperature correspond to a moderate heat dissipation area of ​​the radiator; the third rule: heavy load and high temperature correspond to a large heat dissipation area of ​​the radiator; The reasoning result corresponding to the preset fuzzy rule is: The inference result corresponding to the first rule = a×(μ1(x1)×μ4(x2)); The inference result corresponding to the second rule = b×(μ2(x1)×μ5(x2)); The inference result corresponding to the third rule = c × (μ3 (x1) × μ6 (x2)); Among them, a, b, and c are all preset rule weights.

2. A method for adaptive heat dissipation control of a semi-superconducting electric motor according to claim 1, characterized in that: The membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature are: μ1(x1)=trimf(x1,[0,0,0.5]); μ2(x1)=trimf(x1,[0,0.5,1]); μ3(x1)=trimf(x1,[0.5,1,1]); μ4(x2)=trimf(x2,[0,0,50]); μ5(x2)=trimf(x2,[0,50,100]); μ6(x2)=trimf(x2,[50,100,100]); Among them, μ1(x1) is the membership function of light load; μ2(x1) is the membership function of moderate load; μ3(x1) is the membership function of heavy load; μ4(x2) is the membership function of low temperature; μ5(x2) is the membership function of moderate temperature; μ6(x2) is the membership function of high temperature; x1 is the load data; x2 is the real-time temperature data, and trimf is the representation of the membership function.

3. The method for adaptive heat dissipation control of a semi-superconducting electric motor according to claim 1, characterized in that: The inference result is defuzzified to obtain a defuzzified result, and the method is as follows: Defuzzification result = (the reasoning result corresponding to the first rule × a + the reasoning result corresponding to the second rule × b + the reasoning result corresponding to the third rule × c) / (a ​​+ b + c).

4. A semi-superconducting motor adaptive heat dissipation control method according to claim 3, characterized in that: The fuzzy control algorithm based on genetic algorithm optimization is obtained as follows: Step S10, randomly generating an initial population P according to a set parameter range; the initial population P includes a plurality of individuals Pi, each of the individuals Pi includes three fuzzy rules and six membership function parameters; Step S20, for each individual Pi, according to the current fuzzy rules and membership function parameters, use the fuzzy inference system to perform inference to obtain an output result, wherein the output result is the radiator area and temperature deviation; Step S30, calculating the sum of fitness of all individuals according to the output result and the preset weight coefficient, and calculating the selection probability of each individual, and calculating the adaptive mutation probability according to the selection probability; Step S40, calculating the fitness value of each individual, performing a selection operation on the individuals in the population to generate a parent set P', selecting two individuals from the parent set P' as the father and the mother, performing a crossover operation, and generating a child set C; Step S50, for each individual Pi in the offspring set C, a gene is selected for mutation operation with a set probability according to the adaptive mutation probability; the parent set P' and the offspring set C are merged to obtain a new population P; Steps S20-S50 are executed cyclically until the maximum number of iterations is reached or the convergence condition is met, and the loop is terminated; Step S60, after the cycle ends, the individual with the best fitness is selected as the optimal solution, the optimal solution is the optimal fuzzy rule and membership function parameters, and the fuzzy control algorithm is optimized based on the optimal solution.

5. A method for adaptive heat dissipation control of a semi-superconducting electric motor according to claim 4, characterized in that: The sum of fitness of all individuals is calculated as: The preset fitness function is F(Pi)=A(Pi)×w1+E(Pi)×w2; Where w1 and w2 are weight coefficients used to balance the importance of heat sink area and temperature deviation; A(Pi) represents the heat sink area of ​​individual Pi, and E(Pi) represents the temperature deviation of individual Pi; Fsum=ΣF(Pi); Among them, Fsum is the sum of fitness of all individuals.

6. A method for adaptive heat dissipation control of a semi-superconducting electric motor according to claim 5, characterized in that: The heat sink area and the temperature deviation are calculated as follows: A = p × load + q; E = f × (target temperature - actual temperature) + d; Among them, p and q are two parameters of the membership function of the radiator area; f and d are two parameters of the membership function of the temperature deviation; load is the load input of the motor, the target temperature is the center value of the preset safe temperature range, and the actual temperature is the temperature value calculated according to the current fuzzy rules and membership function parameters; A is the radiator area; E is the temperature deviation.

7. A semi-superconducting electric motor adaptive heat dissipation control system, based on a semi-superconducting electric motor adaptive heat dissipation control method according to any one of claims 1 to 6, characterized in that: The system includes: A temperature acquisition module configured to acquire real-time temperature data of the motor; An input module configured to input the real-time temperature data and motor load data as input data into a fuzzy control algorithm optimized based on a genetic algorithm; An adjustment module, configured to calculate control parameters using the fuzzy control algorithm based on fuzzy rules, and adjust the speed of the motor fan and the heat dissipation area of ​​the radiator based on the control parameters; The control parameter is calculated as follows: The input data is fuzzified using a membership function, wherein the membership function includes preset membership functions of light load, moderate load, heavy load, low temperature, moderate temperature, and high temperature; Based on the membership function and the preset rule weight, the inference result corresponding to the preset fuzzy rule is calculated, the inference result is defuzzified to obtain the defuzzified result, and converted into the control parameter; The preset fuzzy rules are: The first rule: light load and low temperature correspond to a small heat dissipation area of ​​the radiator; the second rule: moderate load and moderate temperature correspond to a moderate heat dissipation area of ​​the radiator; the third rule: heavy load and high temperature correspond to a large heat dissipation area of ​​the radiator; The reasoning result corresponding to the preset fuzzy rule is: The inference result corresponding to the first rule = a×(μ1(x1)×μ4(x2)); The inference result corresponding to the second rule = b×(μ2(x1)×μ5(x2)); The inference result corresponding to the third rule = c × (μ3 (x1) × μ6 (x2)); Among them, a, b, and c are all preset rule weights.

Images