Motor fuzzy set speed regulation method and system for rail type gravity energy storage

Abstract

The invention relates to the technical field of intelligent control, in particular to a motor fuzzy set speed regulation method and system for rail type gravity energy storage, and the method comprises the steps: processing a fuzzy rule, and defining a membership function of each fuzzy set, so as to obtain an initial fuzzy rule and a membership function; parameters of the initial fuzzy rule and the membership function are connected in series, an initial population is generated randomly, and each chromosome in the population represents a group of potential fuzzy rules and membership functions; defining an evaluation function, obtaining a fitness value of the chromosome through the evaluation function, randomly selecting an intersection point on the chromosome according to the fitness value of the chromosome, exchanging the chromosomes of the two parent generations at the intersection point, and randomly changing genes in the chromosomes to generate a new generation of population; and obtaining optimized fuzzy rules and membership function parameters according to the new generation of population. Accurate speed regulation of the motor can be realized, and the operation efficiency and stability are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a motor fuzzy set speed regulation method and system for track-type gravity energy storage. Background Art

[0002] The rail-type gravity energy storage system realizes the storage and release of electric energy by utilizing the mutual conversion of gravitational potential energy and electric energy. It is particularly suitable for large-scale and long-term energy storage needs, and can effectively balance the fluctuations of the power system and improve the utilization rate of green energy. However, in the actual operation of the rail-type gravity energy storage system, the precise speed regulation of the motor has become one of the key factors affecting the system performance.

[0003] Although the traditional PID control method is simple and practical, it is often difficult to achieve ideal control effects when faced with complex and changeable operating environments and external disturbances. Especially under complex working conditions such as slope changes and multi-motor coordinated operation, the limitations of PID control are particularly obvious, which can easily lead to problems such as slow system response, large overshoot, and large synchronization errors.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a motor fuzzy set speed regulation method and system for track-type gravity energy storage, which can achieve precise speed regulation of the motor and improve operating efficiency and stability.

[0006] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0007] In a first aspect, a motor fuzzy set speed control method for track-type gravity energy storage comprises:

[0008] Define fuzzy sets and establish a fuzzy rule framework to obtain fuzzy rules;

[0009] Process the fuzzy rules and define the membership function of each fuzzy set to obtain the initial fuzzy rules and membership functions;

[0010] The initial fuzzy rules are connected in series with the parameters of the membership function to randomly generate the initial population, where each chromosome in the population represents a set of potential fuzzy rules and membership functions;

[0011] Define an evaluation function and obtain the fitness value of the chromosome through the evaluation function. According to the fitness value of the chromosome, randomly select a crossover point on the chromosome, exchange the chromosomes of the two parents at the crossover point, and randomly change the genes in the chromosome to generate a new generation of population;

[0012] According to the new generation population, the optimized fuzzy rules and membership function parameters are obtained;

[0013] According to the optimized fuzzy rules and membership function parameters, real-time data is collected, and a fuzzy set of the target speed is obtained according to the real-time data to obtain a fuzzy set of the target speed;

[0014] According to the fuzzy set of the target speed, the motor speed is adjusted to obtain the speed control instruction;

[0015] Multiple motors are coordinated and controlled according to the speed control instructions to achieve motor speed regulation.

[0016] In any of the above schemes, a preferred embodiment connects the initial fuzzy rules and the parameters of the membership function in series to randomly generate an initial population, including:

[0017] Define fuzzy rules, including determining the number N of fuzzy rules and the number M of parameters contained in each rule;

[0018] Determine Gaussian membership functions and parameters of each Gaussian membership function, the parameters including a center value and a width;

[0019] According to the fuzzy rules and Gaussian membership functions, a chromosome is constructed, where each chromosome is a vector of length N×M, and the elements of the chromosome correspond to each parameter of each fuzzy rule in turn;

[0020] Setting initialization ranges for each parameter of the Gaussian membership function;

[0021] The initial population is randomly generated according to the chromosome and initialization range.

[0022] In a preferred embodiment of any of the above schemes, the calculation formula of the evaluation function is defined as:

[0023]

[0024] Where T(x) represents the time required for the motor to reach the target speed from startup; v i Indicates the rotation speed measurement value at each time point; represents the average value of the speed; n represents the number of data points for speed measurement; P represents the average power of the motor; t represents the running time of the motor; w1, w2 and w3 represent weights; ∈ represents a constant; i represents an index; F(x) represents an evaluation function.

[0025] In any of the above schemes, a preferred embodiment randomly selects a crossover point on a chromosome, exchanges the chromosomes of two parents at the crossover point, and randomly changes the genes in the chromosome to generate a new generation population, including:

[0026] Randomly select two chromosomes from the current population as parents and randomly select a position as the crossover point;

[0027] The fragments of the two parent chromosomes at the crossover point are exchanged; in the chromosome after the crossover, one or more gene positions are randomly selected as mutation points; the genes at the selected mutation points are randomly changed until the preset number of iterations is reached to generate a new generation of population.

[0028] In any of the above schemes, a preferred embodiment adjusts the speed of the motor according to the fuzzy set of the target speed to obtain a speed adjustment instruction, including:

[0029] Obtain the fuzzy set of target speed and calculate motor parameters, including rated power, rated speed and torque;

[0030] According to the motor parameters, the difference between the target speed and the actual speed is calculated to obtain the control amount;

[0031] According to the control quantity, the motor speed is adjusted by vector control of zero d-axis current to achieve the actual target speed;

[0032] According to the actual target speed, multiple motors are coordinated and controlled to adjust the speed and torque of each motor to obtain the speed control command.

[0033] In any of the above schemes, a preferred embodiment, according to the control amount, the motor is controlled by vector control of zero d-axis current to adjust the speed of the motor to achieve the actual target speed, including:

[0034] According to the motor parameters, the electromagnetic torque, pole pair number and rotor flux parameters at the target speed are obtained;

[0035] The motor current i in the three-phase stationary coordinate system a 、i b 、i c Transform to the synchronously rotating coordinate system i d 、i q , the d-axis current reference value Set to 0 to control the q-axis current i q ,pass To calculate the q-axis current reference value, where is the q-axis current reference value, is the target electromagnetic torque, n p is the number of motor pole pairs, ψ f is the rotor flux;

[0036] The electromagnetic torque is controlled by adjusting the q-axis current and the motor speed is adjusted to achieve the actual target speed.

[0037] In any of the above schemes, a preferred embodiment performs coordinated control on multiple motors according to the actual target speed, adjusts the speed and torque of each motor to obtain a speed control instruction, including:

[0038] For each motor, obtain its actual target speed from the sensor;

[0039] For adjacent motor pairs, the difference between the actual target speeds of the adjacent motor pairs is calculated to obtain the synchronization error;

[0040] Amplify or reduce the synchronization error to obtain an error compensation value;

[0041] According to the error compensation value, the control signal of each motor is adjusted to generate a corresponding speed control instruction.

[0042] In a second aspect, a motor fuzzy set speed control system for track-type gravity energy storage comprises:

[0043] The acquisition module is used to define fuzzy sets and establish a fuzzy rule framework to obtain fuzzy rules; process the fuzzy rules and define the membership function of each fuzzy set to obtain initial fuzzy rules and membership functions; connect the initial fuzzy rules and the parameters of the membership function in series to randomly generate an initial population, and each chromosome in the population represents a set of potential fuzzy rules and membership functions; define an evaluation function and obtain the fitness value of the chromosome through the evaluation function, and according to the fitness value of the chromosome, randomly select a crossover point on the chromosome, exchange the chromosomes of the two parents at the crossover point, and randomly change the genes in the chromosome to generate a new generation of population;

[0044] The processing module is used to obtain optimized fuzzy rules and membership function parameters according to the new generation population; collect real-time data according to the optimized fuzzy rules and membership function parameters, and obtain the fuzzy set of the target speed according to the real-time data to obtain the fuzzy set of the target speed; adjust the speed of the motor according to the fuzzy set of the target speed to obtain the speed regulation instruction; and coordinately control multiple motors according to the speed regulation instruction to realize motor speed regulation.

[0045] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art:

[0046] Through the fuzzy control algorithm, the dynamic changes of the system can be captured more accurately, and the control strategy can be quickly adjusted according to the real-time data, so as to achieve precise control of the motor speed; through multi-motor coordinated control, the synchronization error between motors can be effectively reduced, and the overall stability and consistency of the multi-motor system can be improved; through real-time monitoring and adjustment of the operating status of the motor, the gravitational potential energy can be maximized for power generation, while reducing unnecessary energy loss, especially when dealing with slope disturbances, the control strategy can be quickly adjusted to maintain optimal power generation efficiency; based on management data, a continuous optimization and adaptive adjustment mechanism is established, which can automatically learn and improve its control strategy to adapt to different operating conditions and external environmental changes; through real-time monitoring and fault warning mechanisms, potential safety hazards can be discovered and dealt with in a timely manner to ensure the safe and stable operation of the system.

[0047] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. Some specific embodiments of the present application will be described in detail in an illustrative and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings:

[0049] Figure 1 It is a schematic diagram of the motor fuzzy set speed regulation method for track-type gravity energy storage of the present invention.

[0050] Figure 2 It is a schematic diagram of the motor fuzzy set speed control system for track-type gravity energy storage according to the present invention.

[0051] It should be noted that these drawings and text descriptions are not intended to limit the conceptual scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. The elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0053] The following embodiment of the present application takes the motor fuzzy set speed control method for track-type gravity energy storage as an example to explain the scheme of the present application in detail, but this embodiment cannot limit the protection scope of the present application.

[0054] like Figure 1 As shown, the present invention provides a motor fuzzy set speed control method for track-type gravity energy storage, comprising:

[0055] Step 11, define fuzzy sets and establish a fuzzy rule framework to obtain fuzzy rules;

[0056] Step 12, processing the fuzzy rules and defining the membership function of each fuzzy set to obtain initial fuzzy rules and membership functions;

[0057] Step 13, the initial fuzzy rules are connected in series with the parameters of the membership function to randomly generate an initial population, where each chromosome in the population represents a set of potential fuzzy rules and membership functions;

[0058] Step 14, define an evaluation function, and obtain the fitness value of the chromosome through the evaluation function. According to the fitness value of the chromosome, randomly select a crossover point on the chromosome, exchange the chromosomes of the two parents at the crossover point, and randomly change the genes in the chromosome to generate a new generation of population;

[0059] Step 15, obtaining optimized fuzzy rules and membership function parameters according to the new generation population;

[0060] Step 16, collecting real-time data according to the optimized fuzzy rules and membership function parameters, and obtaining a fuzzy set of the target speed according to the real-time data to obtain a fuzzy set of the target speed;

[0061] Step 17, regulating the motor speed according to the fuzzy set of the target speed to obtain a speed regulation instruction;

[0062] Step 18, coordinately control multiple motors according to the speed regulation instruction to achieve motor speed regulation.

[0063] In the embodiment of the present invention, through fuzzy logic control, the speed of the motor can be adjusted more accurately to meet the precise requirements of the orbital gravity energy storage system for the motor speed; fuzzy logic control has strong adaptability and can handle uncertainty and complexity problems. Therefore, it can adapt to different working conditions and environmental changes and maintain the stability and accuracy of the motor speed. By considering the collaborative work of multiple motors, the coordination and synchronization between multiple motors are ensured by calculating the synchronization error and compensating for it; by optimizing the fuzzy rules and membership function parameters through genetic algorithms, a parameter combination that is more suitable for practical applications can be obtained, which improves the effect and efficiency of motor speed regulation. Real-time data collection and speed regulation based on the data have faster response speed and better real-time performance, which can meet the real-time requirements of the orbital gravity energy storage system for motor speed regulation.

[0064] In a preferred embodiment of the present invention, step 11 comprises:

[0065] Step 111, setting a fuzzy set definition basis, defining a speed fuzzy set, a slope fuzzy set and a power generation efficiency fuzzy set;

[0066] Step 112, establishing a fuzzy rule framework according to the fuzzy set combination to obtain fuzzy rules.

[0067] In the embodiment of the present invention, by specifically defining the fuzzy sets of speed, slope and power generation efficiency, and establishing a fuzzy rule framework accordingly, the control strategy can be made more in line with the actual system operation requirements, and the accuracy and practicality of the control can be improved; since fuzzy logic control has strong adaptability and can handle uncertainty and complexity problems, by defining multiple fuzzy sets and establishing a corresponding fuzzy rule framework, the system can be better adapted to different working conditions and environmental changes. By adjusting the operating state of the motor according to the changes in slope and speed, the system can maintain a high power generation efficiency under different working conditions, thereby improving the energy efficiency and economy of the overall system.

[0068] In the specific implementation process of the present invention, the speed is divided into several fuzzy sets, such as "slow", "medium speed" and "fast" according to the actual operating speed range of the motor. Taking into account that the rail-type gravity energy storage system may run on tracks with different slopes, the slope is divided into several fuzzy sets, such as "small slope", "medium slope" and "large slope". According to the possible value range of power generation efficiency, it is divided into several fuzzy sets, such as "low efficiency", "medium efficiency" and "high efficiency". Combining the speed fuzzy set, the slope fuzzy set and the power generation efficiency fuzzy set, the following fuzzy rule framework can be established: If the slope is a "small slope" and the speed is "slow", the power generation efficiency may be "low efficiency". If the slope is a "medium slope" and the speed is "medium speed", the power generation efficiency may be "medium efficiency". If the slope is a "large slope" and the speed is "fast", the power generation efficiency may be "high efficiency".

[0069] In a preferred embodiment of the present invention, step 12 comprises:

[0070] Step 121, dividing the fuzzy set into regular intervals, and formulating an output adjustment strategy according to the regular intervals;

[0071] Step 122, according to the fuzzy set, the mean and standard deviation of the Gaussian function are calculated by using the Gaussian membership function to draw a membership function graph of each fuzzy set;

[0072] Step 123, obtaining initial fuzzy rules and membership functions according to the processed fuzzy rules and membership function graphs.

[0073] In the embodiment of the present invention, the processed fuzzy rule interval makes the control strategy more accurate, can better cope with the subtle changes of different input variables, helps to reduce control errors, and improves the accuracy of motor speed regulation. The Gaussian membership function, with its smooth characteristics, can more accurately describe the degree to which the input variable belongs to a fuzzy set, thereby improving the accuracy of control; the processed fuzzy rules enable the system to more flexibly cope with various working conditions and environmental changes; by drawing the membership function graph, the distribution and overlap of each fuzzy set can be intuitively understood, which helps to optimize the design of the fuzzy set and the selection of the membership function; the refined fuzzy rules combined with the membership function make the control strategy more accurate and delicate, which helps to optimize the dynamic response and steady-state performance of the motor.

[0074] In the specific implementation process of the present invention, the input variables and output variables are determined, and fuzzy sets are defined for the input variables according to actual needs and control experience. Each fuzzy set is mapped to a specific numerical interval according to the possible value range of the input variables. For example, for the error variable, NB can be defined as the maximum negative value interval of the error, and PB can be defined as the maximum positive value interval of the error. According to the fuzzy set combination of the input variables, the corresponding output adjustment strategy is formulated. For example, if the error is NB and the error change rate is NB, then the control amount should be PB, and the output adjustment strategy needs to cover all input combinations (for example, if the error and the error change rate are both negative (NB), it means that the system deviates far from the target and the error is increasing, then a larger positive adjustment (PB) is required to correct the system state. In this case, the output control amount should be PB, that is, the system needs to apply a larger positive adjustment force); a Gaussian membership function is selected, and the Gaussian membership function is usually expressed as Among them, c is the mean, σ is the standard deviation, and for each fuzzy set, the membership function graph of each fuzzy set is plotted using MATLAB drawing software. The initial fuzzy rules and membership functions are obtained based on the processed fuzzy rules and membership function graphs.

[0075] In a preferred embodiment of the present invention, step 13 includes:

[0076] Define fuzzy rules, including determining the number N of fuzzy rules and the number M of parameters contained in each rule;

[0077] Determine Gaussian membership functions and parameters of each Gaussian membership function, the parameters including a center value and a width;

[0078] According to the fuzzy rules and Gaussian membership functions, a chromosome is constructed, where each chromosome is a vector of length N×M, and the elements of the chromosome correspond to each parameter of each fuzzy rule in turn;

[0079] Setting initialization ranges for each parameter of the Gaussian membership function;

[0080] The initial population is randomly generated according to the chromosome and initialization range.

[0081] In the embodiment of the present invention, by defining fuzzy rules and using Gaussian membership functions, the dynamic behavior of the system can be described more flexibly; by automatically adjusting and optimizing fuzzy rules, the system can maintain better performance under different working conditions. Fuzzy logic control has strong robustness to the uncertainty and interference of the system. The robustness of the system can be further enhanced by reasonable fuzzy rule definition and parameter optimization. By constructing chromosomes and using optimization techniques such as genetic algorithms, the optimal fuzzy rule parameter combination can be efficiently searched, thereby improving the optimization efficiency.

[0082] In the specific implementation process of the present invention, the Gaussian membership function is a common membership function form, and its shape is determined by two parameters: the center value and the width. For each input of each fuzzy rule, one or more Gaussian membership functions need to be set. The center value of each Gaussian membership function represents the peak position of the membership function, while the width controls the flatness or steepness of the membership function. Determine the number of fuzzy rules N, determine the number of parameters M for each rule, and each chromosome is a vector of length N×M. This vector will contain all the parameters of all fuzzy rules. The elements of the vector are arranged in a specific order, for example, all the parameters of the first rule are listed first, then all the parameters of the second rule, and so on. Set the range for the parameters of the Gaussian membership function: for the center value, set its initialization range according to the possible value range of the input variable; for the width, usually set a positive range to ensure that the membership function has a reasonable shape. Determine the size of the population, that is, the number of chromosomes to be generated. For each chromosome, use a random number generator to generate a random value for each parameter within the previously set initialization range. All randomly generated chromosomes are combined together to form an initial population. This population will serve as the starting point of the genetic algorithm for subsequent iterations and optimization processes.

[0083] In a preferred embodiment of the present invention, in step 14, the calculation formula of the evaluation function is defined as:

[0084]

[0085] Where T(x) represents the time required for the motor to reach the target speed from startup; v i Indicates the rotation speed measurement value at each time point; represents the average value of the speed; n represents the number of data points for speed measurement; P represents the average power of the motor; t represents the running time of the motor; w1, w2 and w3 represent weights; ∈ represents a constant; i represents an index; F(x) represents an evaluation function.

[0086] In the embodiment of the present invention, the evaluation function comprehensively considers the rapidity of the motor response, the volatility of the speed and the energy consumption, and can more comprehensively evaluate the performance of the motor control strategy. By adjusting the weight coefficients and, the proportion of each evaluation index can be flexibly adjusted according to different application requirements and control objectives, so that the evaluation result is more in line with actual needs. The evaluation function quantifies each evaluation index into a specific value, which is convenient for numerical comparison and analysis.

[0087] In a preferred embodiment of the present invention, step 14 comprises:

[0088] Randomly select two chromosomes from the current population as parents and randomly select a position as the crossover point;

[0089] The fragments of the two parent chromosomes at the crossover point are exchanged; in the chromosome after the crossover, one or more gene positions are randomly selected as mutation points; the genes at the selected mutation points are randomly changed until the preset number of iterations is reached to generate a new generation of population.

[0090] In the embodiment of the present invention, through crossover and mutation operations, new solutions can be quickly explored in the search space to improve optimization efficiency. Random selection of parents and mutation points, as well as the randomness of crossover and mutation operations, help maintain the diversity of the population and avoid falling into local optimal solutions. By combining the excellent characteristics of the two parents and introducing new genetic information, the global search ability of the algorithm can be enhanced, and it is more likely to find the global optimal solution.

[0091] In the specific implementation process of the present invention, the population size, that is, the number of chromosomes (individuals), the length of the chromosome, the crossover rate and the mutation rate, and the number of iterations, that is, the total number of rounds of the algorithm are set. The initial population is randomly generated, and each chromosome represents a possible solution. For each generation, a selection algorithm, such as roulette selection, is used; two chromosomes are randomly selected from the current population as parents. A random number is generated, and if the random number is less than the crossover rate, a crossover operation is performed. A position is randomly selected as a crossover point. This position can be any point on the chromosome, but usually does not include the starting point and the end point. The fragments of the two parent chromosomes at the crossover point are exchanged to generate two new daughter chromosomes. For each daughter chromosome, a random number is generated, and if the random number is less than the mutation rate, a mutation operation is performed. One or more gene positions are randomly selected in the chromosome as mutation points. The genes at the selected mutation points are randomly changed. The change can be flipped, such as 0 in binary coding becomes 1, and 1 becomes 0. Replace part or all of the old chromosomes in the population with the newly generated daughter chromosomes. Evaluate the fitness of the new population, that is, the quality of the corresponding solution of each chromosome. If the preset number of iterations is reached, the iteration stops.

[0092] In a preferred embodiment of the present invention, step 15 comprises:

[0093] Each set of fuzzy rules and membership function parameters of each chromosome in the new generation population is evaluated by the evaluation function to obtain the evaluation result;

[0094] According to the evaluation results, the chromosome with the best performance is selected from the new generation population as the current optimal solution, and some or all of the chromosomes in the new generation population are replaced by new chromosomes generated by crossover and mutation operations. The above process of evaluation, selection and population update is repeated until the maximum number of iterations is met to obtain the optimized fuzzy rules and membership function parameters.

[0095] In an embodiment of the present invention, through an iterative optimization process, fuzzy rules and membership function parameters can be automatically searched and optimized. By continuously evaluating, selecting and updating the population, there is a greater chance of finding the global optimal solution. The optimized fuzzy rules and membership function parameters will be used in actual motor control strategies, which can significantly improve the motor's response speed, speed stability, and energy consumption performance.

[0096] In the specific implementation process of the present invention, each chromosome (each set of fuzzy rules and membership function parameters) in the new generation population is evaluated using an evaluation function to obtain an evaluation result. The evaluation function will comprehensively consider factors such as the response speed, speed fluctuation, and energy consumption of the motor to give a quantitative performance indicator. According to the evaluation result, the chromosome with the best performance is selected from the new generation population as the current optimal solution. Some or all of the chromosomes in the new generation population are replaced with new chromosomes generated by crossover and mutation operations. Repeat the above process of evaluating, selecting and updating the population until the maximum number of iterations is met. In each iteration, a new chromosome is generated based on the current population, and the optimization direction is guided by the evaluation function. As the iteration proceeds, the chromosomes in the population will gradually approach the optimal solution. When the iterative optimization process ends, the optimized fuzzy rules and membership function parameters will be obtained.

[0097] In a preferred embodiment of the present invention, step 16 comprises:

[0098] According to the optimized fuzzy rules and membership function parameters, relevant operation data of the motor is collected in real time to obtain real-time data;

[0099] Preprocess the collected real-time data, and perform fuzzification on the preprocessed data to obtain a fuzzy set;

[0100] Carry out fuzzy logic reasoning on the fuzzy set to obtain the fuzzy set of the target speed;

[0101] In the embodiment of the present invention, by collecting the operation data of the motor in real time, the control strategy of the motor can be adjusted dynamically. By preprocessing and fuzzifying the real-time data, the influence of data noise and uncertainty on the control strategy can be reduced. Fuzzy logic control can handle nonlinear, time-varying and uncertain systems, making the motor control strategy more flexible and robust. By optimizing the fuzzy rules and membership function parameters, the motor can achieve better performance under different operating conditions.

[0102] In the specific implementation process of the present invention, the relevant operating data of the motor, such as the current speed, load condition, and power supply voltage, are collected in real time according to the optimized fuzzy rules and membership function parameters. The collected real-time data is preprocessed, such as filtering, denoising, and normalization, to ensure the accuracy and availability of the data. The preprocessed data is input into the fuzzy logic controller, and the data is converted into corresponding fuzzy sets according to the optimized membership function parameters; for example, for the speed data, it can be converted into "slow", "medium speed" and "fast" fuzzy sets according to the optimized membership function. According to the optimized fuzzy rules, fuzzy logic reasoning is performed in combination with the fuzzy sets of input variables. The fuzzy rules will give the corresponding output variable fuzzy sets according to different combinations of input variables. According to the results of fuzzy logic reasoning, the fuzzy set of the target speed can be obtained.

[0103] In a preferred embodiment of the present invention, step 17 includes:

[0104] Obtain the fuzzy set of target speed and calculate motor parameters, including rated power, rated speed and torque;

[0105] According to the motor parameters, the difference between the target speed and the actual speed is calculated to obtain the control amount;

[0106] According to the control quantity, the motor speed is adjusted by vector control of zero d-axis current to achieve the actual target speed;

[0107] According to the actual target speed, multiple motors are coordinated and controlled to adjust the speed and torque of each motor to obtain the speed control command.

[0108] In the embodiment of the present invention, the fuzzy set of the target speed is obtained to provide a precise control target for the subsequent motor control. By calculating the rated power, rated speed and torque parameters of the motor, it can be ensured that the motor runs at the optimal working point; according to the motor parameters, the difference between the target speed and the actual speed is calculated to obtain the control quantity, and the motor is adjusted by the vector control method of zero d-axis current, which can achieve precise control of the motor speed. Through precise speed control, it can be ensured that the motor always runs in the high-efficiency area, reducing unnecessary energy loss and improving the overall energy efficiency of the system; by integrating the multi-motor collaborative control strategy, synchronous control between the motors is achieved, which helps to reduce the speed and torque differences between the motors. The multi-motor collaborative control strategy can dynamically adjust the speed and torque of each motor according to the actual load conditions, achieve balanced distribution of load between the motors, and extend the service life of the motor.

[0109] In the specific implementation process of the present invention, the maximum vehicle speed v is obtained according to the fuzzy set of the target speed. max , according to the maximum speed, through and To obtain the maximum power of the generator, where η T is the transmission efficiency, m is the mass of the vehicle and the weight, g is the acceleration due to gravity, a1 is the acceleration, α is the track slope, v max is the maximum vehicle speed, μ I is the friction coefficient between the vehicle and the track, F f2 is the rolling friction between the power station side wheel and the vehicle fender, μ2 is the friction coefficient between the power station side wheel and the vehicle fender, k s is the safety factor. Taking the slope downward as the positive direction, P1 is the maximum power provided to the generator when driving at a constant speed, and P2 is the maximum power provided to the generator when driving at an accelerated speed; according to the maximum speed of the vehicle, To get the peak speed of the motor, where n max is the peak speed of the motor, v max is the maximum vehicle speed, i is the transmission ratio of the reducer, and r is the radius of the driving wheel; according to the power and speed obtained, through T max =9550P max / n N and T N =9550P N / n N , to obtain the peak torque and rated torque of the motor, T max is the peak torque of the motor, T N is the rated torque, P max is the peak power of the motor, P N is the rated power, n N is the rated speed of the motor. According to the design specifications of the motor, the basic parameters of the motor's rated power, rated speed and rated torque are obtained. The PID control algorithm will obtain the control quantity based on the difference between the target speed and the actual speed. According to the control quantity, the motor is regulated by vector control of zero d-axis current to control the motor's electromagnetic torque and speed. The actual speed of the motor is monitored in real time and compared with the target speed. The error is reduced by adjusting the control parameters until the actual target speed is reached. For a multi-motor system, the synchronization error between the motors needs to be calculated. According to the size and direction of the synchronization error, the error is compensated by adjusting the control input of each motor. In the multi-motor collaborative control strategy, the speed and torque of each motor are gradually consistent by continuously calculating and adjusting the synchronization error to achieve synchronous control.

[0110] In a preferred embodiment of the present invention, the above step 17, according to the control amount, adjusts the speed of the motor by vector control of zero d-axis current to achieve the actual target speed, including:

[0111] According to the motor parameters, the electromagnetic torque, pole pair number and rotor flux parameters at the target speed are obtained;

[0112] The motor current i in the three-phase stationary coordinate system a 、i b 、i c Transform to the synchronously rotating coordinate system i d 、i q , set the d-axis current reference value id * Set to 0 to control only the q-axis current i q ,pass To calculate the q-axis current reference value, where is the q-axis current reference value, is the target electromagnetic torque, n p is the number of motor pole pairs, ψ f is the rotor flux,

[0113] The electromagnetic torque is controlled by adjusting the q-axis current and the motor speed is adjusted to achieve the actual target speed.

[0114] In an embodiment of the present invention, in a synchronous rotating coordinate system, precise control of the electromagnetic torque can be achieved by directly controlling the q-axis current. This method can respond to load changes more accurately than traditional open-loop control or simple closed-loop control, thereby improving the dynamic performance and steady-state accuracy of the system. Through vector control, the speed regulation process of the motor is smoother, speed fluctuations and shocks are reduced, and the operating stability and reliability of the system are improved. Precise torque control helps to reduce the mechanical stress of the motor, thereby reducing noise and vibration.

[0115] In the specific implementation process of the present invention, the electromagnetic torque, pole pair number and rotor flux parameters at the target speed are obtained. The current of the motor in the three-phase stationary coordinate system is transformed into the two-phase stationary coordinate system using Clarke transformation, and then transformed into the synchronous rotating coordinate system using Park transformation. d 、i q , in the synchronous rotating coordinate system, the d-axis current reference value id * . Calculate the q-axis reference current based on the target electromagnetic torque, motor pole pair number and rotor flux Use a PID controller to adjust the motor's q-axis current so that it tracks the reference value By adjusting the q-axis current, the electromagnetic torque of the motor can be controlled. The actual speed of the motor is monitored in real time and compared with the target speed. If the actual speed is lower than the target speed, the reference value of the q-axis current is increased to increase the electromagnetic torque and increase the speed; if the actual speed is higher than the target speed, the reference value of the q-axis current is reduced to reduce the electromagnetic torque and reduce the speed. The above process forms a closed-loop control system, and by continuously adjusting the q-axis current, the actual speed of the motor gradually approaches and stabilizes at the target speed.

[0116] In a preferred embodiment of the present invention, step 18 comprises:

[0117] For each motor, obtain its actual target speed from the sensor;

[0118] For adjacent motor pairs, the difference between the actual target speeds of the adjacent motor pairs is calculated to obtain the synchronization error;

[0119] Amplify or reduce the synchronization error to obtain an error compensation value;

[0120] ,According to the error compensation value, the control signal of each motor is adjusted to generate the corresponding speed control command.

[0121] In an embodiment of the present invention, by calculating the synchronization error between adjacent motors and compensating for it, the synchronization performance of the multi-motor system can be significantly improved. By amplifying or reducing the synchronization error, the error can be effectively prevented from propagating and accumulating in the multi-motor system. By accurately adjusting the control signal of each motor, the motor speed and torque can be accurately controlled. Through the coordinated control strategy, the stability and robustness of the multi-motor system can be enhanced, so that it can maintain excellent performance under various operating conditions.

[0122] In the specific implementation process of the present invention, the actual speed data of the motor is read from each sensor in real time through the sensor interface. Adjacent motor pairs are selected from the multi-motor system as comparison objects. For each pair of adjacent motors, the difference between their actual target speeds is calculated by simple subtraction. According to the control requirements, a factor for error amplification or reduction is set. The synchronization error is multiplied by the amplification / reduction factor to obtain the error compensation value. The calculated error compensation value is subjected to necessary restriction processing, and the control signal of each motor is adjusted according to the calculated error compensation value. This can be achieved by adding or subtracting the error compensation value from the original control signal. The adjusted control signal is converted into a specific speed control instruction.

[0123] like Figure 2 As shown, a motor fuzzy set speed control system 20 for track-type gravity energy storage includes the following steps:

[0124] The acquisition module 21 is used to define fuzzy sets and establish a fuzzy rule framework to obtain fuzzy rules; process the fuzzy rules and define the membership function of each fuzzy set to obtain initial fuzzy rules and membership functions; connect the initial fuzzy rules and the parameters of the membership function in series to randomly generate an initial population, where each chromosome in the population represents a set of potential fuzzy rules and membership functions; define an evaluation function and obtain the fitness value of the chromosome through the evaluation function, and according to the fitness value of the chromosome, randomly select a crossover point on the chromosome, exchange the chromosomes of two parent generations at the crossover point, and randomly change the genes in the chromosome to generate a new generation of population;

[0125] The processing module 22 is used to obtain optimized fuzzy rules and membership function parameters based on the new generation population; collect real-time data based on the optimized fuzzy rules and membership function parameters, and obtain the fuzzy set of the target speed based on the real-time data to obtain the fuzzy set of the target speed; adjust the speed of the motor based on the fuzzy set of the target speed to obtain a speed regulation instruction; and coordinately control multiple motors based on the speed regulation instruction to achieve motor speed regulation.

[0126] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0127] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A motor fuzzy set speed control method for track-type gravity energy storage, characterized in that: include: Define fuzzy sets and establish a fuzzy rule framework to obtain fuzzy rules; Process the fuzzy rules and define the membership function of each fuzzy set to obtain the initial fuzzy rules and membership functions; The initial fuzzy rules are connected in series with the parameters of the membership function to randomly generate the initial population, where each chromosome in the population represents a set of potential fuzzy rules and membership functions; Define an evaluation function and obtain the fitness value of the chromosome through the evaluation function. According to the fitness value of the chromosome, randomly select a crossover point on the chromosome, exchange the chromosomes of the two parents at the crossover point, and randomly change the genes in the chromosome to generate a new generation of population; According to the new generation population, the optimized fuzzy rules and membership function parameters are obtained; According to the optimized fuzzy rules and membership function parameters, real-time data is collected, and a fuzzy set of the target speed is obtained according to the real-time data to obtain a fuzzy set of the target speed; According to the fuzzy set of the target speed, the motor speed is adjusted to obtain the speed control instruction; Multiple motors are coordinated and controlled according to the speed control instructions to achieve motor speed regulation.

2. The motor fuzzy set speed control method for track-type gravity energy storage according to claim 1 is characterized in that: The initial fuzzy rules are connected in series with the parameters of the membership function to randomly generate the initial population, including: Define fuzzy rules, including determining the number N of fuzzy rules and the number M of parameters contained in each rule; Determine Gaussian membership functions and parameters of each Gaussian membership function, the parameters including a center value and a width; According to the fuzzy rules and Gaussian membership functions, a chromosome is constructed, where each chromosome is a vector of length N×M, and the elements of the chromosome correspond to each parameter of each fuzzy rule in turn; Setting initialization ranges for each parameter of the Gaussian membership function; The initial population is randomly generated according to the chromosome and initialization range.

3. The motor fuzzy set speed control method for track-type gravity energy storage according to claim 2 is characterized in that: The calculation formula for defining the evaluation function is: Where T(x) represents the time required for the motor to reach the target speed from startup; v i Indicates the rotation speed measurement value at each time point; represents the average value of the speed; n represents the number of data points for speed measurement; P represents the average power of the motor; t represents the running time of the motor; w1, w2 and w3 represent weights; ∈ represents a constant; i represents an index; F(x) represents an evaluation function.

4. The motor fuzzy set speed control method for track-type gravity energy storage according to claim 3 is characterized in that: A crossover point on the chromosome is randomly selected, the chromosomes of the two parents are exchanged at the crossover point, and the genes in the chromosome are randomly changed to produce a new generation of population, including: Randomly select two chromosomes from the current population as parents and randomly select a position as the crossover point; The fragments of the two parent chromosomes at the crossover point are exchanged; in the chromosome after the crossover, one or more gene positions are randomly selected as mutation points; the genes at the selected mutation points are randomly changed until the preset number of iterations is reached to generate a new generation of population.

5. The motor fuzzy set speed control method for track-type gravity energy storage according to claim 4 is characterized in that: According to the fuzzy set of the target speed, the motor speed is adjusted to obtain the speed control instruction, including: Obtain the fuzzy set of target speed and calculate motor parameters, including rated power, rated speed and torque; According to the motor parameters, the difference between the target speed and the actual speed is calculated to obtain the control amount; According to the control quantity, the motor speed is adjusted by vector control of zero d-axis current to achieve the actual target speed; According to the actual target speed, multiple motors are coordinated and controlled to adjust the speed and torque of each motor to obtain the speed control command.

6. The motor fuzzy set speed control method for track-type gravity energy storage according to claim 5 is characterized in that: According to the control quantity, the motor is regulated by vector control of zero d-axis current to achieve the actual target speed, including: According to the motor parameters, the electromagnetic torque, pole pair number and rotor flux parameters at the target speed are obtained; The motor current i in the three-phase stationary coordinate system a 、i b 、i c Transform to the synchronously rotating coordinate system i d 、i q , the d-axis current reference value Set to 0 to control the q-axis current i q ,pass To calculate the q-axis current reference value, where is the q-axis current reference value, is the target electromagnetic torque, n p is the number of motor pole pairs, ψ f is the rotor flux; The electromagnetic torque is controlled by adjusting the q-axis current and the motor speed is adjusted to achieve the actual target speed.

7. The motor fuzzy set speed control method for track-type gravity energy storage according to claim 6 is characterized in that: According to the actual target speed, multiple motors are coordinated and controlled to adjust the speed and torque of each motor to obtain the speed control command, including: For each motor, obtain its actual target speed from the sensor; For adjacent motor pairs, the difference between the actual target speeds of the adjacent motor pairs is calculated to obtain the synchronization error; Amplify or reduce the synchronization error to obtain an error compensation value; According to the error compensation value, the control signal of each motor is adjusted to generate a corresponding speed control instruction.

8. A motor fuzzy set speed control system for track-type gravity energy storage, characterized in that: Applied to the method according to any one of claims 1 to 7, comprising: The acquisition module is used to define fuzzy sets and establish a fuzzy rule framework to obtain fuzzy rules; process the fuzzy rules and define the membership function of each fuzzy set to obtain initial fuzzy rules and membership functions; connect the initial fuzzy rules and the parameters of the membership function in series to randomly generate an initial population, and each chromosome in the population represents a set of potential fuzzy rules and membership functions; define an evaluation function and obtain the fitness value of the chromosome through the evaluation function, and according to the fitness value of the chromosome, randomly select a crossover point on the chromosome, exchange the chromosomes of the two parents at the crossover point, and randomly change the genes in the chromosome to generate a new generation of population; The processing module is used to obtain optimized fuzzy rules and membership function parameters according to the new generation population; collect real-time data according to the optimized fuzzy rules and membership function parameters, and obtain the fuzzy set of the target speed according to the real-time data to obtain the fuzzy set of the target speed; adjust the speed of the motor according to the fuzzy set of the target speed to obtain the speed regulation instruction; and coordinately control multiple motors according to the speed regulation instruction to realize motor speed regulation.

9. A computing device, characterized in that include: one or more processors; A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images