Design method of leaded hybrid supercapacitors in extremely low temperature environments
By collecting vehicle and environmental parameters in hybrid electric vehicles and using automotive internet and high-frequency feature clustering optimization algorithms to design supercapacitors, the problem of existing design methods being unable to be combined with application scenarios is solved, enabling precise design in extremely low temperature environments and improving the accuracy and efficiency of the design.
Patent Information
- Application Number
- CN202411112304.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-14
AI Technical Summary
The existing design methods for leaded hybrid supercapacitors in hybrid electric vehicles cannot accurately analyze the requirements of the application scenario, resulting in design results that cannot accurately adapt to the performance requirements in extremely low temperature environments. This leads to a high degree of blindness and randomness in the design, resulting in poor design accuracy and efficiency.
By collecting vehicle attribute characteristics, low-temperature environment parameters, and capacitor performance requirements, information retrieval is performed using the automotive internet, high-frequency feature clustering and mutation evolution optimization algorithms are used, capacitor design parameters are optimized within a visual simulation platform, an optimized design parameter set is output, and performance testing and evaluation are conducted under predetermined vehicle operating conditions. Finally, the optimal design parameters are determined for mass production.
It improves the accuracy and intelligence of supercapacitor demand analysis, reduces the blindness and randomness of design, enables rapid and accurate design based on application scenarios, and ensures the safe operation of hybrid vehicles in extremely low temperature environments.
Smart Images

Figure CN118627322B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of capacitor design optimization, and in particular to a design method for a lead-type hybrid supercapacitor in an extremely low temperature environment. Background Art
[0002] In hybrid vehicles, the design of leaded hybrid supercapacitors is crucial to improving the vehicle's energy recovery efficiency and starting assistance performance. Supercapacitors can provide fast charging and discharging capabilities, which enables them to effectively recover braking energy in hybrid vehicles and provide instantaneous high power at startup. Existing design methods often lack in-depth analysis of application scenarios and fail to accurately identify the specific requirements of the vehicle for supercapacitor performance under different operating conditions, such as operation in extremely low temperature environments. Due to the lack of precise understanding of application scenarios, the designed supercapacitors cannot meet the performance requirements in actual operation, resulting in a mismatch between the design results and the actual application scenario requirements.
[0003] At present, the existing lead-type hybrid supercapacitor design method for hybrid vehicles has technical problems such as the inability to conduct accurate demand analysis in combination with application scenarios, resulting in a large degree of blindness and randomness in capacitor design, and the design results cannot accurately adapt to the application scenario requirements, resulting in poor accuracy and efficiency of supercapacitor design. Summary of the invention
[0004] The purpose of this application is to provide a design method for a lead-type hybrid supercapacitor in an extremely low temperature environment, so as to solve the technical problems in the existing design method of lead-type hybrid supercapacitors for hybrid vehicles, such as the inability to conduct accurate demand analysis in combination with application scenarios, resulting in large blindness and randomness in capacitor design, and the inability of design results to accurately adapt to application scenario requirements, resulting in poor accuracy and efficiency of supercapacitor design.
[0005] In view of the above problems, the present application provides a design method for a lead-type hybrid supercapacitor in an extremely low temperature environment, including: collecting vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements of a target vehicle; using the vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements as a comparison benchmark, and using the lead-type hybrid supercapacitor as a guiding condition, performing information retrieval based on the automotive Internet to obtain a sample capacitor design parameter set; performing high-frequency feature clustering on the sample capacitor design parameter set, and constructing a design parameter optimization space based on the clustering results; based on the design parameter optimization space, using a mutation evolution optimization algorithm and a capacitor performance predictor, optimizing capacitor design parameters in a visual simulation platform, and outputting an optimized design parameter set; performing sample production according to the optimized design parameter set to obtain multiple sample supercapacitors, performing performance test evaluation on the multiple sample supercapacitors under predetermined vehicle operating conditions, and determining the optimal design parameters for mass production based on the performance evaluation results.
[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0007] By taking vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements as comparison benchmarks, and taking lead-type hybrid supercapacitors as guiding conditions, information retrieval is performed based on the automotive Internet to obtain a sample capacitor design parameter set; then, high-frequency feature clustering is performed on the sample capacitor design parameter set, and a design parameter optimization space is constructed based on the clustering results; then, based on the design parameter optimization space, the capacitor design parameters are optimized in a visual simulation platform using a mutation evolution optimization algorithm and a capacitor performance predictor, and an optimized design parameter set is output; further, samples are produced according to the optimized design parameter set to obtain multiple sample supercapacitors, and performance tests and evaluations are performed on multiple sample supercapacitors under predetermined vehicle operating conditions, and finally, the optimal design parameters are determined according to the performance evaluation results for mass production; the accuracy and intelligence of supercapacitor demand analysis can be improved, the blindness and randomness of capacitor design can be reduced, and design time and design resources can be saved, thereby achieving the technical goal of quickly and accurately designing supercapacitors according to application scenarios, and achieving the technical effect of ensuring the safe driving of hybrid vehicles in extremely low temperature environments.
[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0010] Figure 1 A schematic diagram of a design method of a lead-type hybrid supercapacitor in an extremely low temperature environment for this application;
[0011] Figure 2 A schematic diagram of a flow chart for obtaining a sample capacitor design parameter set in a design method for a lead-type hybrid supercapacitor in an extremely low temperature environment in this application. DETAILED DESCRIPTION
[0012] This application provides a design method for lead-type hybrid supercapacitors in an extremely low temperature environment, which solves the technical problem that the lead-type hybrid supercapacitor design method for existing hybrid electric vehicles cannot be combined with application scenarios for accurate demand analysis, resulting in large blindness and randomness in capacitor design, and the design results cannot accurately adapt to the application scenario requirements, resulting in poor accuracy and efficiency of supercapacitor design. It can improve the accuracy and intelligence of supercapacitor demand analysis, reduce the blindness and randomness of capacitor design, save design time and design resources, thereby achieving the technical goal of quickly and accurately designing supercapacitors according to application scenarios, and achieving the technical effect of ensuring the safe driving of hybrid electric vehicles in extremely low temperature environments.
[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0014] For examples, please see the attached Figure 1 The present application provides a design method for a lead-type hybrid supercapacitor in an extremely low temperature environment, which specifically includes the following steps:
[0015] Step 1: Collect vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements of the target vehicle.
[0016] Specifically, first, the target vehicle is obtained, and the target vehicle is a hybrid vehicle equipped with a lead-type hybrid supercapacitor, in which the supercapacitor is mainly used for vehicle start-up assistance, instantaneous acceleration and kinetic energy recovery. The target vehicle type can be set according to actual conditions. Then, the vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements of the target vehicle are collected, wherein the vehicle attribute characteristics at least include the vehicle type, power system and braking system; the low-temperature environmental parameters at least include the ambient temperature threshold and the ambient humidity threshold
[0017] The ambient temperature threshold can be set according to the actual scenario. For example, in an extremely low temperature environment, the ambient temperature threshold is usually between minus 30 degrees Celsius and minus 60 degrees Celsius. The capacitor performance requirements include at least the expected power-to-energy ratio, expected charge-discharge efficiency, expected cycle life, and expected engineering constraints. Technical personnel in this field can also add or delete the above feature information according to actual conditions. By obtaining the vehicle attribute characteristics, low-temperature environmental parameters, and capacitor performance requirements of the target vehicle, support is provided for the next step of related information retrieval, and the accuracy and efficiency of information retrieval can be improved.
[0018] Step 2: Using the vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements as comparison benchmarks, and using lead-type hybrid supercapacitors as guiding conditions, information retrieval is performed based on the automotive Internet to obtain a sample capacitor design parameter set.
[0019] Specifically, first, with the lead-type hybrid supercapacitor as the guiding condition, information retrieval is performed based on the automotive Internet, which refers to an information retrieval platform that stores a large amount of automotive-related information, to obtain a retrieval data set, wherein the retrieval data includes capacitor design parameters and corresponding scenario information. Then, with the vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements as the comparison benchmark, the retrieval data set is associated and screened, that is, the data in the retrieval data whose similarity with the comparison benchmark is greater than a predetermined similarity threshold is selected and set as the sample capacitor design parameters to obtain the capacitor design parameter set. By setting matching retrieval conditions according to the actual application scenarios of the target vehicle, the accuracy and adaptability of the sample capacitor design parameter set can be improved, thereby providing support for the subsequent optimization of capacitor design parameters.
[0020] Step 3: Cluster the high-frequency features of the sample capacitor design parameter set, and construct a design parameter optimization space based on the clustering results.
[0021] Specifically, high-frequency feature clustering is performed on the sample capacitor design parameter set, wherein the sample capacitor design parameters include at least electrode material type, electrode area, electrode thickness, electrolyte material type, electrolyte concentration, diaphragm thickness, diaphragm porosity, and lead layout, that is, the capacitor design parameters with higher frequency in the sample capacitor design parameters are selected and set as high-frequency design parameters, and feature clustering results are generated based on multiple high-frequency design parameters, and the feature clustering results are further set as the design parameter optimization space. By constructing the design parameter optimization space, a basis is provided for the subsequent capacitor design parameter optimization. Since the design parameter optimization space is constructed based on the feature clustering results, it can improve the pertinence and accuracy of the design parameter selection, reduce the blind selection time, and improve the optimization efficiency.
[0022] Step 4: Based on the design parameter optimization space, the capacitor design parameters are optimized in a visual simulation platform using a mutation evolution optimization algorithm and a capacitor performance predictor, and an optimized design parameter set is output.
[0023] Specifically, first, a plurality of initial design parameters are randomly generated based on the design parameter optimization space, wherein the initial design parameters meet the expected uniformity constraint and the expected quantity, for example, the number of randomly generated parameters is defined to ensure that the generated initial design parameters meet the expected quantity, and the uniformity constraint of the randomly generated parameters is set to ensure that the generated parameters are more random. Then, on the visual simulation platform, a working condition simulation operation is performed based on the plurality of initial design parameters to determine a plurality of capacitor simulation parameter sets.
[0024] A capacitor performance predictor is constructed based on a BP neural network, wherein the capacitor performance predictor is a neural network model that can be iteratively optimized in machine learning, and is used to predict capacitor performance, and is constructed by supervised training through a training data set. Then, multiple capacitor simulation parameter sets are input into the capacitor performance predictor for performance prediction, and multiple performance evaluation coefficients are output, which are set as multiple performance fitnesses. Then, based on the multiple performance fitnesses, a variation evolution optimization algorithm is used to optimize the capacitor design parameters, and an optimized design parameter set is obtained based on the optimization result, wherein the optimized design parameter set includes multiple better optimized design parameters. The variation evolution optimization algorithm is an optimization method constructed based on a searcher optimization algorithm, which is used to search for the optimal solution in the design parameter optimization space, and can improve the global search capability of parameter optimization, thereby improving the accuracy and practicality of the optimization result.
[0025] Step 5: Produce samples according to the optimized design parameter set to obtain multiple sample supercapacitors, perform performance testing and evaluation on the multiple sample supercapacitors under predetermined vehicle operating conditions, and determine optimal design parameters for batch production based on the performance evaluation results.
[0026] Specifically, first, according to the predetermined production plan, samples are produced according to the optimized design parameter set to ensure that the design parameters are strictly followed during the sample production process, including material selection, structural design, manufacturing process, etc., to obtain multiple sample supercapacitors. Obtain the predetermined vehicle operating conditions, which at least include starting conditions, acceleration conditions, climbing conditions, deceleration conditions and braking conditions; then, the performance of the multiple sample supercapacitors is tested and evaluated under the predetermined vehicle operating conditions, and the test should include key performance indicators such as capacitance, power density, operating voltage, operating temperature range, self-discharge rate, etc., and then multiple comprehensive performance evaluation results of multiple optimized design parameters are obtained based on the performance test results; finally, the optimized design parameters corresponding to the highest comprehensive performance evaluation results are selected as the optimal design parameters, and the optimal design parameters are used to mass produce supercapacitors to ensure that the performance of the produced supercapacitors meets the requirements of the optimal design parameters.
[0027] By providing a design method for a lead-type hybrid supercapacitor in an extremely low temperature environment, it is possible to solve the technical problems in the existing design method of lead-type hybrid supercapacitors for hybrid vehicles, such as the inability to conduct accurate demand analysis in combination with application scenarios, resulting in greater blindness and randomness in capacitor design, and the inability of design results to accurately adapt to application scenario requirements, resulting in poor accuracy and efficiency in supercapacitor design. By taking vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements as comparison benchmarks, and taking lead-type hybrid supercapacitors as guiding conditions, information retrieval is performed based on the automotive Internet to obtain a sample capacitor design parameter set; then, high-frequency feature clustering is performed on the sample capacitor design parameter set, and a design parameter optimization space is constructed based on the clustering results; then, based on the design parameter optimization space, the capacitor design parameters are optimized in a visual simulation platform using a mutation evolution optimization algorithm and a capacitor performance predictor, and an optimized design parameter set is output; further, samples are produced according to the optimized design parameter set to obtain multiple sample supercapacitors, and performance tests and evaluations are performed on multiple sample supercapacitors under predetermined vehicle operating conditions, and finally, the optimal design parameters are determined according to the performance evaluation results for mass production; the accuracy and intelligence of supercapacitor demand analysis can be improved, the blindness and randomness of capacitor design can be reduced, and design time and design resources can be saved, thereby achieving the technical goal of quickly and accurately designing supercapacitors according to application scenarios, and achieving the technical effect of ensuring the safe driving of hybrid vehicles in extremely low temperature environments.
[0028] Further, the vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements of the target vehicle are collected. Step 1 of this application includes:
[0029] The vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements of the target vehicle are collected, wherein the vehicle attribute characteristics include at least the vehicle type, power system and braking system, the low-temperature environmental parameters include at least the ambient temperature threshold and the ambient humidity threshold, and the capacitor performance requirements include at least the expected power-to-energy ratio, the expected charge-discharge efficiency, the expected cycle life and the expected engineering constraints.
[0030] Specifically, first, the vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements of the target vehicle are collected, where the vehicle attribute characteristics include at least the vehicle type, power system and braking system, and the low-temperature environmental parameters include at least the ambient temperature threshold and the ambient humidity threshold. For example, in an extremely low temperature environment, the ambient temperature threshold is usually between minus 30 degrees Celsius and minus 60 degrees Celsius; the capacitor performance requirements include at least the expected power-to-energy ratio, the expected charge-discharge efficiency, the expected cycle life and the expected engineering constraints, where the power-to-energy ratio refers to the ratio of power to energy provided by the unit mass of the electric energy carrier. A high power-to-energy ratio means that the capacitor can store more energy while providing high power output; the charge-discharge efficiency refers to the efficiency of energy conversion during the charge-discharge process of the capacitor. A high charge-discharge efficiency means that the capacitor has less energy loss during the charge-discharge process and has a higher energy utilization efficiency; the cycle life refers to the number of charge-discharge cycles that the capacitor can withstand. The longer the expected cycle life, the better the durability of the capacitor and the lower the cost of use; the engineering constraints include the size, weight, cost, environmental adaptability, etc. of the capacitor. These constraints ensure that the design and manufacture of the capacitor can meet the restrictions in actual applications. These performance requirements play an important role in the design and selection of capacitors, determining their performance and suitability for use in a specific application.
[0031] Further, obtain the sample capacitor design parameter set, as shown in the attached Figure 2 As shown, step 2 of this application includes:
[0032] Taking the lead-type hybrid supercapacitor as a guiding condition, information retrieval is performed based on the automotive Internet to obtain a retrieval data set, and a first retrieval data is randomly selected from the retrieval data set, wherein the first retrieval data includes a first vehicle attribute feature, a first low-temperature environment parameter, a first capacitor performance requirement and a first capacitor design parameter; taking the vehicle attribute feature as a benchmark, a similarity analysis is performed on the first vehicle attribute feature to determine a first similarity; if the first similarity is greater than a predetermined similarity threshold, a similarity analysis is performed on the first low-temperature environment parameter based on the low-temperature environment parameter to determine a second similarity; if the second similarity is greater than the predetermined similarity threshold, a similarity analysis is performed on the first capacitor performance requirement based on the capacitor performance requirement to determine a third similarity; if the third similarity is greater than the predetermined similarity threshold, the first retrieval data is added to the sample capacitor design parameter set.
[0033] Specifically, first, with the lead-type hybrid supercapacitor as the guiding condition, information retrieval is performed based on the automotive Internet to obtain a retrieval data set; then, any retrieval data in the retrieval data set is randomly selected and set as the first retrieval data, wherein the first retrieval data includes a first vehicle attribute feature, a first low-temperature environment parameter, a first capacitor performance requirement and a first capacitor design parameter.
[0034] Then, based on the vehicle attribute characteristics, the first vehicle attribute characteristics are analyzed for similarity, for example, a suitable similarity calculation method is selected for comparison, such as Euclidean distance, cosine similarity, Jaccard coefficient, etc. Then, according to the selected method, the similarity between the target vehicle attribute characteristics and other vehicle attribute characteristics is calculated; for example, multiple similarity comparison algorithms can be selected at the same time, and the comprehensive similarity is obtained by weighted calculation according to the accuracy of the comparison algorithm to determine the first similarity. The first similarity is further judged according to a predetermined similarity threshold, wherein the predetermined similarity threshold can be set by a technician in this field according to actual conditions; if the first similarity is greater than the predetermined similarity threshold, then the first low temperature environment parameter is analyzed for similarity based on the low temperature environment parameter to determine the second similarity; if the second similarity is greater than the predetermined similarity threshold, then the first capacitor performance requirement is analyzed for similarity based on the capacitor performance requirement to determine the third similarity; if the third similarity is greater than the predetermined similarity threshold, the first search data is added to the sample capacitor design parameter set. If the first similarity is less than or equal to a predetermined similarity threshold or the second similarity is less than or equal to a predetermined similarity threshold or the third similarity is less than or equal to the predetermined similarity threshold, the first search data is discarded.
[0035] Further, the design parameter optimization space is constructed. Step three of this application includes:
[0036] A sample capacitor design parameter set is obtained, wherein the sample capacitor design parameters include at least electrode material type, electrode area, electrode thickness, electrolyte material type, electrolyte concentration, diaphragm thickness, diaphragm porosity and lead layout; a first design parameter set is randomly selected from the sample capacitor design parameter set, the number of identical parameters in the first design parameter set is counted and set as a first parameter frequency, a first design parameter corresponding to a first parameter frequency that meets a predetermined frequency threshold is selected and set as a first high-frequency design parameter, a first design parameter threshold is constructed according to multiple first high-frequency design parameters, and is added to the design parameter optimization space.
[0037] Specifically, first, a sample capacitor design parameter set is obtained, wherein the sample capacitor design parameters include at least electrode material type, electrode area, electrode thickness, electrolyte material type, electrolyte concentration, diaphragm thickness, diaphragm porosity and lead layout. Those skilled in the art may add additional capacitor design parameters according to actual conditions. Then, any sample capacitor design parameter is randomly selected from the sample capacitor design parameter set and set as the first design parameter to obtain the first design parameter set. Then, the same design parameters in the first design parameter set are clustered, and the number of the same parameters in the first design parameter set is counted and set as the first parameter frequency; the first parameter frequency is further judged according to a predetermined frequency threshold, and the first design parameter corresponding to the first parameter frequency that meets the predetermined frequency threshold is selected and set as the first high-frequency design parameter, and multiple first high-frequency design parameters are obtained; then, a first design parameter threshold is constructed according to multiple first high-frequency design parameters, and multiple design parameter thresholds corresponding to multiple design parameters are obtained in turn, and a design parameter optimization space is constructed according to multiple design parameter thresholds.
[0038] Further, the optimized design parameter set is outputted. Step 4 of this application includes:
[0039] Obtaining predetermined vehicle operating conditions, wherein the predetermined vehicle operating conditions at least include starting conditions, acceleration conditions, climbing conditions, deceleration conditions, and braking conditions; determining a plurality of capacitor simulation scenarios based on the predetermined vehicle operating conditions in a three-dimensional simulation platform, and constructing a capacitor simulation space; in the capacitor simulation space, optimizing capacitor design parameters based on the design parameter optimization space using a mutation evolution optimization algorithm and a capacitor performance predictor, and outputting the optimized design parameter set.
[0040] Specifically, first, a predetermined vehicle operating condition is obtained, wherein the predetermined vehicle operating condition includes at least a starting condition, an acceleration condition, a climbing condition, a deceleration condition and a braking condition; then, in a three-dimensional simulation platform, multiple capacitor simulation scenarios are determined based on the predetermined vehicle operating condition, wherein each simulation scenario should simulate the operating conditions of the predetermined vehicle under a specific condition, including speed, acceleration, load, etc.; then, a capacitor simulation space is constructed based on multiple capacitor simulation scenarios, and the capacitor simulation space should be able to simulate the performance of the capacitor under different conditions, such as capacitance, power density, charge and discharge efficiency, etc.; at the same time, corresponding simulation parameters are set for each simulation scenario, such as the design parameters, working voltage, working temperature, etc. of the capacitor, to ensure that the simulation parameters match the predetermined vehicle operating condition and the capacitor design requirements. Then, in the capacitor simulation space, multiple initial design parameters are selected based on the design parameter optimization space, and then, based on the multiple initial design parameters, the capacitor design parameter optimization is performed using the mutation evolution optimization algorithm and the capacitor performance predictor, and the optimized design parameter set is output.
[0041] Further, to output the optimized design parameter set, the present application also includes the following steps:
[0042] Based on the design parameter optimization space, a plurality of initial design parameters are randomly generated, and searcher positions are randomly assigned among the plurality of initial design parameters to determine a plurality of searchers and a plurality of subpopulations; within the capacitor simulation space, the plurality of searchers are simulated to output a plurality of capacitor simulation parameter sets, and the plurality of capacitor simulation parameter sets are input into the capacitor performance predictor to output a plurality of performance coefficients, which are set as a plurality of performance fitnesses, and an individual optimal position, a neighborhood optimal position, and a global optimal position are determined based on the plurality of performance fitnesses; based on the individual optimal position, the neighborhood optimal position, and the global optimal position, a search direction and a search step length of each searcher are calculated according to a predetermined optimization function to determine a search direction set and a search step length set; according to the search direction set and the search step length set, the positions of the plurality of searchers are updated, and the performance fitness of each updated searcher after the update is calculated to determine a plurality of updated performance fitnesses; an updated individual optimal position, an updated neighborhood optimal position, and an updated global optimal position are determined based on the plurality of updated performance fitnesses; iterative optimization is continuously performed until a preset termination condition is met, an optimal individual is determined, and a plurality of individuals within the neighborhood of the optimal individual are output and set as the optimized design parameter set.
[0043] Specifically, first, based on the design parameter optimization space, a plurality of initial design parameters are randomly generated; then, the searcher positions are randomly assigned in the plurality of initial design parameters to determine a plurality of searchers, and then, as needed, the searchers are divided into a plurality of sub-populations, and the sub-populations can be divided based on certain characteristics or attributes of the searchers, such as fitness, position, etc. Further, within the capacitor simulation space, the plurality of searchers are simulated, and a plurality of capacitor simulation parameter sets are output, wherein the capacitor simulation parameters include simulated capacitance, simulated storage energy, and simulated output power; then, the plurality of capacitor simulation parameter sets are input into the capacitor performance predictor, and a plurality of performance coefficients are output, which are set as a plurality of performance fitnesses. Then, based on the multiple performance fitnesses, the individual optimal position, the neighborhood optimal position and the global optimal position are determined. The individual optimal position is determined based on the analysis of egoistic behavior, wherein each searcher maintains its own individual optimal position, which is the optimal solution found by the searcher so far, and the searcher will adjust its search direction and step size according to the individual optimal position; the neighborhood optimal position is determined based on the analysis of altruistic behavior, and the neighborhood optimal position refers to the optimal solution found by other searchers within the searcher's neighborhood, and the searcher will adjust its search strategy according to the information of the neighborhood optimal position; the global optimal position is determined based on the analysis of pre-action behavior (combined with historical experience and learning), and the global optimal position refers to the optimal solution found by all searchers during the entire search process, and the global optimal position is open to all searchers, and they will adjust their search strategies according to the information of the global optimal position.
[0044] Then, based on the individual optimal position, the neighborhood optimal position and the global optimal position, the search direction and search step length of each searcher are calculated according to the predetermined optimization function, wherein the predetermined optimization function can be selected and adjusted according to the actual scenario, the search direction is calculated according to the individual optimal position, the neighborhood optimal position and the global optimal position, the search step length is calculated according to the search direction, which determines the distance the searcher moves in the search space, and the size of the step length will be adjusted according to the individual's current position, the individual optimal position and the global optimal position, and the search direction set and the search step length set are determined. Further, according to the search direction set and the search step length set, the positions of the multiple searchers are updated, and the performance fitness of each updated searcher after the update is calculated to determine multiple updated performance fitnesses. Then, according to the multiple updated performance fitnesses, the updated individual optimal position, the updated neighborhood optimal position and the updated global optimal position are re-determined. The above method is used to continuously iterate the optimization until the preset termination condition is met, the optimal individual is determined, and multiple individuals within the neighborhood range of the optimal individual are output and set as the optimization design parameter set.
[0045] Further, to construct a capacitor performance predictor, the present application also includes the following steps:
[0046] A first capacitor simulation scenario is selected from the multiple capacitor simulation scenarios, and a first sample data set is retrieved based on the first capacitor simulation scenario, wherein the first sample data includes sample capacitance, sample storage energy, sample output power and sample performance coefficient; with the sample capacitance, sample storage energy and sample output power as input and the sample performance coefficient as supervision, a BP neural network is supervised and trained through the first sample data set to obtain a first performance prediction branch that meets the expected convergence constraint; a first weight of the first capacitor simulation scenario is obtained, and a first performance prediction unit is constructed based on the first weight and the first performance prediction branch, wherein the first weight is positively correlated with the frequency of use of the first capacitor simulation scenario; multiple performance prediction units of multiple capacitor simulation scenarios are constructed in sequence, and the capacitor performance predictor is generated according to the multiple performance prediction units, wherein the output of the capacitor performance predictor is the sum of the output results of the multiple performance prediction units.
[0047] Specifically, first, a first capacitor simulation scene is randomly selected from the multiple capacitor simulation scenes, and the first capacitor simulation scene is used as a constraint condition to retrieve and obtain a first sample data set, wherein the first sample data includes sample capacitance, sample storage energy, sample output power and sample performance coefficient, and the performance coefficient represents the performance state of the capacitor. The larger the performance coefficient, the better the performance state of the capacitor. Then, the sample capacitance, sample storage energy and sample output power are used as inputs, and the sample performance coefficient is used as supervision, and the BP neural network is supervised and trained through the first sample data set, that is, the network weights are adjusted through the error back propagation algorithm to minimize the difference between the predicted value and the true value for training, and the performance of the network is monitored during the training process, such as the loss function, accuracy, etc. The network structure and training parameters are adjusted according to the monitoring results to improve the prediction ability of the network, and the first performance prediction branch that meets the expected convergence constraint is obtained.
[0048] Then, a first weight of the first capacitor simulation scenario is obtained, wherein the first weight is positively correlated with the frequency of use of the first capacitor simulation scenario, that is, the greater the frequency of use, the greater the first weight; then, a first performance prediction unit is constructed according to the first weight and the first performance prediction branch, and multiple performance prediction units of multiple capacitor simulation scenarios are sequentially constructed using the same method, and the capacitor performance predictor is generated according to the multiple performance prediction units, wherein the output of the capacitor performance predictor is the sum of the output results of the multiple performance prediction units. By constructing a capacitor performance predictor based on a BP neural network, the efficiency and accuracy of capacitor performance prediction can be improved.
[0049] Further, after determining the optimal design parameters, step five of this application also includes:
[0050] Establish a mapping association among the vehicle attribute characteristics, low-temperature environmental parameters, capacitor performance requirements and optimal design parameters; according to the mapping association, add the vehicle attribute characteristics, low-temperature environmental parameters, capacitor performance requirements as sub-nodes and the optimal design parameters as leaf nodes of the sub-nodes to the design parameter matching space, and use the design parameter matching space to perform subsequent capacitor design optimization.
[0051] Specifically, first, a mapping association is established between the vehicle attribute characteristics, low-temperature environmental parameters, capacitor performance requirements and optimal design parameters; the decision tree is a commonly used supervised learning algorithm for classification and regression tasks, which represents a series of decision rules through a tree structure, in which each node represents a characteristic attribute, each branch represents a decision, and the leaf node represents a category or predicted value, then based on the decision tree principle, according to the mapping association, the vehicle attribute characteristics, low-temperature environmental parameters, capacitor performance requirements are added as sub-nodes, and the optimal design parameters are the leaf nodes of the sub-nodes, and the design parameter matching space is constructed; finally, the design parameter matching space is used to perform subsequent capacitor design optimization to save design analysis time and improve capacitor design efficiency and accuracy.
[0052] In summary, the design method of a lead-type hybrid supercapacitor in an extremely low temperature environment provided by the present application has the following technical effects:
[0053] By taking vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements as comparison benchmarks, and taking lead-type hybrid supercapacitors as guiding conditions, information retrieval is performed based on the automotive Internet to obtain a sample capacitor design parameter set; then, high-frequency feature clustering is performed on the sample capacitor design parameter set, and a design parameter optimization space is constructed based on the clustering results; then, based on the design parameter optimization space, the capacitor design parameters are optimized in a visual simulation platform using a mutation evolution optimization algorithm and a capacitor performance predictor, and an optimized design parameter set is output; further, samples are produced according to the optimized design parameter set to obtain multiple sample supercapacitors, and performance tests and evaluations are performed on multiple sample supercapacitors under predetermined vehicle operating conditions, and finally, the optimal design parameters are determined according to the performance evaluation results for mass production; the accuracy and intelligence of supercapacitor demand analysis can be improved, the blindness and randomness of capacitor design can be reduced, and design time and design resources can be saved, thereby achieving the technical goal of quickly and accurately designing supercapacitors according to application scenarios, and achieving the technical effect of ensuring the safe driving of hybrid vehicles in extremely low temperature environments.
[0054] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0055] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. A design method for a lead-type hybrid supercapacitor in an extremely low temperature environment, characterized in that: include: Collect vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements of the target vehicle; Taking the vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements as comparison benchmarks, and taking the lead-type hybrid supercapacitor as a guide condition, information retrieval is performed based on the automotive Internet to obtain a sample capacitor design parameter set; Performing high-frequency feature clustering on the sample capacitor design parameter set, and constructing a design parameter optimization space based on the clustering results; Based on the design parameter optimization space, the capacitor design parameter optimization is performed in a visual simulation platform using a mutation evolution optimization algorithm and a capacitor performance predictor, and an optimized design parameter set is output; Producing samples according to the optimized design parameter set to obtain a plurality of sample supercapacitors, performing performance tests and evaluations on the plurality of sample supercapacitors under predetermined vehicle operating conditions, and determining optimal design parameters for batch production based on the performance evaluation results; The sample capacitor design parameter set is obtained, including: Taking the lead-type hybrid supercapacitor as a guide condition, information retrieval is performed based on the automotive Internet to obtain a retrieval data set, and first retrieval data is randomly selected from the retrieval data set, wherein the first retrieval data includes a first vehicle attribute feature, a first low-temperature environment parameter, a first capacitor performance requirement, and a first capacitor design parameter; Based on the vehicle attribute feature, a similarity analysis is performed on the first vehicle attribute feature to determine a first similarity; if the first similarity is greater than a predetermined similarity threshold, based on the low temperature environment parameter, a similarity analysis is performed on the first low temperature environment parameter to determine a second similarity; If the second similarity is greater than a predetermined similarity threshold, performing a similarity analysis on the first capacitor performance requirement based on the capacitor performance requirement to determine a third similarity; If the third similarity is greater than a predetermined similarity threshold, adding the first search data to the sample capacitor design parameter set; Build a capacitor performance predictor, including: Selecting a first capacitor simulation scenario from the multiple capacitor simulation scenarios, and retrieving and acquiring a first sample data set based on the first capacitor simulation scenario, wherein the first sample data includes sample capacitance, sample storage energy, sample output power, and sample performance coefficient; Taking the sample capacitance, sample storage energy, and sample output power as inputs and the sample performance coefficient as supervision, the BP neural network is supervised and trained through the first sample data set to obtain a first performance prediction branch that meets the expected convergence constraint; Obtaining a first weight of a first capacitor simulation scenario, and constructing a first performance prediction unit based on the first weight and the first performance prediction branch, wherein the first weight is positively correlated with a usage frequency of the first capacitor simulation scenario; Multiple performance prediction units of multiple capacitor simulation scenarios are sequentially constructed, and the capacitor performance predictor is generated according to the multiple performance prediction units, wherein the output of the capacitor performance predictor is the sum of the output results of the multiple performance prediction units.
2. The design method of lead-type hybrid supercapacitor in an extremely low temperature environment according to claim 1, characterized in that: Collect the target vehicle's vehicle attribute characteristics, low temperature environment parameters and capacitor performance requirements, including: The vehicle attribute characteristics, low-temperature environmental parameters and capacitor performance requirements of the target vehicle are collected, wherein the vehicle attribute characteristics include at least the vehicle type, power system and braking system, the low-temperature environmental parameters include at least the ambient temperature threshold and the ambient humidity threshold, and the capacitor performance requirements include at least the expected power-to-energy ratio, the expected charge-discharge efficiency, the expected cycle life and the expected engineering constraints.
3. The design method of lead-type hybrid supercapacitor in an extremely low temperature environment according to claim 1, characterized in that: Construct the design parameter optimization space, including: Acquire a sample capacitor design parameter set, wherein the sample capacitor design parameters at least include electrode material type, electrode area, electrode thickness, electrolyte material type, electrolyte concentration, diaphragm thickness, diaphragm porosity, and lead layout; A first design parameter set is randomly selected from the sample capacitor design parameter set, the number of identical parameters in the first design parameter set is counted and set as a first parameter frequency, a first design parameter corresponding to a first parameter frequency that meets a predetermined frequency threshold is selected and set as a first high-frequency design parameter, a first design parameter threshold is constructed according to multiple first high-frequency design parameters, and is added to the design parameter optimization space.
4. The design method of lead-type hybrid supercapacitor in an extremely low temperature environment according to claim 1, characterized in that: Output optimized design parameter set, including: Obtaining a predetermined vehicle operating condition, wherein the predetermined vehicle operating condition at least includes a starting condition, an acceleration condition, a climbing condition, a deceleration condition, and a braking condition; In the three-dimensional simulation platform, a plurality of capacitor simulation scenarios are determined based on the predetermined vehicle operating conditions to construct a capacitor simulation space; In the capacitor simulation space, based on the design parameter optimization space, a mutation evolution optimization algorithm and a capacitor performance predictor are used to optimize capacitor design parameters, and the optimized design parameter set is output.
5. The design method of lead-type hybrid supercapacitor in an extremely low temperature environment according to claim 4, characterized in that: Outputting the optimized design parameter set includes: Based on the design parameter optimization space, a plurality of initial design parameters are randomly generated, searcher positions are randomly assigned among the plurality of initial design parameters, and a plurality of searchers and a plurality of subpopulations are determined; In the capacitor simulation space, simulating the plurality of searchers, outputting a plurality of capacitor simulation parameter sets, inputting the plurality of capacitor simulation parameter sets into the capacitor performance predictor, outputting a plurality of performance coefficients, setting them as a plurality of performance fitnesses, and determining an individual optimal position, a neighborhood optimal position, and a global optimal position based on the plurality of performance fitnesses; Based on the individual optimal position, the neighborhood optimal position and the global optimal position, the search direction and the search step length of each searcher are calculated according to a predetermined optimization function to determine a search direction set and a search step length set; According to the search direction set and the search step set, the positions of the multiple searchers are updated, and the performance fitness of each updated searcher after the update is calculated to determine multiple updated performance fitnesses; Determine, according to the multiple update performance fitnesses, to update the individual optimal position, to update the neighborhood optimal position, and to update the global optimal position; Iterate and optimize continuously until the preset termination condition is met, determine the optimal individual, and output multiple individuals within the neighborhood of the optimal individual as the optimization design parameter set.
6. The design method of lead-type hybrid supercapacitor in an extremely low temperature environment according to claim 1, characterized in that: Determine the optimal design parameters, followed by: Establishing a mapping association between the vehicle attribute characteristics, low temperature environment parameters, capacitor performance requirements and optimal design parameters; According to the mapping association, the vehicle attribute characteristics, low temperature environment parameters, and capacitor performance requirements are taken as sub-nodes, and the optimal design parameters are taken as leaf nodes of the sub-nodes, which are added to the design parameter matching space, and the design parameter matching space is used to perform subsequent capacitor design optimization.
Citation Information
Patent Citations
Method for matching and optimizing parameters of mixed power locomotive with fuel cell and super capacitor
CN104071033A
Method for determining parameters of city rail train mounted supercapacitor bank
CN108376190A
Direct current bus capacitor ripple current parameter design method for electric vehicle
CN115203914A
Optimization method and system for high-temperature-resistant welding buckle type supercapacitor
CN117153310A
Zinc ion capacitor, preparation method thereof and vehicle
CN118098830A
