Optimization Method for N-Type Battery Preparation Process Based on Combined Process Flow Simulation

Abstract

The present invention belongs to the technical field of solar cells, and discloses an optimization method for the preparation process of N-type cells based on combined process flow simulation. The method includes: obtaining process flow data and silicon wafer data; constructing a simulation model corresponding to each process step in the N-type cell preparation process according to the process flow data; collecting m groups of corresponding process parameters for each process step, and performing process simulation on each process step according to the simulation model, process parameters and silicon wafer data corresponding to each process step to obtain excellent process parameters corresponding to each process step; randomly combining the excellent process parameters corresponding to each process step into p process flows; combining the simulation models corresponding to each process step, and performing process simulation according to the obtained process flows to obtain the optimal combined process parameters. The present invention realizes the comprehensive optimization of the process parameters for the preparation of N-type cells, thereby improving the overall performance of N-type cells.

Description

Technical Field

[0001] The present invention relates to the technical field of solar cells, and more specifically, to an optimization method for the preparation process of N-type cells based on the simulation of combined process flows. Background Art

[0002] The N-type cell is a new type of solar cell technology that uses a positive electrode material with a high energy density to achieve higher energy conversion efficiency and better battery stability. However, the preparation process of N-type cells involves multiple process steps, such as texturing, diffusion, post-cleaning, etc. The process parameters of each step will affect the performance of the final cell. Therefore, it is necessary to optimize the process parameters of each step.

[0003] Currently, the optimization of the process parameters for the preparation of N-type cells mainly relies on the trial-and-error method and empirical adjustment, which is inefficient and prone to errors. For example, the patent with the authorization announcement number CN101562220B discloses a manufacturing process for amorphous silicon thin-film solar cells. Another example is the patent with the publication number CN108847428A, which discloses a solar cell based on a silicon nanowire array and its preparation method. Therefore, there is an urgent need for an intelligent process parameter optimization method.

[0004] In view of this, the present invention proposes an optimization method for the preparation process of N-type cells based on the simulation of combined process flows to solve the above problems. Summary of the Invention

[0005] To overcome the above defects of the prior art and to achieve the above object, the present invention provides the following technical solution: an optimization method for the preparation process of N-type cells based on the simulation of combined process flows, including:

[0006] S1: Obtain process flow data and silicon wafer data;

[0007] S2: According to the process flow data, construct a simulation model corresponding to each process step in the preparation process of N-type cells;

[0008] S3: Collect m groups of corresponding process parameters for each process step. According to the simulation model, process parameters, and silicon wafer data corresponding to each process step, perform process simulation on each process step to obtain the excellent process parameters corresponding to each process step;

[0009] S4: Randomly combine the excellent process parameters corresponding to each process step into p process flows;

[0010] S5: Combine the simulation models corresponding to each process step, perform process simulation according to the obtained process flows, and obtain the optimal combined process parameters.

[0011] Further, the process flow data includes a process flow chart, equipment information, raw material data, and evaluation criteria; the equipment information includes preparation equipment and equipment parameters;

[0012] The process flow chart is a flow chart of the process transfer relationship for N-type battery preparation; the preparation equipment is the equipment corresponding to each process step; the equipment parameters are the technical parameters of each preparation equipment; the raw material data are the technical indicators of the raw materials used in the N-type battery preparation process; the evaluation criteria are the quality indicators corresponding to each process step;

[0013] The silicon wafer data includes silicon wafer quality, silicon wafer size, and silicon wafer structure;

[0014] The silicon wafer quality is the weight of the silicon wafer; the silicon wafer size is the side length of the silicon wafer; the silicon wafer structure is the type of crystal structure of the silicon wafer.

[0015] Further, the process steps include texturing, diffusion, post-cleaning, deposition of an antireflection film, and cell assembly; the simulation model is a mathematical and physical model for numerically describing and calculating the process steps.

[0016] Further, the method for obtaining the excellent process parameters corresponding to each process step includes:

[0017] Obtain m' simulation results after process simulation under m groups of corresponding process parameters for each process step. The simulation results are the evaluation criteria, m = m', and the simulation results correspond one-to-one with the process parameters;

[0018] Input the evaluation criteria corresponding to each process step into the trained optimization analysis model to predict the optimization direction corresponding to each process step; the optimization direction is the tendency of the evaluation criteria during the optimization process;

[0019] According to the optimization direction corresponding to each process step, screen out n' simulation results from the m' simulation results corresponding to each process step, obtain the corresponding n groups of process parameters according to the n' simulation results, and mark them as excellent process parameters; where n = n', m > n > 0.

[0020] Further, the training process of the optimization analysis model includes:

[0021] Pre-set corresponding judgment results for multiple groups of evaluation criteria. The judgment results include a tendency peak and a tendency valley, and different digital labels are set for both the tendency peak and the tendency valley;

[0022] Mark the digital label of the judgment result as a judgment tag, and convert the evaluation criteria and the corresponding judgment tag into a corresponding set of feature vectors;

[0023] Use each group of feature vectors as the input of the optimization analysis model. The optimization analysis model outputs a group of prediction judgment labels corresponding to each group of evaluation criteria, uses the actual judgment labels corresponding to each group of evaluation criteria as the prediction target, and the actual judgment label is the digital label of the judgment result corresponding to the evaluation criteria set in advance; use minimizing the sum of the prediction errors of all evaluation criteria as the training target; train the optimization analysis model until the sum of the prediction errors converges and then stop training; the optimization analysis model is a deep neural network model;

[0024] Obtain the corresponding judgment results according to the predicted judgment labels, and judge the optimization direction of the evaluation criteria corresponding to each process step.

[0025] Furthermore, randomly select a group of process parameters from the excellent process parameters corresponding to each process step, combine the group of process parameters selected for each process step into a process flow, and a total of p process flows are combined, where p = n 5 。

[0026] Furthermore, combine the simulation models corresponding to each process step according to the order of the process steps to obtain a combined simulation model; use the combined simulation model to simulate the whole process of N-type battery preparation according to p process flows and wafer data, and obtain the battery performance data corresponding to p process flows;

[0027] The battery performance data includes battery capacity, cycle life, and energy density;

[0028] The battery capacity is the amount of electricity that the N-type battery can store; the cycle life is the service life of the N-type battery; the energy density is the amount of electricity that the N-type battery can store per unit volume.

[0029] Furthermore, the method for obtaining the optimal combined process parameters includes:

[0030] Step a: Preset the initial temperature T max , the lowest temperature T min , the temperature reduction coefficient δ, and the maximum number of iterations and let the current temperature T = T max ;

[0031] Step b: Randomly set a feasible solution χ, where the feasible solution χ is the process flow, obtain the process flow range, and the process flow range is p process flows, and the process flow range is the range of the feasible solution χ;

[0032] Step c: Determine the fitness function;

[0033] The expression of the fitness function is: f = DZ;

[0034] In the formula, f is the fitness, and DZ is the comprehensive battery score;

[0035] Step d: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform a random perturbation within the neighborhood of the current point to obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′;

[0036] Step e: Calculate the fitness difference f″, and the expression of the fitness difference f″ is f″ = f′ - f;

[0037] If the fitness difference f″ > 0, then let χ = χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″ ≤ 0, then calculate the probability p′, and let χ = χ′ according to the probability p′; the expression of the probability p′ is: where e is the natural constant;

[0038] Step f: Loop steps d to e until the number of loops reaches the maximum number of iterations At this time, the loop ends and enters step g;

[0039] Step g: Let the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the cooled value to the current temperature; let the maximum number of iterations That is, assign the reduced value of the maximum number of iterations to the maximum number of iterations; if the reduced maximum number of iterations is not an integer, then round up the reduced maximum number of iterations to make the reduced maximum number of iterations an integer;

[0040] Step h: Loop steps d to g until the current temperature T < T min At this time, the loop ends, obtain the process flow corresponding to the feasible solution χ, and mark it as the optimal process flow; take the process parameters corresponding to the optimal process flow as the optimal combined process parameters.

[0041] Further, the calculation method of the comprehensive battery score includes:

[0042] DZ = ω1 × DR + ω2 × XS + ω3 × NM;

[0043] where DR is the battery capacity, XS is the cycle life, NM is the energy density, and ω1, ω2, ω3 are preset weight coefficients.

[0044] Further, analyze p process flows and screen out x process flows;

[0045] The method for screening x process flows includes:

[0046] Number the \(n'\) simulation results corresponding to each process step according to the corresponding optimization direction; if the optimization direction corresponding to the process step is towards the valley value, then sort the corresponding \(n'\) simulation results from small to large, and set numbers for the \(n'\) simulation results in ascending order successively, with the number range being \([R1, R2]\), where \(R2 - R1 + 1=n'\); if the optimization direction of the process step is towards the peak value, then sort the corresponding \(n'\) simulation results from large to small, and set numbers for the \(n'\) simulation results in ascending order successively, with the number range being \([R1, R2]\).

[0047] According to the numbers of the \(n'\) simulation results corresponding to each process step, also set numbers for the corresponding \(n\) groups of process parameters, and the numbers of the process parameters are the same as the numbers of the corresponding simulation results.

[0048] Successively add up the numbers of the process parameters corresponding to each process flow to obtain the total number ZH of each process flow i , \(i\in[1, p]\);

[0049] Compare the total number ZH of each process flow i with the number threshold TH; the expression of the number threshold TH is

[0050] If ZH i >TH, then do not mark the process flow corresponding to the total number ZH i as an excellent process flow;

[0051] If ZH i ≤TH, then mark the process flow corresponding to the total number ZH i as an excellent process flow;

[0052] Select the \(x\) process flows marked as excellent process flows from the \(p\) process flows, where \(p>x>0\).

[0053] The technical effects and advantages of the method for optimizing the N-type battery manufacturing process based on the simulation of combined process flows of the present invention are as follows:

[0054] 1. By constructing a simulation model corresponding to each process step, collecting silicon wafer data and process parameters of different process steps, performing process simulation on each process step, so as to obtain excellent process parameters for each process step; it can greatly reduce the parameter space for the whole process optimization, improve the optimization efficiency; perform process simulation on the process flows composed of the excellent process parameters of different process steps, obtain battery performance data, and optimize the process flows using the simulated annealing algorithm; realize the comprehensive optimization of the process parameters of each process step of the N-type battery, and find the best combined process parameters; improve the intelligence and automation, and effectively improve the battery capacity, cycle life and energy density of the N-type battery, thereby improving the overall performance of the N-type battery.

[0055] 2. By analyzing, evaluating, and screening all the original process flows, the better-performing process flows are included in the search scope of the subsequent simulated annealing algorithm, and the poorly-performing process flows are filtered out; thus, the problem scale is streamlined, the computational amount is reduced, and the algorithm efficiency can be effectively improved and the global optimization quality can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flowchart of the optimization method for the N-type battery manufacturing process based on the combined process flow simulation in Embodiment 1 of the present invention;

[0057] Figure 2 It is a flowchart of the optimization method for the N-type battery manufacturing process based on the combined process flow simulation in Embodiment 2 of the present invention;

[0058] Figure 3 It is a schematic diagram of an electronic device in Embodiment 3 of the present invention;

[0059] Figure 4 It is a schematic diagram of a storage medium in Embodiment 4 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0061] Embodiment 1:

[0062] Please refer to Figure 1 As shown, the optimization method for the N-type battery manufacturing process based on the combined process flow simulation in this embodiment includes:

[0063] S1: Obtain process flow data and silicon wafer data;

[0064] The process flow data includes a process flow chart, equipment information, raw material data, and evaluation criteria; the equipment information includes manufacturing equipment and equipment parameters;

[0065] The process flow chart is a flowchart of the process flow relationship of the N-type battery manufacturing process; the process flow chart includes at least process steps, process flow sequence, process names, etc.; the process flow chart is obtained according to relevant documents and papers on the N-type battery manufacturing process;

[0066] The process steps include texturing, diffusion, post-cleaning, deposition of an anti-reflection film, and cell assembly;

[0067] The preparation equipment is the equipment corresponding to each process step; the equipment parameters are the technical parameters of each preparation equipment; the preparation equipment is, for example, a CVD equipment, a high-temperature gradient heat treatment furnace, an etching machine, etc.; the equipment parameters are, for example, the working temperature range and processing size of the CVD equipment, the working temperature range and temperature rise / fall rate of the high-temperature gradient heat treatment furnace, the etching flow rate and etching rate of the etching machine, etc.; the equipment information is obtained according to the technical data of the equipment manufacturer;

[0068] The raw material data are the technical indicators of the raw materials used in the preparation process of the N-type battery; the raw material data are, for example, the crystal structure and thickness of the silicon wafer, the doping elements and doping concentrations of the P-type doping raw material and N-type doping raw material, etc.; the raw material data are obtained according to the raw material product information manual;

[0069] The evaluation criteria are the quality indicators corresponding to each process step; the evaluation criteria are, for example, the surface roughness in the texturing step, the impurity concentration in the diffusion step, etc.; the evaluation criteria are obtained according to the enterprise quality documents;

[0070] Each data in the process flow data can also be obtained by combining the actual experience of those skilled in the art.

[0071] The silicon wafer data includes the silicon wafer quality, silicon wafer size and silicon wafer structure;

[0072] The silicon wafer quality is the weight of the silicon wafer; the silicon wafer size is the side length of the silicon wafer; the silicon wafer structure is the type of crystal structure of the silicon wafer (such as single-crystalline silicon or polycrystalline silicon); the silicon wafer data are obtained by those skilled in the art according to the silicon wafer to be optimized;

[0073] S2: According to the process flow data, construct a simulation model corresponding to each process step in the N-type battery preparation process;

[0074] The simulation model is a mathematical and physical model for numerically describing and calculating the process step; the simulation model is established through modeling and simulation software such as TCAD, CoventorWare, COMSOL, Silvaco, etc.;

[0075] S3: Collect m groups of corresponding process parameters for each process step. According to the simulation model, process parameters and silicon wafer data corresponding to each process step, perform process simulation on each process step to obtain the excellent process parameters corresponding to each process step;

[0076] Process parameters are the parameters during the implementation of each process step; the process parameters corresponding to each process step are all different, and the m sets of process parameters corresponding to one process step are also all different. Process parameters include, for example, temperature and pressure in the texturing step, temperature and holding time in the diffusion step, solution concentration and time in the post-treatment step, etc.; the m sets of process parameters corresponding to each process step are all obtained from the historical successful process record data, and the historical successful process record data is the process parameters during the successful preparation of historical N-type batteries;

[0077] The method for obtaining the excellent process parameters corresponding to each process step includes:

[0078] Obtain m' simulation results after process simulation under the m sets of corresponding process parameters for each process step. The simulation results are the evaluation criteria, where m = m', and the simulation results correspond one-to-one with the process parameters;

[0079] Input the evaluation criteria corresponding to each process step into the trained optimization analysis model to predict the optimization direction corresponding to each process step; the optimization direction is the tendency of the evaluation criteria during the optimization process;

[0080] The specific training process of the optimization analysis model includes:

[0081] Pre-set corresponding judgment results for multiple groups of evaluation criteria. The judgment results include the tendency peak value and the tendency valley value, and different digital labels are set for the tendency peak value and the tendency valley value. Exemplarily, the digital label 0 is set for the tendency peak value, and the digital label 1 is set for the tendency valley value; the tendency peak value indicates that the evaluation criteria should be optimized in the direction of the maximum value, that is, the larger the evaluation criteria, the better; the tendency valley value indicates that the evaluation criteria should be optimized in the direction of the minimum value, that is, the smaller the evaluation criteria, the better; the judgment results corresponding to the evaluation criteria are collected by those skilled in the art for each process step during the preparation of historical N-type batteries. Those skilled in the art judge the optimization directions corresponding to multiple different evaluation criteria according to experience and set the corresponding judgment results for the multiple different evaluation criteria in sequence;

[0082] Mark the digital label of the judgment result as the judgment label, and convert the evaluation criteria and the corresponding judgment label into a corresponding set of feature vectors;

[0083] Use each set of feature vectors as the input of the optimization analysis model. The optimization analysis model outputs a set of predicted judgment labels corresponding to each set of evaluation criteria, uses the actual judgment label corresponding to each set of evaluation criteria as the prediction target, and the actual judgment label is the digital label of the judgment result pre-set corresponding to the evaluation criteria; uses minimizing the sum of the prediction errors of all evaluation criteria as the training target; where the calculation formula for the prediction error is Z k =(α k -μ k) 2 , where Z k is the prediction error, k is the group number of the eigenvector corresponding to the evaluation criterion, and α k is the prediction judgment label corresponding to the k-th group of evaluation criteria, and μ k is the actual judgment label corresponding to the k-th group of evaluation criteria; train the optimization analysis model until the sum of the prediction errors reaches convergence and then stop training;

[0084] The above optimization analysis model is specifically a deep neural network model;

[0085] Obtain the corresponding judgment result according to the predicted judgment label to judge the optimization direction of the evaluation criterion corresponding to each process step;

[0086] According to the optimization direction corresponding to each process step, screen out n' simulation results from the m' simulation results corresponding to each process step, obtain the corresponding n groups of process parameters according to the n' simulation results, and mark them as excellent process parameters; where, n = n', m > n > 0;

[0087] Exemplarily, the evaluation criterion in the texturing step is surface roughness. In the N-type battery manufacturing process, texturing is to form a uniform and smooth thin film on the surface to provide better light absorption and photoelectric conversion efficiency; a smaller surface roughness can reduce surface reflection and scattering and improve light absorption and utilization; by optimizing the texturing step, controlling and reducing the surface roughness, the performance of the N-type battery can be improved; therefore, the optimization direction corresponding to the texturing step should be towards the valley value, that is, the smaller the surface roughness, the more successful the texturing step; sort the m' simulation results corresponding to the texturing step from small to large, and screen out the top n' simulation results as the excellent process parameters of the texturing step;

[0088] S4: Randomly combine the excellent process parameters corresponding to each process step into p process flows;

[0089] Randomly select a set of process parameters from the excellent process parameters corresponding to each process step, combine the set of process parameters selected from each process step into a process flow, and a total of p process flows are combined, where p = n 5 ;

[0090] S5: Combine the simulation models corresponding to each process step, perform process simulation according to the obtained process flows, and obtain the optimal combined process parameters;

[0091] Combine the simulation models corresponding to each process step according to the order of the process steps to obtain a combined simulation model; use the combined simulation model to simulate the entire process of N-type battery manufacturing according to the p process flows and the silicon wafer data, and obtain the battery performance data corresponding to the p process flows;

[0092] The battery performance data includes battery capacity, cycle life, and energy density;

[0093] The battery capacity is the amount of electricity that an N-type battery can store; the cycle life is the service life of the N-type battery; the energy density is the amount of electricity that the N-type battery can store per unit volume;

[0094] The larger the battery capacity, the stronger the internal structure design and energy storage ability of the N-type battery, indicating better energy storage performance of the N-type battery; the longer the cycle life, the stronger the stability of the materials and structure of the N-type battery under repeated charge and discharge, and the more reliable the electrochemical reaction, indicating better cycle use performance of the battery; the higher the energy density, the higher the utilization rate of the energy storage materials per unit volume of the battery core; the better internal structure design and energy conversion efficiency of the N-type battery enable the electric quantity to be fully released in a more compact space, and the performance of the N-type battery is better;

[0095] The method for obtaining the optimal combination of process parameters includes:

[0096] Step a: Preset the initial temperature T max , the lowest temperature T min , the temperature reduction coefficient δ, and the maximum number of iterations And let the current temperature T = T max ;

[0097] Step b: Randomly set a feasible solution χ, and the feasible solution χ is the process flow. Obtain the process flow range, and the process flow range is p process flows, and the process flow range is the range of the feasible solution χ;

[0098] Step c: Determine the fitness function;

[0099] The expression of the fitness function is: f = DZ;

[0100] In the formula, f is the fitness, and DZ is the comprehensive battery score;

[0101] The calculation method of the comprehensive battery score includes:

[0102] DZ = ω1×DR + ω2×XS + ω3×NM;

[0103] In the formula, DR is the battery capacity, XS is the cycle life, NM is the energy density, and ω1, ω2, ω3 are preset weight coefficients;

[0104] The specific values of the weight coefficients in the formula can be set according to the actual situation. The weight coefficients reflect the influence degree of each battery performance data on the comprehensive battery score. Those skilled in the art can preset the corresponding weight coefficients according to the actual influence degree of each battery performance data on the comprehensive battery score to accurately evaluate the performance of the N-type battery;

[0105] It should be noted that the battery performance data are the influencing parameters of the comprehensive battery score. The larger the battery capacity, the larger the comprehensive battery score, and vice versa. The larger the cycle life, the larger the comprehensive battery score, and vice versa. The larger the energy density, the still larger the comprehensive battery score, and vice versa. Since the comprehensive battery score is only used to reflect the performance of the N-type battery, the calculation of the comprehensive battery score is a dimensionless calculation;

[0106] Step d: Calculate the fitness f corresponding to the feasible solution χ. Taking the feasible solution χ as the current point, perform a random perturbation within the neighborhood of the current point to obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′;

[0107] Step e: Calculate the fitness difference f″. The expression of the fitness difference f″ is f″ = f′ - f;

[0108] If the fitness difference f″ > 0, then let χ = χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″ ≤ 0, then calculate the probability p′, and let χ = χ′ according to the probability p′. The expression of the probability p′ is: where e is the natural constant;

[0109] Step f: Loop steps d to e until the number of loops reaches the maximum number of iterations At this time, the loop ends and enters step g;

[0110] Step g: Let the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the cooled value to the current temperature; let the maximum number of iterations That is, assign the value of the reduced maximum number of iterations to the maximum number of iterations; if the reduced maximum number of iterations is not an integer, then round up the reduced maximum number of iterations to make the reduced maximum number of iterations an integer;

[0111] Step h: Loop steps d to g until the current temperature T < T min At this time, the loop ends, obtain the process flow corresponding to the feasible solution χ, and mark it as the optimal process flow; take the process parameters corresponding to the optimal process flow as the optimal combined process parameters;

[0112] It should be noted that the initial temperature T max , the lowest temperature T min , the cooling coefficient δ, and the maximum number of iterations As preset parameters, the preset parameters are collected by those skilled in the art in the historical preparation of N-type batteries. Q analysis sets are collected, and each analysis set includes p process flows. For the same analysis set, multiple different groups of preset parameters are sequentially preset. The simulated annealing algorithm is sequentially used to obtain the process flows, the fitness corresponding to each process flow is calculated, the process flow corresponding to the maximum fitness is obtained, and it is marked as the maximum process flow; the preset parameters corresponding to the maximum process flow are used as the preset parameters corresponding to this analysis set, and so on to obtain the preset parameters corresponding to Q analysis sets. The average value of multiple preset parameters (i.e., the average value of the initial temperature, the lowest temperature, the cooling coefficient, and the maximum number of iterations) is used as the preset initial temperature T in step a max , the lowest temperature T min , the cooling coefficient δ, and the maximum number of iterations

[0113] In this embodiment, by constructing a simulation model corresponding to each process step, collecting silicon wafer data and process parameters of different process steps, and performing process simulation on each process step, excellent process parameters for each process step can be obtained; the parameter space for the whole-process optimization can be greatly reduced, and the optimization efficiency can be improved; the process flow composed of the excellent process parameters of different process steps is simulated to obtain battery performance data, and the simulated annealing algorithm is used to optimize the process flow; the process parameters of each process step of the N-type battery are comprehensively optimized to find the best combination of process parameters; the intelligence and automation are improved, and the battery capacity, cycle life, and energy density of the N-type battery are effectively improved, thereby improving the overall performance of the N-type battery

[0114] Embodiment 2:

[0115] Please refer to Figure 2 As shown, this embodiment further improves the design on the basis of Embodiment 1. In Embodiment 1, when using the simulated annealing algorithm to obtain the best combination of process parameters, the range of feasible solutions is p process flows, and the range of feasible solutions is too large, resulting in too large a computational amount of the simulated annealing algorithm and low efficiency in obtaining the best combination of process parameters; therefore, this embodiment provides an N-type battery preparation process optimization method based on combined process flow simulation, which further includes:

[0116] S6: Analyze the p process flows and screen out x process flows

[0117] The method for screening x process flows includes:

[0118] Number the \(n'\) simulation results corresponding to each process step according to the corresponding optimization direction. If the optimization direction corresponding to the process step is towards the valley value, sort the corresponding \(n'\) simulation results from small to large, and sequentially assign numbers to the \(n'\) simulation results in ascending order. The number range is \([R1, R2]\), where \(R2 - R1 + 1=n'\). If the optimization direction of the process step is towards the peak value, sort the corresponding \(n'\) simulation results from large to small, and sequentially assign numbers to the \(n'\) simulation results in ascending order. The number range is \([R1, R2]\).

[0119] According to the numbers of the \(n'\) simulation results corresponding to each process step, also assign numbers to the corresponding \(n\) sets of process parameters. The numbers of the process parameters are the same as the numbers of the corresponding simulation results.

[0120] Sequentially add up the numbers of the multiple process parameters corresponding to each process flow to obtain the total number ZH of each process flow i , \(i\in[1, p]\);

[0121] For the total number ZH of each process flow i Compare it with the number threshold TH. The expression of the number threshold TH is

[0122] If ZH i >TH, then do not mark the process flow corresponding to the total number ZH i as an excellent process flow;

[0123] If ZH i ≤TH, then mark the process flow corresponding to the total number ZH i as an excellent process flow;

[0124] Select the \(x\) process flows marked as excellent process flows from the \(p\) process flows, where \(p>x>0\);

[0125] In this embodiment, by analyzing, evaluating and screening all the original process flows, the process flows with better performance are included in the search range of the subsequent simulated annealing algorithm, and the process flows with poor performance are filtered out; thus, the problem scale is streamlined, the calculation amount is reduced, and the algorithm efficiency can be effectively improved and the global optimization quality can be guaranteed.

[0126] Example 3:

[0127] Please refer to Figure 3As shown, according to another aspect of the present application, an electronic device 500 is further provided. The electronic device 500 may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute the method for optimizing the preparation process of N-type batteries based on combined process flow simulation as described above.

[0128] The method or system according to the embodiments of the present application can also be implemented by means of Figure 3 the architecture of the electronic device shown. As Figure 3 shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a ROM 503, a RAM 504, a communication port 505 connected to the network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store the method for optimizing the preparation process of N-type batteries based on combined process flow simulation provided by the present application. Further, the electronic device 500 may further include a user interface 508. Of course, Figure 3 the architecture shown is only exemplary. When implementing different devices, one or more components in the Figure 3 shown electronic device can be omitted according to actual needs.

[0129] Example 4:

[0130] Please refer to Figure 4 shown, which is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are run by a processor, the method for optimizing the preparation process of N-type batteries based on combined process flow simulation according to the embodiments of the present application described with reference to the above drawings can be executed. The storage medium 600 includes but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0131] In addition, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, and the non-transitory machine-readable storage medium stores machine-readable instructions, and the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, such as: the method for optimizing the preparation process of N-type batteries based on combined process flow simulation. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0132] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0133] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0134] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0135] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0136] The unit described as a separating component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, in each embodiment of the present invention, each functional unit may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit.

[0138] As mentioned above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0139] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An N-type battery manufacturing process optimization method based on combined process flow simulation, characterized in that: include: S1: Acquire process flow data and silicon wafer data; S2: Based on the process flow data, a simulation model corresponding to each process step in the N-type battery preparation process is constructed; S3: m groups of corresponding process parameters are collected for each process step, and process simulation is performed on each process step according to the simulation model, process parameters and silicon wafer data corresponding to each process step to obtain the excellent process parameters corresponding to each process step; S4: Randomly combine the excellent process parameters corresponding to each process step into p process flows; Analyze p process flows and select x process flows; Methods for screening x process flows include: The n′ simulation results corresponding to each process step are numbered according to the corresponding optimization direction; if the optimization direction corresponding to the process step is to tend to the valley value, the corresponding n′ simulation results are sorted from small to large, and the numbers are set for n′ simulation results in ascending order, and the number range is [R1, R2], R2-R1+1=n′; if the optimization direction of the process step is to tend to the peak value, the corresponding n′ simulation results are sorted from large to small, and the numbers are set for n′ simulation results in ascending order, and the number range is [R1, R2]; According to the numbers of the n′ simulation results corresponding to each process step, the corresponding n groups of process parameters are also numbered, and the numbers of the process parameters are consistent with the numbers of the corresponding simulation results; Add up the process parameter numbers corresponding to each process flow in turn to obtain the total number of each process flow. i , i∈[1,p]; The sum of the numbers of each process flow is ZH i Compare with the number threshold TH; the expression of the number threshold TH is If ZH i >TH, the total number ZH is not i The corresponding process flow is marked as an excellent process flow; If ZH i ≤TH, then the sum of the numbers ZH i The corresponding process flow is marked as an excellent process flow; Select x process flows marked as excellent process flows from p process flows, where p>x>0; S5: combining the simulation models corresponding to each process step, performing process simulation according to the acquired process flow, and obtaining the best combined process parameters; the method for obtaining the best combined process parameters includes: Step a: Preset initialization temperature T max , minimum temperature T min , cooling coefficient δ and maximum number of iterations And let the current temperature T = T max ; Step b: randomly set a feasible solution χ, the feasible solution χ is the process flow, obtain the process flow range, the process flow range is x process flows, and the process flow range is the range of the feasible solution χ; Step c: determine the fitness function; The expression of fitness function is: f = DZ; In the formula, f is the fitness, DZ is the comprehensive score of the battery; Step d: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbations in the neighborhood of the current point, obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′; Step e: Calculate the fitness difference f″, the expression of the fitness difference f″ is f″=f′-f; If the fitness difference f″>0, let χ=χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″≤0, calculate the probability p′, and let χ=χ′ according to the probability p′; the expression of probability p′ is: Where e is a natural constant; Step f: Repeat steps d to e until the number of loops reaches the maximum number of iterations. When , the loop ends and enters step g; Step g: Set the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the value after cooling to the current temperature; set the maximum number of iterations That is, assign the value of the maximum number of iterations after the reduction to the maximum number of iterations; if the maximum number of iterations after the reduction is not an integer, the maximum number of iterations after the reduction is rounded up to make the maximum number of iterations after the reduction an integer; Step h: Repeat steps d to g until the current temperature T < T min When , the loop ends, the process flow corresponding to the feasible solution χ is obtained and marked as the optimal process flow; the process parameters corresponding to the optimal process flow are used as the optimal combined process parameters.

2. The N-type battery manufacturing process optimization method based on combined process flow simulation according to claim 1 is characterized in that: The process data includes process flow chart, equipment information, raw material data and evaluation criteria; the equipment information includes preparation equipment and equipment parameters; The process flow chart is a flow chart of the flow relationship of the N-type battery preparation process; the preparation equipment is the equipment corresponding to each process step; the equipment parameters are the technical parameters of each preparation equipment; the raw material data are the technical indicators of the raw materials used in the preparation process of the N-type battery; the evaluation standard is the quality indicator corresponding to each process step; The silicon wafer data includes silicon wafer quality, silicon wafer size and silicon wafer structure; The silicon wafer mass is the weight of the silicon wafer; The silicon wafer size refers to the side length of the silicon wafer; the silicon wafer structure refers to the crystalline structure type of the silicon wafer.

3. The N-type battery preparation process optimization method based on combined process flow simulation according to claim 2, characterized in that: The process steps include texturing, diffusion, post-cleaning, anti-reflection film plating and battery cell assembly; the simulation model is a mathematical and physical model for numerical description and calculation of the process steps.

4. The N-type battery preparation process optimization method based on combined process flow simulation according to claim 3 is characterized in that: The method for obtaining the excellent process parameters corresponding to each process step includes: Obtain m′ simulation results after process simulation for each process step under m groups of corresponding process parameters. The simulation results are the evaluation criteria, m=m′, and the simulation results correspond to the process parameters one by one. Input the evaluation criteria corresponding to each process step into the trained optimization analysis model to predict the optimization direction corresponding to each process step; the optimization direction is the trend of the evaluation criteria during the optimization process; According to the optimization direction corresponding to each process step, n′ simulation results are screened out from the m′ simulation results corresponding to each process step, and the corresponding n groups of process parameters are obtained according to the n′ simulation results, and marked as excellent process parameters; wherein n=n′, m>n>0.

5. The N-type battery preparation process optimization method based on combined process flow simulation according to claim 4 is characterized in that: The training process of the optimization analysis model includes: Pre-setting corresponding judgment results for multiple groups of evaluation criteria, the judgment results include trending peak values ​​and trending valley values, and setting different digital labels for trending peak values ​​and trending valley values; The digital labels of the judgment results are marked as judgment labels, and the evaluation criteria and the corresponding judgment labels are converted into a corresponding set of feature vectors; Each group of feature vectors is used as the input of the optimization analysis model. The optimization analysis model uses a group of prediction judgment labels corresponding to each group of evaluation criteria as output, and uses the actual judgment labels corresponding to each group of evaluation criteria as prediction targets, where the actual judgment labels are pre-set digital labels of the judgment results corresponding to the evaluation criteria; minimizing the sum of the prediction errors of all evaluation criteria is used as the training target; the optimization analysis model is trained until the sum of the prediction errors reaches convergence and the training is stopped; the optimization analysis model is a deep neural network model; Obtain the corresponding judgment results based on the predicted judgment labels, and determine the optimization direction of the corresponding evaluation criteria for each process step.

6. The N-type battery manufacturing process optimization method based on combined process flow simulation according to claim 5, characterized in that: Randomly select a set of process parameters from the excellent process parameters corresponding to each process step, and combine the set of process parameters selected from each process step into a process flow, and combine a total of p process flows, p = n 5 .

7. The N-type battery manufacturing process optimization method based on combined process flow simulation according to claim 6 is characterized in that: The simulation models corresponding to each process step are combined according to the order of the process steps to obtain a combined simulation model; the combined simulation model is used to simulate the entire process of N-type battery preparation according to p process flows and silicon wafer data to obtain battery performance data corresponding to the p process flows; Battery performance data includes battery capacity, cycle life and energy density; Battery capacity is the amount of electricity that an N-type battery can store; cycle life is the service life of an N-type battery; and energy density is the amount of electricity that an N-type battery can store per unit volume.

8. The N-type battery manufacturing process optimization method based on combined process flow simulation according to claim 7 is characterized in that: The calculation method of the battery comprehensive score includes: DZ=ω1×DR+ω2×XS+ω3×NM; Where DR is the battery capacity, XS is the cycle life, NM is the energy density, and ω1, ω2, and ω3 are preset weight coefficients.

Images