Battery positive electrode material production line mixing machine control method, device, equipment and medium

Abstract

The application belongs to the technical field of industrial control, and discloses a battery positive electrode material production line mixer control method, device, equipment and medium, which comprises the following steps: determining constraint conditions according to various key parameters related to production capacity, energy consumption and particle size; constructing a multi-objective optimization function with the goal of maximizing mixer production capacity, minimizing energy consumption and stabilizing particle size; constructing a fitness function according to energy consumption, production capacity and particle size; constructing a dynamic optimization model based on a particle swarm optimization algorithm according to the constraint conditions, the multi-objective optimization function and the fitness function; collecting data corresponding to each key parameter in real time to obtain real-time data, inputting all the real-time data into the dynamic optimization model to obtain control parameters, and controlling the mixer according to the control parameters. The efficiency and product quality of the battery positive electrode material production line can be improved.

Description

Technical Field

[0001] This invention belongs to the field of industrial control technology, specifically relating to a method, device, equipment, and medium for controlling a mixer in a battery cathode material production line. Background Technology

[0002] Battery cathode materials (such as bismuth oxide) Materials such as cobalt oxide (CoO2) and lithium iron phosphate (LiFePO4) are mainly used in lithium-ion batteries and other types of batteries. With the rapid development of electric vehicles, the market demand for high-performance batteries is increasing, which in turn drives the demand for high-quality battery cathode materials, leading to increasingly higher requirements for the purity, particle size, and morphology control of battery cathode materials.

[0003] Not only does the efficiency of the mixer affect the production capacity of the battery cathode material production line, but the uniformity of the raw material mixing and the operating parameters of the mixer play an important role in controlling the purity, particle size and morphology of the battery cathode material.

[0004] Currently, it is difficult to precisely control factors such as temperature, stirring speed, and material concentration during the oxidation reaction in the mixing process in existing production processes. This often leads to incomplete or excessive oxidation, making it difficult to effectively control the particle size distribution and morphology of the final product, thus affecting the consistency and quality stability of the product. Moreover, there is often a mismatch between the capacity of the mixer and the production efficiency of the production line.

[0005] Therefore, the efficiency and product quality of battery cathode material production lines need to be improved. Summary of the Invention

[0006] The purpose of this invention is to provide a mixing machine control method, device, equipment, and storage medium for a battery cathode material production line, which can improve the efficiency and product quality of the battery cathode material production line.

[0007] The first aspect of this invention discloses a method for controlling a mixer in a battery cathode material production line, comprising:

[0008] Constraints are determined based on key parameters related to capacity, energy consumption, and particle size.

[0009] A multi-objective optimization function is constructed with the objectives of maximizing mixer capacity, minimizing energy consumption, and stabilizing particle size.

[0010] A fitness function is constructed based on energy consumption, production capacity, and granularity.

[0011] Based on the constraints, the multi-objective optimization function, and the fitness function, a dynamic optimization model is constructed using the particle swarm optimization algorithm.

[0012] Real-time data is collected for each of the key parameters to obtain real-time data. All the real-time data is then input into the dynamic optimization model to obtain control parameters. The mixer is then controlled according to the control parameters.

[0013] In some embodiments, the expression of the multi-objective optimization function is:

[0014] ,

[0015] in, For energy consumption, Indicates reference energy consumption; The parameters to be optimized are... For temperature, For speed, For traffic; These are weighting coefficients for different objectives, used to balance energy consumption, production capacity, and granularity; For production capacity; For granularity function, The target granularity.

[0016] In some embodiments, after constructing the dynamic optimization model, the method further includes:

[0017] Based on historical data of the key parameters, calculate the correlation between the key parameters and at least one of production capacity, energy consumption, and particle size;

[0018] The dynamic optimization model is adjusted based on the correlation.

[0019] In some embodiments, adjusting the dynamic optimization model based on the correlation includes:

[0020] Based on the correlation, determine the coefficient terms that need to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted;

[0021] Adjust the coefficient terms according to the adjustment model.

[0022] In some embodiments, the fitness function is expressed as:

[0023] ,

[0024] in, These are the weighting coefficients for different objectives. Indicates reference energy consumption. Let be the energy consumption value of particle i. Let i be the energy production value of particle i. For target granularity, Let be the particle size value of particle i.

[0025] In some embodiments, the control parameters include rotational speed, temperature, and material flow rate. Controlling the mixer according to the control parameters includes:

[0026] Based on the rotational speed in the control parameters, a first PLC instruction is obtained, and the first PLC instruction is input into the variable frequency motor control system that controls the mixer.

[0027] Based on the temperature in the control parameters, a second PLC instruction is obtained, and the heating device or cooling system is controlled according to the second PLC instruction;

[0028] Based on the material flow rate in the control parameters, a third PLC instruction is obtained, and the valve of the feed pipe is controlled according to the third PLC instruction.

[0029] A second aspect of this invention discloses a mixing machine control device for a battery cathode material production line, comprising:

[0030] The model building module is used to determine constraints based on various key parameters related to capacity, energy consumption, and granularity; construct a multi-objective optimization function with the objectives of maximizing mixer capacity, minimizing energy consumption, and stabilizing granularity; construct a fitness function based on energy consumption, capacity, and granularity; and construct a dynamic optimization model based on the particle swarm optimization algorithm according to the constraints, the multi-objective optimization function, and the fitness function.

[0031] The real-time control module is used to collect data corresponding to each of the key parameters in real time, obtain real-time data, input all the real-time data into the dynamic optimization model to obtain control parameters, and control the mixer according to the control parameters.

[0032] In some embodiments, the expression of the multi-objective optimization function is:

[0033] ,

[0034] in, For energy consumption, Indicates reference energy consumption; The parameters to be optimized are... For temperature, For speed, For traffic; These are weighting coefficients for different objectives, used to balance energy consumption, production capacity, and granularity; For production capacity; For granularity function, The target granularity.

[0035] A third aspect of the present invention discloses an electronic device, including a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the mixer control method for a battery cathode material production line disclosed in the first aspect.

[0036] The fourth aspect of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the mixing machine control method for a battery cathode material production line disclosed in the first aspect.

[0037] The beneficial effects of this invention lie in that by defining constraints based on capacity, energy consumption, and granularity, constructing multi-objective optimization functions and fitness functions, and thereby building a dynamic optimization model based on the particle swarm optimization algorithm, key parameters in the production process are monitored. Combined with the particle swarm optimization algorithm, real-time capacity optimization of the mixer and intelligent control of the entire production line are achieved. This solves the problem of mismatch between mixer capacity and production line efficiency, and improves production line efficiency and product consistency. Attached Figure Description

[0038] The accompanying drawings illustrate specific examples of the technical solutions described in this invention and, together with the detailed embodiments, form part of the specification, serving to explain the technical solutions, principles, and effects of this invention.

[0039] Unless otherwise specified or defined, the same reference numerals in different figures represent the same or similar technical features, and different reference numerals may be used to represent the same or similar technical features.

[0040] Figure 1 This is a flowchart of a mixing machine control method for a battery cathode material production line disclosed in an embodiment of the present invention;

[0041] Figure 2 This is a flowchart illustrating the control of a mixer based on control parameters according to an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of the mixing machine control device in the battery cathode material production line according to an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0044] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. When combined with the technical solutions of the invention in a real-world scenario, all technical and scientific terms used herein may also have meanings corresponding to the purpose of achieving the technical solutions of the invention. The terms "first," "second," etc., used herein are merely for distinguishing names and do not represent a specific number or order. The term "and / or," as used herein, includes any and all combinations of one or more of the associated listed items.

[0045] It should be noted that when a component is considered "fixed" to another component, it can be directly fixed to the other component or there can be an intervening component; when a component is considered "connected" to another component, it can be directly connected to the other component or there can be an intervening component; when a component is considered "mounted" on another component, it can be directly mounted on the other component or there can be an intervening component; when a component is considered "placed" on another component, it can be directly placed on the other component or there can be an intervening component.

[0046] Unless otherwise specified or defined, the terms "described" or "the" as used herein refer to the technical features or technical content mentioned or described prior to the relevant section, which may be the same as or similar to the technical features or technical content mentioned herein. Furthermore, the terms "comprising" and "having," and any variations thereof, as used herein, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0047] To optimize the production process of battery cathode materials, improve production efficiency, reduce energy consumption, and ensure product consistency and high quality, this invention focuses on optimizing the relationship between mixer capacity and production line control. By monitoring key parameters in the production process (such as temperature, humidity, rotation speed, flow rate, pressure, and material particle size) and combining this with particle swarm optimization (PSO) algorithm, real-time capacity optimization of the mixer and intelligent control of the entire production line are achieved. Through real-time data acquisition and dynamic optimization models, the mismatch between mixer capacity and production line efficiency is resolved; production line efficiency and product consistency are improved, providing an innovative solution for the production of high-quality battery cathode materials.

[0048] This invention discloses a mixer control method for a bismuth oxide production line, which can be implemented by computer programming, either as an independent control system or as part of a control system within a bismuth oxide feeding and conveying system. The execution subject of this method can be an electronic device such as a computer, laptop, or tablet, or a control chip embedded in an electronic device; this invention does not limit this to any particular type.

[0049] To facilitate understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0050] like Figure 1 As shown, the method includes the following steps:

[0051] Step S100: Determine the constraints based on the key parameters related to capacity, energy consumption, and particle size;

[0052] Many parameters are related to capacity, energy consumption, and particle size (material particle size and / or product particle size). Among these parameters, those with a greater impact on one or more of these factors are selected as key parameters. In this embodiment, for the bismuth oxide production line, the identified key parameters include temperature, humidity, rotational speed, and flow rate, which are the main parameters for mixer and production line control. These key parameters, along with energy consumption and material particle size, serve as the search dimensions for the Particle Swarm Optimization (PSO) algorithm used in the dynamic optimization model.

[0053] In particle swarm optimization, it is necessary to ensure that the solutions found by the particles are feasible and do not violate the safety and quality requirements of the production process. Therefore, it is necessary to set constraints for the dynamic optimization model, that is, to determine the constraints corresponding to each key parameter. Specifically:

[0054] Temperature (T) is a key parameter affecting reaction rate and mixing efficiency; the constraints on temperature are as follows: The mixer speed (N) directly affects mixing uniformity and efficiency; the constraint condition for the speed is... Material flow rate (F) determines the amount of material entering the mixer per unit time. The constraint condition for the flow rate is... Humidity (H) affects material flowability and mixing uniformity; the constraint conditions for humidity are as follows: Material particle size (G) is a key quality indicator of the final product, affected by factors such as temperature, humidity, rotational speed, and flow rate. The constraints on material particle size are as follows: , For target granularity, The tolerance range for particle size; energy consumption (E) is the equipment energy consumption of the mixer, which is related to speed, temperature, etc., and the energy consumption constraint is... The maximum and minimum values ​​in the above constraints need to be set based on experience, taking into account the specific products of the battery cathode material production line and the parameters of the mixing equipment in the production line.

[0055] In some embodiments, cluster analysis can be performed using clustering algorithms such as K-means to analyze parameter combinations across different production batches and identify which parameters are most important under similar production conditions. For example, suppose we have multiple production batches, each with different temperatures T, rotational speed N, flow rates F, and corresponding production capacities. The data was clustered using the K-means clustering algorithm, dividing the historical data into k groups. First, the objective function of K-means was defined: ,in It is the i-th cluster. X is the cluster center, and X is the data point. K-means clustering divides historical data into several groups (clusters), each group corresponding to similar production conditions. Suppose we find that the T, N, and F parameters of some batches are similar, and the production capacity... A higher value indicates that these parameter combinations are ideal and represent a combination of key parameters.

[0056] Step S200: Construct a multi-objective optimization function with the objectives of maximizing mixer capacity, minimizing energy consumption, and stabilizing granularity;

[0057] Building a dynamic optimization model also requires setting the optimization objective of the particle swarm optimization algorithm within the model, including: maximizing the mixer's capacity. Minimize energy consumption Optimize product particle size and quality .

[0058] Specifically, energy consumption The calculation formula is: ,in This indicates the power consumption of the mixer under its current operating conditions. Indicates processing time. Power consumption of the mixer. Due to the influence of multiple factors, this embodiment uses the formula Approximate representation, where This indicates the power consumption of the mixer when it is unloaded. Indicates the mixer speed. This indicates the operating temperature of the mixer. These represent coefficients related to equipment characteristics, set empirically. The final energy consumption minimization objective function is: ,in, This indicates the volume of material in each batch. This indicates the processing speed of the mixer. It can be further refined into , represents the coefficient related to the characteristics of the mixer, which is set according to experience. is the material flow rate.

[0059] The calculation formula for production capacity is: , in production, determining the production capacity is not only about the efficiency of the mixer, but other factors also need to be considered: For example: 1. The coordination between equipment, such as conveyor belts, packaging systems, cooling systems, etc., whose speed may become a bottleneck and limit the overall production capacity. 2. The characteristics of different materials during the mixing process (such as viscosity, density, particle size) will affect the processing efficiency. 3. The equipment shows different energy efficiencies under different conditions (such as high rotational speed, different material flow rates), and the relationship between energy consumption and production capacity also needs to be considered. Considering the above factors, therefore, the minimum value function is used to find the link with the minimum energy efficiency in the production line, that is, the bottleneck equipment, in order to more realistically reflect the production capacity of the mixer. Among them, represents the material property adjustment factor, reflecting the impact of different materials on the mixing efficiency; represents the equipment energy efficiency adjustment factor, indicating the impact of energy efficiency on the processing speed. The above two can be set according to experience or obtained by fitting historical data; respectively represent the upper limit values of the production capacities of the conveyor belt, packaging, and cooling systems, represents the coefficient related to the characteristics of the mixer, which is set according to experience.

[0060] The calculation formula for particle size is: , where, The parameters in represent temperature, rotational speed, and flow rate respectively, is an empirical coefficient, and the goal is to control the particle size function within the target range: , where is the tolerance range of particle size.

[0061] Finally, comprehensively considering energy consumption, production capacity, and particle size targets, a multi-objective optimization function is constructed. The specific expression is:

[0062] ,

[0063] Among them, is the energy consumption, represents the reference energy consumption, that is, under standard production conditions, the typical energy consumption value per unit time or per unit batch; are the parameters to be optimized, is the temperature, is the rotational speed, is the flow rate; are the weight coefficients of different objectives, used to balance energy consumption, production capacity, and particle size; is the production capacity; is the particle size function, The target granularity.

[0064] Step S300: Construct a fitness function based on energy consumption, production capacity, and granularity;

[0065] During optimization, the dynamic optimization model, based on the particle swarm optimization algorithm, determines the fitness of each particle using a fitness function. The higher the fitness (i.e., the lower the fitness function value), the closer the particle is to the optimal solution.

[0066] The fitness function is expressed as follows:

[0067] ,

[0068] in, These are the weighting coefficients for different objectives. Indicates reference energy consumption. Let be the energy consumption value of particle i. Let i be the energy production value of particle i. The target particle size of the material. Let be the particle size value of particle i.

[0069] The particle swarm optimization algorithm adjusts the position and velocity of each particle based on the fitness function calculated for each particle, so that it moves closer to the global optimum.

[0070] Step S400: Based on the constraints, multi-objective optimization function, and fitness function, construct a dynamic optimization model using the particle swarm optimization algorithm;

[0071] Particle Swarm Optimization (PSO) is a swarm intelligence-based optimization algorithm suitable for solving multi-objective optimization problems. When constructing a dynamic optimization model based on PSO, it is necessary to define the constraints, objective function (such as the multi-objective optimization function in this embodiment), and fitness function.

[0072] First, particle swarm initialization is performed. (Set of parameters) This defines the search space for the particle swarm optimization algorithm. The initial particle swarm is generated based on historical production line data and empirically defined parameter ranges. The position of each particle is specified in the provided text. This represents a set of parameters (temperature, speed, flow rate), with the initial position represented as: ,in, Randomly generated from within a range of parameters. The velocity of each particle. Its direction of movement in the search space is determined by the initial velocity, which is expressed as: The initial speed value can be set to a small random number.

[0073] During the optimization process of the dynamic optimization model, particles adjust their velocity and position based on their current position, velocity, local optimal position (the optimal position experienced by each particle), and global optimal position (the optimal position of the entire particle swarm). Specifically, the velocity update formula is as follows:

[0074] ,

[0075] in, Inertial weights are used to control the inertia of particle motion. The learning factors represent the speed at which a particle approaches its historical best position and its global best position, respectively. This represents a random number, which is a random number between [0, 1], increasing the randomness of the algorithm; This represents the local optimal position of the particle; Indicates the current position of the particle.

[0076] The position update formula is as follows: .

[0077] After each particle's position is updated, its fitness value is recalculated according to the fitness function. If the current particle's fitness is better than its historical best value, the local optimum is updated; if the current particle's fitness is better than the global optimum, the global optimum is updated. This process searches for a better combination of production parameters in the parameter space.

[0078] Step S500: Collect data corresponding to each key parameter in real time to obtain real-time data, input all real-time data into the dynamic optimization model to obtain control parameters, and control the mixer according to the control parameters.

[0079] Various sensors are installed at key locations within the mixer to monitor critical parameters such as temperature, humidity, rotational speed, pressure, and flow rate, as well as material and / or product particle size during the production process. For example: temperature and humidity sensors are installed at key points inside and outside the mixer to collect real-time temperature and humidity information of the material and environment; rotational speed sensors are installed on the mixer drive system to accurately monitor changes in the mixer's rotational speed; flow meters are installed on the material conveying pipelines to detect the feed and discharge flow rates; pressure sensors are installed in the mixing chamber or conveying system to monitor and measure the pressure inside the mixer chamber in real time; and laser particle size analyzers are installed at the outlet of the mixed materials to monitor the particle size distribution of the product or material.

[0080] The data collected by the sensors is output as digital signals and transmitted to the central control system via industrial communication protocols to obtain real-time data and save it as historical data. For example, the data can also be preprocessed, such as by cleaning and filtering to remove noise and outliers.

[0081] All real-time data is input into the dynamic optimization model. The dynamic optimization model uses the PSO algorithm to dynamically adjust based on the real-time data, continuously optimizes the working state of the mixer, gradually finds the optimal parameter combination, obtains the control parameters, and then feeds the control parameters back to the mixer. The PLC control execution unit then adjusts the actions.

[0082] The control parameters in this embodiment include rotational speed, temperature, and material flow rate. The specific steps for controlling the mixer according to these parameters are as follows: Figure 2 As shown, it includes:

[0083] Step S510: Obtain the first PLC instruction based on the rotational speed in the control parameters, and input the first PLC instruction into the variable frequency motor control system that controls the mixer;

[0084] Step S520: Obtain the second PLC instruction based on the temperature in the control parameters, and control the heating device or cooling system according to the second PLC instruction;

[0085] Step S530: Obtain the third PLC instruction based on the material flow rate in the control parameters, and control the valve of the feed pipe according to the third PLC instruction.

[0086] Specifically, after each iteration of the PSO algorithm, the dynamic optimization model will derive the current optimal control parameters. ,in, To optimize the optimal speed, it is converted into a first PLC instruction, which is then input into the variable frequency motor control system that controls the mixer to adjust the speed of the mixer. To optimize the most effective temperature, it is converted into a second PLC instruction. The heating device or cooling system is controlled according to the second PLC instruction to keep the temperature of the material in the mixer within the optimal range. To optimize the obtained optimal material flow rate, it is converted into a third PLC instruction. This instruction is then used to adjust and control the valves in the feed pipe, maintaining the material flow rate at its optimal value and ensuring the mixer operates under optimal conditions. Converting the optimal rotational speed, most effective temperature, and optimal material flow rate into PLC instructions is a standard technique in this field and will not be elaborated upon further.

[0087] In summary, by constructing a dynamic optimization model based on the PSO algorithm, the PSO algorithm iterates continuously during the generation process. Each iteration recalculates the optimal control parameters based on the latest real-time sensor data (such as temperature, rotational speed, and material flow rate), thereby controlling the mixer. This allows for continuous monitoring of the actual operation of the production line and timely reflection of changes in production conditions.

[0088] This embodiment, after constructing the dynamic optimization model, also includes:

[0089] First, historical data is accumulated by collecting key parameters and granularity data. Feature extraction and data analysis are then performed on this historical data to calculate the correlation between key parameters and at least one of capacity, energy consumption, and granularity. The data analysis process can be achieved through the following methods:

[0090] 1. Conduct statistical analysis, such as analyzing the patterns of historical data using indicators like mean, variance, and standard deviation, to identify key parameters related to production efficiency, energy consumption, and product quality. For example:

[0091] With temperature Rotation speed ,flow and production capacity For example, collect T, N, F and Calculate the mean from time series data. ;variance : Standard deviation ,in Here, n represents the data points for each production cycle, and n is the total amount of data. Statistical analysis can reveal the average level and fluctuation range of these parameters. For example, large fluctuations in temperature T while flow rate F remains stable suggest that temperature may be the primary cause of fluctuations in production efficiency.

[0092] 2. Conduct correlation analysis, using methods such as Pearson correlation coefficient, to identify the correlation between various production parameters (such as temperature, rotation speed, flow rate, etc.) and production capacity, energy consumption, and particle size. That is:

[0093] Use the Pearson correlation coefficient formula to calculate the degree of linear correlation between two variables:

[0094] ,

[0095] Where X and Y represent temperatures respectively. Rotation speed ,flow and production capacity Data sequence, This represents the correlation coefficient, with values ​​ranging from -1 to 1. Assume that temperature T and production capacity are derived using the Pearson correlation coefficient formula. The correlation coefficient between them is The value indicates a strong positive correlation between the two, which means that temperature has a significant impact on production capacity.

[0096] 3. Perform principal component analysis to reduce the dimensionality of multidimensional production data, extracting the most representative features, reducing noise and redundancy, and understanding which parameters are crucial for production optimization. For example:

[0097] Dimensionality reduction was performed on multi-dimensional data such as temperature T, rotational speed N, flow rate F, pressure P, and particle size G to identify the main influencing factors. First, data standardization was performed so that the mean of each parameter was 0 and the standard deviation was 1. Then calculate the covariance matrix. The covariance matrix is ​​decomposed into eigenvalues ​​and eigenvectors. PCA analysis is used to assume the first principal component contributes 70% of the variance; it is likely mainly composed of temperature T and rotational speed N. This indicates that these two parameters are most important for production optimization, while the remaining parameters have a smaller impact on the results.

[0098] Then, based on the correlation between key parameters and capacity, energy consumption, and product granularity, the weights of key parameters with high correlation are adjusted, thereby adjusting the dynamic optimization model.

[0099] Specifically, firstly, based on the correlation, determine the coefficient terms that need to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted;

[0100] Assuming that correlation analysis shows temperature (T) has a significant impact on production capacity and energy consumption, the multi-objective optimization function can be expressed as: ,in, Let be the energy consumption function. For capacity function, This is the granularity function. The weighting coefficients are adjusted based on the correlation with temperature. When temperature changes have a significant impact, the weight of production capacity or energy consumption also increases, reflecting the importance of temperature to the mixer at this stage. It is a fixed weight independent of temperature and is applicable to targets related to product quality (such as particle size and composition uniformity).

[0101] Common adjustment models for weighting coefficients include: linear weighting adjustment, nonlinear weighting adjustment, dynamic adjustment based on standard deviation, and interval segmentation adjustment. The appropriate adjustment model should be selected based on the characteristics of the key parameter data.

[0102] If historical data shows that the relationship between temperature T and production capacity and energy consumption is approximately linear, then... Perform linear adjustment: ,in: The coefficients are obtained through regression analysis, fitted based on the correlation between temperature and target values. When T increases, if its impact on production capacity is significant, The model will be adjusted accordingly to focus more on production capacity at high temperatures.

[0103] If the relationship between temperature and production capacity / energy consumption is non-linear (e.g., exhibiting an exponential or logarithmic trend), then a non-linear weighting relationship can be constructed. For example, an exponential relationship: When the temperature rises or falls significantly, it can respond more sensitively to the weights, making it particularly suitable for situations where temperature changes lead to a significant increase in energy consumption or fluctuations in production capacity.

[0104] Temperature fluctuations can also be expressed using standard deviation. This is used for measurement. A higher standard deviation indicates greater temperature fluctuations, and the dynamic changes in temperature can be incorporated into the weighting adjustment. Where: c is the smoothing coefficient, used to prevent the weights from increasing unreasonably when the standard deviation is close to 0. These are the basic weights, determined through experimental and empirical data.

[0105] Different weights can also be assigned to different temperature ranges. If temperature has a greater impact on production capacity and energy consumption within certain ranges, then weights can be set in segments:

[0106] ,

[0107] This approach allows for precise control over the optimization focus of the model within different temperature ranges, which helps to address situations where sudden temperature changes or specific temperature ranges significantly impact production capacity and energy consumption.

[0108] After determining the coefficients to be adjusted and the adjustment model, the coefficients are then adjusted based on historical data. It's important to emphasize that historical data can also be data collected over a period of time prior to the current moment. In other words, after the dynamic optimization model is built, the weight coefficients can be adjusted immediately based on historical data, making the multi-objective optimization function more accurate; alternatively, the weight coefficients can be adjusted during production line operation based on historical data accumulated over a recent period.

[0109] During production line operation, the PSO algorithm model also possesses a self-learning mechanism. By continuously learning from historical data, it can gradually improve the parameter adjustment strategies within the PSO model, enabling it to better adapt to complex and ever-changing production conditions. This process can be achieved through data-driven model updates. Control parameters in the PSO model (such as inertia weights) Learning factors (etc.) will be gradually optimized as data accumulates. The self-learning mechanism mainly includes:

[0110] 1. Dynamic weight adjustment

[0111] The system adjusts the weights of the multi-objective optimization function in the dynamic optimization model based on historical production results. For example, when historical data shows that energy consumption has a significant impact on production line costs, the system will automatically increase the weight of energy consumption optimization.

[0112] The formula for updating the weights is: ,in This is the expected production result. It is the actual result. It is the learning rate.

[0113] 2. Adaptive updating of parameter adjustment strategy

[0114] As production data increases, the movement of the particle swarm in the PSO algorithm can be improved by training with historical data. For example, machine learning models such as random forests or gradient boosting trees can be used to automatically identify the optimal parameter combinations under certain conditions, thereby improving the behavior of particles during the search process. Based on the above data accumulation, analysis, and learning, the overall performance of the dynamic optimization model can be gradually improved.

[0115] In some embodiments, the following method is also used to optimize the dynamic optimization model:

[0116] 1. Model retraining based on historical data

[0117] Every so often (e.g., every 3 months or every production cycle), the dynamic optimization model is rebuilt based on historically accumulated production data. This includes: adjusting the initial particle swarm, i.e., determining the initial values ​​of the particle swarm based on historical data to make the particle swarm closer to the actual optimal solution for production, thereby accelerating the search process; and improving the multi-objective optimization function, i.e., updating the weights of each item in the multi-objective optimization function in combination with the latest production conditions and data, so that the optimization of energy consumption, capacity, and granularity are more in line with actual production needs.

[0118] 2. Update parameters based on evaluation results

[0119] During each production process, the performance of the dynamic optimization model is evaluated. For example, the results of each run are recorded, and the average and variance of the optimal solution are calculated to assess the stability and consistency of the algorithm. By evaluating the impact of parameters on production targets (such as energy consumption and capacity), the following PSO parameters are automatically adjusted: inertia weights. That is, if it is found that the system is difficult to find the global optimum under certain production conditions, the inertia weight is appropriately increased or decreased so that the particle swarm can explore a larger or smaller parameter space; learning factor That is, when the local optimal solution and the global optimal solution deviate significantly, the learning factor is adjusted appropriately to make the particles approach the global optimal solution more quickly.

[0120] In some examples, production strategies are also dynamically adjusted based on optimization results. Specifically, after iterative optimization, the dynamic optimization model dynamically adjusts production strategies based on the latest optimal parameter combination. For example, adjusting material ratios involves automatically adjusting the material ratios based on historical data to identify the significant impact of different material ratios on product particle size; and optimizing temperature control strategies involves discovering the optimal temperature range for production within a specific temperature range through self-learning and adjusting the operating status of heating or cooling equipment in real time.

[0121] Therefore, through continuous data accumulation and analysis, the dynamic optimization model achieves self-learning and gradually optimizes the performance of the PSO algorithm. Data-driven adaptive adjustment, reinforcement learning feedback, and rolling optimization mechanisms enable the PSO algorithm to dynamically adapt to changes in the production process, thereby achieving an optimal balance between energy consumption, production capacity, and product quality.

[0122] like Figure 3 As shown, based on the above-mentioned mixer control method for battery cathode material production lines, this embodiment of the invention discloses a mixer control device for battery cathode material production lines, comprising:

[0123] The model building module 600 is used to determine constraints based on various key parameters related to capacity, energy consumption, and granularity; construct a multi-objective optimization function with the objectives of maximizing mixer capacity, minimizing energy consumption, and stabilizing granularity; construct a fitness function based on energy consumption, capacity, and granularity; and construct a dynamic optimization model based on the particle swarm optimization algorithm according to the constraints, the multi-objective optimization function, and the fitness function.

[0124] The real-time control module 610 is used to collect data corresponding to each of the key parameters in real time, obtain real-time data, input all the real-time data into the dynamic optimization model to obtain control parameters, and control the mixer according to the control parameters.

[0125] In some embodiments, the expression of the multi-objective optimization function is:

[0126] ,

[0127] in, For energy consumption, Indicates reference energy consumption; The parameters to be optimized are... For temperature, For speed, For traffic; These are weighting coefficients for different objectives, used to balance energy consumption, production capacity, and granularity; For production capacity; For granularity function, The target granularity.

[0128] like Figure 4 As shown, an embodiment of the present invention discloses an electronic device, including a memory 401 storing executable program code and a processor 402 coupled to the memory 401;

[0129] The processor 402 calls the executable program code stored in the memory 401 to execute the mixer control method for the battery cathode material production line described in the above embodiments.

[0130] This invention also discloses a computer-readable storage medium storing a computer program that causes a computer to execute the mixing machine control method for the battery cathode material production line described in the above embodiments.

[0131] The purpose of the above embodiments is to reproduce and derive the technical solution of the present invention by way of example, and to fully describe the technical solution, purpose and effect of the present invention. The purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosure of the present invention, and not to limit the scope of protection of the present invention.

[0132] The above embodiments are not an exhaustive list based on the present invention, and there may be many other embodiments not listed. Any substitutions and improvements made without departing from the concept of the present invention are within the protection scope of the present invention.

Claims

1. A method for controlling the mixer in a battery cathode material production line, characterized in that, include: Constraints are determined based on key parameters related to capacity, energy consumption, and particle size. A multi-objective optimization function is constructed with the objectives of maximizing mixer capacity, minimizing energy consumption, and stabilizing particle size. A fitness function is constructed based on energy consumption, production capacity, and granularity. Based on the constraints, the multi-objective optimization function, and the fitness function, a dynamic optimization model is constructed using the particle swarm optimization algorithm. Real-time data is collected for each of the key parameters to obtain real-time data. All the real-time data is input into the dynamic optimization model to obtain control parameters. The mixer is then controlled according to the control parameters. The expression for the multi-objective optimization function is: Among them, E consumption (x) represents energy consumption, E ref This represents the reference energy consumption; x = [T, N, F] are the parameters to be optimized, where T is temperature, N is rotational speed, and F is flow rate; w1, w2, and w3 are weighting coefficients for different objectives, used to balance energy consumption, production capacity, and granularity; P output (x) represents the production capacity; G(T, N, F) is the granularity function, G target Target granularity; The expression for the granularity function is: Where T is temperature, N is rotational speed, F is flow rate, and α1, α2, α3 are coefficients; After constructing the dynamic optimization model, it also includes: Based on historical data of the key parameters, calculate the correlation between the key parameters and at least one of production capacity, energy consumption, and particle size; The dynamic optimization model is adjusted based on the correlation. The step of adjusting the dynamic optimization model based on the correlation includes: Based on the correlation, determine the coefficient terms that need to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted; Adjust the coefficient terms according to the adjustment model; Energy consumption E consumption The formula for calculating (x) is: E consumption (x)=P mix ·T proc , where P mix T represents the power consumption of the mixer in its current operating state. proc Indicates processing time; power consumption P of the mixer. mix =P base +c1·N 2 +c2·T, where P base The power consumption of the mixer when it is unloaded is represented by N, the speed of the mixer is represented by T, the operating temperature of the mixer is represented by c1c2, and the coefficients related to the characteristics of the equipment are represented by c1c2. The formula for calculating production capacity is Q. output =min((k1·N+k2·F)·α material ·β efficiency Q transfer Q wrap Q cold ), where α material This represents the material property adjustment factor, reflecting the impact of different materials on mixing efficiency; β efficiency Q represents the equipment energy efficiency adjustment factor, indicating the impact of energy efficiency on processing speed. transfer Q wrap Q cold These represent the upper capacity limits of the conveyor belt, packaging, and cooling systems, respectively; k1 and k2 represent coefficients related to the characteristics of the mixer; N represents the mixer speed; and F represents the flow rate. The expression for the fitness function is: Where w1, w2, and w3 are the weight coefficients for different objectives, E ref E represents the reference energy consumption. i Let P be the energy consumption value of particle i. i Let G be the energy production value of particle i. target For the target granularity, G i Let be the particle size value of particle i.

2. The mixing machine control method for a battery cathode material production line as described in claim 1, characterized in that, The control parameters include rotational speed, temperature, and material flow rate. Controlling the mixer according to these control parameters includes: Based on the rotational speed in the control parameters, a first PLC instruction is obtained, and the first PLC instruction is input into the variable frequency motor control system that controls the mixer. Based on the temperature in the control parameters, a second PLC instruction is obtained, and the heating device or cooling system is controlled according to the second PLC instruction; Based on the material flow rate in the control parameters, a third PLC instruction is obtained, and the valve of the feed pipe is controlled according to the third PLC instruction.

3. A mixing machine control device for a battery cathode material production line, characterized in that, include: The model building module is used to determine constraints based on various key parameters related to capacity, energy consumption, and granularity. A multi-objective optimization function is constructed with the goals of maximizing mixer capacity, minimizing energy consumption, and stabilizing granularity; a fitness function is constructed based on energy consumption, capacity, and granularity. Based on the constraints, the multi-objective optimization function, and the fitness function, a dynamic optimization model is constructed using the particle swarm optimization algorithm. The real-time control module is used to collect data corresponding to each of the key parameters in real time, obtain real-time data, input all the real-time data into the dynamic optimization model to obtain control parameters, and control the mixer according to the control parameters; The expression for the multi-objective optimization function is: Among them, E consumption (x) represents energy consumption, E ref This represents the reference energy consumption; x = [T, N, F] are the parameters to be optimized, where T is temperature, N is rotational speed, and F is flow rate; w1, w2, and w3 are weighting coefficients for different objectives, used to balance energy consumption, production capacity, and granularity; P output (x) represents the production capacity; G(T, N, F) is the granularity function, G target Target granularity; The expression for the granularity function is: Where T is temperature, N is rotational speed, F is flow rate, and α1, α2, α3 are coefficients; After constructing the dynamic optimization model, it also includes: Based on historical data of the key parameters, calculate the correlation between the key parameters and at least one of production capacity, energy consumption, and particle size; The dynamic optimization model is adjusted based on the correlation. The step of adjusting the dynamic optimization model based on the correlation includes: Based on the correlation, determine the coefficient terms that need to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted; Adjust the coefficient terms according to the adjustment model; Energy consumption E consumption The formula for calculating (x) is: E consumption (x)=P mix ·T proc , where P mix T represents the power consumption of the mixer in its current operating state. proc Indicates processing time; power consumption P of the mixer. mix =P base +c1·N 2 +c2·T, where P base The power consumption of the mixer when it is unloaded is represented by N, the speed of the mixer is represented by T, the operating temperature of the mixer is represented by c1c2, and the coefficients related to the characteristics of the equipment are represented by c1c2. The formula for calculating production capacity is Q. output =min((k1·N+k2·F)·α material ·β efficiency Q transfer Q wrap Q cold ), where α material This represents the material property adjustment factor, reflecting the impact of different materials on mixing efficiency; β efficiency Q represents the equipment energy efficiency adjustment factor, indicating the impact of energy efficiency on processing speed. transfer Q wrap Q cold These represent the upper capacity limits of the conveyor belt, packaging, and cooling systems, respectively; k1 and k2 represent coefficients related to the characteristics of the mixer; N represents the mixer speed; and F represents the flow rate. The expression for the fitness function is: Where w1, w2, and w3 are the weight coefficients for different objectives, E ref E represents the reference energy consumption. i Let P be the energy consumption value of particle i. i Let G be the energy production value of particle i. target For the target granularity, G i Let be the particle size value of particle i.

4. An electronic device, characterized in that, It includes a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the mixer control method of the battery cathode material production line according to claim 1 or 2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program causes a computer to perform the mixing machine control method for a battery cathode material production line as described in claim 1 or 2.

Images