Mixing machine control method, device and equipment of battery positive electrode material production line and medium

Abstract

The invention belongs to the technical field of industrial control, and discloses a mixing machine control method, device, equipment and medium of a battery positive electrode material production line, and the method comprises the following steps: determining constraint conditions according to each key parameter related to productivity, energy consumption and granularity; constructing a multi-objective optimization function by taking the productivity maximization, the energy consumption minimization and the granularity stability of the mixing machine as objectives; constructing a fitness function according to the energy consumption, the productivity and the granularity; constructing a dynamic optimization model based on a particle swarm optimization algorithm according to the constraint condition, the multi-objective optimization function and the fitness function; and acquiring 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. And the efficiency and the product quality of a battery positive electrode material production line can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of industrial control technology, and specifically relates to a mixer control method, device, equipment and medium for a battery positive electrode material production line. Background Art

[0002] Battery cathode materials (such as bismuth oxide , cobalt oxide CoO2, lithium iron phosphate LiFePO4, etc.), 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 positive electrode materials, resulting in higher and higher requirements for the purity, particle size, and morphology control of battery positive electrode materials.

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

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

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

[0006] The object of the present invention is to provide a mixer control method, device, equipment and storage medium for a battery positive electrode material production line, which can improve the efficiency and product quality of the battery positive electrode material production line.

[0007] The first aspect of the present invention discloses a mixer control method for a battery positive electrode material production line, comprising: Determine constraints based on 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 particle size; Construct a fitness function based on energy consumption, capacity, and granularity; According to the constraint conditions, the multi-objective optimization function and the fitness function, a dynamic optimization model is constructed based on a particle swarm optimization algorithm; The data corresponding to each of the key parameters are collected in real time to obtain real-time data, all the real-time data are input into the dynamic optimization model to obtain control parameters, and the mixer is controlled according to the control parameters.

[0008] In some embodiments, the expression of the multi-objective optimization function is: , in, For energy consumption, represents the reference energy consumption; is the parameter to be optimized, For temperature, For the speed, For flow; is the weight coefficient of different objectives, used to balance energy consumption, capacity and granularity; For production capacity; is the particle size function, is the target particle size.

[0009] In some embodiments, after the dynamic optimization model is constructed, the method further includes: Calculating, based on historical data of the key parameter, a correlation between the key parameter and at least one of production capacity, energy consumption, and particle size; The dynamic optimization model is adjusted according to the correlation.

[0010] In some embodiments, adjusting the dynamic optimization model according to the correlation includes: According to the correlation, determining the coefficient items to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted; The coefficient terms are adjusted according to the adjustment model.

[0011] In some embodiments, the fitness function is expressed as: , in, are the weight coefficients of different objectives, represents the reference energy consumption, is the energy consumption value of particle i, is the production capacity of particle i, is the target particle size, is the particle size value of particle i.

[0012] In some embodiments, the control parameters include rotation speed, temperature, and material flow rate, and controlling the mixer according to the control parameters includes: Obtaining a first PLC instruction according to the rotation speed in the control parameter, and inputting the first PLC instruction into a variable frequency motor control system for controlling the mixer; Obtaining a second PLC instruction according to the temperature in the control parameter, and controlling the heating device or the cooling system according to the second PLC instruction; A third PLC instruction is obtained according to the material flow in the control parameter, and the valve of the feed pipeline is controlled according to the third PLC instruction.

[0013] The second aspect of the present invention discloses a mixer control device for a battery positive electrode material production line, comprising: A model building module is used to determine constraint conditions according to various key parameters related to production capacity, energy consumption and particle size; construct a multi-objective optimization function with the goals of maximizing the production capacity of the mixer, minimizing energy consumption and stabilizing the particle size; construct a fitness function according to energy consumption, production capacity and particle size; and construct a dynamic optimization model based on the particle swarm optimization algorithm according to the constraint conditions, the multi-objective optimization function and the fitness function; 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, obtain control parameters, and control the mixer according to the control parameters.

[0014] In some embodiments, the expression of the multi-objective optimization function is: , in, For energy consumption, represents the reference energy consumption; is the parameter to be optimized, For temperature, For the speed, For flow; is the weight coefficient of different objectives, used to balance energy consumption, capacity and granularity; For production capacity; is the particle size function, is the target particle size.

[0015] The third aspect of the present invention discloses an electronic device, comprising 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 positive electrode material production line disclosed in the first aspect.

[0016] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute the mixer control method for a battery positive electrode material production line disclosed in the first aspect.

[0017] The beneficial effect of the present invention is that by determining the constraint conditions through production capacity, energy consumption and granularity, constructing a multi-objective optimization function and a fitness function, a dynamic optimization model is constructed based on a particle swarm optimization algorithm, key parameters in the production process are monitored, and the particle swarm optimization algorithm is combined to achieve real-time production capacity optimization of the mixer and intelligent control of the global production line. The problem of mismatch between the production capacity of the mixer and the efficiency of the production line is solved; the production line efficiency and product consistency are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein show specific examples of the technical solutions described in the present invention, and together with the specific implementation methods, constitute a part of the specification, and are used to explain the technical solutions, principles and effects of the present invention.

[0019] Unless otherwise specified or defined, the same reference numerals in different drawings represent the same or similar technical features, and the same or similar technical features may also be represented by different reference numerals.

[0020] Figure 1 It is a flow chart of a mixer control method for a battery positive electrode material production line disclosed in an embodiment of the present invention; Figure 2 is a flow chart of controlling a mixer according to control parameters according to an embodiment of the present invention; Figure 3 2 is a schematic structural diagram of a mixer control device for a battery positive electrode material production line according to an embodiment of the present invention; Figure 4 It is a structural schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art. In combination with the technical solution of the present invention in a realistic scenario, all technical and scientific terms used herein may also have meanings corresponding to the purpose of implementing the technical solution of the present invention. The "first, second..." used herein is only used to distinguish the names and does not represent a specific quantity or order. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0022] It should be noted that when a component is considered to be "fixed to" another component, it can be directly fixed to the other component or there can be a central component; when an component is considered to be "connected to" another component, it can be directly connected to the other component or there can be a central component at the same time; when an component is considered to be "installed on" another component, it can be directly installed on the other component or there can be a central component at the same time. When an component is considered to be "set on" another component, it can be directly set on the other component or there can be a central component at the same time.

[0023] Unless otherwise specified or defined, the "said" and "the" used in this document refer to the technical features or technical contents mentioned or described before the corresponding position, and the technical features or technical contents may be the same as or similar to the technical features or technical contents mentioned therein. In addition, the terms "including" and "having" and any variations thereof used in this document are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0024] In order to optimize the production process of battery positive electrode materials, improve production efficiency, reduce energy consumption, and ensure product consistency and high quality, this invention focuses on the optimization between the mixer capacity and production line control in the production line. By monitoring key parameters in the production process (such as temperature, humidity, speed, flow, pressure, material particle size, etc.), combined with the particle swarm optimization algorithm (PSO), the real-time capacity optimization of the mixer and the intelligent control of the global production line are realized. Through real-time data collection and dynamic optimization models, the problem of mismatch between mixer capacity and production line efficiency is solved; production line efficiency and product consistency are improved, providing innovative solutions for the production of high-quality battery positive electrode materials.

[0025] The embodiment of the present invention discloses a mixer control method for a bismuth oxide production line, which can be implemented by computer programming as an independent control system or as a part of a control system in a bismuth oxide feeding and conveying system. The execution subject of the method can be an electronic device such as a computer, a laptop, a tablet computer, or a control chip embedded in an electronic device, and the present invention is not limited to this.

[0026] In order to facilitate the understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0027] like Figure 1 As shown, the method comprises the following steps: Step S100: determining constraint conditions according to various key parameters related to production capacity, energy consumption and granularity; There are many parameters related to production capacity, energy consumption and particle size (material particle size and / or product particle size). Among these parameters, one or more of the parameters that have a greater impact on production capacity, energy consumption and particle size are selected as key parameters. In this embodiment, for the bismuth oxide production line, the key parameters determined include: temperature, humidity, rotation speed, flow rate, which are the main parameters for mixer and production line control. These key parameters, together with energy consumption and material particle size, are used as the search dimensions of the particle swarm algorithm (PSO) used in the dynamic optimization model.

[0028] In the particle swarm optimization process, it is necessary to ensure that the solution searched by the particles is a feasible solution and does not violate the safety and quality requirements of the production process. Therefore, it is necessary to set the constraints of the dynamic optimization model, that is, to determine the constraints corresponding to each key parameter. Specifically: Temperature (T) is the key parameter that affects the reaction rate and mixing effect. The temperature constraint is ; The mixer speed (N) directly affects the mixing uniformity and efficiency. The speed constraint is ;The material flow rate (F) determines the amount of material entering the mixer per unit time. The flow rate constraint is ; Humidity (H) affects material fluidity and mixing uniformity. The humidity constraint is ; Material particle size (G) is a key quality indicator of the final product. It is affected by temperature, humidity, rotation speed, flow rate, etc. The constraints of material particle size are: , is the target particle size, is the tolerance range of particle size; energy consumption (E) is the equipment energy consumption of the mixer, which is related to the speed, temperature, etc. The constraint condition of energy consumption is Among the above constraints, the maximum and minimum values ​​need to be set based on experience, referring to the specific products of the battery positive electrode material production line and the parameters of the mixer equipment in the production line.

[0029] In some embodiments, cluster analysis can be performed to analyze the parameter combinations of different production batches through clustering algorithms such as K-means to find out which parameters are most important under similar production conditions. For example, suppose we have multiple production batches, each with different temperature T, speed N, flow F and corresponding production capacity. Data, using K-means clustering algorithm, historical data is divided into k groups. First, define the objective function of K-means: ,in is the ith cluster, is the cluster center, and X is the data point. K-means clustering divides historical data into several groups (clusters), each corresponding to similar production conditions. Suppose it is found 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 are the key parameter combinations.

[0030] Step S200: constructing a multi-objective optimization function with the objectives of maximizing the mixer's production capacity, minimizing energy consumption, and stabilizing particle size; To build a dynamic optimization model, it is also necessary to set the optimization goals of the particle swarm algorithm in the dynamic optimization model, including: maximizing the mixer capacity , minimize energy consumption , optimize product particle size and quality .

[0031] Specifically, energy consumption The calculation formula is: ,in Indicates the power consumption of the mixer in the current working state. Indicates the processing time. Power consumption of the mixer Affected by multiple factors, this embodiment uses the formula Approximately, Indicates the power consumption of the mixer when it is unloaded. Indicates the mixer speed, Indicates the operating temperature of the mixer, represents the coefficient related to the equipment characteristics and is set based on experience. The final energy consumption minimization objective function is ,in, Indicates the volume of material in each batch, Indicates the processing speed of the mixer, Can be further refined into , The coefficients representing the characteristics of the mixer are set based on experience. is the material flow rate.

[0032] The calculation formula for production capacity is: In production, the efficiency of the mixer is not the only factor that determines production capacity. Other factors also need to be considered: for example: 1. Coordination between equipment, such as conveyor belts, packaging systems, cooling systems, etc., their speed may become a bottleneck and limit 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. Equipment exhibits different energy efficiency under different conditions (such as high speed, different material flow rates), and the relationship between energy consumption and production capacity also needs to be considered. Taking the above factors into consideration, the minimum function is used to find the link with the lowest energy efficiency in the production line, that is, the bottleneck equipment, in order to more truly reflect the production capacity of the mixer. Among them, Indicates the material property adjustment factor, reflecting the impact of different materials on mixing efficiency; It represents the equipment energy efficiency adjustment factor, which indicates the impact of energy efficiency on processing speed. The above two items can be set based on experience or obtained by fitting historical data; They represent the upper limits of the production capacity of the conveyor belt, packaging, and cooling systems respectively. This is a coefficient related to the mixer characteristics and is set based on experience.

[0033] The particle size calculation formula is: ,in, The parameters in represent temperature, speed and flow rate respectively. is the empirical coefficient, the goal is to transform the particle size function Stay within target range: ,in is the tolerance range of the particle size.

[0034] Finally, considering energy consumption, production capacity and granularity targets comprehensively, a multi-objective optimization function is constructed. The specific expression is: , in, For energy consumption, Indicates reference energy consumption, i.e., the typical energy consumption per unit time or per unit batch under standard production conditions; is the parameter to be optimized, For temperature, For the speed, For flow; is the weight coefficient of different objectives, used to balance energy consumption, capacity and granularity; For production capacity; is the particle size function, is the target particle size.

[0035] Step S300: constructing a fitness function according to energy consumption, capacity and granularity; When the dynamic optimization model is optimized, according to the particle swarm algorithm, the fitness of each particle is determined by the fitness function The higher the fitness (i.e. the lower the fitness function value), the closer the particle is to the optimal solution.

[0036] The expression of the fitness function is: , in, are the weight coefficients of different objectives, represents the reference energy consumption, is the energy consumption value of particle i, is the production capacity of particle i, is the target particle size of the material, is the particle size value of particle i.

[0037] The particle swarm algorithm adjusts the position and speed of particles according to the fitness of each particle calculated by the fitness function to make them approach the global optimal solution.

[0038] Step S400: constructing a dynamic optimization model based on a particle swarm optimization algorithm according to constraints, multi-objective optimization functions and fitness functions; Particle Swarm Optimization (PSO) is an optimization algorithm based on swarm intelligence, which is suitable for solving multi-objective optimization problems. When building a dynamic optimization model based on the PSO, it is necessary to clarify the constraints, the objective function (such as the multi-objective optimization function of this embodiment) and the fitness function.

[0039] First, initialize the particle swarm. The set of parameters is the search space of the particle swarm optimization algorithm. The generation of the initial particle swarm is based on the historical data of the production line and the parameter range set by experience. Represents a set of parameters (temperature, speed, flow), and the initial position is expressed as: ,in, Randomly generated from the range of each parameter. The speed of each particle Determine its moving direction in the search space, and the initial velocity is expressed as: , the initial value of the speed can be set to a smaller random number.

[0040] During the optimization process of the dynamic optimization model, particles adjust their speed and position according to their current position, speed, local optimal position (the optimal position experienced by each particle) and global optimal position (the optimal position of the entire particle group). Specifically, the speed update formula is: , in, is the inertia weight, which is used to control the inertia of particle motion; are learning factors, which represent the speed at which the particle approaches its historical optimal position and the global optimal position respectively; Represents a random number, which is a random number between [0, 1], which increases the randomness of the algorithm; represents the local optimal position of the particle; Indicates the current position of the particle.

[0041] The position update formula is as follows: .

[0042] After the position of each particle is updated, its fitness value is recalculated according to the fitness function. If the fitness of the current particle is better than its historical optimal value, the local optimal value is updated; if the fitness of the current particle is better than the global optimal value, the global optimal value is updated. Thus, a better combination of production parameters is searched in the parameter space.

[0043] Step S500: collect data corresponding to each key parameter in real time to obtain real-time data, input all real-time data into a dynamic optimization model to obtain control parameters, and control the mixer according to the control parameters.

[0044] Various sensors are installed at key locations of the mixer to monitor key parameters such as temperature, humidity, speed, pressure, flow rate, and material particle size and / or product particle size during the production process. For example: temperature sensors and humidity sensors are installed at key points inside and outside the mixer to collect temperature and humidity information of the material and environment in real time; speed sensors are installed on the mixer drive system to accurately monitor the speed changes of the mixer; flow meters are installed on the material conveying pipeline to detect the flow rate of feed and discharge; pressure sensors are installed in the mixing chamber or conveying system to monitor the pressure inside the mixer chamber in real time; laser particle size analyzers are installed at the outlet of the mixed material to monitor the particle size distribution of the product or material.

[0045] The data collected by the sensor is output in the form of a digital signal, and the data is transmitted to the central control system through an industrial communication protocol to obtain real-time data and save it as historical data. For example, the data can also be pre-processed, such as cleaning and filtering to remove noise and abnormal values.

[0046] All real-time data are input into the dynamic optimization model, and the PSO algorithm is used in the dynamic optimization model to make dynamic adjustments based on the real-time data, continuously optimize the working state of the mixer, gradually find the optimal parameter combination, obtain the control parameters, and then feed the control parameters back to the mixer, and adjust the action through the PLC control execution unit.

[0047] The control parameters of this embodiment include rotation speed, temperature, and material flow rate. The specific steps of controlling the mixer according to the control parameters are as follows: Figure 2 As shown, including: Step S510: obtaining a first PLC instruction according to the rotation speed in the control parameter, and inputting the first PLC instruction into a variable frequency motor control system for controlling the mixer; Step S520: obtaining a second PLC instruction according to the temperature in the control parameter, and controlling the heating device or the cooling system according to the second PLC instruction; Step S530: Obtain a third PLC instruction according to the material flow in the control parameter, and control the valve of the feed pipeline according to the third PLC instruction.

[0048] Specifically, after the PSO algorithm completes each iteration, the dynamic optimization model will obtain the current optimal control parameters ,in, The optimized optimal speed is converted into a first PLC instruction, and the first PLC instruction is input into a variable frequency motor control system for controlling the mixer to adjust the speed of the mixer; The most effective temperature is optimized and converted into a second PLC instruction, and 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; In order to optimize the obtained optimal material flow, it is converted into a third PLC instruction, and the valve of the feed pipeline is adjusted and controlled according to the third PLC instruction to keep the material flow at the optimal value and ensure that the mixer works under the best conditions. Among them, converting the optimal speed, the most effective temperature, and the optimal material flow into PLC instructions is a conventional technical means in this field and will not be repeated here.

[0049] In summary, by building a dynamic optimization model based on the PSO algorithm, the PSO algorithm is continuously iterated during the generation process, and each iteration will recalculate the optimal control parameters based on the latest real-time sensor data (such as temperature, speed, material flow, etc.), thereby controlling the mixer. It can continuously monitor the actual operation of the production line and promptly reflect changes in production conditions.

[0050] After building the dynamic optimization model, this embodiment further includes: First, the key parameters and granularity data are accumulated to form historical data, and feature extraction and data analysis are performed on the historical data to calculate the correlation between the key parameters and at least one of the capacity, energy consumption and granularity. The data analysis process can be achieved through the following means: 1. Conduct statistical analysis, such as analyzing the changing patterns of historical data through indicators such as mean, variance, and standard deviation, and find out the key parameters related to production efficiency, energy consumption, and product quality. For example: By temperature , speed ,flow and production capacity For example, collect T, N, F and Time series data, calculate the mean ;variance : ; Standard deviation ,in is the data point of each production cycle, and n is the total amount of data. Through statistical analysis, we can understand the average level and fluctuation range of the above parameters. For example, if the temperature T fluctuates greatly and the flow F is stable, it can be concluded that temperature may be the main reason for the fluctuation of production efficiency.

[0051] 2. Carry out correlation analysis, using methods such as Pearson correlation coefficient, to find out the correlation between various production parameters (such as temperature, speed, flow rate, etc.) and production capacity, energy consumption and particle size. That is: Use the Pearson correlation coefficient formula to calculate the linear correlation between two variables: , Where X and Y represent the temperature , speed ,flow and production capacity The data sequence, Represents the correlation coefficient, and its value range is [-1,1]. Assume that the temperature T and capacity are obtained according to the Pearson correlation coefficient formula. The correlation coefficient between , indicating that the two have a strong positive correlation, which means that temperature has a greater impact on production capacity.

[0052] 3. Perform principal component analysis to reduce the dimensionality of multi-dimensional production data, extract several most representative features, reduce noise and redundancy, and understand which parameters are critical to production optimization. For example: Reduce the multidimensional data such as temperature T, speed N, flow F, pressure P and particle size G to find out the main influencing factors. First, standardize the data so that the average value of each parameter is 0 and the standard deviation is 1: , then calculate the covariance matrix , perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors. Through PCA analysis, assuming that the variance contribution rate of the first principal component is 70%, it may be mainly composed of temperature T and speed N, which indicates that these two parameters are most important for production optimization, and the remaining parameters have little effect on the results.

[0053] Then, according to the correlation between the key parameters and the production capacity, energy consumption and product particle size, the weights of the key parameters with high correlation are adjusted, thereby adjusting the dynamic optimization model.

[0054] Specifically, firstly, the coefficient items to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted are determined according to the correlation; Assuming that temperature (T) has a significant impact on production capacity and energy consumption according to correlation analysis, the multi-objective optimization function can be expressed as: ,in, is the energy consumption function, is the capacity function, is a function of particle size. It is the weight coefficient adjusted according to the correlation of temperature. When the temperature change has a greater impact, the weight of production capacity or energy consumption will also increase, reflecting the importance of temperature to the mixer at this stage. It is a fixed weight that is independent of temperature and is applicable to objectives related to product quality (such as particle size and composition uniformity).

[0055] Common adjustment models for weight coefficients include: linear weight adjustment, nonlinear weight adjustment, dynamic adjustment based on standard deviation, and interval segmentation adjustment. Select the appropriate adjustment model based on the characteristics of the key parameter data.

[0056] If historical data show that the relationship between temperature T and production capacity and energy consumption is approximately linear, To make a linear adjustment: ,in: is the coefficient obtained through regression analysis, which is obtained by fitting based on the correlation between temperature and target value. When T increases, if its impact on production capacity is significant, Adjustments will be made accordingly so that the model pays more attention to production capacity at high temperatures.

[0057] If the relationship between temperature and production capacity and energy consumption is nonlinear (such as showing an exponential or logarithmic trend), a nonlinear weight relationship can be constructed. For example, an exponential relationship: , it can respond more sensitively to the weight when the temperature rises or drops significantly, which is especially suitable for situations where temperature changes lead to significant increases in energy consumption or fluctuations in production capacity.

[0058] The temperature fluctuation can also be expressed as If the standard deviation is high, it means that the temperature fluctuates greatly, and the dynamic change of temperature can be incorporated into the weight adjustment: , where: c is the smoothing coefficient, which is used to prevent the weight from increasing unreasonably when the standard deviation is close to 0. is the basic weight, determined through experiments and empirical data.

[0059] You can also set different weights for different temperature ranges. If the temperature has a greater impact on production capacity and energy consumption in certain ranges, you can set the weights in sections: , This method can accurately control the optimization focus of the model in different temperature ranges, which helps to deal with situations where sudden temperature changes or specific temperature ranges have a significant impact on production capacity and energy consumption.

[0060] After determining the coefficient items and adjustment model to be adjusted, adjust the coefficient items according to historical data. It should be emphasized that historical data can also be data collected some time before the current moment. In other words, after the dynamic optimization model is built, the weight coefficient items can be adjusted immediately according to historical data, so that the multi-objective optimization function is more accurate; the weight coefficient items can also be adjusted during the operation of the production line according to the historical data accumulated in the recent period.

[0061] During the operation of the production line, the PSO algorithm model also has a self-learning mechanism. By continuously learning from historical data, the parameter adjustment strategy in the PSO model can be gradually improved to better adapt to complex and changing production conditions. This process can be updated through data-driven model updates. The control parameters in the PSO model (such as inertia weight , learning factor etc.) will be gradually optimized as data accumulates. The self-learning mechanism mainly includes: 1. Dynamic weight adjustment The weights of the multi-objective optimization functions in the dynamic optimization model are adjusted according to historical production results. For example, when historical data shows that energy consumption has a greater impact on production line costs, the system will automatically increase the weight of energy consumption optimization.

[0062] The formula for updating weights is: ,in is the desired production result, is the actual result, is the learning rate.

[0063] 2. Adaptive update of parameter adjustment strategy As production data increases, the movement of particle swarms in the PSO algorithm is improved through historical data training. For example, through machine learning models such as random forests or gradient boosting trees, the optimal parameter combination under certain conditions can be automatically identified, 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.

[0064] In some embodiments, the following method is also used to optimize the dynamic optimization model: 1. Model retraining based on historical data At regular intervals (such as 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, that is, determining the initial value of the particle swarm based on historical data, so that the particle swarm is closer to the actual optimal solution for production, thereby speeding up the search process; improving the multi-objective optimization function, that is, combining the latest production conditions and data, updating the weights of each item in the multi-objective optimization function, so that the optimization of energy consumption, production capacity, and granularity is more in line with actual production needs.

[0065] 2. Update parameters based on evaluation results During each production process, the operation effect of the dynamic optimization model is evaluated, for example: the results of each operation are recorded, the average and variance of the optimal solution are calculated to evaluate the stability and consistency of the algorithm. By evaluating the impact of parameters on production goals (such as energy consumption and capacity), the following PSO parameters are automatically adjusted: Inertia weight , that is, if it is found that the system is difficult to find the global optimal solution under certain production conditions, the inertia weight is appropriately increased or decreased to enable the particle swarm to explore a larger or smaller parameter space; the learning factor That is, when the local optimal solution and the global optimal solution deviate greatly, the learning factor is adjusted appropriately to make the particles approach the global optimal solution faster.

[0066] In some examples, the production strategy is also dynamically adjusted based on the optimization results. Specifically, after iterative optimization, the dynamic optimization model dynamically adjusts the production strategy based on the latest optimal parameter combination. For example: adjusting the material ratio, that is, through historical data, it is found that different material ratios have a greater impact on the product particle size, and the material ratio is automatically adjusted; temperature control strategy optimization, that is, within a specific temperature range, through self-learning, the temperature range with the best production effect is found, and the working status of the heating or cooling equipment is adjusted in real time.

[0067] Therefore, through continuous data accumulation and analysis, the dynamic optimization model realizes self-learning and gradually optimizes the performance of the PSO algorithm. Through data-driven adaptive adjustment, reinforcement learning feedback and rolling optimization mechanism, the PSO algorithm can dynamically adapt to changes in the production process, thereby achieving the optimal balance between energy consumption, production capacity and product quality.

[0068] like Figure 3 As shown, based on the above-mentioned mixer control method for a battery positive electrode material production line, an embodiment of the present invention discloses a mixer control device for a battery positive electrode material production line, including: The model building module 600 is used to determine the constraint conditions according to various key parameters related to the production capacity, energy consumption and particle size; construct a multi-objective optimization function with the objectives of maximizing the production capacity of the mixer, minimizing the energy consumption and stabilizing the particle size; construct a fitness function according to the energy consumption, production capacity and particle size; and construct a dynamic optimization model based on the particle swarm optimization algorithm according to the constraint conditions, the multi-objective optimization function and the fitness function; 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, obtain control parameters, and control the mixer according to the control parameters.

[0069] In some embodiments, the expression of the multi-objective optimization function is: , in, For energy consumption, represents the reference energy consumption; is the parameter to be optimized, For temperature, For the speed, For flow; is the weight coefficient of different objectives, used to balance energy consumption, capacity and granularity; For production capacity; is the particle size function, is the target particle size.

[0070] like Figure 4 As shown, an embodiment of the present invention discloses an electronic device, including a memory 401 storing executable program codes and a processor 402 coupled to the memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute the mixer control method for the battery positive electrode material production line described in the above embodiments.

[0071] An embodiment of the present invention further discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the mixer control method for a battery positive electrode material production line described in the above embodiments.

[0072] The purpose of the above embodiments is to exemplarily reproduce and deduce the technical solution of the present invention, and to fully describe the technical solution, purpose and effect of the present invention. Its purpose is to make the public understand the disclosed content of the present invention more thoroughly and comprehensively, and it does not limit the scope of protection of the present invention.

[0073] The above embodiments are not exhaustive enumerations of the present invention, and there may be multiple other implementations not listed. Any replacement and improvement made without violating the concept of the present invention shall fall within the protection scope of the present invention.

Claims

1. A mixer control method for a battery positive electrode material production line, characterized in that: include: Determine constraints based on 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 particle size; Construct a fitness function based on energy consumption, capacity, and granularity; According to the constraint conditions, the multi-objective optimization function and the fitness function, a dynamic optimization model is constructed based on a particle swarm optimization algorithm; The data corresponding to each of the key parameters are collected in real time to obtain real-time data, all the real-time data are input into the dynamic optimization model to obtain control parameters, and the mixer is controlled according to the control parameters.

2. The mixer control method for a battery positive electrode material production line according to claim 1, characterized in that: The expression of the multi-objective optimization function is: ， in, For energy consumption, represents the reference energy consumption; is the parameter to be optimized, For temperature, For the speed, For flow; is the weight coefficient of different objectives, used to balance energy consumption, capacity and granularity; For production capacity; is the particle size function, is the target particle size.

3. The mixer control method for a battery positive electrode material production line according to claim 2, characterized in that: After building a dynamic optimization model, it also includes: Calculating, based on historical data of the key parameter, a correlation between the key parameter and at least one of production capacity, energy consumption, and particle size; The dynamic optimization model is adjusted according to the correlation.

4. The mixer control method for a battery positive electrode material production line according to claim 3, characterized in that: The step of adjusting the dynamic optimization model according to the correlation comprises: According to the correlation, determining the coefficient items to be adjusted in the weight coefficients of the dynamic optimization model and the adjustment model to be adopted; The coefficient terms are adjusted according to the adjustment model.

5. The mixer control method for a battery positive electrode material production line according to claim 1, characterized in that: The expression of the fitness function is: ， in, are the weight coefficients of different objectives, represents the reference energy consumption, is the energy consumption value of particle i, is the production capacity of particle i, is the target particle size, is the particle size value of particle i.

6. The mixer control method for a battery positive electrode material production line according to claim 1, characterized in that: The control parameters include rotation speed, temperature, and material flow rate. Controlling the mixer according to the control parameters includes: Obtaining a first PLC instruction according to the rotation speed in the control parameter, and inputting the first PLC instruction into a variable frequency motor control system for controlling the mixer; Obtaining a second PLC instruction according to the temperature in the control parameter, and controlling the heating device or the cooling system according to the second PLC instruction; A third PLC instruction is obtained according to the material flow in the control parameter, and the valve of the feed pipeline is controlled according to the third PLC instruction.

7. A mixer control device for a battery positive electrode material production line, characterized in that: include: Model building module for determining 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 the mixer's capacity, minimizing energy consumption, and stabilizing particle size; a fitness function is constructed based on energy consumption, capacity, and particle size; According to the constraint conditions, the multi-objective optimization function and the fitness function, a dynamic optimization model is constructed based on a 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, obtain control parameters, and control the mixer according to the control parameters.

8. The mixer control device for the battery positive electrode material production line according to claim 7, characterized in that: The expression of the multi-objective optimization function is: ， in, For energy consumption, represents the reference energy consumption; is the parameter to be optimized, For temperature, For the speed, For flow; is the weight coefficient of different objectives, used to balance energy consumption, capacity and granularity; For production capacity; is the particle size function, is the target particle size.

9. 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 for the battery positive electrode material production line according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the mixer control method for a battery positive electrode material production line according to any one of claims 1 to 6.

Images