Color master batch processing energy consumption and efficiency collaborative optimization system based on production data

Abstract

The invention relates to the technical field of production management, in particular to a color master batch processing energy consumption and efficiency collaborative optimization system based on production data, which comprises a data acquisition and analysis module for integrating production, energy consumption and efficiency data to form a structured data set; the objective function construction module deeply mines production, energy consumption and efficiency characteristics in the data and constructs a multi-objective optimization function set according to the production, energy consumption and efficiency characteristics; the multi-target collaborative optimization module adopts an improved NSGA-II algorithm, introduces a simulated annealing mechanism to enhance the local search ability of an elite solution, combines with a cross, mutation probability and targeted search strategy based on multi-modal feature dynamic adjustment, and applies dynamic process, equipment and security constraints at the same time to solve globally optimal multi-dimensional scheduling parameters. Through combination of deep data analysis and an advanced optimization algorithm, the overall production management efficiency of color master batch production is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and particularly to a collaborative optimization system for the processing energy consumption and efficiency of masterbatch based on production data. Background Technique

[0002] In the existing masterbatch production process, the setting of processing process parameters mainly depends on manual experience, which leads to the lack of necessary flexibility and adaptability of the system in dealing with different batches, different formulas and changes in market demands; moreover, the traditional management mode fails to fully consider the collaborative optimization between processing energy consumption and production efficiency. This management method often results in excessive energy consumption or low efficiency, ultimately restricting the overall management efficiency and economic benefits of masterbatch production.

[0003] In the traditional system, the processing process parameters of masterbatch are often set manually, lacking flexibility; and the collaborative optimization between processing energy consumption and production efficiency is not fully considered, resulting in limited management efficiency of masterbatch production.

[0004] Therefore, a collaborative optimization system for the processing energy consumption and efficiency of masterbatch based on production data is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a collaborative optimization system for the processing energy consumption and efficiency of masterbatch based on production data. The data acquisition and analysis module integrates production, energy consumption and efficiency data to form a structured data set; the objective function construction module deeply mines the production, energy consumption and efficiency characteristics in the data and constructs a set of multi-objective optimization functions based on this; the multi-objective collaborative optimization module adopts an improved NSGA-II algorithm, introduces a simulated annealing mechanism to enhance the local search ability of elite solutions, combines the crossover, mutation probability and targeted search strategy dynamically adjusted based on multi-modal characteristics, and simultaneously imposes dynamic process, equipment and safety constraints to obtain the globally optimal multi-dimensional scheduling parameters. The present invention effectively improves the overall production management efficiency of masterbatch production through the combination of in-depth data analysis and advanced optimization algorithms.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: A collaborative optimization system for the processing energy consumption and efficiency of masterbatch based on production data, comprising: A data acquisition and analysis module, used to obtain the first production data, the second energy consumption data and the third efficiency data; analyze based on these three types of data to obtain the first structured data set; An objective function construction module, used to construct a multi-modal analysis model to analyze the first structured data set to obtain the first multi-modal characteristics; the first multi-modal characteristics include production characteristics, energy consumption characteristics and efficiency characteristics; obtain the first set of multi-objective functions based on these three types of characteristics; The multi-objective collaborative optimization module is used to optimize the first multi-objective function set by constructing an improved NSGA-II algorithm. The improved NSGA-II algorithm introduces a simulated annealing algorithm into the NSGA-II algorithm and dynamically constrains the first multi-objective function set, and finally determines the first multi-dimensional scheduling parameters. The first multi-dimensional scheduling parameters include production process scheduling parameters, energy consumption scheduling parameters, and efficiency scheduling parameters; The production management module is used to dynamically manage the production process based on the first multi-dimensional scheduling parameters.

[0007] Preferably, the first structured data set is obtained by weighted fusion of the first production data, the second energy consumption data, and the third efficiency data.

[0008] Preferably, the multi-modal analysis model includes a multi-dimensional data input layer, a multi-dimensional data preprocessing layer, a multi-modal feature extraction layer, and a multi-modal feature output layer; The multi-dimensional data input layer is used to input the first structured data set into the multi-modal analysis model; The multi-dimensional data preprocessing layer is used to preprocess the first structured data set to obtain a second structured data set; The multi-modal feature extraction layer includes a production feature extraction sub-layer, an energy consumption feature extraction sub-layer, and an efficiency feature extraction sub-layer; each sub-layer respectively performs feature analysis by fusing LSTM and CNN to obtain production features, energy consumption features, and efficiency features; The multi-modal feature output layer is used to output production features, energy consumption features, and efficiency features.

[0009] Preferably, the obtaining process of the first multi-objective function set includes: obtaining an energy consumption feature sub-function based on the energy consumption features; obtaining an efficiency feature sub-function based on the efficiency features; obtaining an energy consumption target sub-function based on the energy consumption feature sub-function and the first influence coefficient; obtaining an efficiency target sub-function based on the efficiency feature sub-function and the second influence coefficient; and further obtaining the first multi-objective function set.

[0010] Preferably, the improved NSGA-II algorithm dynamically adjusts the crossover probability, mutation probability, selection pressure, and distribution estimation parameters of the NSGA-II algorithm based on the first multi-modal features; for the elite individuals in the Pareto front solution set output by the NSGA-II, a simulated annealing algorithm is introduced for local depth search and perturbation.

[0011] Preferably, the improved NSGA-II algorithm constructs a targeted search strategy based on the importance analysis of each first multi-modal feature; the strategy analyzes the correlation strength between the first multi-modal features and each sub-objective of the first multi-objective function set; and dynamically adjusts the search focus of the improved NSGA-II algorithm.

[0012] Preferably, the dynamic constraints include process constraints, equipment constraints, and safety constraints; the process constraints are used to constrain the extrusion temperature range, screw speed limit, material ratio boundary, and product quality requirements; the equipment constraints are used to constrain the motor power limit, melt pressure range, cooling system capacity, and production line production capacity limit; the safety constraints are used to constrain the temperature safety boundary, pressure safety limit, energy consumption peak limit, and environmental protection emission standard.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. By constructing a multi-modal analysis model integrating LSTM and CNN, the present invention performs in-depth feature extraction and fusion analysis on production, energy consumption, and efficiency data; compared with the traditional method relying on experience or single parameters, it can more accurately and comprehensively identify the key influencing factors under complex working conditions, effectively analyze the production, energy consumption, and efficiency characteristics; and effectively improve the overall production management efficiency of masterbatch production.

[0014] 2. The present invention adopts an improved NSGA-II algorithm, innovatively integrates the simulated annealing algorithm to strengthen the local deep search and perturbation of elite individuals on the Pareto front, and dynamically adjusts the algorithm parameters and constructs a targeted search strategy based on multi-modal features. This hybrid optimization strategy can more effectively perform global search in the complex multi-objective space of energy consumption and efficiency, overcome the disadvantages that traditional optimization methods are prone to falling into local optima or difficult to balance multiple conflicting objectives, thereby realizing a deeper level of collaborative optimization between energy consumption and efficiency, and effectively improving the overall production management efficiency of masterbatch production.

[0015] 3. The present invention can not only be optimized by improving the NSGA-II algorithm, but also continuously dynamically manage the production process based on the optimized multi-dimensional scheduling parameters; combined with dynamic constraint conditions, it forms a closed-loop intelligent system from data collection, analysis, optimization decision-making to execution feedback. This mechanism enables production management to respond to changes in working conditions in real time, continuously optimize resource allocation, thereby significantly improving the overall operation efficiency, material utilization rate, and energy efficiency, and effectively improving the overall production management efficiency of masterbatch production. Description of the Drawings

[0016] Figure 1 It is a schematic structural diagram of a masterbatch processing energy consumption and efficiency collaborative optimization system based on production data provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a multi-modal analysis model provided by an embodiment of the present invention. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1 In order to improve the production management efficiency of masterbatch, a collaborative optimization system for masterbatch processing energy consumption and efficiency based on production data is applied, as Figure 1 shown in the structural schematic diagram of a collaborative optimization system for masterbatch processing energy consumption and efficiency based on production data provided by the embodiments of the present invention, which specifically includes: A data acquisition and analysis module, configured to obtain first production data, second energy consumption data, and third efficiency data; and analyze these three types of data to obtain a first structured data set; Further, the first production data includes the extrusion machine screw speed, barrel temperature distribution, melt pressure, and material ratio; the second energy consumption data includes the power consumption of the extrusion machine motor, energy consumption of the heating system, energy consumption of the cooling system, and energy consumption of auxiliary equipment; the third efficiency data includes product output, product qualification status, and material usage.

[0019] The barrel temperature distribution represents the temperature data of each heating area and each cooling area; the material ratio represents the ratio of each raw material; Further, the first structured data set includes: The first structured data set is obtained by performing data cleaning and normalization on the first production data, second energy consumption data, and third efficiency data, and then performing weighted fusion.

[0020] A target function construction module, configured to construct a multi-modal analysis model to analyze the first structured data set to obtain first multi-modal features; the first multi-modal features include production features, energy consumption features, and efficiency features; and obtain a first multi-objective function set based on these three types of features; Further, the multi-modal analysis model includes a multi-dimensional data input layer, a multi-dimensional data preprocessing layer, a multi-modal feature extraction layer, and a multi-modal feature output layer; Figure 2 shown in the structural schematic diagram of a multi-modal analysis model provided by the embodiments of the present invention; The multi-dimensional data input layer is configured to input the first structured data set into the multi-modal analysis model; The multi-dimensional data preprocessing layer is configured to preprocess the first structured data set to obtain a second structured data set; the preprocessing includes normalization; The multi-modal feature extraction layer includes a production feature extraction sub-layer, an energy consumption feature extraction sub-layer, and an efficiency feature extraction sub-layer; each sub-layer performs feature analysis by integrating LSTM and CNN to obtain production features, energy consumption features, and efficiency features respectively; The multi-modal feature output layer is used to output production features, energy consumption features, and efficiency features.

[0021] Specifically, parallel LSTM branches and CNN branches are deployed in the multi-modal feature extraction layer, which are respectively used to deeply extract the temporal dynamic features and local features of the input data. After obtaining the feature vectors extracted by the LSTM branch and the CNN branch, weighted averaging is performed based on the preset weights of the two branches to obtain a fused "final feature vector"; the preset weights are based on built-in quantization methods (e.g., Monte Carlo Dropout) to evaluate the confidence of the feature vectors extracted by the LSTM branch and the CNN branch in real time. The higher the confidence of the branch feature, the higher the weight is given during fusion.

[0022] The production features include the average temperature of each region of the barrel, the maximum temperature difference of each region of the barrel, the average melt pressure, the ratio of screw speed to melt pressure, and the material ratio of each material; the energy consumption features include the total average power consumption, the average energy consumption of the heating system, and the average energy consumption of the cooling system; the efficiency features include the output per unit time, the product qualification rate, and the material utilization rate; In this embodiment, by constructing a multi-modal analysis model that integrates LSTM and CNN, deep feature extraction and fusion analysis are performed on production, energy consumption, and efficiency data; compared with the traditional method that relies on experience or single parameters, it can more accurately and comprehensively identify the key influencing factors under complex working conditions, effectively analyze production, energy consumption, and efficiency features; and effectively improve the overall production management efficiency of masterbatch production.

[0023] Furthermore, the obtaining process of the first multi-objective function set includes: obtaining an energy consumption feature sub-function based on the energy consumption features; obtaining an efficiency feature sub-function based on the efficiency features; obtaining an energy consumption target sub-function based on the energy consumption feature sub-function and the first influence coefficient; obtaining an efficiency target sub-function based on the efficiency feature sub-function and the second influence coefficient; and then obtaining the first multi-objective function set.

[0024] Furthermore, an energy consumption feature sub-function is obtained based on each energy consumption feature and a preset target value; the specific formula is: ; where represents the energy consumption feature sub-function; represents the number of energy consumption features; represents the th energy consumption feature; represents the The target value of an energy consumption characteristic; Based on the multiplication of the energy consumption characteristic sub-function and the first influence coefficient, the energy consumption target sub-function is obtained; based on the efficiency characteristic, the efficiency characteristic sub-function is obtained; the specific formula is: ; Among them, represents the efficiency characteristic sub-function; represents the number of efficiency characteristics; represents the th efficiency characteristic; represents the th target value of the efficiency characteristic; Based on the multiplication of the efficiency characteristic sub-function and the second influence coefficient, the efficiency target sub-function is obtained; and based on the energy consumption target sub-function and the efficiency target sub-function, the first multi-objective function set is obtained; The first multi-objective function set includes the energy consumption target sub-function and the efficiency target sub-function; The first multi-objective function set is as follows: ; Among them, represents the first multi-objective function set; represents the energy consumption target sub-function; represents the efficiency target sub-function; The energy consumption target sub-function is: ; Among them, represents the first influence coefficient; represents the energy consumption characteristic sub-function; The efficiency target sub-function is: ; Among them, represents the second influence coefficient; represents the efficiency characteristic sub-function; Furthermore, the specific acquisition processes of the first influence coefficient and the second influence coefficient are as follows: based on the energy consumption characteristic and the production characteristic, correlation analysis is carried out through the Pearson coefficient to obtain the energy consumption-production correlation coefficient; the energy consumption-production correlation coefficient is used as the first influence coefficient; based on the efficiency characteristic and the production characteristic, correlation analysis is carried out through the Pearson coefficient to obtain the efficiency-production correlation coefficient; the efficiency-production correlation coefficient is used as the second influence coefficient; The multi-objective collaborative optimization module is used to construct an improved NSGA-II algorithm to optimize the first multi-objective function set, and dynamically constrain the first multi-objective function set, and finally determine the first multi-dimensional scheduling parameters; the first multi-dimensional scheduling parameters include production process scheduling parameters, energy consumption scheduling parameters, and efficiency scheduling parameters; Furthermore, the improved NSGA-II algorithm dynamically adjusts the crossover probability, mutation probability, selection pressure, and distribution estimation parameters of the NSGA-II algorithm based on the first multi-modal features; specifically including: By analyzing the energy consumption characteristics, the characteristic variances of each batch are obtained; if the variances fluctuate greatly, the global exploration ability needs to be enhanced, so the crossover probability is increased.

[0025] By calculating and analyzing the efficiency characteristic variances of different batches of masterbatch products, if the fluctuations are small, it indicates that the efficiency is relatively stable. At this time, the mutation probability needs to be reduced to achieve local optimization focus; When the correlation strength between the production characteristics of the masterbatch and the objective function is high, it indicates that the production characteristics have a significant impact on the optimization objective. At this time, the selection pressure is increased to preferentially retain high-quality individuals.

[0026] The distribution estimation parameters control the search range of the crossover and mutation operations and affect the distribution uniformity of the solutions; when the multi-modal features (production features, efficiency features, and energy consumption features) are unevenly distributed, the distribution estimation parameters are reduced to focus on local search; otherwise, the search range is expanded; For the elite individuals in the Pareto front solution set output by NSGA-II, a simulated annealing algorithm is introduced for local deep search and perturbation.

[0027] The specific process includes: Elite individual selection: Extract elite individuals from the Pareto front of NSGA-II; Using the crowding distance screening, individuals with a sparser distribution are preferentially selected to maintain the diversity of the solution set; for example, if the front contains 100 solutions, the individuals with the top 20% crowding distance are selected for simulated annealing.

[0028] Simulated annealing initialization: Using the selected elite individual as the starting point; Including multi-dimensional scheduling parameters (such as the screw speed of the extruder, the barrel temperature distribution, the melt pressure, and the material ratio); determining the initial temperature, cooling coefficient (0.95), and termination temperature; Perturbation mechanism: Including perturbing the parameter vector of to generate a neighborhood solution ; The perturbation method is based on the Gaussian distribution: The perturbation step size is adjusted according to (the average value of the variances of each multi-modal feature); the variances of the multi-modal features; Acceptance criterion: Calculate the objective function values of; including the energy consumption objective function value and the efficiency objective function value; and judge whether it is non-dominated by ; If so, accept ; Otherwise, accept it with a probability according to the Metropolis criterion.

[0029] Iterate to the termination temperature to obtain the optimized elite individuals.

[0030] Furthermore, the improved NSGA-II algorithm constructs a targeted search strategy based on the importance analysis of each first multi-modal feature; the strategy analyzes the association strength between the first multi-modal feature and each sub-objective of the first multi-objective function set; and dynamically adjusts the search focus of the improved NSGA-II algorithm.

[0031] Furthermore, the targeted search strategy includes obtaining the comprehensive importance weight based on each eigenvalue in the multi-modal feature (such as the average temperature of each region of the barrel, the maximum temperature difference of each region of the barrel) and the objective function value (such as the energy consumption objective function value and the efficiency objective function value); In this embodiment, the improved NSGA-II algorithm is adopted, which innovatively integrates the simulated annealing algorithm to strengthen the local depth search and perturbation of the elite individuals on the Pareto front, and dynamically adjusts the algorithm parameters and constructs a targeted search strategy based on the multi-modal features. This hybrid optimization strategy can more effectively perform global search in the complex multi-objective space of energy consumption and efficiency, overcome the drawbacks that traditional optimization methods are prone to fall into local optima or difficult to balance multiple conflicting objectives, so as to achieve a deeper collaborative optimization between energy consumption and efficiency, and effectively improve the overall production management efficiency of masterbatch production.

[0032] Furthermore, the specific process of obtaining the comprehensive importance weight is as follows: calculate the correlation coefficient according to each eigenvalue in the multi-modal feature (such as the average temperature of each region of the barrel, the maximum temperature difference of each region of the barrel) and the objective function value (such as the energy consumption objective function value and the efficiency objective function value) through the Pearson coefficient formula; then obtain the correlation matrix based on each correlation coefficient; obtain the ratio by taking the quotient of the correlation coefficient between each feature and each objective function and the sum of the correlation coefficients of all features, and the ratio represents the importance weight of each feature for each objective function; then obtain the comprehensive importance weight by weighting the importance weight of this feature and each objective function; for the feature with a larger comprehensive importance weight: narrow the search range, focus on the neighborhood of the current high-quality solution, and promote local precise search. For the feature with a smaller comprehensive importance weight: expand the search range.

[0033] The first multi-dimensional scheduling parameters include production process scheduling parameters (such as screw speed, barrel temperature, material ratio), energy consumption scheduling parameters (such as motor power, heating energy consumption and cooling energy consumption), and efficiency scheduling parameters (such as output, qualification rate and material utilization rate); Furthermore, the dynamic constraints include process constraints, equipment constraints, and safety constraints; the process constraints are used to constrain the extrusion temperature range, screw speed limit, material ratio boundary, and product quality; the equipment constraints are used to constrain the motor power limit, melt pressure range, cooling system capacity, and upper limit of production line capacity; the safety constraints are used to constrain the temperature safety boundary, pressure safety limit, energy consumption peak limit, and environmental protection emission standard.

[0034] The production management module is used to dynamically manage the production process based on the first multi-dimensional scheduling parameters.

[0035] This embodiment can not only be optimized by improving the NSGA-II algorithm, but also continuously and dynamically manage the production process based on the optimized multi-dimensional scheduling parameters; combined with the dynamic constraint conditions, it forms a closed-loop intelligent system from data collection, analysis, optimization decision-making to execution feedback. This mechanism enables production management to respond to changes in working conditions in real time, continuously optimize resource allocation, thereby significantly improving the overall operation efficiency, material utilization rate, and energy efficiency, and effectively improving the overall production management efficiency of masterbatch production.

[0036] The present invention integrates production, energy consumption, and efficiency data through the data collection and analysis module to form a structured data set; the objective function construction module deeply mines the production, energy consumption, and efficiency characteristics in the data and constructs a multi-objective optimization function set based on this; the multi-objective collaborative optimization module adopts an improved NSGA-II algorithm, introduces a simulated annealing mechanism to enhance the local search ability of elite solutions, and combines cross-over, mutation probabilities, and targeted search strategies dynamically adjusted based on multi-modal characteristics, while imposing dynamic process, equipment, and safety constraints to obtain the globally optimal multi-dimensional scheduling parameters. The present invention effectively improves the overall production management efficiency of masterbatch production through the combination of in-depth data analysis and advanced optimization algorithms.

[0037] Embodiment 2 In order to improve the production management efficiency of masterbatch, a collaborative optimization system for masterbatch processing energy consumption and efficiency based on production data is applied, as Figure 1 is a schematic structural diagram of a collaborative optimization system for masterbatch processing energy consumption and efficiency based on production data provided by an embodiment of the present invention, specifically including: The data collection and analysis module is used to obtain the first production data, the second energy consumption data, and the third efficiency data; analyze these three types of data to obtain the first structured data set; The objective function construction module is used to construct a multi-modal analysis model to analyze the first structured data set to obtain the first multi-modal characteristics; the first multi-modal characteristics include production characteristics, energy consumption characteristics, and efficiency characteristics; based on these three types of characteristics, obtain the first multi-objective function set; A multi-objective collaborative optimization module is used to construct an improved NSGA-II algorithm to optimize the first multi-objective function set. The improved NSGA-II algorithm introduces a simulated annealing algorithm into the NSGA-II algorithm and dynamically constrains the first multi-objective function set, and finally determines the first multi-dimensional scheduling parameters. The first multi-dimensional scheduling parameters include production process scheduling parameters, energy consumption scheduling parameters, and efficiency scheduling parameters. A production management module is used to dynamically manage the production process based on the first multi-dimensional scheduling parameters.

[0038] Furthermore, the first structured data set is obtained by weighted fusion of the first production data, the second energy consumption data, and the third efficiency data.

[0039] Furthermore, the multi-modal analysis model includes a multi-dimensional data input layer, a multi-dimensional data preprocessing layer, a multi-modal feature extraction layer, and a multi-modal feature output layer. Figure 2 It is a schematic structural diagram of a multi-modal analysis model provided by an embodiment of the present invention. The multi-dimensional data input layer is used to input the first structured data set into the multi-modal analysis model. The multi-dimensional data preprocessing layer is used to preprocess the first structured data set to obtain a second structured data set. The multi-modal feature extraction layer includes a production feature extraction sub-layer, an energy consumption feature extraction sub-layer, and an efficiency feature extraction sub-layer. Each sub-layer respectively performs feature analysis by fusing LSTM and CNN to obtain production features, energy consumption features, and efficiency features. The multi-modal feature output layer is used to output production features, energy consumption features, and efficiency features.

[0040] Furthermore, the obtaining process of the first multi-objective function set includes: obtaining an energy consumption feature sub-function based on the energy consumption features; obtaining an efficiency feature sub-function based on the efficiency features; obtaining an energy consumption target sub-function based on the energy consumption feature sub-function and a first influence coefficient; obtaining an efficiency target sub-function based on the efficiency feature sub-function and a second influence coefficient; and further obtaining the first multi-objective function set.

[0041] Furthermore, the improved NSGA-II algorithm dynamically adjusts the crossover probability, mutation probability, selection pressure, and distribution estimation parameters of the NSGA-II algorithm based on the first multi-modal features. For the elite individuals in the Pareto front solution set output by the NSGA-II, a simulated annealing algorithm is introduced for local depth search and perturbation.

[0042] Furthermore, the improved NSGA-II algorithm constructs a targeted search strategy based on the importance analysis of each first multi-modal feature; the strategy analyzes the association strength between the first multi-modal feature and each sub-goal of the first multi-objective function set; and dynamically adjusts the search focus of the improved NSGA-II algorithm.

[0043] Furthermore, the dynamic constraints include process constraints, equipment constraints, and safety constraints; the process constraints are used to constrain the extrusion temperature range, screw speed limit, material ratio boundary, and product quality requirements; the equipment constraints are used to constrain the motor power limit, melt pressure range, cooling system capacity, and upper limit of production line capacity; the safety constraints are used to constrain the temperature safety boundary, pressure safety limit, energy consumption peak limit, and environmental protection emission standard.

[0044] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A color masterbatch processing energy consumption and efficiency collaborative optimization system based on production data, characterized in that, Including: A data acquisition and analysis module, which is used to obtain first production data, second energy consumption data, and third efficiency data; Analyze based on these three types of data to obtain a first structured data set; A target function construction module, which is used to construct a multi-modal analysis model to analyze the first structured data set to obtain first multi-modal features; the first multi-modal features include production features, energy consumption features, and efficiency features; based on these three types of features, obtain a first multi-objective function set; A multi-objective collaborative optimization module, which is used to construct an improved NSGA-II algorithm to optimize the first multi-objective function set. The improved NSGA-II algorithm introduces a simulated annealing algorithm into the NSGA-II algorithm and dynamically constrains the first multi-objective function set, and finally determines first multi-dimensional scheduling parameters; the first multi-dimensional scheduling parameters include production process scheduling parameters, energy consumption scheduling parameters, and efficiency scheduling parameters; A production management module, which is used to dynamically manage the production process based on the first multi-dimensional scheduling parameters.

2. The color masterbatch processing energy consumption and efficiency collaborative optimization system based on production data according to claim 1, characterized in that: The first structured data set is obtained by weighted fusion of the first production data, the second energy consumption data, and the third efficiency data.

3. The color masterbatch processing energy consumption and efficiency collaborative optimization system based on production data according to claim 1, characterized in that: The multi-modal analysis model includes a multi-dimensional data input layer, a multi-dimensional data preprocessing layer, a multi-modal feature extraction layer, and a multi-modal feature output layer; The multi-dimensional data input layer is used to input the first structured data set into the multi-modal analysis model; The multi-dimensional data preprocessing layer is used to preprocess the first structured data set to obtain a second structured data set; The multi-modal feature extraction layer includes a production feature extraction sub-layer, an energy consumption feature extraction sub-layer, and an efficiency feature extraction sub-layer; Each sub-layer respectively performs feature analysis by fusing LSTM and CNN to obtain production features, energy consumption features, and efficiency features respectively; The multi-modal feature output layer is used to output production features, energy consumption features, and efficiency features.

4. The system for collaborative optimization of the energy consumption and efficiency of masterbatch processing based on production data according to claim 1, wherein The process of obtaining the first multi-objective function set includes: obtaining an energy consumption feature sub-function based on the energy consumption feature; obtaining an efficiency feature sub-function based on the efficiency feature; obtaining an energy consumption target sub-function based on the energy consumption feature sub-function and a first influence coefficient; obtaining an efficiency target sub-function based on the efficiency feature sub-function and a second influence coefficient; and then obtaining the first multi-objective function set.

5. The system for collaborative optimization of the energy consumption and efficiency of masterbatch processing based on production data according to claim 1, wherein: The improved NSGA-II algorithm dynamically adjusts the crossover probability, mutation probability, selection pressure, and distribution estimation parameters of the NSGA-II algorithm based on the first multi-modal features; for the elite individuals in the Pareto front solution set output by the NSGA-II, a simulated annealing algorithm is introduced for local depth search and perturbation.

6. The system for collaborative optimization of energy consumption and efficiency in masterbatch processing based on production data according to claim 5, characterized in that, The improved NSGA-II algorithm constructs a targeted search strategy based on the importance analysis of each first multi-modal feature; the construction method of the targeted search strategy is to analyze the association strength between the first multi-modal features and each sub-objective of the first multi-objective function set; and dynamically adjust the search focus of the improved NSGA-II algorithm.

7. The system for collaborative optimization of color masterbatch processing energy consumption and efficiency based on production data according to claim 1, characterized in that: The dynamic constraints include process constraints, equipment constraints, and safety constraints; the process constraints are used to constrain the extrusion temperature range, screw speed limit, material ratio boundary, and product quality requirements; the equipment constraints are used to constrain the motor power limit, melt pressure range, cooling system capacity, and upper limit of production line capacity; the safety constraints are used to constrain the temperature safety boundary, pressure safety limit, energy consumption peak limit, and environmental protection emission standards.

Images