Intelligent control method and system for vegetarian meat powder production line

Abstract

The invention provides an intelligent control method and system for a vegetarian meat powder production line, and relates to the technical field of food processing. Determining N vegetarian meat powder production lines; according to the N vegetarian meat powder production lines, feature disassembling is conducted on the vegetarian meat powder production tasks, and N pieces of vegetarian meat powder production task information are obtained; the nth node vegetarian meat powder production task information corresponding to the nth vegetarian meat powder production line is extracted, n is a positive integer, and n is larger than or equal to 1 and smaller than or equal to N; according to the nth vegetarian meat powder production line, constructing an nth vegetarian meat powder production control decision model; and based on the nth node vegetarian meat powder production task information, obtaining an nth vegetarian meat powder production control decision according to the nth vegetarian meat powder production control decision model. The technical problems that the production efficiency is low and the product stability is poor due to the fact that traditional production control depends on manual work are solved, and the technical effect of improving the production efficiency and quality of the vegetarian meat powder is achieved.

Description

Technical Field

[0001] The present application relates to the field of food processing technology, and in particular to an intelligent control method and system for a vegetarian meat powder production line. Background Art

[0002] Vegan meat powder is a plant-based alternative meat product that is widely used in the market. The production process of vegan meat powder is complex, involving multiple steps such as raw material screening, mixing, stirring, and beating. Each step has a direct impact on the taste, nutrition, and safety of the final product.

[0003] The traditional control method of vegetarian meat powder production line mainly relies on manual experience and simple mechanical control. In this method, the allocation of production tasks is usually completed manually, which is prone to problems such as uneven task allocation and failure to fully utilize the potential of each production line. At the same time, due to the lack of real-time data analysis and adjustment capabilities, when there is a deviation between the production plan and the actual execution, the adjustment process is slow and imprecise, resulting in low production efficiency. In addition, traditional production control relies on direct monitoring and intervention by operators, lacks refined control, and is prone to problems such as inadequate monitoring and untimely response, making it difficult to ensure product consistency and stability. Summary of the invention

[0004] The present application provides an intelligent control method and system for a vegetarian meat powder production line, which solves the technical problems of low production efficiency and poor product consistency caused by traditional production control relying on manual labor. Through intelligent control, the technical effect of improving the production efficiency and quality of vegetarian meat powder is achieved.

[0005] In view of the above problems, on the one hand, the present application provides an intelligent control method for a vegetarian meat powder production line, the method comprising: obtaining a vegetarian meat powder production task; determining N vegetarian meat powder production lines, wherein N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node; based on the N vegetarian meat powder production lines, feature-decomposing the vegetarian meat powder production task to obtain N-node vegetarian meat powder production task information; based on the N-node vegetarian meat powder production task information, extracting the n-node vegetarian meat powder production task information corresponding to the n-node vegetarian meat powder production line, wherein n is a positive integer, 1≤n≤N; based on the n-th vegetarian meat powder production line, constructing an n-th vegetarian meat powder production control decision model; based on the n-node vegetarian meat powder production task information, according to the n-th vegetarian meat powder production control decision model, obtaining the n-th vegetarian meat powder production control decision.

[0006] On the other hand, the present application also provides an intelligent control system for a vegetarian meat powder production line, the system comprising: a task acquisition module, the task acquisition module is used to obtain a vegetarian meat powder production task; a production line determination module, the production line determination module is used to determine N vegetarian meat powder production lines, wherein N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node; a feature disassembly module, the feature disassembly module is used to perform feature disassembly on the vegetarian meat powder production task according to the N vegetarian meat powder production lines, and obtain N-node vegetarian meat powder production task information; a task information extraction module, the task information extraction module is used to extract the n-node vegetarian meat powder production task information corresponding to the n-node vegetarian meat powder production line according to the N-node vegetarian meat powder production task information, wherein n is a positive integer, 1≤n≤N; a decision model construction module, the decision model construction module is used to construct an n-th vegetarian meat powder production control decision model according to the n-th vegetarian meat powder production line; a control decision generation module, the control decision generation module is used to obtain the n-th vegetarian meat powder production control decision based on the n-node vegetarian meat powder production task information and the n-th vegetarian meat powder production control decision model.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: Obtain the vegetarian meat powder production task, clarify the production goals and requirements, and provide a basis for subsequent task allocation and production planning. Determine N vegetarian meat powder production lines, where N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node, master the existing production line resource allocation information, and provide data collection and analysis targets for subsequent control decision generation. According to the N vegetarian meat powder production lines, feature the vegetarian meat powder production task, obtain the N-node vegetarian meat powder production task information, refine the production tasks, and provide accurate data reference for the subsequent construction of the production control decision model. According to the N-node vegetarian meat powder production task information, extract the n-node vegetarian meat powder production task information corresponding to the n-node vegetarian meat powder production line, where n is a positive integer, 1≤n≤N, and construct the n-node vegetarian meat powder production control decision model according to the n-node vegetarian meat powder production task information. Based on the n-node vegetarian meat powder production task information, according to the n-node vegetarian meat powder production control decision model, obtain the n-node vegetarian meat powder production control decision, and automatically generate a control strategy for each production line to achieve precise control.

[0008] To summarize, this application decomposes and allocates production tasks to different production lines, builds a control decision model for each production line, and intelligently generates corresponding production control strategies, thereby realizing refined management and optimized control of the vegetarian meat powder production process, improving the accuracy and reliability of production control decisions, and helping to improve product quality and production efficiency.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the process of the intelligent control method of the vegetarian meat powder production line provided in the embodiment of the present application; Figure 2 A schematic diagram of a process for constructing an n-th vegetarian meat powder production control decision model in the intelligent control method for a vegetarian meat powder production line provided in an embodiment of the present application; Figure 3 A schematic diagram of a process for obtaining the nth vegetarian meat powder production control decision in the intelligent control method for the vegetarian meat powder production line provided in an embodiment of the present application; Figure 4 This is a schematic diagram of the structure of the intelligent control system of the vegetarian meat powder production line provided in the embodiment of the present application.

[0011] Explanation of the reference numerals: task acquisition module 10 , production line determination module 20 , feature disassembly module 30 , task information extraction module 40 , decision model construction module 50 , control decision generation module 60 . DETAILED DESCRIPTION

[0012] The embodiment of the present application provides an intelligent control method and system for a vegetarian meat powder production line, provides intelligent decision support for each production line, realizes refined control of the vegetarian meat powder production process, solves the technical problems of low production efficiency and poor product consistency caused by traditional production control relying on manual labor, and achieves the technical effect of improving the production efficiency and quality of vegetarian meat powder.

[0013] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides an intelligent control method for a vegetarian meat powder production line, the method comprising: Step S1: Obtaining a vegetarian meat powder production task.

[0014] Specifically, the vegetarian meat powder production task refers to the specific requirements of the vegetarian meat powder production work that needs to be completed, including production quantity, specifications, quality standards, etc. The vegetarian meat powder production task is obtained by interacting with the order database or production management system or manually inputting, and the specific production goals and requirements are clarified.

[0015] Step S2: Determine N vegetarian meat powder production lines, where N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node.

[0016] Specifically, vegetarian meat powder production lines refer to industrial production lines used to produce vegetarian meat powder. These production lines cover all aspects of the vegetarian meat powder production process, such as raw material handling, mixing, processing, packaging, etc. Each key production link or workstation can be regarded as a production node. Each node is responsible for specific production tasks, such as raw material proportioning, heating, cooling, etc.

[0017] By interacting with the production management system, the N vegetarian meat powder production lines that the factory needs to complete the vegetarian meat powder production task are obtained, and the vegetarian meat powder production nodes corresponding to each production line are determined, where N is a positive integer greater than 1. For example, the raw material screening and mixing production line, the stirring and beating production line, and the packaging production line. Step S2 can determine the existing production resource allocation and provide a basic framework for subsequent production decision generation.

[0018] Step S3: According to the N vegetarian meat powder production lines, feature-decompose the vegetarian meat powder production tasks to obtain N node vegetarian meat powder production task information.

[0019] Specifically, feature decomposition refers to decomposing the overall production task according to specific attributes or characteristics, such as product types, specifications, production processes, etc. The node vegetarian meat powder production task information refers to the specific information of the specific production tasks that need to be completed at each production node, including production quantity, quality standards, process parameters, etc. In step S3, by decomposing the characteristics of the production tasks, the specific production task information of each node can be obtained, including the required raw materials, production processes, quality standards, etc. For example, the raw material screening and mixing production line is responsible for completing the subtasks of raw material screening and mixing, the stirring and beating production line is responsible for completing the stirring and beating subtask of the vegetarian meat powder, and the packaging production line is responsible for completing the packaging subtask of the vegetarian meat powder. Through the above process, the task information is further refined, which is convenient for the subsequent provision of corresponding production control decisions for each production line, and the production quality of each link can be accurately controlled.

[0020] Furthermore, step S3 of the embodiment of the present application also includes: Step S31: According to the N vegetarian meat powder production lines, feature identification is performed on the vegetarian meat powder production tasks to obtain feature information of N node production tasks.

[0021] Step S32: performing data cleaning according to the production task characteristic information of the N nodes to obtain the vegetarian meat powder production task information of the N nodes.

[0022] Specifically, feature recognition refers to identifying and determining the key characteristics that each production node needs to pay attention to when performing production tasks, such as raw material type, processing parameters, quality standards, etc. Data cleaning refers to checking and purifying the collected data, removing erroneous, duplicated or irrelevant data, and ensuring the accuracy and reliability of the data.

[0023] Use data analysis and mining tools, such as Excel, SPSS, Python, etc., to analyze the production tasks corresponding to N vegetarian meat powder production lines, and identify the key features that each production node needs to pay attention to when performing tasks. For example, for the raw material screening and mixing production line, the feature information may include the particle size, mixing ratio, humidity, etc. of the raw materials; for the packaging production line, the feature information may include packaging materials, packaging size, packaging speed, etc. Use data cleaning tools, such as Excel, data cleaning software, etc., to check and purify the collected production task feature information to remove erroneous, duplicate or irrelevant data. For example, some feature information may be found to be missing or erroneous during the cleaning process, and it needs to be corrected or eliminated in time to ensure the accuracy and reliability of the production task information.

[0024] The above steps obtain accurate vegetarian meat powder production task information of N nodes through feature recognition and data cleaning, which helps to clarify the production target of each production node.

[0025] Step S4: extracting the n-th node vegetarian meat powder production task information corresponding to the n-th vegetarian meat powder production line according to the N-node vegetarian meat powder production task information, wherein n is a positive integer, 1≤n≤N.

[0026] Specifically, the nth vegetarian meat powder production line refers to the nth production line among the N vegetarian meat powder production lines determined in step S2, corresponding to the nth node. Wherein, n represents the serial number of the production line, which is a positive integer, and 1≤n≤N, where N is the total number of production lines. The nth node vegetarian meat powder production task information refers to the detailed information of the specific production task undertaken by the nth production node corresponding to the nth production line, including the content, requirements, execution steps, required resources, etc. of the task.

[0027] First, any one of the N vegetarian meat powder production lines determined in step S2 is selected, and this production line has a corresponding number n. Then, the n-node vegetarian meat powder production task information corresponding to the n-node vegetarian meat powder production line is extracted from the N-node vegetarian meat powder production task information obtained in step S3. The above screening process can be implemented through data management and analysis tools, such as using database query tools such as SQL query to quickly locate and extract information, and using Excel to organize and display the extracted task information. Finally, use the production management system or automated control software to confirm and check the extracted production task information to ensure the accuracy and completeness of the information. Step S4 selects a specific production line and the corresponding production task information from multiple production lines to facilitate subsequent targeted data collection and analysis and generate corresponding control decisions.

[0028] Step S5: constructing an n-th vegetarian meat powder production control decision model according to the n-th vegetarian meat powder production line.

[0029] Specifically, the production control decision model refers to a mathematical or statistical model established based on the capabilities and production task requirements of a specific production line, which is used to guide the control decisions of the production process, including parameter adjustment, resource allocation, process optimization, etc. By collecting the historical decision information of the nth vegetarian meat powder production line, building and training a machine learning model, such as a neural network model, support vector machine, etc., the nth vegetarian meat powder production control decision model is obtained. The model can provide the optimal production control strategy and decision-making recommendations based on the production task information and real-time data of the nth production line.

[0030] Furthermore, if Figure 2 As shown, step S5 of the embodiment of the present application also includes: Step S51: collecting control decision record information corresponding to the nth vegetarian meat powder production line to obtain a comprehensive data set of the vegetarian meat powder production line.

[0031] Step S52: Obtain a predetermined division ratio.

[0032] Step S53: Divide the vegetarian meat powder production line comprehensive data set according to the predetermined division ratio to obtain a control decision training set and a control decision test set.

[0033] Step S54: training and testing are performed according to the control decision training set and the control decision test set to generate the nth vegetarian meat powder production control decision model.

[0034] Furthermore, step S54 of the embodiment of the present application also includes: Step S541: training the neural network according to the control decision training set to obtain an initial production control decision model.

[0035] Step S542: testing the production control decision initial model according to the control decision test set to obtain a production control decision loss data set.

[0036] Step S543: Optimizing and training the production control decision initial model according to the production control decision loss data set to obtain the nth vegetarian meat powder production control decision model.

[0037] Specifically, the control decision record information refers to the historical records of all control decisions made for the nth vegetarian meat powder production line during the production process, including decision content, time, results and other information. The comprehensive data set of the vegetarian meat powder production line refers to the collection of all control decision record information collected, which is used for subsequent data analysis and model training. The predetermined division ratio refers to the pre-set ratio of dividing the control decision record set into training set and test set when building the model, which is used to ensure the balance of model training and testing. The control decision training set refers to the data set used to train the production control decision model. Through the training set, the model learns how to make effective production control decisions. The control decision test set refers to the data set used to test the performance of the production control decision model. Through the test set, the generalization ability and accuracy of the model are evaluated.

[0038] First, use a data acquisition system or log recording tool, such as a SCADA system, log analysis software, etc., to collect control decision record information of the nth vegetarian meat powder production line in real time or regularly. For example, record the moisture content of the raw materials, the ambient temperature and humidity, when the temperature, humidity and other parameters were adjusted during the production of vegetarian meat powder by the nth vegetarian meat powder production line, and the impact of these adjustments on the production results. Then, use data management tools such as Excel, database management systems, etc. to organize the collected control decision record information, remove invalid and duplicate records, and ensure the quality of the data set. Based on experience or statistical analysis, pre-set a ratio for dividing the control decision record set into a training set and a test set. Divide the sorted control decision record set into a control decision training set and a control decision test set according to the predetermined division ratio, for example, 80% for training and 20% for testing.

[0039] Use machine learning or artificial intelligence tools, such as Python's TensorFlow and Keras libraries, to build a neural network model, and train and test the production control decision model based on the control decision training set and test set. First, use neural network training tools, such as Python's TensorFlow and Keras libraries, to train the neural network based on the control decision training set. Use the training set data to iterate the neural network multiple times, adjust the network parameters to reduce the difference between the predicted results and the actual results, and obtain the initial model of the production control decision. The initial model of the production control decision is a preliminary model obtained by training the control decision training set, and further optimization is required. Use the control decision test set to test the initial model of the production control decision, evaluate the prediction performance of the model, and record the difference between the predicted results and the actual results, that is, the loss data, to obtain the production control decision loss data set, where the production control decision loss data set refers to the difference data set between the model prediction results and the actual results in the test phase, which is used to measure the performance and accuracy of the model. Then, analyze the production control decision loss data set, find out the deviations and deficiencies in the model prediction based on the loss data set, optimize the initial model of the production control decision, adjust the weights and biases of the neural network to minimize the loss function, and improve the prediction accuracy of the model. After the optimization training, the control decision test set was used again to verify the model to ensure that the performance of the model was improved, and finally a trained n-th vegetarian meat powder production control decision model was obtained.

[0040] Further, as another option: Step S54 in the embodiment of the present application may also be the following steps: Step S5401: constructing a multiple linear regression model based on the comprehensive data set of the vegetarian meat powder production line; Step S5402: dividing the vegetarian meat powder production line comprehensive data set into a control decision training set and a control decision test set according to a predetermined ratio; Step S5403: Use the training set to train the regression model to obtain the regression coefficient; Step S5404: Use the test set to verify the accuracy of the model.

[0041] Specifically, Collect control decision record information of the nth vegetarian meat powder production line, including the following types of data: Production process parameters: such as temperature, humidity, stirring speed, mixing time, etc.; Production result data: such as product quality indicators, production efficiency, etc.; External environmental data: such as air temperature and humidity, moisture content of raw materials, etc.

[0042] The collected data is cleaned and organized to facilitate subsequent model training. The data processing method is as follows: Data cleaning: handling missing values, outliers and duplicate data; Data standardization: Standardize the data so that data with different characteristics have the same scale; Feature extraction: extract key features that have an impact on production control from raw data; According to the predetermined division ratio, the data is divided into a control decision training set and a control decision test set. The example assumes that the predetermined division ratio is 80% training set and 20% test set; Select appropriate machine learning algorithms, use the training set to train the production control decision model, and use the test set to evaluate the model performance; It can select commonly used regression or classification models, such as linear regression, decision tree, random forest, support vector machine (SVM), neural network, etc. As a preferred embodiment, this application selects linear regression; Use the test set data to evaluate the model performance and calculate the error between the model prediction results and the actual results, such as the mean square error; According to the test results, adjust the model parameters and hyperparameters to further optimize the model performance. Common optimization methods can be used to further optimize the model performance, including cross-validation, grid search, regularization, etc.

[0043] Verify the model's effectiveness in the actual production environment, collect production feedback data, and further adjust and optimize the model; The optimized model is deployed to the production control system, and the production parameters are dynamically adjusted according to the real-time data to generate the n-th vegetarian meat powder production control decision.

[0044] Step S5 constructs a corresponding production control decision model for each vegetarian meat powder production line, so that it can generate corresponding production control decisions based on the production task information of the production line, ensure the accuracy and reliability of the model output results, and provide a powerful decision-making tool for each link of the vegetarian meat powder production process.

[0045] Step S6: Based on the n-th node vegetarian meat powder production task information and according to the n-th vegetarian meat powder production control decision model, an n-th vegetarian meat powder production control decision is obtained.

[0046] Specifically, the nth vegetarian meat powder production control decision refers to the specific production control decision generated for the nth node vegetarian meat powder production task information according to the nth vegetarian meat powder production control decision model, and these decisions will guide the actual production operation. First, the nth node vegetarian meat powder production task information extracted in step S4 is input into the nth vegetarian meat powder production control decision model. Then, the model performs calculations based on the input information, uses the previously trained neural network algorithm, analyzes the data and predicts the optimal production control strategy. Then, the nth vegetarian meat powder production control decision is output, which includes production scheduling plans, equipment parameter settings, raw material ratio recommendations, etc. Finally, the generated production control decision is implemented in the actual production of the nth production line, the control effect of the control decision is monitored and feedback is given, and a timely response is given when an abnormal situation occurs to ensure the smooth completion of the production task.

[0047] After obtaining the nth vegetarian meat powder production control decision, the system will automatically select another vegetarian meat powder production line and repeat the process from steps S4 to S6 to build corresponding N vegetarian meat powder production control decision models for the N vegetarian meat powder production lines, and generate N vegetarian meat powder production control decisions based on the corresponding N vegetarian meat powder production task information.

[0048] Furthermore, if Figure 3 As shown, step S6 of the embodiment of the present application also includes: Step S61: Collect basic information of the nth vegetarian meat powder production line to obtain the nth production line information.

[0049] Step S62: performing data cleaning according to the nth production line information to obtain the nth production line data.

[0050] Step S63: inputting the n-th node vegetarian meat powder production task information and the n-th production line data into the n-th vegetarian meat powder production control decision model to generate the n-th vegetarian meat powder production control decision.

[0051] Specifically, the basic information of the nth vegetarian meat powder production line refers to the basic situation of the nth vegetarian meat powder production line, including the configuration of the production line, equipment list, technical parameters, production capacity, etc. The nth production line information refers to the basic information of the nth vegetarian meat powder production line after preliminary sorting, which may also contain some noise or inconsistent data. The nth production line data refers to the information of the nth vegetarian meat powder production line after data cleaning, which has reached a high quality and consistency and is suitable for model input.

[0052] First, basic information of the nth vegetarian meat powder production line is collected from sources such as production management systems, equipment maintenance records, and technical documents. For example, the operating status of production line equipment, worker skill levels, and raw material inventory are recorded. Next, the collected basic information is sorted to form preliminary nth production line information. Then, data cleaning is performed on the nth production line information, using data cleaning tools such as Pandas library, OpenRefine, Excel, etc. to remove duplicate records, correct erroneous data, fill in missing values, and unify data formats. The cleaned nth production line data and the nth node vegetarian meat powder production task information are input into the nth vegetarian meat powder production control decision model. The model analyzes and calculates based on the input data to generate specific nth vegetarian meat powder production control decisions. For example, based on the production task information and production line data, the model may predict the best production parameter settings, such as temperature, humidity, equipment running speed, etc. In this way, effective production control decisions can be generated based on the characteristics of the production line and the production task requirements, guiding the control of the production process and improving production efficiency and product quality.

[0053] Furthermore, the present application can optimize the model parameters through the following functions:

[0054] Among them, L is the loss function, that is, the mean square error, N is the number of samples, i is the prediction result of the i-th sample, a i is the actual result of the i-th sample.

[0055] Adjust production parameters based on the gradient of the loss function; Among them, the method of adjusting the production parameters according to the gradient of the loss function includes: In order to update the model parameters, we need to calculate the gradient of the loss function L with respect to each model parameter. For a simple linear regression model:

[0056] The gradient is as follows:

[0057] in: β j is the jth parameter; x ij is the jth feature of the ith sample.

[0058] In each iteration, the model parameters are updated according to the gradient descent method;

[0059] in: β j （t） is the parameter value at the tth iteration; β j （t+1） is the parameter value at the t+1th iteration; η is the learning rate, which controls the step size of each update; is the loss function L at the tth iteration with respect to the parameter β j The gradient of , so that it can adjust the production parameters to minimize the loss function by calculating the gradient; In each iteration, the parameter β is adjusted according to the current gradient j ; The direction of its adjustment is opposite to the direction of the gradient.

[0060] Through this iterative update process, we can gradually adjust the production parameters to make the production results closer to the target results to improve the accuracy and efficiency of the production process.

[0061] Furthermore, if Figure 3 As shown, step S6 of the embodiment of the present application also includes: Step S64: controlling the nth vegetarian meat powder production line according to the nth vegetarian meat powder production control decision to obtain control feedback data of the nth production line.

[0062] Step S65: Compare the n-th vegetarian meat powder production control decision and the n-th production line control feedback data to obtain the n-th production line control deviation coefficient.

[0063] Step S66: Determine whether the control deviation coefficient of the nth production line is greater than the production line control deviation threshold.

[0064] Step S67: If the control deviation coefficient of the nth production line is greater than the production line control deviation threshold, an nth production line control warning signal is generated.

[0065] Specifically, the nth production line control feedback data refers to the real-time feedback data collected from the nth vegetarian meat powder production line after the implementation of the nth vegetarian meat powder production control decision, including production indicators, equipment status, product quality, etc. The nth production line control deviation coefficient is an indicator to measure the difference between the actual effect and the expected effect of the production control decision. The larger the value, the higher the degree of deviation. The production line control deviation threshold is a preset value used to determine whether the degree of deviation of the production control decision is within an acceptable range. The nth production line control early warning signal is a signal generated when it is detected that the nth production line control deviation coefficient exceeds the threshold, which is used to remind management personnel to take measures to adjust the production control strategy.

[0066] First, use automated control systems, such as PLC, SCADA systems, etc., to actually control the nth vegetarian meat powder production line according to the nth vegetarian meat powder production control decision, for example, adjust the equipment parameters on the production line according to the optimal temperature and humidity settings predicted by the decision model. Use data acquisition tools, such as sensors, monitoring systems, etc., to collect control feedback data on the production line in real time. For example, record the actual temperature and humidity changes of the production line after executing the parameter settings generated by the decision model.

[0067] Then, compare the production control decision of the nth vegetarian meat powder with the actual control feedback data, use data analysis tools, such as Excel, statistical analysis software, etc., to analyze the collected control feedback data, and calculate the difference coefficient between the production control decision and the actual feedback data, that is, the control deviation coefficient of the nth production line. The control deviation coefficient is the ratio of the deviation to the reference value, usually expressed as a percentage. For example, if the actual temperature is lower than the predicted temperature, calculate the deviation between the actual temperature and the predicted temperature, and then calculate the control deviation coefficient. Assuming the actual temperature is 29°C and the predicted temperature is 30°C, then the deviation is 1°C and the control deviation coefficient is .

[0068] Determine whether the control deviation coefficient of the nth production line is greater than the preset production line control deviation threshold. If the control deviation coefficient is less than or equal to the threshold, it is considered that the control effect is good and no further adjustment is required. If the control deviation coefficient is greater than the threshold, a control warning signal for the nth production line is generated to notify relevant managers to intervene. The above process can adjust the production control strategy in a timely manner to ensure production efficiency and product quality by monitoring and evaluating the execution effect of the production control strategy.

[0069] Step S6 utilizes the production control decision model to generate the nth vegetarian meat powder production control decision corresponding to the nth vegetarian meat powder production line, and monitors the control effect of the production control decision to achieve refined and intelligent control of the production process and improve production efficiency and product quality.

[0070] Furthermore, step S2 of the embodiment of the present application also includes: Step S21: collecting real-time monitoring parameters of the N vegetarian meat powder production lines to obtain real-time monitoring data of the N production lines.

[0071] Step S22: performing fault analysis on the N vegetarian meat powder production lines according to the real-time monitoring data of the N production lines to obtain fault analysis results of the N production lines.

[0072] Step S23: providing fault warnings for the N vegetarian meat powder production lines according to the fault analysis results of the N production lines.

[0073] Specifically, real-time monitoring parameters refer to various data about the operating status of the production line, such as temperature, pressure, flow, speed, etc., collected in real time by sensors and monitoring equipment installed on the production line during the production process. Real-time monitoring data of N production lines: refers to the collection of N real-time monitoring parameters collected from N vegetarian meat powder production lines, which reflect the immediate operating status of the production line. Fault analysis results refer to the conclusions drawn after fault analysis of N vegetarian meat powder production lines, including possible fault types, causes, risk levels, etc.

[0074] First, various monitoring parameters of N vegetarian meat powder production lines are collected in real time through sensors and monitoring equipment installed on the production line. The collected real-time monitoring data are sorted to obtain real-time monitoring data of N production lines, and each real-time monitoring data corresponds to a production line. Then, according to the sorted real-time monitoring data of N production lines, data analysis tools such as Excel and data mining software are used to analyze the collected real-time monitoring data to obtain the fault analysis results of N production lines. For example, by analyzing the temperature and pressure data, it is identified whether there are abnormal fluctuations or values ​​outside the normal range. According to the fault analysis results of N production lines, an early warning system, such as monitoring software, SMS notifications, etc., is used to generate a warning signal according to the fault analysis results. For example, if the temperature data continues to exceed the normal range, the early warning system will issue a fault warning signal to prompt the operator to check.

[0075] For example, first, the monitoring parameters of the production line, including the speed of the mixer, the temperature of the drying chamber, the speed of the packaging machine, etc., are collected in real time through temperature sensors and pressure sensors distributed on each production line. The collected real-time data is summarized and sorted using the PLC system to generate real-time monitoring data of the production line and transmit it to the data analysis software. The data is preliminarily sorted and cleaned using data processing software such as Excel. Then, the Scikit-learn library of Python is used to perform fault analysis on these data, and anomaly detection algorithms are used to identify abnormal patterns. The analysis results show that the temperature of the drying chamber of the third production line has fluctuated abnormally and exceeded the preset threshold, which may be caused by the aging of the heating element. Then, a fault warning signal is automatically generated, and the maintenance team is notified through mobile phone APP and email.

[0076] The above steps ensure the smooth progress of the production process and the consistency of product quality by real-time monitoring of the operating status of the production line, timely detection and handling of potential faults, which helps to improve production efficiency, reduce production costs and achieve optimal allocation of resources.

[0077] In summary, the intelligent control method for the vegetarian meat powder production line provided in the embodiment of the present application has the following technical effects: Obtain the vegetarian meat powder production task, clarify the production goals and requirements, and provide a basis for subsequent task allocation and production planning. Determine N vegetarian meat powder production lines, where N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node, master the existing production line resource allocation information, and provide data collection and analysis targets for subsequent control decision generation. According to the N vegetarian meat powder production lines, feature decompose the vegetarian meat powder production task, obtain the N-node vegetarian meat powder production task information, refine the production tasks, and provide accurate data reference for the subsequent construction of the production control decision model. According to the N-node vegetarian meat powder production task information, extract the n-node vegetarian meat powder production task information corresponding to the n-node vegetarian meat powder production line, where n is a positive integer, 1≤n≤N, and construct the n-node vegetarian meat powder production control decision model according to the n-node vegetarian meat powder production task information. Based on the n-node vegetarian meat powder production task information, according to the n-node vegetarian meat powder production control decision model, obtain the n-node vegetarian meat powder production control decision, and automatically generate the corresponding control strategy for each production line to achieve precise control. According to the generated nth vegetarian meat powder production control decision, the nth vegetarian meat powder production line is controlled, the control effect of the production control decision is monitored, the control feedback data of the nth production line is obtained, the control deviation coefficient is calculated according to the control feedback data of the nth production line, and a control early warning signal is generated, so that the control decision can be adjusted in time according to the control effect, closed-loop control is achieved, and the flexibility and control effect of the control decision are improved. In addition, fault analysis and fault early warning are performed according to the real-time monitoring data of N production lines, and problems in the production process are discovered and responded to in time to ensure the safety and stability of the production process.

[0078] To summarize, this application constructs a control decision model for each production line, intelligently generates corresponding production control strategies, and monitors the control effects of production control decisions in real time. It issues timely warnings when the control effects deviate from expectations, and reminds operators to adjust control decisions in a timely manner, thereby ensuring the accuracy and reliability of production control decisions, realizing refined management and optimized control of the vegetarian meat powder production process, and helping to improve product quality and production efficiency.

[0079] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides an intelligent control system for a vegetarian meat powder production line, the system comprising: The task acquisition module 10 is used to obtain the vegetarian meat powder production task.

[0080] The production line determination module 20 is used to determine N vegetarian meat powder production lines, wherein N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node.

[0081] The feature disassembly module 30 is used to perform feature disassembly on the vegetarian meat powder production task according to the N vegetarian meat powder production lines to obtain N node vegetarian meat powder production task information.

[0082] The task information extraction module 40 is used to extract the n-node vegetarian meat powder production task information corresponding to the n-node vegetarian meat powder production line according to the N-node vegetarian meat powder production task information, wherein n is a positive integer, 1≤n≤N.

[0083] The decision model building module 50 is used to build an n-th vegetarian meat powder production control decision model according to the n-th vegetarian meat powder production line.

[0084] The control decision generation module 60 is used to obtain the nth vegetarian meat powder production control decision based on the nth node vegetarian meat powder production task information and the nth vegetarian meat powder production control decision model.

[0085] Furthermore, the feature disassembly module 30 described in the embodiment of the present application is also used to perform the following steps: According to the N vegetarian meat powder production lines, feature identification is performed on the vegetarian meat powder production tasks to obtain feature information of N node production tasks.

[0086] Data cleaning is performed based on the production task characteristic information of the N nodes to obtain the vegetarian meat powder production task information of the N nodes.

[0087] Furthermore, the decision model building module 50 described in the embodiment of the present application is also used to perform the following steps: The control decision record information corresponding to the nth vegetarian meat powder production line is collected to obtain a comprehensive data set of the vegetarian meat powder production line.

[0088] Obtain a predetermined division ratio.

[0089] The vegetarian meat powder production line comprehensive data set is divided according to the predetermined division ratio to obtain a control decision training set and a control decision test set.

[0090] Training and testing are performed according to the control decision training set and the control decision test set to generate the nth vegetarian meat powder production control decision model.

[0091] Furthermore, the decision model building module 50 described in the embodiment of the present application is also used to perform the following steps: A multiple linear regression model was constructed based on the comprehensive dataset of vegetarian meat powder production line; The comprehensive dataset of the vegetarian meat powder production line is divided into a control decision training set and a control decision test set according to a predetermined ratio; Use the training set to train the regression model and obtain the regression coefficient; Use the test set to verify the accuracy of the model.

[0092] Furthermore, the control decision generation module 60 described in the embodiment of the present application is also used to perform the following steps: Collect basic information of the nth vegetarian meat powder production line to obtain the nth production line information.

[0093] Data cleaning is performed according to the nth production line information to obtain the nth production line data.

[0094] The n-th node vegetarian meat powder production task information and the n-th production line data are input into the n-th vegetarian meat powder production control decision model to generate the n-th vegetarian meat powder production control decision.

[0095] Furthermore, the control decision generation module 60 described in the embodiment of the present application is also used to perform the following steps: The nth vegetarian meat powder production line is controlled according to the nth vegetarian meat powder production control decision to obtain control feedback data of the nth production line.

[0096] The nth vegetarian meat powder production control decision and the nth production line control feedback data are compared to obtain the nth production line control deviation coefficient.

[0097] It is determined whether the nth production line control deviation coefficient is greater than a production line control deviation threshold.

[0098] If the control deviation coefficient of the nth production line is greater than the production line control deviation threshold, an nth production line control warning signal is generated.

[0099] Furthermore, the production line determination module 20 described in the embodiment of the present application is also used to perform the following steps: The real-time monitoring parameters of the N vegetarian meat powder production lines are collected to obtain the real-time monitoring data of the N production lines.

[0100] Perform fault analysis on the N vegetarian meat powder production lines according to the real-time monitoring data of the N production lines to obtain fault analysis results of the N production lines.

[0101] According to the fault analysis results of the N production lines, fault warnings are issued to the N vegetarian meat powder production lines.

[0102] Through the above-mentioned detailed description of the intelligent control method of the vegetarian meat powder production line in this specification, those skilled in the art can clearly understand the intelligent control system of the vegetarian meat powder production line in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1, it has corresponding functional modules and beneficial effects. For relevant matters, please refer to the description of the method part.

[0103] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Intelligent control method for vegetarian meat powder production line, characterized in that: The method comprises: Obtain the task of producing vegetarian meat powder; Determine N vegetarian meat powder production lines, where N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node; According to the N vegetarian meat powder production lines, feature-decompose the vegetarian meat powder production tasks to obtain N node vegetarian meat powder production task information; Extracting the nth node vegetarian meat powder production task information corresponding to the nth vegetarian meat powder production line according to the N nodes vegetarian meat powder production task information, wherein n is a positive integer, 1≤n≤N; According to the nth vegetarian meat powder production line, constructing the nth vegetarian meat powder production control decision model; Based on the n-th node vegetarian meat powder production task information and according to the n-th vegetarian meat powder production control decision model, an n-th vegetarian meat powder production control decision is obtained.

2. The method according to claim 1, characterized in that According to the N vegetarian meat powder production lines, the vegetarian meat powder production task is feature-decomposed to obtain N node vegetarian meat powder production task information, including: According to the N vegetarian meat powder production lines, feature identification is performed on the vegetarian meat powder production tasks to obtain feature information of N node production tasks; Data cleaning is performed based on the production task characteristic information of the N nodes to obtain the vegetarian meat powder production task information of the N nodes.

3. The method according to claim 1, characterized in that According to the nth vegetarian meat powder production line, an nth vegetarian meat powder production control decision model is constructed, including: Collecting control decision record information and external factor data corresponding to the nth vegetarian meat powder production line, integrating the control decision record information with the external factor data, and obtaining a comprehensive data set of the vegetarian meat powder production line; Obtaining a predetermined allocation ratio; Divide the vegetarian meat powder production line comprehensive data set according to the predetermined division ratio to obtain a control decision training set and a control decision test set; Training and testing are performed according to the control decision training set and the control decision test set to generate the nth vegetarian meat powder production control decision model.

4. The method according to claim 3, characterized in that Training and testing are performed according to the control decision training set and the control decision test set to generate the nth vegetarian meat powder production control decision model, including: A multiple linear regression model was constructed based on the comprehensive dataset of vegetarian meat powder production line; The comprehensive dataset of the vegetarian meat powder production line is divided into a control decision training set and a control decision test set according to a predetermined ratio; Use the training set to train the regression model and obtain the regression coefficient; Use the test set to verify the accuracy of the model.

5. The method according to claim 1, characterized in that Based on the nth node vegetarian meat powder production task information and according to the nth vegetarian meat powder production control decision model, the nth vegetarian meat powder production control decision is obtained, including: Collecting basic information of the nth vegetarian meat powder production line to obtain information of the nth production line; Perform data cleaning according to the nth production line information to obtain the nth production line data; The n-th node vegetarian meat powder production task information and the n-th production line data are input into the n-th vegetarian meat powder production control decision model to generate the n-th vegetarian meat powder production control decision.

6. The method according to claim 1, characterized in that Obtaining the production control decision of the nth vegetarian meat powder also includes: Controlling the nth vegetarian meat powder production line according to the nth vegetarian meat powder production control decision to obtain control feedback data of the nth production line; Comparing the nth vegetarian meat powder production control decision with the nth production line control feedback data to obtain the nth production line control deviation coefficient; Determining whether the control deviation coefficient of the nth production line is greater than a production line control deviation threshold; If the control deviation coefficient of the nth production line is greater than the production line control deviation threshold, an nth production line control warning signal is generated.

7. The method according to claim 1, characterized in that Determine N vegetarian meat powder production lines, including: Collecting real-time monitoring parameters of the N vegetarian meat powder production lines to obtain real-time monitoring data of the N production lines; Performing fault analysis on the N vegetarian meat powder production lines according to the real-time monitoring data of the N production lines to obtain fault analysis results of the N production lines; Providing fault warnings to the N vegetarian meat powder production lines according to the fault analysis results of the N production lines; An intelligent control system for a vegetarian meat powder production line, wherein the system is used to execute the method according to any one of claims 1 to 7, characterized in that the system comprises: A task acquisition module, the task acquisition module is used to obtain a vegetarian meat powder production task; A production line determination module, the production line determination module is used to determine N vegetarian meat powder production lines, wherein N is a positive integer greater than 1, and each vegetarian meat powder production line corresponds to a vegetarian meat powder production node; A feature disassembly module, wherein the feature disassembly module is used to perform feature disassembly on the vegetarian meat powder production task according to the N vegetarian meat powder production lines, and obtain the vegetarian meat powder production task information of N nodes; A task information extraction module, the task information extraction module is used to extract the n-th node vegetarian meat powder production task information corresponding to the n-th vegetarian meat powder production line according to the N-node vegetarian meat powder production task information, wherein n is a positive integer, 1≤n≤N; A decision model building module, wherein the decision model building module is used to build an n-th vegetarian meat powder production control decision model according to the n-th vegetarian meat powder production line; A control decision generation module, wherein the control decision generation module is used to obtain an nth vegetarian meat powder production control decision based on the nth node vegetarian meat powder production task information and according to the nth vegetarian meat powder production control decision model.

Images