Quarter-system for online customization of gypsum plaster board

Abstract

The invention relates to the technical field of gypsum plaster boards, provides an online customization four-subsystem system for gypsum plaster boards, and aims to solve the problem of material waste caused by incapability of pre-analyzing a sawing process in the prior art, and the system comprises a data acquisition module, a sawing prediction module, a data analysis module, a sawing verification module, a sawing optimization module and the like. A random forest and a deep learning model are trained through preprocessing historical data, and accurate prediction and control of sawing equipment are achieved. And after sawing, the system verifies sawing errors in real time, the control model is optimized through a genetic algorithm, and the sawing precision is improved. According to the invention, the sawing efficiency is effectively improved, the material waste is reduced, the diversified construction requirements are met, and the intelligent production is realized.

Description

Technical Field

[0001] The invention relates to the technical field of gypsum boards, and in particular to an online custom four-part system for gypsum boards. Background Art

[0002] The online customized four-point gypsum board sawing of large panels is widely used in interior decoration and construction projects. When performing online customized four-point sawing of large panels, mechanical equipment is usually used, such as fully automatic four-sided cutting saws or high-precision CNC sawing machines. The fully automatic four-sided cutting saw can improve the accuracy and efficiency of cutting, while reducing the generation of dust, protecting the construction environment and the health of workers. Before sawing, it is necessary to mark the lines to be cut on the gypsum board, and then use the infrared positioning or CNC adjustment function of the mechanical equipment for precise cutting. The customized sawing method is not only suitable for cutting large-area gypsum boards, but can also be flexibly adjusted according to specific needs to meet different construction requirements.

[0003] The existing online customized four-point gypsum board sawing is to cut the gypsum board according to the preset sawing requirements, and it is impossible to perform a pre-analysis before the gypsum board is sawed. When large panels are cut in large quantities, if the large panels are not pre-analyzed and the sawing process is not calibrated, when errors occur in the gypsum board sawing, it will lead to waste of gypsum board materials. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an online customized four-part gypsum board system, which solves the problem that the existing online customized four-part gypsum board sawing is to cut the gypsum board according to the preset sawing requirements, and it is impossible to perform a preliminary analysis before the gypsum board is sawed. When large boards are cut in large quantities, if the sawing of the large boards is not pre-analyzed and the sawing process is not calibrated, when errors occur in the sawing of the gypsum board, it will lead to waste of gypsum board materials.

[0005] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0006] The present invention provides a four-part system for online customization of gypsum board, comprising:

[0007] Data acquisition module, which acquires historical data of raw materials, production process, equipment status, product specifications, customer demand and quality control;

[0008] The sawing prediction module preprocesses the raw material historical data, the production process historical data, the equipment status historical data, the product specification historical data, the customer demand historical data and the quality control historical data to obtain the preprocessed data, uses the preprocessed data to train the random forest model to obtain the sawing equipment prediction model, receives the real-time customer demand data and the real-time sawing quality standard, substitutes the real-time customer demand data into the sawing equipment prediction model to obtain the sawing equipment prediction data;

[0009] The data analysis module obtains the historical data of the four-part system for online customization of gypsum boards and the historical data of the operation of sawing equipment, trains the deep learning model with the historical data of customer demand, historical data of quality control, historical data of the four-part system for online customization of gypsum boards, and historical data of the operation of sawing equipment, obtains the control model of the four-part system for online customization of gypsum boards, substitutes the real-time customer demand data into the control model of the four-part system for online customization of gypsum boards, and outputs the real-time control parameters of the four-part system for online customization of gypsum boards;

[0010] The sawing verification module transmits the control parameters of the real-time gypsum board online customization four-part system to the sawing equipment in the gypsum board online customization four-part system. After the sawing equipment executes the control parameters of the real-time gypsum board online customization four-part system, it generates the real-time operation data of the first sawing equipment, compares the real-time operation data of the first sawing equipment with the predicted data of the sawing equipment, and obtains the sawing error data;

[0011] The sawing optimization module optimizes the online customization four-part system control model of gypsum board to obtain the optimized online customization four-part system control model of gypsum board, substitutes the real-time customer demand data into the optimized online customization four-part system control model of gypsum board to obtain the optimized real-time online customization four-part system control parameters of gypsum board, generates the sawing equipment control parameters at the position to be corrected, and the sawing equipment executes the sawing equipment control parameters at the position to be corrected to complete the cutting of the gypsum board to be cut.

[0012] Furthermore, in the four-part system for online customization of gypsum board of the present invention, the data acquisition module comprises:

[0013] Extract features of the four-part system for online customization of gypsum board to obtain feature data of the four-part system for online customization of gypsum board, and determine the type of data to be obtained based on the feature data of the four-part system for online customization of gypsum board;

[0014] Acquire data according to the type of data to be acquired, and perform data continuity check on the acquired data. If there is data missing, generate data missing warning information;

[0015] Substitute the preset data missing warning information into the data simulation generation model of the four-part system for online customization of gypsum board to generate simulation data corresponding to the data missing warning information, and fill the missing data with the simulation data corresponding to the data missing warning information.

[0016] Furthermore, the sawing prediction module of the four-part online customization system for gypsum board of the present invention comprises:

[0017] Receiving real-time demand data from customers through a data interface or a user input interface, where the real-time demand data from customers includes the size, shape and quantity of gypsum boards;

[0018] Receive real-time sawing quality standards, including sawing accuracy, allowable error range and surface quality;

[0019] Substitute the pre-processed real-time customer demand data into the trained sawing equipment prediction model. The sawing equipment prediction model is trained based on historical data of raw materials, historical data of production processes, and historical data of equipment status. The sawing equipment prediction model predicts the operating parameters and output results of the sawing equipment based on the input customer demand data.

[0020] The prediction data of the sawing equipment is obtained by calculating the sawing equipment prediction model, and the prediction data of the sawing equipment includes sawing position prediction parameters, speed prediction parameters and cutting depth prediction parameters.

[0021] Furthermore, the data analysis module of the four-part online customization system for gypsum board of the present invention includes:

[0022] The historical data of the four-part system for online customization of gypsum board and the historical data on the operation of sawing equipment, the historical data on customer demand, the historical data on quality control, the historical data on the four-part system for online customization of gypsum board and the historical data on the operation of sawing equipment are divided into a training set and a validation set;

[0023] The selected deep learning model is trained using the preprocessed training data set. During the training process, the weight of the model is adjusted through the back propagation algorithm, the model is verified using the validation set, the trained model is evaluated using the test set, the performance indicators of the model are calculated, and the model is optimized based on the evaluation results to obtain the four-part system control model for online customization of gypsum board.

[0024] Furthermore, the sawing verification module of the four-part system for online customization of gypsum board of the present invention comprises:

[0025] Acquire the real-time operation data of the first sawing device from the sawing device, wherein the real-time operation data of the first sawing device includes an actual position parameter, an actual speed parameter, and an actual depth parameter of the sawing;

[0026] Aligning the real-time operation data of the first sawing device with the prediction data of the sawing device in time and space;

[0027] Compare the real-time operation data of the first sawing device with the predicted data of the sawing device item by item, and calculate the error of each data, that is, the difference between the actual value and the predicted value;

[0028] All calculated errors are summarized, and sawing error data is generated based on the error summary results.

[0029] Furthermore, the sawing optimization module of the four-part system for online customization of gypsum board of the present invention comprises:

[0030] The real-time operation data of the first sawing equipment is compared with the real-time sawing quality standard. When the sawing error data is greater than the real-time sawing quality standard, the operation data of the data acquisition end is obtained, and the data acquisition end is inspected based on the operation data of the data acquisition end. If the inspection of the data acquisition end is qualified, the control model of the gypsum board online customization four-point system is optimized using a genetic algorithm based on the sawing error data, the historical data of the gypsum board online customization four-point system and the sawing equipment operation history data to obtain the optimized gypsum board online customization four-point system control model, and the real-time customer demand data is substituted into the optimized gypsum board online customization four-point system control model to obtain the optimized real-time gypsum board online customization four-point system control parameters. The real-time online customization of gypsum board four-part system control parameters are substituted into the sawing equipment prediction model to generate the real-time operation data of the second sawing equipment, and the real-time operation data of the second sawing equipment is compared with the real-time sawing quality standard. If the real-time operation data of the second sawing equipment meets the range of the real-time sawing quality standard, the image data of the cut gypsum board is collected, and the image data of the cut gypsum board is compared with the real-time customer demand data to obtain the position to be corrected of the image data of the cut gypsum board, and the position to be corrected of the image data of the cut gypsum board is transmitted to the optimized online customization of gypsum board four-part system control model to generate the control parameters of the sawing equipment at the position to be corrected, and the sawing equipment executes the control parameters of the sawing equipment at the position to be corrected to complete the cutting of the cut gypsum board.

[0031] Furthermore, the sawing optimization module of the four-part system for online customization of gypsum board of the present invention comprises:

[0032] Determine the optimization target based on sawing error data and real-time sawing quality standards;

[0033] Obtain sawing error data, historical data of the four-part system for online customization of gypsum board, and historical data of sawing equipment operation, and send sawing error data, historical data of the four-part system for online customization of gypsum board, and historical data of sawing equipment operation

[0034] As the input data of genetic algorithm optimization, it is used to train and optimize the online customized four-part system control model of gypsum board;

[0035] Receive and set the parameters of the genetic algorithm, including population size, selection, crossover, mutation probability, and number of iterations;

[0036] Initialize the population, use a random or specific method to generate the initial population, each individual represents a possible control model parameter combination;

[0037] Evaluate each individual in the population and calculate its fitness value;

[0038] Select excellent individuals as parents according to the fitness value to generate the next generation. The selection operation can adopt roulette selection or tournament selection method.

[0039] Perform a crossover operation on the selected parent generation to generate new offspring individuals;

[0040] Perform mutation operations on offspring individuals, introduce new genes, and replace the old population with the newly generated offspring individuals to form a new generation of population;

[0041] Repeat selection, crossover, and mutation until the predetermined number of iterations is reached or the optimization goal is met;

[0042] The individuals with the highest fitness value are selected from the final population as the parameters of the optimized four-part system control model for online customization of gypsum board;

[0043] The control model is updated using the parameters of the optimized gypsum board online customization four-part system control model to obtain the optimized gypsum board online customization four-part system control model.

[0044] Beneficial effects of the present invention:

[0045] By introducing a data acquisition module, a sawing prediction module, a data analysis module, etc., the present invention can make accurate predictions and analyses before sawing operations, thereby improving sawing accuracy and efficiency. Real-time calibration and optimization mechanisms ensure that sawing operations can always maintain a high level of accuracy, reducing material waste caused by sawing errors.

[0046] By performing preliminary analysis and prediction before sawing, the present invention can effectively avoid waste of gypsum board materials due to errors in the mass cutting process. The real-time sawing verification and optimization mechanism further ensures the accuracy of each sawing operation and reduces the scrap rate.

[0047] The present invention can perform customized sawing operations according to the real-time needs of customers to meet their diverse needs. Optimized sawing parameters and accurate cutting results improve product quality, thereby improving customer satisfaction. By integrating a variety of advanced data processing and analysis technologies (such as random forest models, deep learning models, genetic algorithms, etc.), the present invention significantly improves the intelligence and automation level of the system. It reduces the need for manual intervention, reduces the possibility of human error, and improves production efficiency and consistency.

[0048] The present invention establishes a closed-loop optimization mechanism, which continuously optimizes and improves the system control model by continuously collecting and analyzing data during the sawing process. The ability to continuously improve enables the system to adapt to changing customer needs and production environments, maintaining its competitiveness and flexibility.

[0049] The present invention can quickly respond to changes in customer demand in real time, adjust sawing parameters and production plans, and improve production flexibility and response speed. It helps enterprises maintain their competitive advantage in a highly competitive market environment and quickly meet market demand.

[0050] In summary, the present invention has established an efficient, intelligent and flexible online customization four-part system for gypsum board by introducing a variety of advanced data processing and analysis technologies, which has significantly improved the sawing accuracy and efficiency, reduced material waste, and improved customer satisfaction and the intelligence and automation level of the system. At the same time, through continuous optimization and improvement of the mechanism, the present invention has also promoted the improvement of production flexibility and response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0052] Figure 1 A schematic diagram of the functional modules of a four-part system for online customization of gypsum board provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings. In order to better understand the purpose of the present invention, the present invention is further described in detail below.

[0054] The present invention provides a four-part system for online customization of gypsum board, comprising:

[0055] Data acquisition module, which acquires historical data of raw materials, production process, equipment status, product specifications, customer demand and quality control;

[0056] In the four-part system for online customization of gypsum board, it is responsible for collecting and integrating various historical data to support subsequent data analysis and sawing prediction. Specifically, the data acquisition module needs to obtain the following types of historical data:

[0057] The raw material history data records the relevant information of the gypsum board raw materials used in the past, such as the source, batch, quality parameters (such as density, strength, moisture content, etc.) of the raw materials. By analyzing the raw material history data, we can understand the stability and quality fluctuation of the raw materials, thus providing a reference for the setting of sawing parameters.

[0058] Production process history data: Production process data reflects the process parameters and conditions of each link in the gypsum board production process, such as temperature, humidity, pressure, curing time, etc. These data are crucial to understanding how variables in the production process affect the final quality and sawing performance of the gypsum board.

[0059] Equipment status history data: Equipment status data records the status information of the sawing equipment in the past operation, such as the degree of equipment wear, fault records, maintenance records, etc. By analyzing the equipment status data, the current performance of the equipment can be predicted, potential problems can be discovered in time, and material waste caused by equipment failure during the sawing process can be avoided.

[0060] Product specification history data: Product specification data describes the size, shape, thickness and other specifications of different batches or types of gypsum boards. This data is essential for understanding customer needs and customizing sawing solutions.

[0061] Customer demand history data: Customer demand data records the specific needs of customers for gypsum board products, such as size, shape, quantity, delivery time, etc. By analyzing the historical customer demand data, we can understand the trends and changes in market demand and provide a basis for formulating more accurate sawing plans.

[0062] Quality control historical data: Quality control data records the quality information of gypsum board products during the production process and final inspection, such as dimensional deviation, surface quality, strength test results, etc. These data are very important for evaluating the product qualification rate and quality control level, and also provide feedback for the optimization of sawing parameters.

[0063] The data acquisition module provides a basis for subsequent sawing prediction, data analysis and system control by collecting and integrating these historical data.

[0064] The sawing prediction module preprocesses the raw material historical data, the production process historical data, the equipment status historical data, the product specification historical data, the customer demand historical data and the quality control historical data to obtain the preprocessed data, uses the preprocessed data to train the random forest model to obtain the sawing equipment prediction model, receives the real-time customer demand data and the real-time sawing quality standard, substitutes the real-time customer demand data into the sawing equipment prediction model to obtain the sawing equipment prediction data;

[0065] The sawing prediction module is the main function of the four-part system for online customization of gypsum board. It uses historical data to predict the sawing process, thereby providing guidance and optimization suggestions for the actual sawing operation. The following are the detailed steps of the module's work:

[0066] The sawing prediction module preprocesses various historical data obtained from the data acquisition module. The preprocessing steps may include data cleaning (removing outliers, processing missing values), data transformation (such as normalization, standardization), feature selection (selecting key factors that affect sawing prediction), etc. The preprocessed data will be more accurate, consistent, and more suitable for subsequent model training.

[0067] The random forest model is trained using the preprocessed data. Random forest is an ensemble learning method that improves the accuracy and stability of predictions by building multiple decision trees and combining their prediction results. During the training process, the model learns the relationship between various factors in historical data (such as raw material quality, production process parameters, equipment status, etc.) and sawing results, thereby establishing a sawing equipment prediction model.

[0068] When the system receives real-time customer demand data (such as the size, shape, quantity, etc. of gypsum boards) and real-time sawing quality standards (such as sawing accuracy, allowable error range, surface quality, etc.), the sawing prediction module will input these real-time data into the trained sawing equipment prediction model.

[0069] The sawing prediction module predicts the operating parameters and output results of the sawing equipment under the current conditions based on the input data and the rules learned from the historical data, namely the sawing equipment prediction data. These prediction data may include key parameters such as sawing position, speed, cutting depth, etc. According to the prediction data output by the sawing equipment prediction model, the system can set parameters for the sawing equipment, such as adjusting the position, speed, cutting depth, etc. of the saw blade, to ensure that the sawing operation can be carried out according to the expected accuracy and quality standards.

[0070] Through the work of the sawing prediction module, the system can accurately predict and preview the sawing process before the sawing operation, thereby avoiding deviations and errors in the actual sawing process, reducing material waste, and improving production efficiency and product quality. At the same time, the sawing prediction module can also continuously update and optimize the prediction model based on historical data and real-time data to adapt to gypsum board sawing tasks of different batches, different specifications, and different needs.

[0071] The data analysis module obtains the historical data of the four-part system for online customization of gypsum boards and the historical data of the operation of sawing equipment, trains the deep learning model with the historical data of customer demand, historical data of quality control, historical data of the four-part system for online customization of gypsum boards, and historical data of the operation of sawing equipment, obtains the control model of the four-part system for online customization of gypsum boards, substitutes the real-time customer demand data into the control model of the four-part system for online customization of gypsum boards, and outputs the real-time control parameters of the four-part system for online customization of gypsum boards;

[0072] The data analysis module is responsible for processing and analyzing various historical data in the four-part system of online customization of gypsum board to build an efficient system control model to guide the actual production process. The following is a detailed explanation of the workflow of the data analysis module and its specific role:

[0073] The data analysis module will first collect necessary data from inside and outside the system, including historical operation data of the four-part system for online customization of gypsum board, historical operation data of sawing equipment, historical customer demand data, historical quality control data, etc.

[0074] The collected raw data often needs to be preprocessed to ensure the quality and consistency of the data. This includes steps such as data cleaning (removing noise, processing missing values), data transformation (such as normalization, standardization), and feature selection.

[0075] Use the preprocessed data to train the deep learning model. The deep learning model is a powerful machine learning tool that can learn hidden laws and patterns from complex data. In this process, customer demand history data, quality control history data, system history data, and sawing equipment operation history data are used to train the model to establish the relationship between input (customer demand) and output (system control parameters).

[0076] Through optimization techniques such as back-propagation algorithms, the parameters of the deep learning model are continuously adjusted to minimize the prediction error and improve the prediction accuracy of the model.

[0077] When new customer requirements are input, the data analysis module will substitute these real-time customer demand data into the trained gypsum board online customization four-part system control model. The model will quickly calculate the optimal system control parameters based on the input data, and these parameters will directly guide the operation of the sawing equipment to ensure that the gypsum board products produced meet customer requirements.

[0078] The data analysis module will also continuously receive new operational data and quality control data, which will be used for continuous learning and improvement of the model. Over time, the model will be able to automatically adapt to changes in the production process and maintain the accuracy and effectiveness of its prediction and control capabilities.

[0079] Through the work of the data analysis module, the four-part system for online customization of gypsum board can realize intelligent and automated production control, improve production efficiency, reduce production costs, and at the same time improve the stability and consistency of product quality.

[0080] The sawing verification module transmits the control parameters of the real-time gypsum board online customization four-part system to the sawing equipment in the gypsum board online customization four-part system. After the sawing equipment executes the control parameters of the real-time gypsum board online customization four-part system, it generates the real-time operation data of the first sawing equipment, compares the real-time operation data of the first sawing equipment with the predicted data of the sawing equipment, and obtains the sawing error data;

[0081] The sawing verification module is responsible for verifying and optimizing the sawing process in the four-part system of online customization of gypsum board, so that the actual sawing operation is consistent with the expected goal. The following is the specific workflow of the sawing verification module:

[0082] The sawing verification module first receives the real-time gypsum board online customization four-part system control parameters output by the data analysis module, and then transmits the real-time gypsum board online customization four-part system control parameters to the sawing equipment in the gypsum board online customization four-part system.

[0083] The sawing device performs sawing operation according to the received control parameters, and generates real-time operation data of the first sawing device, which includes key information such as actual position parameters, actual speed parameters, and actual depth parameters of the sawing.

[0084] The sawing verification module compares the real-time operation data of the first sawing device with the sawing device prediction data output by the previous sawing prediction module. The comparison is strictly aligned in time and space to ensure the accuracy and comparability of the data.

[0085] By comparison, the control parameters of the real-time gypsum board online customization four-part system calculate the difference between the actual operation data and the predicted data item by item to obtain the sawing error data. These error data reflect the deviation between the actual sawing operation and the expected target.

[0086] The sawing verification module evaluates the calculated sawing error data. If the error is within an acceptable range, it indicates that the sawing operation is basically in line with expectations and no further optimization is required. If the error exceeds a predetermined threshold, the sawing verification module triggers the optimization process and feeds the error data back to the sawing optimization module to adjust and improve the system control model.

[0087] The sawing verification module continuously monitors the operating status of the equipment and the sawing results during the entire sawing process. When an abnormality or deviation is found, the module will immediately issue an alarm and take measures to intervene to prevent the error from further expanding. At the same time, the module will also record the monitoring data and feedback information, providing valuable information for subsequent data analysis and model optimization.

[0088] Through the work of the sawing verification module, the paper-faced gypsum board online customization four-part system can achieve precise control and continuous optimization of the sawing process, thereby producing high-quality gypsum board products that meet customer requirements.

[0089] The sawing optimization module optimizes the online customization four-part system control model of gypsum board to obtain the optimized online customization four-part system control model of gypsum board, substitutes the real-time customer demand data into the optimized online customization four-part system control model of gypsum board to obtain the optimized real-time online customization four-part system control parameters of gypsum board, generates the sawing equipment control parameters at the position to be corrected, and the sawing equipment executes the sawing equipment control parameters at the position to be corrected to complete the cutting of the gypsum board to be cut.

[0090] The sawing optimization module is a four-part system for online customization of gypsum board. Its task is to continuously optimize the system control model to improve the accuracy of sawing operation. The following is the detailed workflow of the sawing optimization module:

[0091] The sawing optimization module first identifies the deficiencies or deviations in the current four-part system control model for online customization of gypsum board based on the sawing error data, actual operation data, customer feedback and other information collected in the early stage. With the help of advanced optimization algorithms such as gradient descent, genetic algorithm or particle swarm optimization, the sawing optimization module iteratively updates the original system control model, striving to find model parameters that can more accurately reflect the relationship between customer needs and the actual operation of the sawing equipment. During the optimization process, the module will fully consider multiple factors such as raw material characteristics, production process differences, equipment status changes, and customer demand fluctuations to ensure the comprehensiveness and adaptability of the model.

[0092] After the model optimization is completed, the sawing optimization module will use historical data or simulation data to verify the new model and evaluate whether its prediction accuracy and stability meet the expected standards. Only when the new model shows significantly better performance than the original model will it be adopted as the official four-part system control model for online customization of gypsum board.

[0093] When new customer requirements are input, the sawing optimization module will substitute these data into the optimized system control model. The optimized system control model can quickly calculate the optimized real-time gypsum board online customization four-part system control parameters according to customer requirements. These parameters are closer to actual production requirements and can effectively reduce sawing errors.

[0094] Based on the optimized system control parameters, the sawing optimization module will further generate the sawing equipment control parameters for the position to be corrected. These parameters specifically guide the sawing equipment in performing various operating details when performing cutting tasks, such as sawing position, speed, depth, and cutting path.

[0095] The sawing device performs the cutting operation according to the received sawing device control parameters of the position to be corrected. During the cutting process, the sawing optimization module continuously monitors the operating status and cutting effect of the equipment, and collects real-time data for subsequent analysis and further optimization.

[0096] The sawing optimization module will trigger a new optimization cycle regularly or according to actual needs, and continuously fine-tune and improve the system control model. Through this continuous optimization process, the paper-faced gypsum board online customization four-point system can gradually approach the ideal sawing effect and improve product quality and production efficiency.

[0097] In summary, the sawing optimization module provides accurate and efficient sawing parameter guidance for the online customization four-part system of gypsum board by continuously optimizing the system control model, thereby realizing refined control and management of the sawing process.

[0098] Specifically, the data acquisition module of the four-part online customization system for gypsum board of the present invention includes:

[0099] Extract features of the four-part system for online customization of gypsum board to obtain feature data of the four-part system for online customization of gypsum board, and determine the type of data to be obtained based on the feature data of the four-part system for online customization of gypsum board;

[0100] Acquire data according to the type of data to be acquired, and perform data continuity check on the acquired data. If there is data missing, generate data missing warning information;

[0101] Substitute the preset data missing warning information into the data simulation generation model of the four-part system for online customization of gypsum board to generate simulation data corresponding to the data missing warning information, and fill the missing data with the simulation data corresponding to the data missing warning information.

[0102] Comprehensive feature extraction is performed on the four-part system of online customization of gypsum board. This process may involve in-depth analysis of the properties, behaviors and relationships of each component of the system (such as raw material processing, production process, equipment status, product specifications, customer needs, quality control, etc.). Through feature extraction techniques (such as principal component analysis, linear discriminant analysis, independent component analysis, etc.), a new feature set that can reflect the characteristics of the system is constructed from the original data, that is, the feature data of the four-part system of online customization of gypsum board.

[0103] Based on the extracted system feature data and the actual needs of system operation, determine the specific data types that need to be obtained. These data types may include but are not limited to raw material quality parameters, production process parameters, equipment status parameters, customer order information, quality control indicators, etc.

[0104] According to the determined data type to be acquired, data is acquired from the corresponding data source (such as sensors, databases, file systems, etc.) in real time or at a scheduled time. The accuracy and completeness of the data must be ensured during the data acquisition process, while considering the timeliness and security of the data.

[0105] Conduct continuity checks on the acquired data to determine whether the data is missing or abnormal. This usually involves analyzing the data's timestamp, value range, and change trend. If data is missing or abnormal, it is necessary to generate data missing warning information or abnormal alarm information in a timely manner for subsequent processing.

[0106] When missing data is detected, the system will generate data missing warning information based on preset rules and thresholds. This information may include the type of missing data, time range, degree of missingness, etc.

[0107] The generated data missing warning information is substituted into the data simulation generation model of the four-part system for online customization of gypsum board. The model can simulate and generate reasonable values ​​corresponding to the missing data based on the historical data and current operating status of the system.

[0108] Use simulated data to fill in missing data to ensure the normal operation of the system and the continuity of data analysis. The accuracy and reliability of simulated data should be considered during the filling process to avoid misleading system decisions.

[0109] The data acquisition module of the four-part system for online customization of gypsum board achieves comprehensive, accurate and timely acquisition of the data required by the system through steps such as feature extraction, data type determination, data acquisition, continuity detection, data missing warning and simulated data filling.

[0110] Specifically, the four-part system for online customization of gypsum board of the present invention, the sawing prediction module, comprises:

[0111] Receiving real-time demand data from customers through a data interface or a user input interface, where the real-time demand data from customers includes the size, shape and quantity of gypsum boards;

[0112] Receive real-time sawing quality standards, including sawing accuracy, allowable error range and surface quality;

[0113] Substitute the pre-processed real-time customer demand data into the trained sawing equipment prediction model. The sawing equipment prediction model is trained based on historical data of raw materials, historical data of production processes, and historical data of equipment status. The sawing equipment prediction model predicts the operating parameters and output results of the sawing equipment based on the input customer demand data.

[0114] The prediction data of the sawing equipment is obtained by calculating the sawing equipment prediction model, and the prediction data of the sawing equipment includes sawing position prediction parameters, speed prediction parameters and cutting depth prediction parameters.

[0115] The sawing prediction module receives the gypsum board customization requirements from customers in real time through data interfaces (such as API, database connection, etc.) or user input interfaces (such as web forms, mobile application interfaces, etc.). The customer demand data specifically includes the size (length, width, thickness), shape (such as rectangle, square, special shape, etc.) and required quantity of the gypsum board.

[0116] At the same time, the sawing prediction module also receives quality standards related to the sawing operation, which are usually provided by the quality control department or directly by the customer. The sawing quality standards include the sawing accuracy requirements (such as the straightness and verticality of the cutting line), the allowable error range (such as dimensional deviation, angular deviation, etc.) and the surface quality requirements (such as smoothness, crack-free, etc.).

[0117] The received customer demand data and sawing quality standards are pre-processed, including data cleaning (removing invalid or erroneous data), data conversion (such as unifying the size unit), data normalization (scaling the data to a specific range), etc., to ensure the consistency and processability of the data.

[0118] Load the trained sawing equipment prediction model. This model is trained based on a large amount of historical data (including raw material historical data, production process historical data, equipment status historical data, etc.), and can reflect the operation rules and output results of sawing equipment under different conditions.

[0119] The pre-processed customer demand data is used as input into the sawing equipment prediction model. These input data provide the model with the necessary information required to make predictions.

[0120] The sawing equipment prediction model predicts the operating parameters and output results of the sawing equipment based on the input customer demand data combined with its internal learning algorithm and parameters.

[0121] The operation parameters may include sawing position parameters (such as starting point, end point, cutting path, etc.), speed parameters (such as cutting speed, acceleration, etc.) and cutting depth parameters (such as cutting depth, cutting level, etc.).

[0122] Through the calculation of the model, the predicted data of the sawing equipment is obtained. This data is an important basis for subsequent sawing operations and is used to guide the sawing equipment to cut according to the predetermined parameters and paths.

[0123] The prediction data of the sawing equipment is passed to the sawing execution module or operator to guide the actual sawing operation. During the sawing process, the actual operation data of the sawing equipment can be collected in real time or regularly and compared with the prediction data to evaluate the accuracy of the prediction and the performance of the model. Based on the comparison results and feedback, the sawing equipment prediction model can be continuously optimized and updated to improve its prediction accuracy and adaptability.

[0124] Through the above process, the sawing prediction module can realize the accurate prediction of the sawing operation in the four-part online customization system of gypsum board, providing strong support for the automated and intelligent operation of the system.

[0125] Specifically, the data analysis module of the four-part online customization system for gypsum board of the present invention includes:

[0126] The historical data of the four-part system for online customization of gypsum board and the historical data on the operation of sawing equipment, the historical data on customer demand, the historical data on quality control, the historical data on the four-part system for online customization of gypsum board and the historical data on the operation of sawing equipment are divided into a training set and a validation set;

[0127] The selected deep learning model is trained using the preprocessed training data set. During the training process, the weight of the model is adjusted through the back propagation algorithm, the model is verified using the validation set, the trained model is evaluated using the test set, the performance indicators of the model are calculated, and the model is optimized based on the evaluation results to obtain the four-part system control model for online customization of gypsum board.

[0128] Summarize the historical data of the four-part system of online customization of paper-faced gypsum board, covering various parameter records in the production process, such as raw material information, production process parameters, equipment status, etc. Collect historical data on the operation of sawing equipment, including sawing parameters (position, speed, depth, etc.), equipment status (temperature, vibration, etc.) and maintenance records. Organize historical data on customer needs and record customer customization requirements for the size, shape, quantity, etc. of gypsum board. Summarize historical data on quality control, including the results of quality inspections, analysis of the causes of non-conforming products, and improvement measures.

[0129] The collected data is divided into training set, validation set and test set. The training set is used for model learning, the validation set is used for verification during model training to adjust hyperparameters, and the test set is used to finally evaluate the performance of the model. Data division should follow the principles of randomness, representativeness and balance to ensure the reliability and generalization ability of model training.

[0130] Choose a deep learning model. According to the characteristics and requirements of the four-point system for online customization of gypsum board, choose a suitable deep learning model. It may be a convolutional neural network (CNN) for image processing (such as identifying surface defects of gypsum board), or a recurrent neural network (RNN) for time series prediction (such as predicting equipment failure), or other types of deep learning models.

[0131] Data preprocessing: preprocessing of training sets, validation sets, and test sets, including data cleaning (removing outliers, filling missing values), data conversion (such as normalization, standardization), feature selection (extracting features useful for model prediction), etc.

[0132] Model training: Use the preprocessed training data set to train the selected deep learning model. During the training process, the weights of the model are adjusted through the back propagation algorithm to minimize the error between the model's prediction results and the actual data.

[0133] Set reasonable hyperparameters such as the number of training rounds, learning rate, batch size, etc., and adjust these hyperparameters based on the performance of the validation set.

[0134] During the training process, the validation set is used regularly to validate the model and evaluate whether the model's performance meets expectations. If the performance of the validation set decreases, it may mean that the model is overfitting, and the model structure or hyperparameters need to be adjusted.

[0135] Use the test set to comprehensively evaluate the trained model and calculate the model's performance indicators, such as accuracy, recall, F1 score, mean square error, etc. These performance indicators can reflect the model's generalization ability on unknown data.

[0136] According to the evaluation results, the model is optimized, which may include adjusting the model structure (such as increasing or decreasing the number of network layers, changing the activation function, etc.), adding data enhancement techniques (such as image processing techniques such as rotation, scaling, and flipping), or using integrated learning methods (such as random forests, gradient boosting, etc.) to improve the performance of the model.

[0137] The optimized model was determined as the control model of the four-part system for online customization of gypsum board and deployed in the actual production environment. The model can receive customer demand data, quality control data, etc. in real time, and output optimized sawing parameters, production process parameters, etc. to guide the online customization production of gypsum board. At the same time, the data analysis module also continuously monitors the performance of the model in actual production, and continuously optimizes and updates the model based on feedback data.

[0138] Specifically, the four-part system for online customization of gypsum board of the present invention, the sawing verification module comprises:

[0139] Acquire the real-time operation data of the first sawing device from the sawing device, wherein the real-time operation data of the first sawing device includes an actual position parameter, an actual speed parameter, and an actual depth parameter of the sawing;

[0140] Aligning the real-time operation data of the first sawing device with the prediction data of the sawing device in time and space;

[0141] Compare the real-time operation data of the first sawing device with the predicted data of the sawing device item by item, and calculate the error of each data, that is, the difference between the actual value and the predicted value;

[0142] All calculated errors are summarized, and sawing error data is generated based on the error summary results.

[0143] Acquire the real-time operation data of the first sawing device. The sawing verification module first acquires the operation data of the first sawing device in real time through the data interface or directly from the sawing device. These data include actual position parameters of sawing (such as cutting starting point, end point, path, etc.), actual speed parameters (such as cutting speed, acceleration, etc.) and actual depth parameters (such as cutting depth, layer, etc.).

[0144] In order to ensure the accuracy of the comparison, the sawing verification module aligns the real-time operation data of the first sawing device with the sawing device prediction data output by the previous sawing prediction module in time and space. This means that it is necessary to ensure that the two sets of data correspond to the sawing operations at the same time point or time period, and that the data items can correspond one to one.

[0145] The sawing verification module compares the real-time operation data of the first sawing device with the predicted data of the sawing device item by item. For each data item (such as position, speed, depth), the actual value is compared with the predicted value.

[0146] During the comparison process, the sawing verification module calculates the error of each data item, that is, the difference between the actual value and the predicted value. These errors may be expressed in absolute, relative or percentage forms, depending on the nature of the data and the needs of the system.

[0147] The sawing verification module summarizes all calculated errors. This may include statistical indicators such as the mean, standard deviation, maximum, and minimum of the calculated errors to comprehensively evaluate the operating performance of the sawing equipment and the accuracy of the prediction model.

[0148] Based on the error summary results, the sawing verification module generates sawing error data. These data not only reflect the deviation between the actual operation of the sawing equipment and the prediction, but can also be used for subsequent analysis, optimization and decision-making processes. For example, if the error exceeds the set threshold, the system can trigger an alarm or adjust the sawing parameters to reduce the error.

[0149] The sawing error data can be passed to other modules of the system (such as data analysis module, control module, etc.) for further processing and analysis. Based on the sawing error data, the system can optimize and adjust the operating parameters of the sawing equipment, the parameters of the prediction model or the entire production process to improve production efficiency and product quality. At the same time, the sawing verification module can also provide a real-time feedback mechanism to help operators understand the operating status of the sawing equipment and the accuracy of the prediction model in a timely manner, so as to make corresponding adjustments and decisions.

[0150] Specifically, the four-part system for online customization of gypsum board of the present invention, the sawing optimization module, comprises:

[0151] The real-time operation data of the first sawing equipment is compared with the real-time sawing quality standard. When the sawing error data is greater than the real-time sawing quality standard, the operation data of the data acquisition end is obtained, and the data acquisition end is inspected based on the operation data of the data acquisition end. If the inspection of the data acquisition end is qualified, the control model of the gypsum board online customization four-point system is optimized using a genetic algorithm based on the sawing error data, the historical data of the gypsum board online customization four-point system and the sawing equipment operation history data to obtain the optimized gypsum board online customization four-point system control model, and the real-time customer demand data is substituted into the optimized gypsum board online customization four-point system control model to obtain the optimized real-time gypsum board online customization four-point system control parameters. The real-time online customization of gypsum board four-part system control parameters are substituted into the sawing equipment prediction model to generate the real-time operation data of the second sawing equipment, and the real-time operation data of the second sawing equipment is compared with the real-time sawing quality standard. If the real-time operation data of the second sawing equipment meets the range of the real-time sawing quality standard, the image data of the cut gypsum board is collected, and the image data of the cut gypsum board is compared with the real-time customer demand data to obtain the position to be corrected of the image data of the cut gypsum board, and the position to be corrected of the image data of the cut gypsum board is transmitted to the optimized online customization of gypsum board four-part system control model to generate the control parameters of the sawing equipment at the position to be corrected, and the sawing equipment executes the control parameters of the sawing equipment at the position to be corrected to complete the cutting of the cut gypsum board.

[0152] The sawing error detection module first receives the sawing error data from the sawing verification module and compares the data with the real-time sawing quality standard. If the sawing error data exceeds the threshold set by the real-time sawing quality standard, the subsequent optimization process is triggered.

[0153] After confirming that the sawing error exceeds the standard, the module will obtain the operating data of the data acquisition terminal and verify it. The purpose of the verification is to ensure that there is no fault or error in the data acquisition terminal itself, so as to eliminate the sawing error caused by data acquisition problems. If the data acquisition terminal passes the inspection, the subsequent optimization steps will continue; if it fails, the data acquisition terminal needs to be repaired or replaced.

[0154] The sawing error data, the historical data of the four-part system of online customization of gypsum board and the historical data of sawing equipment operation are collected as the input of the optimization algorithm.

[0155] Genetic algorithm is used to optimize the control model of the four-part system for online customization of gypsum board. Genetic algorithm is a search algorithm that simulates natural selection and genetic mechanism and is suitable for solving complex optimization problems.

[0156] Through the iterative process of genetic algorithm, the parameters of the control model are continuously adjusted to minimize the sawing error and meet the real-time sawing quality standards.

[0157] After optimization by genetic algorithm, the optimized four-part system control model of online customization of gypsum board is obtained. The real-time customer demand data is substituted into the optimized control model to generate the optimized real-time four-part system control parameters of online customization of gypsum board.

[0158] These control parameters are substituted into the sawing equipment prediction model to generate the real-time operation data of the second sawing equipment, including sawing position parameters, speed parameters, cutting depth parameters, etc., which are used to guide subsequent sawing operations.

[0159] The real-time operation data of the second sawing device is compared with the real-time sawing quality standard to verify whether the sawing result meets the standard. If the sawing result meets the standard, the image data of the cut gypsum board is collected. These image data are compared with the real-time customer demand data to find the position to be corrected in the image data of the cut gypsum board (such as size deviation, shape discrepancy, etc.).

[0160] The position to be corrected is transmitted to the optimized control model to generate the sawing device control parameters of the position to be corrected. The sawing device performs correction operations according to these correction parameters to complete the accurate cutting of the gypsum board to be cut.

[0161] The entire sawing optimization module is a cyclic optimization process. By continuously detecting sawing errors, optimizing control models, generating control parameters, verifying sawing results and correcting deviations, the continuous improvement and optimization of the four-part system for online customization of gypsum board is achieved. The optimization mechanism not only improves production efficiency and product quality, but also enhances the system's adaptability and robustness, enabling it to better cope with changes in customer needs and uncertainties in the production process.

[0162] Specifically, the four-part system for online customization of gypsum board of the present invention, the sawing optimization module, comprises:

[0163] Determine the optimization target based on sawing error data and real-time sawing quality standards;

[0164] Obtain sawing error data, historical data of the four-part system for online customization of gypsum board, and historical data of sawing equipment operation, and send sawing error data, historical data of the four-part system for online customization of gypsum board, and historical data of sawing equipment operation

[0165] As the input data of genetic algorithm optimization, it is used to train and optimize the online customized four-part system control model of gypsum board;

[0166] Receive and set the parameters of the genetic algorithm, including population size, selection, crossover, mutation probability, and number of iterations;

[0167] Initialize the population, use a random or specific method to generate the initial population, each individual represents a possible control model parameter combination;

[0168] Evaluate each individual in the population and calculate its fitness value;

[0169] Select excellent individuals as parents according to the fitness value to generate the next generation. The selection operation can adopt roulette selection or tournament selection method.

[0170] Perform a crossover operation on the selected parent generation to generate new offspring individuals;

[0171] Perform mutation operations on offspring individuals, introduce new genes, and replace the old population with the newly generated offspring individuals to form a new generation of population;

[0172] Repeat selection, crossover, and mutation until the predetermined number of iterations is reached or the optimization goal is met;

[0173] The individuals with the highest fitness value are selected from the final population as the parameters of the optimized four-part system control model for online customization of gypsum board;

[0174] The control model is updated using the parameters of the optimized gypsum board online customization four-part system control model to obtain the optimized gypsum board online customization four-part system control model.

[0175] Determine the optimization goal, based on the sawing error data and real-time sawing quality standards, clarify the optimization goal. This usually includes minimizing the sawing error, improving cutting accuracy, meeting specific size and shape requirements, etc.

[0176] Obtain sawing error data, which reflects the deviation between the current sawing operation and the ideal state. Collect historical data of the four-part system of online customization of gypsum board, including past sawing operation records, system configuration parameters, etc. Obtain historical data of sawing equipment operation, including equipment performance parameters, maintenance records, etc.

[0177] Data input, using the above data as input data for genetic algorithm optimization, is used to train and optimize the online customization four-part system control model of gypsum board.

[0178] Genetic algorithm parameter setting, receive and set the parameters of the genetic algorithm, these parameters have an important impact on the performance and convergence speed of the algorithm.

[0179] Population size: Determines the number of individuals in the initial population.

[0180] Selection probability: determines the probability of excellent individuals being selected in the selection operation.

[0181] Crossover Probability: Controls how often the crossover operation occurs.

[0182] Mutation probability: determines the probability of mutation operation occurring, introducing new genes to increase the diversity of the population.

[0183] Iterations: Set the maximum number of iterations for the algorithm to run, which serves as one of the stopping conditions.

[0184] Initialize the population, use random or specific methods to generate the initial population, each individual represents a possible control model parameter combination. These parameter combinations will serve as the starting point for genetic algorithm optimization.

[0185] Each individual in the population is evaluated and its fitness value is calculated. The fitness value is usually determined based on the sawing error data and the objective function of the control model, reflecting the degree of excellence of the individual in the optimization problem.

[0186] Selection, according to the fitness value, selects excellent individuals as parents to generate the next generation. The selection operation can use methods such as roulette selection and tournament selection to ensure the inheritance of excellent genes.

[0187] Crossover, perform a crossover operation on the selected parent to generate new offspring individuals. The crossover operation produces offspring with new characteristics by exchanging some gene fragments of the parent individuals.

[0188] Mutation, perform mutation operations on offspring individuals and introduce new genes. The mutation operation can randomly change certain gene values ​​of individuals to increase the diversity of the population and explore new solution spaces.

[0189] Update the population and replace the old population with the newly generated offspring individuals to form a new generation of population. Repeat the selection, crossover, and mutation process until the predetermined number of iterations is reached or the optimization goal is met.

[0190] The individuals with the highest fitness value are selected from the final population as the parameters of the optimized gypsum board online customization four-part system control model. These parameters are used to update the control model to obtain the optimized gypsum board online customization four-part system control model. This model will be used to guide subsequent sawing operations to improve cutting accuracy and meet customer needs.

[0191] The sawing optimization module is a continuous optimization process. In practical applications, the parameters and optimization goals of the genetic algorithm can be continuously adjusted according to the feedback of the sawing operation and the changes in customer needs to achieve better optimization results.

[0192] Through the above process, the sawing optimization module uses genetic algorithms to optimize the control model of the four-part system for online customization of gypsum board, thereby improving the accuracy and stability of the sawing operation and providing a strong guarantee for the efficient operation of the system and customer satisfaction.

[0193] The present invention solves the problems existing in the existing online customized quartered gypsum board sawing through the following technical solutions:

[0194] Obtain historical data on raw materials, production processes, equipment status, product specifications, customer demand, and quality control. These data provide a basis for subsequent analysis and prediction. Preprocess the acquired data, use the preprocessed data to train the random forest model, and obtain the sawing equipment prediction model.

[0195] Receive real-time customer demand data and real-time sawing quality standards, substitute the real-time customer demand data into the sawing equipment prediction model, and obtain the sawing equipment prediction data. These prediction data include parameters such as sawing position, speed, cutting depth, etc., providing preliminary analysis for subsequent sawing operations.

[0196] Obtain the historical data of the four-part system of online customization of gypsum board and the historical data of sawing equipment operation. Use these data (including historical data of customer demand, historical data of quality control, etc.) to train the deep learning model and obtain the control model of the four-part system of online customization of gypsum board. Substitute the real-time customer demand data into the control model and output the real-time control parameters of the four-part system of online customization of gypsum board. These parameters provide precise guidance for the actual operation of the sawing equipment.

[0197] The real-time gypsum board online customization four-part system control parameters are transmitted to the sawing equipment, and the sawing equipment generates the first sawing equipment real-time operation data after execution. These real-time operation data are compared with the sawing equipment prediction data to obtain the sawing error data. This step realizes the real-time calibration of the sawing process to ensure the accuracy of the sawing operation.

[0198] When the sawing error data is greater than the real-time sawing quality standard, the genetic algorithm is used to optimize the online customization four-part system control model of gypsum board based on the sawing error data, system history data, and equipment operation history data. More accurate control parameters are obtained through the optimized model, and the sawing equipment control parameters for the position to be corrected are generated. The sawing equipment executes these parameters to complete the accurate correction of the cut gypsum board.

[0199] Through the above technical solution, the present invention realizes the pre-analysis before gypsum board sawing and the real-time calibration of the sawing process, thereby effectively avoiding the problem of gypsum board material waste caused by sawing errors. At the same time, by continuously optimizing the system control model, the sawing accuracy and efficiency are improved to meet different construction requirements.

Claims

1. A four-part system for online customization of gypsum board, characterized in that: include: Data acquisition module, which acquires historical data of raw materials, production process, equipment status, product specifications, customer demand and quality control; The sawing prediction module preprocesses the raw material historical data, the production process historical data, the equipment status historical data, the product specification historical data, the customer demand historical data and the quality control historical data to obtain the preprocessed data, uses the preprocessed data to train the random forest model to obtain the sawing equipment prediction model, receives the real-time customer demand data and the real-time sawing quality standard, substitutes the real-time customer demand data into the sawing equipment prediction model to obtain the sawing equipment prediction data; The data analysis module obtains the historical data of the four-part system for online customization of gypsum boards and the historical data of the operation of sawing equipment, trains the deep learning model with the historical data of customer demand, historical data of quality control, historical data of the four-part system for online customization of gypsum boards, and historical data of the operation of sawing equipment, obtains the control model of the four-part system for online customization of gypsum boards, substitutes the real-time customer demand data into the control model of the four-part system for online customization of gypsum boards, and outputs the real-time control parameters of the four-part system for online customization of gypsum boards; The sawing verification module transmits the control parameters of the real-time gypsum board online customization four-part system to the sawing equipment in the gypsum board online customization four-part system. After the sawing equipment executes the control parameters of the real-time gypsum board online customization four-part system, it generates the real-time operation data of the first sawing equipment, compares the real-time operation data of the first sawing equipment with the predicted data of the sawing equipment, and obtains the sawing error data; The sawing optimization module optimizes the online customization four-part system control model of gypsum board to obtain the optimized online customization four-part system control model of gypsum board, substitutes the real-time customer demand data into the optimized online customization four-part system control model of gypsum board to obtain the optimized real-time online customization four-part system control parameters of gypsum board, generates the sawing equipment control parameters at the position to be corrected, and the sawing equipment executes the sawing equipment control parameters at the position to be corrected to complete the cutting of the gypsum board to be cut.

2. The four-part system for online customization of gypsum board according to claim 1, characterized in that: The data acquisition module comprises: Extract features of the four-part system for online customization of gypsum board to obtain feature data of the four-part system for online customization of gypsum board, and determine the type of data to be obtained based on the feature data of the four-part system for online customization of gypsum board; Acquire data according to the type of data to be acquired, and perform data continuity check on the acquired data. If there is data missing, generate data missing warning information; Substitute the preset data missing warning information into the data simulation generation model of the four-part system for online customization of gypsum board to generate simulation data corresponding to the data missing warning information, and fill the missing data with the simulation data corresponding to the data missing warning information.

3. The four-part system for online customization of gypsum board according to claim 1, characterized in that: The sawing prediction module comprises: Receiving real-time demand data from customers through a data interface or a user input interface, the real-time demand data from customers including the size, shape and quantity of gypsum boards; Receive real-time sawing quality standards, including sawing accuracy, allowable error range and surface quality; Substitute the pre-processed real-time customer demand data into the trained sawing equipment prediction model. The sawing equipment prediction model is trained based on historical data of raw materials, historical data of production processes, and historical data of equipment status. The sawing equipment prediction model predicts the operating parameters and output results of the sawing equipment based on the input customer demand data. The prediction data of the sawing equipment are obtained by calculating the sawing equipment prediction model, and the prediction data of the sawing equipment include sawing position prediction parameters, speed prediction parameters and cutting depth prediction parameters.

4. The four-part system for online customization of gypsum board according to claim 1, characterized in that: The data analysis module comprises: The historical data of the four-part system for online customization of gypsum board and the historical data on the operation of sawing equipment, the historical data on customer demand, the historical data on quality control, the historical data on the four-part system for online customization of gypsum board and the historical data on the operation of sawing equipment are divided into a training set and a validation set; The selected deep learning model is trained using the preprocessed training data set. During the training process, the weight of the model is adjusted through the back propagation algorithm, the model is verified using the validation set, the trained model is evaluated using the test set, the performance indicators of the model are calculated, and the model is optimized based on the evaluation results to obtain the four-part system control model for online customization of gypsum board.

5. The four-part system for online customization of gypsum board according to claim 1, characterized in that: The sawing verification module comprises: Acquire the real-time operation data of the first sawing device from the sawing device, wherein the real-time operation data of the first sawing device includes an actual position parameter, an actual speed parameter, and an actual depth parameter of the sawing; Aligning the real-time operation data of the first sawing device with the prediction data of the sawing device in time and space; Compare the real-time operation data of the first sawing device with the predicted data of the sawing device item by item, and calculate the error of each data, that is, the difference between the actual value and the predicted value; All calculated errors are summarized, and sawing error data is generated based on the error summary results.

6. The four-part system for online customization of gypsum board according to claim 1, characterized in that: The sawing optimization module comprises: The real-time operation data of the first sawing equipment is compared with the real-time sawing quality standard. When the sawing error data is greater than the real-time sawing quality standard, the operation data of the data acquisition end is obtained, and the data acquisition end is inspected based on the operation data of the data acquisition end. If the inspection of the data acquisition end is qualified, the control model of the gypsum board online customization four-point system is optimized using a genetic algorithm based on the sawing error data, the historical data of the gypsum board online customization four-point system and the sawing equipment operation history data to obtain the optimized gypsum board online customization four-point system control model, and the real-time customer demand data is substituted into the optimized gypsum board online customization four-point system control model to obtain the optimized real-time gypsum board online customization four-point system control parameters. The real-time online customization of gypsum board four-part system control parameters are substituted into the sawing equipment prediction model to generate the real-time operation data of the second sawing equipment, and the real-time operation data of the second sawing equipment is compared with the real-time sawing quality standard. If the real-time operation data of the second sawing equipment meets the range of the real-time sawing quality standard, the image data of the cut gypsum board is collected, and the image data of the cut gypsum board is compared with the real-time customer demand data to obtain the position to be corrected of the image data of the cut gypsum board, and the position to be corrected of the image data of the cut gypsum board is transmitted to the optimized online customization of gypsum board four-part system control model to generate the control parameters of the sawing equipment at the position to be corrected, and the sawing equipment executes the control parameters of the sawing equipment at the position to be corrected to complete the cutting of the cut gypsum board.

7. The four-part system for online customization of gypsum board according to claim 6, characterized in that: The sawing optimization module comprises: Determine the optimization target based on sawing error data and real-time sawing quality standards; Obtain sawing error data, historical data of the four-part system for online customization of gypsum board, and historical data of sawing equipment operation, and send sawing error data, historical data of the four-part system for online customization of gypsum board, and historical data of sawing equipment operation As the input data of genetic algorithm optimization, it is used to train and optimize the online customized four-part system control model of gypsum board; Receive and set the parameters of the genetic algorithm, including population size, selection, crossover, mutation probability, and number of iterations; Initialize the population, use a random or specific method to generate the initial population, each individual represents a possible control model parameter combination; Evaluate each individual in the population and calculate its fitness value; Select excellent individuals as parents according to the fitness value to generate the next generation. The selection operation can adopt roulette selection or tournament selection method. Perform a crossover operation on the selected parent generation to generate new offspring individuals; Perform mutation operations on offspring individuals, introduce new genes, and replace the old population with the newly generated offspring individuals to form a new generation of population; Repeat selection, crossover, and mutation until the predetermined number of iterations is reached or the optimization goal is met; The individuals with the highest fitness value are selected from the final population as the parameters of the optimized four-part system control model for online customization of gypsum board; The control model is updated using the parameters of the optimized gypsum board online customization four-part system control model to obtain the optimized gypsum board online customization four-part system control model.

Images