Plastic product processing control system

Abstract

A plastic product processing control system disclosed by the present invention comprises a plastic product processing device, a server and a background terminal, a data acquisition module is arranged in the plastic product processing device, a data storage module, a data analysis module and a control execution module are arranged in the server, and a data visualization module and a device management module are arranged in the background terminal. The data acquisition module acquires real-time data and transmits the real-time data to the data storage module for classified storage, the data analysis module receives the data and carries out mining by applying various analysis methods and early warning mechanisms, a result is sent to the control execution module and the data visualization module, and the control execution module controls equipment according to an analysis result. The data visualization module displays an analysis result to facilitate decision making, and the equipment management module interacts with all the modules to maintain equipment and optimize equipment management according to data. According to the invention, through mutual cooperation of multiple analysis methods and early warning mechanisms, equipment faults and abnormal conditions in the production process can be quickly and accurately diagnosed.

Description

Technical Field

[0001] The present invention belongs to the technical field of plastic product processing, and specifically relates to a control system for plastic product processing. Background Art

[0002] Plastic is an indispensable material in life, and plastic products are widely used. Its production goes through processes such as raw material mixing, embryo forming, combination, and subsequent processing. The process parameters for each link are strictly required, including the raw material mixing ratio, the temperature and pressure during embryo forming, the embryo combination method, and subsequent processing conditions, etc. Any change in a parameter may trigger a chain reaction, directly resulting in unqualified plastic product finished products. In actual production, a control system for plastic product processing is needed to improve the quality and efficiency of plastic product production.

[0003] Existing control systems for plastic product processing usually only perform simple statistical analysis, insufficiently excavate the complex associations and potential laws between data, cannot extract valuable information from a large amount of data, are difficult to achieve in-depth optimization of the production process and fault prediction, and there is a lag in data analysis, unable to process and analyze the collected data in a timely manner, resulting in a certain impact on production when problems are discovered, and unable to adjust production parameters or take measures in time to avoid quality problems and production accidents. Summary of the Invention

[0004] The purpose of the present invention is to provide a control system for plastic product processing to solve the problem that existing control systems for plastic product processing usually only perform simple statistical analysis, cannot quickly and accurately diagnose equipment failures and abnormal situations in the production process, and there is a risk of data analysis lag.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A control system for plastic product processing, comprising:

[0007] Plastic product processing equipment, in which a data acquisition module is provided. The data acquisition module collects various data of the equipment in real time through sensors and sends the original data to the server;

[0008] A server, in which a data storage module, a data analysis module, and a control execution module are provided. The data storage module receives and stores the collected original data, then classifies and organizes it. The data analysis module extracts data from the storage module, uses a variety of analysis methods and early warning mechanisms to mine valuable information and timely discover abnormalities, and generates analysis results. The control execution module generates control signals according to the analysis results and preset instructions, sends them back to the equipment, and adjusts the operation of the equipment;

[0009] Backend terminal, within which there is a data visualization module and a device management module. The data visualization module obtains analysis results and relevant data from the server and presents them to users in the form of intuitive charts. The device management module provides an operation interface in the backend terminal, where managers can monitor the device status, formulate maintenance plans, and at the same time receive device exception information and feedback it to the server.

[0010] Among them, various sensors on the plastic product processing equipment include temperature sensors, pressure sensors, flow sensors, and displacement sensors. These sensors stably and quickly transmit the collected real-time data to the data analysis module through an industrial network. The data analysis module preprocesses the raw data collected, removes invalid information in noise and duplicate data. The data after the preprocessing operation is transmitted to the data storage module in the server.

[0011] Among them, a relational database is selected within the data storage module to establish a product quality database, which centrally integrates and stores data from different sources and in different formats, and classifies the stored data according to dimensions such as production links, equipment types, and data types, and establishes corresponding indexes to facilitate quick positioning and retrieval of the required data.

[0012] Among them, the data analysis module includes basic data analysis, correlation analysis, process monitoring and early warning analysis, and optimization analysis. The basic data analysis calculates statistical quantities such as mean, median, mode, and standard deviation to understand the central tendency and dispersion degree of the data set, analyzes the data distribution, and judges whether the production process is normal. The correlation analysis uses statistical methods to calculate the correlation coefficient, analyzes the correlation between production parameters, and explores the correlation between production parameters and product quality indicators to clarify key quality control parameters. The process monitoring and early warning analysis sets the normal range and threshold of parameters, collects data in real time and compares them. If it exceeds the range, an early warning will be issued, and methods such as time series are used to analyze the data trend, predict future values, and compare with the actual situation. If the deviation is large or the trend is abnormal, an early warning will be issued. The optimization analysis uses technologies such as machine learning to build models of process parameters, quality, and efficiency, uses optimization algorithms to find the optimal parameter combination, and then combines market demand, equipment production capacity, and raw material supply analysis to reasonably arrange production tasks, improve equipment utilization rate, and reduce costs.

[0013] Among them, the data analysis module further includes a threshold warning mechanism, a trend warning mechanism, an association warning mechanism, and a model warning mechanism. The basic data analysis provides statistics such as mean and standard deviation, sets reasonable thresholds for threshold warning, and its historical data helps the trend warning establish a trend model, screens key parameters for association warning, and also provides data cleaning, transformation, and feature reference for model warning. The correlation analysis clarifies parameter associations, sets trigger conditions for association warning, assists the threshold warning to improve accuracy, helps the model warning select key features, and explores deep associations. The process monitoring and warning collects data in real time, compares with the threshold warning to trigger an abnormal alarm, tracks the trend in the trend warning and compares it with the model, monitors the parameter relationship in the association warning, and provides a problem orientation for optimization analysis. The optimization analysis adjusts the process or model according to the problem directions pointed out by each warning mechanism. After optimization, each warning mechanism re-evaluates, calibrates the threshold, re-evaluates the trend model, examines the association relationship, and retrains the model to achieve the close cooperation between each warning mechanism and various analysis methods.

[0014] Among them, the control execution module generates corresponding control instructions according to the optimization results and control strategies obtained by the data analysis module, and issues the instructions to the controller of the plastic product processing equipment to achieve precise control of the equipment. The control execution module also has an equipment linkage control mechanism, which can realize the linkage control between multiple devices to ensure the coordinated operation of the entire production process.

[0015] Among them, the data visualization module can display the results of data analysis in an intuitive chart form, enabling managers and operators to clearly understand the production status, data trends, and analysis results at a glance, and presenting key indicators and data in the form of a dashboard to facilitate real-time monitoring of the overall operation of the production process. The dashboard can display important information such as the operating status of the equipment, production progress, and quality indicators, enabling operators to quickly grasp the key information of production and make decisions in a timely manner.

[0016] Among them, the equipment management module includes an equipment detection function, an equipment maintenance function, and an equipment performance evaluation function. The equipment detection function monitors the operating status of the equipment in real time, obtains the real-time status data of the equipment by communicating with the control system of the equipment, and displays and records it in the system to promptly detect abnormal situations of the equipment. The equipment maintenance function formulates an equipment maintenance plan and maintenance strategy based on information such as the operating time, usage frequency, and failure history of the equipment, reminds the maintenance personnel to perform maintenance and repair on the equipment on time, and extends the service life of the equipment. The equipment performance evaluation function evaluates and analyzes the performance of the equipment, and finds out the performance bottlenecks and optimization space of the equipment through long-term tracking and comparison of equipment performance data, providing a basis for the upgrading and transformation of the equipment.

[0017] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows:

[0018] In the present invention, a variety of analysis methods and early warning mechanisms are used in combination. By using a variety of analysis methods to analyze and explore the complex relationships between parameters, discover potential laws, and realize fault and trend prediction, data support and analysis basis are provided for the early warning mechanism. Based on this, reasonable thresholds are set, trend models are optimized, and prediction models are trained. The early warning mechanism responds in real time to key parameters exceeding the threshold, captures abnormal change trends of parameters, and then accurately predicts quality and fault problems with the help of machine learning. Moreover, the actual problems are fed back to promote the optimization of analysis methods. The two cooperate closely to make up for the deficiencies of simple statistical analysis in the existing system, solve the problem of lagging data analysis, realize in-depth optimization of production, timely prediction and response to faults, and avoid quality problems and production accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic diagram of the overall structural framework of the present invention;

[0020] Figure 2 is a schematic diagram of the frameworks inside the plastic product processing equipment, server, and background terminal of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] Refer to Figure 1 - Figure 2, A plastic product processing control system includes plastic product processing equipment, a server, and a background terminal. A communication module with an Ethernet interface is installed on the plastic product processing equipment, and the equipment is connected to the local area network where the server or the background terminal is located through a network cable. A data acquisition module is provided inside the plastic product processing equipment. The data acquisition module uses sensors to collect various data of the equipment in real time and sends the original data to the server. The server is equipped with a data storage module, a data analysis module, and a control execution module. The data storage module receives and stores the collected original data, and then classifies and organizes it. The data analysis module extracts data from the storage module, uses various analysis methods and early warning mechanisms to mine valuable information and timely detect anomalies, and generates analysis results. The control execution module generates control signals according to the analysis results and preset instructions, sends them back to the equipment, and adjusts the operation of the equipment. The background terminal is equipped with a data visualization module and an equipment management module. The data visualization module obtains the analysis results and relevant data from the server and displays them to users in intuitive charts. The equipment management module provides an operation interface in the background terminal. Managers can monitor the equipment status, formulate maintenance plans, and at the same time receive equipment anomaly information and feedback it to the server. Through the cooperation of various analysis methods and early warning mechanisms, it makes up for the defects of simple statistical analysis in the existing system, overcomes the problem of lagging data analysis, realizes in-depth optimization of the production process, early prediction of faults, timely adjustment of production parameters, and effectively avoids quality problems and production accidents.

[0023] Refer to Figure 2 As shown, various sensors on the plastic product processing equipment include temperature sensors, pressure sensors, flow sensors, and displacement sensors. The various sensors stably and quickly transmit the collected real-time data to the data analysis module through an industrial network. The data analysis module preprocesses the collected original data, removes invalid information in noise and duplicate data. The data after the preprocessing operation will be transmitted to the data storage module in the server. The data acquisition module is directly connected to the plastic product processing equipment through various sensors, as well as data acquisition cards or gateway devices, and collects various data during the operation of the equipment in real time.

[0024] Refer to Figure 2As shown in the figure, a relational database is selected within the data storage module to establish a product quality database, which centrally integrates and stores data from different sources and in different formats. The stored data is classified according to dimensions such as production processes, equipment types, and data types, and corresponding indexes are established to facilitate quick location and retrieval of the required data. After data preprocessing, a suitable relational database is selected based on data characteristics and system requirements, and installation and configuration are completed. Then, the architecture design of the product quality database is carried out, from clarifying the subject domain and entity relationships in the conceptual model, to refining the table structure in the logical model, and then to optimizing storage and indexes in the physical model. Subsequently, by developing a data transmission interface and adopting appropriate data conversion, cleaning means, and loading strategies, the preprocessed data is transmitted and loaded into the product quality database. During operation, data backup and recovery, monitoring and optimization, and security management are carried out to ensure the stable and efficient operation of the product quality database, while supporting various query analyses and visualization applications, providing strong data support for plastic product processing and production.

[0025] Refer to Figure 2 As shown in the figure, the data analysis module includes basic data analysis, correlation analysis, process monitoring and early warning analysis, and optimization analysis. Basic data analysis calculates statistics such as mean, median, mode, and standard deviation to understand the central tendency and dispersion of the data set, analyzes the data distribution, and determines whether the production process is normal. Correlation analysis uses statistical methods to calculate the correlation coefficient, analyzes the correlation between production parameters, and explores the correlation between production parameters and product quality indicators to identify key quality control parameters. Process monitoring and early warning analysis sets the normal range and threshold of parameters, collects data in real time and compares it. If it exceeds the range, an early warning is issued, and methods such as time series are used to analyze the data trend, predict future values, and compare with the actual values. If the deviation is large or the trend is abnormal, an early warning is issued. Optimization analysis uses technologies such as machine learning to establish models of process parameters, quality, and efficiency, uses optimization algorithms to find the optimal parameter combination, and then combines market demand, equipment production capacity, and raw material supply analysis to reasonably arrange production tasks, improve equipment utilization rate, and reduce costs.

[0026] Specifically, the basic data analysis targets various data during the processes of injection molding, extrusion molding, blow molding, rotational molding, and slush molding of plastic products, including temperature, pressure, and output. It calculates the mean, median, and mode to measure the central tendency of the data. By calculating the mean weight of injection-molded products in different batches, it understands the average level of product weight. At the same time, it evaluates the data dispersion degree through range, variance, and standard deviation, and uses tools such as histograms and probability density functions to analyze the data distribution pattern and determine whether it conforms to the normal distribution or other typical distributions. The correlation analysis uses the methods of Pearson correlation coefficient and Spearman rank correlation coefficient to explore the correlations between production process parameters and study the correlations between product quality indicators and various production parameters. By collecting a large amount of data including plastic particle raw material characteristics, production process parameters, and the tensile strength of plastic products during various molding processes of plastic products, it determines the degree of association between plastic particle raw material characteristics and the tensile strength of plastic products, providing a basis for optimizing raw material selection and production processes. The process monitoring and early warning analysis sets reasonable normal ranges and early warning thresholds for key production parameters, uses the data acquisition system to obtain production data in real time, and compares it with the set thresholds. Once the data exceeds the threshold, it immediately triggers the early warning mechanism and uses time series analysis and moving average method techniques to analyze and predict the change trend of production data. By establishing a trend model, it predicts the future data trend and compares it with the actual data. If the deviation between the predicted value and the actual value is too large, or the data shows abnormal upward or downward trends, it issues an early warning in a timely manner. The optimization analysis, based on the above analysis results, uses machine learning algorithms or mathematical programming methods to establish an optimization model between process parameters, product quality, and production efficiency. By using optimization algorithms to find the optimal combination of process parameters, it improves product quality and reduces production costs. Combining with the actual production situation, it comprehensively evaluates and analyzes the entire production process, identifies bottleneck links and non-value-added activities in the process, and uses concepts and methods such as process reengineering and lean production to optimize the production process, reduce waste, and improve the overall production efficiency.

[0027] Refer to Figure 2As shown, the data analysis module also includes a threshold warning mechanism, a trend warning mechanism, an association warning mechanism, and a model warning mechanism. The basic data analysis provides statistics such as the mean and standard deviation, sets reasonable thresholds for the threshold warning, and its historical data helps the trend warning to establish a trend model, screens key parameters for the association warning, and also provides data cleaning, transformation, and feature references for the model warning. The correlation analysis clarifies the parameter associations, sets trigger conditions for the association warning, assists the threshold warning to improve accuracy, helps the model warning to select key features, and explores deep associations. The process monitoring and warning analysis collects data in real time, compares with the threshold warning to trigger an abnormal alarm, tracks the trend in the trend warning and compares it with the model, monitors the parameter relationships in the association warning, provides a problem orientation for the optimization analysis. The optimization analysis adjusts the process or model according to the problem directions pointed out by each warning mechanism. After optimization, each warning mechanism re-evaluates, calibrates the threshold, re-evaluates the trend model, examines the association relationship, and retrains the model, realizing the close cooperation between each warning mechanism and various analysis methods. The various analysis methods provide data support and analysis basis for the warning mechanism. The results of association analysis, clustering analysis, and predictive analysis are used to set more reasonable warning thresholds, optimize the trend model, and train the predictive model of the model warning. The actual problems feedback by the warning mechanism in turn prompt the further optimization and adjustment of the analysis methods, discover new association relationships, and improve the predictive model parameters. The two cooperate closely, deeply excavate the data value, timely process and analyze the data, effectively solve the deficiencies of the existing system, realize the in-depth optimization of the production process and the timely prediction of faults. Through the close cooperation of the threshold warning mechanism, the trend warning mechanism, the association warning mechanism, the model warning mechanism, and the basic data analysis, the correlation analysis, the process monitoring and warning analysis, and the optimization analysis, the basic data analysis helps to set reasonable thresholds, the correlation analysis clarifies the association warning conditions, and the warning mechanism timely feedbacks problems to promote the optimization of various analyses, realizes the real-time monitoring and dynamic adjustment of the production process, can discover potential risks in advance, quickly respond to anomalies, deeply excavate the data value, optimize the production process and flow, improve product quality and production efficiency, and effectively ensure the stable and efficient operation of the plastic product processing system.

[0028] Refer to Figure 2As shown in the figure, the control execution module generates corresponding control instructions according to the optimization results and control strategies obtained by the data analysis module, and issues the instructions to the controller of the plastic product processing equipment to achieve precise control of the equipment. There is also an equipment linkage control mechanism in the control execution module, which can realize the linkage control between multiple devices to ensure the coordinated operation of the entire production process. The control execution module is the output end of the control system, directly connected to the controller or driver of the processing equipment. According to the instructions of the production management module and the results of the data analysis module, it sends control signals to the equipment, adjusts the operating parameters of the equipment, and obtains the configuration information, control parameters, and operating status data of the equipment from the server to accurately control and adjust the equipment. At the same time, it stores the control instructions and execution results of the equipment in the server to record and trace the equipment control process, and can receive manual control instructions from the background terminal and timely transmit the actual operating status and feedback information of the equipment to the background terminal, so that the operator can understand the control effect and operating conditions of the equipment in real time, realizing human-machine interaction and remote control.

[0029] Refer to Figure 2 As shown in the figure, the data visualization module can display the results of data analysis in an intuitive chart form, enabling managers and operators to clearly understand the production status, data trends, and analysis results at a glance, and presenting key indicators and data in the form of a dashboard to facilitate real-time monitoring of the overall operation of the production process. The dashboard can display important information such as the operating status of the equipment, production progress, and quality indicators, enabling operators to quickly grasp the key information of production and make decisions in a timely manner. The data visualization module obtains the data that needs to be visualized from the server. These data are the results processed by the data analysis module, or raw data, or preprocessed data. The data visualization module selects appropriate visualization methods and tools according to different display requirements and data characteristics, converts the data into intuitive charts, graphs, and maps, and then presents the visualization results to the background terminal, providing an intuitive and easy-to-understand interface for operators and managers, enabling them to quickly understand various information and data trends in the production process. The background terminal users can further explore and analyze the visualized data through interactive operations, so as to better discover problems and make decisions.

[0030] Refer to Figure 2As shown in the figure, the device management module includes a device detection function, a device maintenance function, and a device performance evaluation function. The device detection function monitors the running status of the device in real time. By communicating with the control system of the device, it obtains the real-time status data of the device and displays and records it in the system to promptly detect abnormal conditions of the device. The device maintenance function formulates a device maintenance plan and maintenance strategy based on information such as the running time, usage frequency, and failure history of the device, reminds the maintenance personnel to perform maintenance and repair on the device on time, and extends the service life of the device. The device performance evaluation function evaluates and analyzes the performance of the device. By long-term tracking and comparison of the device performance data, it finds the performance bottlenecks and optimization space of the device, providing a basis for the upgrade and transformation of the device. The device management module is responsible for the comprehensive management and monitoring of plastic product processing equipment, including the management of basic device information, device status monitoring, formulation and execution of device maintenance plans, device fault diagnosis and handling, etc. By communicating with the control system or sensors of the device, it obtains the real-time status and running data of the device to promptly detect abnormal conditions and potential problems of the device, and then stores the relevant information and data of the device in the server to establish a digital material file of the device, providing data support for the full life cycle management of the device. At the same time, it obtains information such as the historical data, maintenance records, and fault cases of the device from the server for analyzing the performance and reliability of the device, optimizing the device management strategy and maintenance plan, and providing an operation interface and function menu for device management to the background terminal. The management personnel can remotely manage and monitor the device through the background terminal. The device management module can also promptly push the alarm information and abnormal conditions of the device to the background terminal to notify the relevant personnel for handling to ensure the normal operation of the device.

[0031] Here, it needs to be explained: the product quality database and the digital material file;

[0032] 1. The product quality database refers to all types of processes and units related to quality that will affect quality throughout the entire process. It centrally integrates and stores data from different sources and in different formats, and classifies the stored data according to dimensions such as production links, device types, and data types, establishing corresponding indexes to facilitate quick location and retrieval of the required data.

[0033] 2. The digital material file refers to a visual and controllable file that can present the material content through various methods. For example, the equipment management module includes functions such as equipment detection, equipment maintenance, and equipment performance evaluation. The equipment detection function monitors the running status of the equipment in real time. By communicating with the control system of the equipment, it obtains the real-time status data of the equipment and displays and records it in the system to form visual content, so as to promptly detect abnormal situations of the equipment. The equipment maintenance function formulates equipment maintenance and reminders according to information such as the running time, usage frequency, and failure history of the equipment, achieving strategies for setting plans, maintenance, and repair, and also providing a basis for future equipment upgrades and transformations. By communicating with the control system or sensors of the equipment, it obtains the real-time status and running data of the equipment to promptly detect abnormal situations and potential problems of the equipment, and then stores the relevant information and data of the equipment in the server to establish the digital material file of the equipment.

[0034] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A plastic product processing control system, characterized in that: include: Plastic product processing equipment, wherein the plastic product processing equipment is provided with a data acquisition module, and the data acquisition module collects various data of the equipment in real time through sensors and sends the original data to the server; The server is provided with a data storage module, a data analysis module and a control execution module. The data storage module receives and stores the collected raw data, and then classifies and organizes them. The data analysis module extracts data from the storage module, uses a variety of analysis methods and early warning mechanisms to mine valuable information and discover abnormalities in a timely manner, and generates analysis results. The control execution module generates a control signal based on the analysis results and preset instructions and sends it back to the device to adjust the operation of the device; The backend terminal is provided with a data visualization module and an equipment management module. The data visualization module obtains analysis results and related data from the server and displays them to the user in the form of intuitive charts. The equipment management module provides an operation interface in the backend terminal, and managers can monitor equipment status, formulate maintenance plans, and receive equipment abnormality information and feed it back to the server.

2. A plastic product processing control system as claimed in claim 1, characterized in that: The various sensors on the plastic product processing equipment include temperature sensors, pressure sensors, flow sensors and displacement sensors. The various sensors transmit the collected real-time data to the data analysis module stably and quickly through the industrial network. The raw data collected by the data analysis module is pre-processed to remove invalid information in noise and duplicate data. The data after pre-processing operations will be transmitted to the data storage module in the server.

3. A plastic product processing control system as claimed in claim 1, characterized in that: The data storage module uses a relational database to establish a product quality database, centrally integrates and stores data from different sources and in different formats, and classifies the stored data according to dimensions such as production links, equipment types, and data types, and establishes corresponding indexes to facilitate rapid positioning and retrieval of required data.

4. A plastic product processing control system as claimed in claim 1, characterized in that: The data analysis module includes basic data analysis, correlation analysis, process monitoring and early warning analysis, and optimization analysis. The basic data analysis calculates statistical quantities such as mean, median, mode, standard deviation, etc. to understand the trend and degree of dispersion of the data, analyze the data distribution, and determine whether the production process is normal. The correlation analysis uses statistical methods to calculate the correlation coefficient, analyze the correlation between production parameters, and explore the correlation between production parameters and product quality indicators, and clarify key quality control parameters. The process monitoring and early warning analysis sets the normal range and threshold of parameters, collects and compares data in real time, and issues an early warning when it exceeds the range. It also uses time series and other methods to analyze data trends, predict future values, compare them with actual values, and issue early warnings for large deviations or abnormal trends. The optimization analysis uses machine learning and other technologies to build process parameter, quality, and efficiency models, and uses optimization algorithms to find the optimal parameter combination. Then, combined with market demand, equipment capacity, and raw material supply analysis, it reasonably arranges production tasks, improves equipment utilization, and reduces costs.

5. A plastic product processing control system as claimed in claim 4, characterized in that: The data analysis module also includes a threshold warning mechanism, a trend warning mechanism, an associated warning mechanism and a model warning mechanism. The basic data analysis provides statistics such as mean and standard deviation to set a reasonable threshold for the threshold warning. Its historical data helps the trend warning to establish a trend model, screen key parameters for associated warning, and provide data cleaning conversion and feature reference for the model warning. The correlation analysis clarifies parameter associations, sets trigger conditions for associated warnings, assists threshold warnings to improve accuracy, helps model warnings select key features, and mines deep associations. The process monitoring and warning analysis collects data in real time, compares it with the threshold warning to trigger abnormal alarms, tracks trends in trend warnings and compares them with models, monitors parameter relationships in associated warnings, and provides problem guidance for optimization analysis. The optimization analysis adjusts the process or model based on the problem direction pointed out by each warning mechanism. After optimization, each warning mechanism is re-evaluated, thresholds are calibrated, trend models are re-evaluated, associated relationships are reviewed, and models are retrained to achieve close coordination between each warning mechanism and multiple analysis methods.

6. A plastic product processing control system as claimed in claim 1, characterized in that: The control execution module generates corresponding control instructions based on the optimization results and control strategies obtained by the data analysis module, and issues the instructions to the controller of the plastic product processing equipment to achieve precise control of the equipment. The control execution module is also provided with an equipment linkage control mechanism, which can realize linkage control between multiple devices and ensure the coordinated operation of the entire production process.

7. A plastic product processing control system as claimed in claim 1, characterized in that: The data visualization module can display the results of data analysis in the form of intuitive charts, so that managers and operators can understand the production status, data trends and analysis results at a glance, and present key indicators and data in the form of dashboards, which is convenient for real-time monitoring of the overall operation of the production process. The dashboard can display important information such as the operating status of the equipment, production progress, quality indicators, etc., so that operators can quickly grasp the key information of production and make decisions in time.

8. A plastic product processing control system as claimed in claim 1, characterized in that: The equipment management module includes equipment detection function, equipment maintenance function and equipment performance evaluation function. The equipment detection function monitors the operating status of the equipment in real time, obtains the real-time status data of the equipment by communicating with the control system of the equipment, and displays and records it in the system so as to timely discover abnormal conditions of the equipment. The equipment maintenance function formulates equipment maintenance plans and maintenance strategies based on the equipment's operating time, usage frequency, fault history and other information, reminds maintenance personnel to maintain and repair the equipment on time, and extend the service life of the equipment. The equipment performance evaluation function evaluates and analyzes the performance of the equipment, finds out the performance bottleneck and optimization space of the equipment through long-term tracking and comparison of equipment performance data, and provides a basis for equipment upgrades and renovations.

Images