Optical glass production and processing monitoring system based on Internet of Things technology

Abstract

The invention discloses an optical glass production and processing monitoring system based on the Internet of Things technology, which relates to the technical field of optical glass production monitoring and comprises an Internet of Things data collector component, a data processing analyzer component, an intelligent monitoring and early warning component, a user interaction control screen component and an authority manager component. Key parameter data in the production and processing process are collected in real time through the Internet of Things data collector component, real-time processing and analysis are carried out through a big data processing engine and a machine intelligent learning algorithm library, a prediction algorithm is constructed in combination with historical data to predict the production trend, the system can predict the future production trend, and the production efficiency is improved. And scanning and one-by-one calculation are carried out for each time period in the production cycle, so that the predicted production capacity or production trend of each time point in the whole production cycle is obtained, the production efficiency and the quality control are improved, and intelligent management and optimization of the production process are realized through adaptive learning and fault prediction functions.

Description

Technical Field

[0001] The present invention relates to the technical field of optical glass production monitoring, and in particular to an optical glass production and processing monitoring system based on Internet of Things technology. Background Art

[0002] Optical glass is a high-grade glass used to manufacture optical instruments. It has excellent optical properties and is a key material for manufacturing various optical instruments and optical components. Therefore, real-time monitoring is required during the production and processing of optical glass. During the production and processing of traditional optical glass, multiple staff members are required to conduct manual monitoring and experience-based judgment.

[0003] The defects of the existing optical glass production and processing monitoring system are: 1. Patent document US07043323B2 discloses that glass processing equipment has a dynamic continuous production control system. However, the glass processing equipment in the above document has a technical problem that the production trend cannot be predicted in advance during use, which leads to reduced production efficiency. 2. Patent document US08997525B2 discloses a system and method for manufacturing foam glass using submerged combustion. However, the above document has the technical problem of difficulty in timely warning and handling of abnormal situations when manufacturing foam glass; 3. Patent document JP2010254547A discloses a glass product manufacturing system and a glass product manufacturing method. However, the glass product manufacturing system in the above document has a technical problem that it is unable to update and adjust the system's predicted production trend in real time according to the monitored real-time production data during the preparation process; 4. Patent document CN118444619B discloses an intelligent management system for borosilicate glass processing based on the Internet of Things. However, the intelligent management system for glass processing in the above document has technical problems in the production process, such as being unable to judge the probability and time point of potential failures based on historical failure data and real-time operation data, and installing maintenance resources in advance. Summary of the invention

[0004] The purpose of the present invention is to provide an optical glass production and processing monitoring system based on Internet of Things technology to solve the technical problems raised in the above background technology.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: an optical glass production and processing monitoring system based on Internet of Things technology, comprising an Internet of Things data collector component, a data processing and analysis component, an intelligent monitoring and early warning component, a user interactive control screen component, a permission manager component, an adaptive learning optimization component, and a fault prediction and maintenance management component; The IoT data collector component is configured at various key locations of optical glass production and processing equipment to collect data on temperature and humidity parameters, pressure parameters, flow parameters, viscosity parameters, and processing component parameters during the production and processing process in real time; The data processing and analysis component is electrically connected to the IoT data collector component, and is responsible for receiving, storing, processing and analyzing the key parameter data, and predicting production trends through large-scale data analysis algorithms and machine intelligence learning algorithms, while obtaining adaptive optimization and fault prediction data in the production process; The data processing and analysis component includes a big data processing engine and a machine intelligence learning algorithm library, which is used to process and analyze massive data in real time and provide production trend prediction, adaptive optimization and fault prediction functions; The steps of predicting production trends using the large-scale data analysis algorithm and machine intelligence learning algorithm are as follows: Step 1: Data collection: Real-time data of each link in the production process obtained by the IoT data collector component, including PLC equipment operation data, temperature and humidity data, pressure data, flow data, viscosity data, composition data, quality inspection data and output data; Step 2: Algorithm generation: Based on the historical data obtained in step 1, combined with large-scale data analysis algorithms and machine intelligence learning algorithms, large-scale data analysis algorithms and machine intelligence learning algorithms use linear regression algorithms to generate algorithms for the relationship between production trends and various influencing factors, and then obtain a prediction algorithm, the formula of which is:

[0006] in is the predicted value, that is, the output data predicted by the prediction algorithm based on the input features, is the intercept term, which indicates the baseline level of the predicted value when all independent variables are 0. , is the regression coefficient, which indicates the impact of each independent variable on the prediction. , is the independent variable, i.e., the input feature, which is the data collected in the production process; Step 3: Application of prediction algorithm: Based on the prediction algorithm formula obtained in step 2, input corresponding parameters, i.e. input features, and then estimate the future production trend; Step 4: Trend prediction within the production cycle. Scan each time period within the production cycle and calculate them one by one through the prediction algorithm formula to obtain the expected production volume or production trend at each time point in the entire production cycle.

[0007] Preferably, the IoT data collector component includes a PLC interface, a sensor component interface and a quality detection equipment interface; PLC interface, used to connect and monitor PLC equipment on the production line and obtain PLC equipment operation data; The sensor component interface is used to connect the temperature and humidity sensor component, the pressure sensor component, the flow sensor component, the viscosity sensor component and the component analyzer to obtain temperature and humidity data, pressure data, flow data, viscosity data, component data, quality inspection data and output data; The quality inspection equipment interface is used to connect to the optical glass quality inspection equipment to obtain quality inspection data. The data parameters collected by the Internet of Things data collector component are transmitted to the data processing and analysis component via wired or wireless connection.

[0008] Preferably, the intelligent monitoring and early warning component is electrically connected to the data processing and analysis component, monitors the status of the production line in real time based on the analysis results provided by the data processing and analysis component, and immediately triggers the early warning mechanism when an abnormality is detected, and sends early warning information to the management personnel through a preset early warning mechanism and communication method.

[0009] Preferably, the intelligent monitoring and early warning component includes an early warning rule library and an early warning execution component. The early warning rule library stores and records the judgment criteria and early warning levels of various types of production anomalies. The early warning execution component captures abnormal conditions in the production process based on the analysis results of the data processing and analyzer component, matches the rules in the early warning rule library, triggers corresponding early warning actions, and performs real-time early warning processing through sound and light alarms, text messages, emails or APP push methods, ensuring that the early warning information can be delivered to management staff through multiple channels and in real time.

[0010] Preferably, the user interactive control screen component is connected to each component of the production and processing monitoring system by wired or wireless means, and provides a remote access interface, so that managers can remotely monitor the production status of the production line, view real-time data, historical data and analysis results, and perform parameter adjustments and remote management operations through mobile devices or computers.

[0011] Preferably, the user interactive control screen component provides a graphical display function, including a real-time monitoring diagram of the production status, a historical data trend diagram, an abnormal event record table and production report generation, to support management personnel to conduct intuitive and convenient remote management and monitoring. The user interactive control screen component includes a remote optimization component, and the remote optimization component is electrically connected to the data processing analyzer component to automatically or manually adjust the production parameters according to the analysis results to optimize the production process.

[0012] Preferably, the user interaction control screen component includes a control interface, which is used to connect a voice input component and a gesture input component. The voice input component includes a multi-voice translation package, and the gesture input component includes a gesture translation package and a high-precision camera for capturing and analyzing the gesture movements of the manager.

[0013] Preferably, the authority manager component is electrically connected to the user interaction control screen component, and different operation management authorities are allocated according to the responsibilities of the managers to prevent unauthorized misoperation.

[0014] Preferably, the adaptive learning optimization component is electrically connected to the data processing analyzer component and the user interaction control screen component to continuously collect feedback data during the production process, and continuously train and optimize the prediction algorithm and production process control strategy in combination with the machine intelligence learning algorithm; The adaptive learning optimization component includes an algorithm verification unit and an update unit, forming a closed-loop algorithm optimization system. The algorithm verification unit regularly verifies the prediction algorithm and evaluates the accuracy of the algorithm by comparing the results of the algorithm prediction with the actual production data. Once the algorithm prediction performance is found to have declined, the update process of the algorithm update unit is immediately triggered, and the algorithm is retrained using the latest data set to ensure the timeliness and accuracy of the prediction algorithm.

[0015] Preferably, the fault prediction maintenance management component is electrically connected to the data processing analyzer component and the user interaction control screen component to analyze historical fault data and real-time operation data, predict the probability and time point of occurrence of potential faults, automatically generate maintenance plans and early warning notifications, arrange maintenance resources in advance, and reduce unplanned downtime; The fault prediction maintenance management component includes a spare parts management sub-component. Based on the results of equipment fault prediction, it automatically calculates and recommends the type, quantity and best purchasing time of the required spare parts, optimizes spare parts inventory management, reduces inventory costs, and ensures the timely supply of spare parts during maintenance.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention collects key parameter data in the production and processing process in real time through the Internet of Things data collector component. These data are transmitted to the data processing and analysis component, which uses the big data processing engine and the machine intelligence learning algorithm library for real-time processing and analysis. Among them, the large data analysis algorithm and the machine intelligence learning algorithm use the linear regression algorithm and combine historical data to construct a prediction algorithm to predict the production trend. This prediction process includes data collection, algorithm generation, prediction algorithm application and trend prediction steps within the production cycle. By inputting corresponding parameters, the system can estimate future production trends, and scan and calculate each time period within the production cycle one by one, so as to obtain the estimated production volume or production trend at each time point in the entire production cycle, which not only improves production efficiency and quality control, but also realizes intelligent management and optimization of the production process through adaptive learning and fault prediction functions; 2. The intelligent monitoring and early warning component of the present invention monitors the overall status of the production line in real time based on the in-depth analysis results provided by the data processing and analysis component. Once any abnormal signs are detected, the intelligent monitoring and early warning component will quickly start the early warning mechanism, and the component has a built-in early warning rule library, which records in detail the judgment criteria and corresponding early warning levels of various production abnormalities. The early warning execution component can accurately capture abnormal situations in the production process, quickly match relevant rules in the early warning rule library, and immediately trigger corresponding early warning actions. In order to ensure the immediate transmission of early warning information, the intelligent monitoring and early warning component adopts a variety of early warning methods, including sound and light alarms, text messages, emails, and APP push, to ensure that the early warning information can be delivered to the management staff in real time and accurately through multiple channels, so as to respond to and handle production abnormalities in a timely manner and ensure the smooth operation of the production process; 3. The present invention is electrically connected to closely cooperate with the data processing and analysis component and the user interactive control screen component. The component continuously collects feedback data in the production process, and uses advanced machine intelligence learning algorithms to deeply analyze these data. Based on this, the prediction algorithm and production process control strategy are continuously trained and optimized. The algorithm verification unit regularly verifies the accuracy of the prediction algorithm, and by comparing the prediction results with the actual production data, it promptly finds the situation where the algorithm performance has declined, and immediately triggers the update unit to start the update process. The update unit uses the latest data set to retrain the prediction algorithm to ensure that the prediction algorithm always maintains timeliness and high accuracy, thereby effectively improving production efficiency and product quality; 4. The present invention accurately predicts the probability and time of occurrence of potential faults by analyzing historical fault data and real-time operation data, and then automatically generates maintenance plans and early warning notifications, so that maintenance resources can be arranged in advance, thereby significantly reducing unplanned downtime and ensuring the continuous and stable operation of the production line. In addition, the fault prediction maintenance management component is also equipped with a spare parts management sub-component, which can intelligently calculate and recommend the type, quantity and optimal procurement time of the required spare parts based on the equipment fault prediction results. It not only optimizes the spare parts inventory management and reduces inventory costs, but also ensures the immediate supply of spare parts during maintenance, further improving the overall maintenance efficiency and production benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is an overall system block diagram of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0019] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0020] Example 1: Please refer to Figure 1 , an embodiment provided by the present invention: an optical glass production and processing monitoring system based on the Internet of Things technology, including an Internet of Things data collector component, a data processing and analysis component, an intelligent monitoring and early warning component, a user interactive control screen component, a permission manager component, an adaptive learning optimization component and a fault prediction maintenance management component; The IoT data collector components are installed in key parts of optical glass production and processing equipment to collect temperature and humidity parameters, pressure parameters, flow parameters, viscosity parameters and processing component parameter data in real time during the production and processing process; The data processing and analysis component is electrically connected to the IoT data collector component and is responsible for receiving, storing, processing and analyzing key parameter data, predicting production trends through large-scale data analysis algorithms and machine intelligence learning algorithms, and obtaining adaptive optimization and fault prediction data in the production process; The data processing and analysis component includes a big data processing engine and a machine intelligence learning algorithm library, which is used to process and analyze massive data in real time, and provide production trend prediction, adaptive optimization, and fault prediction functions; The steps for large-scale data analysis algorithms and machine intelligence learning algorithms to predict production trends are as follows: Step 1: Data collection: Real-time data of each link in the production process obtained by the IoT data collector component, including PLC equipment operation data, temperature and humidity data, pressure data, flow data, viscosity data, composition data, quality inspection data and output data; Step 2: Algorithm generation: Based on the historical data obtained in step 1, combined with large-scale data analysis algorithms and machine intelligence learning algorithms, large-scale data analysis algorithms and machine intelligence learning algorithms use linear regression algorithms to generate algorithms for the relationship between production trends and various influencing factors, and then obtain a prediction algorithm, the formula of which is:

[0021] in is the predicted value, that is, the output data predicted by the prediction algorithm based on the input features, is the intercept term, which indicates the baseline level of the predicted value when all independent variables are 0. , is the regression coefficient, which indicates the impact of each independent variable on the prediction. , is the independent variable, i.e., the input feature, which is the data collected in the production process; Step 3: Application of prediction algorithm: Based on the prediction algorithm formula obtained in step 2, input corresponding parameters, i.e. input features, and then estimate the future production trend; Step 4: Trend prediction within the production cycle: Scan each time period within the production cycle and calculate them one by one through the prediction algorithm formula to obtain the estimated production volume or production trend at each time point in the entire production cycle; Furthermore, the key parameter data of the production and processing process are collected in real time through the Internet of Things data collector component. These data are transmitted to the data processing and analysis component, which uses the big data processing engine and the machine intelligence learning algorithm library for real-time processing and analysis. Among them, the large-scale data analysis algorithm and the machine intelligence learning algorithm use the linear regression algorithm and combine historical data to construct a prediction algorithm to predict production trends. This prediction process includes data collection, algorithm generation, prediction algorithm application and trend prediction steps within the production cycle. By inputting the corresponding parameters, the system can estimate future production trends, and scan and calculate each time period within the production cycle one by one, so as to obtain the expected production volume or production trend at each time point in the entire production cycle. This system not only improves production efficiency and quality control, but also realizes intelligent management and optimization of the production process through adaptive learning and fault prediction functions.

[0022] Example 2: Please refer to Figure 1 , an embodiment provided by the present invention: the IoT data collector component includes a PLC interface, a sensor component interface and a quality detection equipment interface; PLC interface, used to connect and monitor PLC equipment on the production line and obtain PLC equipment operation data; The sensor component interface is used to connect the temperature and humidity sensor component, the pressure sensor component, the flow sensor component, the viscosity sensor component and the component analyzer to obtain temperature and humidity data, pressure data, flow data, viscosity data, component data, quality inspection data and output data; The quality inspection equipment interface is used to connect the optical glass quality inspection equipment to obtain the quality inspection data. The data parameters collected by the IoT data collector component are transmitted to the data processing and analysis component through wired or wireless connection; Furthermore, by integrating the PLC interface, sensor component interface and quality inspection equipment interface, the PLC interface can seamlessly connect and monitor the PLC equipment on the production line, and capture the operating status data of the PLC equipment in real time. The sensor component interface is widely connected to temperature and humidity, pressure, flow, viscosity and composition analyzers, thereby comprehensively collecting various key parameters in the production process, and the quality inspection equipment interface is specifically used to connect optical glass quality inspection equipment to ensure the accurate acquisition of quality inspection data. All these collected data parameters are instantly transmitted to the data processing and analyzer component for subsequent processing and analysis through efficient wired or wireless transmission methods, which not only greatly improves the efficiency and accuracy of data collection, but also provides a solid foundation for intelligent monitoring and optimization of the entire production process.

[0023] Example 3: Please refer to Figure 1, an embodiment provided by the present invention: an intelligent monitoring and early warning component is electrically connected to a data processing and analyzing component, monitors the production line status in real time according to the analysis result provided by the data processing and analyzing component, and immediately triggers an early warning mechanism when an abnormality is detected, and sends early warning information to management personnel through a preset early warning mechanism and communication method, and the intelligent monitoring and early warning component includes an early warning rule library and an early warning execution component; The early warning rule library stores and records the judgment criteria and early warning levels of various production anomalies. The early warning execution component captures abnormal situations in the production process according to the analysis results of the data processing and analysis component, matches the rules in the early warning rule library, triggers the corresponding early warning actions, and performs real-time early warning processing through sound and light alarms, SMS, emails or APP push methods, ensuring that the early warning information can be delivered to management staff in real time through multiple channels; Furthermore, the intelligent monitoring and early warning component monitors the overall status of the production line in real time based on the in-depth analysis results provided by the data processing and analyzer component. Once any abnormal signs are detected, the intelligent monitoring and early warning component will quickly activate the early warning mechanism. The component has a built-in early warning rule library, which records in detail the judgment criteria and corresponding early warning levels of various production abnormalities. The early warning execution component can accurately capture abnormal situations in the production process, quickly match relevant rules in the early warning rule library, and immediately trigger corresponding early warning actions. In order to ensure the immediate transmission of early warning information, the intelligent monitoring and early warning component adopts a variety of early warning methods, including sound and light alarms, text messages, emails and APP push, to ensure that the early warning information can be delivered to management staff through multiple channels, in real time and accurately, so as to respond to and handle production abnormalities in a timely manner and ensure the smooth operation of the production process.

[0024] Example 4: Please refer to Figure 1 , an embodiment provided by the present invention: a user interactive control screen component is connected to each component of the production and processing monitoring system through wired or wireless connections, and provides a remote access interface, so that management personnel can remotely monitor the production status of the production line, view real-time data, historical data and analysis results, and perform parameter adjustment and remote management operations through mobile devices or computers; The user interactive control screen component provides a graphical display function, including a real-time monitoring diagram of production status, a historical data trend diagram, an abnormal event record table, and production report generation, supporting managers to conduct intuitive and convenient remote management and monitoring. The user interactive control screen component includes a remote optimization component, and the remote optimization component is electrically connected to the data processing analyzer component to automatically or manually adjust production parameters according to the analysis results to optimize the production process; The user interaction control screen component includes a control interface, which is used to connect a voice input component and a gesture input component. The voice input component includes a multi-voice translation package, and the gesture input component includes a gesture translation package and a high-precision camera for capturing and analyzing gestures of managers. The authority manager component is electrically connected to the user interaction control screen component, and different operation management authorities are assigned according to the responsibilities of the management personnel to prevent unauthorized misoperation; Furthermore, it is connected to various components of the system by wired or wireless means, and provides a remote access interface, so that managers can use mobile devices or computers to remotely monitor production status, view real-time and historical data, abnormal time records, production reports, analysis results, and perform parameter adjustments and remote management anytime and anywhere, providing managers with an intuitive and convenient remote monitoring and management experience. Through the user interactive control screen component, the built-in remote optimization component is closely connected with the data processing analyzer component, and can automatically or manually optimize production parameters according to the analysis results, further improving production efficiency; The control interface incorporates advanced voice input and gesture input technologies, supports multi-language translation and gesture recognition, and greatly enhances the flexibility and convenience of operation. At the same time, the addition of the permission manager component ensures that different operating permissions are allocated according to the responsibilities of managers, effectively preventing unauthorized misoperation and providing a solid guarantee for the safe and stable operation of the entire system.

[0025] Example 5: Please refer to Figure 1 , an embodiment provided by the present invention: an adaptive learning optimization component is electrically connected to a data processing analyzer component and a user interaction control screen component, continuously collects feedback data from the production process, and continuously trains and optimizes the prediction algorithm and the production process control strategy in combination with a machine intelligence learning algorithm; The adaptive learning optimization component includes an algorithm verification unit and an update unit, forming a closed-loop algorithm optimization system. The algorithm verification unit regularly verifies the prediction algorithm and evaluates the accuracy of the algorithm by comparing the results predicted by the algorithm with the actual production data. Once the prediction performance of the algorithm is found to have degraded, the update process of the algorithm update unit is immediately triggered, and the algorithm is retrained with the latest data set, thereby ensuring the timeliness and accuracy of the prediction algorithm. Furthermore, through the close collaboration between the electrical connection and the data processing analyzer component and the user interaction control screen component, this component continuously collects feedback data from the production process, and uses advanced machine intelligence learning algorithms to conduct in-depth analysis of these data, and on this basis continuously trains and optimizes the prediction algorithm and production process control strategy. The algorithm verification unit regularly verifies the accuracy of the prediction algorithm, and by comparing the prediction results with the actual production data, it promptly discovers the degradation of the algorithm performance and immediately triggers the update unit to start the update process. The update unit uses the latest data set to retrain the prediction algorithm to ensure that the prediction algorithm always maintains timeliness and high accuracy, thereby effectively improving production efficiency and product quality.

[0026] Example 6: Please refer to Figure 1 , an embodiment provided by the present invention: a fault prediction maintenance management component is electrically connected to a data processing analyzer component and a user interaction control screen component, analyzes historical fault data and real-time operation data, predicts the probability and time point of occurrence of potential faults, automatically generates maintenance plans and early warning notifications, arranges maintenance resources in advance, and reduces unplanned downtime; The fault prediction maintenance management component includes the spare parts management subcomponent. Based on the results of equipment fault prediction, it automatically calculates and recommends the types, quantities and best purchasing time of the required spare parts, optimizes spare parts inventory management, reduces inventory costs, and ensures the timely supply of spare parts during maintenance. Furthermore, by analyzing historical fault data and real-time operation data, the probability and time of potential faults can be accurately predicted, and maintenance plans and early warning notifications can be automatically generated, so that maintenance resources can be arranged in advance, thereby significantly reducing unplanned downtime and ensuring the continuous and stable operation of the production line. In addition, the fault prediction maintenance management component is also equipped with a spare parts management sub-component, which can intelligently calculate and recommend the type, quantity and best purchasing time of the required spare parts based on the equipment fault prediction results. It not only optimizes the spare parts inventory management and reduces inventory costs, but also ensures the immediate supply of spare parts during maintenance, further improving the overall maintenance efficiency and production benefits.

[0027] Working principle: The key parameter data of the production and processing process are collected in real time through the IoT data collector component. These data are transmitted to the data processing and analysis component, which uses the big data processing engine and machine intelligence learning algorithm library for real-time processing and analysis. Among them, the large-scale data analysis algorithm and machine intelligence learning algorithm use linear regression algorithm and historical data to build a prediction algorithm to predict production trends. This prediction process includes data collection, algorithm generation, prediction algorithm application and trend prediction steps within the production cycle. By inputting the corresponding parameters, the system can estimate future production trends, and scan and calculate each time period within the production cycle one by one, so as to obtain the expected production volume or production at each time point in the entire production cycle. This system not only improves production efficiency and quality control, but also realizes intelligent management and optimization of the production process through adaptive learning and fault prediction functions. By integrating PLC interface, sensor component interface and quality inspection equipment interface, the PLC interface can seamlessly connect and monitor the PLC equipment on the production line, and capture the operating status data of the PLC equipment in real time. The sensor component interface is widely connected to temperature and humidity, pressure, flow, viscosity and composition analyzers, so as to comprehensively collect various key parameters in the production process, and the quality inspection equipment interface is specially used to connect optical glass quality inspection equipment to ensure the accurate acquisition of quality inspection data. All these collected data parameters are transmitted instantly through efficient wired or wireless transmission methods. The data is sent to the data processing and analysis component for subsequent processing and analysis, which not only greatly improves the efficiency and accuracy of data collection, but also provides a solid foundation for the intelligent monitoring and optimization of the entire production process. The intelligent monitoring and early warning component monitors the overall status of the production line in real time based on the in-depth analysis results provided by the data processing and analysis component. Once any abnormal signs are detected, the intelligent monitoring and early warning component will quickly activate the early warning mechanism, and the component has a built-in early warning rule library, which records in detail the judgment criteria and corresponding early warning levels of various production anomalies. The early warning execution component can accurately capture abnormal situations in the production process, quickly match the relevant rules in the early warning rule library, and immediately trigger the corresponding early warning action. In order to ensure the immediate transmission of early warning information, the intelligent monitoring The early warning component adopts a variety of early warning methods, including sound and light alarms, text messages, emails and APP push, to ensure that the early warning information can be delivered to the management staff in real time and accurately through multiple channels, so as to respond to and handle production anomalies in a timely manner and ensure the smooth operation of the production process. It is connected to various components of the system through wired or wireless methods, and provides a remote access interface, so that managers can use mobile devices or computers to remotely monitor production status, view real-time and historical data, abnormal time records, production reports, analysis results, and adjust parameters and remotely manage anytime and anywhere, providing managers with an intuitive and convenient remote monitoring and management experience. Through the user interactive control screen component, the built-in remote optimization component is closely connected with the data processing analyzer component.It can automatically or manually optimize production parameters according to the analysis results to further improve production efficiency. The setting of the control interface incorporates advanced voice input and gesture input technology, supports multi-language translation and gesture recognition, and greatly improves the flexibility and convenience of operation. At the same time, the addition of the permission manager component ensures that different operation permissions are allocated according to the responsibilities of managers, effectively preventing unauthorized misoperation and providing a solid guarantee for the safe and stable operation of the entire system. Through the close cooperation of the electrical connection, data processing analyzer component and user interaction control screen component, this component continuously collects feedback data from the production process, and uses advanced machine intelligence learning algorithms to conduct in-depth analysis of these data. On this basis, it continuously trains and optimizes the prediction algorithm and production process control strategy. The algorithm verification unit regularly verifies the accuracy of the prediction algorithm and sends timely feedback by comparing the prediction results with the actual production data. The system detects the degradation of algorithm performance and immediately triggers the update unit to start the update process. The update unit uses the latest data set to retrain the prediction algorithm to ensure that the prediction algorithm always maintains timeliness and high accuracy, thereby effectively improving production efficiency and product quality. By analyzing historical fault data and real-time operation data, the probability and time of potential faults are accurately predicted, and maintenance plans and early warning notifications are automatically generated, so that maintenance resources can be arranged in advance, thereby significantly reducing unplanned downtime and ensuring the continuous and stable operation of the production line. In addition, the fault prediction maintenance management component is also equipped with a spare parts management sub-component, which can intelligently calculate and recommend the type, quantity and best purchase time of the required spare parts based on the equipment fault prediction results. It not only optimizes spare parts inventory management and reduces inventory costs, but also ensures the immediate supply of spare parts during maintenance, further improving the overall maintenance efficiency and production benefits.

[0028] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. An optical glass production and processing monitoring system based on Internet of Things technology, characterized by: It includes IoT data collector components, data processing and analysis components, intelligent monitoring and early warning components, user interaction control screen components, authority manager components, adaptive learning optimization components, and fault prediction and maintenance management components; The IoT data collector component is configured at various key locations of optical glass production and processing equipment to collect data on temperature and humidity parameters, pressure parameters, flow parameters, viscosity parameters, and processing component parameters during the production and processing process in real time; The data processing and analysis component is electrically connected to the IoT data collector component, and is responsible for receiving, storing, processing and analyzing the key parameter data, and predicting production trends through large-scale data analysis algorithms and machine intelligence learning algorithms, while obtaining adaptive optimization and fault prediction data in the production process; The data processing and analysis component includes a big data processing engine and a machine intelligence learning algorithm library, which is used to process and analyze massive data in real time and provide production trend prediction, adaptive optimization and fault prediction functions; The steps of predicting production trends using the large-scale data analysis algorithm and machine intelligence learning algorithm are as follows: Step 1: Data collection: Real-time data of each link in the production process obtained by the IoT data collector component, including PLC equipment operation data, temperature and humidity data, pressure data, flow data, viscosity data, composition data, quality inspection data and output data; Step 2: Algorithm generation: Based on the historical data obtained in step 1, combined with large-scale data analysis algorithms and machine intelligence learning algorithms, large-scale data analysis algorithms and machine intelligence learning algorithms use linear regression algorithms to generate algorithms for the relationship between production trends and various influencing factors, and then obtain a prediction algorithm, the formula of which is: ， in is the predicted value, that is, the output data predicted by the prediction algorithm based on the input features, is the intercept term, which indicates the baseline level of the predicted value when all independent variables are 0. , is the regression coefficient, which indicates the impact of each independent variable on the prediction. , is the independent variable, i.e., the input feature, which is the data collected in the production process; Step 3: Application of prediction algorithm: Based on the prediction algorithm formula obtained in step 2, input corresponding parameters, i.e. input features, and then estimate future production trends; Step 4: Trend prediction within the production cycle. Scan each time period within the production cycle and calculate them one by one through the prediction algorithm formula to obtain the expected production volume or production trend at each time point in the entire production cycle.

2. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The IoT data collector components include a PLC interface, a sensor component interface, and a quality inspection equipment interface; PLC interface, used to connect and monitor PLC equipment on the production line and obtain PLC equipment operation data; The sensor component interface is used to connect the temperature and humidity sensor component, the pressure sensor component, the flow sensor component, the viscosity sensor component and the component analyzer to obtain temperature and humidity data, pressure data, flow data, viscosity data, component data, quality inspection data and output data; The quality inspection equipment interface is used to connect to the optical glass quality inspection equipment to obtain quality inspection data. The data parameters collected by the Internet of Things data collector component are transmitted to the data processing and analysis component via wired or wireless connection.

3. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The intelligent monitoring and early warning component is electrically connected to the data processing and analysis component, monitors the production line status in real time based on the analysis results provided by the data processing and analysis component, and immediately triggers the early warning mechanism when an abnormality is detected, and sends early warning information to the management personnel through the preset early warning mechanism and communication method. The intelligent monitoring and early warning component includes an early warning rule library and an early warning execution component.

4. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 3 is characterized by: The early warning rule library stores and records the judgment criteria and early warning levels of various types of production anomalies. The early warning execution component captures abnormal situations in the production process based on the analysis results of the data processing and analyzer component, matches the rules in the early warning rule library, triggers corresponding early warning actions, and performs real-time early warning processing through sound and light alarms, text messages, emails or APP push methods, ensuring that early warning information can be delivered to management staff through multiple channels and in real time.

5. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The user interactive control screen component is connected to each component of the production and processing monitoring system through wired or wireless connections, and provides a remote access interface, so that managers can remotely monitor the production status of the production line, view real-time data, historical data and analysis results, and perform parameter adjustments and remote management operations through mobile devices or computers.

6. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The user interactive control screen component provides a graphical display function, including a real-time monitoring diagram of production status, a historical data trend diagram, an abnormal event record table and production report generation, supporting management personnel to conduct intuitive and convenient remote management and monitoring. The user interactive control screen component includes a remote optimization component, and the remote optimization component is electrically connected to the data processing analyzer component to automatically or manually adjust production parameters according to the analysis results to optimize the production process.

7. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The user interaction control screen component includes a control interface, which is used to connect a voice input component and a gesture input component. The voice input component includes a multi-voice translation package, and the gesture input component includes a gesture translation package and a high-precision camera for capturing and analyzing the gesture movements of the manager.

8. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized by: The authority manager component is electrically connected to the user interaction control screen component, and different operation management authorities are allocated according to the responsibilities of the management personnel to prevent unauthorized misoperation.

9. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1 is characterized in that: The adaptive learning optimization component is electrically connected to the data processing analyzer component and the user interactive control screen component to continuously collect feedback data from the production process, and continuously trains and optimizes the prediction algorithm and production process control strategy in combination with the machine intelligent learning algorithm; The adaptive learning optimization component includes an algorithm verification unit and an update unit, forming a closed-loop algorithm optimization system. The algorithm verification unit regularly verifies the prediction algorithm and evaluates the accuracy of the algorithm by comparing the results of the algorithm prediction with the actual production data. Once the algorithm prediction performance is found to have declined, the update process of the algorithm update unit is immediately triggered, and the algorithm is retrained using the latest data set to ensure the timeliness and accuracy of the prediction algorithm.

10. The optical glass production and processing monitoring system based on Internet of Things technology according to claim 1, characterized in that: The fault prediction maintenance management component is electrically connected to the data processing analyzer component and the user interactive control screen component to analyze historical fault data and real-time operation data, predict the probability and time of occurrence of potential faults, automatically generate maintenance plans and early warning notifications, arrange maintenance resources in advance, and reduce unplanned downtime; the fault prediction maintenance management component includes a spare parts management sub-component, which automatically calculates and recommends the type, quantity and optimal procurement time of required spare parts based on the results of equipment fault prediction, optimizes spare parts inventory management, reduces inventory costs, and ensures the timely supply of spare parts during maintenance.

Images