MES platform-based data acquisition and monitoring analysis system

Abstract

The invention provides a data acquisition and monitoring analysis system based on an MES platform, and relates to an industrial software application system. Comprising a low-code development module, a factory modeling module, a monitoring module and a data acquisition module, the low-code development module realizes cross-device linkage development and control program generation through combination of a dragging interface and a device API library in an MES platform integration environment, and guarantees efficient communication control of the device, the factory modeling module integrates two production modes, and the monitoring module is connected with the monitoring module. The monitoring module is used for realizing dynamic modeling and optimizing a production process according to multi-dimensional parameters, the monitoring module is used for realizing ultra-low-delay transmission processing and real-time monitoring of data under high concurrency by applying a dual-cache and message middleware mechanism, and the data acquisition module is used for realizing real-time monitoring of the data based on a machine learning algorithm and a complex event processing technology. Dynamically adjusting the acquisition frequency precision based on the production state; the system aims at improving the efficiency, quality and management level of industrial production, and has wide application prospects and important industrial software application value.

Description

Technical Field

[0001] The present invention relates to an industrial software application system, in particular to a data collection and monitoring and analysis system based on an MES platform. Background Art

[0002] With the continuous development of the manufacturing industry, the demand for intelligent management of factories is growing. In industrial production, efficient data collection, monitoring and analysis are crucial to improving production efficiency, optimizing process flow and ensuring product quality. As a bridge connecting the upper-level planning management system and the lower-level production control system, the MES platform plays an increasingly critical role, and related technologies are also constantly evolving to adapt to the complex and changing production environment.

[0003] Traditional factory management systems mostly use independent software development methods, programming for different equipment and production links separately. For example, for equipment control, professional programmers usually write fixed control codes based on the model and function of specific equipment. In terms of data transmission, it is common to use a single database storage and a simple data transmission protocol, which is difficult to handle large amounts of concurrent data. This approach lacks flexibility, has a long development cycle, and has poor compatibility between different systems.

[0004] Existing technologies are difficult to meet the rapidly changing production needs and complex equipment integration requirements, and the data processing efficiency is low, and it is impossible to optimize the production process in real time. The data collection and monitoring analysis system based on the MES platform proposed in this paper realizes rapid cross-device linkage development through low-code development modules, the factory modeling module integrates multi-dimensional parameter dynamic modeling, the monitoring module uses dual caching and message middleware to ensure efficient data processing, and the data collection module dynamically adjusts the collection based on advanced algorithms and performs multi-dimensional analysis, which comprehensively improves the intelligent level of factory management. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the shortcomings of the prior art, the present invention provides a data collection and monitoring analysis system based on the MES platform to solve the problems of poor equipment linkage, low data collection efficiency, lack of dynamics in factory modeling, and monitoring delays and unstable data processing under high concurrency.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a data acquisition and monitoring analysis system based on the MES platform, including a low-code development module, a factory modeling module, a monitoring module and a data acquisition module, wherein:

[0009] The low-code development module is used to integrate the low-code development environment into the MES platform, realize instant cross-device linkage development through the drag-and-drop interface combined with the device API library, and generate control programs adapted to different devices in real time to achieve efficient communication and control between devices;

[0010] The factory modeling module integrates the two production modes of process production and scattered manufacturing, realizes dynamic factory modeling based on multi-dimensional parameters of equipment status, process route and production rhythm, and optimizes the production process through real-time data analysis;

[0011] The monitoring module adopts dual cache and message middleware mechanism to ensure ultra-low latency transmission and processing of data under high concurrency conditions, and realizes real-time production execution and monitoring during production execution;

[0012] The data collection module dynamically adjusts the data collection frequency and accuracy according to the production status based on machine learning algorithms and complex event processing technology, and provides real-time feedback and optimization suggestions.

[0013] Preferably, the low-code development module is first integrated in the MES platform. In actual operation, it is necessary to comprehensively analyze and understand the architecture and interface of the MES platform, determine the appropriate integration points, and then introduce the core components of the low-code development module into the MES platform, and achieve seamless docking with the platform through standardized interface protocols. During the integration process, it is necessary to ensure the stability and compatibility of the low-code development environment, and to be able to work with the existing functional modules of the MES platform to establish a connection channel with the device API library, so that the device interface can be easily called in the low-code development interface to achieve cross-device interactive operations. At the same time, the drag and drop interface is optimized to adapt to the operating style and user habits of the MES platform, and to be able to interact and share data with other modules of the platform. By configuring relevant parameters and settings, the low-code development module can be automatically started and run in the MES platform.

[0014] Preferably, in actual operation, developers can intuitively see the drag and drop interface. When cross-device linkage development is required, developers select the interface of the target device from the device API library and connect the functional components of different devices by dragging and dropping. For example, to realize the linkage between device A and device B, first find the control component of device A and the response component of device B on the interface, and then connect them by dragging lines. Then, control programs adapted to different devices are automatically generated according to the connection relationship and device parameters. At the same time, changes in device parameters are monitored in real time. Once the parameters change, the control program is adjusted immediately to ensure efficient communication and control between devices.

[0015] Preferably, the control program generated by the low-code development module can be dynamically adjusted according to the device parameters. When the operating status, performance indicators and other parameters of the device change, these changes will be automatically captured. For example, when the operating speed of a device speeds up or slows down, the control program will adjust the frequency of sending instructions to the device according to the new speed parameters. At the same time, the low-code development module also automatically adjusts the interface complexity and functions according to the developer's skill level and project requirements through adaptive development environment configuration; for novice developers, the interface will present relatively simple operation guides and a small number of advanced function options, allowing them to get started quickly; for experienced developers, more advanced functions will be automatically displayed according to their needs to improve development efficiency.

[0016] Preferably, the low-code development module has an automatic matching algorithm for process rules, which can automatically generate the optimal process route configuration according to the real-time status of production equipment and task requirements; during the production process, the system monitors the status of the equipment in real time, including the equipment's operating mode, load conditions and fault conditions; at the same time, combined with the current production task requirements, the complexity and urgency of the task are analyzed, and historical data is analyzed through the automatic matching algorithm for process rules to find the optimal process route configuration cases under similar circumstances, and reference and optimize them; when facing an urgent production task and a certain equipment fails, the automatic matching algorithm for process rules will automatically search for solutions for similar situations in historical data, adjust the process route, bypass the faulty equipment, and select other available equipment as a replacement, thereby reducing manual intervention and optimizing the efficiency and accuracy of production configuration.

[0017] Preferably, the factory modeling module provides a basis for comprehensive modeling of the factory by integrating the two production modes of process production and discrete manufacturing. In actual operation, the multi-dimensional parameters of equipment status, process route and production rhythm are first collected. For equipment status, the operating status, fault conditions, etc. of the equipment are monitored in real time through sensors. For process routes, the production processes and process requirements of different products are analyzed. For production rhythm, the production quantity and production cycle per unit time are counted. At the same time, based on these multi-dimensional parameters, advanced modeling algorithms are used to realize dynamic factory modeling. According to the status of different equipment and the requirements of production tasks, the equipment layout and production process in the factory model are adjusted in real time to adapt to changes in actual production conditions.

[0018] Preferably, the factory modeling module optimizes the production process through real-time data analysis; the system continuously receives real-time data from sensors and production equipment, including equipment operating parameters and product quality data, and at the same time, conducts comprehensive analysis in combination with historical production data; through machine learning algorithms, a large amount of data is mined and analyzed to identify potential problems and optimization space in the production process. When it is found that the product quality of a certain production link shows a downward trend, the equipment status, process parameters and other factors of that link will be analyzed, and the process flow and equipment configuration will be automatically adjusted; for example, adjusting the operating parameters of the equipment, changing a certain process in the process route, thereby optimizing production efficiency.

[0019] Preferably, the factory modeling module uses a machine learning algorithm to optimize the association between production equipment and production tasks, reduce equipment idle time, and improve overall production capacity and flexibility; the factory modeling module establishes an association model between equipment and tasks by analyzing the characteristics of production tasks and the performance of equipment; when a new production task arrives, the most suitable equipment is automatically matched according to the task requirements. If a production task has high precision requirements, high-precision equipment will be automatically selected for allocation; at the same time, through the analysis of historical production data, the idle time of equipment is predicted, and suitable production tasks are arranged in advance to avoid equipment idling and improve equipment utilization.

[0020] Preferably, the monitoring module adopts a dual caching mechanism of Redis and Artemis, combined with asynchronous message middleware, to ensure ultra-low latency transmission and processing of data under high concurrency conditions. During data transmission, the data will first be written into the Redis cache. With its fast read and write speed, the Redis cache can quickly store and read data, providing guarantee for the initial caching of data; then the Artemis message middleware will further process and distribute the data; when the amount of data is large, the Artemis can effectively manage the data transmission queue to ensure that the data will not be lost or delayed, and the characteristics of the asynchronous message middleware ensure that the transmission and processing of data will not block other operations of the system, greatly improving the response speed and stability of the system.

[0021] Preferably, the monitoring module controls the system delay to less than 2 seconds in high-concurrency production tasks; to achieve this goal, firstly, by optimizing the data transmission path, the data transfer links in the transmission process are reduced and the data transmission speed is improved; secondly, the data processing algorithm is optimized to improve the efficiency of data processing; for example, parallel processing technology is used to process multiple data requests at the same time to reduce the processing time of a single request; in addition, the system monitors the system load in real time through load monitoring technology. When the load is too high, the resource scheduling algorithm is used to automatically adjust resource allocation, give priority to processing key data, and ensure that the system delay is always controlled within 2 seconds under high concurrency.

[0022] Preferably, the parallel processing technology uses multi-threading or multi-process programming technology to achieve parallel processing. At the operating system level, thread pool technology is used to create multiple threads, and data requests are assigned to these threads for simultaneous processing; it is mainly achieved by simultaneously utilizing multiple CPU cores or multiple computing units to achieve concurrent execution of multiple tasks, and its performance improvement can be estimated by Amdahl's Law. The formula of Amdahl's Law is: S=1 / ((1-p)+p / n), where S is the speedup ratio, p is the proportion of the parallelizable part, and n is the number of resources for parallel processing; for example, if 80% of a task can be processed in parallel and there are 4 parallel processing units, the speedup ratio calculated according to the formula is 2.5, that is, theoretically the processing time can be shortened to 0.4 times the original time.

[0023] Preferably, the load monitoring technology is to collect key indicators of the system through the performance counters of the system performance monitoring tool, including CPU usage, memory usage, network bandwidth occupancy, etc. These tools are based on the kernel mechanism of the operating system, and obtain system performance data through the file system or interface in the system. According to the pre-set threshold, such as CPU usage reaching 80% is considered as high load, to determine whether the system is in a high load state; the resource scheduling algorithm is a priority scheduling algorithm, and when the system load is too high, resources are allocated according to the priority of the task. For key data processing tasks, a higher priority is given to ensure that they can get priority to obtain resources such as CPU time slices and memory space; its principle is based on queuing theory, which regards the tasks in the system as a queuing system, and reduces the waiting time of key tasks by reasonably arranging the service order of tasks, thereby controlling delays.

[0024] Preferably, the monitoring module dynamically adjusts the cache level through a hierarchical cache strategy for data transmission to adapt to different production task requirements; when the data transmission volume is small, only the first-level cache may be used for data storage and processing, and when the data transmission volume is large, the system will automatically start multi-level cache, first storing the data in the memory cache, and when the memory cache reaches a certain capacity, part of the data will be transferred to the disk cache. The system can dynamically allocate cache resources according to the characteristics of the production task and the importance of the data. For the data of key production tasks, more cache resources will be allocated to ensure rapid processing and transmission of data, thereby ensuring efficient execution of production tasks.

[0025] Preferably, the data acquisition module acquires the status data of the production equipment in real time through the physical layer acquisition unit; the physical layer integrates PLC, RFID and sensor network, providing multiple channels for data acquisition; the PLC can directly acquire the operating parameters of the equipment from the equipment control system; the RFID can be used to identify and track the flow of materials; the sensor network can monitor environmental parameters such as temperature, humidity and pressure in real time, and the data acquisition module can dynamically adjust the acquisition frequency and granularity according to the production rhythm; when the production rhythm is fast, the acquisition frequency is increased to ensure timely acquisition of changes in equipment status; when the production rhythm is slow, the acquisition frequency is appropriately reduced to reduce the occupation of system resources. The granularity of the collected data can be adjusted according to different production needs. For example, when the equipment is finely monitored, the data granularity can be increased to obtain more detailed equipment status information.

[0026] Preferably, the data acquisition module also includes a data integration and filtering unit, which mainly adopts dynamic rules and machine learning algorithms to filter redundant data according to the real-time needs of production tasks and reduce unnecessary data processing load; in the data integration process, the data acquisition module will uniformly process the data from different acquisition channels to form a complete production data view; for example, the equipment operating parameters collected by the PLC, the material information collected by the RFID, and the environmental data collected by the sensor network are integrated; then the data is analyzed through the machine learning algorithm, and it is determined which data is redundant according to the dynamic rules; for redundant data, the system will automatically filter and only retain data that is valuable for production decisions, so as to optimize the real-time and accuracy of data acquisition and monitoring.

[0027] Preferably, the data acquisition module combines complex event processing (CEP) technology to perform multi-dimensional analysis of the data, identify potential production anomalies and issue early warnings; the system will monitor the changing trend of the data in real time, and when abnormal fluctuations in the data are found, the CEP technology will be immediately activated to perform multi-dimensional analysis. If the temperature suddenly rises, the equipment operating parameters change abnormally, and the material flow rate slows down, the data acquisition module will comprehensively consider these factors to determine whether there is a production anomaly. Once it is determined that there is a potential anomaly, an early warning will be issued in time to notify relevant personnel to take measures to avoid the occurrence of production accidents.

[0028] (III) Beneficial effects

[0029] The present invention provides a data collection and monitoring analysis system based on the MES platform.

[0030] Beneficial effects:

[0031] 1. The system realizes efficient linkage of data collection, processing, transmission and feedback through double caching and message middleware mechanism, which greatly reduces the data transmission delay and task scheduling time in the production process. Thanks to this, the system can complete the whole process response from data collection to production scheduling within 2 seconds, ensuring real-time monitoring and dynamic adjustment of equipment status and production process, greatly improving production efficiency and reducing potential downtime risks.

[0032] 2. The system adopts a low-code development platform, allowing users to quickly generate control programs and simplify the configuration process of cross-device linkage. Developers can generate automated workflows by simply dragging and dropping API interfaces without writing complex code; this low-code module allows developers to respond quickly to production needs, reduces development costs, reduces human errors, and improves the speed and flexibility of program deployment, helping companies adapt to market changes and production plan adjustments more quickly.

[0033] 3. The system integrates the dual models of process production and discrete manufacturing. Through comprehensive data analysis and optimization of production equipment status, production environment and process routes, it realizes refined management of multi-level production processes. Its closed-loop feedback mechanism not only optimizes the equipment operation status, but also optimizes energy consumption and resource utilization in the production process through ecological monitoring data, thereby achieving higher resource utilization efficiency. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0035] Embodiment 1:

[0036] An embodiment of the present invention provides a data collection and monitoring and analysis system based on an MES platform, including a low-code development module, a factory modeling module, a monitoring module and a data collection module, aiming to integrate various links in the production process, realize real-time collection, analysis and processing of data, and comprehensive monitoring and optimization of production equipment and processes.

[0037] First, a project implementation team including software development engineers, process engineers, production management personnel and equipment maintenance personnel is established; software development engineers are responsible for system integration and development-related work; process engineers provide professional knowledge of production processes to ensure that the system can accurately reflect and optimize the production process; production management personnel coordinate production resources and arrange production tasks to ensure the smooth testing and implementation of the system; equipment maintenance personnel are responsible for ensuring the normal operation of the equipment and assisting in the collection and connection of equipment data; at the same time, all production equipment in the factory is checked and classified, and information such as the equipment model, function, operating status and interface type is recorded, and then a high-speed and stable industrial Ethernet network is built to cover the entire factory area to ensure that the network bandwidth can meet the transmission needs of large amounts of data.

[0038] The low-code development module is then integrated into the MES platform. At the same time, it is necessary to analyze the architecture and interface specifications of the MES platform. By studying the underlying code of the MES platform and technical communication with the MES supplier, the suitable integration point is determined. The core components of the low-code development module are introduced into the MES platform in the form of standardized interface protocols. Software engineers conduct a series of compatibility tests and debugging to ensure the stable operation of the low-code development environment, especially to achieve seamless integration with existing functional modules such as production planning and quality management.

[0039] On the basis of integration, the system communicates with the drag-and-drop interface in the MES platform through the device API library. Developers can achieve cross-device control through the intuitive drag-and-drop interface. During operation, developers select the control components of device A and device B. For example, device A is an injection molding machine and device B is a conveyor belt. The signals of the two are connected by dragging. When the injection molding machine completes injection molding, the conveyor belt starts automatically. The system will generate corresponding control programs according to the control protocols and parameters of the equipment to ensure the linkage operation of the equipment.

[0040] The low-code development module supports adaptive development environment configuration. For example, for novice developers, the system will present a simple interface, limit advanced functions, and simplify operation steps; for experienced developers, the system will unlock more advanced functions and improve development efficiency; at the same time, the system can monitor real-time changes in equipment parameters and dynamically adjust control programs. For example, when the injection speed changes, the system automatically adjusts the speed of the conveyor belt to ensure the smoothness of the linkage process.

[0041] On this basis, the factory modeling module integrates the two modes of process production and discrete manufacturing. The module models the factory through multi-dimensional parameters, including parameters of equipment status, process route and production rhythm. Through real-time collected equipment status data, such as equipment operation mode, load conditions and different process requirements in the process route, the system can dynamically adjust the production model. The factory modeling module will conduct a comprehensive analysis of these data and adjust the model in combination with the real-time needs of the production task. When a certain equipment fails, the system will automatically adjust the production route according to the urgency of the production task, bypass the faulty equipment, and select other available equipment to ensure that the production process is not affected; in order to optimize the production process, the factory modeling module also mines and analyzes historical production data through machine learning algorithms, finds optimization space and adjusts process parameters in real time. When the system detects that the product quality of a certain link has declined, it can further optimize production efficiency by adjusting the operating parameters of the equipment or replacing a process in the process route; in this way, the factory modeling module can maximize production efficiency based on the comprehensive analysis of real-time data and historical data.

[0042] The core of the monitoring module is the use of double cache and message middleware mechanism to ensure low-latency transmission and processing of data under high concurrency conditions; in the specific implementation process, the data will first be written into the Redis cache, and the high-speed read and write characteristics of Redis will be used to achieve fast cache and data reading. Then the Artemis message middleware will further process and distribute the data to ensure the orderliness and integrity of data transmission under large data volumes. Through this asynchronous message transmission mechanism, the system can quickly process and transmit real-time data in the production execution process without blocking other operations. In the case of high-concurrency tasks, the system controls the response delay within 2 seconds through parallel processing technology and load scheduling mechanism; this goal is achieved by reducing the transit links in the data transmission path and optimizing the data processing algorithm, such as using multi-threading or multi-process parallel processing, so that multiple data requests can be processed simultaneously; the load scheduling technology dynamically adjusts resource allocation by real-time monitoring of the system load, such as CPU usage, memory usage, etc., and prioritizes key data to ensure that the system response speed remains stable under high load conditions.

[0043] The data acquisition module obtains the status data of production equipment in real time through the physical layer acquisition unit. The module integrates PLC, RFID and sensor network to ensure the multi-channel and real-time nature of data acquisition. PLC can directly collect the operating parameters of the equipment from the equipment control system, RFID is responsible for the tracking and identification of materials, and the sensor network monitors environmental parameters in real time, such as temperature and humidity. The system dynamically adjusts the acquisition frequency and accuracy according to the production rhythm. When the production rhythm is accelerated, the system will increase the frequency of data acquisition to ensure timely monitoring of the equipment status. When the production rhythm is slow, the system will appropriately reduce the acquisition frequency to save resources. In addition, the module also integrates and optimizes the data through the data integration and filtering unit. The system will uniformly process the data from different acquisition channels according to machine learning algorithms and dynamic rules to form a complete production data view. For example, after integrating the equipment operating parameters, material flow information and environmental parameters, it will analyze and determine which data is redundant information and filter it effectively, thereby reducing unnecessary system resource consumption and further optimizing the efficiency of data processing. At the same time, the data acquisition module continuously provides the latest equipment status data for the low-code development module.

[0044] Finally, the data acquisition module combines complex event processing (CEP) technology to perform multi-dimensional analysis of the collected data in real time, identify potential production anomalies and issue early warnings; CEP technology can combine the equipment's operating parameters, production task progress and environmental parameters to discover potential production anomalies through multi-dimensional analysis; for example, when the equipment temperature rises abnormally, the operating parameters deviate from the normal range and the material flow speed slows down, the system will comprehensively consider these factors to determine whether there is a production anomaly; once the existence of a potential anomaly is confirmed, the system will automatically trigger the early warning mechanism to notify relevant personnel to take measures to prevent the occurrence of production accidents.

[0045] At the same time, when the data acquisition module finds changes in equipment status or production rhythm, the factory modeling module will respond in real time and adjust the factory model according to the new data; conversely, the equipment layout and production process optimized by the factory modeling module will be monitored through the data acquisition module. When the data acquisition module detects an abnormality in the production equipment, the monitoring module will respond immediately and process it through the asynchronous message middleware, and reschedule resources according to the priority of the production task; after processing these anomalies, the monitoring module will feed back the processing results to the data acquisition module to further monitor whether the adjusted production status has returned to normal.

[0046] The integration of the above modules constitutes a closed-loop system; the low-code development module provides a cross-device linkage development environment, the factory modeling module optimizes the production process through real-time data, the monitoring module ensures low-latency transmission and processing of data under high concurrency conditions, and the data acquisition module adjusts the data acquisition frequency according to the production status and provides feedback; through the synergy between the modules, the system realizes the automation and intelligence of the entire process from data acquisition, production monitoring to process optimization, ensuring the efficiency and stability of the production process.

[0047] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data collection and monitoring analysis system based on the MES platform, including a low-code development module, a factory modeling module, a monitoring module and a data collection module, wherein: The low-code development module is used to integrate the low-code development environment into the MES platform, realize instant cross-device linkage development through the drag-and-drop interface combined with the device API library, and generate control programs adapted to different devices in real time to achieve efficient communication and control between devices; The factory modeling module integrates the two production modes of process production and scattered manufacturing, realizes dynamic factory modeling based on multi-dimensional parameters of equipment status, process route and production rhythm, and optimizes the production process through real-time data analysis; The monitoring module adopts dual cache and message middleware mechanism to ensure ultra-low latency transmission and processing of data under high concurrency conditions, and realizes real-time production execution and monitoring during production execution; The data collection module dynamically adjusts the data collection frequency and accuracy according to the production status based on machine learning algorithms and complex event processing technology, and provides real-time feedback and optimization suggestions.

2. According to the data collection and monitoring analysis system based on the MES platform of claim 1, it is characterized by: The control program in the low-code development module is dynamically adjusted according to device parameters to simplify device management operations; through adaptive development environment configuration, it can automatically adjust the interface complexity and functions according to the developer's skill level and project requirements.

3. The data collection and monitoring analysis system based on the MES platform according to claim 1 is characterized in that: The low-code development module also has an automatic matching algorithm for process rules, which can automatically generate the optimal process route configuration based on the real-time status of production equipment and task requirements, and reduce manual intervention through historical data analysis to optimize the efficiency and accuracy of production configuration.

4. The data collection and monitoring analysis system based on the MES platform according to claim 1 is characterized in that: The factory modeling module realizes dynamic factory modeling by integrating multi-dimensional production parameters such as equipment status, process route and production rhythm, predicts production bottlenecks through real-time sensor data and historical production data, and automatically adjusts process flow and equipment configuration to optimize production efficiency; and uses machine learning algorithms to optimize the association between production equipment and production tasks, reduce equipment idle time, and improve overall production capacity and flexibility.

5. The data collection and monitoring analysis system based on the MES platform according to claim 1 is characterized in that: The monitoring module introduces a dual cache mechanism of Redis and Artemis, combined with asynchronous message middleware, to ensure that there is no data loss or delay during data transmission, and to control system delays within 2 seconds in high-concurrency production tasks, greatly improving the response speed and stability of the system.

6. The data collection and monitoring analysis system based on the MES platform according to claim 1 is characterized in that: The data acquisition module acquires the status data of production equipment in real time through the physical layer acquisition unit, and can dynamically adjust the acquisition frequency and granularity according to the production rhythm. The physical layer integrates PLC, RFID and sensor network; the status data includes production data of equipment status, temperature, humidity and pressure.

7. A data acquisition and monitoring analysis system based on the MES platform according to claim 1 or 7, characterized in that: The data acquisition module also includes a data integration and filtering unit, which uses dynamic rules and machine learning algorithms to filter redundant data according to the real-time needs of production tasks, reduce unnecessary data processing load, and optimize the real-time and accuracy of data acquisition and monitoring; and combines complex event processing (CEP) technology to perform multi-dimensional analysis of data, identify potential production anomalies and issue early warnings.