MES intelligent manufacturing system based on Internet of Things optimization algorithm

Abstract

The invention discloses an MES intelligent manufacturing system based on an Internet of Things optimization algorithm, and the system comprises an ensemble algorithm which comprises the generation of an independent algorithm set of each unit in an MES intelligent manufacturing module. The iteration module comprises a convolutional neural network for carrying out loop learning on a set algorithm; and the network connection platform is used for the iteration module to output the output result of the MES system, and relates to the technical field of MES intelligent manufacturing. According to the invention, through calculating a matrix framework in which independent algorithms are fused into an ensemble algorithm, simulating the ensemble algorithm according to an iterative RNN algorithm and outputting an iterative simulation result, and arranging and optimizing a production scheduling process according to the iterative simulation result, order tasks can be automatically arranged and interspersed, and defects in orders are automatically collected and processed. Therefore, the quality and efficiency of the order can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of MES intelligent manufacturing, and in particular to an MES intelligent manufacturing system based on an Internet of Things optimization algorithm. Background Art

[0002] MES Manufacturing Execution System is a software system used to manage and control the production process. It is combined with the Enterprise Resource Planning (ERP) system and the Planning and Scheduling System (APS) to provide enterprises with comprehensive production management solutions. The MES system is mainly used to monitor and manage key links in the production process, including production scheduling, raw material management, production guidance, quality control, equipment management, etc., so as to help enterprises achieve real-time visualization, intelligence and automation of the production process, improve production efficiency, quality and reliability, and reduce costs and risks.

[0003] The Internet of Things (IoT) optimization algorithm faces some challenges and problems in the intelligentization of the Manufacturing Execution System (MES), mainly including the following aspects:

[0004] Data security and privacy protection: The large amount of data generated by IoT devices needs to be collected, stored, and analyzed in the MES system, but data security and privacy protection is a key issue. Algorithm design must consider how to protect data security during data transmission, storage, and processing to prevent data leakage and unauthorized access.

[0005] Data integration and standardization: IoT devices usually come from different manufacturing equipment and suppliers, so the data format and protocol may be inconsistent. The algorithm needs to process multi-source heterogeneous data, integrate and standardize the data to ensure that the MES system can correctly interpret and use the data.

[0006] Real-time and responsiveness: IoT optimization algorithms need to process and respond to data from various sensors and devices in real time. This requires the algorithm design to have efficient real-time data processing capabilities and be able to quickly identify and respond to changes and anomalies in the manufacturing process.

[0007] Algorithm complexity and resource consumption: IoT optimization algorithms may involve complex data analysis and optimization models, which need to be implemented on resource-limited embedded devices. Therefore, algorithm complexity and resource consumption become an important factor restricting their application.

[0008] System integration and adaptability: IoT devices and MES systems are usually provided by different suppliers, and their integration and adaptation may face technical and standard challenges. The design of the algorithm must take into account the integration and compatibility of the system to ensure that the various parts can work together effectively.

[0009] Human-computer interaction and user acceptance: IoT optimization algorithms need to interact and communicate effectively with operators and managers in practical applications. Algorithm design should not only consider technical implementation, but also user acceptance and usage experience to improve the actual application value of the system.

[0010] Therefore, there is room for improvement in aspects such as data security and privacy protection, data integration, and data algorithms during the application process. Summary of the invention

[0011] The purpose of the present invention is to provide a MES intelligent manufacturing system based on the Internet of Things optimization algorithm to solve the problems raised in the above background technology.

[0012] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, including a set algorithm, the set algorithm includes the independent algorithm set generation of each unit in the MES intelligent manufacturing module; an iteration module, the iteration module includes a convolutional neural network that performs cyclic learning on the set algorithm; and a networked platform, the networked platform is used for the iteration module to output the output results of the MES system.

[0013] A method for using an MES intelligent manufacturing system based on an Internet of Things optimization algorithm, comprising:

[0014] Step S1: Calculate the matrix framework of the independent algorithms fused into the collective algorithm;

[0015] Step S2: simulating the collective algorithm according to the iterative RNN algorithm and outputting the iterative simulation result;

[0016] Step S3: Arrange and optimize the production scheduling process according to the iterative simulation results

[0017] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the MES intelligent manufacturing module includes a real-time data acquisition and transmission unit, an equipment status monitoring and predictive maintenance unit, a production scheduling and optimization unit, and a quality control and defect analysis unit, and the independent algorithm is a matrix framework composed of algorithms listed separately for each unit.

[0018] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm also includes algorithm constraints, and the algorithm constraints include filtering units, and the algorithm constraints conditionally constrain independent algorithms through the filtering units.

[0019] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the iterative module includes a comprehensive RNN algorithm, the comprehensive RNN algorithm uses a real-time data acquisition and transmission unit, an equipment status monitoring and predictive maintenance unit, a production scheduling and optimization unit, and a quality control and defect analysis unit as a pooling library, uses a filtering unit as a convolutional layer loop, and outputs a single simulation result, and the single simulation result outputs an iterative simulation result by reducing the product variance.

[0020] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm also includes a terminal, which includes a mobile terminal or a fixed terminal, and the terminal is electrically connected to the networked platform.

[0021] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the real-time data acquisition and transmission unit includes a data acquisition component and a data transmission optimization component, the data acquisition component includes sensor data acquisition, data cleaning and preprocessing algorithms and provides equipment and production lines with accurate real-time data, the data transmission optimization component selects and optimizes data transmission paths and strategies and provides data transmission and Internet of Things interconnection.

[0022] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the equipment status monitoring and predictive maintenance unit includes an equipment health monitoring component and a predictive maintenance component, the equipment health monitoring component is used for equipment status monitoring, and the predictive maintenance component is used for equipment pre-maintenance.

[0023] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the production scheduling and optimization unit includes an intelligent scheduling component and a production optimization component, the intelligent scheduling component is used for regular scheduling of production tasks, and the production optimization component is used for emergency scheduling of sudden production tasks.

[0024] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the quality control and defect analysis unit includes an intelligent quality control component and a defect analysis and diagnosis component, the intelligent quality control component is used for real-time monitoring of product quality and defect processing, and the defect analysis and diagnosis component is used for product line quality monitoring and defect processing.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The present application calculates a matrix framework that fuses independent algorithms into a collective algorithm, simulates the collective algorithm according to an iterative RNN algorithm and outputs the iterative simulation results, and arranges and optimizes the production scheduling process according to the iterative simulation results. The process can automatically arrange interspersed order tasks and automatically collect and process defects in the order, thereby achieving the completion of orders with quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of a process method in an MES intelligent manufacturing system based on an Internet of Things optimization algorithm of the present invention. DETAILED DESCRIPTION

[0028] 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.

[0029] In the description of the present invention, it should be noted that, for those skilled in the art, the specific meanings of the above terms in the present invention can be understood in specific situations. The following describes an embodiment of the present invention based on its overall structure.

[0030] See also Figure 1 In an embodiment of the present invention, an MES intelligent manufacturing system based on an Internet of Things optimization algorithm includes a collection algorithm, wherein the collection algorithm includes independent algorithm collection generation of each unit in the MES intelligent manufacturing module. Specifically, the collection algorithm includes a collection algorithm solution in multiple industry applications such as the electronics industry, the mechanical equipment industry, and the transportation industry. Before application, the collection algorithm solution can also crawl and search keyword information through software or algorithms such as python, and then couple the keyword information with the algorithm solution to match the scenario to which the algorithm solution is applied;

[0031] Iteration module, the iteration module includes a convolutional neural network for cyclic learning of the set algorithm. Specifically, after the set algorithm is coupled to the adaptation field, the algorithm will perform 3rd party application induction on the adaptation field, and the 3rd party application induction is actually performed by setting the keywords in the induction. The keywords are internally self-planned according to the MES module, including economic module, production module, logistics module, R&D module, marketing module and service module. These modules are supervised by the backpropagation algorithm, including

[0032] Economic module: Iterative calculations are performed based on the costs and benefits in product production. Specifically, the projects are further refined based on the inherent costs and loss costs in the costs (the expenditure fluctuations of the same cost are used as the pooling layer, and the cost output results are used as the convolution layer). The output is the convolution result that can optimize the cost path to achieve better cost control; the same applies to revenue control.

[0033] Production module: Iterative calculation is performed based on the use and loss of products in production. Specifically, it is further refined based on the inherent product expenditures in production and the loss items existing in production (comparing the cost control and loss control of each process under the same process conditions as the pooling layer analysis, and calculating with the cost output as the convolution layer)

[0034] Logistics module: According to the above method, the transportation shipment volume, transportation cost and loss are used as the pooling layer, and the transportation receipt volume is used as the convolution layer for calculation.

[0035] R&D module: According to the above method, R&D cost is used as the pooling layer and R&D results are used as the convolution layer for calculation.

[0036] Marketing module: According to the above method, the marketing cost is calculated as the pooling layer and the marketing revenue is calculated as the convolution layer.

[0037] Service module: According to the above method, the service cost is used as the pooling layer and the service evaluation result is calculated as the convolution layer.

[0038] And a networked platform, wherein the networked platform is used by the iteration module to output the output results of the MES system.

[0039] A method for using an MES intelligent manufacturing system based on an Internet of Things optimization algorithm, comprising:

[0040] Step S1: Calculate the matrix framework of the independent algorithms fused into the collective algorithm;

[0041] Step S2: simulating the collective algorithm according to the iterative RNN algorithm and outputting the iterative simulation result;

[0042] Step S3: Arrange and optimize the production scheduling process according to the iterative simulation results

[0043] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the MES intelligent manufacturing module includes a real-time data acquisition and transmission unit, an equipment status monitoring and predictive maintenance unit, a production scheduling and optimization unit, and a quality control and defect analysis unit, and the independent algorithm is a matrix framework composed of algorithms listed separately for each unit.

[0044] In the embodiments of the present application, the intelligent manufacturing system (MES), with the support of the Internet of Things (IoT) technology, can use various algorithms to realize data collection, analysis and optimization to improve production efficiency and quality.

[0045] Real-time data collection and transmission:

[0046] Data collection algorithms: including sensor data collection, data cleaning and preprocessing algorithms to ensure accurate real-time data is obtained from equipment and production lines.

[0047] Data transmission optimization algorithm: Based on priority and network conditions, the best data transmission path and strategy are selected to ensure that data is transmitted to the cloud or data center in a timely and efficient manner.

[0048] Equipment condition monitoring and predictive maintenance:

[0049] Equipment health monitoring algorithm: Use machine learning and statistical analysis to monitor the operating status, workload, and health of equipment and identify potential failures and anomalies.

[0050] Predictive maintenance algorithms: By analyzing trends and patterns in equipment data, predict when equipment may fail and perform maintenance in advance, reducing downtime and repair costs.

[0051] Production Scheduling and Optimization:

[0052] Intelligent scheduling algorithm: Based on order demand, equipment capacity and human resources, optimize the scheduling and allocation of production tasks to maximize production efficiency and resource utilization.

[0053] Real-time production optimization algorithm: Dynamically adjust production plans and resource allocation based on real-time data and demand changes to respond to emergencies and changes in market demand.

[0054] Quality Control and Defect Analysis:

[0055] Intelligent quality control algorithms: Combine sensor data and visual inspection technology to monitor product quality in real time and perform defect detection and classification.

[0056] Defect Analysis and Root Cause Diagnosis Algorithms: Analyze abnormal data and quality issues in the production process, identify root causes and propose improvement measures to reduce product defect rates.

[0057] Energy consumption optimization:

[0058] Energy monitoring and prediction algorithms: Analyze energy consumption data of equipment and production lines, identify peak hours and abnormal patterns of energy consumption, and propose energy-saving suggestions and optimization plans.

[0059] Environmental Monitoring and Compliance:

[0060] Environmental data analysis algorithm: monitors the temperature, humidity, air quality and other data of the factory environment to ensure compliance with environmental regulations and safety standards.

[0061] Real-time warning and response algorithm: Based on environmental monitoring data, real-time alarms are issued and appropriate measures are taken to prevent environmental accidents and damages.

[0062] These algorithms do not just exist independently, but are usually integrated and collaborated to form a complete intelligent manufacturing system, which uses IoT technology to achieve intelligent connection and management of equipment, production lines, and enterprise resources. This integration capability enables MES to operate and manage the manufacturing process more intelligently and efficiently.

[0063] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm also includes algorithm constraints, and the algorithm constraints include filtering units, and the algorithm constraints conditionally constrain independent algorithms through the filtering units.

[0064] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the iterative module includes a comprehensive RNN algorithm, the comprehensive RNN algorithm uses a real-time data acquisition and transmission unit, an equipment status monitoring and predictive maintenance unit, a production scheduling and optimization unit, and a quality control and defect analysis unit as a pooling library, uses a filtering unit as a convolutional layer loop, and outputs a single simulation result, and the single simulation result outputs an iterative simulation result by reducing the product variance.

[0065] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm also includes a terminal, which includes a mobile terminal or a fixed terminal, and the terminal is electrically connected to the networked platform.

[0066] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the real-time data acquisition and transmission unit includes a data acquisition component and a data transmission optimization component, the data acquisition component includes sensor data acquisition, data cleaning and preprocessing algorithms and provides equipment and production lines with accurate real-time data, the data transmission optimization component selects and optimizes data transmission paths and strategies and provides data transmission and Internet of Things interconnection.

[0067] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the equipment status monitoring and predictive maintenance unit includes an equipment health monitoring component and a predictive maintenance component, the equipment health monitoring component is used for equipment status monitoring, and the predictive maintenance component is used for equipment pre-maintenance.

[0068] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the production scheduling and optimization unit includes an intelligent scheduling component and a production optimization component, the intelligent scheduling component is used for regular scheduling of production tasks, and the production optimization component is used for emergency scheduling of sudden production tasks.

[0069] As a further solution of the present invention: an MES intelligent manufacturing system based on the Internet of Things optimization algorithm, the quality control and defect analysis unit includes an intelligent quality control component and a defect analysis and diagnosis component, the intelligent quality control component is used for real-time monitoring of product quality and defect processing, and the defect analysis and diagnosis component is used for product line quality monitoring and defect processing.

[0070] The working principle of the present invention is: by calculating the matrix framework of the ensemble algorithm by integrating independent algorithms, simulating the ensemble algorithm according to the iterative RNN algorithm and outputting the iterative simulation results, and arranging and optimizing the production scheduling process according to the iterative simulation results, the process can automatically arrange interspersed order tasks, and automatically collect and process the defects in the order, so as to achieve the completion of the order with quality and efficiency.

[0071] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A MES intelligent manufacturing system based on the Internet of Things optimization algorithm, characterized in that: Including a collection algorithm, the collection algorithm includes independent algorithm collection generation of each unit in the MES intelligent manufacturing module; An iteration module, the iteration module comprising a convolutional neural network for cyclically learning an ensemble algorithm; as well as The networked platform is used by the iteration module to output the output results of the MES system.

2. According to claim 1, a MES intelligent manufacturing system based on the Internet of Things optimization algorithm is characterized in that: The MES intelligent manufacturing module includes a real-time data acquisition and transmission unit, an equipment status monitoring and predictive maintenance unit, a production scheduling and optimization unit, and a quality control and defect analysis unit. The independent algorithm is a matrix framework composed of algorithms listed in each unit.

3. According to claim 2, a MES intelligent manufacturing system based on the Internet of Things optimization algorithm is characterized in that: It also includes algorithm constraints, which include a filtering unit, and the algorithm constraints impose conditional constraints on the independent algorithm through the filtering unit.

4. According to claim 3, a MES intelligent manufacturing system based on the Internet of Things optimization algorithm is characterized in that: The iterative module includes a comprehensive RNN algorithm, which uses a real-time data acquisition and transmission unit, an equipment status monitoring and predictive maintenance unit, a production scheduling and optimization unit, and a quality control and defect analysis unit as a pooling library, a filtering unit as a convolutional layer loop, and outputs a single simulation result. The single simulation result outputs an iterative simulation result by reducing the variance.

5. According to claim 4, a MES intelligent manufacturing system based on the Internet of Things optimization algorithm is characterized in that: It also includes a terminal, which includes a mobile terminal or a fixed terminal, and the terminal is electrically connected to the network platform.

6. According to claim 5, a MES intelligent manufacturing system based on the Internet of Things optimization algorithm is characterized in that: The real-time data acquisition and transmission unit includes a data acquisition component and a data transmission optimization component. The data acquisition component includes sensor data acquisition, data cleaning and preprocessing algorithms and provides equipment and production lines with accurate real-time data. The data transmission optimization component selects and optimizes data transmission paths and strategies and provides data transmission and Internet of Things interconnection.

7. The MES intelligent manufacturing system based on the Internet of Things optimization algorithm according to claim 6 is characterized in that: The equipment status monitoring and predictive maintenance unit includes an equipment health monitoring component and a predictive maintenance component. The equipment health monitoring component is used for equipment status monitoring, and the predictive maintenance component is used for equipment pre-maintenance.

8. The MES intelligent manufacturing system based on the Internet of Things optimization algorithm according to claim 7 is characterized in that: The production scheduling and optimization unit includes an intelligent scheduling component and a production optimization component. The intelligent scheduling component is used for regular scheduling of production tasks, and the production optimization component is used for emergency scheduling of sudden production tasks.

9. The MES intelligent manufacturing system based on the Internet of Things optimization algorithm according to claim 8 is characterized in that: The quality control and defect analysis unit includes an intelligent quality control component and a defect analysis and diagnosis component. The intelligent quality control component is used for real-time monitoring of product quality and defect processing, and the defect analysis and diagnosis component is used for product line quality monitoring and defect processing.

10. The method for using the MES intelligent manufacturing system based on the Internet of Things optimization algorithm according to claim 9 is characterized in that: include Step S1: Calculate the matrix framework of the independent algorithms fused into the collective algorithm; Step S2: simulating the collective algorithm according to the iterative RNN algorithm and outputting the iterative simulation result; Step S3: Arrange and optimize the production scheduling process according to the iterative simulation results.

Images