Electric power product manufacturing management method and system based on intelligent equipment

Abstract

The invention discloses an electric power product manufacturing management method and system based on intelligent equipment, and relates to the technical field of manufacturing management systems. Comprising a sensor, an actuator and controller hardware equipment, and is used for acquiring key parameters in a production process in real time and performing corresponding operation according to an instruction of a decision support layer; and the data acquisition and processing layer transmits the data of the intelligent equipment layer to a cloud or a local server in real time through the Internet of Things technology. The auxiliary material storage environment is strictly managed and controlled, storage environment abnormity is early warned and handled in time, the probability of auxiliary material deterioration and failure caused by environmental factors is reduced, operation equipment is connected in a butt joint mode, all operation process equipment is managed and controlled, starting and ending of the equipment are controlled through the system, the equipment automatically uploads related data, manual operation missing is prevented, and the work efficiency is improved. The system records error data and detailed equipment maintenance records, monitors the equipment, prompts an equipment management department to maintain the equipment in time, and reduces the abnormal rate of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of manufacturing management systems, and in particular to a method and system for managing the manufacturing of electric power products based on intelligent devices. Background Art

[0002] With the rapid development of the electronic product manufacturing industry, market competition is becoming increasingly fierce, and the speed of product replacement is accelerating. In this environment, manufacturers are facing huge challenges. How to effectively manage auxiliary materials in the production process has become one of the key factors to improve efficiency, reduce costs, and ensure product quality. Traditional auxiliary material management methods mostly rely on manual operation and record keeping, which is not only inefficient but also prone to errors. In addition, due to the lack of real-time monitoring and precise control, traditional methods are difficult to cope with complex and changing production needs, and cannot effectively prevent and solve quality problems caused by auxiliary materials.

[0003] The production material management systems currently on the market (such as solder paste, glue, tin wire, tin bar, flux, and cleaning agent) basically generate and paste barcodes, collect information by collecting barcodes, and control every step of the use of auxiliary materials. The auxiliary material storage environment is not controlled, and the auxiliary material storage is not connected to the equipment used between delivery and online use. The storage of auxiliary materials is controlled by manual + system, and the key steps from delivery to online use are operated. Once human factors occur, the system will record wrong data, resulting in errors in the traceability of auxiliary material storage and use records, which will seriously lead to batch product quality problems. The auxiliary material storage environment is not monitored in real time, which can easily lead to the deterioration and failure of auxiliary materials due to environmental factors. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for power product manufacturing management based on intelligent devices.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An electric power product manufacturing management system based on intelligent devices, comprising:

[0007] Intelligent device layer: including sensors, actuators, and controller hardware devices, which collect key parameters in the production process in real time and perform corresponding operations according to the instructions of the decision support layer;

[0008] Data collection and processing layer: transmits data from the smart device layer to the cloud or local server in real time through the Internet of Things technology, and performs data cleaning, fusion and storage; receives query requests from the decision support layer, retrieves relevant data from the database and returns it to the decision support layer;

[0009] Decision support layer: Use big data analysis and machine learning algorithms to analyze and mine the data provided by the data collection and processing layer to identify abnormal situations in the production process, optimize production process parameters, and predict product quality;

[0010] Application layer: formulates production plans, scheduling strategies and quality control measures based on the analysis results and suggestions provided by the decision support layer; sends control instructions to the intelligent device layer;

[0011] Prediction and optimization layer: Use time series analysis and machine learning methods to establish a prediction model for key parameters in the production process, provide early warning, and ensure the continuity and stability of production;

[0012] Autonomous learning and adaptation layer: Update and optimize the prediction model and optimization algorithm through real-time collected production data, and automatically adjust the control strategy and parameters according to the real-time monitored production status and environmental changes;

[0013] Collaboration and interaction layer: Through the Internet of Things technology and standardized communication protocols, information sharing and collaborative work between different smart devices can be achieved.

[0014] Preferably, the intelligent device layer coordinates and controls sensors and actuators based on model predictive control, uses models to predict the future state of the system, and optimizes control inputs based on this. The specific formula is:

[0015]

[0016] in:

[0017] H is the forecast horizon;

[0018] is the predicted future output at time t based on the current and assumed future input sequence u(t);

[0019] r(t+i) is the desired reference trajectory;

[0020] Q and R are weight matrices, which are used to weigh tracking error and control effort, respectively;

[0021] is the change in the control input.

[0022] Preferably: the smart device layer includes:

[0023] Sensor module: used to monitor physical quantities and environmental parameters in the production process in real time;

[0024] Actuator module: used to operate production equipment according to control instructions;

[0025] Controller module: responsible for receiving instructions from other layers and coordinating and controlling sensors and actuators according to preset programs or algorithms.

[0026] Preferably, when the controller module performs temperature control, the control input is calculated based on the following formula:

[0027]

[0028] in:

[0029] is the error signal, specifically the difference between the set point and the current measurement;

[0030] is the proportional gain, which determines the intensity of the response to the current error;

[0031] is the integral gain, used to eliminate steady-state errors;

[0032] is the differential gain, which is used to predict error changes and make adjustments in advance;

[0033] is the control input.

[0034] Preferably: the data collection and processing layer includes:

[0035] Data receiving module: responsible for receiving real-time data from the intelligent device layer and performing preliminary processing;

[0036] Data storage module: stores the processed data in a database or cloud server for analysis and retrieval;

[0037] Data processing module: further process and analyze the stored data, including statistical analysis, trend prediction, and anomaly detection.

[0038] Preferably: the decision support layer includes:

[0039] Model building module: Build mathematical models or machine learning models for prediction, optimization, and classification tasks based on historical data and real-time data;

[0040] Strategy formulation module: formulate production plans, scheduling strategies, and quality control measures based on the model's prediction results and current production status.

[0041] Preferably: the application layer includes:

[0042] Production planning module: arranges the production process, time and resources of products according to the production plan formulated by the decision support layer;

[0043] Equipment scheduling module: dynamically schedule the order and time of equipment use according to production plan and equipment status;

[0044] Quality control module: Perform quality inspection and monitoring on products in the production process according to the quality control measures of the decision support layer.

[0045] Preferably: the prediction and optimization layer includes:

[0046] Demand forecasting module: predict product demand in the future based on historical sales data, market trends, and seasonal factors;

[0047] Energy consumption optimization module: by analyzing the energy consumption data in the production process, find out the links of energy waste and propose improvement measures; including optimizing equipment configuration and adjusting process parameters;

[0048] Equipment failure prediction module: By analyzing the equipment operation data, it predicts the type and time of possible equipment failure.

[0049] Preferably: the autonomous learning and adaptation layer includes:

[0050] Online learning module: continuously update and optimize existing prediction models and optimization algorithms using newly collected data;

[0051] Adaptive adjustment module: automatically adjusts control strategies and parameters based on real-time monitored production status and environmental changes.

[0052] Preferably, the auxiliary material management method of the power product manufacturing management system comprises the following steps:

[0053] S1: Maintain and analyze basic data of auxiliary materials;

[0054] S2: Analyze whether it is basic data, if yes, transfer to S3, if not, transfer to S1;

[0055] S3: Print barcodes for auxiliary materials and paste barcodes on them;

[0056] S4: storage;

[0057] S5: dispatch out of warehouse on demand;

[0058] S6: Automatically collect auxiliary material barcodes through the equipment, verify the operation route, and record the relevant data of each operation step. After verification, proceed to S7, otherwise proceed to S5;

[0059] S7: Go online to complete the scan;

[0060] S8: Determine whether it is used up, if yes, recycle the remaining amount and go to step S4, otherwise go to step S9;

[0061] S9: Empty bottle recycling.

[0062] The beneficial effects of the present invention are:

[0063] 1. The present invention strictly controls the storage environment of auxiliary materials, and promptly warns and handles abnormal storage environment, thereby reducing the probability of deterioration and failure of auxiliary materials due to environmental factors. It connects to operating equipment, manages and controls equipment in various operating processes, and controls the start and end of equipment through the system. The equipment automatically uploads relevant data to prevent human omissions. The system records erroneous data and detailed equipment maintenance records, monitors equipment, and promptly reminds the equipment management department to perform equipment maintenance, thereby reducing the abnormality rate of equipment, improving the efficiency of auxiliary material issuance, and reducing the cost of auxiliary material management.

[0064] 2. The present invention has a good traceability mechanism. When product quality problems occur, the source of the problem and the scope of impact can be quickly located, and timely measures can be taken to reduce losses.

[0065] 3. The auxiliary material usage report of the present invention can intuitively display the auxiliary material usage, combine the order quantity, analyze the auxiliary material usage data, thereby optimizing the production operation steps, optimizing the auxiliary material usage, and reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a flow chart of an auxiliary material management method in a power product manufacturing management method based on intelligent devices proposed by the present invention;

[0067] Figure 2 This is a flow chart of auxiliary material usage tracing in a power product manufacturing management method based on smart devices proposed by the present invention. DETAILED DESCRIPTION

[0068] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0069] Embodiment 1:

[0070] An electric power product manufacturing management system based on intelligent devices, comprising:

[0071] Intelligent device layer: mainly includes various hardware devices such as sensors, actuators, controllers, etc., which are used to collect key parameters in the production process (such as temperature, pressure, current, voltage, etc.) in real time, and perform corresponding operations according to the instructions of the decision support layer.

[0072] Data collection and processing layer: The data from the smart device layer is transmitted to the cloud or local server in real time through the Internet of Things technology, and the data is cleaned, integrated and stored. At the same time, it is also responsible for receiving query requests from the decision support layer, retrieving relevant data from the database and returning it to the decision support layer.

[0073] Decision support layer: Use big data analysis and machine learning algorithms to analyze and mine the data provided by the data collection and processing layer to identify abnormal situations in the production process, optimize production process parameters, predict product quality, etc.

[0074] Application layer: According to the analysis results and suggestions provided by the decision support layer, the corresponding production plan, scheduling strategy and quality control measures are formulated. At the same time, it is also responsible for sending control instructions to the intelligent device layer to realize the automation and intelligence of the production process.

[0075] Prediction and optimization layer: Use time series analysis, machine learning and other methods to establish a prediction model for key parameters in the production process (such as demand, energy consumption, equipment failure, etc.), provide early warning of possible problems, and ensure the continuity and stability of production.

[0076] Autonomous learning and adaptation layer: Through real-time collection of production data, the prediction model and optimization algorithm are continuously updated and optimized to enable them to adapt to changes and abnormal situations in the production process; according to the real-time monitored production status and environmental changes, the control strategy and parameters are automatically adjusted to maintain the stability and efficiency of the production process.

[0077] Collaboration and interaction layer: Through the Internet of Things technology and standardized communication protocols, information sharing and collaborative work between different smart devices can be realized. For example, when the production task of one device is completed, the next device can be automatically notified to prepare to receive materials.

[0078] The smart device layer coordinates the control of sensors and actuators based on model predictive control, uses the model to predict the future state of the system, and optimizes the control input based on this. The specific formula is:

[0079]

[0080] in:

[0081] H is the forecast horizon;

[0082] is the predicted future output at time t based on the current and assumed future input sequence u(t);

[0083] r(t+i) is the desired reference trajectory;

[0084] Q and R are weight matrices, which are used to weigh tracking error and control effort, respectively;

[0085] is the change in the control input.

[0086] Wherein, the smart device layer includes:

[0087] Sensor module: including various types of sensors such as temperature, pressure, current, voltage, etc., which are used to monitor various physical quantities and environmental parameters in the production process in real time.

[0088] Actuator module: includes various types of actuators such as motors, valves, switches, etc., which are used to operate production equipment according to control instructions.

[0089] Controller module: As the core of the intelligent device layer, the controller is responsible for receiving instructions from other layers and coordinating the control of sensors and actuators according to preset programs or algorithms.

[0090] Wherein, when the controller module performs temperature control, the control input is calculated based on the following formula:

[0091]

[0092] in:

[0093] is the error signal, specifically the difference between the set point and the current measurement;

[0094] is the proportional gain, which determines the intensity of the response to the current error;

[0095] is the integral gain, used to eliminate steady-state errors;

[0096] is the differential gain, which is used to predict error changes and make adjustments in advance;

[0097] is the control input, such as power to a heating element.

[0098] The data collection and processing layer includes:

[0099] Data receiving module: responsible for receiving real-time data from the intelligent device layer and performing preliminary processing, such as denoising and formatting.

[0100] Data storage module: stores the processed data in a database or cloud server for subsequent analysis and retrieval.

[0101] Data processing module: further process and analyze the stored data, such as statistical analysis, trend prediction, anomaly detection, etc.

[0102] The decision support layer includes:

[0103] Model building module: Build mathematical models or machine learning models for prediction, optimization, classification and other tasks based on historical data and real-time data.

[0104] Strategy formulation module: formulate corresponding production plans, scheduling strategies, and quality control measures based on the model's prediction results and current production status.

[0105] The application layer includes:

[0106] Production planning module: According to the production plan formulated by the decision support layer, the production process, time, resources, etc. of each product are arranged in detail.

[0107] Equipment Scheduling Module: Dynamically schedule the order and time of equipment use based on production plans and equipment status to maximize production efficiency and equipment utilization.

[0108] Quality control module: According to the quality control measures of the decision support layer, the quality of products in the production process is tested and monitored, including raw material inspection, process monitoring, finished product inspection and other links to ensure that product quality meets standards and customer requirements.

[0109] The prediction and optimization layer includes:

[0110] Demand forecasting module: predicts product demand in the future based on historical sales data, market trends, seasonal factors, etc.

[0111] Energy consumption optimization module: By analyzing the energy consumption data in the production process, find out the links of energy waste and propose improvement measures, including optimizing equipment configuration and adjusting process parameters.

[0112] Equipment failure prediction module: By analyzing the equipment operation data, it predicts the type and time of possible equipment failure.

[0113] The autonomous learning and adaptation layer includes:

[0114] Online learning module: Continuously update and optimize existing prediction models and optimization algorithms using newly collected data.

[0115] Adaptive adjustment module: automatically adjusts control strategies and parameters based on real-time monitored production status and environmental changes.

[0116] Embodiment 2:

[0117] A power product manufacturing management system based on intelligent devices, applied to auxiliary material management, specifically including:

[0118] Intelligent device layer: Based on the auxiliary material storage environment / equipment management module, real-time monitoring is performed to determine whether the storage environment is abnormal and whether the equipment is operating normally.

[0119] Data collection and processing layer: Based on the auxiliary material usage management module, manage the basic information of auxiliary materials: auxiliary material categories (types of auxiliary materials, auxiliary material operation routes), auxiliary material information (manufacturer, model, validity period, unique serial number coding rules, standard weight, empty bottle weight, opening control time), auxiliary material barcode management, auxiliary material barcode splitting, online scanning operations, inbound and outbound scanning operations, and auxiliary material scrapping operations.

[0120] Collaboration and interaction layer: Based on the auxiliary material report module, its main function is to trace and query the usage records through the auxiliary material barcode or product SN, detailed records of the operation of all steps of the auxiliary material from warehousing to use, and auxiliary material usage analysis reports.

[0121] The auxiliary material management system docking equipment consists of two parts:

[0122] The first part is to connect environmental testing equipment: thermometer, hygrometer, solder paste cabinet, collect equipment data in real time, compare and set environmental parameters, and issue early warnings in time;

[0123] The second part is to connect the auxiliary material operation equipment: rewarming cabinet, mixer, through the connection control equipment, the auxiliary material barcode is automatically collected by the equipment, the operation route is verified, and the relevant data of each operation step is recorded, including the operation step name, operator, operation start time, operation end time and operation result.

[0124] The basic data maintenance of auxiliary material management includes two parts:

[0125] The first part is the basic information management of auxiliary materials: auxiliary material categories, auxiliary material usage rules, auxiliary material barcode rules, auxiliary material barcode printing templates, auxiliary material barcode management, auxiliary material environmental parameters. By maintaining auxiliary material categories, auxiliary material category associated usage rules, barcode rules, templates, the system generates auxiliary material barcode serial numbers, prints barcodes according to barcode templates, and pastes auxiliary material barcodes;

[0126] The second part is the auxiliary material operation record: auxiliary material in and out of the warehouse, auxiliary material online operation, auxiliary material scrapping operation, by scanning the bar code attached to the auxiliary material into the warehouse, recording the basic information of the auxiliary material, production date, model, operation route, auxiliary material out of the warehouse by scanning the auxiliary material bar code, verifying the auxiliary material validity period, status, operation route node is correct, and recording data, such as Figure 1 .

[0127] Auxiliary material usage tracing and reporting consists of three parts:

[0128] The first part is the auxiliary material usage record (operation) record query, which mainly queries the operation data of each operation node from the storage to the launch of the auxiliary material, as well as the product range data used after the launch;

[0129] The second part is the auxiliary materials usage report: it mainly shows the quantity and trend of various auxiliary materials used in each product in the form of charts;

[0130] The third part is the equipment report: it mainly displays the maintenance records of auxiliary material storage equipment and environmental testing equipment, as well as the records of abnormal problems (abnormal problems, abnormal causes, abnormal start time, handlers, abnormal processing start time, abnormal processing end time, abnormal processing results). Figure 2 .

[0131] The auxiliary material management system maintains auxiliary material category data, auxiliary material information (manufacturer, validity period, model, coding rules, printing template), and operation routes. When auxiliary materials are put into the warehouse, the system prints a barcode, pastes the barcode on the smallest package of the auxiliary materials, scans the barcode to enter the warehouse, scans the barcode to leave the warehouse according to the production plan, and distributes auxiliary materials according to the auxiliary material operation route (connecting to the operating equipment, managing each step of the operation, and preventing human omissions). The auxiliary material management system monitors the storage environment in real time, records temperature and humidity data, and issues timely warnings of abnormalities.

[0132] The auxiliary material management method of the power product manufacturing management system includes the following steps:

[0133] S1: Maintain and analyze basic data of auxiliary materials;

[0134] S2: Analyze whether it is basic data, if yes, transfer to S3, if not, transfer to S1;

[0135] S3: Print barcodes for auxiliary materials and paste barcodes on them;

[0136] S4: storage;

[0137] S5: dispatch out of warehouse on demand;

[0138] S6: Automatically collect auxiliary material barcodes through the equipment, verify the operation route, and record the relevant data of each operation step. After verification, proceed to S7, otherwise proceed to S5;

[0139] S7: Go online to complete the scan;

[0140] S8: Determine whether it is used up, if yes, recycle the remaining amount and go to step S4, otherwise go to step S9;

[0141] S9: Empty bottle recycling.

[0142] The above description 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 power product manufacturing management system based on intelligent devices, characterized in that: include: Intelligent device layer: including sensors, actuators, and controller hardware devices, which collect key parameters in the production process in real time and perform corresponding operations according to the instructions of the decision support layer; Data collection and processing layer: transmits data from the smart device layer to the cloud or local server in real time through the Internet of Things technology, and performs data cleaning, fusion and storage; receives query requests from the decision support layer, retrieves relevant data from the database and returns it to the decision support layer; Decision support layer: Use big data analysis and machine learning algorithms to analyze and mine the data provided by the data collection and processing layer to identify abnormal situations in the production process, optimize production process parameters, and predict product quality; Application layer: formulates production plans, scheduling strategies and quality control measures based on the analysis results and suggestions provided by the decision support layer; sends control instructions to the intelligent device layer; Prediction and optimization layer: Use time series analysis and machine learning methods to establish a prediction model for key parameters in the production process, provide early warning, and ensure the continuity and stability of production; Autonomous learning and adaptation layer: Update and optimize the prediction model and optimization algorithm through real-time collected production data, and automatically adjust the control strategy and parameters according to the real-time monitored production status and environmental changes; Collaboration and interaction layer: Through the Internet of Things technology and standardized communication protocols, information sharing and collaborative work between different smart devices can be achieved.

2. According to claim 1, the power product manufacturing management system based on intelligent devices is characterized in that: The intelligent device layer coordinates the control of sensors and actuators based on model predictive control, uses the model to predict the future state of the system, and optimizes the control input based on this. The specific formula is: in: H is the forecast horizon; is the predicted future output at time t based on the current and assumed future input sequence u(t); r(t+i) is the desired reference trajectory; Q and R are weight matrices, which are used to weigh tracking error and control effort, respectively; is the change in the control input.

3. The power product manufacturing management system based on intelligent devices according to claim 2 is characterized in that: The smart device layer includes: Sensor module: used to monitor physical quantities and environmental parameters in the production process in real time; Actuator module: used to operate production equipment according to control instructions; Controller module: responsible for receiving instructions from other layers and coordinating and controlling sensors and actuators according to preset programs or algorithms.

4. The power product manufacturing management system based on intelligent devices according to claim 3 is characterized in that: When the controller module performs temperature control, the control input is calculated based on the following formula: in: is the error signal, specifically the difference between the set point and the current measurement; is the proportional gain, which determines the intensity of the response to the current error; is the integral gain, used to eliminate steady-state errors; is the differential gain, which is used to predict error changes and make adjustments in advance; is the control input.

5. The power product manufacturing management system based on intelligent devices according to claim 4 is characterized in that: The data collection and processing layer includes: Data receiving module: responsible for receiving real-time data from the intelligent device layer and performing preliminary processing; Data storage module: stores the processed data in a database or cloud server for analysis and retrieval; Data processing module: further process and analyze the stored data, including statistical analysis, trend prediction, and anomaly detection.

6. The power product manufacturing management system based on intelligent devices according to claim 5 is characterized in that: The decision support layer includes: Model building module: Build mathematical models or machine learning models for prediction, optimization, and classification tasks based on historical data and real-time data; Strategy formulation module: formulate production plans, scheduling strategies, and quality control measures based on the model's prediction results and current production status.

7. The power product manufacturing management system based on intelligent devices according to claim 6 is characterized in that: The application layer includes: Production planning module: arranges the production process, time and resources of products according to the production plan formulated by the decision support layer; Equipment scheduling module: dynamically schedule the order and time of equipment use according to production plan and equipment status; Quality control module: Perform quality inspection and monitoring on products in the production process according to the quality control measures of the decision support layer.

8. The power product manufacturing management system based on intelligent devices according to claim 7 is characterized in that: The prediction and optimization layer includes: Demand forecasting module: predict product demand in the future based on historical sales data, market trends, and seasonal factors; Energy consumption optimization module: by analyzing the energy consumption data in the production process, find out the links of energy waste and propose improvement measures; including optimizing equipment configuration and adjusting process parameters; Equipment failure prediction module: By analyzing the equipment operation data, it predicts the type and time of possible equipment failure.

9. The power product manufacturing management system based on intelligent devices according to claim 8, characterized in that: The autonomous learning and adaptation layer includes: Online learning module: continuously update and optimize existing prediction models and optimization algorithms using newly collected data; Adaptive adjustment module: automatically adjusts control strategies and parameters based on real-time monitored production status and environmental changes.

10. The power product manufacturing management system based on intelligent devices according to claim 9, characterized in that: The auxiliary material management method of the power product manufacturing management system comprises the following steps: S1: Maintain and analyze basic data of auxiliary materials; S2: Analyze whether it is basic data, if yes, transfer to S3, if not, transfer to S1; S3: Print barcodes for auxiliary materials and paste barcodes on them; S4: storage; S5: dispatch out of warehouse on demand; S6: Automatically collect auxiliary material barcodes through the equipment, verify the operation route, and record the relevant data of each operation step. After verification, proceed to S7, otherwise proceed to S5; S7: Go online to complete the scan; S8: Determine whether it is used up, if yes, recycle the remaining amount and go to step S4, otherwise go to step S9; S9: Empty bottle recycling.

Images