Intelligent manufacturing resource planning management system

Abstract

The application provides an intelligent manufacturing resource plan management system, comprising a data acquisition module for acquiring multi-type resource data of an intelligent manufacturing whole process.The application has reasonable design, realizes global collaborative control of multiple AGV devices through a resource scheduling module, plans a path in combination with an intelligent optimization algorithm, cooperates with a traffic control unit to sort the passing of single channels and forbidden head-on driving areas, effectively avoids AGV collision and congestion problems, and greatly reduces path redundancy.Meanwhile, resources are dynamically allocated based on logistics task priorities, the accuracy and reliability of multi-AGV data communication are guaranteed in combination with a TCP protocol, logistics task information is interacted in real time with an MES system through a WebService interface, the timeliness and accuracy of material distribution are ensured, the labor cost of enterprise internal material turnover is significantly reduced, and the overall operation efficiency of the workshop logistics link is improved.

Description

Technical Field

[0001] This invention mainly relates to the field of intelligent manufacturing, specifically to an intelligent manufacturing resource planning and management system. Background Technology

[0002] With the widespread adoption of Industrial Internet of Things (IIoT) technology, traditional manufacturing models are accelerating their transformation towards automation and intelligence. Intelligent manufacturing has become the main focus of building a manufacturing powerhouse, permeating all aspects of manufacturing activities, including design, production, management, and service. In this transformation process, resource planning and management (RPM), as the core support of intelligent manufacturing, directly impacts production efficiency, cost control, and market responsiveness, and its importance is increasingly prominent.

[0003] Currently, manufacturing enterprises face numerous pressing technical bottlenecks in the field of resource planning and management, and existing management models and systems are no longer adequate to meet the development needs of intelligent manufacturing: First, there is insufficient resource scheduling and coordination capabilities. Smart manufacturing workshops generally introduce automated equipment such as AGVs to handle material handling tasks, but there is a lack of efficient solutions for the coordination and management, path planning, and traffic control among multiple AGV devices, often resulting in problems such as collisions, congestion, and path redundancy. At the same time, there is a lack of a global optimization mechanism for the scheduling of various resources such as manpower, equipment, and materials, making it difficult to dynamically allocate resources according to task priorities. This leads to a coexistence of idle resources and task backlog, insufficient timeliness of material delivery, and high internal turnover labor costs.

[0004] Secondly, the level of intelligence in production scheduling is low. Traditional production scheduling methods rely heavily on manual experience or static planning, which cannot effectively integrate dynamic information such as order demand and real-time resource status. They are ill-equipped to handle random events such as urgent orders and priority adjustments in multi-variety, small-batch production models. Furthermore, the scheduling process does not adequately consider the balance between cost and efficiency, resulting in insufficient rationality in resource allocation. This leads to a high rate of production plan changes, complex execution tracking, and limited control over production, thus hindering the improvement of production efficiency and market competitiveness.

[0005] Third, data management and processing capabilities are weak. The multimodal data generated during the manufacturing process (such as employee behavior data, equipment operation data, and material flow data) lacks a unified mechanism for collection and fusion processing. Traditional data management systems suffer from limited resources, limited methods, and insufficient data accuracy. The standardization of data cleaning, transformation, and integration is low, and the differences in dimensions are significant, making it difficult for data to effectively support accurate resource planning decisions. Furthermore, the data lacks real-time performance, exhibiting lag and inaccuracy issues, making it difficult to achieve dynamic perception and analysis of the entire production process.

[0006] It should be noted that the above content falls within the scope of the inventor's technical knowledge. Due to the vast and complex nature of the technical content in this field, the above content of this application does not necessarily constitute prior art. Summary of the Invention

[0007] 1. The technical problem that the invention aims to solve: This invention provides an intelligent manufacturing resource planning and management system to solve the technical problems existing in the background art.

[0008] 2. Technical Solution: To achieve the above objectives, the technical solution provided by this invention is: an intelligent manufacturing resource planning and management system, comprising: The data acquisition module is used to collect multi-type resource data throughout the intelligent manufacturing process. The multi-type resource data includes human resource data, equipment resource data, material resource data, AGV operating status data, and multimodal employee behavior data. The data processing module is used to clean, standardize, and integrate the various types of resource data to obtain standardized resource data. The processing includes checking data consistency and handling invalid and missing values. The resource scheduling module is used to schedule multiple AGVs and plan routes based on the standardized resource data and the priority of logistics tasks, so as to realize automated material handling and control traffic in traffic control areas. The intelligent scheduling module is used to integrate the standardized resource data to generate a hierarchical production plan based on order business needs. The hierarchical production plan includes an annual first-level delivery plan, a monthly second-level production plan, and a process-level third-level execution plan. The scheduling scheme is optimized through a cost-efficiency comprehensive evaluation model. The monitoring and early warning module is used to monitor the AGV's operating status, production plan execution progress, equipment operating parameters, and abnormal behavior of multimodal data feedback in real time, and trigger early warning alarms. The collaborative optimization module is used to dynamically adjust production plans and AGV scheduling schemes, integrate production, inventory and sales information to achieve information sharing among all links, and achieve data interoperability through integration with MES, LIMS and MDC systems; The visualization module is used to intuitively display the AGV location, production progress, resource utilization, and plan execution status in the form of a two-dimensional map and dashboard.

[0009] Furthermore, the data acquisition module includes: The human resources data collection unit is used to collect employee attendance, working hours, and multimodal behavior data, including training video learning parameters, classroom interaction parameters, and assignment completion parameters. The equipment resource acquisition unit is used to collect data on the operating status of production equipment, AGV power consumption, and fault data. The material resource acquisition unit is used to collect data on raw material inventory, work-in-process quantity, and material delivery status. The data acquisition module achieves real-time data acquisition through intelligent monitoring equipment and WebService interface.

[0010] Furthermore, the data processing module includes: The data cleaning unit is used to remove inconsistent data, invalid values, and missing values ​​based on data quality tools. The data conversion unit is used to convert resource data in different formats into a unified standard format, eliminating differences in units. The multimodal data processing unit is used to calculate the impact coefficients of employee training video learning time, classroom interaction activity, and homework completion through mathematical models.

[0011] Furthermore, the resource scheduling module includes: The path planning unit is used to plan the optimal transport path for AGVs based on the workshop's two-dimensional map data and intelligent optimization algorithms. The AGV control unit is used to acquire real-time status parameters of AGVs, control AGVs with insufficient power to automatically recharge, and dispatch them to standby points after charging is completed. Traffic control units are used to sequence traffic in single-lane or no-head-to-head traffic areas, guiding AGVs to pass in order. The resource scheduling module implements multi-AGV data communication through the TCP protocol and interacts with the MES system for logistics task information through the WebService interface.

[0012] Furthermore, the intelligent scheduling module includes: The demand acquisition unit is used to retrieve the production quantity, production time, and production specifications of orders from the customer management database. The planning generation unit is used to determine whether the current available manpower and equipment can meet the order requirements. If they can, a production schedule is created based on the minimum completion time. Otherwise, the process sequence group is generated by combining the existing production tasks and the optimal solution is selected.

[0013] Furthermore, the monitoring and early warning module includes: The real-time monitoring unit is used to collect production site data through intelligent monitoring equipment, including raw material arrival time, production line operating status, AGV collision and fault information; The early warning management unit is used to automatically trigger alarms when abnormal behavior is detected and transmit early warning information to management personnel.

[0014] Furthermore, the collaborative optimization module includes: The scheduling optimization unit is used to compare production site data with planned targets in real time, analyze the reasons for the differences, and dynamically adjust the production plan and AGV scheduling scheme. It also introduces a stocking mechanism to deal with order changes and raw material supply issues. The collaborative sharing unit is used to integrate production, inventory and sales information to enable information sharing and collaborative operations among various contracting units. The planning adjustment unit is used to deal with urgent order insertion scenarios, and to urgently modify the secondary production plan and reissue it to each execution unit.

[0015] Furthermore, the MES system adopts a microservice architecture, including a database layer, a microservice platform layer, a gateway layer, and an application layer. The application layer implements basic data management, plan management, resource management, and other functions in the form of an App.

[0016] Furthermore, the visualization module includes a workshop two-dimensional map display unit and a multi-dimensional dashboard unit. The two-dimensional map displays the real-time location of the AGV and the status of logistics tasks, while the dashboard unit displays the annual target completion status, a comparison of delivery data from each contracting unit, and resource utilization rate.

[0017] Furthermore, the data acquisition module is integrated with external systems through WebService interface integration and database intermediate table integration, and the standardized resource data is stored in a MySQL database.

[0018] 3. Beneficial effects: Compared with the prior art, the technical solution provided by this invention has the following advantages: This invention achieves global collaborative management of multiple AGV devices through a resource scheduling module, combines intelligent optimization algorithms for path planning, and coordinates with traffic control units to prioritize single-lane and no-head-on-head driving areas, effectively avoiding AGV collisions and congestion, and significantly reducing path redundancy. Simultaneously, it dynamically allocates resources based on logistics task priorities, uses the TCP protocol to ensure the accuracy and reliability of multi-AGV data communication, and interacts with the MES system in real time via a WebService interface to ensure the timeliness and accuracy of material delivery, significantly reducing the labor costs of internal material turnover and improving the overall operational efficiency of workshop logistics. The intelligent scheduling module generates hierarchical production plans (annual first-level delivery plan, monthly second-level production plan, and process-level third-level execution plan), adapting to multi-variety, small-batch production models. It optimizes and filters scheduling schemes through a cost-efficiency comprehensive evaluation model, dynamically adjusting plans based on order demand and real-time resource status. This allows for flexible responses to random events such as urgent order insertions and priority adjustments, reducing the production plan change rate. For scenarios where idle manpower and equipment meet demand, a production plan is established based on the minimum completion time. For scenarios with insufficient resources, the optimal solution is selected through process sequence groups, achieving global optimization of resource allocation, improving production efficiency and order delivery timeliness, and enhancing the company's market competitiveness. The data processing module removes inconsistent, invalid, and missing values ​​through a data cleaning unit, and standardizes resource data of different formats through a data conversion unit, eliminating dimensional differences and solving the problems of insufficient data accuracy and messy formats in traditional data management systems. For multimodal employee behavior data, a dedicated mathematical model calculates the influence coefficients of video learning time, classroom interaction activity, and homework completion, enabling precise characterization of employee learning status and providing data support for optimal human resource allocation. The standardized resource data provides a reliable basis for production scheduling decisions and optimization, improving the scientific rigor and accuracy of decision-making. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0020] To facilitate understanding of the present invention, a more complete description of the invention will be given below with reference to the accompanying drawings, which illustrate several embodiments of the invention. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of the invention will be more thorough and complete.

[0021] Example See attached document Figure 1 A smart manufacturing resource planning and management system, comprising: The data acquisition module is used to collect multi-type resource data throughout the intelligent manufacturing process. The multi-type resource data includes human resource data, equipment resource data, material resource data, AGV operating status data, and multimodal employee behavior data. The data processing module is used to clean, standardize, and integrate the various types of resource data to obtain standardized resource data. The processing includes checking data consistency and handling invalid and missing values. The resource scheduling module is used to schedule multiple AGVs and plan routes based on the standardized resource data and the priority of logistics tasks, so as to realize automated material handling and control traffic in traffic control areas. The intelligent scheduling module is used to integrate the standardized resource data to generate a hierarchical production plan based on order business needs. The hierarchical production plan includes an annual first-level delivery plan, a monthly second-level production plan, and a process-level third-level execution plan. The scheduling scheme is optimized through a cost-efficiency comprehensive evaluation model. The monitoring and early warning module is used to monitor the AGV's operating status, production plan execution progress, equipment operating parameters, and abnormal behavior of multimodal data feedback in real time, and trigger early warning alarms. The collaborative optimization module is used to dynamically adjust production plans and AGV scheduling schemes, integrate production, inventory and sales information to achieve information sharing among all links, and achieve data interoperability through integration with MES, LIMS and MDC systems; The visualization module is used to intuitively display the AGV location, production progress, resource utilization, and plan execution status in the form of a two-dimensional map and dashboard.

[0023] Furthermore, the data acquisition module includes: The human resources data collection unit is used to collect employee attendance, working hours, and multimodal behavior data, including training video learning parameters, classroom interaction parameters, and assignment completion parameters. The equipment resource acquisition unit is used to collect data on the operating status of production equipment, AGV power consumption, and fault data. The material resource acquisition unit is used to collect data on raw material inventory, work-in-process quantity, and material delivery status. The data acquisition module achieves real-time data acquisition through intelligent monitoring equipment and WebService interface.

[0024] Architecture Deployment: The system adopts a microservice architecture. The underlying database layer uses MySQL to store standardized resource data, the microservice platform layer provides basic service support, the gateway layer realizes real-time communication between modules, and the application layer deploys basic data management, planning management, resource management and other functional modules in the form of App. During deployment, it completes the connection with the enterprise's existing MES, LIMS and MDC systems through two integration methods: WebService interface and database intermediate table, and opens up data interoperability channels.

[0025] Basic data configuration: Initial configuration is completed through the basic data management app, including: Define project templates and structured nodes, such as breaking down batch production tasks into nodes like contract signing and delivery management; Enter static data such as product BOM structure, part process definition, equipment ledger, and employee basic information; Configure data standards, such as data type, format, unit, encoding, and mathematical model parameters, such as the weighting of multimodal data processing coefficients and the cost weighting δ of the production scheduling scoring model. h With time weight δ t wait; Delineate key location information such as traffic control areas, AGV standby points, charging areas, and material preparation areas in the two-dimensional map of the workshop.

[0026] Furthermore, the data processing module includes: The data cleaning unit is used to remove inconsistent data, invalid values, and missing values ​​based on data quality tools. The data conversion unit is used to convert resource data in different formats into a unified standard format, eliminating differences in units. The multimodal data processing unit is used to calculate the impact coefficients of employee training video learning time, classroom interaction activity, and homework completion through mathematical models. Multi-dimensional data collection: The human resources data collection unit collects employee attendance records and working hour data through intelligent monitoring equipment, and at the same time captures multimodal behavioral data: training video learning parameters (total pause time t1, total fast forward time t2, repeated viewing time t3, total duration T), classroom interaction parameters (number of questions x1, number of answers x2, number of discussions x3), and homework completion parameters (accuracy rate η, completion time t, submission time difference Δt). The equipment resource acquisition unit collects the operating status of production equipment (speed, load, fault code) and AGV operating parameters (battery power, speed, current position, task number) in real time [1]; The material resource acquisition unit obtains information such as raw material inventory quantity, work-in-process circulation status, material delivery time, and batch information. The system integration acquisition unit synchronizes real-time production data, inspection and testing data, and equipment operation data through interfaces with MES, LIMS, and MDC systems.

[0027] Data standardization processing: The data cleaning unit uses data quality tools to remove inconsistent data (such as contradictory inventory quantities), invalid values ​​(such as equipment rotation speeds that exceed reasonable ranges), and missing values ​​(such as unfilled job completion times). The data conversion unit converts data in different formats (such as material data in Excel spreadsheets and JSON format operation data of equipment systems) into a unified standard format, eliminating differences in units; The multimodal data processing unit substitutes the data into the mathematical model to calculate the influence coefficient: The impact factor of training video learning time is shown below: ;

[0028] Example: The total duration of an employee training video is T=60 minutes, the pause time is t1=5 minutes, the fast forward time is t2=3 minutes, and the rewatch time is t3=8 minutes. Then a=(5*8) / (60*(60-3))≈0.0118.

[0029] The impact coefficient of classroom interaction activity is shown below: ;

[0030] Example: An employee's interaction parameters for 3 courses are (x1=2,x2=3,x3=4), (x1=1,x2=5,x3=2), and (x1=3,x2=2,x3=5). Then b = ((5*2+3*3+2*4) / 10+(5*1+3*5+2*2) / 10+(5*3+3*2+2*5) / 10) / 3≈(2.7+2.4+3.1) / 3≈2.73.

[0031] Impact coefficients of assignment completion status are shown below: ;

[0032] Example: An employee's accuracy rates for three assignments are η1=90%, η2=85%, and η3=95%, respectively. The submission time differences are Δt1=0, Δt2=10 minutes, and Δt3=-5 minutes (5 minutes early). Then g=(3*(|(85-90) / 90|+|(95-85) / 85|)+1) / (1 / (1+e 0 )+1 / (1+e¹ 0 )+1 / (1+e⁻ 5 ))≈(3*(0.055+0.117)+1) / (0.5+0+0.993)≈(1.086+1) / 1.493≈1.397).

[0033] Furthermore, the resource scheduling module includes: The path planning unit is used to plan the optimal transport path for AGVs based on the workshop's two-dimensional map data and intelligent optimization algorithms. The AGV control unit is used to acquire real-time status parameters of AGVs, control AGVs with insufficient power to automatically recharge, and dispatch them to standby points after charging is completed. Traffic control units are used to sequence traffic in single-lane or no-head-to-head traffic areas, guiding AGVs to pass in order. The resource scheduling module implements multi-AGV data communication through the TCP protocol and interacts with the MES system for logistics task information through the WebService interface.

[0034] Order demand analysis: The demand acquisition unit of the intelligent scheduling module extracts order information from the customer management database, and clarifies the production volume (e.g., 100 sets of composite components), production time (delivery cycle of 3 months), production specifications (material requirements, dimensional accuracy, etc.). At the same time, it synchronizes the company's current production tasks, available manpower (8 skilled workers), available equipment (3 molding machines), and material delivery status (core raw materials arrive in 2 batches per month).

[0035] Resource matching assessment: Based on production specifications, the material analysis unit of the planning generation unit determines that each component requires 5kg of carbon fiber prepreg, with a total production material requirement of 500kg. Considering the material delivery situation (250kg delivered monthly), the minimum time to complete the order is calculated to be 2 months. Further, the target workforce of 6 people and target equipment of 2 units are determined for this timeframe. The assessment unit compares the current available workforce (8 people) and available equipment (3 units) to confirm that the target requirements are met.

[0036] Furthermore, the intelligent scheduling module includes: The demand acquisition unit is used to retrieve the production quantity, production time, and production specifications of orders from the customer management database. The planning generation unit is used to determine whether the current available manpower and equipment can meet the order requirements. If they can, a production schedule is created based on the minimum completion time. Otherwise, the process sequence group is generated by combining the existing production tasks and the optimal solution is selected.

[0037] An initial production schedule is constructed based on the minimum timeframe (2 months), and a score is calculated using a cost-efficiency comprehensive evaluation model, as shown below: ;

[0038] Where δ h =0.4、δ t =0.6, preset cost H=500,000 yuan, preset time T=60 days, production steps n=3, cost of each step h1=150,000 yuan, h2=200,000 yuan, h3=100,000 yuan, time of each step t1=20 days, t2=25 days, t3=15 days, then F=0.4*e^(-(15+20+10) / 50)+0.6e^(-(20+25+15) / 60)=0.4*e^(-0.9)+0.6*e^(-1)≈0.4*0.407+0.6*0.368≈0.383. Because the score is higher than the preset threshold (0.3), the production scheduling scheme is directly adopted to generate an annual first-level delivery plan (delivering 100 sets within 3 months), a monthly second-level production plan (50 sets in the first month and 50 sets in the second month), and a process-level third-level execution plan (specific time nodes for processes such as cutting, forming, curing, and inspection). Plan issuance and execution: For main contractors that have deployed MES systems, the three-level execution plan is automatically issued through the system; for external contractors and other entities that have not deployed MES systems, the plan is issued in a standardized Excel format.

[0039] Furthermore, the monitoring and early warning module includes: The real-time monitoring unit is used to collect production site data through intelligent monitoring equipment, including raw material arrival time, production line operating status, AGV collision and fault information; The early warning management unit is used to automatically trigger alarms when abnormal behavior is detected and transmit early warning information to management personnel.

[0040] AGV scheduling instruction generation: The resource scheduling module is based on the material requirements in the standardized resource data (250kg of carbon fiber prepreg is required for 50 sets of production in the first month), the workshop two-dimensional map data, and the real-time status of AGVs (all 5 AGVs are in an idle state with a power level of ≥80%). Combined with the priority of logistics tasks (material delivery for the molding process has the highest priority), the path planning and scheduling logic is initiated.

[0041] Optimal Path Planning: The path planning unit uses intelligent optimization algorithms to avoid traffic control areas (single-channel inter-process channels), plans the optimal path from the material preparation area to the molding workshop (shortest distance and no congestion points), and converts the path data into execution instructions that can be recognized by the AGV.

[0042] Traffic Control and Execution: When three AGVs need to pass through a single-lane area simultaneously, the traffic control unit prioritizes them according to task priority, guiding the AGVs to pass in sequence to avoid head-on travel and collisions. The AGV control unit obtains the AGV's operating status in real time. If one AGV's battery drops to 20% after completing three delivery tasks, the system automatically issues a charging command, controlling it to go to the charging area to charge. After charging, it returns to the standby point to await new tasks.

[0043] Data interaction and feedback: The resource scheduling module ensures the accuracy of data communication between multiple AGVs through the TCP protocol, and at the same time provides real-time feedback on the material delivery status to the MES system through the WebService interface (such as "250kg of prepreg has been delivered to the molding workshop, and the preparation of materials for 50 sets of production has been completed").

[0044] Furthermore, the collaborative optimization module includes: The scheduling optimization unit is used to compare production site data with planned targets in real time, analyze the reasons for the differences, and dynamically adjust the production plan and AGV scheduling scheme. It also introduces a stocking mechanism to deal with order changes and raw material supply issues. The collaborative sharing unit is used to integrate production, inventory and sales information to enable information sharing and collaborative operations among various contracting units. The planning adjustment unit is used to deal with urgent order insertion scenarios, and to urgently modify the secondary production plan and reissue it to each execution unit.

[0045] Real-time monitoring throughout the entire process: The real-time monitoring unit of the monitoring and early warning module continuously collects production site data through intelligent monitoring equipment: raw material arrival time (250kg of raw materials arrived on time in the first month), production line operation status (stable load on molding equipment), AGV operation status (no collisions or malfunctions), and employee operation status (multimodal data feedback shows good training results and an operation accuracy rate of 92%).

[0046] Anomaly Identification and Early Warning: On the 45th day of production, the inspection data synchronized by the LIMS system showed that the curing strength of 10 sets of components did not meet the standard. After the real-time monitoring unit identified this abnormal behavior, the early warning management unit immediately triggered an alarm and pushed the early warning information ("10 sets of components in batch 202501 do not meet the curing strength standard and need to be re-inspected") to the production management personnel through system pop-ups and SMS.

[0047] Dynamic Adjustment and Collaboration: The scheduling optimization unit of the collaborative optimization module compares on-site data with planned targets, analyzes the causes of anomalies (curing temperature fluctuations), and dynamically adjusts the three-level execution plan: inserting the re-inspection process of the 10 sets of components into day 50, adjusting the time nodes of subsequent inspection processes, and introducing a stock preparation mechanism to add 5 sets of components to the production plan to ensure total delivery. The collaborative sharing unit synchronizes the adjusted plan to all aspects of production, inventory, and sales to ensure information sharing.

[0048] Urgent Order Insertion Processing: On the 50th day of production, the company received an urgent order (20 sets of customized composite components, with a delivery cycle of 1 month). The planning adjustment unit urgently modified the secondary production plan, splitting the original production plan of 50 sets in the second month into 30 sets of regular orders + 20 sets of urgent orders, and reissued them to each contracting unit. The system automatically adjusted the AGV scheduling scheme and production priority to ensure the orderly progress of both urgent and regular orders.

[0049] Furthermore, the MES system adopts a microservice architecture, including a database layer, a microservice platform layer, a gateway layer, and an application layer. The application layer implements basic data management, plan management, resource management, and other functions in the form of an App.

[0050] Furthermore, the visualization module includes a workshop two-dimensional map display unit and a multi-dimensional dashboard unit. The two-dimensional map displays the real-time location of the AGV and the status of logistics tasks, while the dashboard unit displays the annual target completion status, a comparison of delivery data from each contracting unit, and resource utilization rate. Multi-dimensional data display: The workshop 2D map display unit of the visualization display module shows the current location, task status (such as "AGV-03 is performing emergency order material delivery and is heading to the material preparation area") and logistics task progress of 5 AGVs in real time; the multi-dimensional dashboard unit displays the annual target completion status (60 sets of components have been produced, completion rate 60%), the delivery data comparison of each contractor (the main contractor delivered 45 sets, and the outsourcing unit delivered 15 sets) and resource utilization rate (forming equipment utilization rate 85%, manpower utilization rate 70%) in the form of charts.

[0051] Data Export and Analysis: Managers can use the query and statistical management functions to filter order execution data, AGV operation failure records, etc., based on multiple conditions, and export the selected data in Excel format. Based on the dashboard data and exported reports, enterprises can analyze and optimize logistics scheduling efficiency and production scheduling rationality, further reducing production costs and shortening production cycles.

[0052] Furthermore, the data acquisition module is integrated with external systems through WebService interface integration and database intermediate table integration, and the standardized resource data is stored in a MySQL database.

[0053] Resource scheduling efficiency improved by 30%: zero AGV collision and congestion incidents occurred, material delivery timeliness increased from 85% to 98%, and internal material turnover labor costs decreased by 25%; Production scheduling stability optimization: Production plan change rate reduced from 40% to 15%, urgent order insertion response time shortened to within 2 hours, and order delivery on-time rate increased from 80% to 95%; Improved data processing accuracy: Multimodal data processing error ≤3%, the scientific nature of decision-making supported by standardized data is significantly improved, and the resource allocation optimization rate reaches 20%; Enhanced collaborative management capabilities: Data exchange delay between systems is ≤5 seconds, production anomaly response time is reduced from 4 hours to 30 minutes, and overall enterprise operating costs are reduced by 18%.

[0054] The above-described embodiments are merely illustrative of certain implementations of the present invention, and are described in a relatively specific and detailed manner. However, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements are all within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. An intelligent manufacturing resource planning and management system, characterized in that: include: The data acquisition module is used to collect multi-type resource data throughout the intelligent manufacturing process. The multi-type resource data includes human resource data, equipment resource data, material resource data, AGV operating status data, and multimodal employee behavior data. The data processing module is used to clean, standardize, and integrate the various types of resource data to obtain standardized resource data. The processing includes checking data consistency and handling invalid and missing values. The resource scheduling module is used to schedule multiple AGVs and plan routes based on the standardized resource data and the priority of logistics tasks, so as to realize automated material handling and control traffic in traffic-controlled areas. The intelligent scheduling module is used to integrate the standardized resource data to generate a hierarchical production plan based on order business needs. The hierarchical production plan includes an annual first-level delivery plan, a monthly second-level production plan, and a process-level third-level execution plan. The scheduling scheme is optimized through a cost-efficiency comprehensive evaluation model. The monitoring and early warning module is used to monitor the AGV's operating status, production plan execution progress, equipment operating parameters, and abnormal behavior of multimodal data feedback in real time, and trigger early warning alarms. The collaborative optimization module is used to dynamically adjust production plans and AGV scheduling schemes, integrate production, inventory and sales information to achieve information sharing among all links, and achieve data interoperability through integration with MES, LIMS and MDC systems. The visualization module is used to intuitively display the AGV location, production progress, resource utilization, and plan execution status in the form of a two-dimensional map and dashboard.

2. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The data acquisition module includes: The human resources data collection unit is used to collect employee attendance, working hours, and multimodal behavior data, including training video learning parameters, classroom interaction parameters, and assignment completion parameters. The equipment resource acquisition unit is used to collect data on the operating status of production equipment, AGV power consumption, and fault data. The material resource acquisition unit is used to collect data on raw material inventory, work-in-process quantity, and material delivery status. The data acquisition module achieves real-time data acquisition through intelligent monitoring equipment and WebService interface.

3. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The data processing module includes: The data cleaning unit is used to remove inconsistent data, invalid values, and missing values ​​based on data quality tools. The data conversion unit is used to convert resource data in different formats into a unified standard format, eliminating differences in units. The multimodal data processing unit is used to calculate the impact coefficients of employee training video learning time, classroom interaction activity, and homework completion through mathematical models.

4. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The resource scheduling module includes: The path planning unit is used to plan the optimal transport path for AGVs based on the workshop's two-dimensional map data and intelligent optimization algorithms. The AGV control unit is used to acquire real-time status parameters of AGVs, control AGVs with insufficient power to automatically recharge, and dispatch them to standby points after charging is completed. Traffic control units are used to sequence traffic in single-lane or no-head-to-head traffic areas, guiding AGVs to pass in order. The resource scheduling module implements multi-AGV data communication through the TCP protocol and interacts with the MES system for logistics task information through the WebService interface.

5. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The intelligent scheduling module includes: The demand acquisition unit is used to retrieve the production quantity, production time, and production specifications of orders from the customer management database. The planning generation unit is used to determine whether the current available manpower and equipment can meet the order requirements. If they can, a production schedule is created based on the minimum completion time. Otherwise, the process sequence group is generated by combining the existing production tasks and the optimal solution is selected.

6. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The monitoring and early warning module includes: The real-time monitoring unit is used to collect production site data through intelligent monitoring equipment, including raw material arrival time, production line operating status, AGV collision and fault information; The early warning management unit is used to automatically trigger alarms when abnormal behavior is detected and transmit early warning information to management personnel.

7. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The collaborative optimization module includes: The scheduling optimization unit is used to compare production site data with planned targets in real time, analyze the reasons for the differences, and dynamically adjust the production plan and AGV scheduling scheme. It also introduces a stocking mechanism to deal with order changes and raw material supply issues. The collaborative sharing unit is used to integrate production, inventory and sales information to enable information sharing and collaborative operations among various contracting units. The planning adjustment unit is used to deal with urgent order insertion scenarios, and to urgently modify the secondary production plan and reissue it to each execution unit.

8. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The MES system adopts a microservice architecture, including a database layer, a microservice platform layer, a gateway layer, and an application layer. The application layer implements basic data management, plan management, resource management, and other functions in the form of an App.

9. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The visualization module includes a workshop 2D map display unit and a multi-dimensional dashboard unit. The 2D map displays the real-time location of the AGV and the status of logistics tasks, while the dashboard unit displays the annual target completion status, a comparison of delivery data from each contractor, and resource utilization.

10. The intelligent manufacturing resource planning and management system according to claim 1, characterized in that: The data acquisition module is integrated with external systems through WebService interface integration and database intermediate table integration, and the standardized resource data is stored in a MySQL database.

Images