Industrial production intelligent scheduling system
By applying mixed integer planning and nonlinear planning technologies in industrial production intelligent scheduling systems, dynamically adjusting production tasks and resource allocation, the problems of uneven resource allocation and inadequate cost control in traditional systems are solved, and production efficiency and market competition are improved force.
Patent Information
- Application Number
- CN202411076843.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional industrial intelligent scheduling systems lack flexible scheduling tools and cost optimization strategies, resulting in uneven allocation of production resources, inaccurate execution of production plans, and inadequate cost control, making it difficult to cope with complex and changing market demands, affecting the market competitiveness of enterprises and Profitability.
An intelligent industrial production scheduling system was designed, including production demand prediction module, resource allocation module, task priority adjustment module, production line balance module and production cost optimization module. The production tasks and Resource allocation, optimize resource use and cost control of production lines.
By accurately adjusting the process layout and equipment use on the production line, production delays and costs are reduced, production efficiency and economic benefits of resource use are improved, and more refined and efficient cost control is achieved.
Smart Images

Figure CN119005609A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent scheduling, and in particular to an industrial production intelligent scheduling system. Background Art
[0002] The field of intelligent scheduling technology involves the use of methods and techniques from disciplines such as computer science and operations research to optimize production processes, task execution, resource allocation, etc. This technology analyzes large amounts of data, identifies patterns, and formulates decision-making rules to improve production efficiency, reduce costs, shorten production cycles, etc. Intelligent scheduling systems use algorithms to predict, plan, and adjust production activities to adapt to changes in the production process, including machine failures, order changes, or resource shortages. The purpose of the intelligent scheduling system is to optimize production and logistics activities and improve the operational efficiency and market competitiveness of enterprises through a highly automated and intelligent decision-making process.
[0003] Among them, the industrial production intelligent scheduling system aims to achieve optimal resource allocation and task scheduling in the production process. The core purpose of this system is to improve the flexibility and efficiency of the production line, reduce production costs, shorten production preparation and execution time, and achieve higher customer satisfaction and market response speed. By comprehensively considering factors such as production capacity, material supply, worker skills and delivery deadlines, the intelligent scheduling system can dynamically plan production activities and optimize production processes, thereby achieving the goal of improving overall production efficiency and benefits.
[0004] Traditional intelligent production scheduling systems lack flexible scheduling tools and cost optimization strategies, resulting in uneven distribution of production resources, inaccurate production plan execution, and inadequate cost control. This has limited companies from improving their market competitiveness, especially when facing complex and changing market demands. For example, failure to effectively respond to machine failures or sudden increases in orders has caused production stagnation or waste of resources, affecting the company's ability to respond quickly to the market. Inaccurate cost control has prevented companies from effectively reducing production costs, affecting their overall profitability. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an industrial production intelligent scheduling system.
[0006] In order to achieve the above object, the present invention adopts the following technical solution: an industrial production intelligent scheduling system, the system comprising:
[0007] The production demand forecasting module predicts future production tasks and raw material demand based on historical production and sales data and order flow data, and obtains future demand change trends;
[0008] The production resource allocation module allocates raw materials and human resources based on the future demand change trend, matches production demand, and obtains resource allocation solutions;
[0009] The task priority adjustment module dynamically adjusts the execution order of production tasks based on the resource allocation plan and future demand change trends to obtain an optimized production scheduling plan;
[0010] The production line balancing module uses mixed integer programming technology based on the optimized production scheduling scheme to optimize the allocation of manpower and equipment for multiple processes on the production line to obtain the production operation optimization result;
[0011] The production line efficiency evaluation module analyzes the deviation between the current actual production efficiency and the expected target based on the production operation optimization results, formulates matching improvement measures, and obtains the efficiency deviation adjustment strategy;
[0012] The production cost optimization module uses a nonlinear programming method based on the efficiency deviation adjustment strategy and resource allocation plan to optimize the raw material procurement, energy consumption and manpower allocation costs to obtain a cost saving plan.
[0013] The present invention has the following improvements: the future demand change trend includes the predicted product type demand, raw material procurement volume and expected market demand change trend; the resource allocation plan includes the number of allocated human resources, the operating time schedule of each machine and the allocation ratio of raw materials; the optimized production scheduling plan includes the execution sequence of multiple tasks, the scheduled completion time and the required resource list; the production operation optimization result includes the adjusted process layout, the equipment use optimization plan and the human resource allocation strategy; the efficiency deviation adjustment strategy includes the identified production bottlenecks, the recommended improvement measures and the expected efficiency improvement ratio; the cost saving plan includes the energy consumption reduction strategy, the raw material use efficiency improvement measures and the labor cost optimization measures.
[0014] The present invention is improved in that the task priority adjustment module comprises:
[0015] The urgency analysis submodule analyzes the delivery time and market demand urgency of production tasks based on the resource allocation plan and future demand change trends, and assigns a matching urgency level to each task in combination with the raw material arrival time and production capacity constraints to obtain a task urgency ranking table;
[0016] The task importance assessment submodule analyzes the importance of each task on production efficiency, customer satisfaction and revenue based on the task urgency ranking table, and determines a matching importance score for each task based on market feedback and contract penalty risk. A priority list based on task influence is formulated through the score to obtain the task priority assessment result;
[0017] The task sequencing submodule dynamically adjusts the execution order of multiple production tasks based on the task priority evaluation results, gives priority to key tasks, optimizes production efficiency and market response speed, and obtains an optimized production scheduling plan.
[0018] The present invention is improved in that the production line balancing module comprises:
[0019] The production process analysis submodule analyzes multiple process flows on the production line based on the optimized production scheduling plan, including raw material input, semi-finished product processing and finished product assembly, identifies bottleneck links in the process, and obtains process bottleneck identification results;
[0020] The equipment optimization configuration submodule uses mixed integer programming technology based on the process bottleneck identification results, combines the actual production capacity and the production equipment maintenance schedule, adjusts the configuration and use plan of the production equipment, optimizes the idle and waiting time of manpower and equipment, and obtains the production configuration adjustment plan;
[0021] The process balance strategy submodule adjusts the human resources and equipment configuration of multiple production processes based on the production configuration adjustment plan, balances the workload of the production line, optimizes the connection of multiple processes, and obtains production operation optimization results.
[0022] The present invention improves that the mixed integer programming technology is according to the formula:
[0023]
[0024] Calculate each equipment and usage time to get the production configuration adjustment plan, where Z
[0025] is the production line operation cost, n is the total number of equipment on the production line, m is the total number of processes in the production process, c i is the operating cost of the i-th device, x i is a binary variable that determines whether the i-th device is running, d j is the delay cost of the jth process, y j is the delay time of the jth process, k i is the energy efficiency coefficient of equipment i, f i
[0026] is the energy consumption of device i within the target time, l j is the efficiency weight of process j, g j For process j
[0027] Contribution to total production time.
[0028] The present invention is improved in that the production line efficiency evaluation module comprises:
[0029] The production data monitoring submodule collects the operation data of the production line in real time based on the production operation optimization results, including the start and end time of each process, the operation status and output of the machine, integrates and analyzes the data, and obtains real-time status monitoring information;
[0030] The efficiency analysis submodule evaluates the difference between the actual output and the planned output of the production line through statistical analysis based on the real-time status monitoring information, analyzes the key factors affecting production efficiency, including machine failure, raw material shortage and operation error, and obtains the efficiency deviation analysis results;
[0031] The improvement measure proposal submodule formulates matching improvement measures based on the efficiency deviation analysis results, including adjusting the production plan, improving equipment maintenance and optimizing worker training, optimizing the overall efficiency and output quality of the production line, and obtaining an efficiency deviation adjustment strategy.
[0032] The present invention is improved in that the production cost optimization module comprises:
[0033] The cost analysis submodule collects and analyzes multiple cost data in the production process, including raw materials, labor costs and manufacturing expenses, based on the efficiency deviation adjustment strategy and resource allocation plan, identifies cost components and key cost driving factors, and obtains cost component identification results;
[0034] The cost reduction scheme submodule uses nonlinear programming methods based on the cost structure identification results to optimize the raw material procurement plan, energy utilization efficiency and improve worker efficiency, formulate matching cost reduction measures, and obtain a list of cost optimization measures;
[0035] The cost control strategy submodule implements long-term cost control strategies based on the cost optimization measures list, including budget management improvements and cost saving measures promotion, formulates cost control strategies that match current production practices, and obtains cost saving plans.
[0036] The present invention is improved in that the nonlinear programming method is according to the formula:
[0037]
[0038] Calculate the minimum total cost and get a list of cost optimization measures, where C is the total production cost, p i is the unit price of the i-th raw material, q i is the purchase quantity of the i-th raw material, α i
[0039] is the coefficient of change of raw material prices, e j is the unit consumption cost of the j-th energy, s j For the jth
[0040] The consumption of energy, β j is the energy efficiency coefficient, w k is the unit cost of the kth manual operation, h k is the number of hours of manual operation of the kth person, γ k is the labor efficiency improvement coefficient, n, m and l
[0041] They represent the number of raw material types, energy types and manual operation types respectively.
[0042] Compared with the prior art, the advantages and positive effects of the present invention are:
[0043] In the present invention, by applying mixed integer programming technology, according to the production equipment capacity, time and sequence constraints, the optimal allocation of manpower and equipment is carried out, the process layout and equipment use on the production line can be accurately adjusted, the production delays caused by waiting and equipment idleness are reduced, the overall operation efficiency of the production line is improved, and the production cost is reduced. The use of nonlinear programming methods optimizes raw material procurement, energy use and manpower allocation by analyzing energy consumption, raw material use and labor costs, making cost control more refined and efficient, reducing unnecessary expenses, and improving the economic benefits of resource use. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 The present invention proposes a structural diagram of an industrial production intelligent scheduling system;
[0045] Figure 2 A system framework diagram of an industrial production intelligent scheduling system is proposed for the present invention;
[0046] Figure 3 The present invention proposes a schematic diagram of a production demand forecasting module in an industrial production intelligent scheduling system;
[0047] Figure 4 The present invention proposes a schematic diagram of a production resource allocation module in an industrial production intelligent scheduling system;
[0048] Figure 5 The present invention proposes a schematic diagram of a task priority adjustment module in an industrial production intelligent scheduling system;
[0049] Figure 6 The present invention proposes a schematic diagram of a production line balancing module in an industrial production intelligent scheduling system;
[0050] Figure 7 The present invention proposes a schematic diagram of a production line efficiency evaluation module in an industrial production intelligent scheduling system;
[0051] Figure 8The present invention proposes a basic schematic diagram of a production cost optimization module in an industrial production intelligent scheduling system. DETAILED DESCRIPTION
[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0053] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0054] Example
[0055] See also Figure 1 ,The present invention provides a technical solution: an industrial production intelligent scheduling system, the system includes a production demand prediction module, a production resource allocation module, a task priority adjustment module, a production line balancing module, a production line efficiency evaluation module, and a production cost optimization module;
[0056] The production demand forecasting module conducts time series analysis and seasonal factor decomposition based on historical production and sales data and order flow data, predicts future production tasks and raw material demand, and obtains future demand change trends;
[0057] The production resource allocation module uses linear programming methods to allocate raw materials and human resources based on future demand trends, match production needs, optimize resource utilization efficiency, and obtain resource allocation plans;
[0058] The task priority adjustment module analyzes the urgency and importance of multiple production tasks based on the resource allocation plan and future demand change trends, dynamically adjusts the execution order of production tasks, optimizes the execution order of key production tasks, and obtains an optimized production scheduling plan;
[0059] The production line balancing module is based on the optimized production scheduling scheme, applies mixed integer programming technology, combines production equipment capacity, production time and production sequence constraints, optimizes the allocation of manpower and equipment for multiple processes on the production line, optimizes the idle and waiting time of manpower and equipment, and obtains the optimization results of production operations;
[0060] The production line efficiency evaluation module collects production line operation data based on the production operation optimization results, compares the target output and actual output through dynamic simulation and efficiency analysis, analyzes the deviation between the current actual production efficiency and the expected target, formulates matching improvement measures, and obtains the efficiency deviation adjustment strategy;
[0061] The production cost optimization module is based on the efficiency deviation adjustment strategy and resource allocation plan, and adopts nonlinear programming methods. By analyzing energy consumption, raw material usage and labor costs, it optimizes the raw material procurement, energy consumption and labor allocation costs, formulates matching cost optimization strategies, and obtains cost saving plans.
[0062] Future demand change trends include predicted product type demand, raw material procurement volume and expected market demand change trends; resource allocation plans include the number of allocated human resources, the operating time schedule for each machine and the allocation ratio of raw materials; optimized production scheduling plans include the execution sequence of multiple tasks, the scheduled completion time and the required resource list; production operation optimization results include the adjusted process layout, equipment utilization optimization plan and human resource allocation strategy; efficiency deviation adjustment strategies include identified production bottlenecks, recommended improvement measures and expected efficiency improvement ratios; cost saving plans include energy consumption reduction strategies, raw material utilization efficiency improvement measures and labor cost optimization measures.
[0063] See also Figure 2 and Figure 3 ,The production demand forecasting module includes a market analysis submodule, a sales trend submodule, and a demand quantity forecasting submodule;
[0064] The market analysis submodule analyzes market demand trends, new technology impacts, and competitor market strategies based on historical production and sales data and order flow data, comprehensively evaluates market development directions and potential demand, and generates a market trend overview in the following specific processes;
[0065] The market analysis submodule is based on historical production and sales data and order flow data, and uses data mining technology, especially the integration of Python's Pandas library for data preprocessing, such as removing outliers and filling missing values. It also uses the decision tree algorithm in the Sklearn library to classify and analyze market demand trends, segment market details and the potential impact of new technologies, analyze competitors' market strategies, and synthesize the analysis results to generate a comprehensive overview of market trends.
[0066] The sales trend submodule uses statistical methods to analyze historical sales data based on the market trend overview, identify sales growth points and demand decline areas, draw sales trend charts, and obtain sales cyclical change data. The specific process is as follows;
[0067] The sales trend submodule is based on a comprehensive overview of market trends and uses time series analysis methods, especially the Statsmodels library in Python to apply the autoregressive difference moving average model. The model parameters are set to include autoregressive terms, difference orders, and moving average terms. Trend and seasonality analysis is performed on historical sales data. By drawing a decomposition chart of the time series, sales growth points and demand decline areas are identified to obtain sales cyclical change data.
[0068] The demand forecasting submodule is based on the sales cyclical change data, combined with the industry growth rate, seasonal changes and the impact of marketing activities, and uses time series analysis and seasonal factor decomposition to predict future production tasks and raw material demand. The specific process of obtaining future demand change trends is as follows;
[0069] The demand forecasting submodule is based on the analysis results of sales cyclical changes, combined with the industry growth rate, seasonal changes and the impact of marketing activities. It adopts the random forest algorithm in machine learning methods and is implemented using the Sk learn library. The number of trees is set to 100 and the maximum depth is 10. Multiple decision trees are constructed by randomly selecting features and samples to predict future production tasks and raw material demand. Algorithms are used to process time series data and seasonal factors to generate future demand change trends.
[0070] See also Figure 2 and Figure 4 ,The production resource allocation module includes a resource demand analysis submodule, a resource optimization configuration submodule, and a resource allocation strategy submodule;
[0071] The resource demand analysis submodule evaluates the demand for raw materials, manpower and equipment resources in future production plans based on the trend of future demand changes, including resource types, quantities and usage time, analyzes the capabilities of the resource supply chain, formulates a resource demand plan, and obtains the specific process of the production demand list as follows;
[0072] The resource demand analysis submodule is based on the future demand change trend and uses data analysis methods. It uses Python language with NumPy and Pandas libraries to process historical production and sales data and order flow data. By calculating and comparing data changes in different time periods, it evaluates the demand for raw materials, manpower and equipment resources for future production plans, including identification of resource types, quantity forecasting and estimation of usage time. After analyzing the data, it integrates the capacity information of the resource supply chain, formulates a demand plan covering all necessary resource details, and generates a detailed production demand list.
[0073] The resource optimization configuration submodule uses linear programming method to allocate raw materials and human resources based on the production demand list, optimize resource utilization, and obtain the specific process of optimizing resource utilization strategy:
[0074] The resource optimization configuration submodule is based on a detailed production requirement list and adopts a linear programming method, especially using Lingo software to build and solve the model of resource allocation problems. The objective function is set to maximize resource utilization. The constraints include restrictions on resource type, quantity, and usage time. Raw materials and human resources are effectively allocated to ensure that each resource can be used most reasonably in the production process, thereby obtaining an optimized resource utilization strategy.
[0075] The resource allocation strategy submodule formulates a matching resource allocation execution plan based on the optimization resource utilization strategy, including personnel work scheduling, raw material procurement, distribution schedule and equipment maintenance and scheduling plan. The specific process of obtaining the resource allocation plan is as follows;
[0076] The resource allocation strategy submodule designs a specific resource allocation execution plan based on the resource optimization utilization strategy. It uses project management software such as Microsoft Project to arrange personnel work schedules, formulate raw material procurement and distribution schedules, and consider equipment maintenance and scheduling plans to ensure that the implementation of the resource allocation plan can meet production needs while maintaining efficiency and flexibility. A set of detailed operating guidelines and schedules are formulated to obtain a comprehensive resource allocation plan.
[0077] See also Figure 2 and Figure 5 ,The task priority adjustment module includes the urgency analysis submodule, the task importance evaluation submodule, and the task sequencing submodule;
[0078] The urgency analysis submodule analyzes the delivery time and market demand urgency of production tasks based on resource allocation plans and future demand change trends. Combined with the arrival time of raw materials and production capacity constraints, it assigns a matching urgency level to each task and obtains the task urgency ranking table. The specific process is as follows:
[0079] The urgency analysis submodule uses decision support system software and logistic regression algorithm to analyze the delivery time and market demand urgency of production tasks based on resource allocation plans and future demand change trends. The logistic regression model sets short delivery time and high market demand as positive categories, and long delivery time and low market demand as negative categories. By calculating the urgency probability of each task, a matching urgency level is assigned to each task to obtain a task urgency ranking table.
[0080] The task importance assessment submodule analyzes the importance of each task on production efficiency, customer satisfaction and revenue based on the task urgency ranking table, and determines a matching importance score for each task based on market feedback and contract penalty risk. Through the score, a priority list based on task influence is formulated. The specific process of obtaining the task priority assessment result is as follows;
[0081] The task importance assessment submodule is based on the task urgency level ranking, adopts the multi-attribute decision analysis method, and through the hierarchical analysis process, combines market feedback and contract penalty risks to evaluate the importance of each task on production efficiency, customer satisfaction and revenue. By constructing a judgment matrix, the weight score of each task is calculated, and a priority list based on task influence is formulated to generate task priority assessment results.
[0082] The task sorting submodule dynamically adjusts the execution order of multiple production tasks based on the task priority evaluation results, prioritizes key tasks, optimizes production efficiency and market response speed, and obtains the specific process of optimizing the production scheduling plan as follows;
[0083] The task sorting submodule is based on the task priority scoring results and uses the priority queue algorithm for dynamic adjustment. It sorts each task according to the urgency and importance of the task to ensure that high-scoring tasks are executed first. It is implemented in the programming language Python and uses the priority queue data structure to dynamically adjust the position of tasks in the queue according to the score, optimize production efficiency and market response speed, form a production task execution plan with a clear order, and obtain an optimized production scheduling plan.
[0084] See also Figure 2 and Figure 6 ,The production line balancing module includes the production process analysis submodule, the equipment optimization configuration submodule, and the process balancing strategy submodule;
[0085] The production process analysis submodule is based on the optimization of production scheduling scheme, analyzes multiple process flows on the production line, including raw material input, semi-finished product processing and finished product assembly, identifies the bottleneck links in the process, and obtains the specific process of process bottleneck identification results as follows;
[0086] The production process analysis submodule is based on optimizing the production scheduling plan and using process mapping technology. It uses Python's Matplotlib library and Graphviz tools to draw a detailed flow chart of the production line. The flow chart includes every link from raw material input, semi-finished product processing to finished product assembly. During the analysis process, combined with field observations and employee interviews, Python scripts are used to automatically collect and process information, identify stagnation points and bottleneck links in the process, refine the time consumption and resource utilization of each link, and generate process bottleneck identification results.
[0087] The equipment optimization configuration submodule uses mixed integer programming technology based on the process bottleneck identification results, combined with the actual production capacity and production equipment maintenance schedule, to adjust the configuration and use plan of production equipment, optimize the idle and waiting time of manpower and equipment, and obtain the specific process of the production configuration adjustment plan:
[0088] The equipment optimization configuration submodule is based on the process bottleneck identification results and adopts mixed integer programming technology. It builds an optimization model through Python's PuLP library, sets model parameters including the number limit of production equipment, maintenance time frame and production capacity upper limit, and uses the Gurobi optimizer to solve the model, adjust the layout and use plan of production equipment, reduce the idle and waiting time of manpower and equipment, and rearrange the equipment use order and process layout after optimization to ensure the continuity and efficiency of the production process and generate a production configuration adjustment plan.
[0089] Mixed integer programming technique, according to the formula:
[0090]
[0091] Calculate each equipment and usage time to get the production configuration adjustment plan, where Z
[0092] is the production line operation cost, n is the total number of equipment on the production line, m is the total number of processes in the production process, c i is the operating cost of the i-th device, x i is a binary variable that determines whether the i-th device is running, d j is the delay cost of the jth process, y j is the delay time of the jth process, k i is the energy efficiency coefficient of equipment i, reflecting the ratio of the equipment’s energy consumption to its production efficiency, f i For device i
[0093] Energy consumption within the target time, l j is the efficiency weight of process j, indicating the importance of the efficiency of this process relative to other processes, g j For process j
[0094] Contribution to the total production time, that is, the proportion of time taken by this process.
[0095] The specific implementation process of the improved formula is as follows:
[0096] By determining the total number of equipment n and the total number of processes m on the production line
[0097] , for each equipment and each process, collect necessary data, including operating costs c i , energy consumption f i
[0098] , delay cost d j , and the delay time y j
[0099] , by analyzing the energy efficiency standards and historical production data of the equipment, an energy efficiency coefficient k is assigned to each device iand assign an efficiency weight l to each process j , calculate the contribution of each process to the total production time g j , g j Through time tracking analysis of past production cycles, it is concluded that the proportion of time occupied by this process in the entire production process is obtained, and a mixed integer programming model is constructed and solved by Gurobi optimizer to find the equipment operation state x that minimizes the production line operation cost. i and process execution time y j
[0100] By adjusting the equipment layout and usage plan, balancing the process execution sequence, the goal of reducing idle and waiting time of manpower and equipment is achieved, and an equipment configuration optimization plan that comprehensively considers cost, energy efficiency and production efficiency is generated.
[0101] The process balance strategy submodule adjusts the human resources and equipment configuration of multiple production processes based on the production configuration adjustment plan, balances the workload of the production line, optimizes the connection of multiple processes, and obtains the specific process of production operation optimization results:
[0102] The process balance strategy submodule is based on the equipment configuration optimization plan, applies work study and operation analysis methods, and uses Python's SimPy library to simulate and analyze the production process. It examines the time relationship and resource allocation between each process, dynamically adjusts human resources and equipment allocation, balances the workload of each process on the production line, optimizes the connection between processes, eliminates production bottlenecks, and obtains production operation optimization results.
[0103] See also Figure 2 and Figure 7 ,The production line efficiency evaluation module includes the production data monitoring submodule, the efficiency analysis submodule, and the improvement measure proposal submodule;
[0104] The production data monitoring submodule collects the operation data of the production line in real time based on the optimization results of production operations, including the start and end time of each process, the operation status and output of the machine, and integrates and analyzes the data to obtain the specific process of real-time status monitoring information:
[0105] The production data monitoring submodule deploys a real-time data acquisition system based on the optimization results of production operations. It uses the Node-RED streaming programming tool to connect sensors and data acquisition devices on the production line, writes JavaScript function nodes to collect the start and end time of each process, the machine's operating status and output, and uses the MQTT protocol to achieve real-time data transmission. It performs preliminary integration and time series analysis on the collected data to generate real-time status monitoring information.
[0106] The efficiency analysis submodule evaluates the difference between the actual output and the planned output of the production line through statistical analysis based on real-time status monitoring information, and analyzes the key factors affecting production efficiency, including machine failure, raw material shortage and operation errors. The specific process of obtaining the efficiency deviation analysis results is as follows;
[0107] The efficiency analysis submodule uses the Python SciPy library for statistical analysis based on the real-time status monitoring data set, and uses t-
[0108] Test and variance analysis methods are used to evaluate the difference between the actual output and the planned output of the production line, identify the key influencing factors of efficiency deviation, such as statistical analysis of machine failure rate, frequency analysis of delayed raw material arrival, and regression analysis of operation errors, analyze the various influencing factors of production efficiency, and obtain detailed efficiency deviation analysis results.
[0109] The improvement measures proposal submodule formulates matching improvement measures based on the efficiency deviation analysis results, including adjusting production plans, improving equipment maintenance and optimizing worker training, optimizing the overall efficiency and output quality of the production line, and obtaining the specific process of the efficiency deviation adjustment strategy as follows;
[0110] The improvement measure proposal submodule is based on the detailed efficiency deviation analysis results, combined with the production process and resource allocation, and uses the decision tree algorithm to diagnose problems and generate solutions. The decision tree model is implemented using Python's Sklearn library. According to the type and impact of the efficiency deviation, targeted improvement measures are automatically derived, such as recommending maintenance plan adjustments for equipment with high failure rates, making procurement optimization suggestions for raw material shortages, and proposing employee retraining plans for links with frequent operating errors, forming a set of efficiency deviation adjustment strategies aimed at comprehensively improving production line efficiency and output quality.
[0111] See also Figure 2 and Figure 8 ,The production cost optimization module includes a cost analysis submodule, a cost reduction scheme submodule, and a cost control strategy submodule;
[0112] The cost analysis submodule collects and analyzes multiple cost data in the production process, including raw materials, labor costs and manufacturing expenses, based on the efficiency deviation adjustment strategy and resource allocation plan, identifies the cost composition and key cost drivers, and obtains the specific process of cost composition identification results as follows;
[0113] The cost analysis submodule deploys an automated data collection system based on the efficiency deviation adjustment strategy and resource allocation plan, writes scripts in Python, extracts detailed records of raw materials, labor costs, and manufacturing expenses from the enterprise resource planning system through SQL queries, and uses the Pandas library for data cleaning and preliminary analysis, such as calculating the mean, median, and coefficient of variation of various types of costs to identify cost structures and key cost drivers, and organizes and analyzes multiple cost data in the production process to generate detailed cost structure identification results.
[0114] The cost reduction program submodule uses nonlinear programming methods based on the cost structure identification results to optimize the raw material procurement plan, energy utilization efficiency and improve worker efficiency, formulate matching cost reduction measures, and obtain the specific process of the cost optimization measures list as follows;
[0115] The cost reduction plan submodule is based on a detailed cost structure analysis report and adopts a nonlinear programming method. It is specifically implemented through the Optimization Toolbox toolbox of MATLAB. The objective function is set to minimize the total cost. The constraints include the raw material procurement cost, energy consumption limit and the lower limit of labor efficiency. The optimal solution of raw material procurement quantity, energy use strategy and labor allocation is obtained by solving, and a set of specific measures aimed at reducing the total cost are formulated, including the operational steps of optimizing the raw material procurement plan and improving energy utilization efficiency, and generating a list of cost optimization measures.
[0116] Nonlinear programming method, according to the formula:
[0117]
[0118] Calculate the minimum total cost and get a list of cost optimization measures, where C is the total production cost, p i is the unit price of the i-th raw material, q i is the purchase quantity of the i-th raw material, α i
[0119] is the coefficient of change of raw material prices, e j is the unit consumption cost of the j-th energy, s j For the jth
[0120] The consumption of energy, β j is the energy efficiency coefficient, w k is the unit cost of the kth manual operation, h k is the number of hours of manual operation of the kth person, γ k is the labor efficiency improvement coefficient, n, m and l
[0121] They represent the number of raw material types, energy types and manual operation types respectively.
[0122] The specific implementation process of the improved formula is as follows:
[0123] For each raw material, energy and labor operation, the basic cost parameter p i 、e j 、w k
[0124] Set up and introduce new system i , β j , γ k
[0125] Reflects the nonlinear changes in costs when purchasing in large quantities, improving energy efficiency, and improving labor efficiency, for example, α i
[0126] It can be calculated based on past market price fluctuation data, reflecting the trend of raw material prices changing with the increase in procurement volume, β j
[0127] Based on the analysis of historical data on energy efficiency, it indicates the cost saving effect brought by the reduction of energy consumption, γ k
[0128] Determined based on the expected impact assessment of labor efficiency improvement measures, the contribution of labor hours reduction to cost savings is expressed. The improved formula is applied through MATLAB's Optimization Toolbox to solve the nonlinear programming problem and obtain the optimized raw material procurement quantity q i , Energy use strategies j and manual allocation k The optimal solution is to comprehensively consider the changes in raw material prices, energy efficiency and labor efficiency improvements, formulate a set of specific measures to reduce total costs, and generate a list of cost reduction strategies.
[0129] The cost control strategy submodule implements long-term cost control strategies based on the cost optimization measures list, including budget management improvement and cost saving measures promotion, and formulates cost control strategies that match current production practices. The specific process for obtaining cost saving plans is as follows;
[0130] The cost control strategy submodule designs and implements a long-term cost control strategy based on the cost reduction strategy list, uses financial analysis software such as QuickBooks to improve budget management, and combines Python's Dash library to build an interactive cost monitoring dashboard to track the implementation of cost-saving measures in real time. By executing comprehensive cost management activities including budget control, cost analysis, and efficiency monitoring, it establishes and promotes a set of cost-saving measures for the entire company, forming a comprehensive cost-saving plan that meets the actual needs of current production.
[0131] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical contents to change or modify equivalent embodiments to apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. An industrial production intelligent scheduling system, characterized in that: The system comprises: The production demand forecasting module predicts future production tasks and raw material demand based on historical production and sales data and order flow data, and obtains future demand change trends; The production resource allocation module allocates raw materials and human resources based on the future demand change trend, matches production demand, and obtains resource allocation solutions; The task priority adjustment module dynamically adjusts the execution order of production tasks based on the resource allocation plan and future demand change trends to obtain an optimized production scheduling plan; The production line balancing module uses mixed integer programming technology based on the optimized production scheduling scheme to optimize the allocation of manpower and equipment for multiple processes on the production line to obtain the production operation optimization result; The production line efficiency evaluation module analyzes the deviation between the current actual production efficiency and the expected target based on the production operation optimization results, formulates matching improvement measures, and obtains the efficiency deviation adjustment strategy; The production cost optimization module uses a nonlinear programming method based on the efficiency deviation adjustment strategy and resource allocation plan to optimize the raw material procurement, energy consumption and manpower allocation costs to obtain a cost saving plan.
2. The industrial production intelligent scheduling system according to claim 1 is characterized in that: The future demand change trend includes the predicted product type demand, raw material procurement volume and expected market demand change trend; the resource allocation plan includes the number of allocated human resources, the operating time schedule of each machine and the allocation ratio of raw materials; the optimized production scheduling plan includes the execution sequence of multiple tasks, the scheduled completion time and the required resource list; the production operation optimization results include the adjusted process layout, equipment utilization optimization plan and human resource allocation strategy; the efficiency deviation adjustment strategy includes the identified production bottlenecks, recommended improvement measures and the expected efficiency improvement ratio; the cost saving plan includes energy consumption reduction strategy, raw material utilization efficiency improvement measures and labor cost optimization measures.
3. The industrial production intelligent scheduling system according to claim 1 is characterized in that: The task priority adjustment module includes: The urgency analysis submodule analyzes the delivery time and market demand urgency of production tasks based on the resource allocation plan and future demand change trends, and assigns a matching urgency level to each task in combination with the raw material arrival time and production capacity constraints to obtain a task urgency ranking table; The task importance assessment submodule analyzes the importance of each task on production efficiency, customer satisfaction and revenue based on the task urgency ranking table, and determines a matching importance score for each task based on market feedback and contract penalty risk. A priority list based on task influence is formulated through the score to obtain the task priority assessment result; The task sequencing submodule dynamically adjusts the execution order of multiple production tasks based on the task priority evaluation results, gives priority to key tasks, optimizes production efficiency and market response speed, and obtains an optimized production scheduling plan.
4. The industrial production intelligent scheduling system according to claim 1 is characterized in that: The production line balancing module includes: The production process analysis submodule analyzes multiple process flows on the production line based on the optimized production scheduling plan, including raw material input, semi-finished product processing and finished product assembly, identifies bottleneck links in the process, and obtains process bottleneck identification results; The equipment optimization configuration submodule uses mixed integer programming technology based on the process bottleneck identification results, combines the actual production capacity and the production equipment maintenance schedule, adjusts the configuration and use plan of the production equipment, optimizes the idle and waiting time of manpower and equipment, and obtains the production configuration adjustment plan; The process balance strategy submodule adjusts the human resources and equipment configuration of multiple production processes based on the production configuration adjustment plan, balances the workload of the production line, optimizes the connection of multiple processes, and obtains production operation optimization results.
5. The industrial production intelligent scheduling system according to claim 4 is characterized in that: The mixed integer programming technique is based on the formula: Calculate each equipment and usage time to get the production configuration adjustment plan, where Z is the production line operation cost, n is the total number of equipment on the production line, m is the total number of processes in the production process, and c i is the operating cost of the i-th device, x i is a binary variable that determines whether the i-th device is running, d j is the delay cost of the jth process, y j is the delay time of the jth process, k i is the energy efficiency coefficient of equipment i, f i is the energy consumption of device i within the target time, l j is the efficiency weight of process j, g j is the contribution of process j to the total production time.
6. The industrial production intelligent scheduling system according to claim 1 is characterized in that: The production line efficiency evaluation module includes: The production data monitoring submodule collects the operation data of the production line in real time based on the production operation optimization results, including the start and end time of each process, the operation status and output of the machine, integrates and analyzes the data, and obtains real-time status monitoring information; The efficiency analysis submodule evaluates the difference between the actual output and the planned output of the production line through statistical analysis based on the real-time status monitoring information, analyzes the key factors affecting production efficiency, including machine failure, raw material shortage and operation error, and obtains the efficiency deviation analysis results; The improvement measure proposal submodule formulates matching improvement measures based on the efficiency deviation analysis results, including adjusting the production plan, improving equipment maintenance and optimizing worker training, optimizing the overall efficiency and output quality of the production line, and obtaining an efficiency deviation adjustment strategy.
7. The industrial production intelligent scheduling system according to claim 1 is characterized in that: The production cost optimization module includes: The cost analysis submodule collects and analyzes multiple cost data in the production process, including raw materials, labor costs and manufacturing expenses, based on the efficiency deviation adjustment strategy and resource allocation plan, identifies cost components and key cost driving factors, and obtains cost component identification results; The cost reduction scheme submodule uses nonlinear programming methods based on the cost structure identification results to optimize the raw material procurement plan, energy utilization efficiency and improve worker efficiency, formulate matching cost reduction measures, and obtain a list of cost optimization measures; The cost control strategy submodule implements long-term cost control strategies based on the cost optimization measures list, including budget management improvements and cost saving measures promotion, formulates cost control strategies that match current production practices, and obtains cost saving plans.
8. The industrial production intelligent scheduling system according to claim 7 is characterized in that: The nonlinear programming method is according to the formula: Calculate the minimum total cost and get a list of cost optimization measures, where C is the total production cost, pi is the unit price of the i-th raw material, qi is the purchase volume of the i-th raw material, αi is the coefficient of change of raw material prices, e j is the unit consumption cost of the j-th energy, s j is the consumption of the jth energy source, β j is the energy efficiency coefficient, w k is the unit cost of the kth manual operation, h k is the number of hours of manual operation of the kth person, γ k is the labor efficiency improvement coefficient, n, m and l represent the number of raw material types, energy types and manual operation types respectively.
Citation Information
Cited By
Intelligent scheduling method for collaborative manufacturing of tunnel boring machines
CN119671136A
Intelligent scheduling method for tunnel boring machine collaborative manufacturing
CN119671136B
Circuit board production management system and method
CN119721558A
Customer order intelligent production scheduling system based on multi-source data analysis
CN119721609A
Large model production and operation management system and method of ERP (Enterprise Resource Planning) system
CN119809203A
