Scheduling calculation method of production plan scheduling platform

Abstract

The invention provides a production scheduling calculation method of a production plan scheduling platform. The method comprises the steps of data collection, demand prediction intelligent analysis, productivity planning and bottleneck analysis, production scheduling plan making, real-time monitoring and dynamic adjustment, plan execution and feedback analysis and report generation and decision support. Through distributed scheduling and real-time dynamic adjustment, the production plan can respond to emergencies such as equipment failure and order change in production in time, the continuity and stability of the production process can be ensured, production stagnation or delay caused by the emergencies is avoided, meanwhile, the production scheduling plan can be rapidly adjusted through real-time data feedback, and the production efficiency is improved. Resource utilization is optimized, waste is reduced, production efficiency is improved, intelligent productivity analysis and bottleneck identification are utilized, an enterprise can comprehensively know the use condition of each production resource, and possible bottleneck problems are found and solved in advance.

Description

Technical Field

[0001] The invention belongs to the technical field of production scheduling, and in particular relates to a production scheduling calculation method for a production planning and scheduling platform. Background Art

[0002] In the current manufacturing environment, with the rapid changes in market demand and the increasing diversification of consumer preferences, efficient and accurate production planning and scheduling have become an important part of corporate competitiveness. However, traditional production planning methods often rely on manual experience judgment and static data analysis, which leads to many challenges in the production process, such as the complexity and inefficiency of production scheduling calculations: in the face of large-scale, multi-variety, short-cycle production needs, traditional production scheduling calculations rely on manual compilation or simple software tools, which are difficult to quickly handle complex production constraints (such as equipment capacity, material supply, human resources, etc.), resulting in low production efficiency and insufficient optimization. In addition, the lack of support from intelligent tools makes it difficult for management to comprehensively consider multiple factors when making decisions, and it is difficult to make the best decision in a short time. Insufficient flexibility in dealing with emergencies: Equipment failures, order changes and other emergencies are often encountered during the production process. Traditional production planning and scheduling systems often lack sufficient flexibility and real-time response capabilities, and cannot quickly adjust production plans to cope with these changes. This will not only lead to production stagnation or delays, but may also cause resource waste and cost increases. Summary of the invention

[0003] 1. Technical issues to be resolved

[0004] The present invention proposes a production scheduling calculation method for a production planning and scheduling platform to solve the technical problem of how to improve flexibility and real-time response capability.

[0005] (II) Technical solution

[0006] In order to solve the above technical problems, the present invention proposes a production scheduling calculation method for a production planning and scheduling platform, which comprises the following steps:

[0007] S1. Data collection

[0008] Obtain order data from ERP and MES systems in real time through the cloud platform, collect the real-time status and availability of equipment, shift information of human resources, and production line capacity data, store the data in the cloud, and store the product production process, required equipment, and processing time information in the cloud platform database;

[0009] S2. Intelligent analysis of demand forecast

[0010] Use AI models to analyze historical order data using time series, predict future order demand, and determine short-term and long-term production targets;

[0011] S3. Capacity planning and bottleneck analysis

[0012] Analyze existing capacity utilization and identify bottleneck resources, and evaluate whether it is necessary to adjust production resource allocation or introduce temporary resources, analyze the availability of different production resources, and develop flexible production plans;

[0013] S4. Production planning

[0014] Based on the forecast demand, a linear programming model is used to perform preliminary production scheduling calculations on the cloud platform to generate a basic production scheduling plan. The preliminary production scheduling plan is optimized using a genetic algorithm, taking into account multiple objectives, including total production cost and total delay time, and weighing different constraints to generate the optimal production scheduling plan.

[0015] S5. Real-time monitoring and dynamic adjustment

[0016] Through cloud IoT devices, real-time collection of production progress, equipment status, and manual operation status is conducted to update the production execution status. Based on real-time data, distributed scheduling algorithms are used to adjust production schedules in the cloud in real time to handle equipment failures and emergency order emergencies.

[0017] S6. Plan execution and feedback analysis

[0018] Track the execution of production schedules in real time through the cloud platform, monitor key performance indicators (KPIs), analyze problems and deviations in production execution, generate improvement suggestions, and adjust parameters in future production scheduling models;

[0019] S7. Report generation and decision support: Generate production reports and performance analysis based on production execution and monitoring data, provide them to management for decision-making reference, analyze production line performance, equipment utilization, order delivery, and provide optimization suggestions, including equipment updates and resource allocation adjustment suggestions.

[0020] Furthermore, in step S1, the order data includes order information, delivery date, customer priority and historical order details.

[0021] Furthermore, in step S2, the AI ​​model is a time series prediction model, and the expression is:

[0022] Y t =φ 1 Y t-1 +φ 2 Y t-2 +...+φ p Y t-p +θ 1 ε t-1 +θ 2 ε t-2 +...+θq ε t-q +ε t

[0023] Among them, Y t is the demand or order quantity at time t; φ i is the autoregressive coefficient, which is used to describe the impact of historical data on current data; p is the order of the autoregressive term, which indicates the number of time steps to review; θ j is the moving average coefficient, which is used to describe the impact of previous forecast errors on current data; q is the order of the moving average term; ε t is white noise, indicating random error.

[0024] Furthermore, in step S3, the expression for analyzing the existing capacity utilization is:

[0025]

[0026] Among them, Ui is the capacity utilization rate of equipment i; Ti is the actual production time of equipment i; Ci is the total available capacity time of equipment i.

[0027] Furthermore, in step S3, the expression for identifying the bottleneck resource is:

[0028]

[0029] Among them, Bi is the bottleneck coefficient of resource i; Di is the production time required for resource i; Pi is the available production time of resource i.

[0030] Furthermore, in step S4, the expression of the linear programming model is:

[0031]

[0032] The constraints are:

[0033]

[0034] Where Ci is the cost or penalty coefficient or delay penalty for producing order i; Xi is the decision variable for whether to choose to produce order i, 0 or 1; Tij is the time that order i occupies on resource j; Cj is the total available time of resource j.

[0035] Furthermore, in step S4, the genetic algorithm is specifically:

[0036] f(x) = objective function value (total production cost, total delay time)

[0037] Among them, selection, crossover and mutation operations are:

[0038] Selection: select some individuals for reproduction according to the fitness function value;

[0039] Crossover: Genetically recombine the selected individuals to generate new individuals;

[0040] Mutation: Randomly change part of the genes of new individuals to increase population diversity.

[0041] Furthermore, in step S5, the distributed scheduling algorithm expression is:

[0042] ΔX=f(R,S,D)

[0043] Among them, ΔX is the adjustment amount of the production plan; R is the real-time resource status, including equipment failure and changes in resource availability; S is the current production schedule; and D is a new order or demand change.

[0044] Furthermore, in step S6, the KPI includes production cycle, equipment utilization rate and order completion rate.

[0045] Furthermore, in step S6, the calculation expression for monitoring the key performance indicator KPI is:

[0046]

[0047] Among them, KPIi is the achievement rate of the i-th key performance indicator; the actual value is the measured value in actual production, including the actual production cycle; the target value is the pre-set target value, including the planned production cycle.

[0048] (III) Beneficial effects

[0049] The present invention proposes a production scheduling calculation method for a production planning and scheduling platform, including data collection, demand forecasting intelligent analysis, capacity planning and bottleneck analysis, production scheduling plan formulation, real-time monitoring and dynamic adjustment, plan execution and feedback analysis, and report generation and decision support. Through distributed scheduling and real-time dynamic adjustment, the present invention can timely respond to emergencies in production, such as equipment failures, order changes, etc., and can ensure the continuity and stability of the production process, avoid production stagnation or delays caused by unexpected situations, and can quickly adjust the production scheduling plan through real-time data feedback, optimize resource utilization, reduce waste, and improve production efficiency. By using intelligent capacity analysis and bottleneck identification, enterprises can fully understand the use of various production resources and discover and solve possible bottleneck problems in advance.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] (1) The present invention combines cloud computing and AI technology. Through in-depth analysis and learning of historical data, the system can more accurately predict future order demand. Its accurate demand forecast can reduce the uncertainty in production plans, allowing enterprises to more reasonably arrange production resources and production capacity to avoid overproduction or resource shortages. At the same time, the use of linear programming models can quickly process a large number of complex production scheduling calculation tasks, helping management to make the best decision in a short time, thereby improving overall decision-making efficiency;

[0052] (2) Through distributed scheduling and real-time dynamic adjustment, the production plan of the present invention can respond to emergencies in production in a timely manner, such as equipment failure, order changes, etc., to ensure the continuity and stability of the production process and avoid production stagnation or delays due to unexpected situations. At the same time, the production schedule can be quickly adjusted through real-time data feedback to optimize resource utilization, reduce waste and improve production efficiency.

[0053] (3) The present invention utilizes intelligent capacity analysis and bottleneck identification, so that enterprises can fully understand the usage of various production resources, discover and solve possible bottleneck problems in advance, and through distributed scheduling algorithms, the system can better balance the load of production resources, reduce resource idle time, and maximize the utilization of equipment and manpower, which helps to reduce production costs and improve the profitability of the enterprise.

[0054] (4) Through real-time monitoring and KPI tracking, the present invention enables management to fully grasp the execution progress of the production plan and various key performance indicators. This transparency makes the production process more controllable, and the company can discover and solve problems in production at any time, reduce the risk of delivery delays, and improve customer satisfaction. At the same time, the automated report generation and intelligent feedback functions provide management with comprehensive decision-making support to help them better plan future production strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 The present invention is a flow chart of the production scheduling calculation method of the production planning and scheduling platform. DETAILED DESCRIPTION

[0056] In order to make the purpose, content and advantages of the present invention more clear, the specific implementation methods of the present invention are further described in detail below in conjunction with the drawings and examples.

[0057] The present invention proposes a production scheduling calculation method for a production planning and scheduling platform, the process of which is as follows: Figure 1 As shown, the specific steps include:

[0058] S1. Data collection

[0059] Obtain order data from ERP and MES systems in real time through the cloud platform, including order information, delivery date, customer priority, and historical order details, collect the real-time status and availability of equipment, shift information of human resources, and production line capacity data, store the data in the cloud for distributed access, and store the product's production process, required equipment, and processing time information in the cloud platform's database to ensure that all modules of the system share consistent information;

[0060] S2. Intelligent analysis of demand forecast

[0061] Through AI models, historical order data is analyzed using time series to predict future order demand, determine short-term and long-term production goals, simulate and verify demand forecast results multiple times, automatically adjust forecast parameters, and improve forecast accuracy;

[0062] The AI ​​model is a time series prediction model, namely the ARIMA model, and its expression is:

[0063] Y t =φ 1 Y t-1 +φ 2 Y t-2 +...+φ p Y t-p +θ 1 ε t-1 +θ 2 ε t-2 +...+θ q ε t-q +ε t

[0064] Among them, Y t is the demand or order quantity at time t; φ i is the autoregressive coefficient, which is used to describe the impact of historical data on current data; p is the order of the autoregressive term, which indicates the number of time steps to review; θ j is the moving average coefficient, which is used to describe the impact of previous forecast errors on current data; q is the order of the moving average term; ε t is white noise, indicating random error.

[0065] The ARIMA model is used to perform time series analysis on historical order data and predict future demand trends, which helps companies plan production resources in advance and reduce inventory backlogs and production bottlenecks.

[0066] S3. Capacity planning and bottleneck analysis

[0067] Analyze existing capacity utilization and identify bottleneck resources, and evaluate whether it is necessary to adjust production resource allocation or introduce temporary resources, such as overtime or outsourcing, analyze the availability of different production resources, and develop flexible production plans to ensure that demand fluctuations can be addressed;

[0068] The expression for analyzing the current capacity utilization is:

[0069]

[0070] Among them, Ui is the capacity utilization rate of equipment i; Ti is the actual production time of equipment i; Ci is the total available capacity time of equipment i.

[0071] The expression for identifying bottleneck resources is:

[0072]

[0073] Among them, Bi is the bottleneck coefficient of resource i; Di is the production time required for resource i; Pi is the available production time of resource i.

[0074] By calculating the bottleneck coefficient, the key resources that limit the overall efficiency in production can be identified. Bottleneck resources will be scheduled and optimized first to improve overall production capacity.

[0075] S4. Production planning

[0076] Based on the forecast demand, a linear programming model is used to perform preliminary production scheduling calculations on the cloud platform to generate a basic production scheduling plan. The preliminary production scheduling plan is optimized using a genetic algorithm, taking into account multiple objectives, including total production cost and total delay time, and weighing different constraints to automatically generate the optimal production scheduling plan.

[0077] The linear programming model is expressed as:

[0078]

[0079] The constraints are:

[0080]

[0081] Where Ci is the cost or penalty coefficient or delay penalty for producing order i; Xi is the decision variable for whether to choose to produce order i, 0 or 1; Tij is the time that order i occupies on resource j; Cj is the total available time of resource j.

[0082] The linear programming model is used to optimize production scheduling, determine the optimal production plan under multiple constraints, maximize corporate profits or minimize costs, and is suitable for scheduling multiple orders and multiple resources in complex production environments.

[0083] The genetic algorithm is specifically:

[0084] f(x) = objective function value (total production cost, total delay time)

[0085] Among them, selection, crossover and mutation operations are:

[0086] Selection: select some individuals for reproduction according to the fitness function value;

[0087] Crossover: Genetically recombine the selected individuals to generate new individuals;

[0088] Mutation: Randomly change part of the genes of new individuals to increase population diversity.

[0089] Genetic algorithms search for the optimal solution to production scheduling problems by simulating the biological evolution process. They are suitable for solving large and complex combinatorial optimization problems, including multi-objective production scheduling.

[0090] S5. Real-time monitoring and dynamic adjustment

[0091] Through cloud IoT devices, real-time collection of production progress, equipment status, and manual operation status is carried out to update the production execution status. Based on real-time data, distributed scheduling algorithms are used to adjust production schedules in real time on the cloud to handle equipment failures and emergency order emergencies, ensuring the continuity and stability of the production process.

[0092] The expression of distributed scheduling algorithm is:

[0093] ΔX=f(R,S,D)

[0094] Among them, ΔX is the adjustment amount of the production plan; R is the real-time resource status, including equipment failure and changes in resource availability; S is the current production schedule; and D is a new order or demand change.

[0095] The real-time dynamic scheduling model is used to make real-time adjustments to the production plan based on changes in actual production, including equipment failures or order changes, to ensure production continuity and flexibility.

[0096] S6. Plan execution and feedback analysis

[0097] Track the execution of production schedules in real time through the cloud platform, monitor key performance indicators (KPIs), including production cycle, equipment utilization, and order completion rate, analyze problems and deviations in production execution, generate improvement suggestions, and automatically adjust parameters in future production scheduling models to improve the accuracy and efficiency of subsequent production scheduling;

[0098] The calculation expression for monitoring key performance indicators KPI is:

[0099]

[0100] Among them, KPIi is the achievement rate of the i-th key performance indicator; the actual value is the measured value in actual production, including the actual production cycle; the target value is the pre-set target value, including the planned production cycle.

[0101] KPI is used to evaluate the execution effect of production scheduling. By comparing the differences between actual production and targets, enterprises can identify problems and optimize the system.

[0102] S7. Report generation and decision support: Automatically generate production reports and performance analysis based on production execution and monitoring data, provide them to management for decision-making reference, analyze production line performance, equipment utilization, and order delivery, and provide optimization suggestions to management, including equipment updates and resource allocation adjustment suggestions.

[0103] As can be seen from the above, by combining cloud computing and AI technology, through in-depth analysis and learning of historical data, the system can more accurately predict future order demand. Its accurate demand forecast reduces uncertainty in production plans, enabling enterprises to arrange production resources and production capacity more reasonably, and avoid overproduction or resource shortages. At the same time, the use of linear programming models can quickly process a large number of complex production scheduling calculation tasks, helping management to make the best decision in a short time, thereby improving overall decision-making efficiency; through distributed scheduling and real-time dynamic adjustment, production plans can respond to emergencies in production in a timely manner, such as equipment failures, order changes, etc., to ensure the continuity and stability of the production process, and avoid production stagnation or delays caused by unexpected situations. At the same time, through real-time data feedback, production scheduling plans can be quickly adjusted to optimize resource utilization, reduce waste, and improve production efficiency.

[0104] The following is a specific implementation example of a production scheduling calculation method for a production planning and scheduling platform, which is used to demonstrate how to use the above method to optimize the production plan of a manufacturing enterprise.

[0105] 1. Data collection and system initialization

[0106] Background information:

[0107] Business Type: A manufacturer of high-end home appliances.

[0108] Main products: refrigerators, washing machines, air conditioners.

[0109] Production equipment: 5 production lines, each of which can produce all types of products.

[0110] Human Resources: 3 shifts, 8 hours per shift, 20 workers per production line.

[0111] Data collected:

[0112] Order Information:

[0113] Order 1: Produce 1,000 refrigerators, with a delivery date of 10 days.

[0114] Order 2: Produce 1,500 washing machines, with a delivery date of 8 days.

[0115] Order 3: Produce 2,000 air conditioners, with a delivery date of 12 days.

[0116] Device information:

[0117] The availability of each production line is 95%.

[0118] Hourly production capacity of each device:

[0119] Refrigerator: 20 units / hour;

[0120] Washing machines: 25 units / hour;

[0121] Air conditioning: 15 units / hour;

[0122] Historical data: order records and production progress data for the past 6 months.

[0123] 2. Demand forecasting and intelligent analysis

[0124] Demand Forecast Implementation:

[0125] Historical order data: average monthly order volume within 6 months.

[0126] Forecasting model: Use the ARIMA model to forecast the order volume for the next 30 days. ARIMA model application:

[0127] Order 1 (Refrigerator): Y t =0.5Y t-1 +0.3Y t-2 +ε t

[0128] Forecast result: There is expected to be a demand for 500 refrigerators in the next 10 days.

[0129] Order 2 (washing machine): Y t =0.6Y t-1 +0.2Y t-2 +ε t

[0130] Forecast result: It is estimated that there will be a demand for 800 washing machines in the next 10 days.

[0131] Order 3 (air conditioning): Y t =0.7Y t-1 +0.1Y t-2 +ε t

[0132] Forecast result: It is estimated that there will be a demand for 1,000 air conditioners in the next 10 days.

[0133] 3. Capacity planning and bottleneck analysis

[0134] Capacity calculation:

[0135] Each production line runs 24 hours a day, and the maximum daily production capacity of each production line is: refrigerators: 480 units / day (20 units / hour × 24 hours);

[0136] Washing machines: 600 units / day (25 units / hour x 24 hours);

[0137] Air conditioning: 360 units / day (15 units / hour x 24 hours);

[0138] Bottleneck analysis:

[0139] According to order demand, washing machines have a larger production volume and the highest equipment utilization, so they may become a bottleneck.

[0140] Bottleneck coefficient calculation:

[0141] Refrigerator production: 1000 / 480 = 2.08 days;

[0142] Washing machine production: 1500 / 600 = 2.5 days;

[0143] Air conditioning production: 2000 / 360 = 5.56 days;

[0144] The production lines for the above-mentioned washing machines and air conditioners have high utilization rates and may become bottlenecks.

[0145] 4. Production planning

[0146] Initial production schedule:

[0147] Use the linear programming model to calculate the optimal production schedule:

[0148] Objective function:

[0149] min(C1X1+C2X2+C3X3)

[0150] Among them, C1=10 (production cost of refrigerator), C2=8 (production cost of washing machine), and C3=12 (production cost of air conditioner).

[0151] Constraints:

[0152]

[0153] X1 is the production time of refrigerator; X2 is the production time of washing machine; X3 is the production time of air conditioner.

[0154] Optimization results:

[0155] Refrigerator production is arranged on production lines 1, 2 and 3, and takes a total of 2.08 days to complete.

[0156] The production of washing machines is scheduled on production lines 4 and 5, and takes a total of 2.5 days to complete.

[0157] Air conditioning production is scheduled on all production lines and will take a total of 5.56 days to complete.

[0158] 5. Real-time monitoring and dynamic adjustment

[0159] Real-time scheduling implementation:

[0160] Use IoT devices to monitor the progress and equipment status of the production line in real time.

[0161] It is found that the demand for washing machines in order 2 increases to 2,000 units. The dynamic adjustment model is used:

[0162] ΔX=f(R,S,D)

[0163] Based on real-time monitoring data, the production plan was adjusted to transfer part of the refrigerator production tasks to Line 3, where equipment utilization rate was lower.

[0164] Adjusted production schedule:

[0165] Refrigerator production is arranged on production lines 1 and 3, and takes a total of 2.5 days to complete.

[0166] The production of washing machines is arranged on production lines 2, 4 and 5, and takes a total of 3.33 days to complete.

[0167] Air conditioning production remained unchanged, completing in 5.56 days.

[0168] 6. Plan execution and feedback analysis

[0169] KPI monitoring:

[0170] KPI calculation:

[0171] Equipment utilization rate: 95% (efficient utilization)

[0172] 100% on-time order completion rate

[0173] Average production cycle: 4 days (in line with expectations)

[0174] Feedback analysis: Through the operation data of the AI ​​analysis system, it is found that the production demand for washing machines fluctuates greatly, so it is possible to consider adding temporary workers or overtime in the future.

[0175] 7. Report generation and system optimization

[0176] Automated reporting:

[0177] The generated report shows:

[0178] All orders were delivered on time.

[0179] The average production line utilization rate reached 95%.

[0180] There were no major equipment failures.

[0181] According to the report's recommendations, the production scheduling strategy for washing machines will be adjusted in the future, and a certain amount of production capacity will be reserved in advance to cope with demand fluctuations.

[0182] From the above, we can see that through systematic and intelligent production planning and scheduling, enterprises can significantly improve production efficiency and shorten product production cycles, which enables enterprises to respond more quickly to changes in market demand, shorten delivery time, and improve market competitiveness. At the same time, optimized production plans reduce unnecessary inventory backlogs, reduce capital occupation, and improve the company's capital turnover efficiency.

[0183] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A production scheduling calculation method for a production planning and scheduling platform, characterized in that: The production scheduling calculation method comprises the following steps: S1. Data collection Obtain order data from ERP and MES systems in real time through the cloud platform, collect the real-time status and availability of equipment, shift information of human resources, and production line capacity data, store the data in the cloud, and store the product production process, required equipment, and processing time information in the cloud platform database; S2. Intelligent analysis of demand forecast Use AI models to analyze historical order data using time series, predict future order demand, and determine short-term and long-term production targets; S3. Capacity planning and bottleneck analysis Analyze existing capacity utilization and identify bottleneck resources, and evaluate whether it is necessary to adjust production resource allocation or introduce temporary resources, analyze the availability of different production resources, and develop flexible production plans; S4. Production planning Based on the forecast demand, a linear programming model is used to perform preliminary production scheduling calculations on the cloud platform to generate a basic production scheduling plan. The preliminary production scheduling plan is optimized using a genetic algorithm, taking into account multiple objectives, including total production cost and total delay time, and weighing different constraints to generate the optimal production scheduling plan. S5. Real-time monitoring and dynamic adjustment Through cloud IoT devices, real-time collection of production progress, equipment status, and manual operation status is conducted to update the production execution status. Based on real-time data, distributed scheduling algorithms are used to adjust production schedules in the cloud in real time to handle equipment failures and emergency order emergencies. S6. Plan execution and feedback analysis Track the execution of production schedules in real time through the cloud platform, monitor key performance indicators (KPIs), analyze problems and deviations in production execution, generate improvement suggestions, and adjust parameters in future production scheduling models; S7. Report generation and decision support: Generate production reports and performance analysis based on production execution and monitoring data, provide them to management for decision-making reference, analyze production line performance, equipment utilization, order delivery, and provide optimization suggestions, including strategic suggestions for equipment updates and resource allocation adjustments.

2. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S1, the order data includes order information, delivery date, customer priority and historical order details.

3. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S2, the AI ​​model is a time series prediction model, and the expression is: Y t =φ1Y t-1 +φ2Y t-2 +...+φ p Y t-p +θ1ε t-1 +θ2ε t-2 +...+θ q e t-q +e t Among them, Y t is the demand or order quantity at time t; φ i is the autoregressive coefficient, which is used to describe the impact of historical data on current data; p is the order of the autoregressive term, which indicates the number of time steps to review; θ j is the moving average coefficient, which is used to describe the impact of previous forecast errors on current data; q is the order of the moving average term; ε t is white noise, indicating random error.

4. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S3, the expression for analyzing the existing capacity utilization is: Among them, Ui is the capacity utilization rate of equipment i; Ti is the actual production time of equipment i; Ci is the total available capacity time of equipment i.

5. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S3, the expression for identifying bottleneck resources is: Among them, Bi is the bottleneck coefficient of resource i; Di is the production time required for resource i; Pi is the available production time of resource i.

6. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S4, the expression of the linear programming model is: The constraints are: Where Ci is the cost or penalty coefficient or delay penalty for producing order i; Xi is the decision variable for whether to choose to produce order i, 0 or 1; Tij is the time that order i occupies on resource j; Cj is the total available time of resource j.

7. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S4, the genetic algorithm is specifically: f(x) = objective function value (total production cost, total delay time) Among them, selection, crossover and mutation operations are: Selection: select some individuals for reproduction according to the fitness function value; Crossover: Genetically recombine the selected individuals to generate new individuals; Mutation: Randomly change part of the genes of new individuals to increase population diversity.

8. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S5, the distributed scheduling algorithm expression is: ΔX=f(R,S,D) Among them, ΔX is the adjustment amount of the production plan; R is the real-time resource status, including equipment failure and changes in resource availability; S is the current production schedule; and D is a new order or demand change.

9. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S6, the KPIs include production cycle, equipment utilization and order completion rate.

10. The production scheduling calculation method of the production planning and scheduling platform according to claim 1, characterized in that: In step S6, the calculation expression for monitoring the key performance indicator KPI is: Among them, KPIi is the achievement rate of the i-th key performance indicator; the actual value is the measured value in actual production, including the actual production cycle; the target value is the pre-set target value, including the planned production cycle.

Images