Intelligent scheduling method for intelligent manufacturing digital workshop

Through the intelligent scheduling method of the digital workshop of intelligent manufacturing, combined with sensor network and reinforcement learning algorithm, the optimal production switching scheduling strategy and resource allocation plan are generated, which solves the problems of low production scheduling efficiency and resource waste, and improves production efficiency and system flexibility sex.

CN118938835AInactive Publication Date: 2024-11-12YANSHAN UNIV
View PDF 0 Cites 11 Cited by

Patent Information

Application Number
CN202411124071.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

When facing complex production environments and changing production tasks, the existing production scheduling methods have problems such as inefficiency, waste of resources and untimely response, especially in the low production switching efficiency, lack of intelligence in scheduling strategies and resource management. Incomplete situations.

Method used

A smart scheduling method for intelligent manufacturing digital workshops is proposed, combining sensor network and data through production task analysis, equipment status evaluation, process parameter preset, intelligent scheduling strategy generation, switching process optimization, switching execution and dynamic resource allocation. Acquisition units, reinforcement learning algorithms and Internet of Things technology to generate the optimal production switching scheduling strategy and resource allocation plan.

Benefits of technology

It significantly improves production efficiency, ensures the rationality of equipment scheduling order and resource allocation, reduces production switching time and resource waste, improves the continuity and stability of the production process, enhances the flexibility and adaptability of the production system, and improves the The competitiveness of the enterprise and the speed of market response.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938835A_ABST
    Figure CN118938835A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of workshop scheduling management, in particular to an intelligent scheduling method for an intelligent manufacturing digital workshop, which comprises the following steps of: establishing a task priority model to determine a priority sequence of production switching; establishing an equipment state database to provide data support for production switching; the method comprises the following steps: presetting process parameters of equipment according to process requirements of a to-be-switched task; generating an optimal production switching scheduling strategy by using an intelligent scheduling algorithm; a standardized production switching process is designed; issuing the generated switching scheduling strategy to each production unit; and after production switching, resource allocation is dynamically adjusted again according to actual requirements, so that smooth production switching is ensured. According to the invention, by combining the production switching scheduling strategy and the dynamic resource allocation strategy, the production efficiency is obviously improved, and the generated optimal production switching scheduling strategy ensures the reasonability of the equipment scheduling sequence and the resource allocation scheme.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of workshop scheduling management, and in particular to a smart scheduling method for a smart manufacturing digital workshop. Background Art

[0002] With the rapid development of intelligent manufacturing technology, digital workshops are increasingly being used in industrial production. However, existing production scheduling methods often suffer from problems such as low efficiency, waste of resources, and untimely response when faced with complex production environments and changing production tasks. These problems are mainly reflected in the following aspects:

[0003] Low production switching efficiency: In the multi-variety and small-batch production mode, the frequent switching of production tasks puts higher requirements on production efficiency. The existing methods often lack standardized processes in the production switching process and cannot quickly and efficiently complete the switching of production tasks.

[0004] Lack of intelligence in scheduling strategies: Traditional production scheduling methods mostly rely on fixed scheduling algorithms and manual experience, and are unable to flexibly respond to changes in different production tasks and production environments, resulting in low scheduling efficiency and unreasonable resource allocation.

[0005] Imperfect resource management: The existing scheduling system lacks effective analysis and utilization of the large amount of data generated during the production process, especially in the real-time monitoring and dynamic allocation of resources, resulting in waste of resources and increased production costs. Summary of the invention

[0006] Based on the above objectives, the present invention provides a smart scheduling method for smart manufacturing digital workshops.

[0007] A smart scheduling method for a smart manufacturing digital workshop includes the following steps:

[0008] S1, production task analysis: analyze the current and to-be-switched production tasks, obtain the production requirements, resource requirements and process parameters of each task, and establish a task priority model to determine the priority order of production switching;

[0009] S2, equipment status assessment: through the sensor network and data acquisition unit, the status of production equipment in the workshop is monitored in real time, including the operating status, maintenance status and availability of the equipment, and an equipment status database is established to provide data support for production switching;

[0010] S3, process parameter preset: according to the process requirements of the task to be switched, the process parameters of the equipment are pre-set, and the parameters are checked before production switching to ensure that the equipment can meet the process requirements after switching;

[0011] S4, intelligent scheduling strategy generation: Combined with the production task analysis and equipment status assessment results, the intelligent scheduling algorithm is used to generate the optimal production switching scheduling strategy to ensure the optimization of equipment utilization and resource allocation during the production switching process;

[0012] S5, switching process optimization: design a standardized production switching process, including the end of production tasks, equipment cleaning, process parameter adjustment and new task start-up;

[0013] S6, switching execution: Send the generated switching scheduling strategy to each production unit and monitor the switching execution;

[0014] S7, dynamic resource allocation: After production switching, real-time monitoring of resource usage, including raw materials, energy, and labor, and dynamic adjustment of resource allocation again according to actual needs to ensure smooth production switching.

[0015] Optionally, the task priority model is established in S1 to determine the priority order of production switching, specifically including:

[0016] S11, task information collection: obtaining detailed information of current and pending production tasks from the production management system (MES) and enterprise resource planning system (ERP), including task name, task type, task priority, planned start time and end time;

[0017] S12, process parameter extraction: extract the process parameters of each production task, including the process configuration of the required equipment, production process steps, and process parameters;

[0018] S13, Resource Requirements Analysis: Analyze the resource requirements of each production task to obtain the types, quantities, and distribution of required raw materials, energy, labor, equipment, and tools;

[0019] S14, task relevance analysis: Analyze the relevance between the current and to-be-switched production tasks, including the dependencies between tasks, the usage of shared resources, and the similarities of process steps, to identify conflicts and coordination points;

[0020] S15, task priority model establishment:

[0021] Establish a task priority model based on task urgency, customer demand, production schedule, and resource availability factors;

[0022] Use the multi-factor weight analysis method to assign weight values ​​to each factor and calculate the priority score of each production task;

[0023] Combined with the results of task relevance analysis, the priority score is adjusted to ensure that the priority model can truly reflect the actual urgency and importance of the task;

[0024] The priority model is expressed as:

[0025] P i =w1×U i +w2×D i +w3×R i +w4×C i , where P i is the priority score of production task i, U i Score the urgency of production task i, D i Score the customer demand for production task i, R i Score the resource availability of production task i, C i is the task relevance score of production task i, w1, w2, W3, W4 are the weight values ​​of each factor, satisfying w1+w2+w3+w4=1;

[0026] S16, priority order determination: according to the calculation result of the priority model, all current and to-be-switched production tasks are sorted to determine the priority order of production switching.

[0027] Optionally, establishing a device status database in S2 specifically includes:

[0028] S21, sensor network deployment: install a variety of sensors at key locations of production equipment, including temperature sensors, pressure sensors, vibration sensors, and current sensors, to monitor equipment operating status parameters;

[0029] S22, data acquisition unit setting: a data acquisition unit is set up in the workshop to collect real-time data from various sensors and transmit the data to the central control unit through a wireless network. The central control unit performs data normalization processing on the collected equipment status data to ensure the accuracy and consistency of the data;

[0030] S23, equipment status monitoring:

[0031] Operation status monitoring: Real-time monitoring of the equipment's operation status parameters, including temperature, pressure, vibration, and current, etc., using preset thresholds and rules to determine whether the equipment's operation status is normal, and scoring the equipment's current operation status;

[0032] Maintenance status monitoring: record the maintenance history of the equipment, including maintenance time, maintenance content, maintenance personnel and maintenance result information, evaluate the maintenance status of the equipment, and score the maintenance status of the equipment;

[0033] Availability monitoring: Calculate the availability score of the equipment based on the operation status score and maintenance history score, set a threshold to determine whether the equipment is available, and identify whether the current equipment can be used for production tasks;

[0034] S24, equipment status database establishment: the processed equipment status data is stored in the equipment status database, including the real-time status data, historical maintenance data and availability data of the equipment, to provide data support for production switching.

[0035] Optionally, the process parameter preset in S3 includes:

[0036] S31, process requirement acquisition: obtaining detailed process requirements of the task to be switched from the production management system, including temperature, pressure, and operating speed process parameters;

[0037] S32, process parameter presetting: presetting various process parameters of the equipment according to the process requirements of the task to be switched, including temperature parameters, pressure parameters, and operating speed;

[0038] S33, process parameter verification: before production switching, the preset process parameters are verified to ensure that each parameter can quickly reach the target value after the equipment is switched;

[0039] Monitor the changes of various process parameters in real time through the sensor network and record the current parameter values;

[0040] S34, calculating the deviation values ​​ΔT, ΔP, ΔV of each parameter;

[0041] S35, parameter adjustment and optimization: According to the deviation values ​​ΔT, ΔP, ΔV, adjust the process parameter control system of the equipment to ensure that each parameter reaches the target value.

[0042] Optionally, the generation of the intelligent scheduling strategy in S4 specifically includes:

[0043] S41, integration of production task and equipment status data: integrating the task priority model obtained from the production task analysis and the equipment status database established in the equipment status assessment to form a comprehensive data set;

[0044] S42, objective function definition: Based on production demand and resource utilization objectives, define the optimization objective function, which includes the following:

[0045] Maximize equipment utilization: Improve equipment utilization by maximizing equipment operating time and reducing equipment idle time;

[0046] Optimize resource allocation: Rationally allocate raw materials, energy and labor resources, reduce resource waste and improve resource utilization efficiency;

[0047] Minimize production cycle: shorten production switching time and minimize production cycle by optimizing scheduling strategies;

[0048] S43, constraint setting: according to the process requirements and equipment status of the production task, set the constraints that need to be met in the scheduling process, including equipment capacity, resource limitations and production task priority.

[0049] S44, generation of scheduling strategy based on reinforcement learning: using reinforcement learning algorithm, through interactive learning of production tasks and equipment status data, gradually optimize the scheduling strategy. In the training process, introduce reward mechanism, give rewards according to the optimization of equipment utilization, resource utilization and production cycle, and gradually guide the algorithm to the optimal solution;

[0050] S45, initialization and training: Initialize the scheduling algorithm according to the comprehensive data set, set the initial policy network parameters, expressed as: θ0 = random_initialization, where θ0 is the initial policy network parameter, random_initialization is random initialization, the training process includes simulating the production task switching process in a virtual simulation environment, and continuously adjusting the scheduling policy network parameters through the reinforcement learning algorithm. Through multiple rounds of training, the policy network parameters are optimized to improve the effectiveness of the scheduling strategy. The update of the policy network parameters is expressed as: Among them, θ t is the policy network parameter of the tth round, α is the learning rate, is the gradient of the reward function in round t;

[0051] S46, apply the trained scheduling strategy to the actual production environment, conduct small-scale verification, verify the feasibility and effectiveness of the strategy, and update the strategy network parameters for the second time based on the verification results:

[0052] θ new =θ current +β·Δθ, where θ new is the updated policy network parameter, θ current is the current strategy network parameter, β is the adjustment coefficient, and Δθ is the adjustment amount;

[0053] S47, after training and verification, outputs the optimal production switching scheduling strategy, including detailed equipment scheduling sequence, resource allocation plan and production switching plan.

[0054] Optionally, the objective function definition includes:

[0055] Maximize equipment utilization: Among them, U i is the running time of device i, T is the total scheduling time, and N is the total number of devices;

[0056] Optimizing resource allocation: Among them, R jis the usage of resource j, M is the total number of resources;

[0057] Minimize production cycle: min(T cycle ), where T cycle is the production cycle time;

[0058] The constraint definition includes:

[0059] Equipment capacity constraints: the maximum processing capacity and load of each equipment;

[0060] Resource constraints: the available quantity and allocation limits of each resource;

[0061] Production task priority constraint: Determine the priority of tasks based on the priority model.

[0062] Optionally, a reward mechanism is introduced into the reinforcement learning algorithm, and rewards are given according to the optimization of equipment utilization, resource utilization and production cycle, so as to gradually guide the algorithm to approach the optimal solution, which is expressed as:

[0063] Among them, R is the reward value, w5, w6, w7 are the weight coefficients of each optimization target.

[0064] Optionally, the standardized production switching process designed in S5 specifically includes:

[0065] S51, end of production task: after the current production task is completed, a task completion signal is sent through the production management system (MES), the end time and status of the current production task are recorded, and it is confirmed that all production steps have been completed, the product quality inspection is qualified, and the production task is officially ended;

[0066] S52, Equipment Cleaning:

[0067] Start the equipment cleaning process according to the equipment's process requirements and cleaning specifications;

[0068] Use automated cleaning equipment or manual cleaning to ensure thoroughness and consistency of cleaning;

[0069] During the cleaning process, the cleaning parameters are monitored in real time, including cleaning time, cleaning liquid concentration and temperature, to ensure the cleaning effect. After cleaning, the equipment is dried to ensure that there is no residual cleaning liquid and impurities in the equipment.

[0070] S53, process parameter adjustment: obtain the process parameter requirements of the new task, including temperature, pressure, and operating speed, and set new process parameters according to the deviation values ​​ΔT, ΔP, and ΔV of each parameter to ensure that each parameter reaches the target value;

[0071] S54, new task start: after the process parameters are adjusted and verified, a new production task is started, the start instruction of the new task is issued through the production management system (MES), and the start time and status of the new task are recorded.

[0072] Optionally, S6 also includes obtaining the generated production switching scheduling strategy, including equipment scheduling sequence, resource allocation plan, and production switching process, and issuing the comprehensive scheduling plan to each production unit through the production management system (MES). The scheduling strategy issued includes equipment scheduling instructions, resource allocation instructions, and production switching process instructions to ensure that each production unit can accurately execute the scheduling strategy.

[0073] Optionally, the dynamic resource allocation in S7 specifically includes:

[0074] S71, real-time monitoring of resource usage:

[0075] Raw material monitoring: Through IoT sensors and RFID technology, real-time monitoring of the use of raw materials in the production process, recording the inventory, consumption rate and replenishment status of raw materials;

[0076] Energy monitoring: Through smart meters and workshop energy consumption monitoring systems, the energy consumption of production equipment is monitored in real time, including the usage of electricity, gas and water resources, and the consumption rate and remaining amount of various energy sources are recorded;

[0077] Labor monitoring: Through the workshop time management system and RFID cards, the working status, working hours and task progress of production personnel are monitored in real time, and the distribution and utilization efficiency of labor are recorded;

[0078] S72, resource demand prediction: Based on the process parameters of the production task after switching and the real-time monitoring data, the demand for various resources after production switching is predicted. The prediction is expressed as:

[0079]

[0080] Among them, D material (t),D energy (t) and D labor (t) are raw materials, energy and labor at time t respectively;

[0081] S73, dynamic resource allocation: dynamically adjust the allocation of various resources based on real-time monitoring data and prediction results. The dynamic adjustment is expressed as:

[0082] A material (t)=max(0,min(S material -D material (t), I material ));

[0083] A energy (t)=max(0,min(S energy -D eneray (t),I energy ));

[0084] A labor (t)=max(0,min(S labor -D labor (t),I labor ));

[0085] Among them, A material (t), A energy (t) and A labor (t) are the raw materials, energy and labor allocation at time t, S material , S energy and S labor are the current inventory or available quantity, I material ,I energy and I labor are the amounts replenished during the replenishment interval, respectively.

[0086] Beneficial effects of the present invention:

[0087] The present invention significantly improves production efficiency by combining production switching scheduling strategy with dynamic resource allocation strategy. The generated optimal production switching scheduling strategy ensures the rationality of equipment scheduling sequence and resource allocation plan, and is accurately issued to each production unit through the MES system. Combined with the dynamic resource allocation strategy, during the production switching process, resource usage is further monitored in real time, resource demand is predicted, resource allocation is dynamically adjusted, and the timeliness and accuracy of resource supply are ensured, which effectively reduces production switching time and resource waste, and improves the continuity and stability of the production process.

[0088] The present invention utilizes a dynamic resource allocation strategy to monitor the usage of raw materials, energy, and labor in real time through IoT sensors and monitoring systems. Based on real-time data and prediction results, the resource allocation plan is dynamically adjusted to ensure the rational use of resources. In particular, during the handling of abnormal situations, early warnings can be issued in a timely manner and the optimal production switching scheduling strategy can be automatically adjusted to avoid resource waste and production delays, thereby optimizing the overall utilization efficiency of resources and improving the economic benefits of the production process.

[0089] The present invention combines an intelligent scheduling algorithm based on reinforcement learning to make the production scheduling system highly flexible and adaptable. It not only improves the intelligence level of the production system, but also accumulates a large amount of production data, providing valuable data support and experience accumulation for subsequent scheduling optimization, so that the production system can maintain efficient operation in a complex and changeable production environment, significantly improving the competitiveness and market response speed of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0091] Figure 1 A schematic diagram of a scheduling method flow chart of an embodiment of the present invention;

[0092] Figure 2 A schematic diagram of the intelligent scheduling strategy generation process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0093] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0094] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0095] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0096] like Figure 1-Figure 2 As shown, a smart scheduling method for a smart manufacturing digital workshop includes the following steps:

[0097] S1, production task analysis: analyze the current and to-be-switched production tasks, obtain the production requirements, resource requirements and process parameters of each task, and establish a task priority model to determine the priority order of production switching;

[0098] S2, equipment status assessment: through the sensor network and data acquisition unit, the status of production equipment in the workshop is monitored in real time, including the operating status, maintenance status and availability of the equipment, and an equipment status database is established to provide data support for production switching;

[0099] S3, process parameter preset: according to the process requirements of the task to be switched, the process parameters of the equipment are pre-set, including temperature, pressure, and operating speed, and parameter verification is performed before production switching to ensure that the equipment can quickly meet the process requirements after switching;

[0100] S4, intelligent scheduling strategy generation: Combined with the production task analysis and equipment status assessment results, the intelligent scheduling algorithm is used to generate the optimal production switching scheduling strategy to ensure the optimization of equipment utilization and resource allocation during the production switching process;

[0101] S5, switching process optimization: design a standardized production switching process, including the end of production tasks, equipment cleaning, process parameter adjustment and new task start-up;

[0102] S6, switching execution: Send the generated switching scheduling strategy to each production unit and monitor the switching execution;

[0103] S7, dynamic resource allocation: After production switching, real-time monitoring of resource usage, including raw materials, energy, and labor, and dynamic adjustment of resource allocation again according to actual needs to ensure smooth production switching.

[0104] In S1, a task priority model is established to determine the priority order of production switching, including:

[0105] S11, task information collection: obtaining detailed information of current and pending production tasks from the production management system (MES) and enterprise resource planning system (ERP), including task name, task type, task priority, planned start time and end time;

[0106] S12, process parameter extraction: extract the process parameters of each production task, including the process configuration of the required equipment, production process steps, and process parameters (such as temperature, pressure, and speed);

[0107] S13, Resource Requirements Analysis: Analyze the resource requirements of each production task to obtain the types, quantities, and distribution of required raw materials, energy, labor, equipment, and tools;

[0108] S14, task relevance analysis: Analyze the relevance between the current and to-be-switched production tasks, including the dependencies between tasks, the usage of shared resources, and the similarity of process steps, to identify possible conflicts and coordination points;

[0109] S15, task priority model establishment:

[0110] Establish a task priority model based on task urgency, customer demand, production schedule, and resource availability factors;

[0111] Use the multi-factor weight analysis method to assign weight values ​​to each factor and calculate the priority score of each production task;

[0112] Combined with the results of task relevance analysis, the priority score is adjusted to ensure that the priority model can truly reflect the actual urgency and importance of the task;

[0113] The priority model is expressed as:

[0114] P i =w1×U i +w2×D i +w3×R i +w4×C i , where P i is the priority score of production task i, U i Score the urgency of production task i, D i Score the customer demand for production task i, R i Score the resource availability of production task i, C i is the task relevance score of production task i, w1, w2, w3, w4 are the weight values ​​of each factor, satisfying w1+w2+w3+w4=1;

[0115] Specific:

[0116] 1. Urgency score U i : Based on the planned start and end time of the production task, the higher the urgency score, the higher the priority;

[0117] Calculation method: Set the urgency rating range from 1 to 10. The closer to the current time, the higher the rating: Among them, T current is the current time, T start is the planned start time of the production task, T end The planned end time of the production task;

[0118] 2. Customer demand score D i : Score customer needs based on their importance and urgency;

[0119] Calculation method: Set the customer demand score range from 1 to 10, determined by the importance and urgency of the customer demand: Among them, D importance Rate the importance of customer needs on a scale of 1 to 10. urgency Rate the urgency of the customer's request on a scale of 1 to 10.

[0120] 3. Resource availability score R i : Scoring based on the availability of resources required for production tasks;

[0121] Calculation method: Set the resource availability score range from 1 to 10. The more abundant the resources, the higher the score: Among them, R material Rating of raw material availability on a scale of 1 to 10, R energy Rating energy availability on a scale of 1 to 10, R labor Rate the availability of labor on a scale of 1 to 10, R equipment Rate the device usability on a scale of 1 to 10.

[0122] 4. Task relevance score C i : Score based on the correlation between the current and to-be-switched production tasks;

[0123] Calculation method: Set the task relevance score range from 1 to 10. The higher the relevance, the higher the score: Among them, C dependency Score task dependencies on a scale of 1 to 10. shared_eresources Score the shared resource usage on a scale of 1 to 10. process_similarity Score the process step similarity on a scale of 1 to 10.

[0124] S16, priority order determination: according to the calculation result of the priority model, all current and to-be-switched production tasks are sorted to determine the priority order of production switching.

[0125] The establishment of the device status database in S2 specifically includes:

[0126] S21, sensor network deployment: install a variety of sensors at key locations of production equipment, including temperature sensors, pressure sensors, vibration sensors, and current sensors, to monitor equipment operating status parameters;

[0127] S22, data acquisition unit setting: a data acquisition unit is set up in the workshop to collect real-time data from various sensors and transmit the data to the central control unit through a wireless network. The central control unit performs data normalization processing on the collected equipment status data to ensure the accuracy and consistency of the data;

[0128] S23, equipment status monitoring:

[0129] Operation status monitoring: Real-time monitoring of the equipment's operation status parameters, including temperature, pressure, vibration, and current, etc., using preset thresholds and rules to determine whether the equipment's operation status is normal, and scoring the equipment's current operation status;

[0130] Maintenance status monitoring: record the maintenance history of the equipment, including maintenance time, maintenance content, maintenance personnel and maintenance result information, evaluate the maintenance status of the equipment, and score the maintenance status of the equipment;

[0131] Availability monitoring: Calculate the availability score of the equipment based on the operation status score and maintenance history score, set a threshold to determine whether the equipment is available, and identify whether the current equipment can be used for production tasks;

[0132] S24, equipment status database establishment: the processed equipment status data is stored in the equipment status database, including the real-time status data, historical maintenance data and availability data of the equipment, to provide data support for production switching.

[0133] Sensor Network Deployment:

[0134] Temperature sensor: installed in the hot part of the equipment to monitor temperature changes.

[0135] Pressure sensor: installed in pressure pipes or chambers to monitor the internal pressure of the equipment.

[0136] Vibration sensor: installed near the vibration source of the equipment to monitor the vibration status of the equipment.

[0137] Current sensor: Installed on the power line to monitor current changes in the equipment.

[0138] 1. Operation status score:

[0139] Define the normal range of each operating status parameter:

[0140] Normal temperature range: T min ,T max ;

[0141] Normal pressure range: P min ,P max ;

[0142] Normal vibration range: V min ,V max ;

[0143] Normal current range: I min ,I max

[0144] Rating calculation: Among them, x i is the actual value of the i-th parameter, x 正常范围 is the normal value range of the parameter, and N is the total number of parameters;

[0145] 2. Maintain historical scores:

[0146] Define maintenance indicators:

[0147] Regular maintenance completion score: M 定期维护 ;

[0148] Fault repair frequency score: M 故障频率 ;

[0149] Rating calculation: S 维护情况 =w 定期维护 ×M 定期维护 +w 故障频率 ×M 故障频率 , where w 定期维护 and w 故障频率 is the weight of each indicator, satisfying w 定期维护 +w 故障频率 =1.

[0150] 3. Usability overall score: S 可用性 =α×S 运行状态 +β×S 维护情况

[0151] Among them, α and β are weights, satisfying α+β=1.

[0152] According to the comprehensive availability score, set the threshold S 可用性(阈值) , if S 可用性 ≥S 可用性(阈值) , the device is determined to be available; otherwise, it is determined to be unavailable.

[0153] The process parameter presets in S3 include:

[0154] S31, process requirement acquisition: obtaining detailed process requirements of the task to be switched from the production management system, including temperature, pressure, and operating speed process parameters;

[0155] S32, process parameter presetting: presetting various process parameters of the equipment according to the process requirements of the task to be switched, including temperature parameters, pressure parameters, and operating speed, among which;

[0156] Preset the temperature parameters and set the target temperature value T target ;

[0157] Preset the pressure parameters and set the target pressure value P tar get ;

[0158] Preset the running speed parameters and set the target running speed value V tar get ;

[0159] S33, process parameter verification: before production switching, the preset process parameters are verified to ensure that each parameter can quickly reach the target value after the equipment is switched;

[0160] Through the sensor network, the changes of each process parameter are monitored in real time and the current parameter value T is recorded. current P current ,V current ;

[0161] S34, calculate the deviation value of each parameter:

[0162] S35, parameter adjustment and optimization: According to the deviation values ​​ΔT, ΔP, ΔV, adjust the process parameter control system of the equipment to ensure that each parameter reaches the target value.

[0163] The intelligent scheduling strategy generation in S4 specifically includes:

[0164] S41, integration of production task and equipment status data: integrating the task priority model obtained from the production task analysis and the equipment status database established in the equipment status assessment to form a comprehensive data set;

[0165] S42, objective function definition: Based on production demand and resource utilization objectives, define the optimization objective function, which includes the following:

[0166] Maximize equipment utilization: Improve equipment utilization by maximizing equipment operating time and reducing equipment idle time;

[0167] Optimize resource allocation: Rationally allocate raw materials, energy and labor resources, reduce resource waste and improve resource utilization efficiency;

[0168] Minimize production cycle: shorten production switching time and minimize production cycle by optimizing scheduling strategies;

[0169] S43, constraint setting: according to the process requirements and equipment status of the production task, set the constraints that need to be met in the scheduling process, including equipment capacity, resource limitations and production task priority.

[0170] S44, generation of scheduling strategy based on reinforcement learning: using reinforcement learning algorithm, through interactive learning of production tasks and equipment status data, gradually optimize the scheduling strategy. In the training process, introduce reward mechanism, give rewards according to the optimization of equipment utilization, resource utilization and production cycle, and gradually guide the algorithm to the optimal solution;

[0171] S45, initialization and training: Initialize the scheduling algorithm according to the comprehensive data set, set the initial policy network parameters, expressed as: θ0 = random_initialization, where θ0 is the initial policy network parameter, random_initialization is random initialization, the training process includes simulating the production task switching process in a virtual simulation environment, and continuously adjusting the scheduling policy network parameters through the reinforcement learning algorithm. Through multiple rounds of training, the policy network parameters are optimized to improve the effectiveness of the scheduling strategy. The update of the policy network parameters is expressed as: Among them, θ t is the policy network parameter of the tth round, Δ is the learning rate, is the gradient of the reward function in round t;

[0172] S46, apply the trained scheduling strategy to the actual production environment, conduct small-scale verification, verify the feasibility and effectiveness of the strategy, and update the strategy network parameters for the second time based on the verification results:

[0173] θ new =θ current +β·Δθ, where θ new is the updated policy network parameter, θ current is the current strategy network parameter, β is the adjustment coefficient, and Δθ is the adjustment amount;

[0174] S47, after training and verification, outputs the optimal production switching scheduling strategy, including detailed equipment scheduling sequence, resource allocation plan and production switching plan.

[0175] The objective function definition includes:

[0176] Maximize equipment utilization: Among them, U i is the running time of device i, T is the total scheduling time, and N is the total number of devices;

[0177] Optimizing resource allocation: Among them, R j is the usage of resource j, M is the total number of resources;

[0178] Minimize production cycle: min(T cycle ), where T cycle is the production cycle time;

[0179] The constraint definition includes:

[0180] Equipment capacity constraints: the maximum processing capacity and load of each equipment;

[0181] Resource constraints: the available quantity and allocation limits of each resource;

[0182] Production task priority constraint: Determine the priority of tasks based on the priority model.

[0183] The reward mechanism is introduced into the reinforcement learning algorithm. Rewards are given according to the optimization of equipment utilization, resource utilization and production cycle, and the algorithm is gradually guided to move closer to the optimal solution. It is expressed as:

[0184] Among them, R is the reward value, w5, w6, w7 are the weight coefficients of each optimization target.

[0185] The standardized production switching process designed in S5 specifically includes:

[0186] S51, end of production task: after the current production task is completed, a task completion signal is sent through the production management system (MES), the end time and status of the current production task are recorded, and it is confirmed that all production steps have been completed, the product quality inspection is qualified, and the production task is officially ended;

[0187] S52, Equipment Cleaning:

[0188] Start the equipment cleaning process according to the equipment's process requirements and cleaning specifications;

[0189] Use automated cleaning equipment or manual cleaning to ensure thoroughness and consistency of cleaning;

[0190] During the cleaning process, the cleaning parameters are monitored in real time, including cleaning time, cleaning liquid concentration and temperature, to ensure the cleaning effect. After cleaning, the equipment is dried to ensure that there is no residual cleaning liquid and impurities in the equipment.

[0191] S53, process parameter adjustment: obtain the process parameter requirements of the new task, including temperature, pressure, and operating speed, and set new process parameters according to the deviation values ​​ΔV, ΔP, and ΔV of each parameter to ensure that each parameter reaches the target value;

[0192] S54, new task start: after the process parameters are adjusted and verified, start the new production task, issue the start instruction of the new task through the production management system (MES), record the start time and status of the new task, monitor the start process of the new task, and ensure that the equipment operates normally according to the predetermined process parameters and processes.

[0193] S6 also includes obtaining the generated production switching scheduling strategy, including equipment scheduling sequence, resource allocation plan, and production switching process. Through the production management system (MES), the comprehensive scheduling plan is issued to each production unit. The scheduling strategy issued includes equipment scheduling instructions, resource allocation instructions, and production switching process instructions to ensure that each production unit can accurately execute the scheduling strategy.

[0194] Dynamic resource allocation in S7 specifically includes:

[0195] S71, real-time monitoring of resource usage:

[0196] Raw material monitoring: Through IoT sensors and RFID technology, real-time monitoring of the use of raw materials in the production process, recording the inventory, consumption rate and replenishment status of raw materials;

[0197] Energy monitoring: Through smart meters and workshop energy consumption monitoring systems, the energy consumption of production equipment is monitored in real time, including the usage of electricity, gas and water resources, and the consumption rate and remaining amount of various energy sources are recorded;

[0198] Labor monitoring: Through the workshop time management system and RFID cards, the working status, working hours and task progress of production personnel are monitored in real time, and the distribution and utilization efficiency of labor are recorded;

[0199] S72, resource demand prediction: Based on the process parameters of the production task after switching and the real-time monitoring data, the demand for various resources after production switching is predicted. The prediction is expressed as:

[0200]

[0201] Among them, D material (t),D energy (t) and D labor (t) are raw materials, energy and labor at time t respectively;

[0202] S73, dynamic resource allocation: dynamically adjust the allocation of various resources based on real-time monitoring data and prediction results. The dynamic adjustment is expressed as:

[0203] A material (t)=max(0,min(S material -D material (t), I material ));

[0204] A energy (t)=max(0,min(S energy -D energy (t),I energy ));

[0205] Al abor (t)=max(0,min(S labor -D labor (t),I labor ));

[0206] Among them, A material (t), A energy (t) and A labor (t) are the raw materials, energy and labor allocation at time t, S material , S energy and S labor are the current inventory or available quantity, I material ,I energy and I labor are the amounts replenished during the replenishment interval, respectively.

[0207] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0208] 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A smart scheduling method for a smart manufacturing digital workshop, characterized in that: The following steps are involved: S1, production task analysis: analyze the current and to-be-switched production tasks, obtain the production requirements, resource requirements and process parameters of each task, and establish a task priority model to determine the priority order of production switching; S2, equipment status assessment: through the sensor network and data acquisition unit, the status of production equipment in the workshop is monitored in real time, including the operating status, maintenance status and availability of the equipment, and an equipment status database is established to provide data support for production switching; S3, process parameter preset: according to the process requirements of the task to be switched, the process parameters of the equipment are pre-set, and the parameters are checked before production switching to ensure that the equipment meets the process requirements after switching; S4, intelligent scheduling strategy generation: Combined with the production task analysis and equipment status assessment results, the intelligent scheduling algorithm is used to generate the optimal production switching scheduling strategy to ensure the optimization of equipment utilization and resource allocation during the production switching process; S5, switching process optimization: design a standardized production switching process, including the end of production tasks, equipment cleaning, process parameter adjustment and new task start-up; S6, switching execution: Send the generated switching scheduling strategy to each production unit and monitor the switching execution; S7, dynamic resource allocation: After production switching, real-time monitoring of resource usage, including raw materials, energy, and labor, and dynamic adjustment of resource allocation again according to actual needs to ensure smooth production switching.

2. According to claim 1, a smart scheduling method for a smart manufacturing digital workshop is characterized in that: The task priority model is established in S1 to determine the priority order of production switching, which specifically includes: S11, task information collection: obtaining detailed information of current and to-be-switched production tasks from the production management system and enterprise resource planning system, including task name, task type, task priority, planned start time and end time; S12, process parameter extraction: extract the process parameters of each production task, including the process configuration of the required equipment, production process steps, and process parameters; S13, Resource Requirements Analysis: Analyze the resource requirements of each production task to obtain the types, quantities, and distribution of required raw materials, energy, labor, equipment, and tools; S14, task relevance analysis: Analyze the relevance between the current and to-be-switched production tasks, including the dependencies between tasks, the usage of shared resources, and the similarities of process steps, to identify conflicts and coordination points; S15, task priority model establishment: Establish a task priority model based on task urgency, customer demand, production schedule, and resource availability factors; Use the multi-factor weight analysis method to assign weight values ​​to each factor and calculate the priority score of each production task; Combined with the results of task relevance analysis, the priority score is adjusted to ensure that the priority model can truly reflect the actual urgency and importance of the task; The priority model is expressed as: P i =w1×U i +w2×D i +w3×R i +w4×C i , where P i is the priority score of production task i, U i Score the urgency of production task i, D i Score the customer demand for production task i, R i Score the resource availability of production task i, C i is the task relevance score of production task i, w1, w2, w3, w4 are the weight values ​​of each factor, satisfying w1+w2+w3+w4=1; S16, priority order determination: according to the calculation result of the priority model, all current and to-be-switched production tasks are sorted to determine the priority order of production switching.

3. According to claim 1, a smart scheduling method for a smart manufacturing digital workshop is characterized in that: The establishment of the device status database in S2 specifically includes: S21, sensor network deployment: install a variety of sensors at key locations of production equipment, including temperature sensors, pressure sensors, vibration sensors, and current sensors, to monitor equipment operating status parameters; S22, data acquisition unit setting: a data acquisition unit is set up in the workshop to collect real-time data from various sensors and transmit the data to the central control unit through a wireless network. The central control unit performs data normalization processing on the collected equipment status data to ensure the accuracy and consistency of the data; S23, equipment status monitoring: Operation status monitoring: Real-time monitoring of the equipment's operation status parameters, including temperature, pressure, vibration, and current, etc., using preset thresholds and rules to determine whether the equipment's operation status is normal, and scoring the equipment's current operation status; Maintenance status monitoring: record the maintenance history of the equipment, including maintenance time, maintenance content, maintenance personnel and maintenance result information, evaluate the maintenance status of the equipment, and score the maintenance status of the equipment; Availability monitoring: Calculate the availability score of the equipment based on the operation status score and maintenance history score, set a threshold to determine whether the equipment is available, and identify whether the current equipment can be used for production tasks; S24, equipment status database establishment: the processed equipment status data is stored in the equipment status database, including the real-time status data, historical maintenance data and availability data of the equipment, to provide data support for production switching.

4. According to claim 1, a smart scheduling method for a smart manufacturing digital workshop is characterized in that: The process parameter presets in S3 include: S31, process requirement acquisition: obtaining detailed process requirements of the task to be switched from the production management system, including temperature, pressure, and operating speed process parameters; S32, process parameter presetting: presetting various process parameters of the equipment according to the process requirements of the task to be switched, including temperature parameters, pressure parameters, and operating speed; S33, process parameter verification: before production switching, the preset process parameters are verified to ensure that each parameter can reach the target value after the equipment is switched; Monitor the changes of various process parameters in real time through the sensor network and record the current parameter values; S34, calculating the deviation value of each parameter; S35, parameter adjustment and optimization: According to the deviation value, adjust the process parameter control system of the equipment to ensure that each parameter reaches the target value.

5. According to claim 1, a smart scheduling method for a smart manufacturing digital workshop is characterized in that: The generation of the intelligent scheduling strategy in S4 specifically includes: S41, integration of production task and equipment status data: integrating the task priority model obtained from the production task analysis and the equipment status database established in the equipment status assessment to form a comprehensive data set; S42, objective function definition: Based on production demand and resource utilization objectives, define the optimization objective function, which includes the following: Maximize equipment utilization: Improve equipment utilization by maximizing equipment operating time and reducing equipment idle time; Optimize resource allocation: Rationally allocate raw materials, energy and labor resources, reduce resource waste and improve resource utilization efficiency; Minimize production cycle: shorten production switching time and minimize production cycle by optimizing scheduling strategies; S43, constraint setting: according to the process requirements and equipment status of the production task, set the constraints that need to be met in the scheduling process, including equipment capacity, resource limitations and production task priority. S44, generation of scheduling strategy based on reinforcement learning: using reinforcement learning algorithm, through interactive learning of production tasks and equipment status data, gradually optimize the scheduling strategy. In the training process, introduce reward mechanism, give rewards according to the optimization of equipment utilization, resource utilization and production cycle, and gradually guide the algorithm to the optimal solution; S45, initialization and training: Initialize the scheduling algorithm according to the comprehensive data set, set the initial policy network parameters, expressed as: θ0 = random_initialization, where θ0 is the initial policy network parameter, random_initialization is random initialization, the training process includes simulating the production task switching process in a virtual simulation environment, continuously adjusting the scheduling policy network parameters through the reinforcement learning algorithm, and optimizing the policy network parameters through multiple rounds of training. The update of the policy network parameters is expressed as: Among them, θ t is the policy network parameter of the tth round, α is the learning rate, is the gradient of the reward function in round t; S46, apply the trained scheduling strategy to the actual production environment, conduct small-scale verification, verify the feasibility and effectiveness of the strategy, and update the strategy network parameters for the second time based on the verification results: θ new =θ current +β·Δθ, where θ new is the updated policy network parameter, θ current is the current strategy network parameter, β is the adjustment coefficient, and Δθ is the adjustment amount; S47, after training and verification, outputs the optimal production switching scheduling strategy, including equipment scheduling sequence, resource allocation plan and production switching plan.

6. The intelligent scheduling method for intelligent manufacturing digital workshop according to claim 5 is characterized in that: The objective function definition includes: Maximize equipment utilization: Among them, U i is the running time of device i, T is the total scheduling time, and N is the total number of devices; Optimizing resource allocation: Among them, R j is the usage of resource j, M is the total number of resources; Minimize production cycle: min(T cycle ), where T cycle is the production cycle time; The constraint definition includes: Equipment capacity constraints: the maximum processing capacity and load of each equipment; Resource constraints: the available quantity and allocation limits of each resource; Production task priority constraint: Determine the priority of tasks based on the priority model.

7. The intelligent scheduling method for intelligent manufacturing digital workshop according to claim 5 is characterized in that: The reinforcement learning algorithm introduces a reward mechanism, which gives rewards based on the optimization of equipment utilization, resource utilization, and production cycle, and gradually guides the algorithm to move closer to the optimal solution, which is expressed as: Among them, R is the reward value, W5, W6, and w7 are the weight coefficients of each optimization objective.

8. The intelligent scheduling method for intelligent manufacturing digital workshop according to claim 4 is characterized in that: The standardized production switching process designed in S5 specifically includes: S51, production task end: after the current production task is completed, a task completion signal is sent through the production management system to record the end time and status of the current production task, confirm that all production steps have been completed, the product quality inspection has passed, and the production task is officially ended; S52, Equipment Cleaning: Start the equipment cleaning process according to the equipment's process requirements and cleaning specifications; Use automated cleaning equipment or manual cleaning to ensure thoroughness and consistency of cleaning; During the cleaning process, the cleaning parameters are monitored in real time, including cleaning time, cleaning liquid concentration and temperature, to ensure the cleaning effect. After cleaning, the equipment is dried to ensure that there is no residual cleaning liquid and impurities in the equipment. S53, process parameter adjustment: obtain the process parameter requirements of the new task, including temperature, pressure, and operating speed, set new process parameters according to the deviation values ​​of each parameter, and ensure that each parameter reaches the target value; S54, new task start: after the process parameters are adjusted and verified, a new production task is started, the start instruction of the new task is issued through the production management system, and the start time and status of the new task are recorded.

9. The intelligent scheduling method for intelligent manufacturing digital workshop according to claim 1 is characterized in that: The S6 also includes obtaining the generated production switching scheduling strategy, including equipment scheduling sequence, resource allocation plan, and production switching process. Through the production management system, the comprehensive scheduling plan is issued to each production unit. The scheduling strategy issued includes equipment scheduling instructions, resource allocation instructions, and production switching process instructions to ensure that each production unit can accurately execute the scheduling strategy.

10. The intelligent scheduling method for intelligent manufacturing digital workshop according to claim 1 is characterized in that: The dynamic resource allocation in S7 specifically includes: S71, real-time monitoring of resource usage: Raw material monitoring: Through IoT sensors and RFID technology, real-time monitoring of the use of raw materials in the production process, recording the inventory, consumption rate and replenishment status of raw materials; Energy monitoring: Through smart meters and workshop energy consumption monitoring systems, the energy consumption of production equipment is monitored in real time, including the usage of electricity, gas and water resources, and the consumption rate and remaining amount of various energy sources are recorded; Labor monitoring: Through the workshop time management system and RFID cards, the working status, working hours and task progress of production personnel are monitored in real time, and the distribution and utilization efficiency of labor are recorded; S72, resource demand prediction: Based on the process parameters of the production task after switching and the real-time monitoring data, the demand for various resources after production switching is predicted. The prediction is expressed as: Among them, D material (t),D energy (t) and D labor (t) are raw materials, energy and labor at time t respectively; S73, dynamic resource allocation: dynamically adjust the allocation of various resources based on real-time monitoring data and prediction results. The dynamic adjustment is expressed as: A material (t)=max(0,min(S material -D material (t),I material )); A energy (t)=max(0,min(S energy -D energy (t),I energy )); A labor (t)=max(0,min(S labor -D labor (t),I labaor )); Among them, A material (t), A energy (t) and A labor (t) are the raw materials, energy and labor allocation at time t, S material , S energy and S labor are the current inventory or available quantity, I material ,I energy and I labor are the amounts replenished during the replenishment interval, respectively.

Citation Information

Cited By

  • Mechanical automation scheduling test method and system

    CN119539432A

  • Intelligent factory advanced scheduling optimization method based on big data

    CN119721648A

  • An intelligent ring main unit automatic production control system and production control method

    CN119781416A

  • Management method and system based on intelligent manufacturing digital workshop

    CN120181643A

  • Coating production line scheduling method and device, storage medium and program product

    CN120491566A