17 results about "Manufacturing scheduling" patented technology

The invention is suitable for the technical field of intelligent manufacturing scheduling, and provides a discrete manufacturing workshop multi-stage dynamic scheduling method based on transportation state feedback, which comprises the following steps: determining a multi-stage structure of tasks in a workshop, and establishing a corresponding task flow chart and a resource dependence model; a scheduling modeling basis with resource constraint and physical connection is formed; based on the current state of the system, key state variables are extracted, and a scheduling action space is defined; a transportation index is introduced into the reinforcement learning structure, and a composite reward function is constructed; reinforcement learning is adopted for training, and scheduling strategy parameters are iteratively optimized based on interaction between the intelligent agent and the environment. According to the method, rapid restoration and resource continuity maintenance of a scheduling strategy in a dynamic disturbance environment are realized, the real-time response capability and scheduling adaptability of a scheduling system under complex resource constraints are remarkably improved, and the method is suitable for manufacturing scenes facing high-frequency task change and transportation bottleneck problems.

This invention addresses the challenge of complex scheduling tasks in industrial manufacturing, where multiple tasks exist simultaneously with coupled constraints, leading to high optimization difficulty. It proposes an intelligent multi-task optimization method based on constraint coupling strength indices. This method aims to minimize the number of vehicles used and the total transportation cost. First, a knowledge graph network is constructed to store task information and constraints. Then, a constraint coupling strength index is calculated based on the relationship between constraints and decision variables. Subsequently, during the multi-task differential evolution search, candidate solutions are grouped according to constraint coupling strength, and differentiated cross-tabulation, mutation, and cross-task knowledge transfer strategies are employed to guide the search process towards efficient convergence. This method effectively characterizes complex constraint structures, enhances multi-task collaborative optimization capabilities, and provides an efficient and feasible optimization solution for transportation scheduling in industrial manufacturing.

The application discloses a denture manufacturing scheduling control method, device, equipment and medium, and relates to the field of production and manufacturing. The method comprises the following steps: acquiring a batch order set; acquiring a preset process node sequence of each denture manufacturing order and a priority score based on multi-dimensional characteristics based on order information of the batch order set to obtain an order priority set queue; the higher the priority score is, the higher the urgency of completing the corresponding denture manufacturing order is; establishing an MDCN decision tree based on process types and corresponding resources; and matching corresponding resources for each preset process node based on preset rule constraints and the MDCN decision tree to obtain a feasible scheme set, wherein the feasible scheme set comprises at least one feasible scheme, and each feasible scheme comprises resources matched by each preset process node and operation time of the resources; and performing optimization screening on the feasible scheme set to obtain a target scheme. The application can improve the synergy between resources and the comprehensive utilization rate of resources.

The application discloses an intelligent scheduling multi-objective optimization method based on a pulse propagation algorithm, relates to the field of manufacturing scheduling, and comprises the following steps: a scheduling data preparation stage, which is used for making a pre-decision for the schedulable resources in a pool and generating data of an input model; a multi-objective model establishment stage, which describes scheduling rules and optimization targets in a mathematical modeling mode; and a pulse propagation algorithm stage, which solves the above multi-objective model by designing an epsilon-constraint and a pulse propagation algorithm. The application greatly reduces the work burden of a planner, and the batch decision and specific scheduling details can be automatically completed by an embedded advanced model and intelligent algorithm. The intelligent decision mechanism not only improves work efficiency, but also ensures the accuracy and rationality of the scheduling plan.

The invention discloses a job shop scheduling method based on a large model, and belongs to the technical field of intelligent manufacturing scheduling. The method comprises the following steps: constructing a scheduling domain knowledge base, and extracting a scheduling model, a process route and a scheduling scheme from industry research and historical data through a large model; a modeling agent is trained, so that the modeling agent can automatically generate a mathematical model containing a target function and constraint conditions according to the problem description; training a scheduling agent, and generating a scheduling rule or a detailed plan based on historical data; constructing an evaluation feedback agent, performing multi-index evaluation on the model and the scheduling scheme, and feeding back optimization suggestions; and finally, enhancing the response and scheduling capability of the intelligent agent under dynamic disturbance through human feedback reinforcement learning. According to the method, the modeling difficulty of a scheduling problem is remarkably reduced, the generation efficiency and quality of a scheduling scheme are improved, and quick response and closed-loop optimization under a dynamic event are supported.

The invention belongs to the related technical field of semiconductor manufacturing scheduling and intelligent optimization, and discloses a semiconductor furnace tube area batch processing equipment scheduling method and equipment based on rule decoding. The invention provides an integrated solving method of coding initialization, rule active decoding, fitness evaluation and elite retention, genetic evolution and hierarchical neighborhood enhancement. According to the method, a process sequence decision, a machine allocation decision, a batch formation decision and a time window control decision are incorporated into a unified solution chain, the problem of conflict accumulation caused by staged isolated decisions in an existing method is avoided, and process sorting, machine allocation, batch formation and time window control are cooperatively processed in the unified solution chain. Comprehensive optimization of the maximum completion time, the batch rate and the time window violation rate is realized, and an efficient, stable and executable scheduling scheme can be provided for batch processing equipment in a semiconductor furnace tube area.

This application relates to the field of manufacturing scheduling technology, specifically disclosing a production scheduling method, apparatus, and storage medium based on a hybrid production mode. This application determines the safety stock levels of finished and semi-finished products based on inventory parameters such as the first average replenishment lead time for finished products, the second average replenishment lead time for semi-finished products, the average demand rate and standard deviation for each order type within a preset time period, the normal quantile corresponding to the target service level, the proportion of MTO orders, the response time of MTO orders, the MTO additional inventory coefficient, the correlation coefficient between different demand sources, the semi-finished product conversion rate, the inventory reduction rate, and the lower limit ratio of finished product inventory. This allows for the scheduling of production plans for different types of orders from customers using their respective corresponding production modes to ensure optimal delivery speed and ultimately fulfill order requirements, while simultaneously reducing the risk of inventory backlog for finished and semi-finished products.

The present application relates to a kind of wafer manufacturing scheduling trigger decision system considering multilevel relationship, information collection module accepts the multidimensional heterogeneous data from system;Information processing module encodes and pre-processes the data collected;Multilevel relationship perception module carries out relationship modeling to the data processed, constructs the multilevel relationship model including physical layer, process layer and scheduling layer;Scheduling trigger decision module carries out scheduling decision and trigger to multilevel relationship model in combination with deep reinforcement learning, realizes predictive trigger, event-driven trigger and multilevel collaborative trigger;GUI result output module visualizes the scheduling result and system state and shows.Solve the problem that existing wafer manufacturing scheduling trigger decision system is difficult to meet the high complexity requirement of wafer manufacturing, the present application can effectively handle the complex scheduling problem in wafer manufacturing process, improve production efficiency and equipment utilization, reduce production cycle time, adapt to dynamic changing manufacturing environment.

The invention belongs to the technical field of industrial manufacturing scheduling, and discloses an MIP casting intelligent scheduling method and system based on multi-dimensional expert rule embedding and dynamic compensation, and the method comprises the steps: carrying out the multi-dimensional expert rule modeling, and carrying out a primary scheduling plan according to the modeling result; scanning an equipment window period in the primary production scheduling plan; according to order weights in delivery time priority modeling, proper work tasks are inserted into an equipment air window period according to the sequence of the weights from high to low; after the work task is inserted, carrying out constraint verification on the production scheduling plan again, and checking whether a productivity determination principle, an upper and lower process balance principle, a process neat set principle and an economic batch principle are met or not; and if the verification is not passed, adjusting the work task insertion scheme until all constraint conditions are satisfied, thereby obtaining a final optimized production scheduling result.

The application discloses a kind of based on photovoltaic crystal-pulling industry production automatic generation scheduling plan method and system, it is related to industrial manufacturing scheduling technical field.The method includes: receiving order data to be scheduled, furnace table real-time state data and material inventory data, constructs dynamic rule base;Call structured parameter in dynamic rule base and execute process constraint pre-check, generate schedulable order-furnace candidate set;Future scheduling cycle is divided into execution lock area and pre-scheduling adjustment area, and scheduling comprehensive evaluation index is constructed;Based on scheduling comprehensive evaluation index, schedulable order-furnace candidate set is traversed and matched using hierarchical allocation strategy, and initial scheduling sequence is generated;When preset disturbance trigger condition is identified, local rearrangement repair based on neighborhood search is executed to affected associated order, and dynamic rule base is called to perform hard constraint check;According to the performance of core performance indicator of continuous preset quantity of scheduling cycle, the weight coefficient of scheduling comprehensive evaluation index is adjusted.

The application discloses an intelligent manufacturing scheduling method and device, electronic equipment and medium. Through the application of the technical solution, the total cost including product processing cost, overtime cost of employees, product delay delivery cost, and product inventory cost is taken as the optimization target. And combined with the deep reinforcement learning algorithm, the scheduling plan corresponding to the order information is output at the lowest cost. Thus, on the one hand, the production manufacturer can automatically give a scheduling scheme within a period of time in real time. On the other hand, the scheduling scheme is not accurate due to the problem that the employee production cost in the production process is not considered in the related art.

The invention discloses an electric power tower manufacturing optimization method based on a knowledge graph, and the method comprises the following steps: collecting order information, process information, equipment information and delivery time constraint data, extracting manufacturing constraint data, and constructing the knowledge graph; adopting a TransE model to generate entity embedding vectors corresponding to various types of information; generating a manufacturing state representation based on the entity embedding vector; executing dynamic feasible region clipping by adopting a hybrid reasoning mechanism to generate a scheduling action set; an improved T-DRL model is adopted to carry out strategy training, and an optimal scheduling action is generated; constructing a task arrangement plan and calculating scheduling index data; strategy parameters of the improved T-DRL model are updated, training is repeated until convergence conditions are met, and a manufacturing scheduling scheme is output. According to the method, knowledge driving and intelligent optimization of the power tower manufacturing process are realized, and the reasonability of task arrangement and the efficiency of production scheduling are improved.

This invention discloses a cloud-edge collaborative data management method and system for factory uniform customization, relating to the field of industrial internet data management, to address the problems of privacy data leakage and the disconnect between cloud scheduling and the actual production capacity of underlying equipment in customized production scheduling. First, the edge device extracts point cloud data of factory uniforms and generates text feature parameters. After destroying the original data, an anonymous customized feature matrix is ​​constructed to ensure privacy and achieve data dimensionality reduction. Then, the edge device quantifies and reports the production changeover cost index based on real-time equipment operating conditions. The cloud then aggregates similar orders into virtual common production batches, uses changeover cost as a constraint weight to execute cross-node resource allocation, and issues a global game-theoretic scheduling graph. Finally, the edge device dynamically adjusts costs based on equipment wear and tear, and accurately feeds back migration requests to drive cloud node updates when process conflicts occur, constructing a closed-loop system for data security and dynamic scheduling, providing scientific support for flexible manufacturing scheduling.

The invention discloses a semiconductor manufacturing scheduling method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring information of each machine in a to-be-scheduled machine group and information of a current to-be-processed product of the to-be-scheduled machine group, and obtaining corresponding relation information between each machine in the to-be-scheduled machine group and a batch and a process menu of the current to-be-processed product; inputting the information of each machine in a to-be-scheduled machine group, the information of the current to-be-processed product and the corresponding relation information between each machine in the to-be-scheduled machine group and the batch and process menu of the current to-be-processed product into a machine group real-time scheduling model to obtain a scheduling work order of each machine in the to-be-scheduled machine group, the number of machining products in the to-be-dispatched machine group is balanced; and scheduling each machine in the to-be-scheduled machine group based on the scheduling work order of each machine in the to-be-scheduled machine group. By the adoption of the scheme, the machines can be scheduled in real time under the condition that it is guaranteed that the number of machined products between the machines is balanced.

The invention provides a complex discrete type processing and manufacturing scheduling method and device, and relates to the technical field of discrete processing and manufacturing, and the method comprises the steps: obtaining complex discrete type processing and manufacturing order information, and extracting a schedulable work order from the complex discrete type processing and manufacturing order information based on the external condition constraint of production processing; generating a scheduling strategy set for the schedulable work order; and based on the target function considering the equipment remodeling time, in combination with a pre-constructed processing constraint condition set, performing iterative optimization on scheduling strategies in the scheduling strategy set to determine a target scheduling strategy, the target scheduling strategy being used for describing a corresponding relationship among the schedulable work order, the processing procedure and the processing equipment. According to the method, comprehensive optimization of the complex discrete type machining and manufacturing process can be better achieved, so that the production efficiency is improved, the cost is reduced, it is ensured that the production plan can be completed on time, and the actual production requirement is better met.

The invention provides a flexible manufacturing scheduling system, which comprises a data acquisition module, a scheduling model, a digital twinning module and an emergency decision module, and is characterized in that the data acquisition module periodically acquires equipment state, order demand and energy constraint type dynamic data, and pre-processes and transmits the data to the scheduling model and the digital twinning module; the scheduling model comprises a rolling optimization scheduling algorithm, calculates an optimal production sequence according to a preset period in combination with dynamic data, and outputs the optimal production sequence to the digital twin module; the digital twin module simulates a scheduling scheme for balancing the delivery cycle and the production cost through a multi-objective optimization algorithm based on the dynamic data and the optimal production sequence, and outputs the scheduling scheme to the emergency decision module; and the emergency decision module is in real-time butt joint with ERP and MES system data, and generates an emergency scheduling scheme within a preset time according to the simulation scheduling scheme when the equipment fails.

The invention discloses a semiconductor scheduling method based on dynamic priority and reinforcement learning decision, relates to the technical field of semiconductor manufacturing scheduling, and aims to solve the problems of low utilization rate, delivery delay and poor dynamic adaptability of traditional scheduling equipment. The method comprises the following steps: fusing equipment space topology and process dependence, and generating a machine family low-dimensional coding vector; constructing a 13-dimensional dynamic feature vector, standardizing the 13-dimensional dynamic feature vector, inputting the standardized 13-dimensional dynamic feature vector into a strategy network consisting of a multi-head attention network and a feedforward network, and outputting a real-time priority; a reinforcement learning framework is constructed based on event driving, and the network is optimized through a three-level machine distribution rule, a negative penalty reward function and a natural evolution strategy. According to the invention, equipment load balancing and scheduling intelligent adaptation are realized, the equipment utilization rate is effectively improved, the wafer batch tardiness and completion time are reduced, and the method is suitable for a complex dynamic semiconductor manufacturing scene.