Production scheduling is critical to manufacturing system. Dispatching rules are usually applied dynamically to schedule the job in a dynamic job-shop. Existing scheduling approaches seldom address machine selection i...Production scheduling is critical to manufacturing system. Dispatching rules are usually applied dynamically to schedule the job in a dynamic job-shop. Existing scheduling approaches seldom address machine selection in the scheduling process. Composite rules, considering both machine selection andjob selection, are proposed in this paper. The dynamic system is trained to enhance its learning and adaptive capability by a reinforcement learning (RL) algorithm. We define the conception of pressure to describe the system feature. Designing a reward function should be guided by the scheduling goal to accurately record the learning progress. Competitive results with the RL-based approach show that it can be used as real-time scheduling technology.展开更多
Knowledge plays an active role in job-shop scheduling, especially in dynamic environments. A novel case-based immune framework was developed for static and dynamic job-shop problems, using the associative memory and k...Knowledge plays an active role in job-shop scheduling, especially in dynamic environments. A novel case-based immune framework was developed for static and dynamic job-shop problems, using the associative memory and knowledge reuse from case-based reasoning (CBR) and immune response mechanisms. A 2-level similarity index which combines both job routing and problem solution characteristics based on DNA matching ideas was defined for both the CBR and immune algorithms. A CBR-embedded immune algorithms (CBR-IAs) framework was then developed focusing on case retrieval and adaptation methods. In static environments, the CBR-IAs have excellent population diversity and fast convergence which are necessary for dynamic problems with jobs arriving and leaving continually. The results with dy-namic scheduling problems further confirm the CBR-IAs effectiveness as a problem solving method with knowledge reuse.展开更多
为解决在扰动情况下的负荷不均和能耗问题,构建了以平均流经时间和能耗为优化目标的柔性作业车间调度模型。针对上述模型,设计了一种遗传算法和模拟退火算法相结合的GASA(Genetic and Simulated annealing Algorithm)算法,通过遗传算法...为解决在扰动情况下的负荷不均和能耗问题,构建了以平均流经时间和能耗为优化目标的柔性作业车间调度模型。针对上述模型,设计了一种遗传算法和模拟退火算法相结合的GASA(Genetic and Simulated annealing Algorithm)算法,通过遗传算法的选择交叉变异操作产生一组新个体,对各个个体进行模拟退火过程,以避免陷入局部最优。针对柔性作业车间动态调度,在机器故障的扰动情况下,采用滚动窗口技术与GASA算法相结合的方法来求解动态调度问题。通过实验算例仿真,证明了算法的有效性。展开更多
文摘Production scheduling is critical to manufacturing system. Dispatching rules are usually applied dynamically to schedule the job in a dynamic job-shop. Existing scheduling approaches seldom address machine selection in the scheduling process. Composite rules, considering both machine selection andjob selection, are proposed in this paper. The dynamic system is trained to enhance its learning and adaptive capability by a reinforcement learning (RL) algorithm. We define the conception of pressure to describe the system feature. Designing a reward function should be guided by the scheduling goal to accurately record the learning progress. Competitive results with the RL-based approach show that it can be used as real-time scheduling technology.
基金the National Natural Science Foundation of China (No. 60004010) and the National High-Tech Research and Development (863) Program of China (No. 2001AA411020)
文摘Knowledge plays an active role in job-shop scheduling, especially in dynamic environments. A novel case-based immune framework was developed for static and dynamic job-shop problems, using the associative memory and knowledge reuse from case-based reasoning (CBR) and immune response mechanisms. A 2-level similarity index which combines both job routing and problem solution characteristics based on DNA matching ideas was defined for both the CBR and immune algorithms. A CBR-embedded immune algorithms (CBR-IAs) framework was then developed focusing on case retrieval and adaptation methods. In static environments, the CBR-IAs have excellent population diversity and fast convergence which are necessary for dynamic problems with jobs arriving and leaving continually. The results with dy-namic scheduling problems further confirm the CBR-IAs effectiveness as a problem solving method with knowledge reuse.
文摘为解决在扰动情况下的负荷不均和能耗问题,构建了以平均流经时间和能耗为优化目标的柔性作业车间调度模型。针对上述模型,设计了一种遗传算法和模拟退火算法相结合的GASA(Genetic and Simulated annealing Algorithm)算法,通过遗传算法的选择交叉变异操作产生一组新个体,对各个个体进行模拟退火过程,以避免陷入局部最优。针对柔性作业车间动态调度,在机器故障的扰动情况下,采用滚动窗口技术与GASA算法相结合的方法来求解动态调度问题。通过实验算例仿真,证明了算法的有效性。
