الگوریتم ژنتیک یادگیری فعال برای برنامه ریزی عملیات یکپارچه و زمان بندی

In traditional approaches, process planning and scheduling are carried out sequentially, where scheduling is done separately after the process plan has been generated. However, the functions of these two systems are usually complementary. The traditional approach has become an obstacle to improve the productivity and responsiveness of the manufacturing system. If the two systems can be integrated more tightly, greater performance and higher productivity of a manufacturing system can be achieved. Therefore, the research on the integrated process planning and scheduling (IPPS) problem is necessary. In this paper, a new active learning genetic algorithm based method has been developed to facilitate the integration and optimization of these two systems. Experimental studies have been used to test the approach, and the comparisons have been made between this approach and some previous approaches to indicate the adaptability and superiority of the proposed approach. The experimental results show that the proposed approach is a promising and very effective method on the research of the IPPS problem.

Process planning and scheduling are two of the most important sub-systems in the manufacturing system. A process plan specifies raw materials or components what are needed to produce a product, processes and operations which are necessary to transform those raw materials into the final product. The outcome of process planning includes the identification of machines, tools and fixtures suitable for a job and the arrangement of operations for a job. Process planning is the bridge of the product design and manufacturing. With the process plans of jobs as inputs, a scheduling task is to scheduling the operations of all jobs on machines while precedence relationships in the process plans are satisfied. Scheduling is the link of the two production steps which are the preparing processes and putting them into action. Although there is a close relationship between process planning and scheduling, the integration of them is still a challenge in both research and applications (Sugimura, Hino, & Moriwaki, 2001). In traditional approaches, process planning and scheduling were carried out in a sequential way, where scheduling was conducted separately after the process plans had been generated. Those approaches have become an obstacle to improve the productivity and responsiveness of the manufacturing systems. Because of the development of the modern manufacturing system, the process planning system can generate more than one process plans for each job. In this case, the process planning and scheduling have to be integrated to meet the requirements (including flexibility and real-time requirements) from the modern manufacturing enterprises. Therefore, there is an increasing need for deep research and application of the integrated process planning and scheduling (IPPS) system. The IPPS can introduce significant improvements to the efficiency of manufacturing through eliminating or reducing scheduling conflicts, reducing flow-time and work-in-process, improving production resources utilizing and adapting to irregular shop floor disturbances (Lee & Kim, 2001). Without IPPS, a true computer integrated manufacturing system (CIMS), which strives to integrate the various phases of manufacturing in a single comprehensive system, may not be effectively realized. However, the IPPS problem is very different from the separate process planning problem and the scheduling problem. Because, the objectives, the constraints and the solution space between them are very different. The IPPS problem has more constraints, and it is more complicated than the process planning problem and the scheduling problem. The previous methods for the scheduling cannot be used to solve the IPPS problem. And the traditional intelligent algorithms also have to be modified and improved to solve this new problem effectively. Therefore, in this research, a new active learning genetic algorithm (ALGA) based approach has been developed to facilitate the integration and optimization of the IPPS problem. Through experimental studies, the merits of the proposed approach can be shown clearly. The remainder of this paper is organized as follows: Section 2 introduces the related works. Problem formulation is discussed in Section 3. ALGA-based optimization approach for IPPS is proposed in Section 4. Experimental studies and discussions are reported in Section 5. Section 6 is conclusion.

Considering the complementarity of process planning and scheduling, the research has been conducted to develop an active learning genetic algorithm to facilitate the optimization of the IPPS problem. Experimental studies have been used to test the performance of the proposed approach. The results show that the developed approach has achieved significant improvement. The contributions of this research include: • An active leaning genetic algorithm has been proposed. This algorithm can more accurately reflect the laws of the biological evolution. Therefore, it has better searching ability than the simple GA. • Based on the features of the IPPS problem, we design all the parts of the ALGA method. This algorithm can reflect the essential characteristics of this problem. And ALGA has been successfully used to solve the IPPS problem. It obtains better results than some previous methods. It means that the proposed approach is a promising and very effective method on the research of IPPS. • This paper provides a new way to solve other problems in the manufacturing field, such as process planning problem, assembly sequencing problem, scheduling problem and so on. Because some aspects of these problems are similar with the IPPS problem, the ALGA maybe also very effective in solving these problems.