A self-learning algorithm based on support vector machine for scheduling a job-shop-like knowledgeable manufacturing cell
The job-shop-like knowledgeable manufacturing cell scheduling is a NP-complete problem and there has not been a completely valid algorithm for it until now. An algorithm with self -learning ability is proposed through the addition of precedence constraint of operations on the basis of directed graph. A method based on support vector machine is constructed to choose accurately interchangeable operations by small samples earning to obtain the better scheduling. The classification accuracy can be improved by the continuous addition of new instances to the sample library. The results of simulation show that the algorithm performs well for the job-shop-like knowledgeable manufacturing cell.
Knowledgeable manufacturing cell Job-shop Constraint guided Self-learning
LI Wen-chao YAN Hong-sen
School of Automation Key Laboratory of Measurement and Control of Complex Systems Engineering, Minis School of Automation Key Laboratory of Measurement and Control of Complex Systems Engineering, Minis
国际会议
大连
英文
369-373
2011-10-19（万方平台首次上网日期，不代表论文的发表时间）