ON A MULTIVALUED TEST SEQUENCING PROBLEM

摘要：

Test sequencing is a binary identification problem where one needs to develop a minimal expected cost test procedure to determine which one of a finite number of possible failure states is present.In this paper, we consider a multivalued test sequencing (MVTS) problem, in which a test may have an arbitrary number of possible outcomes denoting different behaviors.The multivalued lest sequencing problem can be solved through multivalued dynamic programming (MVDP).This method can find the optimal test sequence, but the time and space is large.In order to deal with this problem, we propose multivalued AO* algorithm, called MVAO*.based on multivalued heuristic evaluation function (MVHEF) in the AO*.With one example we demonstrate that MVAO* is efficient and effective for optimizing test sequences problem with multiple test responses.

关键词： Fault diagnosis test sequencing heuristic search Huffman coding AO* noiseless diagnosis

作者: WEI WANG QINGHUA HU DAREN YU

作者单位: Department of Energy Science and Engineering, Harbin Institute of Technology, Harbin 150001, China

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 2541-2546

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）