一种有效的组合电路测试生成算法（英文）  

An effective combinational circuit test generation algorithm

作　　者：曲萍萍[1] 赵莹[1] 赵航 马建宇 李艳娟[3] Ping-ping QU;Ying ZHAO;Hang ZHAO;Jian-yu MA;Yan-juan LI(Electrical&Jnformation Engineering College,Beihua University,Jilin 132021,China;The No.2 Middle School of Jiutai City,Jiutai 130500,China;College of Information an Computer Enginering,NortheasS Forestry University,Harbin 150040,China)

机构地区：[1]北华大学电气信息工程学院,吉林吉林132021 [2]吉林省九台市第二中学,吉林九台130513 [3]东北林业大学信息与计算机学院,哈尔滨150040

出　　处：《机床与液压》2018年第18期100-103,156,共5页Machine Tool & Hydraulics

基　　金：The National Natural Science Foundation of China(Study on Higher-Order Logic Based Inductive Logic Programming Learning Algorithm and Its Application,61300098);The Project of Jilin Province Department of Education,Science and Technology Research Project of Beihua University(The Monitoring System of Electrolyzer Tank Voltage)and Youth Promotion Plan of Beihua University

摘　　要：为了改善组合电路测试生成效率,提出了一种有效的基于三值神经网络的组合电路测试生成算法。该算法不需要传播和回溯,而是使用三值神经网络把组合电路表示为双向神经元网络,并构建网络的能量函数,最后使用遗传算法求出全局最小值点作为电路的测试矢量,所以组合电路的测试生成问题转换为优化问题。在标准电路上的测试实验结果表明该算法具有较高的故障覆盖率和较短的测试生成时间。In order to improve the quality of combinational circuit test generation,an effective combinational circuits test generation algorithm based three-valued neural networks[]is proposed in this paper.This algorithm does not need propagation and backtracks,but represents the combinational circuits as a bidirectional network of neurons using the three-valued neural networks,and constructs the energy function for the network.A genetic algo rithm was used to find the global minimal as the test vectors.The problem of the combinational test generation was formulated to an optimization problem.The experimental results on some standard circuits demonstrate that the proposed algorithm has high fault coverage and short test time.

关 键 词：三值神经网络 测试生成算法 遗传算法 能量函数 

分 类 号：TN407[电子电信—微电子学与固体电子学]