A New Test Approach of Digital Circuits Using Neural Networks and Cultural Algorithms
It is necessary to carry out the test of digital circuits in order to ensure the reliability of circuits. A new test approach for stuck-at faults in digital circuits is presented in this paper, which uses artificial neural networks and cultural algorithms. In this approach, the circuit test generation is formulated as computing the optimal solutions of the energy function of a neural network. First of all, the neural network model corresponding to a digital circuit is built. Secondly, an algorithm based on cultural algorithms is proposed to compute the optimal solutions of energy functions. An evolution process that uses two populations parallel competition is presented for the design of population space in cultural algorithm, which is able to avoid the premature convergence of the algorithm. Experimental results on a lot of digital circuits show that the test approach proposed in this paper can produce the test vectors of faults in reasonable time.
Zhongliang Pan Ling Chen Guangzhao Zhang
Department of Electronics, School of Physics and Telecommunication, South China Normal University, G Department of Electronics, School of Information Technology, Sun Yat-sen University, Guangzhou 51027
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）