一种基于混沌神经网络的自动测试生成算法

An Approach to Automatic Test Pattern Generation Using Chaotic Neural Networks

阐述了一种基于混沌神经网络的自动测试生成 (ATPG)算法。由神经元构成的双向神经网络来表示组合电路 ,神经元的阈值和神经元之间的连接权值则代表了电路的功能。给电路注入故障后 ,网络中的神经元的状态在满足测试序列的时候 ,神经网络的能量函数具有全局最小点。采用具有衰减步长的混沌模拟退火 (CSA)算法来找到能量函数的最小点 ,实现了组合电路的自动测试生成。计算机仿真表明了算法的可行性。

A new automatic test pattern generation (ATPG) methodology based on chaotic neural network method is described. The digital circuit is represented as a bidirectional network of neurons, and the circuit function is coded in the firing thresholds of neurons and the weights of interconnection links. A fault is injected into the neural network and an energy function is constructed with global minima at test vectors. Global minima are determined by chaotic neural network method employing chaotic simulated annealing (CSA) with decaying timestep. Simulation results on combinational circuits confirm the feasibility of this technique.