In this paper, we present a system level fault diagnosis algorithm for identifying faulty and fault-free units in sparsely interconnected systems. The algorithm is partially based on a comparison approach where identical test vectors are applied to all units and their outputs are compared among themselves. Typical comparison diagnosis schemes based on majority voting or voting with threshold=1 are shown to be inappropriate for diagnosing those systems implemented on a single chip or wafer. Unlike other schemes, our scheme can adjust algorithm parameters depending on unit yield, degree of connectivity, and the probability that common mode failures will occur. Further improvements in fault coverage are made by disseminating test results to neighbors. The fault coverage of our diagnosis algorithm is remarkably high, and diagnosis decisions are made in a distributed fashion.
在本文中,我们提出了一种系统级的故障诊断算法,用于识别稀疏互连的系统中的有故障和无故障的单元。该算法部分基于比较方法,其中将相同的测试向量应用于所有单元,并比较它们的输出。基于多数投票或阈值= 1的投票的典型比较诊断方案被证明不适用于诊断在单个芯片或晶圆上实现的那些系统。与其他方案不同,我们的方案可以根据单位产量,连接程度和共模故障发生的可能性来调整算法参数。通过将测试结果分发给邻居,可以进一步提高故障覆盖率。我们的诊断算法的故障覆盖率非常高,并且以分布式方式做出诊断决策。 P>
Department of Computer Science, University of Minnesota, Minneapolis, MN;
机译:稀疏互连系统中的系统级自我诊断
机译:具有稀疏连接的网络互连系统中的分布式事件触发调度
机译:互连系统的稀疏分布滑模控制
机译:稀疏互连的多处理器系统的故障诊断
机译:一种用于非线性动态系统故障诊断的概率估计方法。
机译:稀疏数据的持续Citemporal概率建模系统生物学网络
机译:采用泵送存储的单系统的概率生产成本和发电规划中的互联系统。