Mixed-Model Fault Diagnosis

本研究是对模型无关的故障诊断系统的研究，旨在使系统具有健壮性、全面性、可扩展性和实用性。方法是利用系统的基本概率框架，这使得有可能将不同的诊断算法、不同的数据集和混合的故障模型纳入单一的诊断结果。异类故障候选的使用将允许基于从逻辑测试、延迟测试和IDDQ测试的结果中收集的数据来精确定位问题区域的诊断结果。利用实际的工业集成电路失效数据对研究结果进行了验证。展示研究思路的算法和软件正在开发中。

This research is an investigation of model-independent fault diagnosis systems that are intended to be robust, comprehensive, extendible, andpractical. The approach is to exploit the underlying probabilisticframework of the system, which makes it possible to incorporate disparatediagnostic algorithms, different sets of data, and a mixture of faultmodels into a single diagnostic result. The use of heterogeneous faultcandidates will allow a diagnosis result that pinpoints problem areas basedon data gleaned from the results of logic tests, delay tests, and IDDQtests. The research results are being verified by testing them using actualindustrial IC failure data. Algorithms and software demonstrating theresearch ideas are being developed.