Mixed-Model Fault Diagnosis

本研究旨在研究与模型无关的故障诊断系统，使其具有鲁棒性、综合性、可扩展性和实用性。该方法是利用系统的潜在概率框架，这使得将不同的诊断算法，不同的数据集和混合故障模型合并到单个诊断结果中成为可能。使用异构候选故障将允许根据从逻辑测试、延迟测试和iddq测试的结果收集的数据确定问题区域的诊断结果。通过实际工业集成电路故障数据的测试，验证了研究结果。演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.