Board-Level Functional Fault Identification using Streaming Data
Board-Level Functional Fault Identification using Streaming Data
复制标题
DOI：
10.1109/vts.2019.8758599
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Mengyun Liu;Fangming Ye;Xin Li;K. Chakrabarty;Xinli Gu
中科院分区：
文献类型：
--
作者：
Mengyun Liu;Fangming Ye;Xin Li;K. Chakrabarty;Xinli Gu
印刷电路板的高集成密度和设计复杂性使得板级功能故障识别极其困难。机器学习提供了以高精度识别功能故障的机会，从而降低了维修成本。然而，大量的制造数据以流格式出现，并且在生产环境中表现出与时间相关的概念漂移。这些缺点限制了传统机器学习算法的有效性。我们提出了一个诊断工作流程，利用在线学习，在每一步用一小块数据递增地训练分类器。这些在线学习算法通过精心设计的更新规则快速适应概念漂移。还提出了一种混合算法来处理在不同时间收集不同数量的板的数据的情况。实验结果表明，使用两个板在大批量生产的帮助下，在线学习和所提出的混合算法，诊断的F1分数可以提高57.3%到78.9%。
High integration densities and design complexity of printed-circuit boards make board-level functional fault identification extremely difficult. Machine learning provides an opportunity to identify functional faults with high accuracy and thereby reduce repair cost. However, the large volume of manufacturing data comes in a streaming format and exhibits time-dependent concept drift in a production environment. These drawbacks limit the effectiveness of traditional machine-learning algorithms. We propose a diagnosis workflow that utilizes online learning to train classifiers incrementally with a small chunk of data at each step. These online learning algorithms adapt to concept drift quickly with carefully designed update rules. A hybrid algorithm is also proposed to handle the scenario that data for varying numbers of boards are collected at different times. Experimental results using two boards in high-volume production show that, with the help of online learning and the proposed hybrid algorithm, the F1-score for diagnosis can be improved from 57.3% to 78.9%.