基于贝叶斯网络的硬件产品设计缺陷评估

摘要

An assessing model of product development status using Bayesian Networks(BN)is proposed to predict design defects of hardware product during product design and development process. The method of fault tree is used to build Bayesian networks structure of defects assess-ment model and evidential reasoning is used to get probability data. The method has proven to be efficient by a case studying to analyze the relationships between the factors and design defects and to quantify the probability of defect occurrence. The validity of the proposed model is tested by using a realistic case study with high compliance at last.%为了预测硬件产品设计研发过程中的设计缺陷，提出利用贝叶斯网络构建产品设计缺陷评估模型。通过故障树建立评估模型的贝叶斯网络结构，利用证据推理方法确定评估模型的概率。研究案例表明，该方法可分析缺陷因素对设计缺陷的影响关系，实现对产品设计缺陷的定量预测，研究结果与实际情况对比具有较好的符合性。