Neural-network-driven fuzzy reasoning of dependency relationships among product development processes

Product development process can be viewed as a set of sub-processes with stronger interrelated dependency relationships. In this article, the quantitative and qualitative dependency measures of serial and parallel product development processes are analyzed. The neural-network-driven fuzzy reasoning mechanism of dependency relationships is developed in the case that there is no sufficient quantitative information or the information is fuzzy and imprecise. In the reasoning mechanism, a three-layer feedforward neural network is used to replace fuzzy evaluation in the fuzzy system. A hybrid learning algorithm that combined unsupervised learning and supervised gradient-descent learning procedures is used to build the fuzzy rules and train membership functions. Results show that the proposed method can improve the reasoning efficiency, reduce the cost and complexity degree of process improvement, and make a fast response to the dynamic development environment.