A novel approach for analysing evolutional motivation of empirical engineering knowledge

Empirical engineering knowledge (EEK), a specific technical know-how about solving engineering problems, is frequently accumulated and reused in this era of mass innovation and knowledge-driven economy. Since EEK is abidingly evolving because of the intense business competitions, continual technical renovations and wide industrial concern, it’s a new challenge both in theories and applications of knowledge management to analyse EEK evolution and its motivations. This paper proposes a novel approach to tackle this non-trivial issue. Based on the constructed domain hierarchy and EEK networks, EEK clusters are grouped and represented with populations, latent topics and distributions. Then four kinds of evolutional patterns are defined and recognised from the EEK clusters in neighbouring time intervals. The evolutional motivations of these patterns are discovered from the important evolutional events, with the proposed abductive reasoning algorithm. This paper also integrates all techniques, and implements a knowledge management system EEK-KEAS in computer-aided design (CAD), a typical engineering field. Experimental result shows that EEK-KEAS operations well in revealing the evolutional motivations of CAD EEKs, and outperforms the former approaches in feasibility and effectiveness, thereby opening up a novel way for further understanding the evolution of EEK.