Knowledge-based decision support for the improvement of standard products

Throughout the last couple of years several approaches for the feedback-based improvement of capital goods have been developed. Based on previous research work the authors are proposing a new methodology of decision support for the improvement of existing mass-produced standard products. This approach is based on prescriptive decision theory and uses feedback data in addition to product-specific characteristics and properties. For the prediction and evaluation of different improvement alternatives, the presented solution uses object-oriented Bayesian networks (OOBN). The validation of the proposed solution has been demonstrated on the basis of decision processes for the improvement of centrifugal pumps.