The idea of knowledge supplementation and explanation using neural networks to support decisions in construction engineering

Abstract

The article presents the problem of knowledge in knowledge-based systems, such as advisory systems used in construction engineering. The unique characteristics of construction engineering translate directly into unique characteristics of knowledge resources, which is evident in the potential sources of knowledge. Many of them are not open, uncertain, fuzzy, of different credibility, and incomplete. One of the knowledge sources is the mental models of experts working in specific fields of construction engineering. Based on the knowledge acquisition sessions that have been completed, it can be concluded that only a certain part of the knowledge contained in mental models has been acquired. In order to ensure more completeness of the knowledge and explain the mechanism of inference, the KBANN (Knowledge Based Artificial Neural Network) algorithm was used, which enables extracting rules that are not a part of the original state of knowledge using trained neural networks. This method effectively supports the process of construction of advisory systems.