A human-knowledge-based sensor implemented in an intelligent fermentation-sensor system

Abstract

In many complex, ill-structured chemical and biological processes the quality variables related to the performance of a product of defined quality are hard to measure on-line. It is a fact that many processes depend on the human operator's experience and knowledge to manage unexpected situations that may occur. This paper discusses the problem of integrating human perceptual information into an objective sensor system. An intelligent fermentation-sensor system is presented, implementing the human-knowledge-based sensor in a complex operator-influenced and intuitive application. A conventional single sensor is integrated with extended computer-based time-series analysis. By extracting three statistical moments which are fused with the opinion of a human operator, we obtain an intelligent sensor system. The sensor system is applied to a bread-making fermentation process with promising results. The system is able to analyse a fermentation process and support the operator to perform the optimal decision. The sensor system can thus be used to facilitate on-line supervisory control, especially to detect and predict unexpected property variations in the measured process.