On-line measurement for the BHE fouling of brewery wort evaporator using a soft sensing approach

Abstract

Fouling is one of key problems to design and operate heat exchanger. To many batch heat exchangers (BHE), their fouling resistance changed periodically because of the alternation of batch washing and CIP washing. For on-line measuring the BHE fouling resistance, a novel soft-sensing approach based on FNN (fuzzy neural network) and OED (orthogonal experimental design) was investigated. The BHE fouling resistance is modeled by two parts: the increase of short-term fouling in one batch and the long-term irreversible fouling at the beginning of the batch. A brewery wort evaporator in multi-phase flow was taken as the case. OED were designed to select out the key parameters influencing the long-term fouling and the short-term fouling respectively. Two FNN networks are trained to learn the formation trends of the short-term fouling and the long-term fouling respectively. The experimental results and the comparison to experimental formula show the soft-sensing approach is effective.