Virtual Sensing for Online Fault Diagnosis of Heat Exchangers

Abstract

Heat exchangers play essential roles in power generation and petrochemical industry. Although physical sensors are widely deployed in the process industry, timely fault detection and diagnosis method remain a significant challenge to its safe and reliable operation for accurate and reliable equipment condition monitoring. To address this challenge, this paper proposes a new virtual sensing method for online fault diagnosis method of heat exchangers. The virtual sensing models are constructed by incorporating the equipment failure mechanism and inference analytics. Complemented by high-precision in-process data measurements, fouling thickness and tube leakage in heat exchangers are quantified in real time using virtual sensing models. Therefore, the proposed virtual sensing method based on the fusion of physical mechanisms and measured data enables the online fault diagnosis of heat exchangers with only limited operating parameters while keeping the heat exchanger operational. The effectiveness of the proposed virtual sensing models is experimentally validated using a set of run-to-failure tests on real heat exchangers.