Forecasting of Fouling in Air Pre-Heaters Through Deep Learning

Abstract

Thermal power plants employ regenerative type air pre-heaters (APH) for recovering heat from the boiler flue gases. APH fouling occurs due to deposition of ash particles and products formed by reactions between leaked ammonia from the upstream selective catalytic reduction (SCR) unit and sulphur oxides (SOx) present in the flue gases. Fouling is strongly influenced by concentrations of ammonia and sulphur oxide as well as the flue gas temperature within APH. It increases the differential pressure across APH over time, ultimately leading to forced outages. Owing to lack of sensors within APH and the complex thermo-chemical phenomena, fouling is quite unpredictable. We present a deep learning based model for forecasting the gas differential pressure across the APH using the Long Short Term Memory (LSTM) networks. The model is trained and tested with data generated by a plant model, validated against an industrial scale APH. The model forecasts the gas differential pressure across APH within an accuracy band of 5–10% up to 3 months in advance, as a function of operating conditions. We also propose a digital twin of APH that can provide real-time insights into progression of fouling and preempt the forced outages.

Physics Informed Neural Network for Health Monitoring of an Air Preheater

“…Numerical solution of the governing equations for the APH is obtained using finite difference method described by Li (1983). The numerical solution was validated with experimental data earlier (Gupta et al 2021). Design and material related parameter values of APH used for the simulation are mentioned in Appendix A.1.…”

“…Empirical models proposed for estimating propensity of fouling (Burke & Johnson 1982;Wang et al 2019;Chen, Xu, Yang, Wang, & Wang 2020) also require the internal temperature profile of APH for accurate estimations. Datadriven models based on machine or deep learning have been explored for fouling estimation (Sundar, Rajagopal, Zhao, Kuntumalla, Meng, Chang, Shao, Ferreira, Miljkovic, Sinha, & Salapaka, 2020;and Gupta, Jadhav, Patil, Deodhar, & Runkana, 2021). However, these models are heavily dependent on the quality and availability of data.…”

Dense Residual LSTM-Attention Network for Boiler Steam Temperature Prediction with Uncertainty Analysis

“…The generation of the steam temperature has a significant delay characteristic. The long short-term memory network (LSTM) has good performance in time-series forecasting, which solves the problems of gradient disappearance, gradient explosion, and a long sequence dependence in the long sequence training process. , Gupta et al used a single layer of LSTM with 32 nodes to predict fouling in air preheaters, which can be predicted 3 months in advance. Tan et al analyzed the effect of different delay time sequences on the model.…”