Modelling the clogging of gas turbine filter houses in heavy-duty power generation systems

Abstract

A prognostic approach based on a MISO (multiple inputs and single output) fuzzy logic model was introduced to estimate the pressure difference across a gas turbine (GT) filter house in a heavy-duty power generation system. For modelling and simulation of clogging of the GT filter house, nine real-time process variables (ambient temperature, humidity, ambient pressure, GT produced load, inlet guide vane position, airflow rate, wind speed, wind direction and PM10 dust concentration) were fuzzified using a graphical user interface within the framework of an artificial intelligence-based methodology. The results revealed that the proposed fuzzy logic model produced very small deviations and showed a superior predictive performance than the conventional multiple regression methodology, with a very high determination coefficient of 0.974. A complicated dynamic process, such as clogging phenomenonin heavy-duty GT system, was successfully modelled due to high capability of the fuzzy logic-based prognostic approach in capturing the nonlinear interactions.

A novel integrated modeling approach for filter diagnosis in gas turbine air intake system

“…Nine variables (ambient temperature, humidity, ambient pressure, gas turbine produced load, inlet guide vane position, airflow rate, wind speed, wind direction and PM 10 dust concentration) contribute to pressure loss, as discussed in. 21 This work takes 5 of them into account, including air mass flow rate ( G a ), ambient temperature ( T 0 ), ambient pressure ( P 0 ), relative humidity ( RH ), and PM 10 dust concentration ( DC ). Wind speed and wind direction have been shown to be not significantly interacted with the pressure loss, as the corresponding p-values are 0.90 and 0.29 respectively.…”

“…Wind speed and wind direction have been shown to be not significantly interacted with the pressure loss, as the corresponding p-values are 0.90 and 0.29 respectively. 21 Turbine produced load and inlet guide vane position are not considered in the filter pressure loss model either due to no direct relationship with the air intake system. The filter health parameter ( SF ) is defined in this work to evaluate the degradation state of the air intake system.…”

“…Data-driven method is another common fault diagnosis method, for example, neural networks 19,20 and fuzzy logic. 21 However, take the case of neural networks, data-driven method needs a lot of failure data to train the model, and it is usually a black-box model, so the results are poorly interpretable. Hence, GPA method is selected to decouple evaluation index and external factors in this paper.…”

Machine-Learning-Based Condition Assessment of Gas Turbines—A Review

“…A prognostic approach based on a multiple-input and single-output (MISO) fuzzy logic model was suggested in [100] to estimate the pressure difference across a GT filter house in a heavy-duty power-generation system. The associated results revealed that the proposed fuzzy logic model returned very small deviations and showed a higher predictive performance than conventional multiple regression methodologies.…”

“…Pınar Tüfekci [97] 2014 Several ML algorithms Full-load electrical power prediction Martha A. Zaidan et al [93] 2015 Bayesian hierarchical model RUL inference S. Kiakojoori and K. Khorasani [91] 2016 NARX, Elman NN Estimation of compressor fouling and turbine erosion dynamic degradation Apeksha Wankhede and Vilas Ghate [98] 2018 ANN Electrical power prediction Iman Koleini et al [102] 2018 MRP, ANN EGT prediction based on shaft velocity Divish Rengasamy et al [92] 2020 DNN, CNN, LSTM RUL prediction Zuming Liu and Iftekhar A. Karimi [94] 2020 HDMR + ANN Compressor and turbine operation characteristics prediction Thambirajah Ravichandran et al [95] 2020 OLS + MCDM Short-and long-term degradation estimation Salama Alketbi et al [96] 2020 RF Electrical power prediction Maria Grazia De Giorgi and Marco Quarta [99] 2020 MGGP + NARX EGT prediction Sabah Ahmed Abdul-Wahab et al [100] 2020 MISO fuzzy logic Pressure difference of GT filter estimation Yeseul Park et al [101] 2020 ANN Combustor performance prediction Tomas Olsson et al [90] 2021 RNN Micro-GT degradation prediction…”