Prediction of compressor nominal characteristics of a turboprop engine using artificial neural networks for build standard assessment

Abstract

Compressor characteristics of a single spool turboprop engine have been studied in this paper. It has been brought outhow constant power lines in the compressor characteristics of these compressors make them different from others. Constant speed lines and constant power lines have also been highlighted. A novel method of modeling of compressorof a single spool turboprop engine has also been studied in this paper. Application of neural networks in prediction of compressor characteristics has been investigated. Multilayer Perceptron feed forward neural network has been considered with different transfer functions to assess the potential capability of network in extrapolation and interpolation. Effectiveness of prediction with and without engine bleed valve open and anti-ice valve open situations have been assessed. Network Predictionshas been compared with engine test data to assess the accuracy of prediction and to quantify the build variation in the manufacture of engines. Capability of network with limited test data to predict the complete performance has also been assessed and presented in this paper.

Noise‐robust gas path fault detection and isolation for a power generation gas turbine based on deep residual compensation extreme learning machine

“…Recent applications include predicting the remaining useful life of drilling pumps, 13 identifying sensor anomalies in internal combustion engines, 14 enabling fault detection and isolation of water reactors, 15 and vessels, 16 and even facilitating sensor fault diagnosis of autonomous vehicles 17 . In the context of equipment like gas turbines, which exhibit nonlinear behavior, these machine learning tools offer the capability to accurately simulate the inherent nonlinear nature of the data 18 . In this context, Fentaye et al recently estimated the magnitude of gas path faults by using a multilayer perceptron 19 .…”

“…17 In the context of equipment like gas turbines, which exhibit nonlinear behavior, these machine learning tools offer the capability to accurately simulate the inherent nonlinear nature of the data. 18 In this context, Fentaye et al recently estimated the magnitude of gas path faults by using a multilayer perceptron. 19 To achieve a higher success rate (SR) in fault classification, Togni et al recently used an artificial neural network in combination with a fuzzy system and the Kalman filter method to detect faults in a two-shaft engine.…”