Fault detection of gas turbine engines using dynamic neural networks

Tayarani-Bathaie, S. Sina; Vanini, Z. N. Sadough; Khorasani, K.

doi:10.1109/ccece.2012.6334837

Cited by 14 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The steam turbine has been largely applied to power plant because of the costs efficiencies with respect to the capacity, application, and desired performance; a different level of complexity is offered for the structure of steam turbines, to increase the thermal efficiency so that the steam turbine consists of high pressure, intermediate pressure, and low pressure stages due to the complexity of turbine structure using artificial neural network to study the performance of steam turbine and more difficultly to predict the effects of proposed control system on the steam turbine in power plant, therefore, developing nonlinear analytical models. Design, synthesis, and performing real-time simulations and monitoring the desired state can be used, these models for control system in power plant [11][12][13][14][15][16][17]. A steam turbine of a 160MW power plant consists of steam extractions, feed water heaters, moisture separators, and the related motives.…”

Section: Simulation Of Steam Turbine Control Systemmentioning

confidence: 99%

Enhancement of Performance for Steam Turbine in Thermal Power Plants Using Artificial Neural Network and Electric Circuit Design

Salim

Faisal

Jawad

2018

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

Design and implantation of electric circuit for enhanced performance of steam power plant and artificial neural networks technique are used to control turbine. Artificial neural networks technique is used to control a lot of industrial models practically. Artificial neural network has been applied to control the important variables of turbine in AL–Dura power plant in Baghdad such as pressure, temperature, speed, and humidity. In this study Simulink model was applied in MATLAB program (v 2014 a) by using artificial neural network (ANN). The method of controlling model is by using NARMA to generate data and train network. ANN is offline. ANN requires data to obtain results and for comparison with actual power plant. The values of the input variables have a large effect on the number of nodes and epochs and in hidden layer of the artificial neural network they also affect performance of ANN. The electric circuit of sensors consists of transformer, DC bridge, and voltage regulator. Comparing the results from modeling by ANN and electric circuit with experimental data reveals a good agreement and the maximum deviation between the experimental data and predicted results from ANN and circuit design is less than 1%. The novelty in this paper is applying NARMA controller for the purpose of enhancement of turbine performance.

show abstract

Section: Simulation Of Steam Turbine Control Systemmentioning

confidence: 99%

Enhancement of Performance for Steam Turbine in Thermal Power Plants Using Artificial Neural Network and Electric Circuit Design

Salim

Faisal

Jawad

2018

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

show abstract

“…Another feasible technique for fault detection in the Exhaust Gas Temperature (EGT) is based on applying a convolutional neural network to obtain the value difference between two consecutive observations in EGT profile, which improves the sensitivity of anomaly detection (Liu, Liu, Yu, Kang, Yan, Wang, and Pecht, 2018). A methodology based on dynamic neural network has been verified and its advantages have been studied in recognizing faults in a turbofan engine (Tayarani-Bathaie, Vanini, and Khorasani, 2012).…”

Section: Introductionmentioning

confidence: 99%

A Field Programmable Gate Array (FPGA) Based Non-Linear Filters for Gas Turbine Prognostics

Nayak

Prasad

Ganguli

2021

IJPHM

View full text Add to dashboard Cite

The removal of noise from signals obtained through the health monitoring systems in gas turbines is an important consideration for accurate prognostics. Several filters have been designed and tested for this purpose, and their performance analysis has been conducted. Linear filters are inefficient in the removal of outliers and noise because they cause smoothening of the sharp features in the signal which can indicate the onset of a fault event. On the other hand, non-linear filters based on image processing methods can provide more precise results for gas turbine health signals. Among others, the weighted recursive median (WRM) filter has been shown to provide greater accuracy due to its weight adaptability depending on the signal type. However, sampling data at high rates is possible which needs hardware implementation of the filter. In this paper, the design, simulation and implementation of WRM filters on the FPGA (Field Programmable Gate Arrays) platforms Vivado Design Suite by Xilinx and Quartus Pro Lite Edition 19.3 has been performed. The architectural detail and performance result with the FPGA filters when subjected to abrupt and gradual fault signal is presented.

show abstract

“…Health monitoring and fault diagnosis of aircraft engines have been widely studied in literature (Litt et al , 2005). Neural networks are most widespread because they provide a viable tool for dealing with nonlinear problems and modelling complex and nonlinear dynamic systems with great flexibility and capability (Tayarani-Bathaie et al , 2012; Dragomir et al , 2009).…”

Section: Introductionmentioning

confidence: 99%

Jet engine degradation prognostic using artificial neural networks

Giorgi

Ficarella

Carlo

2019

AEAT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to propose and develop artificially intelligent methodologies to discover degradation trends through the detection of engine’s status. The objective is to predict these trends by studying their effects on the engine measurable parameters. Design/methodology/approach The method is based on the implementation of an artificial neural network (ANN) trained with well-known cases referred to real conditions, able to recognize degradation because of two main gas turbine engine deterioration effects: erosion and fouling. Three different scenarios are considered: compressor fouling, turbine erosion and presence of both degraded conditions. The work consists of three parts: the first one contains the mathematical model of real jet engine in healthy and degraded conditions, the second step is the optimization of ANN for engine performance prediction and the last part deals with the application of ANN for prediction of engine fault. Findings This study shows that the proposed diagnostic approach has good potential to provide valuable estimation of engine status. Practical implications Knowledge of the true state of the engine is important to assess its performance capability to meet the operational and maintenance requirements and costs. Originality/value The main advantage is that the engine performance data for model validation were obtained from real flight conditions of the engine VIPER 632-43.

show abstract

Fault detection of gas turbine engines using dynamic neural networks

Cited by 14 publications

References 9 publications

Enhancement of Performance for Steam Turbine in Thermal Power Plants Using Artificial Neural Network and Electric Circuit Design

Enhancement of Performance for Steam Turbine in Thermal Power Plants Using Artificial Neural Network and Electric Circuit Design

A Field Programmable Gate Array (FPGA) Based Non-Linear Filters for Gas Turbine Prognostics

Jet engine degradation prognostic using artificial neural networks

Contact Info

Product

Resources

About