Neural network monitoring system used for the frequency vibration prediction in gas turbine

Rahmoune, Mohamed Ben; Hafaifa, Ahmed; Guemana, Mouloud

doi:10.1109/ceit.2015.7233185

Cited by 9 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods of nonlinear identification of stiffness characteristics of bearing supports were also developed in the works [8,9,10]. Upto-date trends in the field of rotor dynamics analysis are discovered in the research papers [11,12,13].…”

Section: Literature Reviewmentioning

confidence: 99%

Ensuring the Vibration Reliability of Rotors Connected by Spline Joints

Verbovyi

Neamțu

Sieryk

et al. 2019

JES

View full text Add to dashboard Cite

This article is devoted to the development of refined numerical mathematical models of rotor dynamics of high-performance turbomachines having a spline connection. These models consider the dependence of the critical frequencies of the shaft on the angular stiffness of the spline connection, as well as the procedure of virtual balancing. As a result of the complex application of this approach, the methods of calculation of vibration characteristics taking into ac-count variable values of angular rigidity of splined connection are offered. In addition, the method of evaluating the system of initial imbalances with the corresponding displacements of the rotor axis in the correction and calculation sections has also been improved. The proposed approaches, based on the integrated application of CAE software and computational intelligent systems, allow for modal and harmonic analysis and implement virtual balancing with a significant reduction in preparation and machine time without loss of relative accuracy. In addition, the developed mathematical model of free and forced vibrations of rotor systems have been implemented in the program code operational files “Critical Frequencies of the Rotor” and “Forced Oscillations of the Rotor” of the computer algebra system MathCAD that allows improving the dynamic balancing procedure for evaluating primary imbalances. The high accuracy of the proposed approach is confirmed by checking the dynamic deviations of the rotor axis by the system of residual imbalances in accordance with the standards of vibration stability. Keywords: turbomachine, spline connection, angular stiffness, virtual balancing, modal analysis, harmonic analysis.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Ensuring the Vibration Reliability of Rotors Connected by Spline Joints

Verbovyi

Neamțu

Sieryk

et al. 2019

JES

View full text Add to dashboard Cite

show abstract

“…There are many works in the literature regarding the usage of static neural networks in modelling and simulation of industrial gas turbine engines. (Fast et al 2009, Rahmoune et al 2015) are considered to be major research activities in this area. These works are based on feed-forward NNs, with a single hidden layer and different numbers of neurons, trained by using a back propagation learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Real time modeling and Hardware in the loop simulation of an aero-derivative gas turbine engine

Ibrahem¹,

Akhrif²,

Moustapha³

et al. 2020

Proceedings of Global Power &Amp; Propulsion Society

View full text Add to dashboard Cite

Modelling and simulation of gas turbines plays a key role in manufacturing and improving performance of gas turbine engines. In recent years, the importance of ADGTEs in the energy industry has sparked a great interest among manufacturers to improve the performance and increase the reliability of the engine, which in turn requires an accurate and real time model to simulate the engine dynamics during the full operating range. For this purpose, a real-time modelling and hardware in the loop (HIL) simulation of an aero-derivative gas turbine engine (ADGTE) are developed in this paper. A non-linear autoregressive network with exogenous inputs (NARX) is used to develop this model in MATLAB environment using operational closed-loop data collected from Siemens (SGT-A65) three-spool dry low emission ADGTE. A multiple-input single-output (MISO) NARX models with different configurations are used to represent each of the ADGTE output parameters with the same input parameters. First, data preprocessing and estimation of the order of these MISO models are performed. Next, a comprehensive computer program code is developed to perform a comparative study and to select the best NARX model configuration, which can represent the system dynamics. Finally, to demonstrate the performance of the MISO NARX model developed in this study, a HIL simulation is performed. In this simulation, the physical ADGTE is replaced with the MISO NARX model, and the physical engine controller is used to control that model. In addition, the neural model is validated with experimental data. The simulation results show that the proposed MISO NARX models followed the targets precisely and can predict the response with high accuracy and reliability. In addition, the proposed model presents high computation speed, which allows for real time applications.

show abstract

“…Then, artificial intelligent techniques (machine learning models) can provide promising results to identify the vibration features in a turbine generator, such as artificial neural networks, fuzzy neural networks, and wavelet neural networks. (8)(9)(10)(11) From practical records, big data analysis and collection can extract the key frequency features to separate the normal condition from any fault. The characteristic features are extracted using the FFT method, including the frequencies 1 × f, 2 × f, 3 × f, ..., and 9 × f, where the frequency f is 60 Hz.…”

Section: Introductionmentioning

confidence: 99%

Mechanical Vibration Fault Detection for Turbine Generator Using Frequency Spectral Data and Machine Learning Model: Feasibility Study of Big Data Analysis

2018

Sensors and Materials

View full text Add to dashboard Cite

Keywords: vibration signal, mechanical vibration fault, frequency spectral data, radial-based color relation analysisThe frequency spectra of vibration signals can be used to monitor the mechanical conditions of a turbine generator. Frequency-based features are extracted by fast Fourier transformation (FFT). The changes in frequency spectral data and amplitude are used to separate the normal condition from the fault conditions. These features indicate that the characteristic frequencies are 1 × f, 2 × f, 3 × f, and two other frequency bands, < 0.4 × f and > 3 × f, where the frequency f is the rotor frequency. The power spectral data shows the mechanical vibration fault at particular characteristic frequencies. Then, radial-based color relation analysis (CRA) is applied to identify mechanical faults, including normal condition, oil-membrane oscillation, imbalance, and no orderliness. Using practical records, the experimental results will show that the proposed method has a higher accuracy in mechanical vibration fault detection.

show abstract

Neural network monitoring system used for the frequency vibration prediction in gas turbine

Cited by 9 publications

References 17 publications

Ensuring the Vibration Reliability of Rotors Connected by Spline Joints

Ensuring the Vibration Reliability of Rotors Connected by Spline Joints

Real time modeling and Hardware in the loop simulation of an aero-derivative gas turbine engine

Mechanical Vibration Fault Detection for Turbine Generator Using Frequency Spectral Data and Machine Learning Model: Feasibility Study of Big Data Analysis

Contact Info

Product

Resources

About