Adaptive sliding mode observer for sensor fault diagnosis of an industrial gas turbine

In this paper, a controller is recommended for the regulation of two electrical plants. Since electrical plants generate electricity all the time, the regulation to get that all the plant states reach constant behaviors is important. Two main characteristics of the introduced method are: (i) it is based in the separation of the plant model equations, only some model equations are chosen for the regulation while the other model equations are ignored, it avoids the difficulty in the consideration of the full plant model; (ii) the Lyapunov strategy is employed to analyze the stability of the selected model equations in the electrical plant, it lets to ensure the regulation purpose. The advised method is applied in a gas turbine and a wind turbine for the electricity generation.

show abstract

“…In [1] and [2], mathematical models of the gas turbines are described. In [1] and [2], mathematical models of the gas turbines are described.…”

Section: Introductionmentioning

confidence: 99%

Control of two Electrical Plants

Rubio¹,

López

Pacheco³

et al. 2017

Asian Journal of Control

View full text Add to dashboard Cite

show abstract

“…Recently, a large variety of methods for sensor validation have been introduced in the literature; these methods can be grouped into two categories: modeldriven methods and data-driven methods (Rahme and Meskin, 2015). The model-driven methods use mathematical linear or nonlinear representation based on the chemical and physical principles underlying the process (Bastin and Gevers, 1988;Winkler et al, 2010;Pantelides and Renfro, 2013).…”

Section: Introductionmentioning

confidence: 99%

“…However, this method is only effective for linear systems, and has the same drawbacks as other multiple-model methods. The main drawback of all multiple-model approaches is the redundancy of using a bank of diagnosing systems (Rahme and Meskin, 2015). This paper proposes a new modeling method for validating single or multiple sensor fault(s) in nonlinear systems, based on a robust ITNN (RITNN).…”

Section: Introductionmentioning

confidence: 99%

Multiple Sensor Validation for Natural Gas Combined Cycle Power Plants Based on Robust Input Training Neural Networks

Ren

2017

J. Chem. Eng. Japan / JCEJ

View full text Add to dashboard Cite

Modern industrial power plants require continuous monitoring to ensure their safe and reliable operation. This monitoring depends heavily on accurate sensor readings from a large number of sensors, making sensors an important part of any plant. The possibility of more than a single sensor being simultaneously faulty should not be overlooked. In this paper, a nonlinear system data validation approach based on a robust input-training neural network is proposed for detecting, isolating, and reconstructing multiple sensor faults in a power plant. An in uence factor function and reliability coe cients were introduced into an objective function for the purpose of inhibiting the in uence of numerous failure data with signi cant errors. The proposed method was evaluated on a single-shaft gas turbine from a natural gas combined cycle power plant. The result shows that the proposed model has a high degree of accuracy in multiple sensor failure cases.

show abstract

“…The fuzzy c-means clustering requires the existence of a multiple input and output data for the validations tests. This structure is used like an initial fuzzy inference system for the preparation of the adaptive fuzzy neural network inference system [18][19][20].…”

Section: Gas Turbine Modelingmentioning

confidence: 99%

Gas turbine modeling using adaptive fuzzy neural network approach based on measured data classification

Benyounes

Hafaifa

Kouzou

et al. 2016

Mathematics-in-Industry Case Studies

View full text Add to dashboard Cite

The use of gas turbines is widespread in several industries such as; hydrocarbons, aerospace, power generation. However, despite to their many advantages, they are subject to multiple exploitation problem that need to be solved. Indeed, the purpose of the present paper is to develop mathematical models of this industrial system using an adaptive fuzzy neural network inference system. Where the knowledge variables in this complex system are determined from the real time input/output data measurements collected from the plant of the examined gas turbine. It is obvious that the advantage of the neuro-fuzzy modeling is to obtain robust model, which enable a decomposition of a complex system into a set of linear subsystems. On the other side, by focusing on the membership functions for residual generator to get consistent settings based on the used data structure classification and selection, where the main goal is to obtain a robust system information to ensure the supervision of the examined gas turbine.

show abstract

Adaptive sliding mode observer for sensor fault diagnosis of an industrial gas turbine

Cited by 83 publications

References 23 publications

Control of two Electrical Plants

Control of two Electrical Plants

Multiple Sensor Validation for Natural Gas Combined Cycle Power Plants Based on Robust Input Training Neural Networks

Gas turbine modeling using adaptive fuzzy neural network approach based on measured data classification

Contact Info

Product

Resources

About