Multi-objective Optimization for Fault Detection Using a Multivariable Wavelet Identification Procedure

نویسندگان

  • Marco Aparecido Queiroz Duarte
  • Roberto Kawakami Harrop Galvão
  • Henrique Mohallem Paiva
چکیده

This paper presents a multi-objective wavelet identification procedure for fault detection in dynamic systems. For this purpose, a multi-objective genetic algorithm is used to search for the Pareto frontier. Two objectives are taken into account, the minimization of the residual signal in nominal operating conditions and its maximization in faulty operating conditions. Thus, the proposed approach takes into account the effect of the fault in the residue. The multivariable consistency check is compared with single variable consistency checks to characterize the advantage of the multivariable approach, providing better fault detection results. For illustration, a simulated example involving the detection of a sensor fault in 747 aircraft is presented. Keywords— Fault Detection, Pareto Frontier, Dynamic Systems, Wavelets, Multi-objective Optimization. Resumo— Este artigo apresenta um procedimento multiobjetivo de identificação de parâmetros wavelets para a detecção de falhas em sistemas dinâmicos. Para isto, um algoritmo genético multiobjetivo é usado na busca pela fronteira de Pareto. Dois objetivos são levados em conta, a minimização do sinal residual em condições normais de operação e a sua maximização em condições de falha. Assim, o método proposto leva em consideração o efeito da falha no reśıduo. A verificação de consistência multivariável é comparada com a verificação de única variável para mostrar que esta é vantajosa sobre a segunda, levando a melhores resultados na detecção de falhas. Para ilustração, um exemplo simulado envolvendo a detecção de falha em um sensor em uma aeronave 747 é apresentado. Keywords— Detecção de Falhas, Fronteira de Pareto, Sistemas Dinâmicos, Wavelets, Otimização Multiobjetivo.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Fault diagnosis of gearboxes using LSSVM and WPT

This paper concentrates on a new procedure which experimentally recognises gears and bearings faults of a typical gearbox system using a least square support vector machine (LSSVM). Two wavelet selection criteria Maximum Energy to Shannon Entropy ratio and Maximum Relative Wavelet Energy are used and compared to select an appropriate wavelet for feature extraction. The fault diagnosis method co...

متن کامل

A Novel Methodology for Structural Matrix Identification using Wavelet Transform Optimized by Genetic Algorithm

With the development of the technology and increase of human dependency on structures, healthy structures play an important role in people lives and communications. Hence, structural health monitoring has been attracted strongly in recent decades. Improvement of measuring instruments made signal processing as a powerful tool in structural heath monitoring. Wavelet transform invention causes a g...

متن کامل

Fault Detection of Plain Circular Knitted Fabrics Using Wavelet Transform

Quality control of textile products is an important stage in textile industries. To this end, the conventional method in fault detection is human inspection. In the present work, Wavelet transform was applied on images of simple circular knitted fabrics to diagnose five regular defects. The results showed that the method applied was accurate and fast in addition to being capable of determining ...

متن کامل

Fault Detection of Plain Circular Knitted Fabrics Using Wavelet Transform

Quality control of textile products is an important stage in textile industries. To this end, the conventional method in fault detection is human inspection. In the present work, Wavelet transform was applied on images of simple circular knitted fabrics to diagnose five regular defects. The results showed that the method applied was accurate and fast in addition to being capable of determining ...

متن کامل

Studying Influence of Preheating Conditions on Design Parameters of Continuous Paint Cure Ovens

This paper concentrates on a new procedure which experimentally recognises gears and bearings faults of a typical gearbox system using a least square support vector machine (LSSVM). Two wavelet selection criteria Maximum Energy to Shannon Entropy ratio and Maximum Relative Wavelet Energy are used and compared to select an appropriate wavelet for feature extraction. The fault diagnosis method co...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013