Detection of rotor faults based on Hilbert Transform and neural network for an induction machine

Bensaoucha, Saddam; Ameur, A.; Ahmed, Bessedik Sid; Seghiour, Abdellatif

doi:10.1109/icee-b.2017.8192029

Cited by 11 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pontos adicionais das particularidades da aplicação do motor são tratados como dificuldades extras e intensificam a complexidade desta metodologia, uma vez que há necessidade de estar definida a velocidade de operação da máquina e estabelecida a frequência específica a se observar, além de necessidade de um processamento de alta resolução dos sinais para um diagnóstico mais preciso, como são afirmados em Saddam et al (2017) e Martin-Diaz et al (2017. Ainda, em Bellini et al (2008) fica evidenciado que este método funciona corretamente quando o MI está em estágio avançado de deterioração.…”

Section: Figura 1 Percentual De Falhas Em MI Por Origemunclassified

Harmônicos de Referência Observados por Sistemas Inteligentes na Identificação de Falhas Elétricas em Motores de Indução

Gongora¹,

Silva

Goedtel

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

This article presents a methodology for the classification of electric faults in induction motors through the treatment of search harmonic reference signals injected into the machine's power supply. The proposal is based on the observation by intelligent sistems of the electric current signals of the motor, preprocessed by the FFT and with the analysis of the signature components of the machine. However, the supply voltage signals are multiplexed with harmonic reference signals inserted by the frequency converter module of the machine itself. In order to improve accuracy in fault classification and diagnose degradation status, as well as to attest to the functionality of the method, the practical data of the actual application of the system in the laboratory are processed by different intelligent systems. In this aspect of generalization of the proposal the results are validated by different algorithms whose performances are compared between the following methods: k-nearest neighbors, Naive Bayes, Support Vector Machine, Multilayer Perceptron and Decision tree. Resumo: Este artigo apresenta uma metodologia para a classificação de falhas elétricas em motores de indução através do tratamento de sinais harmônicos de referência de busca injetados pela fonte de alimentação da máquina. A proposta baseia-se na observação por sistemas inteligentes dos sinais de corrente elétrica do motor, pré-processados pela FFT e com a análise das componentes de assinatura da máquina. Para tanto, os sinais de tensão de alimentação são multiplexados com sinais de referência harmônica inseridos pelo próprio módulo inversor de frequência da máquina. Buscando melhorar a precisão na classificação de falhas e diagnosticar o estado de degradação, bem como atestar a funcionalidade do método, dados práticos da aplicação real do sistema em laboratório são processados por sistemas inteligentes distintos. Neste aspecto de generalização da proposta os resultados são validados por diferentes algoritmos cujos desempenhos são comparados entre os seguintes métodos: k-vizinhos mais próximos, Naive Bayes, Máquina de Vetor de Suporte, Perceptron multicamadas eÁrvore de Decisão.

show abstract

Section: Figura 1 Percentual De Falhas Em MI Por Origemunclassified

Harmônicos de Referência Observados por Sistemas Inteligentes na Identificação de Falhas Elétricas em Motores de Indução

Gongora¹,

Silva

Goedtel

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

show abstract

“…Furthermore, regarding the traditional methodology of MCSA, according to the literature, for a more accurate fault diagnosis in rotating electrical machines, a high-resolution processing, as shown in Martin-Diaz et al (2017), and sensor speed monitoring are needed to determine the specific frequency of analysis (Saddam et al 2017). The authors in Gritli et al (2017) also point out that the current signal analysis used to detect faults works properly when the IM is extremely damaged.…”

Section: Introductionmentioning

confidence: 99%

Reference Signal Injection in Induction Motors Drives to Electrical Failures Detection

Gongora

Silva

Goedtel

et al. 2019

J Control Autom Electr Syst

View full text Add to dashboard Cite

This paper shows an alternative method to electrical fault diagnosis in three-phase induction motors using reference signal injection. The proposal is based on the insertion of search reference harmonic signals in the supply voltage by the frequency inverter module of the induction machine and the observation of the signals of the electric current of the motor, preprocessed through the FFT and machine signature component analysis. In order to obtain a greater precision of fault classification and state of degradation through intelligent systems, results are validated by different algorithms whose performance are compared in the following methods: k nearest neighbors, naive Bayes, support vector machine, multilayer perceptron and decision tree. The practical results for the tests with controlled simulation of the electrical faults of broken rotor bars and short circuit in stator windings show the capacity that this insertion technique has when it is used as a tool to diagnose three-phase induction motors. The five proposals of intelligent systems result in a classification with success rates of 93% to 100% in different classes, separated into types of faults and according to the degradation intensity.

show abstract

“…Particularly, squirrel cage induction motors' (SCIMs) use is widespread in many processes, by virtue of their simple construction, low-cost manufacturing, reduced downtime and cheap maintenance (Karmakar et al, 2016;Thomson and Fenger, 2001;Benbouzid and Kliman, 2003). Despite the above-cited advantages, many faults may appear on an SCIM, which can be classified into mechanical faults (40-50 per cent of all faults), electrical faults as the stator faults (30-40 per cent), and the rotor cage faults which is the most rugged part of the SCIM (5-10 per cent of the reported faults) (Saddam et al, 2017;Puche-Panadero et al, 2009;Jaksch, 2003). For such reasons, the monitoring of SCIMs has become a permanent concern.…”

Section: Introductionmentioning

confidence: 99%

“…This method is based on the processing of signals obtained from the sensors of various physical quantities of the machine, such as stator lines currents, instantaneous power, rotational speed, axial flux and vibrational effects generated by machine faults (Karmakar et al, 2016;Cardoso et al, 1999;Lamim Filho et al, 2016). The obtained signals are analyzed using different diagnostic techniques, such as fast Fourier transform (FFT) method (Benbouzid and Kliman, 2003), shorttime Fourier transform (Benbouzid and Kliman, 2003), Hilbert Transform (HT) (Saddam et al, 2017;Jaksch, 2003;Puche-Panadero et al, 2009), Hilbert-Huang transform (Elbouchikhi et al, 2017) and Park's vector approach (PVA) (Perez-Cruz et al, 2017;Cardoso et al, 1999;Benbouzid and Kliman, 2003;Xu et al, 2013;Jaksch, 2003). MCSA has the advantage of being an independent internal flow system and does not need the machine to be turned off; therefore, the information carried by the signals will not be affected by the possible modeling error (Puche-Panadero et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

“…Recently, the stator current modulus obtained via HT or PVA, based on the three-phase stator currents analysis, had been widely used to detect SCIM faults. It is highly recommended to use the FFT spectrum analysis of the signal modulus for SCIM faults, which is considered as effective alternative to the classical FFT applied directly on stator current signal, especially when the machine operates in low-load conditions (Xu et al, 2013;Saddam et al, 2017;Puche-Panadero et al, 2009;Jaksch, 2003;Benbouzid and Kliman, 2003;Elbouchikhi et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Induction motors broken rotor bars detection using RPVM and neural network

Bensaoucha

Bessedik

Ameur

et al. 2019

COMPEL

View full text Add to dashboard Cite

Purpose The purpose of this study aims to focus on the detection and identification of the broken rotor bars (BRBs) of a squirrel cage induction motor (SCIM). The presented diagnosis technique is based on artificial neural networks (NNs) that use as inputs the results of the spectral analysis using the fast Fourier transform (FFT) of the reduced Park’s vector modulus (RPVM), along with the load values in which the motor operates. Design/methodology/approach First, this paper presents a comparative study between FFT applied on Hilbert modulus, Park’s vector modulus and RPVM to extract feature frequencies of BRB faults. Moreover, the extracted features of FFT applied to RPVM and the load values were selected as NNs’ inputs for the detection of the number of BRBs. Findings The obtained simulation results using MATLAB (Matrix Laboratory) environment show the effectiveness and accuracy of the proposed NNs based approach. Originality/value The current paper presents a novel diagnostic method for BRBs’ fault detection in SCIM, based on the combination between the signal processing analysis (FFT of RPVM) and artificial intelligence (NNs).

show abstract

Detection of rotor faults based on Hilbert Transform and neural network for an induction machine

Cited by 11 publications

References 12 publications

Harmônicos de Referência Observados por Sistemas Inteligentes na Identificação de Falhas Elétricas em Motores de Indução

Harmônicos de Referência Observados por Sistemas Inteligentes na Identificação de Falhas Elétricas em Motores de Indução

Reference Signal Injection in Induction Motors Drives to Electrical Failures Detection

Induction motors broken rotor bars detection using RPVM and neural network

Contact Info

Product

Resources

About