Vibration Based Fault Detection of Centrifugal Pump by Fast Fourier Transform and Adaptive Neuro-Fuzzy Inference System

Farokhzad, Saeid

doi:10.18005/jmet0103001

Cited by 30 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Frequency analysis is considered to be the most traditional method which can be employed for analyzing the vibration signals [61][62][63]. Fourier analysis transforms a signal from its original domain (usually space or time) into frequency domain and vice versa.…”

Section: Vibration Analysis Techniques For Fault Detection 31 Fast Fourier Transform (Fft)mentioning

confidence: 99%

Fault Diagnosis in Rotating System Based on Vibration Analysis

AbdulBary

Embaby

Gomaa

2021

ERJ. Engineering Research Journal

View full text Add to dashboard Cite

Vibration is one of the major parameters to consider in condition monitoring of rotating systems. If an undetected fault is noticed in the rotating system, then, at best, the issue will not be too significant and can be remedied cheaply and quickly; at worst case, it may result in down-time, expensive damage, injury, or even life loss, therefore early fault identification is a critical factor in ensuring and extending the working life of the rotating systems. By measurement and analysis of the vibration of rotating machinery, it is possible to detect and locate important faults such as mass unbalance, misalignment, bearing failure, gear faults and rotor cracks. This article is aimed to guide the researchers to implement identification, diagnosis and remedy techniques of common fault types using vibration analysis and outlines many important techniques used for condition monitoring of rotating systems such as fast Fourier transform, frequency domain decomposition method, wavelet transform, stochastic subspace identification and deep learning.

show abstract

Section: Vibration Analysis Techniques For Fault Detection 31 Fast Fourier Transform (Fft)mentioning

confidence: 99%

Fault Diagnosis in Rotating System Based on Vibration Analysis

AbdulBary

Embaby

Gomaa

2021

ERJ. Engineering Research Journal

View full text Add to dashboard Cite

show abstract

“…Syafutra [7] melakukan penelitian mendeteksi kavitasi pada pompa sentrifugal dengan metode FFT. Farokhzad [8] menggunakan metode Adaptive Network Fuzzy Inference System (ANFIS) untuk mendeteksi kerusakan pada pompa sentrifugal. Dengan teknik FFT, dia mengekstrak fitur-fitur yang akan digunakan sebagai vektor input ke dalam ANFIS.…”

Section: Pendahuluanunclassified

Ekstraksi Parameter Statistik Domain Waktu dan Domain Frekuensi untuk Mendeteksi Kavitasi pada Pompa Sentrifugal Berbasis Principal Component Analysis (PCA)

Kamiel

Prastomo

Riyanta

2019

JRM

View full text Add to dashboard Cite

“…For data acquisition, an accelerometer is commonly used to measure vibrations. [5][6][7][8][9][10][11] In data analysis, three main analysis methods have been applied in time domain, 6,10,12 frequency domain, [9][10][11][12][13] and time-frequency domain. [14][15][16][17] Fast Fourier Transform (FFT) is a frequency domain algorithm that has been used successfully for extracting statistical parameters, as it is able to present physical characteristics of frequency domain data.…”

Section: Introductionmentioning

confidence: 99%

“…Automatic fault classification has been implemented and investigated using many machinery fault diagnostic methods, in order to improve precision and reduce mistakes caused due to human misinterpretation. 10 Previously, discrete wavelet transform (DWT) has been applied by many researchers for applications of rotating machinery, accountability diagnosis combined with AI systems. 7,[24][25][26] Srinivas et al 27 proposed MLP and DWT based on Daubechies wavelet function to diagnose faults on rotor unbalance and shaft bent.…”

Section: Introductionmentioning

confidence: 99%

Faults diagnosis of a centrifugal pump using multilayer perceptron genetic algorithm back propagation and support vector machine with discrete wavelet transform‐based feature extraction

Tobi

Bevan

Wallace

et al. 2020

Computational Intelligence

View full text Add to dashboard Cite

This paper presents a comparative study of two artificial intelligent systems, namely; Multilayer Perceptron (MLP) and support vector machine (SVM), to classify six fault conditions and the normal (nonfaulty) condition of a centrifugal pump. A hybrid training method for MLP is proposed for this work based on the combination of Back Propagation (BP) and Genetic Algorithm (GA). The two training algorithms are tested and compared separately as well. Features are extracted using Discrete Wavelet Transform (DWT), both approximations, details, and two mother wavelets were used to investigate their effectiveness on feature extraction. GA is also used to optimize the number of hidden layers and neurons of MLP. In this study, the feature extraction, GA-based hidden layers, neurons selection, training algorithm, and classification performance, based on the strengths and weaknesses of each method, are discussed. From the results obtained, it is observed that

show abstract

Vibration Based Fault Detection of Centrifugal Pump by Fast Fourier Transform and Adaptive Neuro-Fuzzy Inference System

Cited by 30 publications

References 8 publications

Fault Diagnosis in Rotating System Based on Vibration Analysis

Fault Diagnosis in Rotating System Based on Vibration Analysis

Ekstraksi Parameter Statistik Domain Waktu dan Domain Frekuensi untuk Mendeteksi Kavitasi pada Pompa Sentrifugal Berbasis Principal Component Analysis (PCA)

Faults diagnosis of a centrifugal pump using multilayer perceptron genetic algorithm back propagation and support vector machine with discrete wavelet transform‐based feature extraction

Contact Info

Product

Resources

About