scholarly journals Novel Orbit-based CNN Model for Automatic Fault Identification of Rotating Machines

2020 ◽  
Vol 12 (1) ◽  
pp. 7
Author(s):  
Xiaomo Jiang ◽  
Fumin Wang ◽  
Haixin Zhao ◽  
Shengli Xu ◽  
Lin Lin
Keyword(s):  
Condition Monitoring ◽  
Steam Turbines ◽  
Rotating Machines ◽  
Automated Identification ◽  
Centrifugal Compressors ◽  
Vibration Signals ◽  
Vibration Data ◽  
Component Faults ◽  
Bayesian Wavelet ◽  
Fault Information

Various faults in high-fidelity turbomachinery such as steam turbines and centrifugal compressors usually result in unplanned outage thus lowering the reliability and productivity while largely increasing the maintenance costs. Condition monitoring has been increasingly applied to provide early alerting on component faults by using the vibration signals. However, each type of fault in different types of rotating machines usually require an individual model to isolate the damage for accurate condition monitoring, which require costly computation efforts and resources due to the data uncertainties and modeling complexity. This paper presents a generalized deep learning methodology for accurately automatic diagnostics of various faults in general rotating machines by utilizing the shaft orbits generated from vibration signals, considering the high non-linearity and uncertainty of the sensed vibration signals. The sensor anomalies and environmental noise in the vibration signals are first addressed through waveform compensation and Bayesian wavelet noise reduction filtering. Shaft orbit images are generated from the cleansed vibration data collected from different turbomachinery with various fault modes. A multi-layer convolutional neural network model is then developed to classify and identify the shaft orbit images of each fault. Finally, the fault diagnosis of rotating machinery is realized through the automated identification process. The proposed approach retains the fault information in the axis trajectory to the greatest extent, and can adeptly extract and accurately identify features of various faults. The effectiveness and feasibility of the proposed methodology is demonstrated by using the sensed vibration signals collected from real-world centrifugal compressors and steam turbines with different fault modes.

scholarly journals Integrated Fault Detection Framework for Classifying Rotating Machine Faults Using Frequency Domain Data Fusion and Artificial Neural Networks

Machines ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 59 ◽  
Author(s):  
Kenisuomo C. Luwei ◽  
Akilu Yunusa-Kaltungo ◽  
Yusuf A. Sha’aban
Keyword(s):  
Data Fusion ◽  
Condition Monitoring ◽  
Real Life ◽  
General Concept ◽  
Rotating Machines ◽  
Classification Approach ◽  
Vibration Data ◽  
Artificial Neural ◽  
Machine Health ◽  
Artificial Neural Network Ann

The availability of complex rotating machines is vital for the prevention of catastrophic failures in a significant number of industrial operations. Reliability engineering theories stipulate that optimising the mean-time-to-repair (MTTR) for failed machines can immensely boost availability. In practice, however, a significant amount of time is taken to accurately detect and classify rotor-related anomalies which often negate the drive to achieve a truly robust maintenance decision-making system. Earlier studies have attempted to address these limitations by classifying the poly coherent composite spectra (pCCS) features generated at different machine speeds using principal components analysis (PCA). As valuable as the observations obtained were, the PCA-based classifications applied are linear which may or may not limit their applicability to some real-life machine vibration data that are often associated with certain degrees of non-linearities due to faults. Additionally, the PCA-based faults classification approach used in earlier studies sometimes lack the capability to self-learn which implies that routine machine health classifications would be done manually. The initial parts of the current paper were presented in the form of a thorough search of the literature related to the general concept of data fusion approaches in condition monitoring (CM) of rotation machines. Based on the potentials of pCCS features, the later parts of the article are concerned with the application of the same features for the exploration of a simplified two-staged artificial neural network (ANN) classification approach that could pave the way for the automatic classification of rotating machines faults. This preliminary examination of the classification accuracies of the networks at both stages of the algorithm offered encouraging results, as well as indicates a promising potential for this enhanced approach during field-based condition monitoring of critical rotating machines.

Faults Diagnosis in Rotating Machines Using Higher Order Spectra

2014 ◽  
Author(s):  
Akilu Yunusa-Kaltungo ◽  
Jyoti K. Sinha
Keyword(s):  
Signal Processing ◽  
Condition Monitoring ◽  
Transverse Crack ◽  
Higher Order ◽  
Vibration Response ◽  
Rotating Machines ◽  
Vibration Signals ◽  
Faults Diagnosis ◽  
Higher Order Spectra ◽  
Recent Attention

Higher order spectra (HOS) and higher order coherences (HOC) are two classes of higher order signal processing tools that have gained recent attention in the area of rotating machines’ condition monitoring (CM). Hence, the current study compares and presents the results of the performances of both HOS and HOC in the diagnosis of rotating machines’ faults, through the numerically simulated vibration signals and the experimentally measured vibration response on a rotating rig with healthy condition and the rotor with a transverse crack.

Experimental Evaluation of a Structure-Based Connectionist Network for Fault Diagnosis of Helicopter Gearboxes

1998 ◽  
Vol 120 (1) ◽  
pp. 106-112 ◽  
Author(s):  
V. B. Jammu ◽  
K. Danai ◽  
D. G. Lewicki
Keyword(s):  
Fault Diagnosis ◽  
Supervised Learning ◽  
Experimental Evaluation ◽  
Diagnostic System ◽  
Salient Feature ◽  
Connectionist Network ◽  
Vibration Signals ◽  
Preceding Article ◽  
Vibration Data ◽  
Component Faults

This paper presents the experimental evaluation of the Structure-Based Connectionist Network (SBCN) fault diagnostic system introduced in the preceding article (Jammu et al, 1998). For this, vibration data from two different helicopter gearboxes: OH-58A and S-61, are used. A salient feature of SBCN is its reliance on the knowledge of the gearbox structure and the type of features obtained from processed vibration signals as a substitute to training. To formulate this knowledge, approximate vibration transfer models are developed for the two gearboxes and utilized to derive the connection weights representing the influence of component faults on vibration features. The validity of the structural influences is evaluated by comparing them with those obtained from experimental RMS values. These influences are also evaluated by comparing them with the weights of a connectionist network trained through supervised learning. The results indicate general agreement between the modeled and experimentally obtained influences. The vibration data from the two gearboxes are also used to evaluate the performance of SBCN in fault diagnosis. The diagnostic results indicate that the SBCN is effective in detecting the presence of faults and isolating them within gearbox subsystems based on structural influences, but its performance is not as good in isolating faulty components, mainly due to lack of appropriate vibration features.

scholarly journals Effective vibration-based condition monitoring (eVCM) of rotating machines

2017 ◽  
Vol 23 (3) ◽  
pp. 279-296 ◽  
Author(s):  
Akilu Yunusa-kaltungo ◽  
Jyoti K. Sinha
Keyword(s):  
Frequency Domain ◽  
Condition Monitoring ◽  
Lessons Learned ◽  
Practical Implementation ◽  
Rotating Machines ◽  
Data Combination ◽  
Content Type ◽  
Vibration Data ◽  
Rotating Machine ◽  
Faults Diagnosis

Purpose The purpose of this paper is mainly to highlight how a simplified and streamlined approach to the condition monitoring (CM) of industrial rotating machines through the application of frequency domain data combination can effectively enhance the eMaintenance framework. Design/methodology/approach The paper commences by providing an overview to the relevance of maintenance excellence within manufacturing industries, with particular emphasis on the roles that rotating machines CM of rotating machines plays. It then proceeds to provide details of the eMaintenance as well as its possible alignment with the introduced concept of effective vibration-based condition monitoring (eVCM) of rotating machines. The subsequent sections of the paper respectively deal with explanations of data combination approaches, experimental setups used to generate vibration data and the theory of eVCM. Findings This paper investigates how a simplified vibration-based rotating machinery faults classification method based on frequency domain data combination can increase the feasibility and practicality of eMaintenance. Research limitations/implications The eVCM approach is based on classifying data acquired under several experimentally simulated conditions on two different machines using combined higher order signal processing parameters so as to reduce CM data requirements. Although the current study was solely based on the application of vibration data acquired from rotating machines, the knowledge exchange platform that currently dominates present day scientific research makes it very likely that the lessons learned from the development of eVCM concept can be easily transferred to other scientific domains that involve continuous CM such as medicine. Practical implications The concept of eMaintenance as a cost-effective and smart means of increasing the autonomy of maintenance activities within industries is rapidly growing in maintenance-related literatures. As viable as the concept appears, the achievement of its optimum objectives and full deployment to the industry is still subjective due to the complexity and data intensiveness of conventional CM practices. In this paper, an eVCM approach is proposed so that rotating machine faults can be effectively detected and classified without the need for repetitive analysis of measured data. Social implications The main strength of eVCM lies in the fact that it permits the sharing of historical vibration data between identical rotating machines irrespective of their foundation structures and speed differences. Since eMaintenance is concerned with driving maintenance excellence, eVCM can potentially contribute towards its optimisation as it cost-effectively streamlines faults diagnosis. This therefore implies that the simplification of vibration-based CM of rotating machines positively impacts the society with regard to the possibility of reducing how much time is actually spent on the accurate detection and classification of faults. Originality/value Although the currently existing body of literature already contains studies that have attempted to show how the combination of measured vibration data from several industrial machines can be used to establish a universal vibration-based faults diagnosis benchmark for incorporation into eMaintenance framework, these studies are limited in the scope of faults, severity and rotational speeds considered. In the current study, the concept of multi-faults, multi-sensor, multi-speed and multi-rotating machine data combination approach using frequency domain data fusion and principal components analysis is presented so that faults diagnosis features for identical rotating machines with different foundations can be shared between industrial plants. Hence, the value of the current study particularly lies in the fact that it significantly highlights a new dimension through which the practical implementation and operation of eMaintenance can be realized using big data management and data combination approaches.

scholarly journals Fault severity detection of a worm gearbox based on several feature extraction methods through a developed condition monitoring system

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Berkan Hızarcı ◽  
Rafet Can Ümütlü ◽  
Zeki Kıral ◽  
Hasan Öztürk
Keyword(s):  
Fault Detection ◽  
Condition Monitoring ◽  
Extraction Methods ◽  
Poincaré Plot ◽  
Vibration Data ◽  
Sliding Motion ◽  
Fault Severity ◽  
Fault Features ◽  
Gearbox Vibration ◽  
Condition Monitoring System

AbstractThis study presents the severity detection of pitting faults on worm gearbox through the assessment of fault features extracted from the gearbox vibration data. Fault severity assessment on worm gearbox is conducted by the developed condition monitoring instrument with observing not only traditional but also multidisciplinary features. It is well known that the sliding motion between the worm gear and wheel gear causes difficulties about fault detection on worm gearboxes. Therefore, continuous monitoring and observation of different types of fault features are very important, especially for worm gearboxes. Therefore, in this study, time-domain statistics, the features of evaluated vibration analysis method and Poincaré plot are examined for fault severity detection on worm gearbox. The most reliable features for fault detection on worm gearbox are determined via the parallel coordinate plot. The abnormality detection during worm gearbox operation with the developed system is performed successfully by means of a decision tree.

Condition Monitoring of Wind Turbines Based on the Scattering Transform of Vibration Data

2021 ◽  
Author(s):  
Junyu Qi ◽  
Alexandre Mauricio ◽  
Konstantinos Gryllias
Keyword(s):  
Condition Monitoring ◽  
Wind Turbines ◽  
Wind Farms ◽  
Operating Conditions ◽  
Vibration Data ◽  
Bearing Diagnostics ◽  
Scattering Transform ◽  
The One ◽  
Envelope Spectrum ◽  
High Effort

Abstract As a renewable, unlimited and free resource, wind energy has been intensively deployed in the past to generate electricity. However, the maintenance of Wind Turbines (WTs) can be challengeable. On the one hand, most wind farms operate in remote areas and on the other hand, the dimension of WTs’ tip/hub/rotor are usually enormous. In order to prevent abrupt breakdowns of WTs, a number of Condition Monitoring (CM) methods have been proposed. Focusing on bearing diagnostics, Squared Envelope Spectrum is one of the most common techniques. Moreover in order to identify the optimum demodulation frequency band, fast Kurtogram, Infogram and Sparsogram are nowadays popular tools evaluating respectively the Kurtosis, the Negentropy and the Sparsity. The analysis of WTs usually requires high effort due to the complexity of the drivetrain and the varying operating conditions and therefore there is still need for research on effective and reliable CM techniques for WT monitoring. Thus the purpose of this paper is to investigate a blind and effective CM approach based on the Scattering Transform. Through the comparison with state of the art techniques, the proposed methodology is found more powerful to detect a fault on six validated WT datasets.

Sign in / Sign up

Export Citation Format

Share Document