Evaluation of Novelty Detection Methods for Condition Monitoring applied to an Electromechanical System

Condition monitoring is an indispensable element related to the operation of rotating machinery. In this article, the monitoring system for the parallel gearbox was proposed. The novelty detection approach is used to develop the condition assessment support system, which requires data collection for a healthy structure. The measured signals were processed to extract quantitative indicators sensitive to the type of damage occurring in this type of structure. The indicator’s values were used for the development of four different novelty detection algorithms. Presented novelty detection models operate on three principles: feature space distance, probability distribution, and input reconstruction. One of the distance-based models is adaptive, adjusting to new data flowing in the form of a stream. The authors test the developed algorithms on experimental and simulation data with a similar distribution, using the training set consisting mainly of samples generated by the simulator. Presented in the article results demonstrate the effectiveness of the trained models on both data sets.

Download Full-text

Evaluation of Novelty Detection Methods in On-Body Smartphone Localization Problem

2019 IEEE 8th Global Conference on Consumer Electronics (GCCE) ◽

10.1109/gcce46687.2019.9015347 ◽

2019 ◽

Cited By ~ 1

Author(s):

Mitsuaki Saito ◽

Kaori Fujinami

Keyword(s):

Novelty Detection ◽

Detection Methods ◽

Localization Problem

Download Full-text

Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

Energies ◽

10.3390/en13061474 ◽

2020 ◽

Vol 13 (6) ◽

pp. 1474 ◽

Cited By ~ 4

Author(s):

Francesco Castellani ◽

Luigi Garibaldi ◽

Alessandro Paolo Daga ◽

Davide Astolfi ◽

Francesco Natili

Keyword(s):

Wind Turbine ◽

Condition Monitoring ◽

Wind Turbines ◽

Statistical Tests ◽

Novelty Detection ◽

General Idea ◽

Data Set ◽

Vibration Measurements ◽

Bearing Fault ◽

Operation Conditions

Condition monitoring of gear-based mechanical systems in non-stationary operation conditions is in general very challenging. This issue is particularly important for wind energy technology because most of the modern wind turbines are geared and gearbox damages account for at least the 20% of their unavailability time. In this work, a new method for the diagnosis of drive-train bearings damages is proposed: the general idea is that vibrations are measured at the tower instead of at the gearbox. This implies that measurements can be performed without impacting the wind turbine operation. The test case considered in this work is a wind farm owned by the Renvico company, featuring six wind turbines with 2 MW of rated power each. A measurement campaign has been conducted in winter 2019 and vibration measurements have been acquired at five wind turbines in the farm. The rationale for this choice is that, when the measurements have been acquired, three wind turbines were healthy, one wind turbine had recently recovered from a planetary bearing fault, and one wind turbine was undergoing a high speed shaft bearing fault. The healthy wind turbines are selected as references and the damaged and recovered are selected as targets: vibration measurements are processed through a multivariate Novelty Detection algorithm in the feature space, with the objective of distinguishing the target wind turbines with respect to the reference ones. The application of this algorithm is justified by univariate statistical tests on the selected time-domain features and by a visual inspection of the data set via Principal Component Analysis. Finally, a novelty index based on the Mahalanobis distance is used to detect the anomalous conditions at the damaged wind turbine. The main result of the study is that the statistical novelty of the damaged wind turbine data set arises clearly, and this supports that the proposed measurement and processing methods are promising for wind turbine condition monitoring.

Download Full-text

Design requirements for wireless sensor-based novelty detection in machinery condition monitoring

Engineering Asset Lifecycle Management ◽

10.1007/978-0-85729-320-6_47 ◽

2010 ◽

pp. 420-429

Author(s):

Christos Emmanouilidis ◽

Petros Pistofidis

Keyword(s):

Condition Monitoring ◽

Novelty Detection ◽

Wireless Sensor ◽

Machinery Condition Monitoring ◽

Design Requirements

Download Full-text

Learning Factorial Codes by Predictability Minimization

Neural Computation ◽

10.1162/neco.1992.4.6.863 ◽

1992 ◽

Vol 4 (6) ◽

pp. 863-879 ◽

Cited By ~ 85

Author(s):

Jürgen Schmidhuber

Keyword(s):

Unsupervised Learning ◽

Supervised Learning ◽

General Principle ◽

Novelty Detection ◽

The Other ◽

Detection Methods ◽

Local Algorithm ◽

The Novel ◽

Abstract Concepts ◽

Internal Representations

I propose a novel general principle for unsupervised learning of distributed nonredundant internal representations of input patterns. The principle is based on two opposing forces. For each representational unit there is an adaptive predictor, which tries to predict the unit from the remaining units. In turn, each unit tries to react to the environment such that it minimizes its predictability. This encourages each unit to filter "abstract concepts" out of the environmental input such that these concepts are statistically independent of those on which the other units focus. I discuss various simple yet potentially powerful implementations of the principle that aim at finding binary factorial codes (Barlow et al. 1989), i.e., codes where the probability of the occurrence of a particular input is simply the product of the probabilities of the corresponding code symbols. Such codes are potentially relevant for (1) segmentation tasks, (2) speeding up supervised learning, and (3) novelty detection. Methods for finding factorial codes automatically implement Occam's razor for finding codes using a minimal number of units. Unlike previous methods the novel principle has a potential for removing not only linear but also nonlinear output redundancy. Illustrative experiments show that algorithms based on the principle of predictability minimization are practically feasible. The final part of this paper describes an entirely local algorithm that has a potential for learning unique representations of extended input sequences.

Download Full-text

A Novelty Detection Technique for Machine Condition Monitoring Using S. O. M

Jurnal Kejuruteraan ◽

10.17576/jkukm-2008-20-16 ◽

2008 ◽

Vol 20 (1) ◽

pp. 175-182

Author(s):

M. L. Dennis ◽

Keyword(s):

Condition Monitoring ◽

Novelty Detection ◽

Detection Technique ◽

Machine Condition ◽

Machine Condition Monitoring

Download Full-text

Semi-Supervised Machine Condition Monitoring by Learning Deep Discriminative Audio Features

Electronics ◽

10.3390/electronics10202471 ◽

2021 ◽

Vol 10 (20) ◽

pp. 2471

Author(s):

Iordanis Thoidis ◽

Marios Giouvanakis ◽

George Papanikolaou

Keyword(s):

Neural Network ◽

Anomaly Detection ◽

Convolutional Neural Network ◽

Condition Monitoring ◽

Feature Learning ◽

Detection Methods ◽

Mechanical Equipment ◽

Learning Approach ◽

Audio Features ◽

Front End

In this study, we aim to learn highly descriptive representations for a wide set of machinery sounds and exploit this knowledge to perform condition monitoring of mechanical equipment. We propose a comprehensive feature learning approach that operates on raw audio, by supervising the formation of salient audio embeddings in latent states of a deep temporal convolutional neural network. By fusing the supervised feature learning approach with an unsupervised deep one-class neural network, we are able to model the characteristics of each source and implicitly detect anomalies in different operational states of industrial machines. Moreover, we enable the exploitation of spatial audio information in the learning process, by formulating a novel front-end processing strategy for circular microphone arrays. Experimental results on the MIMII dataset demonstrate the effectiveness of the proposed method, reaching a state-of-the-art mean AUC score of 91.0%. Anomaly detection performance is significantly improved by incorporating multi-channel audio data in the feature extraction process, as well as training the convolutional neural network on the spatially invariant front-end. Finally, the proposed semi-supervised approach allows the concise modeling of normal machine conditions and accurately detects system anomalies, compared to existing anomaly detection methods.

Download Full-text

Condition Monitoring of Motor-Gear System Dynamics With Rotor and Gear Faults

Journal of Computational and Nonlinear Dynamics ◽

10.1115/1.4048196 ◽

2020 ◽

Vol 15 (11) ◽

Author(s):

Wenyu Bai ◽

Guanjun Bao ◽

Datong Qin ◽

Yawen Wang ◽

Teik C. Lim

Keyword(s):

Condition Monitoring ◽

Planetary Gear ◽

Response Spectra ◽

Rotational Frequency ◽

Gear System ◽

Electromechanical System ◽

Gear Mesh ◽

Dynamic Eccentricity ◽

Mechanical Faults ◽

Slip Frequency

Abstract An electromechanical system consisting of an electric motor and planetary gear set is modeled and analyzed in this paper. The model integrates various internal excitations including time-varying gear mesh stiffness, nonlinear spatial effect and, saturation effect, and component flaws. The simulation results predict the effects of rotor and gear faults including broken rotor bar, rotor static and dynamic eccentricity, and tooth root crack of the gear on the electromechanical system behavior. It is verified as the results obtained are in accordance with the features derived within previous researches. Furthermore, new sidebands merged on the dynamic response spectra such as slip frequency harmonics, rotor rotational frequency harmonics, and fault-related rotational frequency harmonics can be applied to detect electrical and mechanical faults in the motor-gear system. This paper lays the foundation for the comprehensive further study of working condition monitoring for the motor-gear system.

Download Full-text