scholarly journals Towards Developing an Automated Faults Characterisation Framework for Rotating Machines. Part 1: Rotor-Related Faults

Energies ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 1394 ◽  
Author(s):  
Akilu Yunusa-Kaltungo ◽  
Ruifeng Cao
Keyword(s):  
Failure Modes ◽  
Large Data ◽  
Processing Parameters ◽  
Machine Learning Techniques ◽  
Rotating Machines ◽  
Smart Systems ◽  
Vibration Data ◽  
Learning Techniques ◽  
Faults Diagnosis ◽  
Manual Classification

Rotating machines are pivotal to the achievement of core operational objectives within various industries. Recent drives for developing smart systems coupled with the significant advancements in computational technologies have immensely increased the complexity of this group of critical physical industrial assets (PIAs). Vibration-based techniques have contributed significantly towards understanding the failure modes of rotating machines and their associated components. However, the very large data requirements attributable to routine vibration-based fault diagnosis at multiple measurement locations has led to the quest for alternative approaches that possess the capability to reduce faults diagnosis downtime. Initiatives aimed at rationalising vibration-based condition monitoring data in order to just retain information that offer maximum variability includes the combination of coherent composite spectrum (CCS) and principal components analysis (PCA) for rotor-related faults diagnosis. While there is no doubt about the potentials of this approach, especially that it is independent of the number of measurement locations and foundation types, its over-reliance on manual classification made it prone to human subjectivity and lack of repeatability. The current study therefore aims to further enhance existing CCS capability in two facets—(1) exploration of the possibility of automating the process by testing its compatibility with various machine learning techniques (2) incorporating spectrum energy as a novel feature. It was observed that artificial neural networks (ANN) offered the most accurate and consistent classification outcomes under all considered scenarios, which demonstrates immense opportunity for automating the process. The paper describes computational approaches, signal processing parameters and experiments used for generating the analysed vibration data.

scholarly journals Researching the Research: Applying Machine Learning Techniques to Dissertation Classification

2020 ◽  
Vol 2 (4) ◽  
Author(s):  
Suzanna Schmeelk
Keyword(s):  
Machine Learning ◽  
Full Text ◽  
Doctoral Program ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Full Time ◽  
Learning Techniques ◽  
Manual Classification ◽  
Machine Learning Tool

This research examines industry-based dissertation research in a doctoral computing program through the lens of machine learning algorithms to understand topics explored by senior and experienced full-time working professionals (EFWPs).  Our research categorizes dissertation by both their abstracts and by their full-text using the Graplab Create library from Apple’s Turi. We also compare the dissertation categorizations using IBM’s Watson Discovery deep machine learning tool.  Our research provides perspectives on the practicality of the manual classification of technical documents; and, it provides insights into the: (1) categories of academic work created by EFWPs in a Computing doctoral program, (2) viability of automated categorization versus human abstraction, and (3) differences in categorization algorithms.

scholarly journals IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection

Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2857
Author(s):  
Laura Vigoya ◽  
Diego Fernandez ◽  
Victor Carneiro ◽  
Francisco Nóvoa
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
False Positive Rate ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
High Detection Rate ◽  
Security Vulnerabilities ◽  
Smart Systems ◽  
Learning Techniques ◽  
Positive Rate

With advancements in engineering and science, the application of smart systems is increasing, generating a faster growth of the IoT network traffic. The limitations due to IoT restricted power and computing devices also raise concerns about security vulnerabilities. Machine learning-based techniques have recently gained credibility in a successful application for the detection of network anomalies, including IoT networks. However, machine learning techniques cannot work without representative data. Given the scarcity of IoT datasets, the DAD emerged as an instrument for knowing the behavior of dedicated IoT-MQTT networks. This paper aims to validate the DAD dataset by applying Logistic Regression, Naive Bayes, Random Forest, AdaBoost, and Support Vector Machine to detect traffic anomalies in IoT. To obtain the best results, techniques for handling unbalanced data, feature selection, and grid search for hyperparameter optimization have been used. The experimental results show that the proposed dataset can achieve a high detection rate in all the experiments, providing the best mean accuracy of 0.99 for the tree-based models, with a low false-positive rate, ensuring effective anomaly detection.

Machine Learning Techniques to Fault Detection in Rotating Machines

2021 ◽  
Author(s):  
Luís Otávio Garavaso ◽  
Gregory Bregion Daniel ◽  
Katia Lucchesi Cavalca Dedini
Keyword(s):  
Machine Learning ◽  
Fault Detection ◽  
Machine Learning Techniques ◽  
Rotating Machines ◽  
Learning Techniques

scholarly journals Machine learning in diachronic corpus phonology: mining verse data to infer trajectories in English phonotactics

2018 ◽  
Vol 3 ◽  
Author(s):  
Andreas Baumann
Keyword(s):  
Machine Learning ◽  
Middle English ◽  
Large Data ◽  
Large Data Sets ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Powerful Method ◽  
K Nearest Neighbors ◽  
Learning Techniques ◽  
Standard Techniques

Machine learning is a powerful method when working with large data sets such as diachronic corpora. However, as opposed to standard techniques from inferential statistics like regression modeling, machine learning is less commonly used among phonological corpus linguists. This paper discusses three different machine learning techniques (K nearest neighbors classifiers; Naïve Bayes classifiers; artificial neural networks) and how they can be applied to diachronic corpus data to address specific phonological questions. To illustrate the methodology, I investigate Middle English schwa deletion and when and how it potentially triggered reduction of final /mb/ clusters in English.

Collection and processing of bearing vibration data for their technical condition classification by machine learning methods

2021 ◽  
pp. 10-15
Author(s):  
Ruslan Babudzhan ◽  
Kostiantyn Isaienkov ◽  
Danylo Krasii ◽  
Ruben Melkonian ◽  
Oleksii Vodka ◽  
...  
Keyword(s):  
Machine Learning ◽  
Technical Condition ◽  
Machine Learning Techniques ◽  
Rolling Bearings ◽  
Control Block ◽  
Vibration Data ◽  
Learning Techniques ◽  
Emergency Stop ◽  
Bearing Vibration ◽  
To Receive

An experimental research facility has been developed to receive vibration signals from mechanisms with installed rolling bearings. A control block for all equipment has been created. For the repeatability of the experiment, an external microcontroller with a programmed proportional-integral-derivative regulator was used. Experiments were carried out to obtain initial data for different types of bearings. The processed data were grouped and made publicly available for further research. It is proposed to solve the problem of emergency stop of the generator, arising during operation due to bearings worn, by recognizing the pre-emergency conditions of rotary rig based on the use of advanced machine learning techniques: to highlight the signs of vibration and build clusters according to the degree of worn.

scholarly journals Artificial Intelligence based Edge Computing Framework for Optimization of Mobile Communication

2020 ◽  
Vol 2 (3) ◽  
pp. 160-165
Author(s):  
Sathish
Keyword(s):  
Artificial Intelligence ◽  
Mobile Communication ◽  
Optimal Solution ◽  
Edge Computing ◽  
Machine Learning Techniques ◽  
Mobile Service ◽  
Smart Systems ◽  
Learning Techniques ◽  
Near Future ◽  
System Intelligence

For improving the mobile service quality and acceleration of content delivery, edge computing techniques have been providing optimal solution to bridge the device requirements and cloud capacity by network edges. The advancements of technologies like edge computing and mobile communication has contributed greatly towards these developments. The mobile edge system is enabled with Machine Learning techniques in order to improve the edge system intelligence, optimization of communication, caching and mobile edge computing. For this purpose, a smart framework is developed based on artificial intelligence enabling reduction of unwanted communication load of the system as well as enhancement of applications and optimization of the system dynamically. The models can be trained more accurately using the learning parameters that are exchanged between the edge nodes and the collaborating devices. The adaptivity and cognitive ability of the system is enhanced towards the mobile communication system despite the low learning overhead and helps in attaining a near optimal performance. The opportunities and challenges of smart systems in the near future are also discussed in this paper.

scholarly journals Automatic classification of sources in large astronomical catalogs

2019 ◽  
Vol 15 (S341) ◽  
pp. 109-113
Author(s):  
Agnieszka Pollo ◽  
Aleksandra Solarz ◽  
Małgorzata Siudek ◽  
Katarzyna Małek ◽  
Maciej Bilicki ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Data ◽  
Machine Learning Techniques ◽  
Classification Methods ◽  
Classification Schemes ◽  
Astronomical Catalogs ◽  
Learning Techniques ◽  
Sky Survey ◽  
Optimal Classification

AbstractIn this paper we address two questions related to data analysis in large astronomical datasets, and we demonstrate how they can be answered making use of machine learning techniques. The first question is: how to efficiently find previously unknown or rare objects which can be expected to exist in big data samples? Using the largest existing extragalactic all-sky survey, provided by the WISE satellite, we demonstrate that, surprisingly, supervised classification methods can come to aid. The second question is: having a sufficiently large data sample, how can we look for new optimal classification schemes, possibly finding new and previously unknown classes and subclasses of sources? Based on the VIPERS cutting-edge galaxy catalog at redshift z > 0.5, we demonstrate that unsupervised classification methods can give unexpected but physically well-motivated results.

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.

Analytics

2019 ◽  
pp. 170-179
Author(s):  
Mark E. Frisse ◽  
Karl E. Misulis
Keyword(s):  
Machine Learning ◽  
Quality Improvement ◽  
Cost Management ◽  
Large Data ◽  
Clinical Informatics ◽  
Large Data Sets ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Learning Techniques ◽  
Clinical Action

Healthcare analytics is a subject important to all informatics professionals, from providers to payers to regulators. The analysis of clinical and administrative data is essential to quality improvement, cost management, and research. With the advent of large data sets and sophisticated machine learning techniques, options are growing. Often, the weakness of an analytic approach is more due to a failure to ask a question that leads to clinical action or an inability to answer a question because the data available are not sufficient in either quality or quantity to address the primary concerns. Effective clinical informatics professionals focus on questions for which the data are sufficient and where answers can yield to improved actions.

Classification and Machine Learning

2019 ◽  
pp. 180-193
Author(s):  
Damian Alberto
Keyword(s):  
Machine Learning ◽  
Text Classification ◽  
Automatic Classification ◽  
Machine Learning Techniques ◽  
Classification Problems ◽  
Learning Techniques ◽  
The Subject ◽  
Manual Classification ◽  
Learning Generalization

The manual classification of a large amount of textual materials are very costly in time and personnel. For this reason, a lot of research has been devoted to the problem of automatic classification and work on the subject dates from 1960. A lot of text classification software has appeared. For some tasks, automatic classifiers perform almost as well as humans, but for others, the gap is still large. These systems are directly related to machine learning. It aims to achieve tasks normally affordable only by humans. There are generally two types of learning: learning “by heart,” which consists of storing information as is, and learning generalization, where we learn from examples. In this chapter, the authors address the classification concept in detail and how to solve different classification problems using different machine learning techniques.

Sign in / Sign up

Export Citation Format

Share Document