A cloud-based condition monitoring system for fault detection in rotating machines using PROFINET process data

Dias, André Luís; Turcato, Afonso Celso; Sestito, Guilherme Serpa; Brandão, Dennis; Nicoletti, Rodrigo

doi:10.1016/j.compind.2021.103394

Cited by 34 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fang et al, [10] chose one-class SVM as the unsupervised anomaly detection approach for sewer pipelines. Borges et al, [60] evaluated the performance of the higher order statistic approach for feature extraction and one-class SVM for FD, whereas Dias et al, [61] achieved 95.7% reduction in computational time when using one-class SVM with adaptive correlation-based feature selection. Further exploration in the field of SVM was carried out by Wang et al, who studied another variant of SVM in FD (i.e., support vector data description (SVDD)) to cater the imbalanced dataset in UFD learning.…”

Section: Support Vector Machinementioning

confidence: 99%

A Systematic Literature Review of Unsupervised Fault Detection Approach for Complex Engineering System

Sobran

Ismail²

2023

ARAM

View full text Add to dashboard Cite

Monitoring complex engineering systems is an important countermeasure in managing the risk of faulty events. Observing the response of each process flow will avoid further damages in the production cycle. Both fault-tolerant approach that bears with faulty events and scheduled maintenance that helps to reduce tool wearing are deeply involved in condition-based monitoring methods implemented in factories. Thus, identification of faulty equipment is need to avoid major breakdown in the production system. A classification framework shows good performance in classifying faulty events, but a labelled dataset is usually financially consuming. Machine learning (ML) techniques have become a prospective tool in the unsupervised fault detection (UFD) approach to prevent total failures in complex engineering system. However, the efficiency of UFD applications, on the other hand, is determined by the selected ML method. This paper presents a systematic literature review of ML methods applied for UFD, highlighting the methods explored in this field and the success of today's state-of-the-art machine learning techniques. This review focuses on the Scopus scientific database and provides a useful information on ML techniques, challenges and opportunities, and new research works in the UFD field.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

A Systematic Literature Review of Unsupervised Fault Detection Approach for Complex Engineering System

Sobran

Ismail²

2023

ARAM

View full text Add to dashboard Cite

show abstract

“…Aiming to develop learning in vocational education students, this work focusses on some of the technologies, which are: Internet of things, Data mining, and Cloud computing, as they could be used in a wide range of applications, both in the industrial and domestic areas, as well as in the education, commerce, among others, providing students a reflection on their reality, motivation, and interest. The advent of Industry 4.0 represents an opportunity for enterprises to improve their manufacturing processes, based on technologies such as artificial intelligence algorithms, the Internet of Things (IoT), and cloud computing (Dias et al, 2021). These technologies aim to improve the operational efficiency of industries which could imply deep modifications in work relationships and production activities.…”

Section: Construction Of Referencesmentioning

confidence: 99%

Interdisciplinary Teaching Activities for High School Integrated to Vocational Education Promoting Reflections on Industry 4.0 Technologies and Their Implication in Society

Vieira

Gouveia

Dias

2022

JTET

View full text Add to dashboard Cite

The educational system in Brazil, especially the high school level, is characterized by a division, offering a general and humanist formation for the economic elite, and direct preparation for labor, for the working-class. Aiming to overcome this duality and contribute to the polytechnic formation of vocational education students, this paper presents and analyzes interdisciplinary teaching activities that discuss the relationships between Industry 4.0 technologies, production systems, and education. The educational product, developed and applied based on the action research methodology, consisted of identifying the students' prior knowledge, three units of teaching activities, and a final evaluation questionnaire. According to the students' background and their suggestions, the content and didact methodology of each unit was selected, including the history of industrial revolutions, technologies arising from Industry 4.0 (internet of things, data mining, and cloud computing), the challenges of the fourth Industrial Revolution on the economy and labor. Didact methodologies include dialogic lecture based on slides, hands-on practical activity experimenting Industry 4.0 technologies through free online applications, and debate. Interdisciplinary activities were developed at the Federal Institute of Education, Science and Technology of São Paulo, involving students of the 4th year (last) of high school integrated into vocational education with a qualification in Industrial Automation. During the application it was observed that the use of educational product led to considerable levels of motivation and promoted reflections related to the impact of the Industry 4,0 technologies in society and employment. Also, it has been verified that the didact sequence increases the student capacity to: identify problems and propose possible solutions; understand labor different dimensions (technology, employment, politics, and economics); use strong argumentation based on reliable sources, proposing possible interventions. Thus, the interdisciplinary approach of technological development, considering not only the technical concepts but also the historical and sociological issues related to the application of technologies in the productive system, contributes to a critical teaching-learning process and the omnilateral formation in vocational education.

show abstract

“…For this reason, it is particularly suitable for fault diagnosis in industrial contexts [43]. Different evaluation measures and search techniques are used to produce a suitable feature subset in feature selection [44]. In this paper, the Pearson correlation analysis and the Recursive Feature Elimination (RFE) have been applied, as they are two widespread approaches used in the context of fault diagnosis.…”

Section: Feature Extraction and Selectionmentioning

confidence: 99%

Feature-Based Multi-Class Classification and Novelty Detection for Fault Diagnosis of Industrial Machinery

et al. 2021

View full text Add to dashboard Cite

Given the strategic role that maintenance assumes in achieving profitability and competitiveness, many industries are dedicating many efforts and resources to improve their maintenance approaches. The concept of the Smart Factory and the possibility of highly connected plants enable the collection of massive data that allow equipment to be monitored continuously and real-time feedback on their health status. The main issue met by industries is the lack of data corresponding to faulty conditions, due to environmental and safety issues that failed machinery might cause, besides the production loss and product quality issues. In this paper, a complete and easy-to-implement procedure for streaming fault diagnosis and novelty detection, using different Machine Learning techniques, is applied to an industrial machinery sub-system. The paper aims to offer useful guidelines to practitioners to choose the best solution for their systems, including a model hyperparameter optimization technique that supports the choice of the best model. Results indicate that the methodology is easy, fast, and accurate. Few training data guarantee a high accuracy and a high generalization ability of the classification models, while the integration of a classifier and an anomaly detector reduces the number of false alarms and the computational time.

show abstract

A cloud-based condition monitoring system for fault detection in rotating machines using PROFINET process data

Cited by 34 publications

References 22 publications

A Systematic Literature Review of Unsupervised Fault Detection Approach for Complex Engineering System

A Systematic Literature Review of Unsupervised Fault Detection Approach for Complex Engineering System

Interdisciplinary Teaching Activities for High School Integrated to Vocational Education Promoting Reflections on Industry 4.0 Technologies and Their Implication in Society

Feature-Based Multi-Class Classification and Novelty Detection for Fault Diagnosis of Industrial Machinery

Contact Info

Product

Resources

About