Basit öğe kaydını göster

dc.contributor.authorÇakır, Mustafa
dc.contributor.authorGüvenç, Mehmet Ali
dc.contributor.authorMıstıkoğlu, Selçuk
dc.date.accessioned2021-06-21T12:36:10Z
dc.date.available2021-06-21T12:36:10Z
dc.date.issued2021en_US
dc.identifier.citationCakir, M., Guvenc, M.A., Mistikoglu, S. (2021). The experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring system. Computers and Industrial Engineering, 151, art. no. 106948. https://doi.org/10.1016/j.cie.2020.106948en_US
dc.identifier.urihttps://doi.org/10.1016/j.cie.2020.106948
dc.identifier.urihttps://hdl.handle.net/20.500.12508/1778
dc.description.abstractWith the fourth industrial revolution, which has become increasingly widespread in the manufacturing industry, traditional maintenance has been replaced by the industrial internet of things (IIoT) based on condition monitoring system (CMS). The IIoT concept provides easier and reliable maintenance. Unlike traditional maintenance, IIoT systems that perform real-time monitoring can provide great advantages to the company by notifying the related maintenance team members of the factory before a serious failure occurs. It is very important to detect faulty bearings before they reach the critical level during the rotation. In this study, an industry 4.0 compatible, IIoT based and low-cost CMS was created and it consists of three main parts. Firstly experimental setup, secondly IIoT based condition monitoring application (CMA) and finally machine learning (ML) models and their evaluation. The experimental setup contains mechanical and electronic materials. Although the most common method used in the classification of bearing damage is vibration data, it observed that characteristics such as sound level, current, rotational speed, and temperature should be included in the data set in order to increase the success of the classification. All these data were collected from the setup, which is 6203 type bearing connected to the universal motor shaft. The designed CMA provides real-time monitoring and recording of the data, which comes wirelessly from the setup, on a mobile device that has an Android operating system. The CMA can also send SMS and e-mail notifications to maintenance team supervisors over mobile devices in case critical thresholds are exceeded. Lastly, the data collected from the experimental setup was modeled for classification with popular ML algorithms such as support vector machine (SVM), linear discrimination analysis (LDA), random forest (RF), decision tree (DT), and k-nearest neighbor (kNN). The models were evaluated with accuracy, precision, TPR, TNR, FPR, FNR, F1 score and, Kappa metrics. During the evaluation of all models, it was observed that with the increase in the number of features in the data set, the accuracy, sensitivity, TPR, TNR, F1 score and Kappa metrics increased above 99% at 95% confidence interval, and FPR and FNR metrics fell below 1%. Although ML models gave successful results, LDA and DT models gave results much faster than others did. On the other hand, the classification success of the LDA model is relatively low. However, DT model is the optimum choice for CMS due to its convenience in determining threshold values, and its ability to give fast and acceptable classification rates.en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.isversionof10.1016/j.cie.2020.106948en_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectIndustry 4.0en_US
dc.subjectInternet of thingsen_US
dc.subjectCondition monitoringen_US
dc.subjectMachine learningen_US
dc.subjectPredictive maintenanceen_US
dc.subject.classificationComputer Science
dc.subject.classificationInterdisciplinary Applications
dc.subject.classificationEngineering, Industrial
dc.subject.classificationRolling Bearing
dc.subject.classificationRotating Machinery
dc.subject.classificationFault Diagnosis
dc.subject.otherBearings (machine parts)
dc.subject.otherClassification (of information)
dc.subject.otherCondition monitoring
dc.subject.otherCosts; Decision trees
dc.subject.otherIndustry 4.0
dc.subject.otherLearning algorithms
dc.subject.otherLearning systems
dc.subject.otherNearest neighbor search
dc.subject.otherPredictive analytics
dc.subject.otherPredictive maintenance
dc.subject.otherReal time systems
dc.subject.otherSupport vector machines
dc.subject.otherDecision trees
dc.subject.otherCondition monitoring systems
dc.subject.otherExperimental application
dc.subject.otherIndustrial revolutions
dc.subject.otherK nearest neighbor (KNN)
dc.subject.otherLinear discrimination analysis
dc.subject.otherManufacturing industries
dc.subject.otherMonitoring applications
dc.subject.otherOn condition monitoring
dc.subject.otherIndustrial internet of things (IIoT)
dc.titleThe experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring systemen_US
dc.typearticleen_US
dc.relation.journalComputers and Industrial Engineeringen_US
dc.contributor.departmentMühendislik ve Doğa Bilimleri Fakültesi -- Makina Mühendisliği Bölümüen_US
dc.identifier.volume151en_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.contributor.isteauthorÇakır, Mustafa
dc.contributor.isteauthorGüvenç, Mehmet Ali
dc.contributor.isteauthorMıstıkoğlu, Selçuk
dc.relation.indexWeb of Science - Scopusen_US
dc.relation.indexWeb of Science Core Collection - Science Citation Index Expanded


Bu öğenin dosyaları:

Thumbnail

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster