Predicting process and regeneration air conditions in LT3 molecular sieve desiccant wheels using machine learning and regression methods

Basit Öğe Kaydı
dc.contributor.authorGuruk, Alperen Burak
dc.contributor.authorGuzelel, Yunus Emre
dc.contributor.authorOlmus, Umutcan
dc.contributor.authorCerci, Kamil Neyfel
dc.contributor.authorBuyukalaca, Orhan
dc.date.accessioned2025-03-17T12:27:13Z
dc.date.available2025-03-17T12:27:13Z
dc.date.issued2025
dc.departmentTarsus Üniversitesi
dc.description.abstractThe performance of desiccant wheels is influenced by various design and operational variables. Existing models in the literature for LT3 molecular sieve desiccant wheels often include only a limited number of input parameters or have restricted operating ranges. This study addresses these limitations by generating a dataset encompassing 32,975 scenarios, which was used to develop 192 models using four methods such as multiple linear regression (MLR), decision tree (DT), support vector machine (SVM), and multilayer perceptron (MLP). The models were categorized into two groups to allow for various analyses. Group A models predict the process air outlet conditions of the desiccant wheel, namely temperature (Tpo) and humidity (omega po). Group B models, in contrast, predict the required regeneration air inlet temperature (Tri) necessary to achieve a desired process air exit humidity (omega po), while also predicting Tpo. MLP models demonstrated the best accuracy across both groups. In Group A, the model coded as MLP-7 achieved an RMSE of 0.2017 degrees C for Tpo, and MLP-6 yielded an RMSE of 0.0656 g/kg for omega po. In Group B, MLP-7 recorded an RMSE of 0.1764 degrees C for Tpo, while Tri had an RMSE of 0.7892 degrees C. Additionally, in Group A, the models coded as RS, 3rdCross, DT-28, and SVM-5 also delivered reliable results, while in Group B, the RS, 2ndCross, 3rdCross, DT-28, and SVM-3 models performed well.
dc.description.sponsorshipScientific Research Project Office of Cukurova University [FBA-2023-15407]
dc.description.sponsorshipThe research was supported by the Scientific Research Project Office of Cukurova University under contract no: FBA-2023-15407.
dc.identifier.doi10.1016/j.icheatmasstransfer.2025.108811
dc.identifier.issn0735-1933
dc.identifier.issn1879-0178
dc.identifier.scopus2-s2.0-85218855804
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.icheatmasstransfer.2025.108811
dc.identifier.urihttps://hdl.handle.net/20.500.13099/2118
dc.identifier.volume164
dc.identifier.wosWOS:001438491700001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherPergamon-Elsevier Science Ltd
dc.relation.ispartofInternational Communications in Heat and Mass Transfer
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WOS_20250316
dc.subjectDesiccant wheel
dc.subjectLT3 molecular sieve
dc.subjectMultiple linear regression
dc.subjectMachine learning
dc.subjectSupport vector machine
dc.subjectMultilayer perceptron
dc.subjectDecision tree
dc.titlePredicting process and regeneration air conditions in LT3 molecular sieve desiccant wheels using machine learning and regression methods
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu