Prediction of air compressor faults with feature fusion and machine learning

Simple item page
dc.contributor.authorNambiar, Abhay
dc.contributor.authorVenkatesh, S. Naveen
dc.contributor.authorAravinth, S.
dc.contributor.authorSugumaran, V
dc.contributor.authorRamteke, Sangharatna M.
dc.contributor.authorMarian, Max
dc.date.accessioned2025-01-20T16:08:20Z
dc.date.available2025-01-20T16:08:20Z
dc.date.issued2024
dc.description.abstractAir compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study's input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.
dc.description.funderANID-Chile within the project Fondecyt de Postdoctorado
dc.fuente.origenWOS
dc.identifier.doi10.1016/j.knosys.2024.112519
dc.identifier.eissn1872-7409
dc.identifier.issn0950-7051
dc.identifier.urihttps://doi.org/10.1016/j.knosys.2024.112519
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/90070
dc.identifier.wosidWOS:001316347100001
dc.language.isoen
dc.revistaKnowledge-based systems
dc.rightsacceso restringido
dc.subjectFault diagnosis
dc.subjectAir compressor faults
dc.subjectVibration analysis
dc.subjectFeature fusion
dc.subjectLazy classifiers
dc.subjectMachine learning
dc.titlePrediction of air compressor faults with feature fusion and machine learning
dc.typeartículo
dc.volumen304
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas