Litcius/Paper detail

A hybrid data-driven prognostic scheme based on unsupervised health indicator construction and random-effects Wiener process

Junyu Guo, Yuhang Song, Zhiyuan Wang, Tingxia Ma, Yang Xiao, Zifei Xu

2025Computers & Industrial Engineering13 citationsDOI

Topics & Concepts

AutoencoderInterpretabilityComputer scienceArtificial intelligenceMachine learningConstruct (python library)Process (computing)Reliability (semiconductor)Data miningScheme (mathematics)Feature (linguistics)Unsupervised learningPrognosticsWiener processArtificial neural networkSupervised learningFeature extractionDeep learningPattern recognition (psychology)AccelerationConvolutional neural networkAutoregressive modelRandom forestKernel density estimationFault detection and isolationMoment (physics)Kernel (algebra)Condition monitoringReliability engineeringWeightingMachine Fault Diagnosis TechniquesReliability and Maintenance OptimizationFault Detection and Control Systems
A hybrid data-driven prognostic scheme based on unsupervised health indicator construction and random-effects Wiener process | Litcius