Deep Learning-Based Machinery Fault Diagnostics

• Autore: Chen Hongtian
• Pubblicazione: MDPI - Multidisciplinary Digital Publishing Institute, 2022
• Descrizione fisica: 1 electronic resource (290 p.)
• Soggetto topico: Technology: general issues; History of engineering & technology
• Soggetto non controllato: process monitoring; dynamics; variable time lag; dynamic autoregressive latent variables model; sintering process; hammerstein output-error systems; auxiliary model; multi-innovation identification theory; fractional-order calculus theory; canonical variate analysis; disturbance detection; power transmission system; k-nearest neighbor analysis; statistical local analysis; intelligent fault diagnosis; stacked pruning sparse denoising autoencoder; convolutional neural network; anti-noise; flywheel fault diagnosis; belief rule base; fuzzy fault tree analysis; Bayesian network; evidential reasoning; aluminum reduction process; alumina concentration; subspace identification; distributed predictive control; spatiotemporal feature fusion; gated recurrent unit; attention mechanism; fault diagnosis; evidential reasoning rule; system modelling; information transformation; parameter optimization; event-triggered control; interval type-2 Takagi-Sugeno fuzzy model; nonlinear networked systems; filter; gearbox fault diagnosis; convolution fusion; state identification; PSO; wavelet mutation; LSSVM; data-driven; operational optimization; case-based reasoning; local outlier factor; abnormal case removal; bearing fault detection; deep residual network; data augmentation; canonical correlation analysis; just-in-time learning; fault detection; high-speed trains; autonomous underwater vehicle; thruster fault diagnostics; fault tolerant control; robust optimization; ocean currents
• Persona (resp. second.): ZhongKai; RanGuangtao; ChengChao; ChenHongtian
• Sommario/riassunto: This book offers a compilation for experts, scholars, and researchers to present the most recent advancements, from theoretical methods to the applications of sophisticated fault diagnosis techniques. The deep learning methods for analyzing and testing complex mechanical systems are of particular interest. Special attention is given to the representation and analysis of system information, operating condition monitoring, the establishment of technical standards, and scientific support of machinery fault diagnosis.
• Titolo autorizzato: Deep Learning-Based Machinery Fault Diagnostics
• ISBN: 3-0365-5174-3
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910619469103321
• Lo trovi qui: Univ. Federico II