A Parallel Ensemble Learning Model for Fault Detection and Diagnosis of Industrial Machinery

Accurate fault detection and diagnosis (FDD) is critical to ensure the safe reliable operation of industrial machines. Deep learning has recently emerged as effective methods for machine FDD applications. However, gradient descent optimization method that commonly used in deep suffers from several limitations, such high computational cost local sub-optimal solutions. Accordingly, this paper proposes a new parallel ensemble model comprising hybrid undertaking tasks. Composed three levels learning, proposed employs two base learners meta-learner, executed processing platform achieve efficient computation. The adopt Back-Propagation (BP) Particle Swarm Optimization (PSO) algorithms exploit corresponding global capabilities identifying optimal features improving performance. validated through series experiments using benchmark data sets, i.e., CWRU MAFaulD. results demonstrate performance with accuracy rates 98.45% 99.79% MAFaulD, respectively. Its implementation able reduce computation time, resulting speed-up 5.9 time 7.17 These findings indicate machinery, making it promising solution real-world environments.