Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics

TLDR

Condition‑based maintenance is the most effective policy for safety, efficiency, and reliability, and prognostics—key to CBM—focuses on estimating remaining useful life, yet neural‑network approaches are limited by handcrafted features and manually tuned parameters. This work introduces a multiobjective deep belief networks ensemble (MODBNE) to address these limitations. MODBNE evolves multiple DBNs simultaneously using a multiobjective evolutionary algorithm that balances accuracy and diversity, then combines them into an ensemble whose weights are optimized by a single‑objective differential evolution algorithm, and the method is evaluated on several prognostic benchmark datasets against existing approaches. Experimental results demonstrate that MODBNE outperforms the compared methods.

Abstract

In numerous industrial applications where safety, efficiency, and reliability are among primary concerns, condition-based maintenance (CBM) is often the most effective and reliable maintenance policy. Prognostics, as one of the key enablers of CBM, involves the core task of estimating the remaining useful life (RUL) of the system. Neural networks-based approaches have produced promising results on RUL estimation, although their performances are influenced by handcrafted features and manually specified parameters. In this paper, we propose a multiobjective deep belief networks ensemble (MODBNE) method. MODBNE employs a multiobjective evolutionary algorithm integrated with the traditional DBN training technique to evolve multiple DBNs simultaneously subject to accuracy and diversity as two conflicting objectives. The eventually evolved DBNs are combined to establish an ensemble model used for RUL estimation, where combination weights are optimized via a single-objective differential evolution algorithm using a task-oriented objective function. We evaluate the proposed method on several prognostic benchmarking data sets and also compare it with some existing approaches. Experimental results demonstrate the superiority of our proposed method.