A Deep Learning Feature Fusion Based Health Index Construction Method for Prognostics Using Multiobjective Optimization

Abstract

Degradation modeling and prognostics serve as the basis for system health management. Recently, various sensors provide plentiful monitoring data that can reflect the system status. A multitude of feature fusion techniques based on multisensor data have been proposed to generate a composite health index (HI) for prognostics, which can represent the underlying degradation mechanism. Most existing methods have used linear fusion models and neglected the practical requirements for HI construction, which are insufficient to reveal the nonlinear relations among features and difficult to obtain accurate HIs for complicated systems. This study proposes a novel feature fusion-based HI construction method with deep learning and multiobjective optimization. Multiple degradation features are fused by a deep neutral network (DNN). Several desired properties that the HIs should have for prognostics are adopted to formulate the objective functions of DNN training. To balance the spatial complexity and performance of the fusion model, a multiobjective optimization model is generated for training the DNN. Then, a generalized nonlinear Wiener process model is used to predict the remaining useful life with the resulted HIs. Finally, two cases are analyzed to illustrate the effectiveness and robustness of the proposed method.

Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms

“…To conclude, the proposed approaches can be reliably used to address this important subject concerning the structural integrity of AM components. It must be noted that more complex models and architectures dealing with reliability analysis [46][47][48][49] may have also been used. However, the proposed algorithms, despite their simple architecture, properly and reliably work for two of the most used SLM materials, the AlSi10Mg and the Ti6Al4V alloy, even for a number of available data for the training that is smaller than that generally considered for this kind of algorithms.…”

The RUL prediction based on improved Wiener degradation model for wet friction components

“…Therefore, this degradation can be represented by various indicators such as wear and thermal failure, and these degradation indicators have randomness in degradation rate and path. A single indicator makes it difficult to accurately describe the degradation mechanism of wet friction components, and multi-sensor simultaneous monitoring of equipment health status has been widely applied [2]. The challenge is effectively integrating data from multiple sensors to achieve more accurate degradation modeling and predictive analysis [3].…”

An ensemble model considering health index based classification for remaining useful life prediction

“…Nowadays, Prognostics Health Management (PHM) plays a vital role in the routine maintenance of complex industrial systems, such as aircraft engines, vehicles, heavy industry, and so forth. PHM employs various data generated in industrial systems to perform the prediction and management of the future health state of the system, combined with technologies such as signal processing and data analysis 1,2 . As a key technology of PHM, remaining useful life (RUL) prediction has become a research hotspot of scholars 3 …”

“…PHM employs various data generated in industrial systems to perform the prediction and management of the future health state of the system, combined with technologies such as signal processing and data analysis. 1,2 As a key technology of PHM, remaining useful life (RUL) prediction has become a research hotspot of scholars. 3 In existing studies, RUL prediction methods mainly include three categories: physical model-based methods, 4 datadriven methods, 5 and hybrid methods.…”