A neural network filtering approach for similarity-based remaining useful life estimation

Bektaş, Oğuz; Jones, Jeffrey Alun; Sankararaman, Shankar; Roychoudhury, Indranil; Goebel, Kai

doi:10.1007/s00170-018-2874-0

Cited by 77 publications

(42 citation statements)

References 63 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An evolutionary algorithm is integrated with the conventional DBN training method to evolve multiple DBNs, which are combined to establish an ensemble model for NASA's turbofan engine RUL estimation [47]. Bektas et al proposed a neural network based method by learning a similarity model that is fed by the use of data normalisation and filtering methods for operational trajectories of complex systems for RUL estimation [48].…”

Section: B Machine Learning Based Approachesmentioning

confidence: 99%

Remaining Useful Life Estimation Using Long Short-Term Memory Neural Networks and Deep Fusion

et al. 2020

View full text Add to dashboard Cite

Estimation of Remaining Useful Life (RUL) is a crucial task in Prognostics and Health Management (PHM) for condition-based maintenance of machinery. In order to transmit and store the sensor data for archiving and long term analysis, data compression techniques are regularly used to reduce the requirements of bandwidth, energy and storage in modern remote PHM systems. In these systems the challenge arises of how the compressed sensor data affects the RUL estimation algorithms. A main drawback of conventional statistical modeling approaches is that they require expert prior knowledge and a significant number of assumptions. Alternative regression based approaches and deep neural networks are known to have issues when modeling long-term dependencies in the sequential data. Recently Long Short-Term Memory (LSTM) neural networks have been proposed to overcome these issues and in this paper we create a LSTM network and data fusion approach that can estimate the RUL with compressed (distorted) data. The experimental results indicate that the proposed method is able to estimate RUL reliably with narrower error bands compared to other state-of-the-art approaches. Moreover, the proposed method is able to predict RUL from both the raw and compressed datasets with comparable accuracy. INDEX TERMS Machine health monitoring, remaining useful life (RUL), long-short term memory, recurrent neural network, data compression.

show abstract

Section: B Machine Learning Based Approachesmentioning

confidence: 99%

Remaining Useful Life Estimation Using Long Short-Term Memory Neural Networks and Deep Fusion

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This causes the feature measurements in the normal operation data to differ strongly between different engine loads. Thus, proper data pre-processing, in terms of multiregime normalization, is necessary to present the actual normal operation phenomena for the VAE during the training phase [13].…”

Section: Multiregime Operating Conditions and Normalizationmentioning

confidence: 99%

“…In such complexity, the degradation phenomena cannot be presented directly for cutting-edge spectral anomaly detection algorithms since the sensor measurements are highly connected to the operational loads. Hence, a multiregime normalization method has to be performed on the raw input data to present the degradation phenomena [13]. In addition, the nature of degradation of typical fault types associated with the marine diesel engine might be different from one another and significantly similar to normal operation data.…”

mentioning

confidence: 99%

Online Fault Detection in Autonomous Ferries: Using Fault-type Independent Spectral Anomaly Detection

Ellefsen

Han

Cheng

et al. 2020

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Enthusiasm for ship autonomy is flourishing in the maritime industry. In this context, data-driven prognostics and health management (PHM) systems have emerged as the optimal way to improve operational reliability and system safety. However, further research is needed to enhance the essential actions relating to such a system. Fault detection is the first and most crucial action of any data-driven PHM system. In this article, we propose a fault-type independent spectral anomaly detection algorithm for marine diesel engine degradation in autonomous ferries. The benefits of the algorithm are verified on three fault types where the nature of degradation differs. Both normal operation data and faulty degradation data have been collected from a marine diesel engine using two different engine load profiles. These profiles aim to replicate real autonomous ferry crossing operations, environmental conditions that the ferry may encounter. First, the data are subjected to a feature selection process to remove irrelevant and redundant features. Then, a multiregime normalization method is performed on the data to merge the engine loads into one context. Finally, a variational autoencoder is trained to estimate velocity and acceleration calculations of the anomaly score. Generic and dynamic threshold limits are simultaneously established to detect the fault time step online. The algorithm achieved an accuracy of 97.66% in the final test when the acceleration was used as the fault detector. The results suggest that the algorithm is independent of fault types with different nature of degradation related to the marine diesel engine.

show abstract

“…These models have been used for multi-regime condition monitoring information with high prognostic performance [40, 92,99]. Since the multi-step ahead network-based estimations are challenging [25,105], a synthesis of neural networks with alternative prognostic methods is essential for higher prognostic performance and various applications can be found in the literature [40,81,[98][99][100][101]106]. Each of these can be considered as a hybrid prognostic framework.…”

Section: Artificial Neural Network and Deep Learningmentioning

confidence: 99%

Comparison of Computational Prognostic Methods for Complex Systems Under Dynamic Regimes: A Review of Perspectives

Bektaş

Marshall

Jones

2019

Arch Computat Methods Eng

Self Cite

View full text Add to dashboard Cite

Complex systems are expected to play a key role in the progress of Prognostics Health Management but the breadth of technologies that will highlight gaps in the dynamic regimes are expected to become more prominent and likely more challenging in the future. The design and implementation of sophisticated computational algorithms have become a critical aspect to solve problems in many prognostic applications for multiple regimes. In addition to a wide variety of conventional computational and cognitive paradigms such as machine learning and data mining fields, specific applications in prognostics have led to a wealth of newly proposed methods and techniques. This paper reviews practices for modeling prognostics and remaining useful life applications in complex systems working under multiple operational regimes. An analysis is provided to compare and combine the findings of previously published studies in the literature, and it assesses the effectiveness of techniques for different stages of prognostic development. The paper concludes with some speculations on the likely advances in fusion of advanced methods for case specific modeling.

show abstract

A neural network filtering approach for similarity-based remaining useful life estimation

Cited by 77 publications

References 63 publications

Remaining Useful Life Estimation Using Long Short-Term Memory Neural Networks and Deep Fusion

Remaining Useful Life Estimation Using Long Short-Term Memory Neural Networks and Deep Fusion

Online Fault Detection in Autonomous Ferries: Using Fault-type Independent Spectral Anomaly Detection

Comparison of Computational Prognostic Methods for Complex Systems Under Dynamic Regimes: A Review of Perspectives

Contact Info

Product

Resources

About