Variational encoding approach for interpretable assessment of remaining useful life estimation

Costa, Nahuel; Sánchez, Luciano

doi:10.1016/j.ress.2022.108353

Cited by 63 publications

(24 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RUL-RVE emerges as a solution to these problems: it proposes the use of a powerful yet lightweight Deep Learning model: an encoder, implemented with recurrent networks to deal with the temporality of the data, that provides an interpretable evaluation of the component to be monitored. The framework is still young and has been recently published [7] so it has not yet been used in any other existing publications, however, it can be leveraged both in industry and research.…”

Section: Impact Overviewmentioning

confidence: 99%

“…A demo of the model presented in [7] is available at https:// huggingface.co/spaces/NahuelCosta/RUL-Variational. The user is presented with the 4 subsets of the CMAPSS dataset, from which they can choose which engine of the test set they want to know the RUL and its representation in the latent space.…”

Section: Illustrative Examplesmentioning

confidence: 99%

“…In fact, these are attributes of particular interest, if not demanded, for decision making in safety-critical applications [6]. RUL-RVE [7] is a framework for the task of accurately estimating RUL while providing an explainable and interpretable diagnosis. Its performance was validated on the popular C-MAPSS dataset from NASA [8].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

RUL-RVE: Interpretable assessment of Remaining Useful Life

Costa

Sánchez

2022

Software Impacts

Self Cite

View full text Add to dashboard Cite

Section: Impact Overviewmentioning

confidence: 99%

Section: Illustrative Examplesmentioning

confidence: 99%

See 1 more Smart Citation

RUL-RVE: Interpretable assessment of Remaining Useful Life

Costa

Sánchez

2022

Software Impacts

Self Cite

View full text Add to dashboard Cite

“…Since a degradation trend has not yet developed, it is assumed that a machine-specific and meaningful RUL prediction cannot be obtained during this phase. A common approach to address this issue is to exclude all training samples or relabel those above a certain RUL value to a predefined constant value (in case of C-MAPSS, typically between 120 and 130) [37], [44], [58]- [61]. However, this approach neglects variability between individual machine units.…”

Section: ) Degradation Detectionmentioning

confidence: 99%

Data-Efficient Estimation of Remaining Useful Life for Machinery With a Limited Number of Run-to-Failure Training Sequences

2022

View full text Add to dashboard Cite

Prognostics and Health Monitoring (PHM) of machinery is a research area with great relevance to industrial applications as it can serve as a foundation for safer, more cost-efficient operation and maintenance. The prediction of Remaining Useful Life (RUL) plays an important part in this field and has seen significant advances from the introduction of machine learning methods. However, these methods typically require model training with a large number of run-to-failure sequences, which are often not feasible to obtain due to the required time and cost investments. The present study addresses this issue by introducing a novel methodology, which first quantifies the deviation from the machine's health and fault state and then calculates a machine Health Index (HI) prior to the prediction of RUL. In addition, the start of a degradation state is determined. Alternative implementations of the proposed methodology are compared utilising several methods, including Support Vector Regression (SVR), Long Short-Term Memory (LSTM) Neural Network (NN), Mahalanobis Distance (MD), and LSTM Autoencoder (AE) NN. The methodology is applied to the open turbofan degradation (C-MAPSS) and bearing vibration (FEMTO-ST PROGNOSTIA) datasets. When a reduced subset of training sequences is used, the prediction results demonstrate that the proposed methodology largely outperforms the baseline method without HI generation. For example, when comparing prediction errors of the C-MAPSS dataset at a reduction of the available number of training sequences to 5%, the proposed method shows an average prediction improvement by 6.5% -19.2% relative to the baseline method. The presented approach is therefore suitable to improve model generalisation for cases with a limited number of training sequences. When the full training set is utilised, the most resource-saving variant of the proposed approach achieves an average training duration of 8.9% compared to the baseline method. Hence, an additional contribution of the presented data-efficient approach is the reduction of required computing resources, which has implications on training time, energy consumption, and environmental impact.

show abstract

“…Supervised Learning (SL) is one of the two broad branches of ML that formulates the model permits to predict future outcomes after being trained on an empirical basis [26]. Labeled data is used to train the model to create a function when it is sufficient to be able to estimate the approximate output for new inputs [27] The work has proposed for classifying various types of rice diseases by extracting features from the infected areas of the rice plant images [28]. Fermi energy-based segmentation technique has been suggested to separate the infected area of the image from its surroundings [29].…”

Section: ░ 1 Introductionmentioning

confidence: 99%

Linear Vector Quantization for the Diagnosis of Ground Bud Necrosis Virus in Tomato

Kadam

Dhumale²,

Dhumale

et al. 2022

IJEER

View full text Add to dashboard Cite

In this varying environment, a correct and appropriate disease diagnosis including early preclusion has never been more significant. Our study on disease identification of groundnut originated by Groundnut Bud Necrosis Virus will cover the way to the effective use of image processing approach in agriculture. The difficulty of capable plant disease protection is very much linked to the problems of sustainable agriculture and climate change. Due to the fast advancement of Artificial Intelligence, the work in this paper is primarily focused on applying Pattern Recognition based techniques. The purpose is to determine the grade of disease to control by developing a model for the selection of bud blight disease caused by GBNV in tomatoes. The images are classified according to the grade of the disease. Different methods have been applied to make a proper diagnosis by bringing clarity in the diagnostic results. Linear Vector Quantization works well than, Radial Basis Function, Back Propagation Neural Network and Support Vector Machine.

show abstract

Variational encoding approach for interpretable assessment of remaining useful life estimation

Cited by 63 publications

References 35 publications

RUL-RVE: Interpretable assessment of Remaining Useful Life

RUL-RVE: Interpretable assessment of Remaining Useful Life

Data-Efficient Estimation of Remaining Useful Life for Machinery With a Limited Number of Run-to-Failure Training Sequences

Linear Vector Quantization for the Diagnosis of Ground Bud Necrosis Virus in Tomato

Contact Info

Product

Resources

About