Direct Remaining Useful Life Estimation Based on Support Vector Regression

Khelif, Racha; Chebel-Morello, Brigitte; Malinowski, Simon; Laajili, Emna; Fnaiech, Farhat; Zerhouni, Noureddine

doi:10.1109/tie.2016.2623260

Cited by 323 publications

(117 citation statements)

References 32 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…In order to predict defects and model degradation phenomena in renewable energy storages, the work of [25] introduces an error correction factor that enhances the grey model (GM) without increasing complexity. A predictive method for remaining useful life (RUL) estimation is proposed in [26], that utilizes support vector regression to directly model the correlation between sensor values or health indicators and estimate RUL of equipment. In a related work [27], on RUL estimation and state diagnosis, a support vector regression model is used to simulate the battery aging mechanism and estimate impedance variables whereas a particle filter is employed to mitigate measurement noise and accurately estimate the impedance degradation parameters.…”

Section: Predictive Algorithms In Industrial Processesmentioning

confidence: 99%

A Deep Learning framework for simulation and defect prediction applied in microelectronics

Dimitriou¹,

Leontaris²,

Vafeiadis³

et al. 2020

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

The prediction of upcoming events in industrial processes has been a longstanding research goal since it enables optimization of manufacturing parameters, planning of equipment maintenance and more importantly prediction and eventually prevention of defects. While existing approaches have accomplished substantial progress, they are mostly limited to processing of one dimensional signals or require parameter tuning to model environmental parameters. In this paper, we propose an alternative approach based on deep neural networks that simulates changes in the 3D structure of a monitored object in a batch based on previous 3D measurements. In particular, we propose an architecture based on 3D Convolutional Neural Networks (3DCNN) in order to model the geometric variations in manufacturing parameters and predict upcoming events related to sub-optimal performance. We validate our framework on a microelectronics use-case using the recently published "PCB scans" dataset where we simulate changes on the shape and volume of glue deposited on an Liquid Crystal Polymer (LCP) substrate before the attachment of integrated circuits (IC). Experimental evaluation examines the impact of different choices in the cost function during training and shows that the proposed method can be efficiently used for defect prediction.

show abstract

Section: Predictive Algorithms In Industrial Processesmentioning

confidence: 99%

A Deep Learning framework for simulation and defect prediction applied in microelectronics

Dimitriou¹,

Leontaris²,

Vafeiadis³

et al. 2020

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

show abstract

“…Furthermore, the existing literature relevant to the selection of informative sensors is basically focused on the relevance of a sensor to the degradation process. While metrics of monotonicity [10,25], correlation and robustness [2,29] have been commonly utilized to evaluate the relevance of sensors for prognostics. There is a lack of efforts to consider the degree to which the sensors of a population of systems have the same underlying shape [24].…”

Section: Introductionmentioning

confidence: 99%

Aircraft Engine Prognostics Based on Informative Sensor Selection and Adaptive Degradation Modeling with Functional Principal Component Analysis

Zhang

Zheng

Huang

et al. 2020

Sensors

View full text Add to dashboard Cite

Engine prognostics are critical to improve safety, reliability, and operational efficiency of an aircraft. With the development in sensor technology, multiple sensors are embedded or deployed to monitor the health condition of the aircraft engine. Thus, the challenge of engine prognostics lies in how to model and predict future health by appropriate utilization of these sensor information. In this paper, a prognostic approach is developed based on informative sensor selection and adaptive degradation modeling with functional data analysis. The presented approach selects sensors based on metrics and constructs health index to characterize engine degradation by fusing the selected informative sensors. Next, the engine degradation is adaptively modeled with the functional principal component analysis (FPCA) method and future health is prognosticated using the Bayesian inference. The prognostic approach is applied to run-to-failure data sets of C-MAPSS test-bed developed by NASA. Results show that the proposed method can effectively select the informative sensors and accurately predict the complex degradation of the aircraft engine.Sensors 2020, 20, 920 2 of 21 reducing unnecessary maintenance and minimizing operational costs, prognostics have been an active research field for aircraft engine applications [3].Generally, the existing methods pertaining to aircraft engine prognostics can be classified into two categories: model-based and data-driven methods. For model-based methods, a mathematical model that can describe the engine health degradation process that is normally required to be constructed according to physical failure characteristics before prediction. Some typical model-based methods have been developed for engine health estimation and RUL prediction, such as the Markov model-based [4,5] and particle filtering-based method [6,7]. While model-based methods enable improved accuracy of engine prognostics, certain assumptions and simplifications of the adopted models may pose limitations on their practical deployment. With the rapid development of data mining techniques and the growing availability of health monitoring data, data-driven methods attract increasing attention. Data-driven methods utilize the information extracted or learned from observed data to identify the degradation behavior and predict the future health condition without using any particular physical model [8,9]. In this view, data-driven methods may be the more applicable prognostic solution for complicated systems, as aero-engines that have limited knowledge of physics-of-failure but have massive multi-sensor monitoring data. Among the data-driven prognostic methods, machine learning and statistical approaches are two popular branches. The common machine learning techniques used for prognostics include support vector regression [10], artificial neural network [11,12], fuzzy logic [13], etc. Machine learning methods are capable of dealing with prognostic issues of complex systems, but the predicted results are hard to be explained because ...

show abstract

“…Tao et al [20] considered the dynamic multi-state operating conditions, and trained the corresponding SVR model under different operating conditions, then the RUL of the on-service equipment can be predicted under time varying operating conditions. Some other SVR-based methods were developed in [32][33][34][35]. These studies promote the application of SVR-based methods in PHM, but due to the dispersity of samples' failure time, there is an inevitable drawback that the linearity of SVR model will increase with the increase of sample set, and overfitting or underfitting tends to occur [9].…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction based on a modified SVR method with health stage division, cluster sampling and similarity matching

Yan

Zhong

Cheng

et al. 2020

Preprint

View full text Add to dashboard Cite

Remaining useful life (RUL) prediction is an advanced methodology of prognostics and health management (PHM), and is in advantage of life cycles management of equipment and maintenance cost reduction. Among the data driven methods, support vector regression (SVR) is one of the most suitable methods when there are limited failure history data for analysis. However, many uncertain factors such as individual variation and time varying operating conditions, will lead that the failure time of all equipment statistically dispersive, and with the increase of sample set, such dispersity may inevitably increase and further reflects in the model training. In consequent, the dispersity may cause two drawbacks. On the one hand, the linearity of SVR model will increase with the increase of sample set, and overfitting or underfitting tends to occur. And on the other hand, a single model only performs well in its generalization and robustness, but may lost its effectiveness that it may fail to work well for a new on-service equipment. In order to deal with the two drawbacks, this paper proposes a modified SVR method with health stage division, cluster sampling and similarity matching. Through health stage division and cluster sampling, each state of the whole degradation process can obtain the optimal parameters, then the irrelevant linearity can be reduced. In addition, since that similar input results similar output, the optimal parameters of the most similar testing sample are also suitable for the on-service equipment, and through similarity matching the most similar testing sample can be obtained, thus the drawback of a single model can be avoided. Finally, the effectiveness of the proposed method is verified systematically by a simulated dataset of fatigue crack growth and a real-world degradation dataset of GaAs-based lasers.

show abstract

Direct Remaining Useful Life Estimation Based on Support Vector Regression

Cited by 323 publications

References 32 publications

A Deep Learning framework for simulation and defect prediction applied in microelectronics

A Deep Learning framework for simulation and defect prediction applied in microelectronics

Aircraft Engine Prognostics Based on Informative Sensor Selection and Adaptive Degradation Modeling with Functional Principal Component Analysis

Remaining useful life prediction based on a modified SVR method with health stage division, cluster sampling and similarity matching

Contact Info

Product

Resources

About