Remaining useful life estimation on the non-homogenous gamma with noise deterioration based on Gibbs filtering: A case study

Son, Khanh Le; Fouladirad, Mitra; Barros, Anne

doi:10.1109/icphm.2012.6299520

Cited by 27 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) The performance is still better with the four-branch HsMM model: the score of S = 4056 is again better than the score of S = 4107 obtained with the non homogeneous Gamma process method in Le Son et al (2012b), despite the fact that our model use the "discrete" states to approximate the "continuous" degradation data.…”

Section: Fig 4 Rul Definition At the Quantile Of 95%mentioning

confidence: 67%

“…The results obtained are represented in the Table 2. In this table, we also introduce the score results obtained with an "average" HsMM model, which has only one branch as well as with the Wiener process-based methods in Le Son et al (2012a) and the Gamma process-based method in Le Son et al (2012b). There are some points that could be concluded from the results:…”

Section: Fig 4 Rul Definition At the Quantile Of 95%mentioning

confidence: 92%

See 1 more Smart Citation

Prognosis based on Multi-branch Hidden semi-Markov Models: A case study

Bérenguer

Chatelain

2015

IFAC-PapersOnLine

View full text Add to dashboard Cite

This paper proposes a multi-branch model to deal with Remaining Useful Life (RUL) estimation problem in the case where several deterioration modes co-exist within a single component. By basing on Hidden semi-Markov Models (HsMM), the component is supposed to pass through some discrete and unobservable health states until it fails. The rate and the manner of these state transitions, however, depend on the mode of deterioration that is actually active. We show that by taking into account the co-existence of different deterioration modes, the multibranch model can help to improve prognosis results, which is essential for the implementation of a predictive maintenance. A practical case study is investigated to evaluate the advantages of the proposed model.

show abstract

Section: Fig 4 Rul Definition At the Quantile Of 95%mentioning

confidence: 67%

Section: Fig 4 Rul Definition At the Quantile Of 95%mentioning

confidence: 92%

Prognosis based on Multi-branch Hidden semi-Markov Models: A case study

Bérenguer

Chatelain

2015

IFAC-PapersOnLine

View full text Add to dashboard Cite

show abstract

“…Unlike the Wiener process, the Gamma process is used for modeling monotonic degradation processes where deterioration takes place gradually [20]. As for Wiener process, there are plenty of applications of this method reported in literature: [21] proposes a remaining useful lifetime estimation, by considering a simulated noisy observation set corresponding to a Gamma process with additive Gaussian noise; [22] utilized degradation data in order to simulate the degradation process of components by implementing Gamma process and [23] aimed to predict the residual useful life of a component, by implementing an adaptive gamma process. The author used a state space model for updating the parameters of the gamma model whenever a new observation was available.…”

Section: Current State Of Failure Prognosis Methodsmentioning

confidence: 99%

Implementation of System Operation Modes for Health Management and Failure Prognosis in Cyber-Physical Systems

Ruiz-Arenas

Rusák

Mejía-Gutiérrez

et al. 2020

Sensors

View full text Add to dashboard Cite

Cyber-physical systems (CPSs) have sophisticated control mechanisms that help achieve optimal system operations and services. These mechanisms, imply considering multiple signal inputs in parallel, to timely respond to varying working conditions. Despite the advantages that control mechanisms convey, they bring new challenges in terms of failure prevention. The compensatory action the control exerts cause a fault masking effect, hampering fault diagnosis. Likewise, the multiple information inputs CPSs have to process can affect the timely system response to faults. This article proposes a failure prognosis method, which combines time series-based forecasting methods with statistically based classification techniques in order to investigate system degradation and failure forming on system levels. This method utilizes a new approach based on the concept of the system operation mode (SOM) that offers a novel perspective for health management that allows monitoring the system behavior, through the frequency and duration of SOMs. Validation of this method was conducted by systematically injecting faults in a cyber-physical greenhouse testbed. The obtained results demonstrate that the degradation and fault forming process can be monitored by analyzing the changes of the frequency and duration of SOMs. These indicators made possible to estimate the time to failure caused by various failures in the conducted experiments.

show abstract

“…The extended Kalman filter (EKF) and the particle filter [30][31][32] are examples of state-space algorithms. Other model-based approaches include the Eyring model [33][34][35] and Weibull distribution [36]. Other physical model-based models, that require a mathematical model of the degradation of the system, were used on bearings [37] and aircraft actuators [38].…”

Section: Fault Prognosismentioning

confidence: 99%

Fault Detection, Isolation and Prognosis of Aerospace Systems Using Adaptive Growing Recurrent Neural Networks

ElDali¹

2021

Preprint

View full text Add to dashboard Cite

Due to the increase in complexity in aerospace systems, developing a diagnosis, prognosis and health monitoring (DPHM) framework is a challenge that must be considered to assure the safety of such systems. This thesis discusses this problem by proposing a novel growing neural network model to automate the process of DPHM for aerospace systems. The model optimizes the architecture of a recurrent neural network and was used to make Remaining Useful Lifetime (RUL) predictions for aircraft engines and detect failure for satellite attitude actuators (Reaction Wheels). It was tested on the CMAPSS and PHM08 aircraft engine datasets simulated by NASA, and it was able to make RUL predictions with root mean square errors as low as 14.31 engine cycles. Another application to test the proposed model was on the Kepler Spacecraft’s reaction wheels from which two have failed. The model detected the failure of the two failed reaction wheels by estimating a Health Index value which indicates the probability of failure of the reaction wheels using the residuals between the speed predictions made by the model and measured speed values. Failure was predicted using the model 105 days and 54 days before it occurred for reaction wheels two and four respectively. Prognostics were also applied on the Kepler Mission reaction wheels and RUL predictions were made with mean absolute errors ranging between 2-13 days depending on how close the reaction wheel is to failure. The proposed algorithm showed results in both applications that could regard it as a promising approach for DPHM models.

show abstract

Remaining useful life estimation on the non-homogenous gamma with noise deterioration based on Gibbs filtering: A case study

Cited by 27 publications

References 15 publications

Prognosis based on Multi-branch Hidden semi-Markov Models: A case study

Prognosis based on Multi-branch Hidden semi-Markov Models: A case study

Implementation of System Operation Modes for Health Management and Failure Prognosis in Cyber-Physical Systems

Fault Detection, Isolation and Prognosis of Aerospace Systems Using Adaptive Growing Recurrent Neural Networks

Contact Info

Product

Resources

About