Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones

Li, Qi; Gao, Zhiwei; Tang, Diyin; Li, Bao-An

doi:10.1016/j.cja.2016.04.007

Cited by 27 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section shortly introduces main concepts of RULmodelling, with the focus on work that permit maintenanceintegrated production scheduling. According to [7] the current techniques for RUL estimation can be roughly classified into physical-based approaches, data-driven approaches and their combinations, i.e. hybrid approaches.…”

Section: A Condition Monitoring and Rul Predictionmentioning

confidence: 99%

“…hybrid approaches. As [7] state that "complex systems […] [are too] complicated to map their precise physics to their exact failure mechanisms, thus datadriven approaches are good alternatives to accomplish the prognostic tasks", this section focuses data driven approaches. The reader shall be referred to [8] and [9] for a review of physical-based models for machine components.…”

Section: A Condition Monitoring and Rul Predictionmentioning

confidence: 99%

“…For complex systems as machine tools used in job shop production, many data-driven approaches for RUL estimation employ data fitting methods including machine learning and statistics-based methods to model the system deterioration process. According to [7], "existing methods have broadly presented two ways to describe the uncertainty in a degradation model. One is using probabilistic methods, in which the deterioration phenomenon is considered to have certain random behavior which is often characterized by probability laws, e.g., normal distribution, or by stochastic models, e.g.…”

Section: A Condition Monitoring and Rul Predictionmentioning

confidence: 99%

See 2 more Smart Citations

Formulation and Solution for the Predictive Maintenance Integrated Job Shop Scheduling Problem

Zhai¹,

Rieß²,

Reinhart³

2019

2019 IEEE International Conference on Prognostics and Health Management (ICPHM)

View full text Add to dashboard Cite

Predictive Maintenance has gained a lot of attention in recent years due to the development of improved sensors and intelligent algorithms. These allow for monitoring the health condition of production machinery and predict its future deterioration. In order to generate added value for industrial use cases, two more steps are required: considering the machine's time-varying operational conditions and integrating its dependent deterioration prediction in a holistic scheduling approach. This publication identifies a shortage of deterioration estimation frameworks under time-varying operational conditions as well as a lack of Predictive Maintenance integrated scheduling problems in the literature. Subsequently, a new conceptual framework to model future machine deterioration under time-varying operational conditions and its application in production scheduling is introduced. The Operation Specific Stress Equivalent (OSSE) represents the load of a future production job on the machine and supports a general formulation of the maintenance integrated job shop scheduling problem (MIJSSP). This formulation is presented together with benchmark instances and corresponding sample data. Finally, the formulation is tested with the help of a genetic algorithm that illustrates the potential of using new objective functions for decision support, such as the Reliability Weighted Makespan Cmax R .

show abstract

Section: A Condition Monitoring and Rul Predictionmentioning

confidence: 99%

Section: A Condition Monitoring and Rul Predictionmentioning

confidence: 99%

Section: A Condition Monitoring and Rul Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Formulation and Solution for the Predictive Maintenance Integrated Job Shop Scheduling Problem

Zhai¹,

Rieß²,

Reinhart³

2019

2019 IEEE International Conference on Prognostics and Health Management (ICPHM)

View full text Add to dashboard Cite

show abstract

“…The second approach for estimatingp f j is inspired by the use of Markov chains in regime-switching models in finance and to some extent also in the CBM literature for modeling different enviromental or operating regimes of a process 36,37,46,47 . The η n j,k = P (N j,k = n j,k ) ← estimate from historical data ∀n k 3:…”

Section: Markov Chain Approachmentioning

confidence: 99%

Data-Driven Optimization of Processes with Degrading Equipment

Wiebe

Cecı́lio

Misener

2018

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In chemical and manufacturing processes, unit failures due to equipment degradation can lead to process downtime and significant costs. In this context, finding an optimal maintenance strategy to ensure good unit health while avoiding excessive expensive maintenance activities is highly relevant. We propose a practical approach for the integrated optimization of production and maintenance capable of incorporating uncertain sensor data regarding equipment degradation. To this end, we integrate data-driven stochastic degradation models from Condition-based Maintenance into a process level mixed-integer optimization problem using Robust Optimization. We reduce computational expense by utilizing both analytical and data-based approximations and optimize the Robust Optimization parameters using Bayesian Optimization. We apply our framework to five instances of the State-Task-Network and demonstrate that it can efficiently compromise between equipment availability and cost of maintenance.

show abstract

“…Statistical data-driven methods have been widely used in RUL prediction due to their good mathematical properties [8]. Among the statistical data-driven methods, the most typical methods are based on stochastic process modeling, which mainly includes: regression model [14], gamma process [15], Wiener process [16][17][18], inverse Gaussian process [19][20][21], Markov chain [22,23], etc.…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Prediction Under Imperfect Prior Degradation Information

et al. 2020

View full text Add to dashboard Cite

The remaining useful life (RUL) prediction is the core of equipment maintenance and decisionmaking. Accurate RUL prediction can make effective maintenance before the failure occurs to reduce the probability of equipment failure. However, in industrial practice, we often face the situation that prior information is insufficient or inaccurate, which could influence our prediction of RUL and reduce the prediction accuracy severely. To solve this problem, we study the issue of RUL prediction under imperfect prior degradation data by reasonably fusing the prior information and the field degradation data. Firstly, based on the linear Wiener degradation process, we prove a conclusion that the random parameter estimation results by the joint Bayesian algorithm and the expectation-maximization (EM) algorithm are the same as that by the maximum likelihood estimation (MLE) method. It shows that the joint estimation method completely overcomes the influence of prior information, and the more iterations, the smaller proportion of prior information. Secondly, we also prove that the random parameter joint updating method for the nonlinear Wiener degradation process has the same characteristics. Then, a heuristic algorithm that reasonably fuses the prior information and the field degradation data is proposed, which controls the number of iterations of the joint updating algorithm based on the credibility of the prior information. It is also applied to the nonlinear degradation process by not iterating the nonlinear coefficients. Finally, the correctness of the conclusion of this paper is verified by the simulated degradation data, and the effectiveness of the proposed heuristic updating method is verified by the actual lithium battery degradation data.

show abstract

Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones

Cited by 27 publications

References 31 publications

Formulation and Solution for the Predictive Maintenance Integrated Job Shop Scheduling Problem

Formulation and Solution for the Predictive Maintenance Integrated Job Shop Scheduling Problem

Data-Driven Optimization of Processes with Degrading Equipment

Remaining Useful Life Prediction Under Imperfect Prior Degradation Information

Contact Info

Product

Resources

About