Degradation modeling and monitoring of machines using operation-specific hidden Markov models

Cholette, Michael E.; Djurdjanović, Dragan

doi:10.1080/0740817x.2014.905734

Cited by 18 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is no universal solution for nonlinear problems . HMM is also used for degradation modeling, prognosis, and process monitoring . Vrignat et al proposed an HMM approach that takes into account the events collected about a system, to predict the degradation level of a system.…”

Section: Introductionmentioning

confidence: 99%

Degradation modeling and classification of mixed populations using segmental continuous hidden Markov models

Chen

Xia

et al. 2018

Quality & Reliability Eng

View full text Add to dashboard Cite

With the market demands, the classification for highly reliable products becomes more and more significant. The degradation data can provide information about the degradation states and can be used to classify products to various classes according to the reliability attribute. In this paper, a temporal probabilistic approach, named segmental continuous hidden Markov model (SCHMM), is proposed to tackle the problem of degradation modeling and classification for mixed populations. Separate SCHMMs are built for each class of the mixed populations. The SCHMMs can directly depict the correspondence between actual degradation and the hidden states. A novel method called self-training algorithm for the preprocessing of the original data from the mixed populations is proposed. Furthermore, the unknown parameters of the SCHMMs are estimated by the maximum likelihood method with the complete degradation data.The root mean square error of the estimated degradation value compared with the actual physical degradation value, as well as Akaike information criterion and Bayesian information criterion, is used for the evolution of the fitting accuracy and the selection of model topologies and discretization methods. Then the maximum posterior probability-based classification criteria are developed.Degradation tests are designed for the data collection. To obtain the optimal classification policies, a cost function that consists of the degradation test cost and misclassification cost is constructed. A numerical example is used to illustrate the proposed method and demonstrate its advantages by comparing with other classification methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Degradation modeling and classification of mixed populations using segmental continuous hidden Markov models

Chen

Xia

et al. 2018

Quality & Reliability Eng

View full text Add to dashboard Cite

show abstract

“…Roca et al [11,12] used neural networks and acoustic emission signals to estimate the stability of gas metal arc welding (GMAW) process, and it is a good method to analyze the AE signals, although the characteristics of AE signal of high-speed train gearbox shell is different from that of GMAW. Cholette et al [13] presented a novel data-driven degradation modeling and monitoring methodology based on hidden Markov models; but the method needs a large data set. Hong et al [14] put forward a novel performance degradation assessment method based on ensemble empirical mode composition and Gaussian mixture model, however, their data was not in real-time.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Material Performance Degradation for High-Strength Aluminum Alloy Using Acoustic Emission Method

Sun

Que³

et al. 2015

Metals

View full text Add to dashboard Cite

Structural materials damages are always in the form of micro-defects or cracks. Traditional or conventional methods such as micro and macro examination, tensile, bend, impact and hardness tests can be used to detect the micro damage or defects. However, these tests are destructive in nature and not in real-time, thus a non-destructive and real-time monitoring and characterization of the material damage is needed. This study is focused on the application of a non-destructive and real-time acoustic emission (AE) method to study material performance degradation of a high-strength aluminum alloy of high-speed train gearbox shell. By applying data relative analysis and interpretation of AE signals, the characteristic parameters of materials performance were achieved and the failure criteria of the characteristic parameters for the material tensile damage process were established. The results show that the AE method and signal analysis can be used to accomplish the non-destructive and real-time detection of the material performance degradation process of the high-strength aluminum alloy. This technique can be extended to other engineering materials.

show abstract

A Hidden Markov Model Based Approach to Modeling and Monitoring of Processes with Imperfect Maintenance

Zhang

Djurdjanović

2019

Proceedings of the 4th International Conference on the Industry 4.0 Model for Advanced Manufacturing

View full text Add to dashboard Cite

Degradation modeling and monitoring of machines using operation-specific hidden Markov models

Cited by 18 publications

References 38 publications

Degradation modeling and classification of mixed populations using segmental continuous hidden Markov models

Degradation modeling and classification of mixed populations using segmental continuous hidden Markov models

Investigation of Material Performance Degradation for High-Strength Aluminum Alloy Using Acoustic Emission Method

A Hidden Markov Model Based Approach to Modeling and Monitoring of Processes with Imperfect Maintenance

Contact Info

Product

Resources

About