Condition-Based Maintenance of Machines Using Hidden Markov Models

Bunks, Carey; McCarthy, Dan; Al-Ani, Tarik

doi:10.1006/mssp.2000.1309

Cited by 233 publications

(161 citation statements)

References 5 publications

(6 reference statements)

Supporting

Mentioning

153

Contrasting

Unclassified

Order By: Relevance

“…Hidden Markov models build on the foundations of Markov chains and are particularly applicable in the case of predictive maintenance [35]. These more advanced models take into account the uncertainties underlying identification of which deterioration state an asset occupies.…”

Section: Failure Probabilitymentioning

confidence: 99%

Case Study for the Return on Investment of Internet of Things Using Agent-Based Modelling and Data Science

Houston

Gooberman-Hill

Mathie

et al. 2017

Systems

View full text Add to dashboard Cite

Abstract:As technology advances towards new paradigms such as the Internet of Things, there is a desire among business leaders for a reliable method to determine the value of supporting these ventures. Traditional simulation and analysis techniques cannot model the complex systems inherent in fields such as infrastructure asset management, or suffer from a lack of data on which to build a prediction. Agent-based modelling, through an integration with data science, presents an attractive simulation method to capture these underlying complexities and provide a solution. The aim of this work is to investigate this integration as a refined process for answering practical business questions. A specific case study is addressed to assess the return on investment of installing condition monitoring sensors on lift assets in a London Underground station. An agent-based model is developed for this purpose, supported by analysis from historical data. The simulation results demonstrate how returns can be achieved and highlight features induced as a result of stochasticity in the model. Suggestions of future research paths are additionally outlined.

show abstract

Section: Failure Probabilitymentioning

confidence: 99%

Case Study for the Return on Investment of Internet of Things Using Agent-Based Modelling and Data Science

Houston

Gooberman-Hill

Mathie

et al. 2017

Systems

View full text Add to dashboard Cite

show abstract

“…A five-state HMM is shown in Fig.1. The initial probability distribution vector is set to [1,0,0,0,0] . The observation probability of each state can be represented by mixture Gauss density functions [6].…”

Section: Hidden Markov Modelmentioning

confidence: 99%

“…Then the fitness ( ) f x should be introduced into the optimization function. The position and speed of the particle are updated according to the following evolution equation as ( 1) ( ) denotes the optimal position of the i th particle in current search,…”

Section: Adaptive Particle Swarm Optimization Algorithm With Extremalmentioning

confidence: 99%

See 1 more Smart Citation

Fault diagnosis of rolling bearing based on PSO and continuous Gaussian mixture HMM

Liao¹,

Zhu²,

Liu³

et al. 2016

Proceedings of the 2015 2nd International Conference on Machinery, Materials Engineering, Chemical Engineering and Biotechnolog

View full text Add to dashboard Cite

Abstract.As the hidden Markov model (HMM) has a strong ability of time sequence modeling, the continuous Gaussian mixture HMM is used to establish a model base of the rolling bearing fault. An adaptive particle swarm optimization (APSO) with extremum disturbed operator and dynamic change of inertia weights is introduced to the traditional training algorithm for solving the local extremum problem. The vibration signal is collected for extracting 12 order LPC coefficients as a feature vector through the dispose of adding window. In the given feature vector, the HMM is built for bearing fault condition monitoring and fault diagnosis. Then, different fault conditions experiment are carried out on the motor bearing test-bed. The experiment result shows that the method can use a small amount of samples for training HMM, and it is more effective and has higher classification accuracy in fault diagnosis compared with the traditional training algorithm.

show abstract

“…The degradation process is also often modelled as a Markov process with discrete states. Optimal replacement policies were derived for observable Markov processes by Makis and Jiang [20] and Kharoufeh et al [14] and from the evolution of the hidden states by Bunks et al [4] and Lin and Makis [18]. Further, proportional hazards models are often used to relate the system's condition variables to the hazard function of a system, so that the maintenance policies can be optimized with respect to the optimal risk value of the hazard function; see Jardine et al [12] and Vlok et al [32].…”

Section: Introductionmentioning

confidence: 99%

A condition-based maintenance model for a single component in a system with scheduled and unscheduled downs

Zhu

Peng

Timmermans³

et al. 2017

International Journal of Production Economics

View full text Add to dashboard Cite

Condition-Based Maintenance of Machines Using Hidden Markov Models

Cited by 233 publications

References 5 publications

Case Study for the Return on Investment of Internet of Things Using Agent-Based Modelling and Data Science

Case Study for the Return on Investment of Internet of Things Using Agent-Based Modelling and Data Science

Fault diagnosis of rolling bearing based on PSO and continuous Gaussian mixture HMM

A condition-based maintenance model for a single component in a system with scheduled and unscheduled downs

Contact Info

Product

Resources

About