Machine condition recognition via hidden semi-Markov model

Abstract In intelligent manufacturing systems, machines are subject to condition deterioration.Identifying machine condition is crucial for making practical decisions in production management. This paper studies the machine condition recognition problem in wafer fabrication. A sequence of processing times collected from past production is used to train a hidden semi-Markov model (HSMM). To improve the precision of the HSMM in the application of wafer fabrication, state duration dependency is considered. Experimental analyses based on real data demonstrate the effectiveness of the HSMM and reveal some managerial insights.

[1]  Stanislaw Gawiejnowicz,et al.  Time-Dependent Scheduling , 2008, Monographs in Theoretical Computer Science. An EATCS Series.

[2]  C.-Y. Lee,et al.  Machine scheduling with a rate-modifying activity , 2001, Eur. J. Oper. Res..

[3]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[4]  Chou-Jung Hsu,et al.  Due date assignment and scheduling with time and positional dependent effects , 2018 .

[5]  Kunpeng Zhu,et al.  Online Tool Wear Monitoring Via Hidden Semi-Markov Model With Dependent Durations , 2018, IEEE Transactions on Industrial Informatics.

[6]  Noureddine Zerhouni,et al.  Health assessment and life prediction of cutting tools based on support vector regression , 2015, J. Intell. Manuf..

[7]  Bidyut B. Chaudhuri,et al.  A Modified LSTM Model for Continuous Sign Language Recognition Using Leap Motion , 2019, IEEE Sensors Journal.

[8]  Chin-Chia Wu,et al.  Minimizing the makespan on a single machine with learning and unequal release times , 2010, Comput. Ind. Eng..

[9]  Ali Azadeh,et al.  A single-machine scheduling problem with learning effect, deterioration and non-monotonic time-dependent processing times , 2017, Int. J. Comput. Integr. Manuf..

[10]  Xin Li,et al.  Optimal Bayesian control policy for gear shaft fault detection using hidden semi-Markov model , 2018, Comput. Ind. Eng..

[11]  Elijah Kannatey-Asibu,et al.  Hidden Markov model-based tool wear monitoring in turning , 2002 .

[12]  Ran Jin,et al.  Functional Graphical Models for Manufacturing Process Modeling , 2017, IEEE Transactions on Automation Science and Engineering.

[13]  Ratna Babu Chinnam,et al.  Autonomous diagnostics and prognostics through competitive learning driven HMM-based clustering , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[14]  Hua Chai,et al.  Condition Monitoring Based on Partial Discharge Diagnostics Using Machine Learning Methods: A Comprehensive State-of-the-Art Review , 2020, IEEE Transactions on Dielectrics and Electrical Insulation.

[15]  Vitaly A. Strusevich,et al.  Single machine scheduling with a generalized job-dependent cumulative effect , 2017, J. Sched..

[16]  Dar-Li Yang,et al.  Minimizing the makespan in a single machine scheduling problem with a time-based learning effect , 2006, Inf. Process. Lett..

[17]  Chin-Chia Wu,et al.  Tardiness minimisation for a customer order scheduling problem with sum-of-processing-time-based learning effect , 2019, J. Oper. Res. Soc..

[18]  Huanyi Shui,et al.  Twofold Variation Propagation Modeling and Analysis for Roll-to-Roll Manufacturing Systems , 2019, IEEE Transactions on Automation Science and Engineering.

[19]  Shudong Sun,et al.  A Hidden Semi-Markov Model with Duration-Dependent State Transition Probabilities for Prognostics , 2014 .

[20]  Lu Chen,et al.  A single machine scheduling problem with machine availability constraints and preventive maintenance , 2020 .

[21]  Mehdi Hosseinabadi Farahani,et al.  Minimizing cycle time in single machine scheduling with start time-dependent processing times , 2013 .

[22]  Jay Lee,et al.  Recent advances and trends in predictive manufacturing systems in big data environment , 2013 .

[23]  Min Huang,et al.  Improved estimation of distribution algorithm for the problem of single-machine scheduling with deteriorating jobs and different due dates , 2014 .

[24]  Viliam Makis,et al.  Model parameter estimation and residual life prediction for a partially observable failing system , 2015 .

[25]  Ming Chen,et al.  A novel method for tool condition monitoring based on long short-term memory and hidden Markov model hybrid framework in high-speed milling Ti-6Al-4V , 2019, The International Journal of Advanced Manufacturing Technology.

[26]  Suh-Jenq Yang.  Single-machine scheduling problems with both start-time dependent learning and position dependent aging effects under deteriorating maintenance consideration , 2010, Appl. Math. Comput..

[27]  Thong Ngee Goh,et al.  A modified Weibull extension with bathtub-shaped failure rate function , 2002, Reliab. Eng. Syst. Saf..

[28]  Christos Koulamas,et al.  Single-machine and two-machine flowshop scheduling with general learning functions , 2007, Eur. J. Oper. Res..

[29]  Kun Cao,et al.  Reliability and temperature constrained task scheduling for makespan minimization on heterogeneous multi-core platforms , 2017, J. Syst. Softw..

[30]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[31]  Adam Janiak,et al.  Scheduling jobs with position-dependent processing times , 2004, J. Oper. Res. Soc..

[32]  Dar-Li Yang,et al.  Minimizing the total completion time in a single-machine scheduling problem with a time-dependent learning effect , 2006, Eur. J. Oper. Res..

[33]  Yan Wang,et al.  Real-time FDM machine condition monitoring and diagnosis based on acoustic emission and hidden semi-Markov model , 2017 .

[34]  Ting Wang,et al.  A branch-and-price algorithm for scheduling of deteriorating jobs and flexible periodic maintenance on a single machine , 2018, Eur. J. Oper. Res..

[35]  Yan-Feng Li,et al.  An Enhanced Deep Learning-Based Fusion Prognostic Method for RUL Prediction , 2020, IEEE Transactions on Reliability.

[36]  Pei-Wei Tsai,et al.  Scheduling of unrelated parallel machines considering sequence-related setup time, start time-dependent deterioration, position-dependent learning and power consumption minimization , 2020 .

[37]  Gur Mosheiov,et al.  Minmax scheduling with acceptable lead-times: Extensions to position-dependent processing times, due-window and job rejection , 2017, Comput. Oper. Res..

[38]  Ji-Bo Wang,et al.  Single-machine scheduling problems with the effects of learning and deterioration , 2007 .

[39]  Chin-Chia Wu,et al.  Simulated-annealing heuristics for the single-machine scheduling problem with learning and unequal job release times , 2011 .

[40]  Qiong Liu,et al.  Tool Wear Status Recognition and Prediction Model of Milling Cutter Based on Deep Learning , 2021, IEEE Access.

[41]  Yung-Tsung Hou,et al.  Big data analysis for distributed computing job scheduling and reliability evaluation , 2019, Microelectronics Reliability.

[42]  Bruno Castanier,et al.  Joint optimization of a master production schedule and a preventive maintenance policy , 2013, Proceedings of 2013 International Conference on Industrial Engineering and Systems Management (IESM).

[43]  Jan Lundberg,et al.  Remaining useful life prediction of grinding mill liners using an artificial neural network , 2013 .

[44]  T. C. Edwin Cheng,et al.  Single-machine scheduling with periodic maintenance to minimize makespan , 2007, Comput. Oper. Res..

[45]  Ran Jin,et al.  Ensemble Modeling of In Situ Features for Printed Electronics Manufacturing With In Situ Process Control Potential , 2017, IEEE Robotics and Automation Letters.

[46]  Debi Prosad Dogra,et al.  A segmental HMM based trajectory classification using genetic algorithm , 2018, Expert Syst. Appl..