Abstract
ABSTRACT Health state evaluation of machines is a crucial component of smart manufacturing technology as it provides a prerequisite for predictive maintenance. However, challenges arise not only from the vast amount of data required to train models but also from the low accuracy of the trained models and the complexity of multi-machine health state identification. To address these challenges, a production line health state grading evaluation method based on the bi-Kmeans algorithm and a degraded hidden Markov model was proposed, considering Multi-machine sequences. The bi-Kmeans algorithm was employed to cluster the input data of the production line, optimizing the initial values of the hidden Markov model and making the training results more globally optimal; the exponential degradation factor was utilized to enhance the model’s fitting ability, making it closer to the actual degradation process and improving evaluation accuracy. Finally, using a production line with six machines as an example, the bi-Kmeans algorithm and degradation factor show positive effects in fitting the degradation state of the production line. By employing the degraded hidden Markov model, guidance can be provided to production lines, avoiding unexpected downtimes, reducing maintenance frequency, lowering maintenance costs, and ultimately improving overall efficiency.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Computer Integrated Manufacturing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
