Liner Wear Prediction Using Bayesian Regression Models and Clustering

Chutes, bins, and hoppers are critical assets in bulk commodity handling. Sacrificial wear liners are employed to protect these assets from abrasive wear. An essential maintenance challenge is optimising the timing of liner replacements. Traditionally, episodic human inspections have been in place,...

Full description

Saved in:
Bibliographic Details
Main Authors: Jacob Van Den Broek, Melinda Hodkiewicz, Adriano Polpo
Format: Article
Language:English
Published: The Prognostics and Health Management Society 2025-03-01
Series:International Journal of Prognostics and Health Management
Subjects:
Online Access:https://papers.phmsociety.org/index.php/ijphm/article/view/4266
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280281998622720
author Jacob Van Den Broek
Melinda Hodkiewicz
Adriano Polpo
author_facet Jacob Van Den Broek
Melinda Hodkiewicz
Adriano Polpo
author_sort Jacob Van Den Broek
collection DOAJ
description Chutes, bins, and hoppers are critical assets in bulk commodity handling. Sacrificial wear liners are employed to protect these assets from abrasive wear. An essential maintenance challenge is optimising the timing of liner replacements. Traditionally, episodic human inspections have been in place, but now, real-time wireless IoT sensing systems that measure liner thickness are being used. We propose a novel approach to estimate the remaining useful chute liner life. Instead of linear extrapolation based on individual sensor wear rates (commonly used in industry), we leverage a Clustered Bayesian Hierarchical Modeling (BHM). Two models are developed: Model 1 (Cluster Exemplar) uses parameters from the closest cluster exemplar, while Model 2 (Spatial and Temporal BHM) incorporates data from the active sensor, with prior distribution informed by Model 1. Data are drawn from a single hopper with 88 sensors, 20 of which reached their end-of-life threshold. Both Model 1 and Model 2 outperform the industry regression approach, significantly reducing overprediction. Notably, Model 2 predicts remaining useful life within 95% credible intervals and identifies anomalous sensor performance. This innovative use of historical and adjacent sensor data enhances wear degradation prediction, contributing valuable insights to the literature.
format Article
id doaj-art-0f74bc965ace4e2eacd78fadfd482de6
institution OA Journals
issn 2153-2648
language English
publishDate 2025-03-01
publisher The Prognostics and Health Management Society
record_format Article
series International Journal of Prognostics and Health Management
spelling doaj-art-0f74bc965ace4e2eacd78fadfd482de62025-08-20T01:48:49ZengThe Prognostics and Health Management SocietyInternational Journal of Prognostics and Health Management2153-26482025-03-01161111https://doi.org/10.36001/ijphm.2025.v16i1.4266Liner Wear Prediction Using Bayesian Regression Models and ClusteringJacob Van Den Broek0Melinda Hodkiewicz1Adriano Polpo2https://orcid.org/0000-0002-5959-1808School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, 6009, AustraliaSchool of Engineering, University of Western Australia, Perth, WA, 6009, AustraliaUniversity of Western AustraliaChutes, bins, and hoppers are critical assets in bulk commodity handling. Sacrificial wear liners are employed to protect these assets from abrasive wear. An essential maintenance challenge is optimising the timing of liner replacements. Traditionally, episodic human inspections have been in place, but now, real-time wireless IoT sensing systems that measure liner thickness are being used. We propose a novel approach to estimate the remaining useful chute liner life. Instead of linear extrapolation based on individual sensor wear rates (commonly used in industry), we leverage a Clustered Bayesian Hierarchical Modeling (BHM). Two models are developed: Model 1 (Cluster Exemplar) uses parameters from the closest cluster exemplar, while Model 2 (Spatial and Temporal BHM) incorporates data from the active sensor, with prior distribution informed by Model 1. Data are drawn from a single hopper with 88 sensors, 20 of which reached their end-of-life threshold. Both Model 1 and Model 2 outperform the industry regression approach, significantly reducing overprediction. Notably, Model 2 predicts remaining useful life within 95% credible intervals and identifies anomalous sensor performance. This innovative use of historical and adjacent sensor data enhances wear degradation prediction, contributing valuable insights to the literature.https://papers.phmsociety.org/index.php/ijphm/article/view/4266bayesian hierarchicaliotchuteinstrumented boltlinerwear prediction
spellingShingle Jacob Van Den Broek
Melinda Hodkiewicz
Adriano Polpo
Liner Wear Prediction Using Bayesian Regression Models and Clustering
International Journal of Prognostics and Health Management
bayesian hierarchical
iot
chute
instrumented bolt
liner
wear prediction
title Liner Wear Prediction Using Bayesian Regression Models and Clustering
title_full Liner Wear Prediction Using Bayesian Regression Models and Clustering
title_fullStr Liner Wear Prediction Using Bayesian Regression Models and Clustering
title_full_unstemmed Liner Wear Prediction Using Bayesian Regression Models and Clustering
title_short Liner Wear Prediction Using Bayesian Regression Models and Clustering
title_sort liner wear prediction using bayesian regression models and clustering
topic bayesian hierarchical
iot
chute
instrumented bolt
liner
wear prediction
url https://papers.phmsociety.org/index.php/ijphm/article/view/4266
work_keys_str_mv AT jacobvandenbroek linerwearpredictionusingbayesianregressionmodelsandclustering
AT melindahodkiewicz linerwearpredictionusingbayesianregressionmodelsandclustering
AT adrianopolpo linerwearpredictionusingbayesianregressionmodelsandclustering