Developing and evaluating predictive conveyor belt wear models
Conveyor belt wear is an important consideration in the bulk materials handling industry. We define four belt wear rate metrics and develop a model to predict wear rates of new conveyor configurations using an industry dataset that includes ultrasonic thickness measurements, conveyor attributes, and...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Cambridge University Press
2020-01-01
|
Series: | Data-Centric Engineering |
Subjects: | |
Online Access: | https://www.cambridge.org/core/product/identifier/S2632673620000015/type/journal_article |
_version_ | 1811156498304204800 |
---|---|
author | Callum Webb Joanna Sikorska Ramzan Nazim Khan Melinda Hodkiewicz |
author_facet | Callum Webb Joanna Sikorska Ramzan Nazim Khan Melinda Hodkiewicz |
author_sort | Callum Webb |
collection | DOAJ |
description | Conveyor belt wear is an important consideration in the bulk materials handling industry. We define four belt wear rate metrics and develop a model to predict wear rates of new conveyor configurations using an industry dataset that includes ultrasonic thickness measurements, conveyor attributes, and conveyor throughput. All variables are expected to contribute in some way to explaining wear rate and are included in modeling. One specific metric, the maximum throughput-based wear rate, is selected as the prediction target, and cross-validation is used to evaluate the out-of-sample performance of random forest and linear regression algorithms. The random forest approach achieves a lower error of 0.152 mm/megatons (standard deviation [SD] = 0.0648). Permutation importance and partial dependence plots are computed to provide insights into the relationship between conveyor parameters and wear rate. This work demonstrates how belt wear rate can be quantified from imprecise thickness testing methods and provides a transparent modeling framework applicable to other supervised learning problems in risk and reliability. |
first_indexed | 2024-04-10T04:51:37Z |
format | Article |
id | doaj.art-7fd414bf938343188ce8733727867111 |
institution | Directory Open Access Journal |
issn | 2632-6736 |
language | English |
last_indexed | 2024-04-10T04:51:37Z |
publishDate | 2020-01-01 |
publisher | Cambridge University Press |
record_format | Article |
series | Data-Centric Engineering |
spelling | doaj.art-7fd414bf938343188ce87337278671112023-03-09T12:31:42ZengCambridge University PressData-Centric Engineering2632-67362020-01-01110.1017/dce.2020.1Developing and evaluating predictive conveyor belt wear modelsCallum Webb0https://orcid.org/0000-0001-8029-6670Joanna Sikorska1https://orcid.org/0000-0003-2969-8863Ramzan Nazim Khan2https://orcid.org/0000-0003-3349-5006Melinda Hodkiewicz3https://orcid.org/0000-0002-7336-3932WearHawk Pty. Ltd., Western Australia, AustraliaFaculty of Engineering and Mathematical Sciences, University of Western Australia, Perth, Western Australia, AustraliaDepartment of Mathematics and Statistics, University of Western Australia, Perth, Western Australia, AustraliaFaculty of Engineering and Mathematical Sciences, University of Western Australia, Perth, Western Australia, AustraliaConveyor belt wear is an important consideration in the bulk materials handling industry. We define four belt wear rate metrics and develop a model to predict wear rates of new conveyor configurations using an industry dataset that includes ultrasonic thickness measurements, conveyor attributes, and conveyor throughput. All variables are expected to contribute in some way to explaining wear rate and are included in modeling. One specific metric, the maximum throughput-based wear rate, is selected as the prediction target, and cross-validation is used to evaluate the out-of-sample performance of random forest and linear regression algorithms. The random forest approach achieves a lower error of 0.152 mm/megatons (standard deviation [SD] = 0.0648). Permutation importance and partial dependence plots are computed to provide insights into the relationship between conveyor parameters and wear rate. This work demonstrates how belt wear rate can be quantified from imprecise thickness testing methods and provides a transparent modeling framework applicable to other supervised learning problems in risk and reliability.https://www.cambridge.org/core/product/identifier/S2632673620000015/type/journal_articleConveyor beltcross-validationmeasurementpredictionwear |
spellingShingle | Callum Webb Joanna Sikorska Ramzan Nazim Khan Melinda Hodkiewicz Developing and evaluating predictive conveyor belt wear models Data-Centric Engineering Conveyor belt cross-validation measurement prediction wear |
title | Developing and evaluating predictive conveyor belt wear models |
title_full | Developing and evaluating predictive conveyor belt wear models |
title_fullStr | Developing and evaluating predictive conveyor belt wear models |
title_full_unstemmed | Developing and evaluating predictive conveyor belt wear models |
title_short | Developing and evaluating predictive conveyor belt wear models |
title_sort | developing and evaluating predictive conveyor belt wear models |
topic | Conveyor belt cross-validation measurement prediction wear |
url | https://www.cambridge.org/core/product/identifier/S2632673620000015/type/journal_article |
work_keys_str_mv | AT callumwebb developingandevaluatingpredictiveconveyorbeltwearmodels AT joannasikorska developingandevaluatingpredictiveconveyorbeltwearmodels AT ramzannazimkhan developingandevaluatingpredictiveconveyorbeltwearmodels AT melindahodkiewicz developingandevaluatingpredictiveconveyorbeltwearmodels |