Developing and evaluating predictive conveyor belt wear models

Abstract

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.

DRAT: Data risk assessment tool for university–industry collaborations

“…To achieve robust validation, data from at least one (preferably more than one) industry partner are required. However, a recent review of process system failure and reliability literature reports that "collaborative works between industry and academia are observed to be rare" (Amin et al, 2019) and we have shown elsewhere that few published models in this field are validated using industry data (Webb et al, 2020). We suggest that datasharing in the field of EAM is sufficiently problematic as to be reducing the progress of the field by restricting researchers' access to data required to develop effective models for asset life prediction and to improve maintenance management practice.…”

“…Similarly, individuals are less likely to want to share data if it is labor-intensive to do prepare (Borgman, 2012). As noted earlier EAM data come from numerous data sources and is often very difficult to aggregate and assimilate (Webb et al, 2020). Some of it can even be kept in proprietary systems and thus not possible to extract in an appropriate form.…”

“…Mining company wear conveyor monitoring (Webb et al, 2020) Data for each conveyor in the study: Operating hours and tonnages (movements), Conveyor belt design data, Conveyor usage, Wear thickness reports.…”

Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts

“…The non-destructive testing (NDT) of conveyor belts gives vast possibilities related to optimization of the belt conveyor maintenance costs, through choosing the right moment for repair, replacement or recondition of the belt based on, among others, detected damage [1] or the rate of change of belt thickness [2]. Belt operating time depends on several factors that were presented in the article [2]. NDT research use, inter alia, analysis of the magnetic field changes generated by damaged or missing cords.…”

Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts

“…The non-destructive testing (NDT) of conveyor belts gives vast possibilities related to the optimization of conveyor belt maintenance costs, such as choosing the right moment for repair, replacement or recondition of the belt based on, among other factors, detected damage [1] or the rate of change of belt thickness [2]. Belt operating time depends on several factors that are presented in the literature [2]. Among other things, it is affected by the hardness, size and shape of transported materials, the specificity of transport point and the length and age of belt cord.…”