A Bio-inspired Clustering Model for Anomaly Detection in the Mining Industry

Author(s)
Chiong, Raymond
Hu, Zhongyi
Fan, Zongwen
Lin, Yuqing
Chalup, Stefan
Desmet, Antoine
Publication Date
2019
Abstract
<p>Being able to detect anomalies for predicting machine breakdown is of critical importance in the mining industry. These anomalies are usually found in unlabelled sensor data, and therefore unsupervised models represent the preferred choice for the task. In this chapter, we propose the use of a bio-inspired clustering model based on the self-organizing map (SOM) to detect anomalies in real-world data provided by Joy Global, a manufacturer of high-productivity mining solutions. The proposed SOM is compared to two other well-known clustering models, namely <i>k</i>-means and fuzzy <i>c</i>-means. Simulation experiments using grease cycle data from the manufacturer show that the SOM is able to detect a more reasonable number of anomalies than <i>k</i>-means and fuzzy <i>c</i>-means. Based on real scenarios given by Joy Global, we devise a simple way to prevent machine failures by triggering alarms through the anomalies detected, and the SOM is again shown to be more capable of identifying incidents of potential machine breakdown compared to the other two clustering models.</p>
Citation
Bio-Inspired Computing Models and Algorithms, p. 133-155
ISBN
9789813143180
Link
Publisher
World Scientific Publishing Co Pte Ltd
Title
A Bio-inspired Clustering Model for Anomaly Detection in the Mining Industry
Type of document
Book Chapter
Entity Type
Publication

Files:

NameSizeformatDescriptionLink