A Hierarchical Approach to Improve the Interpretability of Causality Maps for Plant-Wide Fault Identification

Natali Van Zijl,Lidia Auret,Steven Martin Bradshaw,Tobias Muller Louw

doi:10.3390/min11080823

Abstract

Modern mineral processing plants utilise fault detection and diagnosis to minimise time spent under faulty conditions. However, a fault originating in one plant section (PS) can propagate throughout the entire plant, obscuring its root cause. Causality analysis identifies the cause–effect relationships between process variables and presents them in a causality map to inform root cause identification. This paper presents a novel hierarchical approach for plant-wide causality analysis that decreases the number of nodes in a causality map, improving interpretability and enabling causality analysis as a tool for plant-wide fault diagnosis. Two causality maps are constructed in subsequent stages: first, a dimensionally reduced, plant-wide causality map used to localise the fault to a PS; second, a causality map of the identified PS used to identify the root cause. The hierarchical approach accurately identified the true root cause in a well-understood case study; its plant-wide map consisted of only three nodes compared to 15 nodes in the standard causality map and its transitive reduction. The plant-wide map required less fault-state data, time series in the order of hours or days instead of weeks or months, further motivating its application in rapid root cause analysis.

Highlights

Worldwide competition forces modern mineral processing plants to operate at high productivity
While the case study isdescription intentionallyofdesigned challengethe causality analysis algorithms, the conceptual simplicity the system ensures that thethe ground truth is apidentified using causality analysis, and theofresults from applying hierarchical easilytodetermined by humans, enabling a critical evaluation the proposed
The novel hierarchical approach presented in this work is the required step in literature to prepare causality analysis for application in the mineral processing industry

Summary

Introduction

Worldwide competition forces modern mineral processing plants to operate at high productivity. The major challenge in fault identification is the smearing effect, where a fault originates in one area of a plant and propagates throughout the plant, so that numerous variables show an effect of the fault and so obscure the origin of the fault [6]. This is a challenge in contribution plots, the most commonly used fault identification technique, where the root cause variable is identified as a variable with a large contribution to the calculated statistic such as the Q-statistic or D-statistic [7,8]. Since numerous variables are showing an effect of the fault, numerous variables have large contributions to the calculated statistic and any of them could be incorrectly identified as the root cause

Methods

Results

Conclusion