Maintenance intervention predictions using entity-embedding neural networks

Zaharah Allah Bukhsh,Irina Stipanovic,Aaqib Saeed,Andre G Doree

doi:10.1016/j.autcon.2020.103202

Zaharah Allah Bukhsh, Irina Stipanovic + Show 2 more

Open Access

https://doi.org/10.1016/j.autcon.2020.103202

Copy DOI

Abstract

Data-driven decision support can substantially aid in smart and efficient maintenance planning of road bridges. However, many infrastructure managers primary rely on information obtained during visual inspection to subjectively decide on the follow-up maintenance actions. The subjective approach is likely to lack the appropriate use of inspection data and does not promise cost-effective maintenance plans. In this paper, we show that the historical and operational data, readily available at the agencies, is of vital importance and can be used effectively for the recommendations of maintenance advises for bridges. This is achieved by developing a machine learning system that is trained on the past asset management data and provide support to the decision-makers in the condition assessment, risk analysis, and maintenance planning tasks. We have evaluated several traditional learning algorithms as well as the deep neural networks with entity embedding to find the optimal predictive models in terms of predictive capability. Additionally, we have explored the multi-task learning framework that has a shared representation of related prediction tasks to develop a powerful unified model. The analysis of results shows that a unified multi-task learning model performed best for the considered problems followed by task-specific neural networks with entity embedding and class weights. The results of models are further evaluated by instance-level explanations, which provide insights about essential features and explain the importance of data attributes for a particular task.

Highlights

Functional and serviceable transport infrastructure presents one of the essential predispositions for the economic growth of a country
Based on the Inspection to Maintenance Advice (IMA) decision procedure, we have developed several machine learning models that can predict condition states, possible risk levels, and recommend the most suitable maintenance actions
We explored various supervised algorithms from traditional machine learning to deep learning paradigm in order to find the optimal model for the prediction tasks

Summary

Introduction

Functional and serviceable transport infrastructure presents one of the essential predispositions for the economic growth of a country. Bridges represent a vital link in any roadway network They provide the crossings at critical locations, reduce the travel times, and maintain the traffic flow [1]. To handle the amount of information required to achieve these objectives, many infrastructure owners use the computerized management systems to manage and process relevant data and to support the decision-making processes [3]. Many BMS primarily rely on information obtained during the visual inspection process to decide on the follow-up maintenance actions [5]. These systems prompt inspectors to describe the physical state of the structure, which is quantified based on condition score card [6]. Since there is often no systematic procedure to record experts' preferences, their comprehension of structures, and related performance objectives, the maintenance decisions become difficult to follow, justify, and replicate in the future

Objectives

Results

Discussion

Conclusion