Predictive maintenance on event logs: Application on an ATM fleet
- URL: http://arxiv.org/abs/2011.10996v4
- Date: Mon, 22 Nov 2021 07:56:06 GMT
- Title: Predictive maintenance on event logs: Application on an ATM fleet
- Authors: Antoine Guillaume, Christel Vrain, Elloumi Wael
- Abstract summary: In some applications, outputs from sensors are not available, and event logs generated by the machine are used instead.
We first study the approaches used in the literature to solve predictive maintenance problems and present a new public dataset containing the event logs from 156 machines.
- Score: 0.6961253535504979
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Predictive maintenance is used in industrial applications to increase machine
availability and optimize cost related to unplanned maintenance. In most cases,
predictive maintenance applications use output from sensors, recording physical
phenomenons such as temperature or vibration which can be directly linked to
the degradation process of the machine. However, in some applications, outputs
from sensors are not available, and event logs generated by the machine are
used instead. We first study the approaches used in the literature to solve
predictive maintenance problems and present a new public dataset containing the
event logs from 156 machines. After this, we define an evaluation framework for
predictive maintenance systems, which takes into account business constraints,
and conduct experiments to explore suitable solutions, which can serve as
guidelines for future works using this new dataset.
Related papers
- TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled
Prescriptive Maintenance Framework [62.73424880653293]
Industrial systems demand reliable predictive maintenance strategies to enhance operational efficiency and reduce downtime.
This paper introduces an integrated framework that leverages the capabilities of the Transformer model-based neural networks and deep reinforcement learning (DRL) algorithms to optimize system maintenance actions.
arXiv Detail & Related papers (2023-09-29T02:27:54Z) - Optimization paper production through digitalization by developing an
assistance system for machine operators including quality forecast: a concept [50.591267188664666]
The production of paper from waste paper is still a highly resource intensive task, especially in terms of energy consumption.
We have identified a lack of utilization of it and implement a concept using an operator assistance system and state-of-the-art machine learning techniques.
Our main objective is to provide situation-specific knowledge to machine operators utilizing available data.
arXiv Detail & Related papers (2022-06-23T09:54:35Z) - Prescriptive maintenance with causal machine learning [4.169130102668252]
We learn the effect of maintenance conditional on a machine's characteristics from observational data on similar machines.
We validate our proposed approach using real-life data on more than 4,000 maintenance contracts from an industrial partner.
arXiv Detail & Related papers (2022-06-03T13:35:57Z) - Predictive Maintenance using Machine Learning [0.0]
Predictive maintenance (PdM) is implemented to effectively manage maintenance plans of the assets.
Data is collected over a certain period of time to monitor the state of equipment.
arXiv Detail & Related papers (2022-05-19T09:05:37Z) - Artificial Intelligence based tool wear and defect prediction for
special purpose milling machinery using low-cost acceleration sensor
retrofits [0.0]
This paper demonstrates the application of an acceleration sensor to allow for convenient condition monitoring of such a special purpose machine.
We examine a variety of conditions including blade wear and blade breakage as well as improper machine mounting or insufficient transmission belt tension.
arXiv Detail & Related papers (2022-02-07T11:02:48Z) - LogLAB: Attention-Based Labeling of Log Data Anomalies via Weak
Supervision [63.08516384181491]
We present LogLAB, a novel modeling approach for automated labeling of log messages without requiring manual work by experts.
Our method relies on estimated failure time windows provided by monitoring systems to produce precise labeled datasets in retrospect.
Our evaluation shows that LogLAB consistently outperforms nine benchmark approaches across three different datasets and maintains an F1-score of more than 0.98 even at large failure time windows.
arXiv Detail & Related papers (2021-11-02T15:16:08Z) - Robust and Transferable Anomaly Detection in Log Data using Pre-Trained
Language Models [59.04636530383049]
Anomalies or failures in large computer systems, such as the cloud, have an impact on a large number of users.
We propose a framework for anomaly detection in log data, as a major troubleshooting source of system information.
arXiv Detail & Related papers (2021-02-23T09:17:05Z) - Bandit Data-Driven Optimization [62.01362535014316]
There are four major pain points that a machine learning pipeline must overcome in order to be useful in settings.
We introduce bandit data-driven optimization, the first iterative prediction-prescription framework to address these pain points.
We propose PROOF, a novel algorithm for this framework and formally prove that it has no-regret.
arXiv Detail & Related papers (2020-08-26T17:50:49Z) - Predictive Maintenance for Edge-Based Sensor Networks: A Deep
Reinforcement Learning Approach [68.40429597811071]
The risk of unplanned equipment downtime can be minimized through Predictive Maintenance of revenue generating assets.
A model-free Deep Reinforcement Learning algorithm is proposed for predictive equipment maintenance from an equipment-based sensor network context.
Unlike traditional black-box regression models, the proposed algorithm self-learns an optimal maintenance policy and provides actionable recommendation for each equipment.
arXiv Detail & Related papers (2020-07-07T10:00:32Z) - A general anomaly detection framework for fleet-based condition
monitoring of machines [16.51849885526826]
Machine failures decrease up-time and can lead to extra repair costs or even to human casualties and environmental pollution.
Recent condition monitoring techniques use artificial intelligence in an effort to avoid time-consuming manual analysis and handcrafted feature extraction.
This work proposes an unsupervised, generic, anomaly detection framework for fleet-based condition monitoring.
arXiv Detail & Related papers (2019-12-30T14:35:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.