Condition Monitoring using Convolutional Neural Network in Agricultural Machinery - Use Case: Disc Mower

Michael Jaumann, Ertug Olcay, Timo Oksanen

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations

Abstract

Recent advances in sensing technologies and increasing computation power have accelerated the development of condition monitoring systems based on different approaches. There has been intensive research to automate the detection of anomalies in machines and processes by monitoring the changes in collected sensor data. Especially, a disc mower is prone to damage if it is frequently deployed in places where it might hit solid objects such as boulders and old fence posts. These anomalies cannot be easily recognized by the operator and may cause suboptimal results. In this paper, two deep learning models for intelligent condition monitoring in a disc mower are investigated to notify the machine operator when a failure occurs. For this, a basic convolutional neural network (CNN) and a residual neural network (ResNet) were trained, evaluated and the preliminary results are presented.

Original languageEnglish
Pages (from-to)235-240
Number of pages6
JournalIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume55
Issue number32
DOIs
StatePublished - 2022
Externally publishedYes
Event7th IFAC Conference on Sensing, Control and Automation Technologies for Agriculture, AGRICONTROL 2022 - Munich, Germany
Duration: 14 Sep 202216 Sep 2022

Keywords

  • Condition monitoring
  • agricultural machinery
  • deep learning

Fingerprint

Dive into the research topics of 'Condition Monitoring using Convolutional Neural Network in Agricultural Machinery - Use Case: Disc Mower'. Together they form a unique fingerprint.

Cite this