A machine learning based quality control system for power cable manufacturing

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

3 Citations (Scopus)
106 Downloads (Pure)


We study methods for observing physical defects on the surface of power cables. Quality control is essential for power cable manufacturing and surface defects are an important quality factor. Traditionally power cable manufacturing has relied on manual inspection as automated methods have not been sufficient to be used in industrial production. We have designed and implemented a novel defect detection system that applies machine learning methods to detect power cable surface defects. Our system uses laser scanning to map the surface of a cable during production. For the machine learning, we have evaluated different CNN (Convolutional Neural Net- work) architectures and studied their performance and accuracy. According to our results, CNNs are suitable for the detection of surface defects as they can be trained with large amounts of cable surface data.
Original languageEnglish
Title of host publicationProceedings - 2019 IEEE 17th International Conference on Industrial Informatics, INDIN 2019
Number of pages6
ISBN (Electronic)978-1-7281-2927-3
Publication statusPublished - 2019
MoE publication typeA4 Conference publication
EventIEEE International Conference on Industrial Informatics - Aalto University, Helsinki and Espoo, Finland
Duration: 22 Jul 201925 Jul 2019
Conference number: 17

Publication series

NameIEEE International Conference on Industrial Informatics
ISSN (Electronic)2378-363X


ConferenceIEEE International Conference on Industrial Informatics
Abbreviated titleINDIN
CityHelsinki and Espoo
Internet address


  • deep learning
  • convolutional neural networks, power cables, quality controlvolutional neural networks
  • power cables
  • quality control


Dive into the research topics of 'A machine learning based quality control system for power cable manufacturing'. Together they form a unique fingerprint.

Cite this