Similarity Search of Time Series Data: Evaluation of Search Engine in Industrial Process Data(SIFT)
| Reference number | |
| Coordinator | RISE Research Institutes of Sweden AB - RISE |
| Funding from Vinnova | SEK 3 701 322 |
| Project duration | November 2024 - September 2026 |
| Status | Completed |
| Venture | Advanced digitalization - Enabling technologies |
| Call | Test and demo of advanced digitization in a real environment |
Important results from the project
The SIFT application was developed and demonstrated at Nexans and Nord-Lock, from TRL 3 to 6. It makes itpossible to compare historical production runs and identify deviations and possible relationships. Technical and organizational evaluation showed the value of combining time series data with metadata. Shared data have shown to supports cross-functional, fact-based improvement work. The project also contributed to competence development, two licentiate theses and the follow-up project STIG.
Expected long term effects
SIFT is expected to contribute to better utilization of production data, faster troubleshooting, and more data-driven and proactive ways of working. A shared fact base strengthen collaboration between production, quality, and maintenance, supporting more efficient maintenance and maintenance planning. Production data can also serve as an organizational memory, supporting knowledge transfer and training. In the longer term, contributing to increased productivity, quality, and resource efficiency.
Approach and implementation
The project was carried out by RISE, Chalmers, Nexans, Nord-Lock, and IFM through technical development, industrial testing, and organizational evaluation. The demonstrator was iteratively developed at Nexans and Nord-Lock through testing, workshops, and interviews. The interviews mapped information needs, ways of working, and existing systems. The project generated knowledge about how advanced data-driven solutions should be implemented in industrial environments.