Digital time series manager for predictive maintenance
Time series manager
parsQube has developed a digital time-series manager for predictive maintenance management that can be used across a range of industries.
- 2022–2023Project duration: 01.01.2022 to 31.12.2023
- 24 monthsProject period
- BSFZ 2023Seal for in-house research and development
What was the goal of the project?
The goal of the project was the development of a digital time series manager for predictive maintenance management, especially for industries such as the chemical sector. The focus was on creating standard software capable of handling the high complexity of different sensors and highly fluctuating parameters. This was intended to enable predictive maintenance management for areas where no standardized solutions previously existed.
What were the three biggest risks?
-
There was a risk that the operational and analysis parameters could not be interpreted as intended, because there might be no clear distinction between normal operation and malfunction/maintenance cases, or the data might not be sufficiently specific.
-
It was uncertain whether the collected data would have sufficient statistical relevance to develop reliable models.
-
The complexity of the data and processes could result in the developed models not being transferable to larger or different plants.
What was the result of the project?
The project led to the development of a digital time series manager that differs from previous solutions by enabling predictive maintenance management even for complex industries, such as chemical plants or laboratories. The functionality of the developed models was verified and adjusted through field studies on real plants.