Automatically optimize & control the energy consumed by electrolyzers at a chlorine plant based on their predicted health, the energy price variations in the R2 imbalance market & the production targets.
A predictive model for the health of the electrolyzers was developed & the energy consumption was optimized based on mathematical & data driven models. Further a mathematical optimization was performed in order to account for fluctuations in energy prices, customer orders & storage.
The chemical company wanted to optimize energy consumption at their electrolysis plant in Netherlands based on the predicted health of the electrolyzers, fluctuations in the R2 imbalance market energy prices while meeting the production targets. In addition to their primary need of meeting production targets, they also wanted to adjust their electricity consumption for short periods to benefit from the fluctuations in the R2 imbalance market. Finally, these algorithms had to be operational in real-time based on continuous monitoring of the plant behavior and the energy prices.
MultiViz was used by the experts to annotate data from the electrolyzers. The annotated data was used to build their predictive health models. Mathematical methods were developed & deployed for real-time prediction & optimization of the energy consumed. Control signals for energy consumption were sent back to the plant for controlling the electrolyzers & their energy consumption.
Through continuous optimization & predictive control, several hundreds of thousands of euros are saved.