Solution

The plant used Aleph AI Co-Pilot platform to predict batch output quality and alert the users on potential deviations, including the diagnosis of the potential causes. The plant has also been relying on Aleph AI’s recommendation to ensure swift response against quality deviations.

Outcome

Aleph AI identified the initial causes as suboptimal operating conditions on impeller speeds of compactors and feed flow rates. Aleph AI Co-Pilot has since been generating recommendations to prevent quality deviation for the plant, enabling a 21% improvement on output quality.

Solution

Aleph AI Co-Pilot platform has been used to create digital twins of lab-scale equipment, allowing for detailed process analysis. Aleph AI was then deployed on the digital twins to conduct adaptive virtual experiments, which guided physical trial runs. Data from these trials enabled optimisation of the scale-up design, improving key metrics such as capacity, yield, and efficiency.

Outcome

With Aleph Digital Twins and AI, the company reduced the number of physical trials by up to 50%, accelerating the scale-up process from lab to commercial production by 20-30%. This approach provided optimised process designs in a fraction of the time, enabling faster, more efficient tech transfer.

Solution

The plant used Aleph AI Co-Pilot platform to monitor, predict, diagnose, and alert off-specs in the drying. Subsequently, Aleph Co-Pilot system has constantly been supporting the operators by recommending corrective actions in terms of feed rate, temperature, atomization, etc.

Outcome

The causes of the initial issue identified on inconsistent air temperature, air flow rates, and fluctuation in atomization. Aleph AI Co-Pilot has assisted the plant to constantly achieve the desired drying spec; thus, reducing the rework and off-spec rates by 30%.