Hey,
I wanna predict the CO2 sparge that a system will require to control pH based in the historical data of the same process batches upon change of volume or reactor scale.
I have a chemical process where pH is controlled by CO2 sparge, which is sparged controlled by the system automatically to maintain pH at setpoint. I have the process data for different batches, several parameters together with this sparge, over different scales and replicates. Each batch is described by time (days) and specific volume progression.
I would like to develop a predictive model (based on experimental data of previous batches) that would allow me to predict the CO2 sparge that the system may require when tunning the volume and other parameters when designing the a future batch.
I wouldn't consider it an optimization because the process parameters of the new batch (volume...) are already selected and I need to know which could be the CO2 sparge required in this new setup to maintain the same pH setpoint. The new batch will run in the same scale as some of the available historical data, just the detail of volume progression, and others, is different. Other scales are also available.
I tried to use Fit Model platform, to get a predictive equation, but I am unsure that I build the right model or how to validate it. Finally, I tried to google for tutorials but couldn't find any example on a similar case as mine. I am a JMP 18 user.
Thank you in advance :)
