A Different Approach to Predicting the Impurity in the Product Stream of a Typical Chemical Refining Process – Using the Canvass AI No-Code Platform Built for Engineers.

The published paper proposes a statistical learning procedure that integrates process knowledge for the Dow data challenge problem presented in Braun et al. (2020). The task is to build an accurate inferential sensor model to predict the impurity in the product stream with apparent drifts. The proposed method consists of i) process data exploratory analysis, ii) a method for variable selection, iii) a method to deal with non-negative physical property modeling using a softplus function; and iv) a method for online bias updating based on known data. The study make use of process operation knowledge in all steps of data analytics, including exploratory analysis and feature selection. The report shows the detection of equipment-switching operations in the data and interpolations found in the impurity data. Partial least squares (PLS) and least angle regression solution (LARS) are adopted to model the data with strong collinearity. Pros and cons of LARS and PLS are given with practical implications.

We have taken a different approach to solving the same problem – using the Canvass AI no-code platform, it took a chemical engineer minutes to gain value and solve complex problems and predict impurity in the product stream.

Come see how the Canvass AI no-code platform, built for engineers such as yourselves, is used to solve challenging engineering problems such as this one!