Project Description
ProSensus has the expertise to build global multi-block models that represent your entire process from start to end.
This approach allows you to build a predictive model relating raw material selection, blending ratios, analytical test results (CFC, GPC, DSC, etc.) and operating conditions to product quality in a single model.
Project Details
Polyolefin Multi-Block Modeling
Such a model has many applications for polyolefin manufacturers aiming to develop new and improved products. ProSensus has recently worked with a leading resin manufacturer to develop these global models and tackle some common manufacturing challenges including:
1. Reliable predictions of key quality attributes
Making reliable predictions of key quality variables such as Secant modulus, Elongation, Dart, Tear, etc. Upon validation, the multi-block PLS model can be used backwards for optimization.
Each graph above plots one specific product quality parameter. The “observed” value corresponds to the actual (measured) value of that product quality parameter, while “predicted” indicates the value obtained from the MVA model. A perfect model would result in an R2 = 1.0, RMSEE = 0.0, and all data points lying directly on the identity line (y=x).
2. Assessment of existing tests/measurements
This study is useful for highlighting which data block is most correlated with the final product quality of interest. It is also used to direct the manufacturers to where they should focus their development efforts. ProSensus can also evaluate where there may be redundant testing being performed on the resins.
The coefficients plot above indicates which X-variables have the most overall impact on the Y-variable (product quality) where each bar represents one particular X-variable. The X-variables are colour-coded according to the four defined blocks of data. Note that “Global RX” represents the calculated mixture resin properties based on the resins used and their blending ratios.
One takeaway from this plot can be a re-assessment of the existing analytical tests. Some of the purple bars are important to predict this key quality while others are not that significant. This suggests that some tests could be eliminated saving the manufacturer their associated cost and measurement time.
3. Product variability deep dive
Pointing out any equipment/line/instrument differences that might lead to product variability. This is relevant to the process improvement team since it directs their troubleshooting effort to the process unit leading to inconsistent quality.
In the score plot above, clustering of the data points forms a clear distinction between each of the three reactors used at this plant. In the observed vs predicted plot of a critical quality attribute, it becomes obvious that the product quality obtained from each reactor is significantly different.
4. Product development guidance
Guiding the product development team to an efficient design space for future runs depending on the desired properties of the final product. This is only achievable once the key correlations and trade-offs have been highlighted in the model building step.
4. Customer focused optimization
Once a PLS model has been built, constrained optimization enables the user to optimize the selection of resins, blending ratios, and operating conditions required to formulate targeted products for specific customer needs.
Finally, ProSensus can narrow down the analysis to one or two process units for any focused study of interest. Contact us to learn more about how we can help you predict quality, reduce product variability, and formulate new products.
