Continued from page 21


In a blend, some ingredients usually have bigger impact on some properties and smaller impact on some other properties. In other words, the property blending matrix is usually sparse with a few blocks having the highest weight. For instance, while the base oil selection affects nearly all physicochemical properties of the blend, the pour-point depressant will mostly affect pour point and CCS properties.


it is essential that AI “learns” how variability in the raw material properties affects the final product and proposes a blend composition that meets the desired specifications.


The AI based Formulator Assistant, developed by SBDA in cooperation with BIZOL, relies upon Bayesian optimisation methods, which are especially well suited when working with discrete noisy data sets. Both formulation development and formulation price optimisation can be automated, taking into account available raw material inventories, shared use of certain raw materials across a number of finished products. There also are tools for price capping that allow blenders to counter risks associated with supply disruptions and price volatility.


Furthermore, since the properties of raw materials always show some variations (within the specifications), especially when sourced from different manufacturers, and experimental data always contain measurement errors, application of conventional gradient optimisation techniques is impossible without extensive data filtering and smoothing. Therefore,


22 LUBE MAGAZINE NO.168 APRIL 2022


BIZOL and SBDA are also collaborating with some leading researchers from the University of Sao Paulo, Brasil, and Universitat Politècnica de València, Spain, to extend the above approach to crankcase lubricant development [3-5]. The basic philosophy behind it is as follows: After completing the “virtual” formulation development, the candidate lubricant properties are fed into the engine tribology simulation block that allows predictions of advanced properties, such as performance in mandatory API and/or ACEA engine


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57