SECTOR FOCUS: AUTOMOTIVE PCEO
How AI tools can revolutionise the R&D process in the lube industry
Boris Zhmud, BIZOL Germany GmbH and Yan Chizhevskiy, SBDA Group Ltd
All of you have heard about artificial intelligence (AI), a new hot topic attracting enormous interest from industries and investors. In short, AI is the branch of computer science that deals with the development of adaptive algorithms that bring “intelligence” to machines, known as machine learning (ML).
During the recent years, AI has become a must in several industries: credit scoring in banks, personal targeting in media, predictive maintenance and in heavy industries. Indeed, all the operations mentioned are similar in three parameters: economic effect, frequency/regularity of the process, and available sources of data. First, application of ML algorithms usually allows optimisation of the process by a few percent. Therefore, the implementation of AI-empowered solutions bring significant economic effect. Secondly, the process to be optimised should be regular and owned by middle management, whose decisions will be more well-grounded due to AI assistance. This will ensure a sustainable economic effect. Finally, the sources of historical data should be available to in order to train an ML-model.
However, as Kate Crawford from Microsoft put it, “AI is neither artificial nor intelligent”, simply because all computing algorithms are created by people. Most AI-based computing platforms implement the so-called top-down approach where the human decision-making process to solve a specific task is copied. Major steps include gathering and homogenisation of data, feature extraction, model selection, training the selected model against the available test data, and application of the model. In other words, no eureka moments are to be
20 LUBE MAGAZINE NO.168 APRIL 2022
expected. A number of AI based platforms using open technological stack in Python, Spark and Java have been commercialised during the past decade. A good example is the
Q.LIFE®
Q.LIFE®
Engine used by Lubrizol. The
Engine platform features a set of corporate statistical models integrated into a worldwide accessible system that enables cost-effective formulation development and problem solving [1].
(Source: IT
Chronicles.com)
As possible applications of AI tools in the lubricant industry are concerned, add-pack development, project portfolio management and predictive maintenance with regard to oil condition monitoring should be mentioned. Optimising the cost of the product portfolio by just a few per cent for a large blender would definitely provide a good return on investment.
In the base oil and lubricant sector, blending is routinely used to convert a finite number of distillation cuts produced by a refinery into a large number of final products matching given specifications regarding viscosity, flash point, pour point or other properties of interest. To find the right component ratio for a blend, empirical or semi‐empirical equations linking blend characteristics to those of the individual components
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
