Academy News

In our recent series, we've thoroughly examined the First Principles Blending Model (FPBM) and AI/Machine Learning to evaluate whether these methodologies can achieve the most efficient and profitable blend. Each approach, as discussed in previous articles, has distinct strengths and weaknesses, excelling in particular aspects.

In this installment, we introduce a third strategy that seeks to synergize the best of both worlds. This method involves integrating the First Principles Model with AI/Machine Learning techniques. The precision in merging these complex components is critical to harness their full potential effectively.

We will guide you through the comprehensive blending process, from start to finish, identifying opportunities where the fusion of FPBM and AI/Machine Learning offers the most significant benefits. This exploration aims to provide a deeper understanding of how combined methodologies can enhance efficiency and profitability.

In the previous article, we delved into the Gold Standard First Principle Blending Model (FPBM), exploring its strengths and weaknesses alongside the reasons behind its frequent failures in refinery settings. Among the primary culprits were factors such as management's lack of interest in updating and sustaining the technology, disregarding tangible losses amounting to 25-40 million per year, and issues stemming from attrition, transfers, and inadequate training of operational staff and engineers.

The impact of these controllable factors is vividly illustrated in the chart below. Specifically, non-linear blend models and the absence or dysfunctionality of online analyzers emerge as critical areas that significantly affect the refinery's profitability. It's important to note that a substantial portion of the refinery's profit, ranging from 80-90%, is derived from the blended products manufactured in the offsite operations area. These factors underscore the pressing need for proactive measures to address these challenges and optimize operational efficiency in refinery processes.

First Principles Models aim to describe the behavior of a system from fundamental physical laws or principles, often using mathematical equations and computational methods. These models are advantageous when empirical data is limited, unreliable, or unavailable or when a deep understanding of the underlying physics of a system is necessary.

In our context, let us briefly discuss the First Principle Model for Fuel Blending or FPBM. This model governs how the fuel manufacturing process is modeled and manufactured. Simple as it sounds, it is not because it involves many processes and procedures, all linked and integrated, to get that gasoline in your car. A refinery’s fuel blending system involves eleven automation modules and sub-control systems.