It is hard to imagine a more iconic image of industry than a distillation stack and the surrounding equipment. Petroleum products and the refineries that produce them have been a key driver of industrial development since the Second Industrial Revolution. Fundamental refinery products are feedstocks for polymer production, fuels that power energy production and transportation and important building blocks for medicines.
Digital technology and the internet have revolutionized the offices of every corporation, and the digitization of refinery control and command systems that occurred in the 1980s laid the groundwork for a similar revolution in industry. Refinery modeling creates digital models of a refinery. By simulating how a facility functions, refinery operators can review the conditions of an entire refinery at a glance. Today’s technology allows companies to use digital sensors and controls to develop incredibly accurate digital models of their assets and processes.
Refinery modeling is a type of process simulation. Producing a refinery model requires specialized process simulation software. In this software, refiners create a dynamic digital copy of the refinery. Process simulator software holds a numerical representation of the refinery; different settings may be adjusted within the software, then the simulation produces realistic reactions and results. In short, a properly constructed refinery model will behave the same as the refinery being modeled.
One important caveat is that the model must be created using accurate data. Programming the refinery model with parameters based on the refinery’s original engineering designs creates a gap between the model and the real world. To create a truly connected and accurate refinery model, this form of process simulation requires live sensor data. By incorporating the actual operating conditions, technicians and operators will have greater assurance that the model they have created is accurate.
Refineries have large physical footprints and are strategically located where pipelines meet the sea. In the past, a company with many geographically distant refineries would have required skilled technicians to work in all the regions where they operate.
The industrial internet of things has allowed technicians to monitor installations remotely. Refinery modeling means that one skilled operator can observe the digital versions of their functional areas without having to visit separate locations. The savings, both in travel time and in allowing highly skilled personnel to work more efficiently, makes refinery modelling a smart choice for petroleum processors.
Refinery modeling can also guide refinery optimization to maximize margins and reduce environmental impacts. Process adjustments can be tuned in the model, which means there is no need to risk production exploring different operating settings. Models let refiners explore a large number of different scenarios before bringing the changes to the real world, allowing for much wider experimentation. If the refinery is operating as a smart refinery, the model will be used by the optimization software.
Prior to the development of refinery modeling, engineers and operators were limited in the amount of changes they could realistically deploy. Refineries require significant capital expenditures – and experimentation can put those investments at risk. Therefore, any changes to the refining process had real-world financial consequences, leading to a conservative approach.
With accurate digital models, the difficulty comes from the sheer volume of choices. Any one human can never have enough time to explore every combination of adjustments to a refinery model, but an artificial intelligence program can try hundreds of combinations at once. The AI can be programmed with different goals to achieve as it tweaks the model. Refinery optimization goals might be to increase margins, increase reliability by reducing equipment failures, reduce energy usage or find a balance of all of these demands. Specialized AI for oil and gas algorithms can provide recommendations and demonstrate them in the model for human operators to appraise.
How is refinery modeling different from digital twin technology?
A refinery model may be created without being connected to the actual asset’s live data. For instance, when designing a new refinery, a computer model may be used that simulates the functions of the future installation. The model may also be disconnected from live sensor data when running analyses after equipment failure. The model will use the recorded sensor data from the period in question.
A digital twin is a live representation, connected through networked sensors that use the industrial internet of things to keep the digital twin up to date.
What does a company need to build a refinery model?
Refinery modeling requires specialized process simulation software, as well as a deep understanding of the refinery that is being modeled. If the model is to be used for refinery optimization, the software will also need commodity price information so that the cost of inputs can be taken into account during optimization.
The Digital Twin and the Smart Enterprise
Hybrid Modeling AI and Domain Expertise Combine to Optimize Assets