A new approach to process optimization
The Imubit Closed Loop Neural Network™ platform is an AI process optimization technology that enables plant managers to discover, engineer and monetize process optimization opportunities considered impossible until now. As the first technology of its kind in the industry, our proven solution allows refineries and petrochemical plants to interconnect their people and processes to optimize their most dynamic and profitable units and capture millions of dollars in annual margin.
The Imubit Closed Loop Neural Network™ platform is named “Best Modeling Technology” for 2023 by Hydrocarbon Processing
7 of the top 10 US refiners use Imubit AI process optimization technology to discover, capture, and sustain automation of plant economic operating strategies that were previously too complex to go after. Using their own plant’s data, Imubit customers model and discover their plant’s true process relationships and dynamics, drastically improving operations to maximize yields and minimize emissions.
We make more money on days we run Imubit than days we don’t. We now have 24×7 optimized units.”
– Short term planning engineer
An interconnecting neural network aligns all teams and stakeholders
lmubit is built for hydrocarbon processors who are looking for new ways to unlock margin from their assets. Unlike AI solutions that are bolted onto your existing methodologies, procedures and technologies, Imubit’s Closed Loop Neural Network™ crosses process unit and plant area boundaries. It flows through the traditional layers and interconnects all of the various teams. This allows everyone to speak the same language and drive towards a common economic goal. It manipulates carefully selected key variables by interconnecting real-time product prices with process constraints and economically critical properties. Instead of each team managing its own model in a discrete stack layer, all of the various disciplines interface with the Closed Loop Neural Network™.
Planning and economics feed direct real-time product and feedstock prices directly into the neural network. Process engineers input true unit operational constraints along with known process relationships. Process control engineers manage the interaction between the neural network and the existing advanced process control (APC) and distributed control system (DCS). Operators interact with the neural network on a 24/7 basis, constraining it to their desired bounds and limits in real time to allow for a safe and compliant closed-loop operation.
Hydrocarbon processing expertise
Deep reinforcement learning
Our interconnected AI solution is built on a deep reinforced learning architecture that uses your minute-by-minute data for real-time process optimization.