Case study

Oxbow runs petroleum coke calcining in closed loop

Oxbow runs its rotary kiln operations for petroleum coke calcining in closed loop with Imubit, raising yield and cutting natural gas use within specification.

Wireframe illustration of a rotary kiln for calcining petroleum coke, with its burner hood and cooler

About Oxbow

Oxbow is a global producer of calcined petroleum coke.

The challenge

Oxbow faced pressure to raise yield from its calcining operations while reducing energy consumption. In a rotary calcining kiln, yield and energy trade against each other, and both have to be balanced against strict product specifications while feed and operating conditions vary.

The solution

Imubit applied closed-loop control to Oxbow's rotary kiln operations. The controller anticipates volatility in the process and adapts the kiln's operation to it, so the kiln can run for higher yield and better energy efficiency while consistently meeting product specifications.

Imubit's closed-loop control is built on Deep Learning Process Control® (DLPC®). A model learned from the unit's own operating history, guided by first principles, predicts how the process will respond. A controller trained by reinforcement learning writes setpoints to the APC or DCS minute by minute, inside limits set by plant engineers.

Results

Oxbow's kiln operations run at higher yield and with lower natural gas consumption, while consistently meeting product specifications. Oxbow's SmartKiln® is decarbonizing through that yield improvement, producing more calcined coke from each tonne of green coke.

What it means for Oxbow's engineers

We have these younger, newer engineers that are coming in place of 30 year employees, who no longer have to wait 30 years to acquire that experience. With Imubit, they have an opportunity to come in and make their mark on the organization.

Kris Kissel-Weir, VP, Manufacturing Systems & Data Analytics, Oxbow

Calcining kilns share many control problems with cement kilns. See closed-loop control for cement and kiln process optimization.

Where to start

Find out what your gap to plan is costing you.

  • One to two hours for your team to prepare and upload the data package

  • Results within a few working days of approval

  • No workshops

Send your data as it is. Gaps, outages and noisy tags are normal, and our engineers screen and clean them in the platform. If anything limits a use case, we tell you.