Automated Step Testing & Model Identification
Whether implementing a new Model Predictive Control (MPC) project
or maintaining an existing Advanced Process Control (APC) application,
model identification is the most difficult, time consuming, and
labor-intensive part of the process.
A traditional plant test can take weeks of around-the-clock work to
complete since the test is conducted manually, one variable at a time.
For years, industry has been searching for a method to deploy APC
faster with lower costs and less support, while maintaining safe and
effective plant operation.
Using industry-leading TaiJi identification technology, Control
Performance Monitor automatically step tests multiple variables
simultaneously, which affords a more concise model identification data
set. The result is reduced test times, analysis, model identification,
and ultimately lower costs for implementing and maintaining MPC
- Determine expected gains vs. benchmarked performance
- Create a functional design and configure the plant test, including MVs, DVs, and CVs
- Execute multivariate step-testing in closed-loop operations
- Automatically initiate model identification and validation
- Continually improve the implemented model
- Lower impact on the unit and product quality through non-disruptive testing
- Verify MCP performance against the initial benchmarked values
- Require less operator intervention than traditional testing to maintain signal-to-noise ratios while still maintaining CVs within operating constraints