(314e) Analytics Framework and Infrastructure - Integrating Big-Data Cloud Technologies with First-Principle Modeling

Samudra, A. P. - Presenter, Rockwell Automation
Smith, A. B., University of Illinois
Sayyar-Rodsari, B., Rockwell Automation
In many industries sources of data are geographically distributed. Oil well pumps, electric motor drives, and heavy construction equipment are examples of such sources. These units require advanced and robust analytics capabilities to maximize their efficient utilization and minimize costs associated with unplanned downtime and uncertainty. While embedded control solutions manage the safe operation of the asset, analytics technologies can perform fault-diagnostics, operational predictions, and performance modeling for a battery of assets.

This paper presents the analytics framework and infrastructure built to integrate big-data cloud technologies with traditional process system engineering tools such as first-principle modeling, deterministic optimization techniques for scheduling, and process control. The engines include

  • Proprietary model identification system which identifies the basic first-principles behaviors such as mass and energy balances, along with time-depended performance metrics such as fouling and physical performance degradation
  • Scheduling platform developed for production scheduling of continuous processes with special emphasis on utility systems along with interactive interfaces for visual construction of optimization problems

We also present the deployment strategies for such engines which range from in-chassis deployment tightly coupled with the controller to deployment as cloud services for extreme scalability. The use of cloud facilities such as high throughput, multi-source data ingestion, stream processing of data, and elastic web applications is demonstrated through case-studies.