Self-Organizing Sensing and Actuation for Advanced Process Control

As new power generation technologies and systems mature, the plant that encompasses these systems will become inherently complex. In order to manage complexity, the process control architecture that supports these systems will need to evolve to manage the complexity and achieve optimal performance. To meet this demand, we propose a novel process control architecture based on distributed intelligence and self-organizing methodologies that can distribute and utilize the intelligence in the sensing and actuation levels to manage complexity and solve real process control problems. We call this Self-Organizing Process Control Architecture that can enable distributed intelligence at all levels, and allow the sensing and actuation networks to function in a self-organizing manner. The overall objective of a multi-phase SBIR effort is to research, design, develop, test, evaluate, benchmark, and bring to production a novel advanced process control architecture that includes (1) Self-Organizing Sensing (SOS), and (2) Self-Organizing Actuation (SOA) methods, technologies, and commercial products. In Phase I, we will evaluate, simulate, and determine the feasibility of developing the novel control architecture by investigating 2 realistic sensing and actuation scenarios, where conventional sensors and actuators do not work. The tasks include: (1) Complete the design of the Self-Organizing Process Control Architecture; (2) Develop the concept and features of Self- Organizing Sensing (SOS) technology; (3) Develop an Artificial Neural Network (ANN) based SOS algorithm; (4) Implement the SOS algorithm in LabVIEW software; (5) Test and demonstrate the performance of a novel SOS Bed Thickness Sensor; (6) Develop the concept and features of Self-Organizing Actuation (SOA) technology; (7) Develop an SOA algorithm for controlling disruptive gas flows; (8) Implement the SOA algorithm in LabVIEW software; (9) Develop a real-time simulation model for a gas flow process that has 2 valves in sequence with significant upstream and downstream pressure variations; and (10) Test and demonstrate the performance of the SOA Gas Flow Actuator using the gas flow process model. In Phase II, appropriate software and hardware products will be developed to demonstrate the solution. CyboSoft has achieved good results for advanced boiler control and actuation control in 2 DOE SBIR grant projects. This proposed project can take advantage of the results obtained. For instance, the CFB boiler process model we developed in the boiler control project can be used for testing the novel Self-Organizing Sensor. CyboSoft has the experience and expertise to solve tough industry-wide problems, and develop successful commercial products. We believe the novel Self-Organizing Sensing and Self-Organizing Actuation technologies and products can be strategically important to the energy industry as well as process industries at large.