Written by: STATISTICA News 2/10/2009 11:00 AM
Thomas Hill, Ph.D., VP Analytic Solutions for StatSoft Power Solutions, and Jay Lipscomb, Implementation Support Consultant at StatSoft Power Solutions presented two papers at the Energy and Environment Conference (EUEC 2009) in Phoenix.
The EUEC meeting is the premier conference focused on new technologies and approaches for achieving environmentally friendly and sustainable methods for energy production. Dr. Hill and Jay Lipscomb’s presentations focused on StatSoft Power Solutions’ recent successes in the industry, applying advanced analytic methods and optimization strategies, based on historic process data, to achieve significant reductions in NOx and CO emissions, and to sustain those reductions by implementing advanced process monitoring strategies.
Jay Lipscomb Implementation Support Consultant StatSoft Power Solutions
Thomas Hill, Ph.D VP Analytic Solutions StatSoft Power Solutions
Abstract Too much information, and too few insights: That is a typical opportunity facing engineers who manage highly automated and well instrumented processes. Over the past decade, a number of data acquisition, storage, and related technologies have become so inexpensive, that their implementation to support and monitor complex continuous processes (such as power generation or the effective operation of environmental control systems) is now common in virtually all process industries. While these technologies can provide a wealth of information describing a process, extracting useful insights from that information or leveraging that information to implement effective process monitoring and control systems often requires the application of lesser known multivariate data analysis and data mining techniques. The purpose of this presentation is to provide a brief summary and a high level overview of useful data analysis methods and techniques that can be applied to high-dimensional datasets and continuous multivariate data streams, to improve process quality and efficiency, to solve common problems in the power generation industry. Specifically, we will present brief overviews of multivariate control charting methods, as well as model based process monitoring techniques (and their implementation).
Abstract Data driven optimization strategies, based on historical performance data, (e.g., data mining) have been widely adopted in various industries (e.g. chemical manufacturing, mining, refining, pharmaceutical manufacturing, to name a few). These methods have become indispensable tools for cost-effective performance optimization with existing equipment, instrumentation, and machines. This presentation will illustrate the approach and specific methodologies in various case studies involving wall-fired and older cyclone furnaces to (1) lower emissions (NOx, CO) and (2) improve operations over a wide range of coal flows, loads, fuel qualities, etc., thus leading to less downtime (greater reliability of generation capacity), lower operational costs, and improved safety. These methods, which can be applied to any boiler technology and plants with various degrees of instrumentation, and typically without requiring modifications to the control system, will also be contrasted with traditional analytic approaches such as DOE (design of experiments), CFD (computational fluid dynamics), as well as neural-networks and neural-networks based closed loop control and "optimization": None of these methods can address complex systems with large numbers of parameters, are often costly to implement (e.g., closed loop control), and are not suitable to achieve robust optimization of multiple performance goals (low NOx, CO, LOI, SCR, SNCR, etc.) with existing instrumentation and control systems.
StatSoft Power Solutions, Inc. is a wholly owned subsidiary of StatSoft, Inc. and offers highly effective software solutions for the Power Generation Industry.