Over the past year there has been a lot of activity in the area of on-line equipment monitoring, diagnostics, and prognostics and this trend is expected to continue.  On-line diagnostic and prognostic information regarding equipment/asset health is extremely valuable for scheduling and carrying out maintenance and preventing unplanned down-time.  The net effect is an overall increase in the efficiency, safety, and profitability of power industry processes.  There are different techniques and approaches for deducing and acquiring this information including but not limited to: empirical modeling techniques, statistical modeling, physical or first principles modeling, and the application of additional sensors, including wireless sensors.  This session focuses on new ideas and applications in the area of monitoring, diagnostics and prognostics, as well as the application of these techniques in the power industry.

 

 

P009-“Early Discovery of Failing Equipment and Sensors in Power Plants using Advanced Pattern Recognition”

Elmer Hansen, Performance Consulting Services

 

This study describes the application of advance Pattern Recognition on-line Monitoring in a power plant fleet environment.  Advanced Pattern Recognition has failures not typically detected by traditional control systems. Typical failure identification and alarming is carried out applying high and low limits to the range of a single instrument measurement. This results in a rather wide fixed window of operation.  Advanced Pattern Recognition technology has been employed to monitor multiple sensor systems using a moving window to identify normal and abnormal operation.  Using a moving window takes into account the current operating conditions of the equipment and allows the early detection of many types of failures.  The moving window is defined by a pattern recognition generated expected value and the threshold of normal range about the expected value.  The abnormalities can then compare to typical failure signatures to suggest the failure origin.  The expected value can also be used to validate the signal and provide a replacement signal value.  Practical applications of advanced pattern recognition to detect plant equipment and sensor failures will be described.  The variety of incipient equipment failures, which have been identified in real plant environments will be categorized. Several failures will be profiled.  These will also be illustrated by case studies. Advanced pattern recognition has been       used successfully in power plant environments to provide the early detection of equipment and sensor failures.

 

 

P016-“Sensor Fault Detectability Measures for Autoassociative Empirical Models

Wes Hines, University of Tennessee

 

Traditionally, the calibration of safety critical nuclear instrumentation has been performed during each refueling cycle.  However, many nuclear plants have moved toward condition-directed rather than time-directed calibration.  This condition-directed calibration is accomplished through the use of on-line monitoring. On-line monitoring (OLM) commonly uses an autoassociative empirical modeling architecture to assess instrument channel performance.  An autoassociative architecture predicts a group of correct sensor values when supplied a group of sensor values that is usually corrupted with process and instrument noise, and could also contain faults such as sensor drift or complete failure.  This paper describes one such autoassociative model architecture, specifically autoassociative kernel regression (AAKR), and presents five metrics that may be used to evaluate performance.  These metrics include the previously developed accuracy, auto-sensitivity, cross-sensitivity, metrics along with a description of two new fault detectability performance metrics for application to instrument calibration verification (ICV) and anomaly detection.  These parameters are calculated for an AAKR model of an operating nuclear power plant steam system and were used to describe the effects of model architecture on performance.  It is shown that the ability of an empirical model to detect sensor faults in ICV systems is largely dependent on the model uncertainty and to a lesser degree its robustness.  It is also shown that the ability of an empirical model to detect anomalies via the Sequential Probability Ratio Test (SPRT) is also related to uncertainty and the SPRT detectability is on the order of 32% smaller than the ICV detectability.  These guidelines provide a framework for developing various models, in that models intended to be applied to ICV and anomaly detection tasks should focus on the minimization of uncertainty.  Furthermore, the ICV and anomaly detection performance metrics are shown to be within the traditional ±1% calibration tolerance and their performance under artificially faulted conditions are shown to be in direct agreement with their theoretical foundations.

 

 

P017-“Low Cost Wireless Condition Monitoring

Lloyd Pentecost, Southern California Edison Company

 

At the San Onofre Nuclear Generating Station, we have implemented two different wireless condition monitoring systems. The first is a WiFi (802.11b) system that allows for easily and quickly establishing a new monitoring system based on emergent plant needs. The second is based on a Zigbee (802.15.4) like system that allows for very low cost condition monitoring for low data rate applications.  For low data rate applications, Zigbee and Zigbee-like systems have the potential to reduce the cost of data collection by a factor of 10 or better.  This reduction in cost will change the cost/benefit ratio and dramatically expand the number of data points available for collection. The purpose of this presentation is to describe some early applications of both WiFi and Zigbee-like systems,         success stories, cost benefits and potential future applications.

 

 

P049-“Performance Improvement for Cooling Water Systems; Corrosion – The New Process Variable”

Dawn C Eden, David A Eden & Russell D Kane, Honeywell International, Inc.

 

Availability of the cooling water system is critical to the operation of power plant.  Under inadequate control, the cooling water system can present significant difficulty to the plant in loss of production capacity, increased cost of cleaning and protective chemicals, increased energy and maintenance costs, and a reduction in service life.  Although regular checks are made to determine water quality and compliance with prescribed operating conditions, these checks can be infrequent enough to allow corrosion, fouling and scaling to get out of control.  This inevitably leads to outages that can be costly and severely affect production.  Technology exists that enables a continuous, rapid update of the key general and localized (pitting) corrosion, scaling and fouling information that can assist the plant operator in real-time to ensure cooling water system availability.

 

This paper reviews a field proven on-line, real-time process control technology with a heat transfer efficiency and corrosion measurement to provide a comprehensive understanding of unit operating condition and fouling/scaling activity in cooling water and heat exchange equipment.  Data from field-installed systems are presented, with reference to heat exchange operations in a petrochemical plant and a nuclear power plant.  Recent advances in the technology and its implementation are also discussed, specifically with regard to wireless communications and direct-to-DCS capability.

 

 

P042-“Integrated Wireless Systems for Power Applications”

Peter Fuhr, RAE Systems

 

As wireless devices become more prevalent in the power industries, the need for a managed solution increases. Viewed another way, wireless sensor networks, RFID asset tracking systems, voice over wireless IP systems, WiFi, WiMAX, (etc) all use the limited frequency space and without some coherent strategy for coexistence, systems failures will undoubtedly occur.  A strategy for deployment of integrated wireless systems in industrial settings is identified and example case studies are presented.

 

 

P053-“Finally, Enterprise Management for the Generating Plant”

Dr. Eyal Brill and James Hawkins, P.E.

 

The speed at which state-of-the-art advances in automation and control are applied within the utility industries core business is as fast as waiting for maple sap to drip from a tree in January. Advances in IT have become commonplace in process and manufacturing industries and the yield in efficiency and reliability has been striking.  Utilities are spending millions on enterprise software to integrate and streamline the activities on the business side of their organizations, however, the industry has been slow to integrate and adopt recent advances in IT that can squeeze efficiency, reliability and substantial operating savings from its core business. A new, proven advanced statistically driven enterprise approach, that pushes the envelop for reliability and optimization of the operating side of a utility’s core business is discussed. This new technology has many advances over current solutions including:

·         On-line adaptation of multivariate models based on real-time data. This requires the ability to differentiate between "abnormal" situations and "normal" drift of the process.

·         Ability to combine human expert knowledge with statistical models.

·         Open architecture that enables users, using Microsoft standards, to encapsulate proprietary modeling techniques into the enterprise FDC platform.

·         Pattern recognition for long term phenomenon

This paper will demonstrate the technology principles with actual examples from applications in the field.

 

P056-“On Analysis of Control-Communication Integration in Distributed Power Grid’s Electric, Information & Physical Domains”

Teja Kuruganti, Mallikarjun Shankar, Glenn Allgood, Oak Ridge National Laboratory Seddik Djouadi, University of Tennessee, Knoxville

 

The electric grid is infact two different infrastructures, power grid and the communication grid. As the grid evolves into a network of highly distributed generation, transmission and loads, a more complex communication network follows it. This paper analyzes the dependency of the controls on communication networks and establishes a roadmap for controls and communications in power systems.