Thomas Y. C. Wei

An Innovative Fuzzy-Logic-Based Methodology for Trend Identification

A new fuzzy-logic-based methodology for on-line signal trend identification is introduced. The methodology may be used for detecting the onset of nuclear power plant (NPP) transients at the earliest possible time and could be of great benefit to diagnostic, maintenance, and performance-monitoring programs. Although signal trend identification is complicated by the presence of noise, fuzzy methods can help capture important features of on-line signals, integrate the information included in these features, and classify incoming NPP signals into increasing, decreasing, and steady-state trend categories. A computer program named PROTREN is developed and tested for the purpose of verifying this methodology using NPP and simulation data. The results indicate that the new fuzzy-logic-based methodology is capable of detecting transients accurately, it identifies trends reliably and does not misinterpret a steady-state signal as a transient one.

Prodiag : a process-independent transient diagnostic system - I : theoretical concepts.

A novel first-principles-based diagnostic system called PRODIAG is proposed for on-line detection and identification of faulty components during incipient off-normal process conditions. The concepts of qualitative physics reasoning and function-oriented diagnostics are employed in the design of PRODIAG and result in two unique capabilities not found in other plant-level diagnostic systems. First, PRODIAG is fully portable as it requires only modification of the input files containing the appropriate process schematics information to be able to diagnose single-component failure, in different processes/ plants. Second, PRODIAG detects unanticipated faults. Hence, it does not require the prespecification and formulation of rules to cover every conceivable fault scenario, and unlike traditional approaches, it is not likely to misdiagnose unforeseen events. PRODIAGs approach is to map process symptoms into component faults through a three-step mapping procedure with a knowledge base containing three distinct types of information: qualitative macroscopic balance equation rules, functional classification of process components, and the process piping and instrumentation diagram. The concepts introduced in the proposed diagnostic system are described, and an illustrative example shows how they are used in plant-level diagnostics.

An intelligent emissions controller for fuel lean gas reburn in coal-fired power plants.

ABSTRACT The application of artificial intelligence techniques for performance optimization of the fuel lean gas reburn (FLGR) system is investigated. A multilayer, feedforward artificial neural network is applied to model static nonlinear relationships between the distribution of injected natural gas into the upper region of the furnace of a coal-fired boiler and the corresponding oxides of nitrogen (NOx) emissions exiting the furnace. Based on this model, optimal distributions of injected gas are determined such that the largest NOx reduction is achieved for each value of total injected gas. This optimization is accomplished through the development of a new optimization method based on neural networks. This new optimal control algorithm, which can be used as an alternative generic tool for solving multidimensional nonlinear constrained optimization problems, is described and its results are successfully validated against an off-the-shelf tool for solving mathematical programming problems. Encouraging results obtained using plant data from one of Commonwealth Edisons coal-fired electric power plants demonstrate the feasibility of the overall approach. Preliminary results show that the use of this intelligent controller will also enable the determination of the most cost-effective operating conditions of the FLGR system by considering, along with the optimal distribution of the injected gas, the cost differential between natural gas and coal and the open-market price of NOx emission credits. Further study, however, is necessary, including the construction of a more comprehensive database, needed to develop high-fidelity process models and to add carbon monoxide (CO) emissions to the model of the gas reburn system.

Signal trend identification with fuzzy methods

A fuzzy logic-based methodology for online signal trend identification is introduced. Although signal trend identification is complicated by the presence of noise, fuzzy logic can help capture important features of online signals and classify incoming power plant signals into increasing, decreasing and steady-state trend categories. In order to verify the methodology, a code named PROTREN is developed and tested using plant data. The results indicate that the code is capable of detecting transients accurately, identifying trends reliably, and not misinterpreting a steady-state signal as a transient one.

PRODIAG: A Process-Independent Transient Diagnostic System - II: Validation Tests

The unique capabilities of the first-principles-based PRODIAG diagnostic system to identify unanticipated process component faults and to be ported across different processes/plants through modification of only input data files are demonstrated in two validation tests. The Braidwood Nuclear Power Plant full-scope operator training simulator is used to generate transient data for two plant systems used in the validation tests. The first test consists of a blind test performed with 39 simulated transients of 20 distinct types in the Braidwood chemical and volume control system. Of the 39 transients, 37 are correctly identified with varying precision within the first 40 s into the transient while the remaining two transients are not identified. The second validation test consists of a double-blind test performed with 14 simulated transients in the Braidwood component coolant water system. In addition to having no prior knowledge of the identity of the transients, in the double-blind test they also had no prior information regarding the identity of the component faults that the simulator was capable of modeling. All 14 transient events are correctly identified with varying precision within the first 30 s into the transient. The test results provide enough evidence to successfully confirm the unique capabilities ofmorexa0» the plant-level PRODIAG diagnostic system.«xa0less

On the verification and validation of geospatial image analysis algorithms

Verification and validation (V&V) of geospatial image analysis algorithms is a difficult task and is becoming increasingly important. While there are many types of image analysis algorithms, we focus on developing V&V methodologies for algorithms designed to provide textual descriptions of geospatial imagery. In this paper, we present a novel methodological basis for V&V that employs a domain-specific ontology, which provides a naming convention for a domain-bounded set of objects and a set of named relationships between these objects. We describe a validation process that proceeds through objectively comparing benchmark imagery, produced using the ontology, with algorithm results. As an example, we describe how the proposed V&V methodology would be applied to algorithms designed to provide textual descriptions of facilities.

Systematic Construction of Qualitative Physics-Based Rules for Process Diagnostics

A novel first-principles-based expert system is proposed for on-line detection and identification of faulty component candidates during incipient off-normal process operations. The system performs function-oriented diagnostics and can be reused for diagnosing single-component failures in different processes and different plants through the provision of the appropriate process schematics information. The function-oriented and process-independent diagnostic features of the proposed expert system are achieved by constructing a knowledge base containing three distinct types of information, qualitative balance equation rules, functional classification of process components, and the process piping and instrumentation diagram. The various types of qualitative balance equation rules for processes utilizing single-phase liquids are derived and their usage is illustrated through simulation results of a realistic process in a nuclear power plant.

Plant model of KIPT neutron source facility simulator

Argonne National Laboratory (ANL) of the United States and Kharkov Institute of Physics and Technology (KIPT) of Ukraine are collaborating on constructing a neutron source facility at KIPT, Kharkov Ukraine. The facility has 100-kW electron beam driving a subcritical assembly (SCA). The electron beam interacts with a natural uranium target or a tungsten target to generate neutrons, and deposits its power in the target zone. The total fission power generated in SCA is about 300 kW. Two primary cooling loops are designed to remove 100-kW and 300-kW from the target zone and the SCA, respectively. A secondary cooling system is coupled with the primary cooling system to dispose of the generated heat outside the facility buildings to the atmosphere. In addition, the electron accelerator has a low efficiency for generating the electron beam, which uses another secondary cooling loop to remove the generated heat from the accelerator primary cooling loop. One of the main functions the KIPT neutron source facility is to train young nuclear specialists, therefore ANL has developed the KIPT Neutron Source Facility Simulator for this function. In this simulator, a Plant Control System and a Plant Protection System were developed to perform proper control and to provide automatic protection against unsafe and improper operation of the facility during the steady-state and the transient states using a facility plant model. This report focuses on describing the physics of the plant model and provides several test cases to demonstrate its capabilities. The plant facility model uses the PYTHON script language. It is consistent with the computer language of the plant control system. It is easy to integrate with the simulator without an additional interface, and it is able to simulate the transients of the cooling systems with system control variables changing on real-time.

Diagnosis of Unanticipated Plant Component Faults in a Portable Expert System

We describe the first-principles-based PRODIAG expert system for on-line plant-level diagnosis of component faults in thermal-hydraulic processes. This diagnostic system combines the concepts of fundamental physical principles and function-oriented diagnosis in a qualitative reasoning framework and structures these concepts into three independent knowledge bases. PRODIAG has the unique ability to diagnose unanticipated (unforeseen) component faults and can be ported across different processes/plants through modifications of only input data files containing the appropriate process layout information. Simulation tests for two plant systems with transient data generated with the Braidwood Nuclear Power Plant full-scope training simulator confirm the unique capabilities of PRODIAG.