Case-Based Reasoning Approaches for Gas Turbine Trip Diagnosis

2007 ◽  
Author(s):  
Catherine M. Graichen ◽  
William E. Cheetham
Keyword(s):  
Control System ◽  
Gas Turbines ◽  
Primary Sources ◽  
Initial Assessment ◽  
Case Based Reasoning ◽  
Additional Information ◽  
System A ◽  
And Control ◽  
Case Based

Effective maintenance, repair and design improvements of gas turbines require the classification of turbine automatic shutdown events into actionable categories. In particular, analysis is required at two distinct points in the life cycle of a shutdown event. The first evaluation is at the time of the shutdown when an initial assessment of the cause and the appropriate action must be decided as quickly as possible to return the turbine to service. At the time of the event, the primary sources of data are information collected from the sensors and control system. A second assessment is often performed as a post-event evaluation using additional information to validate the cause. General Electric created Case-Based Reasoning (CBR) tools to perform these classifications automatically. The first CBR tool, which works at the time of the event, was deployed in 2004. The second CBR tool was placed in operation in 2006.

Methodology of Automated Monitoring and Control of Pump Complex Operation Modes in Conditions of Cavitation Occurrence

2021 ◽  
Vol 22 (9) ◽  
pp. 468-474
Author(s):  
A. G. Lutov ◽  
M. B. Novozhenin
Keyword(s):  
Neural Network ◽  
Control System ◽  
Case Based Reasoning ◽  
Monitoring And Control ◽  
Modes Of Operation ◽  
Automated Monitoring ◽  
Operating Modes ◽  
Complex Operation ◽  
And Control ◽  
Case Based

The results of solving the problem of increasing the efficiency of an automated pumping complex for pumping liquids in conditions of non-stationary hydraulic processes, such as cavitation, are presented. The difficulty of determining the conditions for the occurrence of cavitation is associated with a large number of parameters, the mutual correlation of which is difficult to determine. It is shown that the methods used in practice in these conditions for monitoring and controlling pumping complexes based on centrifugal pumps and adjacent pipelines have significant disadvantages or solve the problem only partially. A mathematical model of the pump complex operation for operational control of the parameters of cavitation modes based on the similarity of the modes of operation of the centrifugal pump and the movement of the piston through the pipeline is presented, which simplifies the procedure for determining the presence of cavitation. A criterion for determining the efficiency of the pump complex operation mode is proposed based on an integral assessment of the difference between experimental and model data. A methodology for controlling the modes of operation of the pumping complex in the conditions of cavitation is formed. Due to the complexity of the direct calculation of the cavitation volume, a neural network model was proposed, trained based on experimental data. The structure, algorithms and software of the automated control and control system are developed using neural network models and a case-based approach to quickly determine the conditions for the occurrence of cavitation and correct the operating modes of the pumping complex. Decisions based on case — based reasoning are offered to the operator in the form of a "control effect-expected result" pair. The practical implementation of the automated system for monitoring and controlling the operating modes of the pumping complex is carried out in the AppDesigner package of the Matlab mathematical package. The use of the developed automated monitoring and control system provides an increase (restoration) of the pump complex performance in the conditions of cavitation, prevents the destruction of its elements, increases the service life, reduces operating costs and equipment repair costs.

scholarly journals VILNIUS ADVANCED-SURFACE MOVEMENT GUIDANCE AND CONTROL SYSTEM (A-SMGCS) SAFETY OBJECTIVES / VILNIAUS AERODROMO AUTOMATIZUOTOS ANTŽEMINIO EISMO STEBĖJIMO IR KONTROLĖS SISTEMOS SAUGOS TIKSLŲ ANALIZĖ

Aviation ◽  
2012 ◽  
Vol 16 (4) ◽  
pp. 130-135
Author(s):  
Vaidotas Kondroška ◽  
Jonas Stankūnas
Keyword(s):  
Control System ◽  
System Analysis ◽  
Flight Safety ◽  
Frequency Of Occurrence ◽  
Surface Movement ◽  
Safety Requirements ◽  
Methods Of Determination ◽  
Guidance And Control ◽  
System A ◽  
And Control

This work reviews the innovative and progressive methods of determination and analysis of safety objectives using Vilnius A-SMGCS example. The aim of the analysis is to determine how failures in this system could affect flight safety in Vilnius aerodrome. Identified safety objectives will limit the frequency of occurrence of hazards enough for the associated risk to be acceptable, and will ensure that appropriate mitigation means are reflected subsequently as Safety Requirements for the system. Analysis reflects aspects of A-SMGCS Safety objectives, which should be taken into consideration. Santrauka Darbe apžvelgiami progresyvūs saugos tikslų analizės metodai pagal Vilniaus aerodromo automatizuotos antžeminio eismo stebėjimo ir kontrolės sistemos veiklos pavyzdį. Analizuojama, kaip šios sistemos sutrikimai gali paveikti skrydžių saugą Vilniaus aerodrome. Remiantis galimų pavojų skrydžių saugai analize, tyrime nustatyti saugos tikslai, pagal kuriuos vėliau bus numatomos riziką mažinančios priemonės (galimų pavojų neutralizavimui ar kylančios rizikos sumažinimui iki priimtino lygio). Straipsnyje pateikiami veiksniai, kuriuos reikėtų įvertinti nustatant aerodromo automatizuotos antžeminio eismo stebėjimo ir kontrolės sistemos saugos tikslus.

scholarly journals Towards Transparent Human-in-the-Loop Classification of Fraudulent Web Shops

2020 ◽  
Author(s):  
Daphne Odekerken ◽  
Floris Bex
Keyword(s):  
Case Based Reasoning ◽  
Agent Architecture ◽  
Human In The Loop ◽  
Levels Of Detail ◽  
Legal Case ◽  
Dynamic Argumentation ◽  
Case Based

We propose an agent architecture for transparent human-in-the-loop classification. By combining dynamic argumentation with legal case-based reasoning, we create an agent that is able to explain its decisions at various levels of detail and adapts to new situations. It keeps the human analyst in the loop by presenting suggestions for corrections that may change the factors on which the current decision is based and by enabling the analyst to add new factors. We are currently implementing the agent for classification of fraudulent web shops at the Dutch Police.

scholarly journals Wear Debris Classification of Steel Production Equipment using Feature Fusion and Case-based Reasoning

2018 ◽  
Vol 58 (7) ◽  
pp. 1293-1299 ◽  
Author(s):  
Hongbing Wang ◽  
Rong Huang ◽  
Liyuan Gao ◽  
Weishen Wang ◽  
Anjun Xu ◽  
...  
Keyword(s):  
Wear Debris ◽  
Feature Fusion ◽  
Steel Production ◽  
Production Equipment ◽  
Case Based Reasoning ◽  
Case Based

Intelligent Classification of Palm Oil Tree Pollination Using E-Nose

Mekatronika ◽  
2020 ◽  
Vol 2 (1) ◽  
pp. 28-37
Author(s):  
Abdul Rahim Jalil ◽  
Muhammad Sharfi Najib ◽  
Suhaimi Mohd Daud ◽  
Mujahid Mohamad
Keyword(s):  
Palm Oil ◽  
Case Based Reasoning ◽  
Artificial Intelligent ◽  
Male And Female ◽  
Intelligent Technique ◽  
Insect Activity ◽  
Artificial Intelligent Technique ◽  
Case Based ◽  
Odour Profile

The pollination period is one of the crucial steps needed to ensure crop yield increases, especially in palm oil palm plantations. Most of the research has difficulty determining the pollination period of palm oil. Many problems contribute to this problem, such as difficut to reach and depedency of the polination insect as the insect activity is influenced by the surrounding enviroment.E-Nose can help determine the period by classifiy odour pattern of the male and female palm oil flower. The pattern of each of the flowers were classified using cased – based reasoning artificial intelligent technique. This paper shows the research of the palm oil pollination flower odour profile pattern using case-based reasoning (CBR) classifier.

Case-Based Reasoning and Some Typical Applications

2014 ◽  
pp. 229-267 ◽  
Author(s):  
Durga Prasad Roy ◽  
Baisakhi Chakraborty
Keyword(s):  
Problem Solving ◽  
Machine Intelligence ◽  
Case Based Reasoning ◽  
Engineering System ◽  
Yale University ◽  
Control Pattern ◽  
Clustering And Classification ◽  
How People Learn ◽  
Case Based

Case-Based Reasoning (CBR) arose out of research into cognitive science, most prominently that of Roger Schank and his students at Yale University, during the period 1977–1993. CBR may be defined as a model of reasoning that incorporates problem solving, understanding, and learning, and integrates all of them with memory processes. It focuses on the human problem solving approach such as how people learn new skills and generates solutions about new situations based on their past experience. Similar mechanisms to humans who intelligently adapt their experience for learning, CBR replicates the processes by considering experiences as a set of old cases and problems to be solved as new cases. To arrive at the conclusions, it uses four types of processes, which are retrieve, reuse, revise, and retain. These processes involve some basic tasks such as clustering and classification of cases, case selection and generation, case indexing and learning, measuring case similarity, case retrieval and inference, reasoning, rule adaptation, and mining to generate the solutions. This chapter provides the basic idea of case-based reasoning and a few typical applications. The chapter, which is unique in character, will be useful to researchers in computer science, electrical engineering, system science, and information technology. Researchers and practitioners in industry and R&D laboratories working in such fields as system design, control, pattern recognition, data mining, vision, and machine intelligence will benefit.

The Evolution of Marine Gas Turbine Controls

1990 ◽  
Vol 112 (2) ◽  
pp. 176-181 ◽  
Author(s):  
R. A. Sylvestre ◽  
R. J. Dupuis
Keyword(s):  
Control System ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Electronic Control ◽  
System Complexity ◽  
Control Module ◽  
Initial Application ◽  
Current State ◽  
Aircraft Fuel ◽  
And Control

The background and evolution of gas turbine fuel controls is examined in this paper from a Naval perspective. The initial application of aeroderivative gas turbines to Navy ships utilized the engine’s existing aircraft fuel controls, which were coupled to the ship’s hydropneumatic machinery control system. These engines were adapted to Naval requirements by including engine specific functions. The evolution of Naval gas turbine controllers first to analog electronic, and more recently, to distributed digital controls, has increased the system complexity and added a number of levels of machinery protection. The design of a specific electronic control module is used to illustrate the current state of the technology. The paper concludes with a discussion of the further need to address the issues of fuel handling, metering and control in Navy ships with particular emphasis on integration in the marine environment.

Sign in / Sign up

Export Citation Format

Share Document