DADICC : سیستم هوشمند برای تشخیص ناهنجاری در یک نیروگاه سیکل ترکیبی توربین گازی
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|5554||2008||11 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 5943 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 34, Issue 4, May 2008, Pages 2267–2277
DADICC is the abbreviated name for an intelligent system able to detect on-line and diagnose anomalies as soon as possible in the dynamic evolution of the behaviour of a power plant based on a combined cycle gas turbine. In order to reach this objective, a modelling process is required for the characterization of the normal performance when any symptom of a possible fault is present. This will be the reference for early detection of possible anomalies. If a deviation in respect to the normal behaviour predicted is observed, an analysis of its causes is performed in order to diagnose the potential problem, and, if possible, its prevention. A multi-agent system supports the different roles required in DADICC. The detection of anomalies is based on agents that use models elaborated using mainly neural networks techniques. The diagnosis of the anomalies is prepared by agents based on an expert-system structure. This paper describes the main characteristics of DADICC and its operation.
The Monitoring, Diagnosis and Simulation Center of Iberdrola S.A. (referred to as CMDS in Spanish) is in charge of supervising the 31 Combined Cycle Power Plants (CCPP) all around the world with a production of 67,000 GW h/year. The data acquisition systems of the CMDS are working in real-time with all combined cycle power plants, analyzing operational and maintenance data and suggesting recommendations about the improvement of the availability, reliability and efficiency of the plants. The mission of the CMDS is to identify asset performance degradations and malfunctions in the CCPPs by means of symptoms and indicators of initial stage problems and to provide timely solutions and recommendations regarding plant management, operations, and maintenance that will enable them to optimize their CCPP performance (Mendivil, Alvarez, Sandrea, & García, 2003). DADICC has been developed for the CMDS as a remote monitoring and diagnostic tool which allows to be kept under constant control the operating conditions of the CPPP. This monitoring and diagnosis system automatically detects incipient deviations of both performance and condition from normal operation at an early stage, thus enabling plant management to avoid and reduce performance losses and more serious damage to the assets. DADICC is a tool which was developed by IIT (Instituto de Investigación Tecnológica) in cooperation with IBERDROLA, a Spanish electrical company. The organization of this paper is as follows. Section 2 provides an overview of the main features and architecture of DADICC. Section 3 describes the scope of the system and its knowledge sources. Section 4 is dedicated to the strategy of anomaly detection and process of the normal behaviour modelling. Furthermore, Section 5 describes the multi-agent intelligent architecture of DADICC and in Section 6, the main characteristics of the basic types of agents in DADICC are explained. Finally, Section 7 presents an example of the DADICC operation.
نتیجه گیری انگلیسی
This paper has presented the DADICC system designed and implemented to detect on-line and diagnose anomalies as soon as possible in the dynamic evolution of the behaviour of a power plant based on a combined cycle gas turbine. The DADICC architecture is based on a multi-agent system in which the agents develop several roles for the acquisition of information and its processing in order to detect anomalies and diagnose their causes. The detection of anomalies is based on agents that use models that were previously elaborated using mainly neural networks techniques to characterize the typical normal behaviour in the different parts of the plant when no symptoms of anomalies are present. The diagnosis of the anomalies is prepared by agents based on an expert-system structure. DADICC is designed to extend its configuration to other components to be diagnosed in the future, and also, to include new power plants without any change in its architecture due to the flexibility of the multi-agent conception. Also, this argument allows DADICC the possibility to share its load and agents among different computers in a transparent way for the user. DADICC has been implemented in a CCGT plant owned by IBERDORLA and it has been in operation since July 2005. The performance of the system has been successful till now and future extensions to other CCGT plants and components are planned to be developed.