سیستم استدلال آنلاین مبتنی بر مورد برای بهینه سازی احتراق ترکیب زغال سنگ نیروگاه حرارتی
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|53780||2014||13 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 9182 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : International Journal of Electrical Power & Energy Systems, Volume 62, November 2014, Pages 299–311
Coal blending is becoming increasingly common as more and more off-specification coals are received in coal-fired power plants, given the present coal market in China. This situation requires optimization of the operating parameters for matching the varying coal properties. The motivation for such optimization includes confirming good performance of the units regarding the security, the economy and environmental protection. However, the current adjustments to operation of the plant rely mostly on human experience because of the imperfections of existing theoretical models for coal-blend combustion. In this paper, a Case-Based Reasoning (CBR) method providing online decision-making for optimization of coal-blend combustion was investigated using cases representing successful operation of the unit for specific coal blends and loads. A case base containing a wealth of knowledge about optimal operation modes was constructed from a large number of cases. The development process for the CBR system includes case design, case evaluation, case generation, case retrieval and case reasoning. Case evaluation focused mainly on heating surface security, output capability, slagging tendency, comprehensive fuel consumption and pollutant emissions. Five indexes were introduced to quantify the above characteristics based on actual combustion parameters. A case-generating algorithm employing an evolutionary strategy was proposed in which the case base evolves while retaining new cases. Two methods for measuring case similarity – termed entirely similarity and eigenvalue similarity – were used for case retrieval. Run-time optimization strategies were recommended by the case-reasoning model based on the current operating status. The CBR system using Browser/Server framework were successfully applied to a 600-MW power plant, which provided an opportunity for coal-blend combustion optimization.