A hybrid deep neural network based prediction of 300 MW coal-fired boiler combustion operation condition
نویسندگان
چکیده
In power generation industries, boilers are required to be operated under a range of different conditions accommodate demands for fuel randomness and energy fluctuation. Reliable prediction the combustion operation condition is crucial an in-depth understanding boiler performance maintaining high efficiency. However, it difficult establish accurate model based on traditional data-driven methods, which requires prior expert knowledge large number labeled data. To overcome these limitations, novel method flame imaging hybrid deep neural network proposed. The proposed combination convolutional sparse autoencoder (CSAE) least support vector machine (LSSVM), i.e., CSAE-LSSVM, where with architectures utilized extract essential features image, then input into prediction. A comprehensive investigation optimal hyper-parameter dropout technique carried out improve CSAE-LSSVM. effectiveness evaluated by 300 MW tangential coal-fired images. accuracy reaches 98.06%, its time 3.06 ms/image. It observed that could present superior in comparison other existing models.
منابع مشابه
Multi-objective Optimization of Coal-fired Boiler Combustion Based on NSGA-II
NOx emission characteristics and overall heat loss model for a 300MW coal-fired boiler were established by Back Propagation (BP) neural network, by which the the functional relationship between outputs (NOx emissions & overall heat loss of the boiler) and inputs (operational parameters of the boiler) of a coal-fired boiler can be predicted. A number of field test data from a full-scale operatin...
متن کاملAssessing the Exergy Costs of a 332-MW Pulverized Coal-Fired Boiler
Abstract: In this paper, we analyze the exergy costs of a real large industrial boiler with the aim of improving efficiency. Specifically, the 350-MW front-fired, natural circulation, single reheat and balanced draft coal-fired boiler forms part of a 1050-MW conventional power plant located in Spain. We start with a diagram of the power plant, followed by a formulation of the exergy cost alloca...
متن کاملMining Temporal Data: A Coal-Fired Boiler Case Study
This paper presents an approach to control pluggage of a coal-fired boiler. The proposed approach involves statistics, data partitioning, parameter reduction, and data mining. The proposed approach was tested on a 750 MW commercial coal-fired boiler affected with a fouling problem that leads to boiler pluggage that causes unscheduled shutdowns. The rare-event detection approach presented in the...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Science China-technological Sciences
سال: 2021
ISSN: ['1006-9321', '1869-1900', '1674-7321']
DOI: https://doi.org/10.1007/s11431-020-1796-2