【正文】 前通用的開發(fā)語言平臺，設(shè)計(jì)實(shí)現(xiàn)控制任務(wù)的程序結(jié)構(gòu)框圖。2） 利用MATLAB 建立控制系統(tǒng)仿真模型，從穩(wěn)定性，魯棒性，抗干擾等方面研究所設(shè)計(jì)控制算法的控制效果如何，并與常規(guī)PID控制進(jìn)行比較。擬采用途徑：1) 針對爐膛負(fù)壓控制要求，設(shè)計(jì)爐膛負(fù)壓控制系統(tǒng)總體方案。2) 選擇所需的控制設(shè)備，畫出設(shè)備主要接線圖。3) 根據(jù)爐膛負(fù)壓控制要求，設(shè)計(jì)仿人智能控制算法。4) 設(shè)計(jì)實(shí)現(xiàn)控制任務(wù)的程序結(jié)構(gòu)。5) 利用MATLAB 建立仿真模型，研究控制算法的性能，并與常規(guī)PID控制進(jìn)行比較。四、設(shè)計(jì)（研究）進(jìn)度計(jì)劃：第一周至第三周：資料收集，外文翻譯。第四周：撰寫開題報(bào)告。第五周至第七周：總體方案設(shè)計(jì)。第八周至第十周：控制算法的設(shè)計(jì)。第十一周至第十三周：算法仿真研究。第十四周：畢業(yè)論文撰寫。第十五周：答辯準(zhǔn)備，畢業(yè)答辯。五、參考文獻(xiàn)：1． 文武. 循環(huán)流化床鍋爐床溫動態(tài)建模與仿真. 廈門大學(xué)學(xué)報(bào)(自然科學(xué)版)，2006年第1期。2． 吳慶彬。循環(huán)流化床的模糊控制。南京工業(yè)大學(xué)碩士論文，2004年。3． 劉彬. 專家模糊控制在鍋爐床溫控制中的應(yīng)用. 電氣傳動自動化，2005年第4期.4． 岑可法，倪明江，、:中國電力出版社，1997。5． 邊立秀. 循環(huán)流化床鍋爐床溫控制建模與仿真. 華北電力大學(xué)學(xué)報(bào)，2003年第1期。6． Post Comparison of Methods of Fuzzy Relational Identification, IEE PROCEEDING. 1991，138(3) 。7． Chi and Design of fuzzy Control System. Fuzzy Sets and ,(57):125－140。8． 胡章軍. 仿人智能控制算法研究. 青島科技大學(xué)碩士論文，2006年。9． 徐軍。循環(huán)流化床鍋爐的優(yōu)化控制. 江南大學(xué)碩士論文，2006年。指導(dǎo)教師意見簽名： 月 日教研室（學(xué)術(shù)小組）意見教研室主任（學(xué)術(shù)小組長）（簽章）：月 日 附件二(外文文獻(xiàn))Constrained optimization of bustion in a simulated coalfired boiler using artificial neural network model and information analysisAbstractCombustion in a boiler is too plex to be analytically described with mathematical models. To meet the needs of operation optimization, onsite experiments guided by the statistical optimization methods are often necessary to achieve the optimum operating conditions. This study proposes a new constrained optimization procedure using artificial neural networks as models for target analysis based on random search, fuzzy cmean clustering, and minimization of information free energy is performed iteratively in the procedure to suggest the location of future experiments, which can greatly reduce the number of experiments needed. The effectiveness of the proposed procedure in searching optima is demonstrated by three case studies: (1) a benchmark problem, namely minimization of the modified Himmelblau function under a circle constraint。 (2) both minimization of NOx and CO emissions and maximization of thermal efficiency for a simulated bustion process of a boiler。 (3) maximization of thermal efficiency within NOx and CO emission limits for the same bustion process. The simulated bustion process is based on a mercial software package CHEMKIN, where 78 chemical species and 467 chemical reactions related to the bustion mechanism are incorporated and a plugflow model and a loadcorrelatedtemperature distribution for the bustion tunnel of a boiler are used.1. IntroductionAlthough there have been a lot of experimental and theoretical studies on the basic physical and chemical principles of a boiler’s operation, and great advance has been made in understanding various aspects of theoperation, it is still impracticable, as Caravelle and coworkers [1] have just pointed out, to couple detailed fluid dynamics and kinetics in the bustion system design even with the continuous increase of puter power, not to mention to simulate a boiler and its various auxiliarysubsystems as a whole. If fuel and environment conditions are specified, the thermal efficiency of a given boiler depends mainly on the air to fuel ratio, and on the distribution of air and fuel to burners at different locations if two or more burners are used. For different fuels and different furnace configurations, the best air to fuel ratio and the best air and fuel distributions are surely different, which may be roughly estimated by analysis but can only be determined accurately by testing runs. As for the control of trace pollutant emissions (in terms of ppm or ppd NOx, SO2, etc.) of a boiler, all of such uncertain factors as fuel positions, plexity of flow and temperature fields in the burning chamber, and the plicated mechanism of chemical reactions make model prediction highly unreliable. The inability of theoretical analysis makes empirical approaches necessary to explore the optimum operation conditions of a boiler. Nardin et al. [2] used fractional factorial design procedure and identified the important factors of NOx reduction in a fluidized bed bustor (FBC) with primary measures and selective noncatalyticreduction. Henryton et al. [3] performed an optimizingcontrol of NOx and SO2 emissions in the FBC process based on static models which were regressed from experimental data. George [4] suggested a boiler test system in order to monitor NOx emissions through optimizing various operation conditions in a prehensive and systematical manner, and claimed that achieving NOx emission reduction targets does not necessarily mean equipment retrofits or poor boiler performance. The capability of artificial neural networks (ANNS) as a universal modeling tool has been widely recognized in the last 20 years, and Cyberpunk [5] showed that ANNS could approximate any arbitrary nonlinear functions. ANNS offer an alternative approach to model process behavior, as they do not require a prior i knowledge of the process phenomena. They learn by extracting impede patterns from data that describe the relationship between the inputs and the outputs in any given process phenomenon. When appropriate inputs are applied to an ANN, the ANN acquires ‘knowledge’ from the environment in a process known as ‘learning’. As a result, the ANN assimilates information that can be recalled later. ANNS are capable of handling plex and nonlinear problems, processing information rapidly and reducing the engineering effort required in model development. ANNS have been successfully applied to a variety of problems such as process fault diagnosis, system identification, pattern recognition, process modeling and control, and statistical time series modeling. Karyological [6] gave a review on the application of ANNS in energy systems.Reif man et al. [7] developed an intelligent emissions controller for fuel gas reburning in coalfired power plant,and in their study, a feedforward neural netw