基于arm及小波分析的火检实时系统的研究-计算机应用技术专业论文.docxVIP

摘要摘要 摘要 摘要 锅炉煤粉燃烧已成为工业生产和人民生活所必需的一种能量和动力来源， 而火焰检测系统是保障锅炉安全运行的关键所在。锅炉炉膛中存在炉体火焰和 若干个喷火嘴喷出的火焰，通常在存在炉体背景火焰的情况下，需判断喷嘴火 焰是否存在，以确定喷嘴的运行状态。 本文针对目前炉膛火焰检测系统信号特征提取难度大、信噪比低、难以准 确判断的特点，通过对炉膛煤粉燃烧试验数据的采集与分析，提出了一种基于 Wavelet变换和BP神经网络相结合的火焰检测方法。该方法把采集的含噪信号进 行多尺度的小波分解、特征提取，之后对信号进行软阈值去噪处理，将预处理 后的信息作为神经网络的训练输入。 从信号处理的角度出发，本文阐述了小波时一频分析的优势，以及小波特 有的去噪方法，以小波变换理论为分析工具对现场试验数据进行了具体分析。 通过某电厂炉膛火焰燃烧试验证明：该时频局部化分析方法改善了信噪比，克 服了目前火检系统容易误判的缺点，结果表明该方法能更有效地识别火焰的燃 烧状况，具有广泛的实用价值。 关键词：火焰检测；小波分解；特征提取；阈值；BP神经网络 蛮苎皇奎銮：璺圭兰竺兰銮Abst 蛮苎皇奎銮：璺圭兰竺兰銮 Abst ract n忙energy and power is necessary to people by the coal firing．The flame detection system is the sticking point of making the fIlmaces safely work．There are two kind of flame in fifed fIlnlace．One is ftm瞰aco舢cIy fLamc，the other is flame from furnace nozzles．In order to iudge the operation status of furnace，workers need to know whether the furnace nozzle is burning or not under the background flame of fumace． Traditional flame detection method finds it much difficult to extract the signal feature and recognize the status realiably as the sigrlal-to—noise ratio is very low．we proposed a new method,based on combined the Wavelet transform and Back Propagation neural network，which has been used after the acquisition and analysis of experimental data矗Om the power plant’S coal firing furnace．Firstly,a set of flame intensity data contains of lots of noise．whiell acquired via a sellSor,are decomposed based on multi．scale Wavelet．Next，the feature information is distilled from original signal and then against noise with soR threshold value wavelet transform．Last．the feature information，which distilled by power analysis，ale used as the neural network’s input signals for training purpose． 11lis thesis，which is based on the aspect of signal preeessing，introduces the advantages of wavelet time-frequecy localization and the particular method of denoising，also concretely analyzes the experimental data using the theory of wavelet transform．nle experimental results demonstrate that