论文部分内容阅读
针对现今电厂采用的锅炉燃烧监控系统所采集的火焰动态图像,提出了一种利于辅助分析的炉内火焰燃烧诊断方法。该方法分析了火焰图像的特点,提出了分析火焰稳定性判别的三个特征量,根据现场图像信号作出数据提取,并对提取结果进行了数据分析。提出一种燃烧稳定性判别方法,该方法利用以上三个特征量作为BP神经网络输入参数,得到输出确定为火焰稳定性系数,然后用模糊判别给出准确的燃烧稳定性综合评估。此方法利用了动态图像的差分特性,动态地分析燃烧过程中火焰锋面变化的状况,为现场锅炉监控人员提供了一种燃烧状态监测方法,方便了现场运行人员及时快捷地对现场状况做出准确迅速的判断和操作。通过对现场图像的人工分析和此方法判别结果比对,证明此方法具有很强的辅助分析功能。
Aimed at the flame dynamic images collected by the boiler combustion monitoring system used in the power plant, a method of flame combustion diagnosis in furnace is proposed. The method analyzes the characteristics of flame image, puts forward three features for analyzing the flame stability, extracts the data according to the field image signal, and analyzes the data. A method of discriminating the combustion stability is proposed. The method uses the above three characteristic quantities as the input parameters of BP neural network, determines the output as the flame stability coefficient, and then gives the comprehensive evaluation of the combustion stability by fuzzy judgment. This method utilizes the differential characteristics of dynamic images to dynamically analyze the changes of the flamefront in the combustion process and provides a method for monitoring the combustion status of the boiler supervisors in the field so as to facilitate the on-site operators to make accurate on-the-spot conditions promptly and quickly Quick judgment and operation. Through the manual analysis of the scene images and comparison of the results of this method, it is proved that this method has a strong auxiliary analysis function.