Hot spot detection method for air preheater based on fuzzy kernel function support vector machine

Abstract

The invention discloses a hot spot detecting method of power station boiler air preheater based on ambiguity nuclear function support vector machine, which is characterized by the following: finishing three different classification methods of air-conditioner fire condition through the support vector machine based on ambiguity nucleus function to support vector machine; selecting the measurable temperature value as the input variable of classification unit and fire pattern mark as output variable; dividing the data sample into two parts that two thirds as exercise and residual sample as detection; exercising three classification devices separately; estimating the classification device property through detection sample; computing the classification device ROC curve to compare the classification device property; adapting the adaptive parameter optimization method to select regularized parameter and nuclear parameter of support vector machine.

Description

technical field [0001] The invention belongs to the technical field of industrial automatic detection, relates to an industrial process detection method, in particular to an air preheater hot spot detection method based on a fuzzy kernel function support vector machine. Background technique [0002] The power plant boiler air preheater is a heat exchanger that uses the exhaust heat of the boiler to heat the air. When the excess fuel (including carbon black and oil droplets) accumulated on the heating surface of the air preheater is oxidized and heated up to the ignition temperature, it will cause the combustion accident of the air preheater itself. There are two conditions for the combustion of the air preheater: 1. There is fuel accumulated on the heating surface; 2. The flow rate of air and flue gas in the air preheater is low or uneven, resulting in poor heat dissipation conditions. When unburned or partially burned fuel, especially poorly atomize...

AI Technical Summary

Problems solved by technology

Literature "Research on Hotspot Detection System of Power Plant Air Preheater Based on Least Squares Support Vector Machine" (Liu Han, Li Qi, Liu Ding, Liang Yanming, Song Nianlong: "Power Station Boiler Air Preheater Hotspot Detection System Based on Least Squares Support Vector Machine" Research", Chinese Journal of Electrical Engineering, 2005, 25(3); 147-152), the least squares support vector machine (LS-SVM) was used to study the hot spot detection system of the air preheater, but the method used the least squares The accuracy of multiplication support vector machine classification is relatively low, the execution speed is slow, and the selection of parameters adopts the method of cross-check, which depends more on experience

Images