Solid waste incineration condition recognition method based on multi-scale color moment characteristics and random forest

Abstract

The invention relates to a solid waste incineration condition recognition method based on multi-scale color moment characteristics and a random forest. Redundancy and complexity of incineration flameimage features increase the difficulty of urban solid waste incineration (MSWI) combustion condition recognition. Complexity of solid waste components and inherent nonlinearity, time-varying property,uncertainty and the like of a solid waste incineration process cause instability of incineration image feature distribution. A traditional method based on a fixed sliding window can only extract fixed size features and cannot reflect global and local features, and the working condition recognition accuracy is reduced. The method comprises the following steps: firstly, performing defogging and denoising preprocessing on an image; then, using a sliding window based on a priori set scale to extract color moment features of different scales of the flame image; finally, using the classification precision as a criterion function, using a random forest (RF) algorithm based on feature selection, to achieve accurate recognition of the MSWI incineration working condition. An experiment result verifies the effectiveness of the method.

Description

technical field [0001] The invention belongs to the operation optimization control of municipal solid waste incineration (MSWI) process. Background technique [0002] The status of solid waste incineration in the process of municipal solid waste incineration (MSWI) is closely related to the stable operation of incinerators and steam power plants, the optimal control of the entire process operation, and the emission of pollutants. The key to furnace safety and stability. At present, the current combustion state is mainly judged by the operator observing the distribution position of the flame in the video image, but this method is easily affected by the experience, operation means and mental state of the staff, resulting in low recognition efficiency of the current MSWI state and lagging control means . The recognition of MSWI combustion conditions based on the visual features of flame images has become a new idea in current research. [0003] At present, the recognition of...

AI Technical Summary

Problems solved by technology

[0003] At present, the recognition of MSWI flame images is not mature enough

Affected by the high content of solid waste water and large fluctuations in calorific value, the environment in the incinerator is changeable and complex. The collected incineration flame images have problems such as uneven brightness changes and unclear images due to uneven illumination. The phenomenon of "jumping" is prone to occur. The uncertainty generated by the external environment leads to a large number of extracted flame feature points, severe coupling between features, and increased redundant features. These irrelevant and redundant features have caused serious problems for classification and recognition great influence

Images