An image analysis system and an image analysis method for estimating the burning value of straw

Abstract

The invention relates to an image analysis system and an image analysis method for estimating the burning value of straw, wherein the straw fuel is photographed by a camera, after duplicate checking,using the annotation platform to annotate the images in the cloud server, the data set is obtained, the data set is expanded by the method of data enhancement, the semantic segmentation network is trained by the data set, the straw fuel is continuously photographed by the camera, the image is collected and uploaded to the server, the straw image is segmented by the semantic segmentation network, the proportion is calculated, and the straw burning value is calculated by the proportion. The invention can collect and train images remotely, analyze and feedback the results to the power generationsystem through wireless network, make real-time adjustments to the resolution, exposure value, white balance and other parameters of the image acquisition equipment, delete unnecessary image data, upload effective image data, reduce unnecessary costs, using depth learning method can be more accurate to get the proportion of straw.

Description

technical field [0001] The present invention belongs to the technical field of general image data processing or generation, and particularly relates to a method of collecting and analyzing images of materials before feeding straw fuel into a circulating fluidized bed boiler for combustion and generating electricity, and feeding back the analyzed data to the entire power generation system, and then An image analysis system and image analysis method for estimating straw fuel value to obtain better boiler combustion efficiency. Background technique [0002] Straw is one of the new energy sources with the most potential for development and utilization. It can replace mineral fuels such as coal, oil, and natural gas to generate electricity. Effectively reducing the concentration of PM2.5 in my country can reduce the pollution caused by energy consumption to the environment. At present, Europe and the United States have established relatively complete straw-type agricultural waste...

AI Technical Summary

Problems solved by technology

[0005] In the prior art, the method of controlling the calorific value of fuel in the straw burning power generation process still mainly adopts the manual adjustment method, and workers carry out follow-up adjustments on the basis of measuring the calorific value of straw fuel by taking samples at fixed points in the fuel warehouse. Obviously, the manual adjustment method cannot Realize the automatic control operation of the calorific value of straw fuel, the automation level is low, and it cannot meet the high-quality combustion control requirements of the modern straw combustion power generation process

Images