Optimization of carbon emission peak path based on multisensor information fusion and integrated intelligent algorithm

Abstract

With the development of the social economy, the demand for resources has gradually increased. Since 2005, carbon emissions in various regions have been increasing, and the growth rate of carbon emissions has accelerated. The issue of peak greenhouse gas emissions has become the focus of international climate negotiations. Carbon emissions will lead to global warming and a greenhouse effect; it will also cause extreme weather, such as typhoons, high temperatures, heavy rains, mudslides, dry mornings and other natural disasters; it will accelerate the melting of ice and snow at the South and North poles, causing sea levels to rise year by year; carbon emissions Increased emissions will harm people’s health and quality of life; carbon emissions will lead to higher temperatures, insect plagues in some areas, global food production may be severely affected, and yields will gradually decline.The main work of this paper is based on multisensor information fusion and integrated intelligent algorithm carbon emission peak path optimization research. Multisensor information fusion technology and intelligent algorithms obtain the optimal solution to the problem by fusing information from different sensors and through a large number of simple information transmission and evolution methods to obtain more comprehensive information of the measured object and make correct judgements, improving the optimization of the path to the peak of carbon emissions. This paper uses intelligent algorithms such as multisensor information fusion technology and BP neural networks to quantitatively analyse the carbon emission peak path. By selecting the carbon combustion path optimization model, various influencing factors are expanded, decomposed and studied. The BP neural network is used to model carbon combustion emission characteristics and scenario design. The factors affecting carbon emissions are solved through grey system theory, and the optimization of the carbon emission peak path is studied from the carbon emissions. Optimizing the path to peak carbon emissions is beneficial to energy optimization and energy conservation and emission reduction in the new era of economic development. To achieve sustainable development and develop a green economy. The experimental results in this paper show that the use of a neural network model for carbon emission path optimization based on the BP neural network structure design can produce carbon emission reduction effects. The maximum absolute value of the NOx emission calibration error is 4.3899%, the minimum value is 1.2168%, and the absolute average error is 3.0398%, which is within the acceptable range; the maximum absolute value of the emission optimization efficiency calibration error is 0.2045%, the minimum is 0.0499%, and the absolute average error of the value is 0.1129%, which is within the acceptable range. Research on peak carbon emissions is very important at present.