基于双目视觉耦合激光的垃圾焚烧炉进料速率实时测量技术

入炉垃圾进料速率实时测量对垃圾焚烧炉的稳定运行和污染控制具有重要作用，但传统技术工艺很难实现入炉垃圾进料速率的实时测量。利用双目视觉原理搭建了料堆体积测量平台，为减少垃圾焚烧炉料斗内光线暗、垃圾表面弱纹理等复杂因素的影响，提出了一种双目视觉耦合激光的垃圾进料速率实时检测技术，并开展了验证实验。结果表明，该堆料体积测算方法可将误差控制在1%以下，符合垃圾焚烧炉进料速率测算对精度的要求。通过对某垃圾焚烧电厂经济性分析发现，本炉垃圾进料速率测量设备可大幅度降低经济成本。该研究结果可与焚烧炉运行参数以及污染物排放参数进行耦合计算，通过深度学习与优化控制，以实现垃圾清洁、高效与智慧焚烧。

Real-time measurement technology of waste feeding rate into furnace based on binocular vision coupled laser

The real-time measurement of the feed rate of the waste into the furnace plays an important role in the stable operation and pollution control of the waste incinerator, but it is difficult to realize the real-time measurement of the feed rate of the waste into the furnace with the current technology. A binocular vision principle was used to build a stack volume measurement platform in this paper. In order to reduce the influence of complex factors such as the dark light in the waste incinerator hopper and the weak texture of the waste surface, a binocular vision coupled laser was proposed to realize the real-time waste feed rate and test verification was carried out. The results showed that the error of this stack volume estimation method can be controlled below 1%, which meted the accuracy requirements of the waste incinerator feed rate estimation. Through the economic analysis of a waste incineration power plant, it was found that the installation of the measurement equipment for the feed rate of waste into the furnace proposed in this paper, the economic cost was greatly reducing. The research results can be coupled with the operating parameters of the incinerator and the pollutant emission parameters through deep learning and optimized control to achieve clean, efficient and smart incineration of waste.