Industrial furnace kiln internal combustion flame directly reflects the combustion of fuel quality and stability and determines the security of the whole production process. The flame image contains many important information that cannot be observed by people’s eyes, as a result, how to effectively separate the flame image from the surrounding background by means of science and technology has the great research significance and application value. In this article, the idea of neighborhood particles is introduced into the standard particle swarm optimization algorithm, and a furnace flame recognition method is proposed based on improved particle swarm optimization algorithm. The method first uses red, green and blue color space to design the extraction model of flame image, then uses the proposed improved particle swarm optimization algorithm and Otsu algorithm to solve the optimal segmentation threshold involved in the model. Experimental results show that the proposed improved particle swarm optimization algorithm can always find the optimal segmentation threshold of the flame image within no more than 100 iterations and reduce the computation time nearly 0.01 s. Compared with the previous research results, the recognition rate of the extraction model designed in this article has been greatly improved to over 93%, which is of great value for the safe and stable operation of industrial furnaces.

中文翻译：

---

基于改进粒子群优化算法的炉膛火焰识别

工业炉窑内燃火焰直接反映燃烧燃料的质量和稳定性，决定着整个生产过程的安全性。火焰图像中包含了许多人眼无法观察到的重要信息，因此，如何利用科学技术有效地将火焰图像与周围的背景区分开来具有重要的研究意义和应用价值。本文将邻域粒子的思想引入到标准粒子群优化算法中，并在改进粒子群优化算法的基础上提出了一种炉膛火焰识别方法。该方法首先利用红、绿、蓝颜色空间设计火焰图像的提取模型，然后使用提出的改进粒子群优化算法和Otsu算法求解模型中涉及的最优分割阈值。实验结果表明，所提出的改进粒子群优化算法总能在不超过100次迭代的时间内找到火焰图像的最佳分割阈值，并将计算时间减少近0.01 s。与前人的研究成果相比，本文设计的提取模型的识别率大幅提升至93%以上，对工业炉安全稳定运行具有重要价值。实验结果表明，所提出的改进粒子群优化算法总能在不超过100次迭代的时间内找到火焰图像的最佳分割阈值，并将计算时间减少近0.01 s。与前人的研究成果相比，本文设计的提取模型的识别率大幅提升至93%以上，对工业炉安全稳定运行具有重要价值。实验结果表明，所提出的改进粒子群优化算法总能在不超过100次迭代的时间内找到火焰图像的最佳分割阈值，并将计算时间减少近0.01 s。与前人的研究成果相比，本文设计的提取模型的识别率大幅提升至93%以上，对工业炉安全稳定运行具有重要价值。