煤粉炉燃烧稳定性的研究-控制工程专业毕业论文.docxVIP

摘 摘 要 摘 要 电力是人类生活不可缺少的能源，虽然这些年新能源发电的发展迅速，但煤 炭发电仍占总体发电量的绝大部分。煤粉炉是煤炭发电中至关重要的一个设备， 煤粉炉的燃烧稳定性直接关系着火电厂燃烧的安全与经济性。本文采用基于经典 BP神经网络以及改进粒子群结合BP神经网络等多种方法研究了煤粉炉燃烧稳 定性的问题。 本文的研究内容体现在以下几个方面： 1．本文介绍了BP神经网络模型，对其优缺点进行了详尽的阐述。建立了炉 膛燃烧稳定性的神经网络模型，在选择隐层节点个数时，对原有黄金分割法进行 了改进。与其它隐层节点数计算方法进行对比，结果表明本方法有计算量低、准 确度高的优点； 2．针对BP神经网络的不足，本文采用了粒子群优化算法对BP神经网络模 型中的权值跟阈值进行寻优。并在经典粒子群算法中同时加入极值扰动与变异两 种方法，用于优化燃烧稳定性模型参数，并进行了仿真验证。 关键词：煤粉炉；燃烧稳定性；BP神经网络；粒子群优化算法；火检信号；炉 膛压力；特征量 万方数据 AbstractAbstract Abstract Abstract Electric energy is indispensable to human life．Although new energy power generation has developed rapidly in recent years，coal-fired power generation still accounts for most parts of the overall capacity．Pulverized coal fumace is one of the most important equipment in coal-fired power generation，its combustion stability directly related to fire safety and economy of power plant．In this paper,lots of ways based on the classic BP neural network and improved particle swarm method combined with BP neural network have been used to study the combustion stability of different pulverized coal fumace． In this paper,the research content is embodied in the following aspects： 1．This paper introduces the BP neural network model，the advantages and disadvantages are detailed described．The furnace combustion stability of the neural network model is established．When choosing a number of hidden layer nodes，the original golden section method is improved．With the rest of the number of hidden layer nodes，comparing the calculation results show that this method has the advantages of low computational cost，high accuracy． 2．Aiming at the shortcomings of the BP neural network，this paper USES the particle swarm optimization algorithm for the weight value and threshold of BP neural network model for optimization．And at the same time to join in the classic particle swarm algorithm of extremum disturbance and variation of two ideas，to optimize the combustion stability of model parameters．and a simulation was carried out． Keyw