论文部分内容阅读
质子膜燃料电池(PEMFC)工作被认为是21世纪最有希望的绿色发电技术,其原理涉及热力学、电化学、流体力学、传质学等理论,形成一个非线性复杂系统,难以建立数学模型;因此,利用模糊逻辑系统和人工神经网络具有为非线性系统建模的较强的逼近能力以及自学习能力,采用自适应神经模糊算法,建立PEMFC温度特性模型;利用测试数据作为训练样本,在氢气压力给定的条件下,以空气(或氧气)压力和冷却水作温度为模型的输入量,电池的工作温度为输出量,建立了3种不同PEMFC温度特性模型;表明该方法具有简单、可行、精度高等优点。并为PEMFC控制系统的设计和电池性能的优化提供了基本依据。
Proton membrane fuel cell (PEMFC) work is considered as the most promising green power generation technology in the 21st century. Its principle involves thermodynamics, electrochemistry, fluid mechanics and mass transfer theory to form a non-linear complex system and it is difficult to establish a mathematical model. Therefore, the fuzzy logic system and artificial neural network are used to model the non-linear system with strong approximation ability and self-learning ability. The adaptive neural fuzzy algorithm is used to establish the temperature characteristic model of PEMFC. Using the test data as the training sample, Under the condition of pressure, three models of temperature characteristics of PEMFC were set up based on the input of air (or oxygen) pressure and temperature of cooling water as the model and the working temperature of the battery as the output. The results show that this method is simple and feasible , High precision advantages. And provide the basic basis for the design of PEMFC control system and the optimization of battery performance.