Fuzzy logic modeling of performance proton exchange membrane fuel cell with spin method coated with carbon nanotube
Fuzzy logic modeling of performance proton exchange membrane fuel cell with spin method coated with carbon nanotube
复制标题
DOI：
10.1016/j.ijhydene.2016.04.134
复制
发表时间：
2017-01
影响因子：
7.2
通讯作者：
Sadık Ata;K. Dincer
中科院分区：
文献类型：
--
作者：
Sadık Ata;K. Dincer
本研究以质子交换膜燃料电池为研究对象，以规则为基础的Mamdani-Type Fuzzy（RBMTF）建模技术，对燃料电池的性能进行了实验研究。采用旋涂法在质子交换膜燃料电池膜的阳极侧涂覆碳纳米管。实验研究了该燃料电池在20 °C、40 °C、60 °C下的性能，确定了最佳性能，并利用实验数据，采用RBMTF方法建模。输入参数为：温度（T）、时间（s）、电压密度（V/cm ~ 2）、电流密度（A/cm ~ 2）、输出参数功率密度（W/cm ~ 2）采用RBMTF if-then规则描述。输入和输出变量的数值参数被模糊化为语言变量：非常非常低（L1），非常低（L2），低（L3），负中（L4），中（L5），正中（L 6），高（L7），非常高（L 8）和非常非常高（L9）的语言类。使用语言变量，该系统得到了81条规则。利用统计方法对实验数据和RBMTF进行了比较。未涂覆的PEM和具有CNT（20 °C）的功率密度的多重决定系数（R2）为98.88%，20 °C、40 °C和60 °C温度的功率密度为97.12%。对于未涂覆的PEM和具有CNT的PEM，通过RBMTF技术在20 °C下获得80个值。在20 °C放电期间，实验功率密度最大值为0.021瓦特/平方厘米的未涂覆PEM和模糊模型最大值为0.0205瓦特/平方厘米的未涂覆PEM。实测值和RBMTF结果表明RBMTF可成功应用于PEM燃料电池。没有对中间值进行系统性能测试，中间值是用RMBTF估计的。用模糊逻辑方法预测了30 °C和50 °C时功率密度的78个实验值。
In this study, performance of proton exchange membrane (PEM) fuel cell was experimentally investigated and modeled with Rule-Based Mamdani-Type Fuzzy (RBMTF) modeling technique. Coating on the anode side of the membrane of PEM fuel cell was accomplished with the spin method by using carbon nanotube (CNT). This fuel cell performances at 20 °C, 40 °C, 60 °C were investigated experimentally and the best performance was determined and benefiting from experimental data, modeled with RBMTF method. Input parameters are; temperature (T), time (s), voltage density (V/cm2) and current density (A/cm2); output parameter power density (W/cm2) were described by RBMTF if-then rules. Numerical parameters of input and output variables were fuzzificated as linguistic variables: Very Very Low (L1), Very Low (L2), Low (L3), Negative Medium (L4), Medium (L5), Positive Medium (L6), High (L7), Very High (L8) and Very Very High (L9) linguistic classes. With the linguistic variables used, 81 rules were obtained for this system. The comparison between experimental data and RBMTF is done by using statistical methods. The coefficient of multiple determination (R2) for power density of uncoated PEM and with CNT (20 °C) is 98.88%, power density of 20 °C, 40 °C and 60 °C temperatures is 97.12%. 80 values were obtained by RBMTF technique at 20 °C for uncoated PEM and with CNT. During discharge for 20 °C uncoated PEM for experimental power density maximum 0.021 Watt/cm2and uncoated PEM for fuzzy model maximum 0.0205 Watt/cm2. The actual values and RBMTF results indicated that RBMTF can be successfully used in PEM fuel cell. Performance tests of the system were not done for intermediate values which were estimated with RMBTF. 78 values at 30 °C and 50 °C which are not obtained from experimental work for power density are predicted by fuzzy logic method.