改进北方苍鹰算法在光伏阵列中应用研究

针对北方苍鹰优化算法(NGO)存在收敛精度低和易陷入局部最优等问题，提出一种改进北方苍鹰算法(INGO),并应用于光伏阵列故障诊断。首先，利用Circle映射、自适应权重因子和Levy飞行策略改进了北方苍鹰优化算法，结合高斯检测机制和混合核极限学习机(HKELM)搭建INGO-HKELM故障诊断模型。其次，将INGO算法与NGO、粒子群算法(PSO)、鲸鱼算法(WOA)在测试函数上进行比较，表明在寻优能力、稳定性等方面具有优越性。然后，分析不同运行状态下光伏阵列运行特征，提出一种5维故障特征向量，作为数据的输入。最后，将4种算法分别对HKELM的核参数进行优化并实现故障分类。结果表明，所提方法能够准确地检测出光伏组件发生的异常状态，INGO-HKELM模型准确率达到93.74%,验证了所提算法的有效性和可行性。

Application of improved northern goshawk optimization algorithm in photovoltaic array

Aiming at the problems of the northern goshawk optimization algorithm (NGO), such as low convergence accuracy and easy tofall into local optimum, an improved northern goshawk optimization algorithm (INGO) is proposed and applied to the fault diagnosis ofphotovoltaic array. Firstly, circle mapping, adaptive weight factor and Levy flight strategy are used to improve the INGO. Combined withGaussian detection mechanism and hybrid kernel extreme learning machine ( HKELM), the INGO-HKELM fault diagnosis model isbuilt. Secondly, the INGO algorithm is compared with the NGO, the particle swarm optimization algorithm ( PSO), and the whaleoptimization algorithm (WOA) on the test functions, which shows that it has advantages in optimization ability and stability. Then, theoperating characteristics of photovoltaic arrays under different operating states are analyzed, and a 5-D fault feature vector is proposed asthe input of data. Finally, the four algorithms are used to optimize the kernel parameters of HKELM and achieve fault classification. Theresults show that the proposed method can accurately detect abnormal states of photovoltaic modules, and the accuracy of INGO-HKELMmodel reaches 93. 74%, which verifies the effectiveness and feasibility of the proposed algorithm.