In this paper, the proposed wavelet-based methodology is developed to identify and classify the High Impedance Fault (HIF) in the Power Distribution System (PDS). The planned technique is based on the combination of Ant Lion Optimizer (ALO) and Artificial Neural Network (ANN), which is performed to accurately isolate the HIF. The change in phase current waveforms caused by faults and normal switching events has been used in this methodology. In order to develop the method to detect high impedance arcing faults under the linear conditions. The faults are identified through the computation of the basic electric descriptions of current and voltage signals. From the voltage and current signals, the harmonic components also computed. From the voltage, current signals, the fault are identified and classified in the system which can be able to solve the problem in the system. The harmonics level also analyzed which also detected and able to correct it for enabling the stable operation in the system. ANN is an Artificial Intelligence (AI) method that applied for optimizing precise generation limits as blocking happened. The neural network contains two stages: training stage and testing stage. Here, the ALO algorithm is utilized to improve the performance of the ANN training process. ALO is a new nature-inspired algorithm mimicking the hunting behavior of ant lions. The design of Lifting Wavelet Transform (LWT) is suitable for the classification process. The main objective of ANN with the aid of the ALO algorithm is the detection and classification of the HIF in PDS and analyzed the delay time of different locations. From the evaluation of the proposed technique, the inputs and their corresponding outputs are noted. The performance of the work is implemented in MATLAB/Simulink platform and the presentation of this model is investigated on the basis of the two cases of analysis. The results show that the projected algorithm detects the HIFs accurately and compared with the existing methods ALO, GSA and ANN, and GA and Fuzzy, respectively.

中文翻译：

---

基于 LWT 的 ANN 和 Ant Lion 优化器，用于配电系统中高阻抗故障的检测和分类

在本文中，提出了基于小波的方法来识别和分类配电系统 (PDS) 中的高阻抗故障 (HIF)。计划中的技术基于 Ant Lion Optimizer (ALO) 和人工神经网络 (ANN) 的组合，用于准确隔离 HIF。这种方法中使用了由故障和正常开关事件引起的相电流波形变化。为了开发在线性条件下检测高阻抗电弧故障的方法。通过计算电流和电压信号的基本电气描述来识别故障。根据电压和电流信号，还计算了谐波分量。从电压、电流信号，故障在系统中被识别和分类，能够解决系统中的问题。还分析了谐波水平，这也检测到并能够对其进行校正，以实现系统的稳定运行。ANN 是一种人工智能 (AI) 方法，用于在发生阻塞时优化精确的发电限制。神经网络包含两个阶段：训练阶段和测试阶段。在这里，ALO 算法被用来提高 ANN 训练过程的性​​能。ALO 是一种新的受自然启发的算法，模仿蚂蚁狮子的狩猎行为。提升小波变换 (LWT) 的设计适用于分类过程。ANN 的主要目标是借助 ALO 算法对 PDS 中的 HIF 进行检测和分类，并分析不同位置的延迟时间。从对所提出技术的评估中，记录了输入及其相应的输出。工作性能在MATLAB/Simulink 平台上实现，并在两个案例分析的基础上研究了该模型的呈现。结果表明，投影算法准确地检测了HIF，并分别与现有方法ALO、GSA和ANN以及GA和Fuzzy进行了比较。工作性能在MATLAB/Simulink 平台上实现，并在两个案例分析的基础上研究了该模型的呈现。结果表明，投影算法准确地检测了HIF，并分别与现有方法ALO、GSA和ANN以及GA和Fuzzy进行了比较。工作性能在MATLAB/Simulink 平台上实现，并在两个案例分析的基础上研究了该模型的呈现。结果表明，投影算法准确地检测了HIF，并分别与现有方法ALO、GSA和ANN以及GA和Fuzzy进行了比较。