In this study, a self-organizing interval type-3 fuzzy logic system (SO-IT3FLS) with a new learning algorithm is presented. An adaptive kernel size using fuzzy systems is introduced to improve the robustness of conventional correntropy based Kalman filters against non-Gaussian noise. The maximum correntropy Kalman filter (MCKF) and maximum correntropy unscented Kalman filter (MCUKF) with the proposed adaptive fuzzy kernel size are reformulated to optimize both rule and antecedent parameters, respectively. In addition to the rule parameters, the proposed membership function (MF) parameters and the level of $\alpha$-cuts are also optimized. Five simulation examples with real-world data sets are given for examination. The simulations show that the introduced SO-IT3FLS and learning algorithm result in better accuracy in contrast to the other kind of fuzzy neural networks and conventional learning techniques. Furthermore, it is verified that the robustness of the proposed learning method against non-Gaussian noise is improved in contrast to the conventional Kalman filter, maximum correntropy Kalman filter and unscented Kalman filter.

在这项研究中，提出了一种具有新学习算法的自组织区间类型 3 模糊逻辑系统（SO-IT3FLS）。引入了使用模糊系统的自适应内核大小，以提高传统的基于相关熵的卡尔曼滤波器对非高斯噪声的鲁棒性。具有建议的自适应模糊核大小的最大相关熵卡尔曼滤波器 (MCKF) 和最大相关熵无迹卡尔曼滤波器 (MCUKF) 被重新制定，以分别优化规则和先行参数。除了规则参数之外，建议的隶属函数 (MF) 参数和级别$\alpha$-cuts 也被优化。给出了五个具有真实世界数据集的模拟示例以供检查。仿真表明，与其他类型的模糊神经网络和传统学习技术相比，引入的 SO-IT3FLS 和学习算法具有更好的准确性。此外，与传统的卡尔曼滤波器、最大相关熵卡尔曼滤波器和无迹卡尔曼滤波器相比，所提出的学习方法对非高斯噪声的鲁棒性得到了提高。