Abstract

In this paper, a mathematical model of a neural network defuzzificator is presented. It is a two-layer perceptron and serves to convert a fuzzy solution to a numerical form in fuzzy-logic output procedures. The model allows optimizing the computational load that occurs when using the standard center-of-gravity method, through the use of a neural network. Training and testing are conducted with various settings of the neural-network model. The effectiveness of this approach by measuring the time required for the computation is also proved.

中文翻译：

---

模糊逻辑输出过程中神经网络去模糊器结论的数学模型及其软件实现

摘要

本文提出了神经网络去模糊器的数学模型。它是两层感知器，用于在模糊逻辑输出过程中将模糊解转换为数值形式。该模型允许通过使用神经网络来优化使用标准重心方法时发生的计算负荷。使用神经网络模型的各种设置进行训练和测试。通过测量计算所需的时间，也证明了这种方法的有效性。