Principles of fuzzy neural network and FNN method are adopted for the numerical simulation of network modeling and forecasting of beams with finite deformation of two different materials.
本文运用模糊神经网络原理，采用学习结合型FNN方法，针对两种不同材料梁的大变形进行了网络建模和预测的数值仿真。
In the research of reasoning machine, a FNN reasoning method is used to solve the problem of collision and inefficiency in the fuzzy rules reasoning.
在对推理机制的研究中，采用模糊神经网络推理方法解决了模糊规则推理时存在的冲突和低效率问题。
The method can simplify the structure of network and reduce the time of training that supplies the possibility that FNN is used in realtime control system.
仿真结果表明该方法精简了网络的结构，减少了训练的时间，为模糊神经网络用于实时控制系统提供了可能的条件。
Through comparison calculations between FNN simulation and traditional method using exiting test data, the predicted result of FNN is more accurate than that of the latter.
通过对已有的钻芯、回弹试验数据的对比计算，其强度预测精度高于常规的综合方法。
A variable structure control method based on T-S fuzzy neural network (FNN) is brought forward.
提出基于T - S模糊神经网络的变结构控制方法。
Gradient descent algorithm is an efficient method to train FNN, and it can be realized in batch or incremental manner.
梯度下降算法是训练多层前向神经网络的一种有效方法，该算法可以以增量或者批量两种学习方式实现。
Compared with conventional fault diagnosis method, the FNN fault diagnosis method has better performance for single fault and its diagnosis result has higher precision.
与传统故障诊断方法相比，基于模糊神经网络的故障诊断方法对单一故障具有很好的识别能力，可以提高诊断精度。
The main results can be summarized as following:(1) A novel method of selecting the initial optimum step and its adjustment is presented in FNN, which is suitable for the prediction on-line.
提出了一种适于雷达在线预测的新的前向神经网络训练的优化步长初值选择方法及调整方法。
The structure of the FNN is given, and the learning method is presented. Meanwhile a fault discriminant method for threshold vector is employed, which makes fault discrimination even more flexible.
文中给出了模糊神经网络的结构和学习方法，并提出了一种阈值向量故障判别方法，使故障判别更具灵活性。
With FNN decompose technique added, the method has some merits of shorter training time, higher executing speed, higher reliability and anti noise abilities.
该网络适于进行多传感器刀具状态的识别和分类，具有训练时间短，执行速度快，可靠性高，抗噪能力强的特点。
With FNN decompose technique added, the method has some merits of shorter training time, higher executing speed, higher reliability and anti noise abilities.
该网络适于进行多传感器刀具状态的识别和分类，具有训练时间短，执行速度快，可靠性高，抗噪能力强的特点。
应用推荐