mnn

Experiment results show that the two-layer MNN model outperforms other three models on the robustness and GC . ( 3 ) Apply the soft margin SVM regression algorithm to the soft sensor modeling .

实验结果表明，两层多神经网络模型的鲁棒性和泛化能力优于其他三种模型。（3）将软间隔支持向量机回归算法用于软测量建模。

Modeling research on soft - sensing based on improved MNN

基于混合多神经网络的软测量建模研究

Evaluation on the ability of subject based on MNN

基于人工神经网络的学科能力评价

The Productive Mechanism and Technical Research of MnN

氮化锰制取机理及工艺研究

Manufacturing of Piezoelectric Ceramics PZT ( MNN ) in Inorganic Material

无机材料PZT（MNN）压电陶瓷的研制

MnN production that nitrogen content is about 6.880 % ~ 6.902 % has been obtained .

获得了含氮高达6.880%～6.902%的氮化锰产品。

MNN is not limited by multiple classes .

MNN不受多类问题的限制。

The approach to build software sensor model by multiple neural networks ( MNN ) based on Kmeans clustering method is presented .

本文提出了一种用多神经网络建立动态软测量模型的通用方法。

Individuals ' allocation attention can be modified by practice ; The results of the TKF can be modified by the treated MNN .

多层神经网络经过训练以后，能够对卡尔曼滤波器的结果进行修正。

In order to obtain MnN , manganese power has been nitrided by nitrogen decomposed from ammonia at high temperature in pipe type oven at lab.

采用正交设计法，在实验室管式炉内、高温条件下利用氨气分解产生的活性氮对锰粉进行氮化获得氮化锰粉。

In this paper , a learning algorithm based on the sequencial predict error method ( SPE ) for a multilayered neural network ( MNN ) is derived .

提出一种基于序贯预测误差方法（SPE）的多层神经网络（MNN）的学习算法。

The technology is to obtain MnN production by nitride electrolytic manganese powder through pure nitrogen (≥ 99.99 % ) and nitrogen decomposed by ammonia under high temperature .

此工艺是在高温下利用纯氮（≥99.99%）和氨分解氮对电解金属锰粉进行氮化，获得氮化锰合金。

A structure of a main neural network ( MNN ) and three decentralized neural networks ( DNN ) are designed . The parameter estimations are given by on-line learning of neural network .

并且设计了一个主神经网络和三个分布神经网络的结构，通过神经网络的在线学习，得到需要的参数估计。

Simulation results show that MNN power controller achieves better control performance and system capacity than fixed-step controller due to the inherent ability of MNN to identify the fast time-varying characteristic of inverse channel .

仿真结果表明，由于神经网络能够较好地识别反向链路的时变特性，MNN功率控制方法比传统的固定步长功率控制方法取得了更好的控制性能和系统容量。

In this paper , we firstly introduce the basic concepts of morphological neural networks ( MNN ) and then present a novel class of neural networks , called fuzzy morphological neural networks ( FMNN ) .

该文在简要介绍形态学神经网络（MorphologicalNeuralNetwork，简称MNN）的基础上，提出了一种新型的模糊形态学神经网络，给出了其相应的模型。

The novel modified neural network ( MNN ) described here is composed of two sub - nets : linear neural net-work ( LNN ) and diagonal recurrent neural network ( DRNN ) .

这种改进型神经网络（MNN）由两个子神经网络综合构成：线性神经网络（LNN）和递归神经网络（DRNN）。

The thesis introduces the current research situation of MnN , technological theory of nitrogen process , experimental feasibility , equipments and process , effective factors , MnN structure , chemical analytical method and economic benefit brought by mass production in detail .

文中详细介绍了氮化锰的研究现状、氮化机理、实验可行性、设备及过程、影响因素、氮化锰结构、化学分析方法、X射线衍射物相分析方法和批量生产的技术经济效益。

This paper proposes a implement method of adaptive fuzzy neural controllers used in complex industrial processes . This control system consists of a fuzzy neural controller ( FNNC ) and modeling neural networks ( MNN ), and has the ability of adaptive learning .

针对复杂工业过程系统的特点，提出了一种自适应模糊神经网络控制器，这种控制器由模糊神经网络控制器（FNNC）和模型网络（MNN）组成，具有自适应学习能力。