bpnn

The Structure model and principle of intelligence diagnose system for faults of transformer based on BPNN are described ;

介绍了以BP神经网络理论为基础的变压器故障智能诊断系统的结构模型及其原理；

An acoustic model based on BPNN / HMM

基于BPNN/HMM神经网络的声学模型研究

The Application of Back Propagation Neural Network ( Bpnn ) on Hazard Gradation of Fire Smoke

BP神经网络在火灾烟气危害性分级中的应用

A structural damage detection method based on modified Back-Propagation neural network ( BPNN ) is presented in this thesis .

本文提出了基于改进型BP神经网络进行结构破损诊断的方法。

The back propagation artificial neural network ( BPNN ) was established , which has a very well forecast performance .

此外，本研究还建立了预测性能良好的BP神经网络。

In this paper , that back propagation neural network ( BPNN ) is applied in transformer fault diagnosis is discussed .

本文将BP神经网络应用于变压器故障诊断。

The model performance has been compared with a Back Propagation Neural Network ( BPNN ) forecast model which is normally used .

并与通常使用的反向传播神经网络（backpropagationneuralnetwork，BPNN）预测模型进行比较。

Genetic algorithm ( GA ) and Back Propagation neural network ( BPNN ) have a strong capacity of optimizing parameters .

遗传算法（GA）和误差反向传播算法的多层前馈网络（BPNN）都具有很强的寻优能力。

The process of oil-water separation in hydrocyclones was simulated by improved BP neural network ( BPNN ) .

采用改进的BP神经网络模型模拟水力旋流器的油水分离过程。

As simple and easy to be realized , Back-propagation Neural Network ( BPNN ) has currently been widely used in sales forecasting .

BP神经网络（Back-Propagationneuralnetwork，BPNN）因其结构简单易于实现，在销售预测中得到广泛应用。

Secondly , the thesis applies the Back-Propagation neural network ( BPNN ) to estimate the environment parameter and sets up the corresponding NN model .

其次，针对本文中的扩散模型，对表征宏观因素的环境适宜度参数，提出应用BP神经网络的方法进行量化，建立了相应的神经网络模型；

An image classification method is presented , which trains the back-propagation neural network ( BPNN ) by combining micro-group genetic algorithm and adaptive back propagation algorithm .

介绍了采用微种群遗传算法和自适应BP算法相结合的混合遗传算法来训练前向人工神经网络（BPNN）的方法。

Conclusion Because of the inspirit function 's globaling and the number of the Hidden Layer'node uncertainty the BPNN was not done well .

结论反向传播网络在函数逼近方面差的原因是激励函数的全局性、隐层结点数目的不确定性。

Aim To eliminate the influences of backlash nonlinear characteristics generally existing in servo systems , a nonlinear compensation method using backpropagation neural networks ( BPNN ) is presented .

目的为了消除普遍存在于伺服系统中的间隙非线性的影响，提出一种利用BP神经网络进行非线性补偿的方法。

Because the convergent rate of GA and BPNN is very slow , PID Adjustor based on GA-BPNN can 't be widely used in real-time control system .

由于GA和BPNN的寻优时收敛速度慢，使得基于GA-BPNN的PID调节器在实际控制系统中的运用受到了限制。

But if single neuron PID controller designed in terms of BPNN Theory is adopted , the control effect is not satisfactory because the learning rate and speed of convergence are slow .

使用常规PID控制很难满足手指精确位置控制的要求，而采用依据BPNN原理设计成的常规单神经元PID控制器又因学习速率低，收敛速度慢，控制效果不能令人满意。

Some robust watermarking in frequency domain were researched by using independent component analysis ( ICA ), back-propagation neural network ( BPNN ), error correction coding and orthogonal spread spectrum technology .

应用独立分量分析方法、BP神经网络模型、卷积码纠错编码和正交扩频等技术，提出了一些频域鲁棒性水印算法。

According to its features a short-term load forecasting model is built in which the autoregressive integrated moving average ( ARIMA ) is integrated with back propagation neural network ( BPNN ) .

针对电力系统短期负荷的特点建立了将累积式自回归动平均法（autoregressiveintegratedmovingaverage，ARIMA）和采用反向传播算法（BackPropagation，BP）的神经网络法相结合的短期负荷预测模型。

The paper compares the features and mechanism of Back-propagation neural networks ( BPNN ) with that of Hopfield neural networks ( HNN ), then their application effects in potential field inversion .

比较了BP、Hopfield二种神经网络模型的特性及其运行机制，分别用于位场反演，还比较了各自在位场反演中的应用效果。

Word frequency , marked sources location and ontology relation distances handled by the system are used as input samples of the Back-Propagation Neural Networks ( BPNN ) to predict the document level .

在系统中，通过提取文档集的词频、文档标引源位置特性及本体关系距离等初集本体特征，作为样本集，并采用BP神经网络预测出文档集内文档的分级排序。

The learning of Backpropagation Neural Network ( BPNN ) aimed at lowering the classification error , usually assuming that all the samples had equal price when misclassifications were made .

传统的反向传播神经网络（BPNN）学习以分类错误最小为目标，通常假定在分类错误时所有样本的代价完全相同。

A prediction method based on genetic algorithm ( GA ) and back propagation neural network ( BPNN ) was proposed to solve springback problem of sheet metal after air-bending forming and punch design .

为解决金属板材折弯成形的回弹及凸模设计问题，提出了一种基于遗传算法的反向传播神经网络预测方法。

Using the artificial BP neural network ( BPNN ) to primarily establish a predictive model of our center 's recipients to predict posttransplant survival time , and analyzing whether this modeling method had value .

应用人工BP神经网络初步建立本中心移植受体术后生存期评估模型，判断该方法是否具有应用价值。

An algorithm based on surface EMG signals was proposed by the combination of power spectral coefficient with BP neural networks ( BPNN ), to implement multi-pattern recognition of surface electromyography ( SEMG ) .

结合功率谱比值法和BP神经网络提出一种基于表面肌电信号（EMG）的多运动模式识别算法。

Momentum factor and nonlinear sensitivity factor was introduced in the modified back propagation neural network ( BPNN ) algorithm . The nonlinear sensitivity factor was adjusted according to the change of the integral deviation in the development .

针对传统误差反向传播神经网络（BPNN）的不足，在改进误差反向传播算法中引入了动量因子和非线性敏感度因子，实现了在学习过程中根据整体误差梯度变化对非线性敏感度因子进行动态调整。

To recognize isolated words in noisy environments , A new robust recognition model with dual recognition procedures based on continuous Hidden Markov Models ( CHMM ) and BP neural networks ( BPNN ) is presented .

论文提出了一种连续隐Markov模型和BP神经网络相结合的、具有两次辨识过程的抗噪孤立字识别模型。

The comparison indicates that the GRNN is superior in prediction of a time series to the BPNN , and a satisfactory prediction can be still made by the GRNN even with sparse sample data .

结果表明，该网络的预测性能优于后者，即使样本数据稀少，也能获得满意的预测结果。

In general speaking , for the remote sensing classification of Multi-temporal Images , OOC is the best , BPNN and SAM is better , MLC and CAC are the worst .

上述分析可见，它们对遥感分类处理多时相影像识别算法的适用性选取有一定参考意义。

First , the initialized weights and threshold of BP neural network ( BPNN ) was optimized with GA , and the network was trained by modifying the weights and threshold in the negative gradient direction .

以GA优化BP网络的初始权值和阈值，按负梯度方向修正网络权值及阈值，对网络进行训练。

A novel model based on Bayesian neural networks for prediction of protein secondary structure is provided and a comparison of the performance of Bayesian neural networks ( BNN ) with traditional BP neural networks ( BPNN ) is made .

提出了一种新的基于贝叶斯神经网络（BNN）的蛋白质二级结构预测方法。