反向传播

• 2 . research on learning control with distal teacher of chaotic dynamical system . analyzed the characters , limitations and application of bp nn , prompted a kind of unproved method , that is additive - momentum - method bp nn
  从系统辨识的角度分析了反向传播神经网络在系统辨识过程中的特点、存在的缺陷及其应用，并对其进行了改进，进一步提出了附加动量法的自适应反向传播神经网络算法。
• Based on the test data of 61 steel reinforced concrete columns , a model with 5 input layers , 6 implicit layers and 1 output layer ( 5 - 6 - 1 ) is developed to analyze the influence of various parameters on displacement ductility by the principle of back propagation ( bp ) neural network
  摘要通过对61根型钢混凝土柱试验数据的整理，利用神经网络原理建立5 - 6 - 1型反向传播( bp )神经网络模型，分析不同参数对型钢混凝土柱位移延性系数的影响。
• Proposed a kind of method that is improved back propagation neural network . a neural network controller is designed . the tracking control of hybrid system is realized by model prediction and feedback correct of neural network control
  改进了传统的反向传播神经网络，提出附加动量法的自适应反向传播神经网络算法，并设计了混杂系统的神经网络控制器， ‘通过神经网络控制的模型预测与反馈校正构成闭环控制系统，实现了混杂系统的跟踪控制。
• Secondly , binary probability hypothesis detection is studied and is utilized as actuators " fdi residual decision . thirdly , multi - layer feed - forward ann and error backward propagation ( bp ) algorithm are studied and are utilized as control surfaces " failure detection and sortation
  第三，研究多层前馈神经网络及相应的bp ( errorbackwardpropagation误差反向传播)算法，设计基于模型残差的故障分类器，并通过其来完成全局舵面的故障检测与分类。
• The intelligent fault diagnosis based on bp ann is designed for recognition of leakage fault of a rolling piston radial pump . it combines with the predominance of diagnosis methods based on mathematic model and artificial intelligence , and it is achieved through software on personal computer
  对柱塞泵泄漏故障诊断，设计了基于反向传播神经网络的智能诊断系统，综合了基于数学模型和非模型的诊断方法的优点，用软件的方法在个人机上得以实现。
• Some developed bp algorithms which were simulated and compared using computer seperately are also presented , ann learning algorithm in this paper is constructed on the basis of the goodness of all above algorithms which is suitable for the identification of typical fault mode
  同时，对神经网络的主要学习算法之一的反向传播算法( bp算法)进行了深入的研究，通过对几种改进算法的模拟实现和对比综合，构造了适合于对箱式变电站典型故障进行识别的学习算法。
• Using the back - propagation artificial neural networks which have the satisfactory nonlinear prediction ability , the correlation between molecular structures and flash points of fatty alcohols was studied with molecular structure descriptors as input parameters and flash point as output one
  同时引入具有高度非线性预测能力的误差反向传播人工神经网络方法，以分子结构描述符作为神经网络的输入参数，闪点作为输出，研究脂肪醇的闪点与分子结构之间的相关性。
• An indirect self - adaptive fuzzy - neural network controller ( fnnc ) has been proposed with its parameters and the structure tuned simultaneously by ga in virtue of the powerful optimization property of ga . the structure of the controller is based on the radical basis function ( rbf ) neural network with gaussian membership functions . the performance of the proposed fnnc is compared with a conventional fuzzy - pid controller and the simulation results show that the fnnc presents encouraging advantages
  针对神经网络采用一维反向传播训练算法速度较慢且易于陷入局部极小点的不足，设计了一种间接自校正模糊神经网络控制系统，利用遗传算法( ca )对隶属度函数的结构和参数进行优化，仿真比较表明该控制比模糊pid控制具有更优的性能。
• Abstract : artifical intelligence methods are implemented to simulate thebehaviors of axially and laterally loaded piles using the field observation tests data obtain ed f rom the drilled shafts and driven piles . the optimal neural network model is deve loped using only simple input data of spt - n values and piles ' geometrical featu r es etc . . the analysis for r . c piles of some projects is performed adopting the bp n n and grnn models respectively , and the obtained predicated results are compared w ith the data from conventional design method . it demonstrated the obvious advanta ges of neural networks in the design of pile foundations over the traditional me thods . this paper has an important practical significance and a referential worth iness in the design of pile foundations
  文摘:根据钻孔桩和打击桩的原型试验观测的数据,运用人工智能方法对横向承载桩和轴向承载桩的工作特性进行模拟,并利用标准贯入试验( spt - n )值和桩的几何特性等简单的输入数据,开发出相应的优化神经网络模型;然后,运用反向传播神经网络模型和广义回归神经网络模型分别对某工程的钢筋混凝土桩进行分析,并将求得的预测结果与常规设计法的结果进行比较,结果表明神经网络方法比传统方法有明显的优越性,在实际工程设计中具有重要的参考价值和现实意义。