神经网络在管理中的应用

详细地总结分析了近几年神经网络(NN)在管理领域的应用,探讨了NN应用系统融合的相关技术和相关学科,分析了NN在管理应用中存在的问题及今后的发展趋势.     

神经网络在直接力矩控制中的研究及应用

提出了利用多层神经网络取代传统开关状态选择器在感应电动机直接力矩中的控制以获得最优的开关状态量的方法。利用MATLAB/MULINK软件做的直接力矩控制的仿真系统包括感应电动机、逆变器开关、触发电路和控制电路。在选定了代表开关状态选择器的最优神经网络后 ,设计了神经网络结构图并进行了验证。为了确定神经网络的可靠性和稳定性 ,将其作为直接力矩控制系统的一部分进行了仿真试验 ,结果表明神经网络直接力矩控制系统优于传统的直接力矩控制系统     

基于模糊神经网络的半导体生产线重调度策略优化

针对缺乏半导体生产线重调度策略优化方法的研究现状,提出了基于模糊神经网络的半导体生产线重调度策略优化技术。将重调度策略划分为半导体生产线、设备组和设备重调度层次,利用仿真评价确定优化的重调度策略,并获得样本数据。通过对模糊神经网络训练,建立干扰和半导体生产线状态等输入参数与优化的重调度策略输出之间的映射关系。以上海某125mm晶圆生产线为例,结果表明了该重调度策略优化方法的有效性。     

NONLINEAR MODELING AND CONTROLLING OF ARTIFICIAL MUSCLE SYSTEM USING NEURAL NETWORKS

The pneumatic artificial muscles are widely used in the fields of medical robots, etc. Neuralnetworks are applied to modeling and controlling of artificial muscle system. A single-joint artificialmuscle test system is designed. The recursive prediction error (RPE) algorithm which yields fasterconvergence than back propagation (BP) algorithm is applied to train the neural networks. Therealization of RPE algorithm is given. The difference of modeling of artificial muscles using neuralnetworks with different input nodes and different hidden layer nodes is discussed. On this basis thenonlinear control scheme using neural neworks for artificial muscle system has been introduced. Theexperimental results show that the nonlinear control scheme yields faster response and higher controlaccuracy than the traditional linear control scheme.     

STUDY ON THERMODYNAMIC MODEL OF A COMPRESSOR WITH ARTIFICIAL NEURAL NETWORKS

０ＩＮＴＲＯＤＵＣＴＩＯＮＣｏｍｐｒｅｓｓｏｒｓａｒｅｗｉｄｅｌｙｕｓｅｄｉｎｉｎｄｕｓｔｒｉａｌｆｉｅｌｄｓ,ｓｕｃｈａｓａｉｒｃｏｎｄｉｔｉｏｎｉｎｇ,ｒｅｆｒｉｇｅｒａｔｉｏｎｅｔｃ．．Ｉｔｉｓｏｆｔｅｎｎｅｅｄｅｄｔｏａｓｓｅｓｔｈｅｐｅｒｆ...     

APPLICATION OF ARCHITECTUREBASED NEURAL NETWORKS IN MODELING AND PARAMETER OPTIMIZATION OF HYDRAULIC BUMPER

The dynamic working process of 52SFZ-140-207B type of hydraulic bumper is analyzed. The modeling method using architecture-based neural networks is introduced. Using this modeling method, the dynamic model of the hydraulic bumper is established; Based on this model the structural parameters of the hydraulic bumper are optimized with Genetic algorithm. The result shows that the performance of the dynamic model is close to that of the hydraulic bumper, and the dynamic performance of the hydraulic bumper is improved through parameter optimization.     

直升机自动倾斜器竖向振动的神经网络识别

工程中的许多大型结构中的一些关键部件的振动无法直接测量,因而探索一种间接测量或识别的方法就显得尤为重要。由于直升机飞行状态的复杂性,不但测试困难,而且经典方法处理不理想。文中提出基于BP神经网络方法对直升机自动倾斜器竖向振动进行识别及评估。介绍了网络结构、训练学习过程、试验测试及数据处理过程和识别与估计方法。估计评价的准则主要考虑以估计第一阶谐和频率（6．4Hz)所对应的结果进行比较。由于神经网络方法考虑了不确定性因素,从而估计结果与真实结果相符得较好。最后分析了人工神经网络在用于动力学系统的识别与估计中的多方面问题。     

SURFACE ROUGHNESS PREDICTION USING HYBRID NEURAL NETWORKS

Surface roughness is an important outcome in the machining process and it forms a major part in the manufacturing system. Surface roughness depends on different machining parameters and its prediction and control is a challenge to the researchers. There is a need to predict surface roughness prior to machining to attain higher productivity levels. Owing to advances in computing power there is an increase in the demand for the use of intelligent techniques. Recent research is directed towards hybridization of intelligent techniques to make the best out of each technique. This article proposes the development of a novel hybrid Neural Network (NN) trained with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for the prediction of surface roughness. The proposed hybrid neural network is found to be competent in terms of computational speed and efficiency over the neural network model.     

SURFACE ROUGHNESS PREDICTION USING HYBRID NEURAL NETWORKS

Surface roughness is an important outcome in the machining process and it forms a major part in the manufacturing system. Surface roughness depends on different machining parameters and its prediction and control is a challenge to the researchers. There is a need to predict surface roughness prior to machining to attain higher productivity levels. Owing to advances in computing power there is an increase in the demand for the use of intelligent techniques. Recent research is directed towards hybridization of intelligent techniques to make the best out of each technique. This article proposes the development of a novel hybrid Neural Network (NN) trained with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for the prediction of surface roughness. The proposed hybrid neural network is found to be competent in terms of computational speed and efficiency over the neural network model.     

HIGH-ACCURACY SYNCHRONIZATION CONTROL WITH HYBRID NEURAL NETWORKS

A novel nonlinear control algorithm based on hybrid neural networks is presented to cope with the high-accuracy synchronization control problem for a dual-actuator electrohydraulic drive system which plays an important role for the development of elastomeric launchers. A new objective function for better synchronization performance is introduced and a learning algorithm to adjust the weights of the neural network, based on the gradient descent algorithm, is also derived. The hybrid neural network control algorithm guarantees high-accuracy synchronization performance of two motion cylinders and fast dynamic response as well as good stability of the control system. Prototype test results on the dual-actuator electrohydraulic drive system verifys the effectiveness of the proposed approach.     

基于人工神经网络的机械设计领域知识表达方法的研究

结合人工神经网络技术开展了机械设计领域经验型知识表达方法的研究，提出了一种基于多层神经网络的知识表达方法，该方法适合于数值型经验知识的表达，并对多层神经网络学习的ＢＰ算法进行了改进。     

利用试验模态分析及神经网络技术对结构损伤检测的探讨

选用一工程上常用的截面开口槽形梁,通过试验模态分析对结构损伤引起的模态频率移动进行了分析,从试验角度对四种损伤检测方法进行了有效性比较。并尝试将神经网络与试验模态分析技术相结合应用到结构损伤定量检测的研究中,不仅验证了其可行性,而且指出应变指标对结构损伤更敏感。     

定压网络静液驱动系统神经网络控制的研究

针对定压网络静液传动及其控制系统的特点,提出了对其使用静态神经网络及具有自适应学习率的反传学习算法进行控制,给出了有关的相应结果。     

MULTI-OBJECTIVE OPTIMIZATION OF ABRASIVE FLOW MACHINING PROCESSES USING POLYNOMIAL NEURAL NETWORKS AND GENETIC ALGORITHMS

Abrasive flow machining (AFM) is an economic and effective non-traditional machining technique, which is capable of providing excellent surface finish on difficult to approach regions on a wide range of components. With this method, it has become possible to substitute various time-consuming deburring and polishing operations that had often lead to non-reproducible results. In this paper, group method of data handling (GMDH)-type neural networks and Genetic algorithms (GAs) are first used for modelling of the effects of number of cycles and abrasive concentration on both material removal and surface finish, using some experimentally obtained training and testing data for brass and aluminum. Using such polynomial neural network models obtained, multi-objective GAs (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are then used for Pareto-based optimization of AFM considering two conflicting objectives such as material removal and surface finish. It is shown that some interesting and important relationships as useful optimal design principles involved in the performance of AFM can be discovered by the Pareto-based multi-objective optimization of the obtained polynomial models. Such important optimal principles would not have been obtained without the use of both GMDH-type neural network modelling and multi-objective Pareto optimization approach.     

PROBABILISTIC FAULT IDENTIFICATION USING VIBRATION DATA AND NEURAL NETWORKS

Bayesian formulated neural networks are implemented using hybrid Monte-Carlo method for probabilistic fault identification in structures. Each of the 20 nominally identical cylindrical shells is arbitrarily divided into three substructures. Holes of 10–15 mm diameter are introduced in each of the substructures and vibration data are measured. Modal properties and the coordinate modal assurance criterion (COMAC), with natural-frequency-vector taken as an additional mode, are utilised to train the modal-property-network and the COMAC-network. Modal energies are calculated by determining the integrals of the real and imaginary components of the frequency response functions over bandwidths of 12% of the natural frequencies. The modal energies and the coordinate modal energy assurance criterion (COMEAC) are used to train the modal-energy-network and the COMEAC-network. The average of the modal-property-network and the modal-energy-network as well as the COMAC-network and the COMEAC-network form a modal-energy-modal-property-committee and COMEAC–COMAC-committee, respectively. Both committees are observed to give lower mean square errors and standard deviations than their respective individual methods. The modal-energy- and COMEAC-networks are found to give more accurate fault identification results than the modal-property-network and the COMAC-network, respectively. For classification (the presence or absence of faults) the modal-property-network is found to give the best results, followed by the COMEAC–COMAC-committee. The modal-energies and modal properties are observed to give better identification of faults than the COMEAC and the COMAC data. The main advantage of the Bayesian formulation is that it gives identities of damage and their respective standard deviations.     

基于裂纹闭合解析模型和神经网络理论的疲劳裂纹扩展速率的计算

用裂纹闭合的解析模型作为计算模型,运用神经网络理论对其中的协调方程进行求解,给出了相应的神经网络的结构和参数;对２２１９Ｔ８５１铝合金板材的疲劳裂纹扩展速率的计算进行了数值模拟,与实测结果对比相差很小。计算时间为电路时常数数量级。     

轴承事故的神经网络（ANN）分析

用神经网络分析和模拟轴承事故，分析了基于Ｐｅｔｒｉ网的事故分析的优点和不足。通过构造事故的神经网络，可求出导致顶上事件发生的最小割集和控制事故发生的最小径集，这种分析方法为神经网络在故障诊断中的应用开拓了新的研究思路。     

基于有限元法和神经网络技术的汽车碰撞事故再现

为充分利用事故变形信息,提出采用有限元法和神经网络技术进行事故再现的方法.在该方法中,首先采用数字测量技术得到事故车辆变形关键点的测量值,采用有限元仿真技术得到此关键点的计算值.将事故发生前的车辆运动参数作为神经网络的输入数据,关键点变形量测量值与仿真计算值的偏差作为神经网络的输出数据,将汽车碰撞仿真结果作为网络训练样本,对训练完成的神经网络进行优化求解得到事故发生瞬间的车辆运动参数.应用此方法对一起车-障碍物碰撞事故案例进行再现分析,建立整车、障碍物及地面有限元模型,选取前纵梁及挡泥板上的11个定位孔与螺栓孔作为变形量测量的关键点,再现分析结果验证了该方法的有效性,为事故责任鉴定提供了科学依据.     

基于混合神经网络的门座起重机变幅机构参数优化设计

门座起重机变幅机构优化设计通常采用基于实例推理的方法确定优化设计初始参数,然后再对初始参数进行优化,得出最后的优化设计参数。这种基于实例优化方法的主要问题在于,难于确定相似实例和难于将相似实例应用于当前的实例中,并且由此确定的优化初始参数只偏向于某一个特定的实例,不具备某类实例的普遍特性。提出基于混合神经网络变幅机构优化设计方法,该方法采用一种混合神经网络,可用来确定优化设计的初始参数。这种方法计算上更为简单直观,对于训练好的混合神经网络,可直接由输入参数得到设计初始参数。这种初始参数并带有某类实例的一般特性,对其进行优化可得到较好的优化结果。