基于模糊神经网络控制的电液系统研究

针对大功率电液伺服系统存在严重非线性和时变性,将神经网络与模糊控制理论相结合,根据系统的误差及误差变化对神经网络的学习速率和动量因子进行模糊修正,有效地改善了神经网络的学习速率.实验表明,所设计的神经网络控制器能够保证大功率电液伺服系统的静、动态性能.     

基于神经网络的模糊控制器在变量泵中的应用

本文根据变量泵的具体情况,为其了自适应的神经网络模糊控制变量泵的智能控制。     

基于模糊神经网络的故障诊断方法研究

文章构造了一种模糊神经网络模型,并详细阐述了模糊神经网络(FNN)的结构、算法.经过MATLAB仿真运行证明其可行性,另外在相同的条件下,FNN网络在故障诊断的准确率及训练速度方面均优于传统的BP网络.     

基于遗传算法的模糊神经网络控制器在GTAW中的应用

GTAW(钨极气体保护电弧焊)是一种能够很好控制线能量，进行高质量薄板焊接的方法。焊接过程是一个复杂的、多参数耦合的高度的非线性系统，在实际焊接过程中难以实现实时、有效的在线控制。模糊控制吸收了人的经验思维的特点；神经网络则对信息的处理具有自组织、自学习的特点；遗传算法是一种全局优化搜索方法，具有简单通用、普遍性强，适合并行处理和应用范围广的优点。作者将三者有机地结合起来，在模糊神经网络控制器的基础上利用了改进的遗传算法，并分析了其网络结构和离线学习的方法，协调利用三者的优势设计了一种新型的模糊控制器，并使之用于脉冲GTAW仿真中，结果证明了该新型模糊神经网络控制器比传统的模糊控制器具有一定的优越性。     

基于补偿模糊神经网络的数控机床热误差预报模型

文章提出了一种基于补偿模糊神经网络的数控机床热误差预报模型,讨论了该模型的详细结构、模糊规则、训练算法及相关技术问题,并给出了智能预报结果和精度评价.     

模糊逻辑和神经网络在传动领域中的应用

本文首先分析了人工智能技术中的模糊逻辑和神经网络各自的原理方法及应用，它们的应用已遍及工业制造、家电生产、电力系统等部门和领域，最后简单介绍了模糊神经网络的特点和发展。     

基于遗传算法的间接自校正模糊神经网络控制

针对一般神经网络训练算法训练速度慢和易陷入局部极小点的不足,文章提出了一种基于模糊神经网络的间接自校正控制系统,控制器是以高斯函数为隶属度函数的径向基函数(RBF)神经网络结构,利用改进的遗传算法(GA)对结构和参数进行同步优化.神经网络模型(NNP)利用弹性BP算法进行离线辨识.仿真与传统的模糊PID控制器控制进行比较,结果表明遗传算法大大改善了系统的性能.     

TIG焊背面熔宽的神经网络模糊控制

TIG（Tungsten Inert Gas)焊接过程是一个高度非线性、强耦合、时变的系统,针对这一特点,本文设计了单层神经网络模糊控制器,给出了学习算法,该控制器可以自动学习模糊控制规则,并随系统的变化自动调节模糊控制规则,采用普通CCD（Charged Couple Device)摄像机拍摄熔池的正面图像,提取出熔池正面几何参数,利用熔池正面几何参数与背面熔宽的关系模型,对背面熔宽进行实时控制。仿真及试验结果表明,该控制器具有良好的控制性能和控制效果。     

基于神经网络的模糊可靠性分配

可靠性分配有许多方法，随着掌握的可靠性资料的多少，设计阶段以及目标和限制条件不同而不同，本文提出一种基于神经网络的模糊可靠性分配方法，它有效地利用了设计专家的知识和已有的设计数据，适合于设计条件不很明确时对可靠性进行粗略分配。     

基于模糊神经网络的注塑制品缺陷分析诊断

在对注射成形过程的各种不确定性因素和模糊性问题深入分析的基础上，运用模糊产生式规则和置信度传递算法，以神经网络获取模糊规则的方式实现了模糊逻辑和神经网络的有机结合，建立了用于注塑制品缺陷分析诊断的模糊神经网络结构模型，并给出了运用模糊神经网络进行制品缺陷分析诊断的过程和方法。     

透镜抛光机床模糊控制的神经网络方法

把模糊技术与神经网络方法相结合,采用五层前馈型神经网络,实现了抛光过程的神经网络模糊控制。应用结果表明,其控制效果明显优于一般Ｆｕｚｚｙ控制。     

On-line tool wear estimation in CNC turning operations using fuzzy neural network model

In recent past, several neural network models which employ cutting forces and AErms or their derivatives for estimation as well as classification of flank wear have been developed. However, a significant variation in mean cutting forces and AErms at the start of cutting operation for similar new tools can result in estimation and classification error. In order to deal with this problem, a new on-line fuzzy neural network (FNN) model is presented in this paper. This model has four parts. The first part of the model is developed to classify tool wear by using fuzzy logic. The second part of this model is designed for normalizing the inputs for the next part. The third part consisting of modified least-square backpropagation neural network is built to estimate flank and crater wear. The development of forth part was done in order to adjust the results of the third part. Several basic and derived parameters including forces, AErms, skew and kurtosis of force bands, as well as the total energy of forces were employed as inputs in order to enhance the accuracy of tool wear prediction. The experimental results indicate that the proposed on-line FNN model has a high accuracy for estimating progressive flank and crater wear with small computational time.     

模糊神经网络技术及其在一类复杂工业过程控制中的应用研究

针对毛纺工艺侧吹风的温、湿度控制系统的非线性特点设计了一种模糊神经网络控制器,并将其应用到毛纺车间中,实现了对生产车间的温度的精确控制.最后,用MATLAB和C语言做了仿真,结果令人满意.     

Tool wear detection with fuzzy classification and wavelet fuzzy neural network

In the paper, a new method of tool wear detection with cutting conditions and detected signals is presented, which includes the model of wavelet fuzzy neural network with acoustic emission (AE) and the model of fuzzy classification with motor current. The results of tool wear estimated by cutting conditions and detected signals (spindle motor current, feed motor current and AE) are fused by fuzzy inference. Experimental results show that the method of tool wear detection is reliable and practical.     

基于神经的数控加工热误差补偿

本文提出了一种基于神经网络的数控加工热误差补偿系统，该系统根据测出的数控加工机床的相关结构的温度值，进行实时地热误差补偿，介绍了该方法的原理，阐述了该系统的建立过程及有关技术的处理。     

PWM逆变器残余误差的神经网络消除方法

在分析现有PWM逆变器控制技术的基础上,讨论了单相PWM逆变器残余误差产生的机理,构造出单相PWM逆变器残余误差的神经网络消除模型,论述了神经网络训练样本拾取方法。该控制方法能有效地提高PWM逆变器的输出精度.     

Neural network analysis for corrosion of steel in concrete

Corrosion of the steel embedded in concrete plays a vital role in the determination of life and durability of the concrete structures. Several researchers have studied the corrosion behaviour of the embedded steel and the different types of protective measures that are available to control the corrosion. However, little work has been done to recognize, identify the performance and predict the behaviour of the steel over a long term. Hence, this work concentrates on recognizing the behavioural pattern of the embedded steel and predicting its potential characteristics using artificial neural network (since the potential of the embedded steel is used to determine whether the steel is corroding or not as per ASTM C 876-91).A systematic study to develop a suitable method that can accept, analyze and evaluate experimental data that are at random and/or influenced by external, unpredictable variables has been carried out, using the back propagation method. This method is fast and is able to produce an output that has minimum error for this experimental setup. This has resulted in the development of back propagation neural network, that can train and test the system, to calculate the specified parameter for different conditions and recognize the behavioural pattern. Using this methodology, the corrosion of the steel embedded in concrete is analyzed and it is observed that the error encountered is only about 5% for the predictions made from the analysis.