三自由度直升机模型自适应神经模糊控制

针对三自由度直升机模型的稳定运行控制问题,根据各个自由度运动特性,采用牛顿力学原理,建立了直升机系统的数学模型.采用自适应神经模糊算法对模型进行控制,通过编写MATLAB的M文件和应用ANFIS工具箱结合simulink对控制效果进行仿真,得到仿真曲线,对比模型原厂自带PID控制器的控制效果,神经模糊控制俯仰轴调整时间缩短,超调降低,结果验证了自适应模糊神经算法在三自由度直升机模型的稳定运行控制问题上是有效可行的.     

基于ANFIS的蓄冷系统模糊控制设计

目的 研究蓄冷系统模糊控制,缓解电力生产和供应,减少城市烟尘和二氧化碳CO2的排放.方法 引入ANFIS的"高木-关野(Takagi-Sugeno)"模型进行冰蓄冷系统模糊控制器设计.应用自适应神经模糊控制模型原理,建立了蓄冷量自适应神经模糊控制模型.结果 利用减法聚类进行初始化后,形成输入载冷剂进口温度,载冷剂流速,蓄冷时间和输出蓄冷量之间的控制关系,蓄冷量模糊控制器的控制过程比较平稳,控制过程收敛性能都比较好,比较符合实际的运行情况,训练均方根误差最小为3.042 88×10-4.结论 解决了因冷负荷过大出现蓄冰装置释冷提前结束而不得不启用制冷机组的问题.     

发电用重型燃气轮机的模糊自适应控制

为了克服传统PI控制器的不足，满足燃气轮机对高品质控制性能的要求，对常规PI控制算法进行分析，找出了常规PI控制器不能获得最佳控制效果的原因．同时通过对模糊自适应控制的原理和燃气轮机运行过程的分析，并结合专家经验得出燃气轮机模糊PI控制规律，设计出了透平转速和燃气轮机排气温度的模糊自适应PI控制器．仿真试验结果证实模糊自适应控制器可以提高燃气轮机的性能，而且实现方便——只要在原系统上增加一个微处理器，完成模糊计算即可．     

基于ANFIS的三容系统解耦及液位控制

利用模糊减法聚类技术,建立初始的模糊推理系统(FIS)结构,然后利用自适应神经模糊推理系统(ANFIS)函数对模糊模型进行训练,得出模糊神经网络解耦控制块.实现了对三容系统的解耦及液位控制.利用Matlab仿真工具,对自适应模糊神经网络解耦控制系统进行了研究,结果表明,其与传统的输入变换和状态反馈解耦控制相比,动态响应快,鲁棒性好,具有优异的性能.     

基于ANFIS的电力通信网的可靠性评估

根据以往电力通信网可靠性评估方法,对电力通信网可靠性相关指标进行整理,采用自适应神经模糊推理系统(Adaptive Neural Fuzzy Inference System,ANFIS)构建了电力通信网可靠性评估模型.以MATLAB为工具,利用ANFIS的模糊工具实现了模糊神经推理过程,并经过系统仿真得到结果,通过与神经网络、贝叶斯网络、蒙特卡洛算法结果进行比较,此模型具有更高的准确性.     

基于自适应模糊系统的径向基高斯函数网络系统辨识方法

提出了一种基于自适应模糊系统的径向基高斯函数系统辨识方法,与传统的系统辨识和仿真方法相比,更具有精确性与智能性。RBF(radial basedfunction)网络在逼近能力、分类能力和学习速度上均有优势。自适应神经模糊推理系统(ANFIS)混合学习算法减少了原始纯反向传播算法搜索空间的维数,故收敛速度非常快。根据ANFIS和RBF的特点,将它们结合起来,形成了基于自适应模糊系统的径向基高斯函数网络的系统辨识方法。     

300MW机组主蒸汽温度的模糊控制

本文介绍了建立自适应最优模糊逻辑系统的基本方法。根据300MW机组主蒸汽温度控制结构,构造了控制主蒸汽温度的模糊控制器,并对主蒸汽流量的变化设计了一套模糊预测方法。     

异步电动机的单神经元模糊自适应控制

针对异步电动机矢量控制中PI控制器自适应能力较弱的问题,提出了用单神经元模糊自适应控制器代替转速PI调节器和磁链PI调节器的方法,并基于梯度下降法和单神经元自适应模糊控制原理,将增量式PI控制算法和单神经元自适应学习规则相结合,通过模糊控制修正单神经元的比例系数,提高单神经元模糊自适应控制器参数在线调整能力。为验证单神经元模糊自适应控制器的性能,对系统进行仿真实验。仿真结果表明,采用单神经元模糊自适应控制策略,其控制效果优于传统矢量控制,系统的动态和静态性能比较好,而且控制器对电动机转子电阻变化有较好的鲁棒性。该控制方法具有较好的控制性能,使异步电动机控制系统具有较强的自适应能力。     

基于模糊神经系统的多传感器数据融合算法

将自适应模糊神经推理系统(ANFIS)和卡尔曼滤波器应用于目标跟踪系统中,构成多传感器数据融合算法。该算 法假设在目标运动过程中,过程噪声和测量噪声是相互独立的高斯白噪声序列。使用ANFIS分别对目标的加速度和测量噪声 的方差进行估计,通过卡尔曼滤波器获得目标后验状态,最终由神经网络对多传感数据进行融合得到系统输出。仿真结果表 明,该算法可以通过自适应调整跟踪参数有效地防止目标丢失。     

基于模糊自适应PID的主汽温控制系统

为了改善传统串级PID主汽温度控制系统的控制效果,提出了采用模糊自适应控制器的串级主汽温控方案.主调节器采用模糊自适应PID控制器,副调节器采用传统PID调节器.利用模糊规则,主调节器PID参数可根据误差信号动态调整.仿真结果表明,该系统在机组负荷较大范围变化时,其控制品质优于传统PID串级控制系统.     

Temperature field analysis and adaptive neuro-fuzzy inference system for mgo single crystal production

The temperature field in MgO single crystal furnace is crucial to grow high-purity MgO single crystals with large sizes. In order to build proper temperature gradient, firstly finite element method (FEM) was used to study the temperature field distributions, and then a temperature controller with adaptive neurofuzzy inference system (ANFIS) was developed based on the result of FEM and practical experiences. When the temperature in MgO single crystal furnace was changed, the controller would regulate the positions of threephase electrodes and the voltage of the power simultaneously. The experimental results indicate that using the adaptive neuro-fuzzy control system can improve the quality and the quantity of the MgO single crystal production.     

基于改进算法ANFIS的变压器故障诊断

在分析变压器油中溶解气体进行变压器故障诊断的基础上,提出一种基于改进算法的自适应神经模糊推理系统的变压器绝缘故障诊断方法.该方法使用IEC三比值法的3个气体比值作为ANFIS输入向量,构造三输入一输出的ANFIS,然后使用具有全局收敛性的相关的广义Fletcher-Reeves共轭梯度法改进ANFIS默认的以BP算法和最小二乘法构成的混合学习算法,再使用新的学习算法训练系统.最后,对模型的有效性进行了检验,并与使用BP学习算法训练的诊断结果做了比较.检验结果表明:使用改进算法的ANFIS进行变压器故障诊断是可行的,并且诊断精度有所提高.     

煤矿瓦斯浓度预测的ANFIS方法研究

将时间序列分析方法与自适应神经模糊推理系统（ANFIS）结合，构建煤矿瓦斯浓度的预测模型．根据Takens理论，重构煤矿瓦斯浓度相空间，分别采用互信息法确定相空间时延和假近邻法确定相空间维数；然后在重构相空间中，运用自适应神经模糊推理系统构建煤矿瓦斯浓度的预测模型，并应用混合学习算法整定模型参数．结果表明，得到的模型训练和检验均方根误差分别为0．0214和0．0216，充分体现了ANFIS具有显著的学习能力和良好的泛化能力，同时也表明该预测模型是切实可行的．     

A reversibly used cooling tower with adaptive neuro-fuzzy inference system

An adaptive neuro-fuzzy inference system (ANFIS) for predicting the performance of a reversibly used cooling tower (RUCT) under cross flow conditions as part of a heat pump system for a heating mode in winter was demonstrated. Extensive field experimental work was carried out in order to gather enough data for training and prediction. The statistical methods, such as the correlation coefficient, absolute fraction of variance and root mean square error, were given to compare the predicted and actual values for model validation. The simulation results predicted with the ANFIS can be used to simulate the performance of a reversibly used cooling tower quite accurately. Therefore, the ANFIS approach can reliably be used for forecasting the performance of RUCT.     

Parametric optimization of friction stir welding process of age hardenable aluminum alloys-ANFIS modeling

A comparative approach was performed between the response surface method(RSM) and the adaptive neuro-fuzzy inference system(ANFIS) to enhance the tensile properties, including the ultimate tensile strength and the tensile elongation, of friction stir welded age hardenable AA6061 and AA2024 aluminum alloys. The effects of the welding parameters, namely the tool rotational speed, welding speed, axial load and pin profile, on the ultimate tensile strength and the tensile elongation were analyzed using a three-level, four-factor Box-Behnken experimental design. The developed design was utilized to train the ANFIS models. The predictive capabilities of RSM and ANFIS were compared based on the root mean square error, the mean absolute error, and the correlation coefficient based on the obtained data set. The results demonstrate that the developed ANFIS models are more effective than the RSM model.     

Estimation of Loose Status of Jigging Bed Based on Adaptive Neuro-Fuzzy Inference System

In the separation process with a jig washer, an accurate on-line measurement of loose status of a jigging bed is essential for a successful control of coal quality and loose status is difficult to measure on-line directly in industrial process situations. So a soft-sensor technology is needed for this purpose. The soft-sensor model is developed in the experiment by an adaptive neuro-fuzzy inference system （ANFIS） which has a remarkable ability of learning and generalization. Based on the analysis of the technologic mechanism of jigging bed, the structure of the ANFIS is established to build the soft-sensor model of loose status estimation. The ANFIS is trained by a hybrid learning algorithm. Finally, the simulation results and comparison analysis are presented, which indicate that the ANFIS has better abilities of learning and generalization than the RBF and the BP networks. Thus, it is possible that the loose status of the jigging bed can be estimated on-line bv using ANFIS.     

跳汰机床层松散状况软测量建模方法研究

应用人工智能的方法建立了跳汰机床层松散状况的软测量模型，该软测量模型的建立分2步完成：首先根据工业现场的操作经验和化验分析结果，应用跳汰机分选效果主要指标（不完善度和错配物总量）与床层松散状况的关系建立模糊推理系统（FIS）模型，实现跳汰机床层松散状况的离线评价；然后根据浮标传感器的输出与跳汰机床层松散的关系以及跳汰机床层松散状况的离线评价结果，建立基于自适应神经模糊推理系统（ANFIS）的跳汰机床层松散状况的在线估计模型．实验得到软测量模型的训练均方根误差为0．0147，验证均方根误差为0．0214，充分体现ANFIS具有显著的学习能力和良好的泛化能力．     

煤矿巷道围岩松动圈智能预测研究

针对煤矿巷道围岩松动圈厚度值获取难的问题，采用新兴的智能预测方法(自适应神经模糊推理)，在MATLAB6．5平台上开发了集松动圈预测系统创建和应用于一体的智能预测软件．利用该软件对平煤集团十二矿巷道围岩松动圈厚度进行预测，然后与实测值对比，结果显示预测结果与实测值吻合较好，从而验证了本创建的智能预测系统的有效性，它为松动圈值的获取提供了一条新途径。     

Development and Application of Intelligent Prediction Software for Broken Rock Zone Thickness of Drifts

In order to seek the economical, practical and effective method of obtaining the thickness of broken rock zone, an emerging intelligent prediction method with adaptive neuro-fuzzy inference system (ANFIS) was introduced into the thickness prediction. And the software with functions of creating and applying prediction systems was developed on the platform of MATLAB6.5. The software was used to predict the broken rock zone thickness of drifts at Liangbei coal mine, Xinlong Company of Coal Industry in Xuchang city of Henan province. The results show that the predicted values accord well with the in situ measured ones. Thereby the validity of the software is validated and it provides a new approach to obtaining the broken zone thickness.     

Calculation of maximum surface settlement induced by EPB shield tunnelling and introducing most effective parameter

This study aims to predict ground surface settlement due to shallow tunneling and introduce the most affecting parameters on this phenomenon.Based on data collected from Shanghai LRT Line 2 project undertaken by TBM-EPB method,this research has considered the tunnel's geometric,strength,and operational factors as the dependent variables.At first,multiple regression(MR) method was used to propose equations based on various parameters.The results indicated the dependency of surface settlement on many parameters so that the interactions among different parameters make it impossible to use MR method as it leads to equations of poor accuracy.As such,adaptive neuro-fuzzy inference system(ANFIS),was used to evaluate its capabilities in terms of predicting surface settlement.Among generated ANFIS models,the model with all input parameters considered produced the best prediction,so as its associated R~2 in the test phase was obtained to be 0.957.The equations and models in which operational factors were taken into consideration gave better prediction results indicating larger relative effect of such factors.For sensitivity analysis of ANFIS model,cosine amplitude method(CAM) was employed; among other dependent variables,fill factor of grouting(n) and grouting pressure(P) were identified as the most affecting parameters.