Using BP Neural Network to Determine the Membership Function of the Input of Fuzzy Control System

While design the fuzzy controller, it is very important to determine the membership function of fuzzy variables.The data can be broadly classified as fuzzy sets by using the classification property of the BP neural network. The author selects a BP neural network with one hide layer and uses S function to the input and hide layer, and linear function to the output layer.Advanced BP algorithm isused to train the BP neural network in the environment of MATLAB . The nearer to the target values is the better the last output is.With the trained BP network , the membership values of the inputs can be got ten. This method has high rate and low error.     

BP神经网络在储粮害虫分类中的应用研究

综合利用计算机视觉技术和BP神经网络技术,实现对粮仓害虫的无损检测.通过对粮仓害虫图像的CCD图像预处理,获取了几何特征和不变矩等15个特征参数,并通过优化选取其中七个参数输入神经网络进行训练.仿真结果表明训练网络对粮仓四类常见害虫的识别率达到了85%,得到了较好的识别结果.     

The Software Implementation of Neural Network Fuzzy Inference Cooperation System

This poper sets up a new Neural Network Fuzzy inference Cooperation system which is based on fuzzy inference principle in Expert Systems,take advantage of the powerful learning function, the little sensitivity to input layer's samples,and the fast convergence and so on in FCBP and take advantage of the good sort property and good suit property to fuzzy value in MFART Network.     

基于近红外光谱的小麦品质分类研究

为了快速、简便、准确地鉴别小麦品质的类别,本研究提出了应用近红外光谱分析技术结合BP神经网络的鉴别方法对小麦进行品质分类。研究过程中对小麦样品的光谱数据进行了详细分析,采用马氏距离剔除了光谱数据中异常数据,并通过主成分分析说明利用近红外光谱鉴别小麦品质分类的可行性。为了提高所建模型的性能,采用SPXY算法对小麦样品进行合理的划分。并选取了一阶微分加归一化的预处理方法来处理光谱数据,消除无关信息和噪声对小麦光谱数据的影响。运用偏最小二乘法压缩光谱数据,减少了数据量,节省建模时间。最后采用BP神经网络方法建立了小麦品质分类模型。实验结果显示：模型的鉴别效果较好,对强筋样品识别的准确率高达94.4%,弱筋样品识别的准确率高达100%。实现了快速、准确地对小麦品质强筋和弱筋两类的鉴别,对小麦生产、市场交易及食品加工有着非常重要的意义。     

Fuzzy Backpropagation Algorithms and Their Convergence

The equivalence between fuzzy neural networks model for max-min fuzzy operator and S.Stoeva's is proved by studying the fuzzy neural networks model for max-min fuzzy based on S.Stoeva's.Then the paper proposes the fuzzy backpropagation learning algorithms for changing fuzzy power and probes their convergence properties.Finally,it simulates experiment such as state monitoring of turbo-generator set.The results show that the fuzzy backpropagation learning algorithms presented are convergent on condition that the output of training sample is between maximum and minimum of its input.     

The Application of Fuzzy Neural Network in the Detection for Moving Object

A fuzzy neural network(FNN) of detection for moving object based on BP algorithm is described in this paper.The correctness of the FNN in signal detection for moving object and fault diagnosis for instrument is proved by experiments.     

基于人工神经网络理论的土壤水分预测研究

土壤水分含量是影响作物生长的重要因素,精确的预测技术对水资源的合理利用与管理具有重要的指导意义。利用人工神经网络理论,建立了以降水量、蒸发量、相对湿度和地下水埋深为输入因子,土壤水分含量为输出因子的预测模型,并对其预测精度进行了评价。结果表明,BP神经网络模型预测土壤含水率的最大误差为8.66%,平均误差为4.27%,预测精度达到0.989。模型具有较高的预测精度,其结果可为制定合理的水资源调配方案和调度计划提供科学依据。     

Cost Estimation of Transmission Line Based on Artificial Neural Network

Based on the structure of cost factor in transmission lines project and the characteristic of neural networks, the paper shows up using artificial neural networks to estimate the cost of project and provide a method to investigate them. By analyzing the structure of project cost and influence factor, the paper builds both input and output neural cell for cost of transmission line project. The paper builds the model of artificial neural networks and exports the steps of the algorithmic. The project sample is used in history to train and test the model. At last, the model gets satisfactory result and meets the investigation requirement of engineering budgetary estimation. Therefore, the paper provides an impersonality and quick investigation method for budgetary estimation of power projects.     

土壤含水率与像素颜色之间关系的BP人工神经网络模型

建立像素颜色RGB值与土壤含水率之间的数学关系,是染色入渗法的应用基础。结合沟灌染色入渗试验。研究了染色入渗过程中土壤含水率与像素颜色分量之间关系的BP人工神经网络模型。分析土壤含水率与像素颜色分量之间的关系,确定BP人工神经网络的拓扑结构,以像素颜色分量的相对值作为输入因子。土壤含水率作为输出因子,建立了包含1个隐层的BP人工神经网络。结果表明,该模型具有较高的拟合精度和验证精度,优于二次多项式模型。     

多种分类器在农用地分等中的应用及其用法改良

以广东省第二次土壤普查成果资料为主要数据源,选取贝叶斯决策、BP神经网络、概率神经网络、聚类等分类方法分别对数据源进行分类;并且,笔者为了充分利用有监督学习分类准确率高和无监督学习无需标定的学习样本的优点,提出了基于监督--非监督的聚类算法,然后对上述五种方法的评价结果作了比较分析;实验表明文章提出的基于监督--非监督聚类方法只利用少量的有标定学习样本,即可得到较高的分类准确率,特别在少量样本时,该方法能得到比贝叶斯决策方法、BP神经网络和概率神经网络等监督学习方法更好的土地评价结果;在实际应用中,可以尝试结合监督和非监督学习的方法,实现分类正确率和获取大量有类标签的样本之间的折中。     

Application of soft sensor in the on line measurement of theiron ore’s surface temperature

It is difficult to measure the surface temperature of iron ore directly. A method is put forward to handle this problem by using soft sensing technique. This on line measurement method is used to replace the Lagrange interpolation off line method to estimate surface temperature. The method used L M optimum algorithm to build up ANN soft sensor model combined with off line learning neural network to establish the correlation between input variables and target variables, to achieve the surface temperature on line detection. The results of simulation and experimentation indicate that the method is reasonable and feasible.     

Application of Revised BP -NN Method to Landslide Stability Analysis in the Three Gorges Area

Using the revised BP-NN,this paper presented the neural network method for landslide stability analysis in the Three Gorges area.By choosing 30 typical landslides in this area as examples,the stability state estimated by the revised BP-NN method is highly consistent to that by conventional transfer coefficient method.And the method presented in this paper has following advantages:the input parameters are easily obtained and this method does not deeply rely on investigation quality and shear strength parameters of slips and is a quite simple one.The BP-NN method is a new measure to stability analysis of landslides in the Three Gorges area,which is especially suitable to the stability prediction of landslides before investigation.     

Fuzzy Control and Simulation of Regulating System for Permanent Magnet Synchronous Motor

This paper researches the fuzzy control and simulation of regulating system for PMSM in electrical vehicle. The mathematics model is set up.The PMSM,the PMSM measures demux, dq to abc converter and the three phrase PWM converter models are set up in MATLAB/ Simulink. The fuzzy controller is designed with two dimension fuzzy design method, and take E and EC as input variable, U is the output variable. According to the controller and models, the fuzzy control model of regulating system for PMSM is created in matlab/simulink. At last, to test the accuracy of the control method with the simulation result.     

Fuzzy Identification on Mathematical Model of Dynamic Process of Evaporator in Refrigeration System

Founding the mathematic model of refrigeration system's dynamic process is the basis of realizing the optimal control of refrigeration machines.Refrigeration evaporator is a kind of two-phase flow and heat exchange with complex process.For its obvious nonlinearity and uncertainty,it is difficult to describe by accurate theoretical model.This paper partitions the input data into some clusters by entropy method and competitive learning algorithm,then the on-line fuzzy identification of dynamic process mathematical model of evaporator is achieved by utilizing ultimate parameter which is ascertained by the recursive least-square(RLS).The simulation results show that fuzzy identification method is effective for on-line model process of evaporator in refrigeration system.The model has not only superior identification precise,but also quite perfect generalizable performance and traceable ability.     

基于软X-射线造影和机器智能的玉米种子活力检测方法研究

为了提高玉米单产,在播种之前对种子活力进行检测十分必要。提出一种将传统的软X-射线检测方法与计算机智能识别相结合的新方法。首先建立corn_pixel结构,然后通过确定种子尖端位置和形心建立种胚区域的椭圆不等式对种胚区域进行标识。以椭圆短半轴b及种胚区域渗钡像素比率M1/M和非种胚区域渗钡像素比率K1/K为输入特征,以标准发芽试验结果为输出,建立BP神经网络单粒种子活力识别模型。结果表明,当b=2CD/5时,识别的准确率最高,以该b值为依据进行分组试验的平均准确率可达95%以上。     

A fuzzy logic multicasting algorithm for ad hoc networks

To increase the multicasting efficiency of Ad hoc networks, a fuzzy logic multicasting algorithm (FLMA) is proposed. FLMA adopts the fuzzy logic to tolerate the imprecise information caused by dynamic network topology. The two input variables of the fuzzy logic system are the relative degree of the additional coverage node number and the relative degree of the residual energy. The deferring time of rebroadcast is the output variable of the fuzzy logic system, which is used to optimize the priority of the nodes to rebroadcast. FLMA reduces the redundant retransmission and the chance of the contention and collision, while balances the energy consumption of the nodes. Simulation results reveal that the FLMA achieves better performance than BCAST in terms of the network lifetime, average end-to-end delay, the average number of drops per node and the throughput.     

A data selection method applied to on-line drift compensation for gas sensors

A new data culling and labeling method is proposed to avoid misleading outcomes caused by multi-state samples during drift compensation process. This method culls data by the curve slops of gas sensor array response and labels data by comparing input samples with the memories of pattern recognition algorithm to avoid occurrence of misleading results. Experiments show the method combined with on-line drift compensation algorithm can estimate sample-states automatically and increase the recognizing accuracy from 37.5% to 100%.     

鲜香菇外部品质计算机视觉检测与分级研究

根据鲜香菇图像特点和分级标准,运用计算机视觉技术和神经网络算法对香菇进行自动检测与分级。采用掩模去背景、中值滤波、边缘亮度补偿等技术对图像进行处理。选取香菇菇盖最大直径、圆形度、色调均值及缺陷区域总面积与香菇图像总面积的比值作为鲜香菇分级的特征参数。通过BP神经网络建立了特征参数与鲜香菇等级之间的关系模型,试验结果表明,其预测识别结果达到94.2%。     

Application of BP Neural Networks in Inventory Dynamic Modeling

The authors establish an original inventory model based on BP neural networks in dynamic environment using the inventory history data, and overcome the net overfitting problem occurred with insufficient samples by using early stopping method. After a simple-relation inventory model training is attained, they get inventory model and analyze it dynamically by reconstructing the model after getting new sample data. An example is provided to illustrate the model. The theoretical evidence is provided for the inventory system to make management decision.