Malfunction Diagnosis of Three-phase Full-bridge Controlled Rectifier Based on BP Neural Network

The diagnosis of the power electronic circuit is very intricate. One of the main reasons is that the structure of the circuit will change if the power device is not working .The thyristor is the easiest to be mangled. So diagnosing the malfunction is the most important about the diagnosis of the power electronic circuit. The paper puts forward a malfunction diagnosis of the thyristors of three-phase full-bridge controlled rectifier with BP neural network. After analyzing the output waveforms of malfunctioning circuit and training a BP neural network with the sampling data of malfunctioning waveforms, a well training BP neural network is constructed and used to diagnose the malfunction. The simulation and experiment demonstrate that this method is valid.     

The Study on the Branched Feedforward Neural Network

Based on the BP algorithm,the Branched Feedforward Neural Network,one ofthe artificial neural network medel used for pattern classification is proposed in this paper, and therelated algorithm is also offered here, Several typical examples of pattern classification are studiedwith computer simulation, The simulation results show that the training time of Branched Feedforward Neural Network is obviously reduced and the classifying effect is much better as compared withgeneral BP Network.     

Design and Realization of Video Consultation Classroom Based on IP Network

How to make use of computer network in teaching becomes the focus of concern for the computer engineers and teachers.The remote video consultation classroom can be used in teaching by using internet and NGN server to improve the instruction and stimulate the students' interest in study.As the IP network is widely used in campus,connection could be set up for student dormitory,office or even the teacher's home.On the computer network teacher and student can discuss face to face online and make best use of their time.This paper discusses the problem about how to construct a network-video class room based on computer network including VOIP and NGN(new generation network) switch server.     

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%。     

Fault diagnosis of rotating machinery based on self-learning fuzzy spiking neural network

For fuzziness classific boundry of fault diagnosis of rotating machinery and traditional neural network algorithms difficulted to solve contradiction between application problems example scale and netwok scale,a methord of self-learning fuzzy spiking neural network is put forward. The methord overcomes unavailability of cluster analysis on classific boundry of fault diagnosis of rotating machinery by species encoding of pulse sequence and unsupervised learning. The method shows that it effectively solves boundary fuzziness problem on fault diagnosis of rotating machinery,and greatly improves efficiency of fault diagnosis.     

Inteligent Agricultural Information Network and Service System

The scheme and practice for construct of intelligent agricultural information network are descibed . With Internet form, we set up the computer network of Intelligent Information Technology of Agriculture in Demonstration Section of Chongqing, discussed the design method of expert system in agriculture, and studied 5 expert systems based on vegetable growth, such as tomato and so on. Some software modules are studied, such as the soil information systems on the network, expert system in the vegetable plant diseases and insect pests diagnostician and network on line selling and so on. The structure,function and work flow of information service system based network are introduced.     

Study of Intelligent Fault Diagnostic System for a Kind of Power Plant

Based on the neural networks, object oriented technique, artificial intelligence technique and computer networks, an intelligent fault diagnosis system of the power plant whose need of the operation is presented. The architecture of software system , hardware system and corresponding databases is designed. The software of collecting data is established. The intelligent fault diagnosis system based on neural networks and object oriented technique is also developed. The physical system operation has been shown that the method mentioned above is feasible and effective in practice.     

基于深度卷积神经网络的储粮害虫图像识别

[目的]为了防治储粮害虫带来的危害,借助计算机对储粮害虫进行有效的图像识别是具有重要意义的。[方法]针对基于图像的储粮害虫多分类识别问题,引入了基于深度卷积神经网络的储粮害虫图像识别方法。该方法与传统的储粮害虫识别方法相比,大幅度简化了数据预处理过程,[结果]同时该方法在识别精确度方面达到了97.61%,也明显优于传统方法。[结论]因此基于深度卷积神经网络的储粮害虫识别方法具有较高的实用性,且具有进一步研究和推广的意义。     

农业大棚嵌入式无线温控系统设计

为了有效实施农业大棚温度动态实时监控,提出采用Zigbee无线网络和Linux嵌入式操作系统设计大棚温度监控系统。系统采用C/S结构设计,分为下位机和上位机2部分。下位机系统分为温度采集节点和汇聚节点,温度采集节点完成大棚内不同地点的温度信息采集和无线数据传输功能;汇聚节点除了完成数据中继任务外,还可根据上位机反馈的控制指令完成排风扇的打开或电热系统的开启工作;服务器端的上位机系统完成数据的储存和分析,并根据分析结果完成对下位机系统的实时控制。实践证明,该系统可精确监控大棚温度,有效降低布线成本,有助于降低劳动成本和提高农作物产量。     

Modeling and control system simulation of automobile DCT

In order to reduce development time and cost of dual clutch automated mechanical transmission(DCT) control system,the dynamic model of automobile DCT control system is established by Matlab/SimDriveLine and the engine model is improved by neural network.Based on Matlab/Simulink,the simulation models of DCT control during starting phase,shift phase and shift rule are set up,and then the whole system of DCT is simulated.The simulation result indicates that the DCT system dynamic model and the designed controller are reasonable and feasible,and proofs that the model is suitable for developing DCT control system and improves the design efficiency of DCT system.     

Speed Estimation Methods Based on Neural Network

In order to solve the speed estimation problems of speed sensorless vector-controlled induction motor drives, the paper presents two speed estimation schemes based on neural network mode identification theory. The advantages of each scheme are discussed and the simulation results show that the estimated speed can trace the actual speed better (even under the circumstances of load variation or speed step variation). Also, these schemes are not sensitive to the variations of motor parameters and the effect of iron loss. Therefore, the proposed neural network based on speed sensorless vector-controlled induction motor drives have good performance in stady-state and transient-state operation.     

Calculation Model Based on Improved BP Network of Refrigerant State Parameters

BP network is improved by using Levenberg-Marquardt optimization method. Under large swatch input circumstance, more fast network constringency speed and more highly approach precision are obtained. Calculation model based on improved BP neural network of refrigerant state parameters is established. The main defect of refrigerant hot ties of matter model in existing refrigeration and air-conditioning appliances simulation system is overcome.     

A METHOD OF FILE TRANSFER AND CODE CONVERSION FOR THE DIFFERENT KINDS OF COMPUTERS

The interconnection of different kinds of computers is the main evalution direction of modern computer network. Sharing the data file is one of the target of implementing network interconnection. The paper wants to discuss how to rapidly transfer various files after implementing interconnection between the different kinds of computers and give a detailed implementing principle for file transfer and code conversion.     

Software System Protection & Recovery Technology

In order to solve the problem of software system protection and recovery in large computer laboratory , this paper analyses the current state of software system protection & recovery technology and it's defects in safety and stability. The reason causing these problems are discussed. Some solution plans are suggested.The authors hold that there have two way to solve these problems completely , one is strengthening the support from hardware , particularly strengthening the support to recover card directly from BIOS, another is developing new Host/Terminal computer system , protecting software system by ARC.     

Analysis on the Control of Variable Speed Wind Turbine Using Neural Network Controller

It is very difficult to build the accurate mathematical model of the wind turbine generator system because of the uncertainty of air kinetics and the complexity of power electronics, especially when the wind speed changes abruptly or there is a disturbance. But the classical control needs the model. Using neural network controller to the wind turbine generator system can overcome these difficulties. The wind speed can be followed and the maximum power can be obtained under low wind speed by using the power coefficient curve BP neural network and the optimum pitch angle BP neural network. The maximum power can be kept and under the allowed range in the condition of high wind speed. The simulation model and result are given under the environment of MATLAB. The fluctuation of wind speed can be controlled and the disturbance can be cancelled by BP neural network controller.     

棉花计算机模拟模型的现状及展望

本文在阐明计算机模拟与专家系统基本概念的基础上，着重综述了国内外关于棉花的生育期、叶龄、光合与呼吸作用等６个方面的模拟模型，提出了现有模型存在的问题以及今后的发展方向与前景。     

Neural Network Model for Predicting the Transformation Tendency of the Stress on the Surrounding Rocks of Tunnel

The stress on the surrounding rocks affects severely the stability of tunnel. To estimate the stability of tunnel needs the transformation tendency of the stress on the surrounding rocks. After the transformation tendency of the stress on the surrounding rocks and the factors affected it are analyzed, the neural network model for predicting the stress on the surrounding rocks is created. The model is applied successfully to predict the change of the stress of the Guanyingyan tunnel in the Qiwan expressway, which proves that it is feasible to predict the stress on the surrounding rocks with the neural network model. The method is convenient and correct.     

Research Methods of Brain-computer Interface Technology

Brain computer interface(BCI) is an EEG based communication and control system between human and computer or other electric devices, which does not depend on the brain's normal output channels of peripheral nerves and muscles. It is a novel kind of human interface, may have applications in rehabilitation, control and other fields. The developming speed of brain computer research in recent years is high. Methods of how to use P300, SSVEP, ERS/ERD, SCP, spontaneous EEG and implanted electrode to realize BCI are introduced. Characteristic and limitation of different methods are discussed. Status, problems and application prospects of BCI technology are also included.     

Study on Single-chip Computer Control Systems in Miniature Water Works

In order to enhance automation and to design low price and performance reliable control systems for the miniature water works, the single-chip computer control system was adopted to control the work. The single chip computer control system in the miniature water works, the principle of the hardware and a part of software block diagram were discussed in this paper. Finally, the data acquisition and control network were introduced.     

A Meta-synthetic Approach for Lower-constrained Handwritten Character Recognition

A meta-synthetic network approach for conbination of multiple classifier is proposed aimed at solving the problems of character recognition. It composes of two B-Wavelet neural network classifiers and a Morlet-B-Wavelet neural network classifier.It is shown that the method is effective used in handwritten capital English character recongnizing.