In this paper,a non-destructive testing method for dried shell weight of cocoon is successfully built by means of technology of virtual instrument and neural network ensemble.It realized data collection,signal procession and so on,which was based on the system of software and hardware platform.Firstly,the characteristic parameters of cocoon vibration signal were extracted and selected,which were related to cocoon weights.Then,use the characteristic parameters to train BP model and RBF model,respectively.The input of neural network ensemble is two kinds of models which inputs include six simplex neural networks.The output of neural network ensemble represents cocoon weight.The test results show that the method is effective and feasible.

The core of PCB(printed circuit board) tester is testing algorithm,which directly determines the testing functions and speed of PCB tester.The algorithm based on field programmable gate array(FPGA) not only simplifies the design of circuit board,but also improves the testing speed and reconfiguration ability of system.This paper studied implements of major testing algorithm based on FPGA,gave both the state transition's diagram and the simulation timing diagram with EDA design tools.The experiment results have been demonstrated this method is available and effective.

Data processing of non-destructive testing for the pod is a very complex problem. In this paper neural network ensemble is applied to the non-destructive testing of pod,which can improve the precision and generalization ability of system through training different kinds of neural networks and then combining those results.It compared each the resu1ts of BP model, RBF model, GRNN model and neural network ensemble methods which are employed to test the quality of pod. The results show that neural network ensemble method is better than simplex neural network, and the non-destructive testing of the pod based on neural network ensemble is valid and feasible.

<正>随着互联网技术近年来的不断发展,机电设备融入互连网,并对其进行远程监控得到了广泛应用。基于嵌入式web的远程监控是在传统远程监控的基础上又融合了

During altering the ordinary machine tool (CW6100) to the special pressure roller grinding machine, we applied a numeral alteration method in which the PLC was the kernel part because we had to take into account the factor of cost and workload. The method only added a motional device in X-axis of the machine tool and achieved the harmony of the continuous motion of y-axis and the digit-controlled motion of x-axis. The experiments showed that the method was simple and the cost was cheap. The machine tool could machining the long pressure roller.

A new method for testing the printed circuit board(PCB) was presented in the paper based on hardware architecture of PC104 and FPGA(field programmable gate array) and Kautz algorithm.According to the features of PC104 and FPGA,applying parallel testing synchronously,all electrical nets of PCB can be obtained quickly and accurately by using the method proposed.Implement of Kautz algorithm was studied and the steps of algorithm were given based on hard system in this paper.The experiment results indicate that this method is a fast and effective detecting approach.

A method of DDA interpolation algorithm based on field programmable gate array(FPGA) is presented.The algorithm described by Verilog hardware describe language(HDL),compiled,synthesized and downloaded with QuartusⅡ,which is implemented in a FPGA chip in series of Cyclone from Altera company.The state-machine,program flow chart and the simulation results are also presented.The DDA algorithm running on FPGA chip has the advantages of high speed and excellent anti-disturb capability,and the DDA algorithm designed by Verilog HDL based on IP core can be used repeatedly so as to improve the design efficiency.

The non-destructive testing method of pod was proposed based on neural networks according to pod's vibration signal. The wavelet theory is used to reconstruct chrysalis vibration signals. The characteristic values among chrysalis vibration signal, which were related to chrysalis weights, were extracted respectively. And the characteristic values were selected firstly by fuzzy classification. Then BP model for NDT of silkworm is built, which inputs include seven relevant characteristic values. The output of neural network represents weights of the chrysalis. The weight of cocoon shells can be gain indirectly. The testing result shows that the method is effective and feasible

This paper aims at finding a workable way of transportation of rectilinear-flow powder in outer space.Numerical simulation results indicate that in outer space air transportation of powder in pipes can reduce pressure losses and improve energy utilization ratio.Suitable conditions for the transportation of materials of various kinds according to their own characters are available.The condintions can provide proper level of power for the transportation and reduce losses of materials in the process.

本文介绍了虚拟仪器技术在蚕茧无损质量检测中的应用.将虚拟仪器技术引入到蚕茧无损检测中,并在虚拟仪器的软硬件平台上利用LabVIEW软件的Matlab Script节点功能和LaVIEW图形化的编程环境构建了一个功能强大的数据采集和信息处理平台.

In order to realize the real time monitoring of turbidity and manage the data of turbidity measuring by computer, the working principle of the APMS-10G digital turbidity sensor is studied, and a practical RS-485 bus multipoint communication agreement is designed. Turbidity data of every point are collected by MCS-51 single-chip microcomputer and transferred to the computer by serial communication. At the computer end, MSComm communication control is used to finish serial communication with each point. Binded with MSChart control to figure turbidity data real time, access database is used to save up and dispose turbidity information of every node.

本文深入研究了基于公用电话网的MCS-51单片机远程通信技术,设计了基于DTMF电路HT9200A及MODEM芯片MSM7512B的数据传输装置,详细阐述了通信的实现过程.

The weak signal detection is a key technology of the measuring system.This paper discusses the condition processing of the weak scattered light signal in the intelligent fiber turbidity sensor.According to the characteristic of detection signal,the special signal processing circuit is designed.

In order to realize the intelligent and networked industrial washing machine, the control system software is designed under μC/OS-II embeded operating system. System tasks are compartmentalized to display interface, input of operating commands, washing flow control, motor control, analog signals measure, digital signals measure, valves control, turbidity measure, intelligent reasoning and alarming subtask, etc. Then the model of system tasks is set up. The execute processes of display and washing flow control are analyzed.The intelligent control system of industrial washing machine is of intelligent control and online measuring function with friendly man-machine interface and high stability.

An online configuration method of FPGA based on ISA bus in PC is presented in this paper.By using PS(passive serial) configuration scheme,the configuration data are loaded into FPGA that is on an ISA card through ISA bus.The configuration principle and related hardware and software design are described in detail.Practice has proved that this method is costeffective and easy to use on the spot.

To equip industry washing machine with intelligence and internet remote monitor functions, the function modules of industry washing machine control system were researched,such as man-machine interface, motor control, magnet valves control, washing state detection, temperature measure, cloth volume and cloth properties measure, turbidity measure, intelligent control, internet communication. The hardware of industry washing machine based on ARM7TDMI core was finished. Water level, cloth weight, water volume and rotating speed impulse were researched emphatically with the circuit of water level and cloth weight measure. Results show that the system hardware is of high stability and fast speed in fuzzy inference and neural net study.

A brief introduction of applications of Fuzzy Sets theory in pattern recognition is given in this paper. The basic knowledge of Fuzzy Sets theory is first presented, followed with several different methods of realization of Fuzzy Pattern Recognition, including Maximal Membership Rule method, Near Selection method, Fuzzy Clustering method, Relative Membership Rule method. Comparison is made among the four.

By using the Control System Toolbox and Simulink provided by MATLAB, the author developed a series of CAI coursewares of “Computer Control System”. Three examples are presented in the paper. Through modeling, simulating and programming in MATLAB, these coursewares can illustrate those tedious mathematical derivation and demonstrate the influence of varied parameters on system vividly, which are superior to traditional cartoon. Practice has proved that learning interest of students is enhanced and teaching effect is improved.

A new project for the design of printed circuit board testing machine is introduced. The system′s testing speed and reliability has been highly improved in this project. It is mainly composed of embedded industrial computer based on PC104 bus and FPGA(Field Programmable Gate Array), and its information communicating is based on ISA bus under windows environment. The project for composition of the system′s hardware and software has been focused on.