<p class="MsoNormalIndent" style="text-justify: inter-ideograph; text-align: justify; line-height: 13pt; margin: 0cm 0cm 0pt; mso-line-height-rule: exactly;"><span style="color: black; font-size: 10pt; mso-bidi-font-size: 9.0pt;"><span style="font-family: Times New Roman;">In the study, embedded BASIC Stamp 2 (BS2) microchip controller is used to design with Hopfield neural network (HNN) as the foundation of sample training, which applies for a soldering platform of mechanical vision and accomplishes PCB soldering positioning technology. The proposed system design method in this paper can be divided into two parts: 1) the control rules of RC servo motor is designed by BASIC, and 2) human-machine interface is established to acquire images for pre-processing via C++ Builder. For the method of system image recognition, HNN is employed to do PCB soldering recognition positioning. The system is verified by MATLAB and Simulink to set up the simulation of PCB image soldering positioning. The experiment proves that the proposed method improves the traditional low efficiency of PCB soldering technology, and to achieve the feasibility of PCB image positioning and promote the soldering quality.</span></span></p>

This investigation describes a permanent magnet brushless direct current motor (PMBLDCM) that is based on an intelligent sensorless driver controller. Digital signal processing integrated circuit (DSPIC) is used as the core of the driver since it exploits microcontroller unit (MCU) and digital signal processor (DSP) technology, has the capacity for high-level computing, and is reliable. Not only sample the back electromotive force (back-EMF) by analog-todigital converter ADC but also a virtual neutral voltage is retrieved from the lead of the motor during the non-driven sector for a particular phase. An intelligent control law that combines Cerebellar Model Articulation Controller (CMAC) with the PI controller proposes to control a driver. The drive controller allows the PMBLDCM to reach the rated speed rapidly. However, when a mechanical load is applied, having good speed regulation response is obtained by the developed motor drive. The controller realizes the self-adjustment pursuit of the speed control to a better performance.

Sound waves are the most direct ways to broadcast messages in nature, but due to high-tech skills, the tracing of sound signals can come true only when lots of expenditures human resources, and fine are used. Consequently, this paper offers the advantages of the combination of the grey theory and the fuzzy controller to realize the design of realizing the tracing of sound signals.In order to get a sound source tracing system fast and highly accuracy, we proposed three steps in this paper. The first is to use the piezoel-electric element to make a set of four-direction sound-drawing sensor. It's used to make samples from analog signal information we get, and these samples will be transformed into digital signals for the computer to analyze, compute and handle. The second is to use the advantages of the gray color theory to make analyses and decisions of the characteristic values about grey relational grade. The last is to use the fuzzy controller to make output control of the target object and the returning back of the location sensor.Index Termsgrey theory,fuUJI control/er, signal trace, piezoelectric element 0-7803-8998-0/05/$20.00 ©2005 IEEE 893