The Components Layout Optimization of Circuit Module Based on the Artificial Nerve Network

摘要

With the increasingly complexity function and ameliorative performance of electronic products, the density of the PCB(printed circuit board) and the frequency of the correlative parts are continuously rising, and are resulting in all sorts of challenge concerning high speed and high density PCB design. And with the improvement of the PCB assembly density , the power dissipation per unit area is increased accordingly and the heat in the PCB is concentrated highly.And the temperature increment of some device and component or other will lead to the circuit work stability and reliability, for an example, bringing forth the thermal fatigue failure of the electronic component. So, the thermal design of the electronic product is the keypoint the engineering designer should put emphases on . Among all , reliable thermal analysis and design is just the important method of improving thermal reliability of PCB . In this paper a model for temperature field analysis is established by FEM( finite element method) and computer aided thermal simulation soft,with regard to such factors affecting temperature as heat generation 、 heat diffusion manner and direction 、 ratio of length and width of component 、 thickness of PCB and so on. And the artificial nerve network method for components layout optimization is applied to achived a reasonable components position in a small space and a best temperature distribution . Also some reference of concrete measure and method for thermal design is hoped to do the PCB designers a favor. In this paper , a simplified pc module of the threedimensional asmble circuit module is treated as analysis object , and is analized by general finite element soft -ANSYS . Its geometric and finite element simulation model are shown as figure 1 and 2 respectively, and corresponding material parameters is shown in table 1 . By changing such different variable parameters as heat generation 、 component layout direction 、 PCB thickness and so on, some samples for different temperature distribution through analysis by ANSYS are attained, as are shown in figure 3 and 4.Then adopting artificial nerve network for layout prediction and optimization , preferable PCB components layout and other matter can be achieved, just shown in figure 5. With aboved analysis , such conclusions for component layout for PCB thermal design as : 1) keeping the PCB surface temperature equality and consistency; 2) laying the maximal power dissipation and the maximal component generating heat nearby the best heat dissipation location; 3)no placing the higher heat generation components at the corner of the PCB or around, excepting some heat diffusion equipment around them ; 4) choosing some bigger components while designing and selecting power dissipation ones , and keeping enough heat diffusion space while adjusting PCB layout and so on . Anyway , a reasonable thermal design can enhance the stability and improve the use life of the circuit module, and promote the application and development of the circuit module.