针对现有PM2.5检测装置存在的自动化程度低,检测重复性差、有介质材料消耗等问题,设计了一套基于夫琅禾费衍射理论的激光衍射PM2.5检测系统。通过采用RBF(Radial Basis Function)神经网络对多路激光微粒子衍射信号进行建模计算,有效提高了系统的检测精度和自学习能力;对于系统中光电探测器输出的多路微弱信号,采用信号独立放大、分组采集和通道校准新方法,实现了多路微弱信号的精确调理和实时采集。仿真和实验结果表明,所设计的PM2.5检测系统有效克服了常规检测系统存在的问题,检测精度高,达到了设计要求。 Aiming at the problems of low degree of automation, poor repeatability of detection and consumption of dielectric materials in existing PM2.5 detection devices, a laser diffraction PM2.5 detection system based on Fraunhofer diffraction theory was designed. By using Radial Basis Function (RBF) neural network to modeling and calculating multi-channel laser particle diffraction signals, the detection accuracy and self-learning ability of the system are effectively improved. For the multi-path weak signals output by the photodetector in the system, signal independent Amplification, packet acquisition and channel calibration of new methods to achieve a multi-channel weak signal precision conditioning and real-time acquisition. Simulation and experimental results show that the designed PM2.5 detection system can effectively overcome the existing problems of the conventional detection system and has high detection precision and meets the design requirements.