Title :
Compensation method of PSD´s background light based on improved BP neural network
Author :
Zhang, Feimeng ; Li, Yi ; Li, Hao ; Gu, Guo-hua
Author_Institution :
New Star Res. Inst. of Appl. Tech, Hefei, China
Abstract :
Position sensitive detector (PSD) is an optoelectronic device that can directly detect the position of the spot light on its photosensitive surface. It is commonly used in non-contact precision dynamic displacement detection. According to the principle and the characteristic equation of the PSD, the existence of the characteristics of the PSD output signal when the backlight based on neural network of the PSD background optical nonlinear compensation method is proposed to improve the detection accuracy and reliability. The simulation shows that this method can effectively eliminate the influence of background light.
Keywords :
backpropagation; compensation; computerised instrumentation; displacement measurement; neural nets; optoelectronic devices; photodetectors; position measurement; reliability; PSD background light compensation method; PSD background optical nonlinear compensation method; PSD output signal characteristics; characteristic equation; detection accuracy improvement; detection reliability improvement; improved BP neural network; noncontact precision dynamic displacement detection; optoelectronic device; photosensitive surface; position sensitive detector; spot light position detection; Accuracy; Detectors; Interference; Junctions; Mathematical model; Neural networks; Training; BP neuron network; PSD; background light;
Conference_Titel :
Instrumentation & Measurement, Sensor Network and Automation (IMSNA), 2012 International Symposium on
Conference_Location :
Sanya
Print_ISBN :
978-1-4673-2465-6
DOI :
10.1109/MSNA.2012.6324535
