Quality Detection Of Damaged Bean Kernels By Acoustic Signal Analysis Method

Bean quality has always been threatened by different ways,such as insect damage, sprout damage and so on. Meanwhile, the moisture content is a basic index for evaluating the bean's quality. At present, there are some methods which can be used to detect moisture content or damaged condition, but these methods are either time-consuming or Labor intensive or high-cost, so that they could not be widely used.This paper is aim to propose an acoustic signal detection method when the soybean kernels drop onto a stainless steel plate.The sound wave was acquired by a computer system equipped with a sound sensor. After the filtration of noise from the sound signals, the features, such as the acoustic intensity, time domain fitting parameters, spectrum energy, spectral peak position and peak value were calculated to describe the sound waves. Multiple linear regression, binominal regression and neural network methods were applied in the analyses. The results show that these features have strong correlations with the moisture content and damage degree of soybean kernels. Using the combination of these features, the moisture content and damage degree of soybean kernels can be accurately determined...