摘要
小麦在储藏阶段由于各种灾害导致损失巨大,并降低了面粉质量,及时检测并分离小麦的受损颗粒迫在眉睫。文章以提取4类小麦碰撞声信号为基础,使用数字信号处理方法对小麦完好粒、虫害粒、霉变粒及发芽粒的碰撞声信号提取有效特征,最后利用BP神经网络进行分类,对于3类小麦类型的识别取得了较好的识别率。应用结果表明BP神经网络能够较好地实现区分受损小麦颗粒与完好小麦颗粒。
In storage stage, a huge number of wheat will loss due to various disasters and the damaged wheat kernels reduce the quality of the flour, it is important to detect and separate the damaged wheat kernels timely. This paper use digital signal processing method to analyze the impact acoustic signal of un-damaged kernels, IDK（Insect Damaged Kernels）, slab-damaged kernels and sprout kernels, extract some characteristic features of the four types wheat kernels, and classify the wheat kernels with BP neural network, get a good recognition result of three types wheat kernels in the end. The research shows that the BP neural network is useful to the detection and separation of damaged wheat kernels and un-damaged wheat kernels.
出处
《电子设计工程》
2013年第7期163-164,168,共3页
Electronic Design Engineering
基金
宝鸡文理学院校级重点项目(ZK12109)
关键词
检测方法
碰撞声信号
BP神经网络
detection method
impact acoustic signal
BP neural network
作者简介
张丽娜（1983-），女，陕西宝鸡人，硕士，助教。研究方向：数字信号处理和模式识别。
