基于多模态射频信号融合的粮食水分检测  

Grain moisture detection based on multi‑modal RF signal fusion

作　　者：杨卫东[1,2] 郭思君[3] 段珊珊 胡鹏明[4] 单少伟 Yang Weidong;Guo Sijun;Duan Shanshan;Hu Pengming;Shan Shaowei(School of Artificial Intelligence and Big Data,Henan University of Technology,Zhengzhou,450001,China;Hangzhou Institute of Technology,Xidian University,Hangzhou,310000,China;School of Information Scienceand Engineering,Henan University of Technology,Zhengzhou,450001,China;School of Mechanical andElectrical Engineering,Henan University of Technology,Zhengzhou,450001,China)

机构地区：[1]河南工业大学人工智能与大数据学院,郑州市450001 [2]西安电子科技大学杭州研究院,杭州市310000 [3]河南工业大学信息科学与工程学院,郑州市450001 [4]河南工业大学机电工程学院,郑州市450001

出　　处：《中国农机化学报》2025年第2期132-138,共7页Journal of Chinese Agricultural Mechanization

基　　金：河南省自然科学基金项目(222300420004);河南省重大科技专项项目(201300210100);河南省科技厅自然科学项目(232103810083);粮食信息处理与控制教育部重点实验室开放课题(KFJJ2022010)。

摘　　要：水分检测是粮食存储和贸易中不可或缺的一环,利用各种射频传感技术可以实现无损、快速地粮食水分检测。然而,现有方案都是基于单一种类射频信号开发的,针对不同射频信号需要训练对应检测模型,人力成本增加。基于此,提出一种融合多模态射频信号的粮食水分检测方法RF—Grain。首先,针对多径环境和硬件缺陷引起的噪声问题,提出一种WiFi信道状态信息(CSI)数据预处理方法;其次,提出一种域对抗神经网络模型,用以消除不同类型射频信号提取的粮食水分特征分布差异;最后,设计使用3种不同射频传感技术进行粮食水分检测的试验,以卷积神经网络作为对比,对所提出方法的性能进行评估,并与现有方法进行对比分析。试验表明,所提出方法能够有效检测5种不同含水率的粮食样品,总体准确率为分别为98.87%、96.22%和96.56%,优于传统的卷积神经网络,具有准确率高、泛化性好等优点,为粮食水分无损检测研究提供有力的技术支撑。Moisture detection is an indispensable part of grain storage and trade,and non-destructive and fast grain moisture detection can be achieved by using various RF sensing technologies,such as WiFi,Radio Frequency Identification(RFID),and radar.However,existing solutions are developed based on a single type of RF signal,and corresponding detection models need to be trained for different RF signals,which can lead to additional manpower costs.Therefore,this paper proposes a grain moisture detection method fusing multimodal RF signals,named RF—Grain,which can be applied to multiple RF sensing technologies.Firstly,a WiFi channel state information(CSI)data preprocessing method is proposed to address the noise problem caused by multipath environment and hardware defects.Secondly,a domain-adversarial neural network model is proposed to eliminate the differences in the distribution of grain moisture features extracted from different types of RF signals.Finally,three different RF sensing technologies were designed to detect grain moisture.The convolutional neural network was used as a comparison to evaluate the performance of the proposed method and compare it with existing methods.The experiments showed that the proposed method could effectively detect grain samples with five different moisture levels,with overall accuracy rates of 98.87%,96.22%and 96.56%,better than traditional convolutional neural networks.The proposed method has the advantages of high accuracy and good generalization,and it provides powerful technical support for non-destructive moisture detection of grain.

关 键 词：粮食 水分含量检测 射频传感 多模态 域对抗神经网络 

分 类 号：S5[农业科学—作物学] TP399[自动化与计算机技术—计算机应用技术]