基于声信号的隔膜泵施药量监测方法研究

Research on the dosage monitoring method of diaphragm pump based on acoustic signal

施药量监测技术是实现精准施药、变量施药的基石,是实现我国生态农业的重要保障。针对当前嵌入式施药量监测设备受恶劣工作环境影响,存在精度差和寿命短的问题,提出一种基于声信号处理的非嵌入式隔膜泵施药量监测方法。首先使用小波变换和短时能量的算法提取隔膜泵的工作状态和转速信息,然后通过构建隔膜泵转速与流量数学模型得出系统的施药量,最后进行试验验证。结果表明:短时能量算法能很好地提取出声信号中的振动部分,从而识别出隔膜泵的开关状态,识别最大时间偏差为0.41 s;小波变换的声信号处理方法提取隔膜泵工作转速的精度较高,最大提取误差为2.8%;基于声信号的隔膜泵施药量监测法误差在5%以内。

Drug dosage monitoring technology was the cornerstone of precise drug application and variable drug application and an important guarantee for realizing China’s ecological agriculture.In view of the problems of poor accuracy and short life of the current embedded dose monitoring equipment,this paper proposed a non-embedded diaphragm pump dose monitoring method based on the acoustic signal.Firstly,the working state and speed information of the diaphragm pump was extracted by using the algorithm of wavelet transform and short-term energy.Then the system application amount was obtained by constructing a mathematical model between the speed and flow rate of the diaphragm pump.Finally,the experimental verification was carried out.The results showed that the short-time energy algorithm could extract the vibration signal of the pump to identify the switch state of the diaphragm pump.The maximum time deviation for identification was 0.41 s.The acoustic signal processing method of wavelet transform had a high precision in extracting the working speed of the diaphragm pump,and the maximum extraction error was 2.8%.The error of the diaphragm pump dose monitoring method based on the acoustic signal was within 5%.