Acoustic sensor for estimating grain mass and moisture content and its application to yield-monitoring combine and stationary grain drier

2017 Fiscal Year Final Research Report

• Project/Area Number: 26450353
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Agricultural environmental engineering/Agricultural information engineering
• Research Institution: Kobe University
• Principal Investigator: SHOJI Koichi 神戸大学, 農学研究科, 准教授 (10263394)
• Research Collaborator: USHIO Akihiro ; MATSUMOTO Isao ; KAWAMURA Tsuneo ; ARAI Keisuke ; YOKONO Takashi
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: IT農業 / 籾 / コムギ / イヤホン / 積算値 / 高速フーリエ変換 / 回帰 / 標準誤差

Outline of Final Research Achievements

To function as a practical sensor for current information-based agricultural practices, impact sound of the grain was acquired with an earphone to estimate harvested mass and moisture content on the combine, and the moisture content on the stationary grain drier. A commercially available ceramic earphone was attached on a small impact plate in the grain tank of the combine, and on the side wall of the drier. On the combine, the cumulative output was calibrated to the harvested mass of paddy and wheat grains, and the standard error obtained with simple linear regression was about 1 kg. The time-series outputs of the sensor were then converted into acoustic spectra in frequency domain. By selecting two frequency bands of the spectra for the estimation of grain moisture content, the standard error was 0.4% (w.b.) for paddy and 0.8% (w.b) for wheat on the combine. The same method was applied to the drier and the standard error of 0.1% was obtained for paddy grain.

Free Research Field

農業機械学