Yield Sensor of Cotton Picker Based on SSA-RFR Algorithm
With the increase of mechanization of cotton planting and harvesting, it is particularly important to obtain accurate yield map and analyze field yield data, and it is an effective and feasible method to monitor the yield at the cotton conveying pipeline during the operation of cotton picker. The existing photoelectric beam cotton yield measurement sensor has problems such as mucus blocking detection channel and ambient light influence in operation. Facing the complex field working environment, linear or polynomial model is generally used for sensor calibration, and the accuracy and anti-interference performance are not ideal. In view of the above situation, the anti-interference in the structure and circuit design of the sensor was firstly improved. Then, in the process of sensor calibration, random forest regression (RFR) was used to train and test the experimental samples. After analyzing the performance of the model, a stochastic forest regression model based on sparrow search algorithm (SSA) was proposed. The mean square error was used as fitness value to optimize the model. After verification, the optimized model had better detection accuracy under the same verification set. The optimal detection model was obtained by optimizing the range of upper and lower bounds, balancing the running time and detection accuracy. The model performed well on the validation set with a coefficient of determination (R2) of 0.99 and a mean absolute percentage error (MAPE) of 6.34%. The bench test results showed that the maximum error was 9.21% and the average error was 8.33% at different wind speeds. The improved sensor and detection model had good performance and can accurately detect the cotton quality during the operation of the cotton picker.
Keywords: cotton yield measurement, mass flow, sparrow search algorithm, machine learning
Download Full Text:PDF
NIU Guoliang, LI Bin, LIU Yang, et al. Development and research status of cotton picker in China [ J]. Journal of Chinese Agricultural Mechanization, 2020, 41(2) ; 212 - 218. (in Chinese)
WL Chuanyun, FENG Jian, CHEN Chuanqiang, et al. Analysis of the status quo and mechanization development of cotton producing industry in China [J], Journal of Chinese Agricultural Mechanization, 2021 , 42(5): 215 —221. (in Chinese)
XIN Minghua, WANG Zhanbiao, HAN Yingchun, et al. Review, status and measures of Xinjiang machine-picked cotton [ J ] . Journal of Agricultural Science and Technology, 2021 , 23(7) : 11 -20. (in Chinese)
WILKERSON J B, KIRBY J S, HART W E, et al. Real-time cotton flow sensor [С ] American Society of Agricultural Engineers. Meeting (USA), 1994.
SUI R, THOMASSON J A, MEHRLE R, et al. Mississippi cotton yield monitor*, beta test for commercialization[ J]. Computers and Electronics in Agriculture, 2004, 42(3) ; 149 - 160.
MAILANDER M, MORIASI D. Test of pressure transducer for measuring cotton mass flow[ J]. The Journal of Cotton Science, 2011, 15: 137 - 143.
SANH L E. Development of an electronic hopper weight scale [ C] //American Society of Agricultural and Biological Engineers Annual International Meeting, 2006:146 - 157.
American Society of Agriculture and Biological Engineers. Yield monitor performance test standard^ R]. ASABE, 2007.
НЕ Xiaofeng, WU Guoxin, XU Shoudong. Measurement of cotton fiber numbers by near infrared spectroscopy [ J ]. Transactions of the CSAE, 2009, 25(3) : 119 - 123. ( in Chinese)
AN Guanghui. Design and research of online measurement system of cotton mass flow based on optoelectronic detection [D]. Shihezi: Shihezi University, 2012. (in Chinese)
ZIIOU Liming, LI Shujun, ZHANG Xiaochao, et al. Detection of seed cotton mass flow based on capacitance approach [J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(6) : 47 -52. (in Chinese)
WANG Huan. Design and research of on-line monitoring system for cotton output based on WSN [ D] . Shihezi; Shihezi University,2020. (in Chinese)
REN Ling, CEN Honglei,MA Rong. The feasibility analysis of the cotton quality inspection system based on neural network [J] . Anhui Agri. Sci. Bull. , 2013( 19) : 134 - 135. (in Chinese)
CEN Honglei, REN Ling, M A Rong. Research on modeling of neural networks in the prediction of cotton quality and flow rate [J ]. Agriculture Network Information, 2013( 12) ; 16 - 19. ( in Chinese)
LIN Changjian, LI Yanming, MI AO Zhonghua, et al. Research on model of cotton flow measuring based on genetic algorithm and GRNN[J]. Machinery & Electronics, 2013(4) : 11 - 14, 18. (in Chinese) ftts. 2022, 38(4): 60 -63.
CAO Taoyun. Study on the importance of variables based on random forestfj]. Statistics and Decision, 2022, 38(4) ; 60 - 63. (in Chinese)
WANG Haiyang, JIN Zhiliang, WANG Peipei, et al. Study on effect of TIR lens and reflector for LED collimation [J]. Laser & Optoelectronics Progress, 2021 , 58( 19) : 328 -333. (in Chinese)
ZHOU Liming. Research on detection of yield and seeding rate of cotton based on capacitive method [ D] . Beijing: China Agricultural University, 2014. (in Chinese)
XIAO Yuanbin, ZHAO Yanfang, YANG Yanqi, et al. Effects of multi-factors on the junction temperature of LED automotive lamp chips [J]. Microelectronics and Reliability, 2022, 136; 114658.
SIIEN Lei. The establishment and optimization of photoelectric detection model for seed cotton mass flow in pipe[ D . Shihezi; Shihezi University, 2014. (in Chinese)
SHAH K, PATEL H, SANGHVI D, et al. A comparative analysis of logistic regression, random forest and KNN models for the text classification [ J ]. Augmented Human Research, 2020, 5:1- 16.
DANG C, LIU Y, YUE H, et al. Autumn crop yield prediction using data-driven approaches; support vector machines, random forest, and deep neural network methods [J] . Canadian Journal of Remote Sensing, 2021 , 47( 2 ) ; 162-181.
- There are currently no refbacks.