Design and Experiment of VS-1D CNN-based Clearing Loss Detection System for Corn Kernel Direct Harvester
Abstract
Aiming to address the challenges of arduous threshold delineation, inadequate robustness, and insufficient adaptability of conventional clearing loss detection sensors that depend on temporal domain feature thresholds to distinguish kernel impact signals, a comprehensive clearing loss detection system for corn kernel direct collectors was developed, and a kernel impact classification algorithm predicated on a variable scale one-dimensional convolutional neural network (VS-1D CNN) was proposed. Initially, the hardware circuitry and software processing program were engineered for impact signal acquisition, processing, and transmission, alongside the development of the supporting host computer. Subsequently, a data acquisition testing platform was established to gather and archive the impact signals of weeds and maize kernels under varying impact heights and angles, thereby constructing a data set and training the VS 1D CNN seed impact classification algorithm, with the training outcomes indicating that the model’s accuracy was 94.2% on the testing set. Ultimately, the efficacy of the devised detection system under diverse operational conditions and the classification performance of distinct stray residues and seed mixtures were validated, with results demonstrating that the proposed VS-1D CNN algorithm performed commendably, achieving detection accuracy exceeding 95% across different installation sites and varying seed flow rates;the classification accuracy for identifying different proportions of stray residues and seed mixtures surpassed 93% , signifying that the proposed algorithm exhibited exceptional performance. This underscored that the algorithm delineated in this manuscript possessed remarkable efficacy and can accurately detect seed losses without establishing a fixed temporal domain feature threshold.
Keywords: corn kernel direct harvester, clearing loss, sensor, 1D CNN, deep learning
Download Full Text:
PDFReferences
LI Daoliang, LI Zhen. System analysis and development prospect of unmanned farming[ J]. Transactions of the Chinese Society for Agricultural Machinery,2020,51 (7) : 1 — 12. (in Chinese)
ELDREDGE К W, CLARE В К. Grain loss indicator: AUS, US044909640[P]. 1985 -01 -01.
YILMAZ D, SAGIROGLU H C. Development of measurement system for grain loss of some chickpea varieties [J]. Measurement, 2015, 66; 73 -79.
LIANG Zhenwei, LI Yaoming, ZHAO Zhan, et al. Partial constrained damping design of sensitive plate for grain loss monitoring sensor [J] . Transactions of the Chinese Society for Agricultural Machinery,2014,45(8) : 106 - 111 ,79. (in Chinese)
LIANG Zhenwei. Study on designing method of multi-ductair-and-screen cleaning unit and grain sieve loss monitoring and controlling technology( 13) . Zhenjiang: Jiangsu University, 2018. (in Chinese)
SUN Ying. The basic characteristics of grain impactsensor utilizing two crossed PVDF films [ D]. Hangzhou: Zhejiang University, 2018. (in Chinese)
CAO Rui. Research on signal processing system of multi-channel PVDE piezoelectric thin film grain loss sensor based on DSP [D]. Hangzhou: Zhejiang University, 2020. (in Chinese)
NIE Xin. Design and implementation of online detection software system for harvesting loss of rice and wheat combine harvester [D]. Hangzhou: Zhejiang University, 2021. (in Chinese)
DONG J, ZHANG D, YANG L, et al. Design and experiment of maize kernel loss monitoring system based on signal interval duration [J]- Computers and Electronics in Agriculture, 2023, 213: 108230.
WANG Zhuo, CHE Dong, BAI Xiaoping, et al. Improvement and experiment of cleaning loss rate monitoring device for corn combine harvester [ J]. Transactions of the Chinese Society for Agricultural Machinery, 2018,49 ( 12); 100 - 108. (in Chinese)
LIU Yangchun, LI Minghui, WANG Jizhong, et al. Design and test of entrainment loss detection system for corn kernel direct harvester [J], Transactions of the Chinese Society for Agricultural Machinery,2023,54(5) ; 140 - 149. (in Chinese)
KIRANYAZ S, AVCI 0, ABDELJABER 0, et al. ID onvolutional neural networks and applications: a survey [ J]. Mechanical Systems and Signal Processing, 2021 , 151 ; 107398.
CACCIARI I, RANFAGNI A. Hands-on fundamentals of ID convolutional neural networks—a tutorial for beginner users [ J]. Applied Sciences, 2023, 14(18): 8500.
WU Jun, GUAN Luyang, BAO Ming, et al. Vibration events recognition of optical fiber based on multi-scale ID CNN J]. Opto-Electronic Engineering, 2019, 46(5) ; 79 -86. (in Chinese)
WANG X, MAO D, LI X. Bearing fault diagnosis based on vibro-acoustic data fusion and ID CNN network [J]. Measurement, 2021, 173: 108518.
ZHOU Kui, KANG Yingwei. Fault warning of gas turbine combustor based on CNN - LSTM [ J ]. Journal of Engineering for Thermal Energy and Power,2024 ,39(1): 191 - 197, 215. (in Chinese)
HE J, LI X, CHEN Y, et al. Deep transfer learning method based on ID - CNN for bearing fault diagnosis [ J ]. Shock and Vibration, 2021 , 2021 (1): 6687331.
LIN X, JIANG Q, SHEN Y, et al. Multiscale pooled convolutional domain adaptation network for intelligent diagnosis of rolling bearing under variable conditions [J]. IEEE Sensors Journal, 2023, 23(21): 26163 -26176.
LOSS L H, HAH A K, SAITO D, et al. Analysis of function of rectified linear unit used in deep learning [ С] //2015 International Joint Conference on Neural Networks (1JCNN) , 2015: 1 -8.
ZHOU Y, WANG X, ZHANG M, et al. MPCE: a maximum probability based cross entropy loss function for neural network classification[ J ]. IEEE Access, 2019, 1-. 146331 -146341.
IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[ J]. arXiv preprint arXiv: 1502. 03167 ,2015.
WEI D, WU C, JIANG L, et al. Design and test of sensor for monitoring corn cleaning loss[J ]. Agriculture, 2024, 13(3): 663.
Refbacks
- There are currently no refbacks.
