A5083961524- Agricultural Engineering and Mechanization
- Smart Agriculture and AI
- Seismic Imaging and Inversion Techniques
- Soil Mechanics and Vehicle Dynamics
- Seismic Waves and Analysis
- Belt Conveyor Systems Engineering
- Underwater Acoustics Research
- Methane Hydrates and Related Phenomena
- Advanced Neural Network Applications
- Advanced Algorithms and Applications
- Spectroscopy and Chemometric Analyses
- Retinal Imaging and Analysis
- Terahertz technology and applications
- Retinal Diseases and Treatments
- Inertial Sensor and Navigation
- Advanced Computational Techniques and Applications
- Agriculture and Farm Safety
- Wireless Sensor Networks and IoT
- Wireless Signal Modulation Classification
- Power Systems and Renewable Energy
- Entomopathogenic Microorganisms in Pest Control
- Autonomous Vehicle Technology and Safety
- Plant Disease Management Techniques
- Drilling and Well Engineering
- Control and Dynamics of Mobile Robots
Ocean University of China
2009-2024
Qingdao National Laboratory for Marine Science and Technology
2021-2024
Beijing Academy of Agricultural and Forestry Sciences
2022-2024
Beijing Automation Control Equipment Institute
2018-2022
National Engineering Research Center for Information Technology in Agriculture
2018-2022
China Academy of Launch Vehicle Technology
2017-2022
Tianjin University
2022
Tsinghua University
2017
Nanjing University of Aeronautics and Astronautics
2010
ABSTRACT Corn row‐controlled weeding is a critical crop field management aspect. robots suffer from large errors in seedling and weed identification algorithms, lack of row actuators dry fields, low integration automated devices for identification, navigation, weeding. Therefore, this paper investigates an intelligent robot weeding, which could realize the integrated automatic operation line acquisition, We present fully integrated, autonomous, innovative solution to overcome difficulties...
Aiming at the need to prevent agricultural machinery from colliding with obstacles in operation of unmanned machinery, an obstacle detection algorithm using 2D lidar was proposed, and a pre-collision system designed this algorithm, which tested on harvester. The method uses differences between data frames calculate collision times farm obstacles. consists following steps: pre-processing determine region interest, median filtering, DBSCAN (density-based spatial clustering applications noise)...
Impurities in wheat seriously affect quality and food security. They are mainly produced during the operational process of combine harvesters. To solve recognition classification problems associated with impurities wheat, a method using an improved convolutional neural network is proposed this article. A labeled dataset normal five constructed, which Wiener filtering algorithm multi-scale Retinex enhancement employed for image preprocessing. Based on research Inception_v3, improvement...
In the process of harvesting, feed rate combine harvester could be affected by many factors, such as crop parameters, operation status parameters and working condition. The objective this paper is to ensure relationship its related impact intensity each factor on rate. Based grey relative analysis method, correlation was made degree parameter obtained in paper. factors (e.g. speed, density torque rotating speed feeding auger, inclined conveyor threshing cylinder et. al) from...
By anchoring vertical cable in seawater and receiving the data excited by towing seismic source, reflection from subsurface structures with a high signal-to-noise ratio, wide frequency band, azimuth angle can be obtained, thereby achieving high-quality imaging of target area. However, due to drifting receivers driven ocean currents nonuniform coverage caused orientation receivers, traditional method cannot directly used data. Furthermore, crosstalk between primaries multiples commonly...
The wheat harvesting boundary line is vital reference information for the path tracking of an autonomously driving combine harvester. However, unfavorable factors, such as a complex light environment, tree shade, weeds, and stubble color interference in field, make it challenging to identify harvest accurately quickly. Therefore, this paper proposes recognition model based on MV3_DeepLabV3+ network framework, which can quickly complete identification environments. uses lightweight...
The detection of the wheat moisture content plays a key role in grain storage and classification. Harvested grains were taken as samples current research. A total 240 reaped with different contents tested by applying terahertz (THz) spectroscopy. frequency domain spectra absorption coefficient obtained band 0.1-1.2 THz, pretreated mean centering, Savitzky-Golay (S-G), Multiplicative Scatter Correction (MSC) Stand Normal Variate (SNV), respectively. Then special algorithm Tabu Search (TS) was...
A new boundary domain integral equation with convective heat transfer is presented to solve variable coefficient conduction problems. Green's function for the Laplace used derive basic varying conductivities, and as a result, integrals are included in derived equations. The existing converted into an equivalent using radial integration method by expressing normalized temperature series of basis functions. This treatment results pure element analysis algorithm requires no internal cells...
We propose a convolution neural network based algorithm for simultaneously diagnosing diabetic retinopathy and highlighting suspicious regions. Our contributions are two folds: 1) termed Zoom-in-Net which mimics the zoom-in process of clinician to examine retinal images. Trained with only image-level supervisions, Zoomin-Net can generate attention maps highlight regions, predicts disease level accurately on both whole image its high resolution patches. 2) Only four bounding boxes generated...
To increase the accuracy and real-time performance of on-line assessment maize planting, a CAN bus based monitoring system for precision planting was designed tested both in laboratory field. The mainly comprised of: (a) seeding rate sensors on opposite-type infrared photoelectric cell counting dropping seeds; (b) decimeter GPS receiver acquiring planter position operation speed; (c) vehicle terminal ARM Cotex-m4 core chip to acquire process whole-system data; (d) touchscreen monitor display...
The reversible plough is a quite useful farm machinery for deep tillage, which directly mounted to the tractor. It works on both left and right side with bilateral turnover mechanism automatically reverses position. According its structure characteristic, based deviation correction method, depth online sensing model was proposed firstly by integrated attitude data from tractor plough. In this model, plowing obtained calculate pitch of lower link suspended at back part Then, basis developed...
This paper explores the performance and obtains a reasonable cleaning effect of system combine harvester studies relationship between its influencing factors. We established neural network model loss rate clean parameters. First, we tested results each group under different combinations conditions, analyzed direct or indirect parameters in experiment working condition. Then, according to experimental data obtained experiment, predict clearance for several sets conditions by this model. The...
To obtain the online multi-information of machine performance, working condition and other parameters for gain combine harvester, a controller area network (CAN bus) based distributed data collection, transmission processing system was constructed tested. In this series sensors designed or optimized, such as attitude sensing rise fall header, torque revolution speed measuring power output, rotational speed, GPS module detecting operating location. And with ARM embedded processor, universal...