The yield reduction caused by miss-seeding in potato mechanized sowing is astonishing.The existing research always needs to install a spare compensator on the original seed-metering device.Therefore,problems of comple...The yield reduction caused by miss-seeding in potato mechanized sowing is astonishing.The existing research always needs to install a spare compensator on the original seed-metering device.Therefore,problems of complex planter structure and compensated potato seed poor landing accuracy need to be solved urgently.Consequently,a scheme of integrated seeding and compensating potato planter based on one-way clutch is proposed in this paper.Based on a basic‘improved one raw potato planter’and the working principle of one-way clutch,power of seed-metering system is provided through main power transmission one-way clutch by land wheels when the system works properly.However,when miss-seeding detection system with infrared radiation deciding that a miss-seeding incident has happened,the seed-metering power will be replaced by a compensatory motor through compensating one-way clutch at a higher speed.Thus,the idea of catching-up compensation can be realized.After compensation is completed,the system controller disconnects the compensatory motor,and the seed-metering power will naturally switch to the land wheels again.A prototype based on this idea was built.Field tests showed that the accuracy of seed monitoring system is more than 99.9%;the adoption of catching-up compensation scheme does not bring about empty spoon rate rise significantly.Within the range of 0.2-0.8 m/s of the seed-metering chain speed,although the average success compensation rate decreases evidently with the increase of the chain speed,the success compensation rate is still near 70%even at 0.8 m/s,the vast majority of missed seeds can be compensated effectively.展开更多
In this paper,we propose a intrusion detection algorithm based on auto-encoder and three-way decisions(AE-3WD)for industrial control networks,aiming at the security problem of industrial control network.The ideology o...In this paper,we propose a intrusion detection algorithm based on auto-encoder and three-way decisions(AE-3WD)for industrial control networks,aiming at the security problem of industrial control network.The ideology of deep learning is similar to the idea of intrusion detection.Deep learning is a kind of intelligent algorithm and has the ability of automatically learning.It uses self-learning to enhance the experience and dynamic classification capabilities.We use deep learning to improve the intrusion detection rate and reduce the false alarm rate through learning,a denoising AutoEncoder and three-way decisions intrusion detection method AE-3WD is proposed to improve intrusion detection accuracy.In the processing,deep learning AutoEncoder is used to extract the features of high-dimensional data by combining the coefficient penalty and reconstruction loss function of the encode layer during the training mode.A multi-feature space can be constructed by multiple feature extractions from AutoEncoder,and then a decision for intrusion behavior or normal behavior is made by three-way decisions.NSL-KDD data sets are used to the experiments.The experiment results prove that our proposed method can extract meaningful features and effectively improve the performance of intrusion detection.展开更多
基金We are grateful for the National Natural Science Foundation of China(51765004)the support of Science and Technology Innovation Fund of Gansu Agricultural University(GAU-QDFC-2019-10)+1 种基金the Fuxi Talent Project of Gansu Agricultural University(GAUFX-02J01)and the Sheng Tong Sheng Science and Technology Innovation Fund of Gansu Agricultural University(GSAU-STS-1731).
文摘The yield reduction caused by miss-seeding in potato mechanized sowing is astonishing.The existing research always needs to install a spare compensator on the original seed-metering device.Therefore,problems of complex planter structure and compensated potato seed poor landing accuracy need to be solved urgently.Consequently,a scheme of integrated seeding and compensating potato planter based on one-way clutch is proposed in this paper.Based on a basic‘improved one raw potato planter’and the working principle of one-way clutch,power of seed-metering system is provided through main power transmission one-way clutch by land wheels when the system works properly.However,when miss-seeding detection system with infrared radiation deciding that a miss-seeding incident has happened,the seed-metering power will be replaced by a compensatory motor through compensating one-way clutch at a higher speed.Thus,the idea of catching-up compensation can be realized.After compensation is completed,the system controller disconnects the compensatory motor,and the seed-metering power will naturally switch to the land wheels again.A prototype based on this idea was built.Field tests showed that the accuracy of seed monitoring system is more than 99.9%;the adoption of catching-up compensation scheme does not bring about empty spoon rate rise significantly.Within the range of 0.2-0.8 m/s of the seed-metering chain speed,although the average success compensation rate decreases evidently with the increase of the chain speed,the success compensation rate is still near 70%even at 0.8 m/s,the vast majority of missed seeds can be compensated effectively.
基金supported by National Nature Science Foundation of China (Grant No.61471182)Postgraduate Research&Practice Innovation Program of Jiangsu Province (Grant No.KYCX20_2993)Jiangsu postgraduate research innovation project (SJCX18_0784)。
文摘In this paper,we propose a intrusion detection algorithm based on auto-encoder and three-way decisions(AE-3WD)for industrial control networks,aiming at the security problem of industrial control network.The ideology of deep learning is similar to the idea of intrusion detection.Deep learning is a kind of intelligent algorithm and has the ability of automatically learning.It uses self-learning to enhance the experience and dynamic classification capabilities.We use deep learning to improve the intrusion detection rate and reduce the false alarm rate through learning,a denoising AutoEncoder and three-way decisions intrusion detection method AE-3WD is proposed to improve intrusion detection accuracy.In the processing,deep learning AutoEncoder is used to extract the features of high-dimensional data by combining the coefficient penalty and reconstruction loss function of the encode layer during the training mode.A multi-feature space can be constructed by multiple feature extractions from AutoEncoder,and then a decision for intrusion behavior or normal behavior is made by three-way decisions.NSL-KDD data sets are used to the experiments.The experiment results prove that our proposed method can extract meaningful features and effectively improve the performance of intrusion detection.
