Sediment particles,as one of the key components of drip irrigation technology,significantly affect the service life of emitters and restrict the popularization of drip irrigation technology.Hence,two types of patch dr...Sediment particles,as one of the key components of drip irrigation technology,significantly affect the service life of emitters and restrict the popularization of drip irrigation technology.Hence,two types of patch drip irrigation emitters,focusing on the anti-clogging performance through the experiment,were investigated.The dynamic variations in the clogging characteristics of emitters,specifically were subjected to statistical analysis.The movement mechanism of emitter clogging and discharging sediment was studied.The effects of emitter structure and position factors on emitter clogging were analyzed.The results show that the pressure-compensated emitter exhibits superior anti-clogging perfor-mance,with a service life that is 227.8%greater than that of the labyrinth channel emitter.A single structural factor cannot completely evaluate the anti-clogging performance of emitters.All factors causing emitter clogging should be considered comprehensively.Emitters contain sensitive sediment prone to clogging,however,significant blockage occurs primarily when the sediment content is elevated.The discharge of sediment,denoted as V90,from the emitter is affected by the accumulative effect of clogged sediment.These results may offer valuable insights for the application and advancement of drip irrigation technology.展开更多
Extensive experiments suggest that kurtosis-based fingerprint features are effective for specific emitter identification (SEI). Nevertheless, the lack of mechanistic explanation restricts the use of fingerprint featur...Extensive experiments suggest that kurtosis-based fingerprint features are effective for specific emitter identification (SEI). Nevertheless, the lack of mechanistic explanation restricts the use of fingerprint features to a data-driven technique and fur-ther reduces the adaptability of the technique to other datasets. To address this issue, the mechanism how the phase noise of high-frequency oscillators and the nonlinearity of power ampli-fiers affect the kurtosis of communication signals is investigated. Mathematical models are derived for intentional modulation (IM) and unintentional modulation (UIM). Analysis indicates that the phase noise of high-frequency oscillators and the nonlinearity of power amplifiers affect the kurtosis frequency and amplitude, respectively. A novel SEI method based on frequency and ampli-tude of the signal kurtosis (FA-SK) is further proposed. Simula-tion and real-world experiments validate theoretical analysis and also confirm the efficiency and effectiveness of the proposed method.展开更多
Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the rea...Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the real world,which makes the existing approaches perform poorly for recognition tasks in different scenes.In this paper,we propose a domain generaliza-tion framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments.Specifically,we propose an end-to-end denoising based domain-invariant radar emitter recognition network(DDIRNet)consisting of a denoising model and a domain invariant representation learning model(IRLM),which mutually benefit from each other.For the signal denoising model,a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model.For the domain invariant representation learning model,contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distri-bution.Moreover,we design a data augmentation method that improves the diversity of signal data for training.Extensive experiments on classification have shown that DDIRNet achieves up to 6.4%improvement compared with the state-of-the-art radar emitter recognition methods.The proposed method pro-vides a promising direction to solve the radar emitter signal recognition problem.展开更多
Existing specific emitter identification(SEI)methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages,which reduce the identification accuracy of emi...Existing specific emitter identification(SEI)methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages,which reduce the identification accuracy of emitters and complicate the procedures of identification.In this paper,we propose a deep SEI approach via multidimensional feature extraction for radio frequency fingerprints(RFFs),namely,RFFsNet-SEI.Particularly,we extract multidimensional physical RFFs from the received signal by virtue of variational mode decomposition(VMD)and Hilbert transform(HT).The physical RFFs and I-Q data are formed into the balanced-RFFs,which are then used to train RFFsNet-SEI.As introducing model-aided RFFs into neural network,the hybrid-driven scheme including physical features and I-Q data is constructed.It improves physical interpretability of RFFsNet-SEI.Meanwhile,since RFFsNet-SEI identifies individual of emitters from received raw data in end-to-end,it accelerates SEI implementation and simplifies procedures of identification.Moreover,as the temporal features and spectral features of the received signal are both extracted by RFFsNet-SEI,identification accuracy is improved.Finally,we compare RFFsNet-SEI with the counterparts in terms of identification accuracy,computational complexity,and prediction speed.Experimental results illustrate that the proposed method outperforms the counterparts on the basis of simulation dataset and real dataset collected in the anechoic chamber.展开更多
In low signal-to-noise ratio(SNR)environments,the traditional radar emitter recognition(RER)method struggles to recognize multiple radar emitter signals in parallel.This paper proposes a multi-label classification and...In low signal-to-noise ratio(SNR)environments,the traditional radar emitter recognition(RER)method struggles to recognize multiple radar emitter signals in parallel.This paper proposes a multi-label classification and recognition method for multiple radar-emitter modulation types based on a residual network.This method can quickly perform parallel classification and recognition of multi-modulation radar time-domain aliasing signals under low SNRs.First,we perform time-frequency analysis on the received signal to extract the normalized time-frequency image through the short-time Fourier transform(STFT).The time-frequency distribution image is then denoised using a deep normalized convolutional neural network(DNCNN).Secondly,the multi-label classification and recognition model for multi-modulation radar emitter time-domain aliasing signals is established,and learning the characteristics of radar signal time-frequency distribution image dataset to achieve the purpose of training model.Finally,time-frequency image is recognized and classified through the model,thus completing the automatic classification and recognition of the time-domain aliasing signal.Simulation results show that the proposed method can classify and recognize radar emitter signals of different modulation types in parallel under low SNRs.展开更多
Six-year old apple trees were selected for field experiment.The objective of this study was to obtain the reasonable arrangement of surge-root irrigation emitters in apple orchards.There were three factors:the buried ...Six-year old apple trees were selected for field experiment.The objective of this study was to obtain the reasonable arrangement of surge-root irrigation emitters in apple orchards.There were three factors:the buried depth H(25,40,55 cm),the horizontal distance L(30,40,60 cm)between the emitters and the trunk of the experimental tree,and the number of the irrigation emitters N(1,2,4).The effect of the arrangement of surge-root irrigation emitters on the growth,yield and irrigation water use efficiency(IWUE)of apple trees were studied in Northern Shaanxi where the irrigation quota takes 60%-75%of the field water capacity.The results showed that the arrangement of emitters for surge-root irrigation had a significant effect on apple tree yield and IWUE,especially,the yield and IWUE reached 28388.17 kg/hm2 and 16.83 kg/m3 in treatment T3,respectively.At the same L and N levels(T1,T2,and T3),the yield and IWUE in treatment T3 were the highest,and the yields in treatments T1 and T2 were decreased by 26.22%and 31.48%,while IWUE is reduced by14.02%and 18.12%compared with T3,respectively.At the same H and N levels(T3,T4,and T5),the yield and IWUE of apple trees were decreased with increasing L level.Especially,when L was 30 cm(T3),the yield and IWUE were the highest.The same L and H levels(T3,T6,and T7)could promote the growth of apple trees when N was 2(T3).Compared with treatment T3,it was found that the increment of new shoots was decreased by 8.07%-18.71%,and the fruit diameter was decreased by 5.41%-9.11%.Therefore,two emitters should be arranged symmetrically on both sides of an apple tree,each was buried at a 40 cm depth and 30 cm away from the trunk of the tree to effectively improve the yield and IWUE of the apple tree in mountainous areas in Northern Shaanxi.展开更多
Beam shaping is required for semiconductor lasers to achieve high optical fiber coupling efficiency in many applications.But the positioning errors on optics may reduce beam shaping effects,and then lead to low optica...Beam shaping is required for semiconductor lasers to achieve high optical fiber coupling efficiency in many applications.But the positioning errors on optics may reduce beam shaping effects,and then lead to low optical fiber coupling efficiency.In this work,the positioning errors models for the single emitter laser diode beam shaping system are established.Moreover,the relationships between the errors and the beam shaping effect of each shapers are analysed.Subsequently,the relationship between the errors and the optical fiber coupling efficiency is analysed.The result shows that position errors in the Z axis direction on the fast axis collimator have the greatest influence on the shaping effect,followed by the position errors in the Z axis direction on the converging lens,which should be strictly suppressed in actual operation.Besides,the position errors have a significant influence on the optical fiber coupling efficiency and need to be avoided.展开更多
An analytical approach was developed to design a single uniformly sloping lateral in the micro-irrigation systems.Emission uniformity was used as the water application uniformity criterion.Energy relations based on th...An analytical approach was developed to design a single uniformly sloping lateral in the micro-irrigation systems.Emission uniformity was used as the water application uniformity criterion.Energy relations based on the energy-gradient-line approach were revamped to account for the spatial variance of emitter outflow and the emitter connections local energy losses.Four pressure head grade line profiles were distinguished:uphill,horizontal,gentle downhill and steep downhill.Analytical expressions of emission uniformity by hydraulic variation for each pressure profile were developed based on the design variables:length and diameter of lateral,emitter spacing,emitter flow equation parameters,equivalent length characterizing local losses and ground slope.The design conditions for selecting emitter type,the number of emitters per plant and designing the diameter of the uphill and steep downhill laterals were also developed.The nonlinear equations for determining lateral diameter and lateral length were solved iteratively by using the built-in root-finding function of(Tools>Goal Seek…)in the calculation spreadsheet of Microsoft Excel.The procedures also provide the options to fix the design lateral diameter with the commercial standard size or fix the design lateral length based on the field size.The operating inlet pressure and maximum amplitude of the pressure head throughout the lateral could also be determined easily by the procedure.Two numerical applications with various slope combinations indicate that the proposed analytical approach produces results close to the accurate stepwise numerical solutions.In comparison with Keller method,the proposed approach could produce more appropriate designs.展开更多
In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on m...In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.展开更多
Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition...Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition method based on a small amount of labeled data is developed.First,a small amount of labeled data are randomly sampled by using the bootstrap method,loss functions for three common deep learning net-works are improved,the uniform distribution and cross-entropy function are combined to reduce the overconfidence of softmax classification.Subsequently,the dataset obtained after sam-pling is adopted to train three improved networks so as to build the initial model.In addition,the unlabeled data are preliminarily screened through dynamic time warping(DTW)and then input into the initial model trained previously for judgment.If the judg-ment results of two or more networks are consistent,the unla-beled data are labeled and put into the labeled data set.Lastly,the three network models are input into the labeled dataset for training,and the final model is built.As revealed by the simula-tion results,the semi-supervised learning method adopted in this paper is capable of exploiting a small amount of labeled data and basically achieving the accuracy of labeled data recognition.展开更多
To examine the working principle of vertical tube irrigation, variations in vertical tube emitter discharge and their causes were analyzed in the laboratory experiment. The effects of the pressure head, initial soil w...To examine the working principle of vertical tube irrigation, variations in vertical tube emitter discharge and their causes were analyzed in the laboratory experiment. The effects of the pressure head, initial soil water content, and tube diameter on the emitter discharge of the vertical tube were studied. The results show that quantitative relationship between the time and cumulative infiltration and emitter discharge of the vertical tube is obtained, and R 2 is more than 0.98. Emitter discharge exhibits a positive and negative correlation with the pressure head and soil water content, respectively. Tube dia- meter has a nonsignificant effect on the emitter discharge. Changes of the soil water content around the emitter water outlet are the main causes of emitter discharge variations. In the experiments, the range of vertical tube emitter discharge is 0.056-1.102 L/h. The emitter of vertical tube irrigation automatically adjusts the soil water content and maintains the root zone soil water content within an appropriate range, which achieves continuous irrigation, and further achieves the effect of water-saving.展开更多
基金National Natural Science Foundation of China(52269011,52469008)。
文摘Sediment particles,as one of the key components of drip irrigation technology,significantly affect the service life of emitters and restrict the popularization of drip irrigation technology.Hence,two types of patch drip irrigation emitters,focusing on the anti-clogging performance through the experiment,were investigated.The dynamic variations in the clogging characteristics of emitters,specifically were subjected to statistical analysis.The movement mechanism of emitter clogging and discharging sediment was studied.The effects of emitter structure and position factors on emitter clogging were analyzed.The results show that the pressure-compensated emitter exhibits superior anti-clogging perfor-mance,with a service life that is 227.8%greater than that of the labyrinth channel emitter.A single structural factor cannot completely evaluate the anti-clogging performance of emitters.All factors causing emitter clogging should be considered comprehensively.Emitters contain sensitive sediment prone to clogging,however,significant blockage occurs primarily when the sediment content is elevated.The discharge of sediment,denoted as V90,from the emitter is affected by the accumulative effect of clogged sediment.These results may offer valuable insights for the application and advancement of drip irrigation technology.
基金supported by the Youth Science and Technology Innovation Award of National University of Defense Technology (18/19-QNCXJ)the National Science Foundation of China (62271494)
文摘Extensive experiments suggest that kurtosis-based fingerprint features are effective for specific emitter identification (SEI). Nevertheless, the lack of mechanistic explanation restricts the use of fingerprint features to a data-driven technique and fur-ther reduces the adaptability of the technique to other datasets. To address this issue, the mechanism how the phase noise of high-frequency oscillators and the nonlinearity of power ampli-fiers affect the kurtosis of communication signals is investigated. Mathematical models are derived for intentional modulation (IM) and unintentional modulation (UIM). Analysis indicates that the phase noise of high-frequency oscillators and the nonlinearity of power amplifiers affect the kurtosis frequency and amplitude, respectively. A novel SEI method based on frequency and ampli-tude of the signal kurtosis (FA-SK) is further proposed. Simula-tion and real-world experiments validate theoretical analysis and also confirm the efficiency and effectiveness of the proposed method.
基金supported by the National Natural Science Foundation of China(62101575)the Research Project of NUDT(ZK22-57)the Self-directed Project of State Key Laboratory of High Performance Computing(202101-16).
文摘Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the real world,which makes the existing approaches perform poorly for recognition tasks in different scenes.In this paper,we propose a domain generaliza-tion framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments.Specifically,we propose an end-to-end denoising based domain-invariant radar emitter recognition network(DDIRNet)consisting of a denoising model and a domain invariant representation learning model(IRLM),which mutually benefit from each other.For the signal denoising model,a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model.For the domain invariant representation learning model,contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distri-bution.Moreover,we design a data augmentation method that improves the diversity of signal data for training.Extensive experiments on classification have shown that DDIRNet achieves up to 6.4%improvement compared with the state-of-the-art radar emitter recognition methods.The proposed method pro-vides a promising direction to solve the radar emitter signal recognition problem.
基金supported by the National Natural Science Foundation of China(62061003)Sichuan Science and Technology Program(2021YFG0192)the Research Foundation of the Civil Aviation Flight University of China(ZJ2020-04,J2020-033)。
文摘Existing specific emitter identification(SEI)methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages,which reduce the identification accuracy of emitters and complicate the procedures of identification.In this paper,we propose a deep SEI approach via multidimensional feature extraction for radio frequency fingerprints(RFFs),namely,RFFsNet-SEI.Particularly,we extract multidimensional physical RFFs from the received signal by virtue of variational mode decomposition(VMD)and Hilbert transform(HT).The physical RFFs and I-Q data are formed into the balanced-RFFs,which are then used to train RFFsNet-SEI.As introducing model-aided RFFs into neural network,the hybrid-driven scheme including physical features and I-Q data is constructed.It improves physical interpretability of RFFsNet-SEI.Meanwhile,since RFFsNet-SEI identifies individual of emitters from received raw data in end-to-end,it accelerates SEI implementation and simplifies procedures of identification.Moreover,as the temporal features and spectral features of the received signal are both extracted by RFFsNet-SEI,identification accuracy is improved.Finally,we compare RFFsNet-SEI with the counterparts in terms of identification accuracy,computational complexity,and prediction speed.Experimental results illustrate that the proposed method outperforms the counterparts on the basis of simulation dataset and real dataset collected in the anechoic chamber.
基金The authors would like to acknowledge National Natural Science Foundation of China under Grant 61973037 and Grant 61673066 to provide fund for conducting experiments.
文摘In low signal-to-noise ratio(SNR)environments,the traditional radar emitter recognition(RER)method struggles to recognize multiple radar emitter signals in parallel.This paper proposes a multi-label classification and recognition method for multiple radar-emitter modulation types based on a residual network.This method can quickly perform parallel classification and recognition of multi-modulation radar time-domain aliasing signals under low SNRs.First,we perform time-frequency analysis on the received signal to extract the normalized time-frequency image through the short-time Fourier transform(STFT).The time-frequency distribution image is then denoised using a deep normalized convolutional neural network(DNCNN).Secondly,the multi-label classification and recognition model for multi-modulation radar emitter time-domain aliasing signals is established,and learning the characteristics of radar signal time-frequency distribution image dataset to achieve the purpose of training model.Finally,time-frequency image is recognized and classified through the model,thus completing the automatic classification and recognition of the time-domain aliasing signal.Simulation results show that the proposed method can classify and recognize radar emitter signals of different modulation types in parallel under low SNRs.
基金Supporting founds:National Key R&D Program(2016YFC0400204)Natural Science Foundation of China(51479161,51279157,51779205)。
文摘Six-year old apple trees were selected for field experiment.The objective of this study was to obtain the reasonable arrangement of surge-root irrigation emitters in apple orchards.There were three factors:the buried depth H(25,40,55 cm),the horizontal distance L(30,40,60 cm)between the emitters and the trunk of the experimental tree,and the number of the irrigation emitters N(1,2,4).The effect of the arrangement of surge-root irrigation emitters on the growth,yield and irrigation water use efficiency(IWUE)of apple trees were studied in Northern Shaanxi where the irrigation quota takes 60%-75%of the field water capacity.The results showed that the arrangement of emitters for surge-root irrigation had a significant effect on apple tree yield and IWUE,especially,the yield and IWUE reached 28388.17 kg/hm2 and 16.83 kg/m3 in treatment T3,respectively.At the same L and N levels(T1,T2,and T3),the yield and IWUE in treatment T3 were the highest,and the yields in treatments T1 and T2 were decreased by 26.22%and 31.48%,while IWUE is reduced by14.02%and 18.12%compared with T3,respectively.At the same H and N levels(T3,T4,and T5),the yield and IWUE of apple trees were decreased with increasing L level.Especially,when L was 30 cm(T3),the yield and IWUE were the highest.The same L and H levels(T3,T6,and T7)could promote the growth of apple trees when N was 2(T3).Compared with treatment T3,it was found that the increment of new shoots was decreased by 8.07%-18.71%,and the fruit diameter was decreased by 5.41%-9.11%.Therefore,two emitters should be arranged symmetrically on both sides of an apple tree,each was buried at a 40 cm depth and 30 cm away from the trunk of the tree to effectively improve the yield and IWUE of the apple tree in mountainous areas in Northern Shaanxi.
基金Project(51475479) supported by the National Natural Science Foundation of ChinaProject(2017YFB1104800) supported by the National Key Research and Development Program of China+2 种基金Project(2016GK2098) supported by the Key Research and Development Program of Hunan Province,ChinaProject(ZZYJKT2017-07) supported by the State Key Laboratory of High Performance Complex Manufacturing,Central South University,ChinaProject(JMTZ201804) supported by the Key Laboratory for Precision&Non-traditional Machining of Ministry of Education,Dalian University of Technology,China
文摘Beam shaping is required for semiconductor lasers to achieve high optical fiber coupling efficiency in many applications.But the positioning errors on optics may reduce beam shaping effects,and then lead to low optical fiber coupling efficiency.In this work,the positioning errors models for the single emitter laser diode beam shaping system are established.Moreover,the relationships between the errors and the beam shaping effect of each shapers are analysed.Subsequently,the relationship between the errors and the optical fiber coupling efficiency is analysed.The result shows that position errors in the Z axis direction on the fast axis collimator have the greatest influence on the shaping effect,followed by the position errors in the Z axis direction on the converging lens,which should be strictly suppressed in actual operation.Besides,the position errors have a significant influence on the optical fiber coupling efficiency and need to be avoided.
基金supported by the Special Foundation of National Science & Technology Supporting Plan( 2011BAD29B02)the "111" Project (B12007)
文摘An analytical approach was developed to design a single uniformly sloping lateral in the micro-irrigation systems.Emission uniformity was used as the water application uniformity criterion.Energy relations based on the energy-gradient-line approach were revamped to account for the spatial variance of emitter outflow and the emitter connections local energy losses.Four pressure head grade line profiles were distinguished:uphill,horizontal,gentle downhill and steep downhill.Analytical expressions of emission uniformity by hydraulic variation for each pressure profile were developed based on the design variables:length and diameter of lateral,emitter spacing,emitter flow equation parameters,equivalent length characterizing local losses and ground slope.The design conditions for selecting emitter type,the number of emitters per plant and designing the diameter of the uphill and steep downhill laterals were also developed.The nonlinear equations for determining lateral diameter and lateral length were solved iteratively by using the built-in root-finding function of(Tools>Goal Seek…)in the calculation spreadsheet of Microsoft Excel.The procedures also provide the options to fix the design lateral diameter with the commercial standard size or fix the design lateral length based on the field size.The operating inlet pressure and maximum amplitude of the pressure head throughout the lateral could also be determined easily by the procedure.Two numerical applications with various slope combinations indicate that the proposed analytical approach produces results close to the accurate stepwise numerical solutions.In comparison with Keller method,the proposed approach could produce more appropriate designs.
基金Project(61301095)supported by the National Natural Science Foundation of ChinaProject(QC2012C070)supported by Heilongjiang Provincial Natural Science Foundation for the Youth,ChinaProjects(HEUCF130807,HEUCFZ1129)supported by the Fundamental Research Funds for the Central Universities of China
文摘In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.
文摘Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition method based on a small amount of labeled data is developed.First,a small amount of labeled data are randomly sampled by using the bootstrap method,loss functions for three common deep learning net-works are improved,the uniform distribution and cross-entropy function are combined to reduce the overconfidence of softmax classification.Subsequently,the dataset obtained after sam-pling is adopted to train three improved networks so as to build the initial model.In addition,the unlabeled data are preliminarily screened through dynamic time warping(DTW)and then input into the initial model trained previously for judgment.If the judg-ment results of two or more networks are consistent,the unla-beled data are labeled and put into the labeled data set.Lastly,the three network models are input into the labeled dataset for training,and the final model is built.As revealed by the simula-tion results,the semi-supervised learning method adopted in this paper is capable of exploiting a small amount of labeled data and basically achieving the accuracy of labeled data recognition.
基金National Natural Science Foundation of China (41571222)。
文摘To examine the working principle of vertical tube irrigation, variations in vertical tube emitter discharge and their causes were analyzed in the laboratory experiment. The effects of the pressure head, initial soil water content, and tube diameter on the emitter discharge of the vertical tube were studied. The results show that quantitative relationship between the time and cumulative infiltration and emitter discharge of the vertical tube is obtained, and R 2 is more than 0.98. Emitter discharge exhibits a positive and negative correlation with the pressure head and soil water content, respectively. Tube dia- meter has a nonsignificant effect on the emitter discharge. Changes of the soil water content around the emitter water outlet are the main causes of emitter discharge variations. In the experiments, the range of vertical tube emitter discharge is 0.056-1.102 L/h. The emitter of vertical tube irrigation automatically adjusts the soil water content and maintains the root zone soil water content within an appropriate range, which achieves continuous irrigation, and further achieves the effect of water-saving.
