Global variance reduction is a bottleneck in Monte Carlo shielding calculations.The global variance reduction problem requires that the statistical error of the entire space is uniform.This study proposed a grid-AIS m...Global variance reduction is a bottleneck in Monte Carlo shielding calculations.The global variance reduction problem requires that the statistical error of the entire space is uniform.This study proposed a grid-AIS method for the global variance reduction problem based on the AIS method,which was implemented in the Monte Carlo program MCShield.The proposed method was validated using the VENUS-Ⅲ international benchmark problem and a self-shielding calculation example.The results from the VENUS-Ⅲ benchmark problem showed that the grid-AIS method achieved a significant reduction in the variance of the statistical errors of the MESH grids,decreasing from 1.08×10^(-2) to 3.84×10^(-3),representing a 64.00% reduction.This demonstrates that the grid-AIS method is effective in addressing global issues.The results of the selfshielding calculation demonstrate that the grid-AIS method produced accurate computational results.Moreover,the grid-AIS method exhibited a computational efficiency approximately one order of magnitude higher than that of the AIS method and approximately two orders of magnitude higher than that of the conventional Monte Carlo method.展开更多
The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-n...The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.展开更多
Automatic modulation classification(AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior perfo...Automatic modulation classification(AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior performances in classification accuracy and robustness. In this paper, we propose a novel, high resolution and multi-scale feature fusion convolutional neural network model with a squeeze-excitation block, referred to as HRSENet,to classify different kinds of modulation signals.The proposed model establishes a parallel computing mechanism of multi-resolution feature maps through the multi-layer convolution operation, which effectively reduces the information loss caused by downsampling convolution. Moreover, through dense skipconnecting at the same resolution and up-sampling or down-sampling connection at different resolutions, the low resolution representation of the deep feature maps and the high resolution representation of the shallow feature maps are simultaneously extracted and fully integrated, which is benificial to mine signal multilevel features. Finally, the feature squeeze and excitation module embedded in the decoder is used to adjust the response weights between channels, further improving classification accuracy of proposed model.The proposed HRSENet significantly outperforms existing methods in terms of classification accuracy on the public dataset “Over the Air” in signal-to-noise(SNR) ranging from-2dB to 20dB. The classification accuracy in the proposed model achieves 85.36% and97.30% at 4dB and 10dB, respectively, with the improvement by 9.71% and 5.82% compared to LWNet.Furthermore, the model also has a moderate computation complexity compared with several state-of-the-art methods.展开更多
Blades are one of the important components on aircraft engines.If they break due to vibration failure,the normal operation of the entire engine will be offected.Therefore,it is necessary to measure their natural frequ...Blades are one of the important components on aircraft engines.If they break due to vibration failure,the normal operation of the entire engine will be offected.Therefore,it is necessary to measure their natural frequency before installing them on the engine to avoid resonance.At present,most blade vibration testing systems require manual operation by operators,which has high requirements for operators and the testing process is also very cumbersome.Therefore,the testing efficiency is low and cannot meet the needs of efficient testing.To solve the current problems of low testing efficiency and high operational requirements,a high-precision and high-efficiency automatic test system is designed.The testing accuracy of this system can reach ±1%,and the testing efficiency is improved by 37% compared to manual testing.Firstly,the influence of compression force and vibration exciter position on natural frequency test is analyzed by amplitude-frequency curve,so as to calibrate servo cylinder and fourdimensional motion platform.Secondly,the sine wave signal is used as the excitation to sweep the blade linearly,and the natural frequency is determined by the amplitude peak in the frequency domain.Finally,the accuracy experiment and efficiency experiment are carried out on the developed test system,whose results verify its high efficiency and high precision.展开更多
Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the ...Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.展开更多
Due to the limited computational capability and the diversity of the Internet of Things devices working in different environment,we consider fewshot learning-based automatic modulation classification(AMC)to improve it...Due to the limited computational capability and the diversity of the Internet of Things devices working in different environment,we consider fewshot learning-based automatic modulation classification(AMC)to improve its reliability.A data enhancement module(DEM)is designed by a convolutional layer to supplement frequency-domain information as well as providing nonlinear mapping that is beneficial for AMC.Multimodal network is designed to have multiple residual blocks,where each residual block has multiple convolutional kernels of different sizes for diverse feature extraction.Moreover,a deep supervised loss function is designed to supervise all parts of the network including the hidden layers and the DEM.Since different model may output different results,cooperative classifier is designed to avoid the randomness of single model and improve the reliability.Simulation results show that this few-shot learning-based AMC method can significantly improve the AMC accuracy compared to the existing methods.展开更多
Aiming at the problem that the data-driven automatic correlation methods which are difficult to adapt to the automatic correlation of oil-bearing strata with large changes in lateral sedimentary facies and strata thic...Aiming at the problem that the data-driven automatic correlation methods which are difficult to adapt to the automatic correlation of oil-bearing strata with large changes in lateral sedimentary facies and strata thickness,an intelligent automatic correlation method of oil-bearing strata based on pattern constraints is formed.We propose to introduce knowledge-driven in automatic correlation of oil-bearing strata,constraining the correlation process by stratigraphic sedimentary patterns and improving the similarity measuring machine and conditional constraint dynamic time warping algorithm to automate the correlation of marker layers and the interfaces of each stratum.The application in Shishen 100 block in the Shinan Oilfield of the Bohai Bay Basin shows that the coincidence rate of the marker layers identified by this method is over 95.00%,and the average coincidence rate of identified oil-bearing strata reaches 90.02% compared to artificial correlation results,which is about 17 percentage points higher than that of the existing automatic correlation methods.The accuracy of the automatic correlation of oil-bearing strata has been effectively improved.展开更多
A scheme of guidance and control is presented to meet the requirements for automatic landing of unmanned aerial vehicles (UAVs) based on the airborne digital flight control system and radio tracker on ground station. ...A scheme of guidance and control is presented to meet the requirements for automatic landing of unmanned aerial vehicles (UAVs) based on the airborne digital flight control system and radio tracker on ground station. An automatic landing system is realized for an unmanned aerial vehicle. The results of real time simulation and flight test are given to illustrate the effectiveness and availability of the scheme. Results meet all the requirements for automatic landing of the unmanned aerial vehicle.展开更多
Data acquisition, analysis and calibrating system affiliated with the vehicle is developed for the research on the automatic shift system (ASS). Considering the vehicle’s hard environment such as vibration, high and ...Data acquisition, analysis and calibrating system affiliated with the vehicle is developed for the research on the automatic shift system (ASS). Considering the vehicle’s hard environment such as vibration, high and low temperature, electromagnetic disturbance and so on, the most suitable project is selected. PC104 transfers data with ECU by serial communication and a solid state disk is used as a FLASH ROM. Some techniques including frequency division of data is adopted in the software design in order to ensure the sampling frequency. The analysis and debug software is also contrived according to the characteristic of the ASS. The system plays an important role in the development of the ASS because of the good reliability and practicability in the application.展开更多
To realize automatic control of automobile transmission performance test stand Methods The automatic control technique of the lubricant temperature,the program- controll- edautomaticshifting of the transmission,the c...To realize automatic control of automobile transmission performance test stand Methods The automatic control technique of the lubricant temperature,the program- controll- edautomaticshifting of the transmission,the continuous adjusting of revolution speed and load, data-acquisition and data real-time processing were adopted.Results The lubricant temperature was controlled at the set temperature ±2℃.The automatic shifting of the trans- mission is simple,reliable and accurate.The automatic adjusting of load and rotation speed is rapidandaccurate,the torque divergence is ±1N·m,the rotation speed divergence is ±5r/min Conclusion The four kinds of techniques are applied into the automobile transmission perfor- mance test stand successfully. mancetest stand successfully.展开更多
This paper is concerned about the automatic finite element modeling of a wing structure. The row and column method is used to identify the structure parts(ribs, spars, skins and pillars). A customization module of...This paper is concerned about the automatic finite element modeling of a wing structure. The row and column method is used to identify the structure parts(ribs, spars, skins and pillars). A customization module of PCL(PATRAN Command Language under PATRAN 6.0) code from constructing airfoil curves to creating the entire wing FEM model is designed and developed. The geome tric, mesh density, material, load and boundary parameters can be easily and correctly input with the friendly interactive interface. A VFW614 wing is analyzed from creating airfoil curves to the show of stresses calculated by using NASTRAN 68 as an example. The results show that this customization module is very effective and efficient.展开更多
We summarize the guidance and control techniques of automatic carrier landing for carrier-based aircraft.First,we analyze the carrier landing operations of the manned fixed-wing aircraft,unmanned fixed-wing aircraft a...We summarize the guidance and control techniques of automatic carrier landing for carrier-based aircraft.First,we analyze the carrier landing operations of the manned fixed-wing aircraft,unmanned fixed-wing aircraft and helicopters.Second,we look into the navigation and guidance system and the flight control methods for current different aircraft.Finally,we draw several conclusions of the development prospects for aircraft carrier landing,including the precision landing control techniques,precision approach and landing guidance techniques,and adaptive,reconfigurable and intelligent flight control techniques.展开更多
The control system of Hefei Light Source II(HLS-Ⅱ) is a distributed system based on the experimental physics and industrial control system(EPICS). It is necessary to maintain the central configuration files for the e...The control system of Hefei Light Source II(HLS-Ⅱ) is a distributed system based on the experimental physics and industrial control system(EPICS). It is necessary to maintain the central configuration files for the existing archiving system. When the process variables in the control system are added, removed, or updated, the configuration files must be manually modified to maintain consistency with the control system. This paper presents a new method for data archiving, which realizes the automatic configuration of the archiving parameters. The system uses microservice architecture to integrate the EPICS Archiver Appliance and Rec Sync. In this way, the system can collect all the archived meta-configuration from the distributed input/output controllers and enter them into the EPICS Archiver Appliance automatically. Furthermore, we also developed a web-based GUI to provide automatic visualization of real-time and historical data. At present,this system is under commissioning at HLS-Ⅱ. The results indicate that the new archiving system is reliable and convenient to operate. The operation mode without maintenance is valuable for large-scale scientific facilities.展开更多
Based on detail analysis of clutch engaging process control targets and adaptive demands, a control strategy which is based on speed signal, different from that of based on main clutch displacement signal, is put forw...Based on detail analysis of clutch engaging process control targets and adaptive demands, a control strategy which is based on speed signal, different from that of based on main clutch displacement signal, is put forward. It considers both jerk and slipping work which are the most commonly used quality evaluating indexes of vehicle starting phase. The adaptive control system and its reference model are discussed profoundly. Taking the adaptability to different starting gears and different road conditions as examples, some proving field test records are shown to illustrate the main clutch adaptive control strategy at starting phase. Proving field test gives acceptable results.展开更多
We present a path morphology method to separate total rock pore space into matrix, fractures and vugs and derive their pore structure spectrum. Thus, we can achieve fine pore evaluation in fracture–vug reservoirs bas...We present a path morphology method to separate total rock pore space into matrix, fractures and vugs and derive their pore structure spectrum. Thus, we can achieve fine pore evaluation in fracture–vug reservoirs based on electric imaging logging data. We automatically identify and extract fracture–vug information from the electric imaging images by adopting a path morphological operator that remains flexible enough to fit rectilinear and slightly curved structures because they are independent of the structuring element shape. The Otsu method was used to extract fracture–vug information from the background noise caused by the matrix. To accommodate the differences in scale and form of the different target regions,including fracture and vug path, operators with different lengths were selected for their recognition and extraction at the corresponding scale. Polynomial and elliptic functions are used to fit the extracted fractures and vugs, respectively, and the fracture–vug parameters are deduced from the fitted edge. Finally, test examples of numerical simulation data and several measured well data have been provided for the verification of the effectiveness and adaptability of the path morphology method in the application of electric imaging logging data processing. This also provides algorithm support for the fine evaluation of fracture–vug reservoirs.展开更多
For carrier-based unmanned aerial vehicles(UAVs),one of the important problems is the design of an automatic carrier landing system(ACLS)that would enable the UAVs to accomplish autolanding on the aircraft carrier.How...For carrier-based unmanned aerial vehicles(UAVs),one of the important problems is the design of an automatic carrier landing system(ACLS)that would enable the UAVs to accomplish autolanding on the aircraft carrier.However,due to the movements of the flight deck with six degree-of-freedom,the autolanding becomes sophisticated.To solve this problem,an accurate and effective ACLS is developed,which is composed of an optimal preview control based flight control system and a Kalman filter based deck motion predictor.The preview control fuses the future information of the reference glide slope to improve landing precision.The reference glide slope is normally a straight line.However,the deck motion will change the position of the ideal landing point,and tracking the ideal straight glide slope may cause landing failure.Therefore,the predictive deck motion information from the deck motion predictor is used to correct the reference glide slope,which decreases the dispersion around the desired landing point.Finally,simulations are carried out to verify the performance of the designed ACLS based on a nonlinear UAV model.展开更多
Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extract...Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.展开更多
This paper proposes a PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm. This algorithm combines the linear feature extracted from principal component analysis （PCA） and nonlinear featu...This paper proposes a PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm. This algorithm combines the linear feature extracted from principal component analysis （PCA） and nonlinear feature extracted from kernel principal component analysis （KPCA） respectively, and then utilizes the adaptive feature fusion algorithm which is based on the weighted maximum margin criterion （WMMC） to fuse the features in order to achieve better performance. The linear regression classifier is used in the experiments. The experimental results indicate that the proposed self-fusion algorithm achieves higher recognition rate compared with the traditional PCA and KPCA feature fusion algorithms.展开更多
A new type of a loading and measuring system was developed for testing failure and deformation of rock core samples with an industrial CT （ICT） scanner.The loading and measuring system consisted of a loading system ...A new type of a loading and measuring system was developed for testing failure and deformation of rock core samples with an industrial CT （ICT） scanner.The loading and measuring system consisted of a loading system and a computer control system.The maximum servo-controlled force was 2 tonnes.The new system was a high-stiffness system with a small size.During ICT tests,rock core samples could be easily loaded in the axial direction.So the initiation,propagation,and coalescence of cracks in core samples were observed on ICT images.展开更多
Automatically formed roadway(AFR)by roof cutting with bolt grouting(RCBG)is a new deep coal mining technology.By using this technology,the broken roadway roof is strengthened,and roof cutting is applied to cut off str...Automatically formed roadway(AFR)by roof cutting with bolt grouting(RCBG)is a new deep coal mining technology.By using this technology,the broken roadway roof is strengthened,and roof cutting is applied to cut off stress transfer between the roadway and gob to ensure the collapse of the overlying strata.The roadway is automatically formed owing to the broken expansion characteristics of the collapsed strata and mining pressure.Taking the Suncun Coal Mine as the engineering background,the control effect of this new technology on roadways was studied.To compare the law of stress evolution and the surrounding rock control mechanisms between AFR and traditional gob-side entry driving,a comparative study of geomechanical model tests on the above methods was carried out.The results showed that the new technology of AFR by RCBG effectively reduced the stress concentration of the roadway compared with gob-side entry driving.The side abutment pressure peak of the solid coal side was reduced by 24.3%,which showed an obvious pressure-releasing effect.Moreover,the position of the side abutment pressure peak was far from the solid coal side,making it more beneficial for roadway stability.The deformation of AFR surrounding rock was also smaller than the deformation of the gob-side entry driving by the overload test.The former was more beneficial for roadway stability than the latter under higher stress conditions.Field application tests showed that the new technology can effectively control roadway deformation.Moreover,the technology reduced roadway excavation and avoided resource waste caused by reserved coal pillars.展开更多
基金supported by the Platform Development Foundation of the China Institute for Radiation Protection(No.YP21030101)the National Natural Science Foundation of China(General Program)(Nos.12175114,U2167209)+1 种基金the National Key R&D Program of China(No.2021YFF0603600)the Tsinghua University Initiative Scientific Research Program(No.20211080081).
文摘Global variance reduction is a bottleneck in Monte Carlo shielding calculations.The global variance reduction problem requires that the statistical error of the entire space is uniform.This study proposed a grid-AIS method for the global variance reduction problem based on the AIS method,which was implemented in the Monte Carlo program MCShield.The proposed method was validated using the VENUS-Ⅲ international benchmark problem and a self-shielding calculation example.The results from the VENUS-Ⅲ benchmark problem showed that the grid-AIS method achieved a significant reduction in the variance of the statistical errors of the MESH grids,decreasing from 1.08×10^(-2) to 3.84×10^(-3),representing a 64.00% reduction.This demonstrates that the grid-AIS method is effective in addressing global issues.The results of the selfshielding calculation demonstrate that the grid-AIS method produced accurate computational results.Moreover,the grid-AIS method exhibited a computational efficiency approximately one order of magnitude higher than that of the AIS method and approximately two orders of magnitude higher than that of the conventional Monte Carlo method.
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation 2022M720419 to provide fund for conducting experiments。
文摘The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.
基金supported by the Beijing Natural Science Foundation (L202003)National Natural Science Foundation of China (No. 31700479)。
文摘Automatic modulation classification(AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior performances in classification accuracy and robustness. In this paper, we propose a novel, high resolution and multi-scale feature fusion convolutional neural network model with a squeeze-excitation block, referred to as HRSENet,to classify different kinds of modulation signals.The proposed model establishes a parallel computing mechanism of multi-resolution feature maps through the multi-layer convolution operation, which effectively reduces the information loss caused by downsampling convolution. Moreover, through dense skipconnecting at the same resolution and up-sampling or down-sampling connection at different resolutions, the low resolution representation of the deep feature maps and the high resolution representation of the shallow feature maps are simultaneously extracted and fully integrated, which is benificial to mine signal multilevel features. Finally, the feature squeeze and excitation module embedded in the decoder is used to adjust the response weights between channels, further improving classification accuracy of proposed model.The proposed HRSENet significantly outperforms existing methods in terms of classification accuracy on the public dataset “Over the Air” in signal-to-noise(SNR) ranging from-2dB to 20dB. The classification accuracy in the proposed model achieves 85.36% and97.30% at 4dB and 10dB, respectively, with the improvement by 9.71% and 5.82% compared to LWNet.Furthermore, the model also has a moderate computation complexity compared with several state-of-the-art methods.
基金supported by the National Natural Science Foundation of China (No.51975293)Aeronautical Science Foundation of China (No.2019ZD052010)Postgraduate Research & Practice Innovation Program of NUAA (No.xcxjh20230502)。
文摘Blades are one of the important components on aircraft engines.If they break due to vibration failure,the normal operation of the entire engine will be offected.Therefore,it is necessary to measure their natural frequency before installing them on the engine to avoid resonance.At present,most blade vibration testing systems require manual operation by operators,which has high requirements for operators and the testing process is also very cumbersome.Therefore,the testing efficiency is low and cannot meet the needs of efficient testing.To solve the current problems of low testing efficiency and high operational requirements,a high-precision and high-efficiency automatic test system is designed.The testing accuracy of this system can reach ±1%,and the testing efficiency is improved by 37% compared to manual testing.Firstly,the influence of compression force and vibration exciter position on natural frequency test is analyzed by amplitude-frequency curve,so as to calibrate servo cylinder and fourdimensional motion platform.Secondly,the sine wave signal is used as the excitation to sweep the blade linearly,and the natural frequency is determined by the amplitude peak in the frequency domain.Finally,the accuracy experiment and efficiency experiment are carried out on the developed test system,whose results verify its high efficiency and high precision.
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation under Grant No.2022M720419。
文摘Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.
基金supported in part by National Key Research and Development Program of China under Grant 2021YFB2900404.
文摘Due to the limited computational capability and the diversity of the Internet of Things devices working in different environment,we consider fewshot learning-based automatic modulation classification(AMC)to improve its reliability.A data enhancement module(DEM)is designed by a convolutional layer to supplement frequency-domain information as well as providing nonlinear mapping that is beneficial for AMC.Multimodal network is designed to have multiple residual blocks,where each residual block has multiple convolutional kernels of different sizes for diverse feature extraction.Moreover,a deep supervised loss function is designed to supervise all parts of the network including the hidden layers and the DEM.Since different model may output different results,cooperative classifier is designed to avoid the randomness of single model and improve the reliability.Simulation results show that this few-shot learning-based AMC method can significantly improve the AMC accuracy compared to the existing methods.
基金Supported by the National Natural Science Foundation of China(42272110)CNPC-China University of Petroleum(Beijing)Strategic Cooperation Project(ZLZX2020-02).
文摘Aiming at the problem that the data-driven automatic correlation methods which are difficult to adapt to the automatic correlation of oil-bearing strata with large changes in lateral sedimentary facies and strata thickness,an intelligent automatic correlation method of oil-bearing strata based on pattern constraints is formed.We propose to introduce knowledge-driven in automatic correlation of oil-bearing strata,constraining the correlation process by stratigraphic sedimentary patterns and improving the similarity measuring machine and conditional constraint dynamic time warping algorithm to automate the correlation of marker layers and the interfaces of each stratum.The application in Shishen 100 block in the Shinan Oilfield of the Bohai Bay Basin shows that the coincidence rate of the marker layers identified by this method is over 95.00%,and the average coincidence rate of identified oil-bearing strata reaches 90.02% compared to artificial correlation results,which is about 17 percentage points higher than that of the existing automatic correlation methods.The accuracy of the automatic correlation of oil-bearing strata has been effectively improved.
文摘A scheme of guidance and control is presented to meet the requirements for automatic landing of unmanned aerial vehicles (UAVs) based on the airborne digital flight control system and radio tracker on ground station. An automatic landing system is realized for an unmanned aerial vehicle. The results of real time simulation and flight test are given to illustrate the effectiveness and availability of the scheme. Results meet all the requirements for automatic landing of the unmanned aerial vehicle.
文摘Data acquisition, analysis and calibrating system affiliated with the vehicle is developed for the research on the automatic shift system (ASS). Considering the vehicle’s hard environment such as vibration, high and low temperature, electromagnetic disturbance and so on, the most suitable project is selected. PC104 transfers data with ECU by serial communication and a solid state disk is used as a FLASH ROM. Some techniques including frequency division of data is adopted in the software design in order to ensure the sampling frequency. The analysis and debug software is also contrived according to the characteristic of the ASS. The system plays an important role in the development of the ASS because of the good reliability and practicability in the application.
文摘To realize automatic control of automobile transmission performance test stand Methods The automatic control technique of the lubricant temperature,the program- controll- edautomaticshifting of the transmission,the continuous adjusting of revolution speed and load, data-acquisition and data real-time processing were adopted.Results The lubricant temperature was controlled at the set temperature ±2℃.The automatic shifting of the trans- mission is simple,reliable and accurate.The automatic adjusting of load and rotation speed is rapidandaccurate,the torque divergence is ±1N·m,the rotation speed divergence is ±5r/min Conclusion The four kinds of techniques are applied into the automobile transmission perfor- mance test stand successfully. mancetest stand successfully.
文摘This paper is concerned about the automatic finite element modeling of a wing structure. The row and column method is used to identify the structure parts(ribs, spars, skins and pillars). A customization module of PCL(PATRAN Command Language under PATRAN 6.0) code from constructing airfoil curves to creating the entire wing FEM model is designed and developed. The geome tric, mesh density, material, load and boundary parameters can be easily and correctly input with the friendly interactive interface. A VFW614 wing is analyzed from creating airfoil curves to the show of stresses calculated by using NASTRAN 68 as an example. The results show that this customization module is very effective and efficient.
基金supported in part by the National Natural Science Foundation of China(Nos.61741313,61304223)the Jiangsu Six Peak of Talents Program(No.KTHY-027)+1 种基金the Aeronautical Science Foundation(No.2016ZA52009)the Fundamental Research Funds for the Central Universities(Nos.NS2017015,NJ20170005).
文摘We summarize the guidance and control techniques of automatic carrier landing for carrier-based aircraft.First,we analyze the carrier landing operations of the manned fixed-wing aircraft,unmanned fixed-wing aircraft and helicopters.Second,we look into the navigation and guidance system and the flight control methods for current different aircraft.Finally,we draw several conclusions of the development prospects for aircraft carrier landing,including the precision landing control techniques,precision approach and landing guidance techniques,and adaptive,reconfigurable and intelligent flight control techniques.
基金supported by the National Natural Science Foundation of China(No.11375186)
文摘The control system of Hefei Light Source II(HLS-Ⅱ) is a distributed system based on the experimental physics and industrial control system(EPICS). It is necessary to maintain the central configuration files for the existing archiving system. When the process variables in the control system are added, removed, or updated, the configuration files must be manually modified to maintain consistency with the control system. This paper presents a new method for data archiving, which realizes the automatic configuration of the archiving parameters. The system uses microservice architecture to integrate the EPICS Archiver Appliance and Rec Sync. In this way, the system can collect all the archived meta-configuration from the distributed input/output controllers and enter them into the EPICS Archiver Appliance automatically. Furthermore, we also developed a web-based GUI to provide automatic visualization of real-time and historical data. At present,this system is under commissioning at HLS-Ⅱ. The results indicate that the new archiving system is reliable and convenient to operate. The operation mode without maintenance is valuable for large-scale scientific facilities.
文摘Based on detail analysis of clutch engaging process control targets and adaptive demands, a control strategy which is based on speed signal, different from that of based on main clutch displacement signal, is put forward. It considers both jerk and slipping work which are the most commonly used quality evaluating indexes of vehicle starting phase. The adaptive control system and its reference model are discussed profoundly. Taking the adaptability to different starting gears and different road conditions as examples, some proving field test records are shown to illustrate the main clutch adaptive control strategy at starting phase. Proving field test gives acceptable results.
基金granted access to projects supported by the National Major Fundamental Research Program of China ‘‘On basic research problems in applied geophysics for deep oil and gas fields’’(Grant Number 2013CB228605)CNPC Science and Technology Project(Grant Number 2016A-3303)and CNPC Logging Project(Grant Number 2017E-15)
文摘We present a path morphology method to separate total rock pore space into matrix, fractures and vugs and derive their pore structure spectrum. Thus, we can achieve fine pore evaluation in fracture–vug reservoirs based on electric imaging logging data. We automatically identify and extract fracture–vug information from the electric imaging images by adopting a path morphological operator that remains flexible enough to fit rectilinear and slightly curved structures because they are independent of the structuring element shape. The Otsu method was used to extract fracture–vug information from the background noise caused by the matrix. To accommodate the differences in scale and form of the different target regions,including fracture and vug path, operators with different lengths were selected for their recognition and extraction at the corresponding scale. Polynomial and elliptic functions are used to fit the extracted fractures and vugs, respectively, and the fracture–vug parameters are deduced from the fitted edge. Finally, test examples of numerical simulation data and several measured well data have been provided for the verification of the effectiveness and adaptability of the path morphology method in the application of electric imaging logging data processing. This also provides algorithm support for the fine evaluation of fracture–vug reservoirs.
基金supported in part by the National Natural Science Foundations of China(Nos.61304223,61673209,61533008)the Aeronautical Science Foundation(No.2016ZA 52009)the Fundamental Research Funds for the Central Universities(No.NJ20160026)
文摘For carrier-based unmanned aerial vehicles(UAVs),one of the important problems is the design of an automatic carrier landing system(ACLS)that would enable the UAVs to accomplish autolanding on the aircraft carrier.However,due to the movements of the flight deck with six degree-of-freedom,the autolanding becomes sophisticated.To solve this problem,an accurate and effective ACLS is developed,which is composed of an optimal preview control based flight control system and a Kalman filter based deck motion predictor.The preview control fuses the future information of the reference glide slope to improve landing precision.The reference glide slope is normally a straight line.However,the deck motion will change the position of the ideal landing point,and tracking the ideal straight glide slope may cause landing failure.Therefore,the predictive deck motion information from the deck motion predictor is used to correct the reference glide slope,which decreases the dispersion around the desired landing point.Finally,simulations are carried out to verify the performance of the designed ACLS based on a nonlinear UAV model.
基金supported by the National Natural Science Foundation of China [Nos. 61772452, 61379116]the Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi [No.2019L0847]the Natural Science Foundation of Hebei Province, China [No. F2015203046]
文摘Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.
基金supported in part by the National Natural Science Foundation of China under Grant No. 61033012, No. 611003177, and No. 61070181Fundamental Research Funds for the Central Universities under Grant No.1600-852016 and No. DUT12JR07
文摘This paper proposes a PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm. This algorithm combines the linear feature extracted from principal component analysis （PCA） and nonlinear feature extracted from kernel principal component analysis （KPCA） respectively, and then utilizes the adaptive feature fusion algorithm which is based on the weighted maximum margin criterion （WMMC） to fuse the features in order to achieve better performance. The linear regression classifier is used in the experiments. The experimental results indicate that the proposed self-fusion algorithm achieves higher recognition rate compared with the traditional PCA and KPCA feature fusion algorithms.
基金financially supported by the National Natural Science Foundation of China (Grant No. 50905186,No. 51174213)the Major State Basic Research Development Program Fund (Grant No. 2010CB226804)the Project-sponsored by SRF for ROCS,the Ministry of Education and Fundamental Research Funds for the Central Universities and Research Program in State Key Laboratory of Coal Resources and Safe Mining of China University of Mining and Technology
文摘A new type of a loading and measuring system was developed for testing failure and deformation of rock core samples with an industrial CT （ICT） scanner.The loading and measuring system consisted of a loading system and a computer control system.The maximum servo-controlled force was 2 tonnes.The new system was a high-stiffness system with a small size.During ICT tests,rock core samples could be easily loaded in the axial direction.So the initiation,propagation,and coalescence of cracks in core samples were observed on ICT images.
基金This work was supported by the National Natural Science Foundation of China(Nos.51874188,52074164,42077267,and 51927807)the Natural Science Foundation of Shandong Province,China(Nos.2019SDZY04 and ZR2020JQ23)the Project of Shandong Province Higher Educational Youth Innovation Science and Technology Program,China(No.2019KJG013).
文摘Automatically formed roadway(AFR)by roof cutting with bolt grouting(RCBG)is a new deep coal mining technology.By using this technology,the broken roadway roof is strengthened,and roof cutting is applied to cut off stress transfer between the roadway and gob to ensure the collapse of the overlying strata.The roadway is automatically formed owing to the broken expansion characteristics of the collapsed strata and mining pressure.Taking the Suncun Coal Mine as the engineering background,the control effect of this new technology on roadways was studied.To compare the law of stress evolution and the surrounding rock control mechanisms between AFR and traditional gob-side entry driving,a comparative study of geomechanical model tests on the above methods was carried out.The results showed that the new technology of AFR by RCBG effectively reduced the stress concentration of the roadway compared with gob-side entry driving.The side abutment pressure peak of the solid coal side was reduced by 24.3%,which showed an obvious pressure-releasing effect.Moreover,the position of the side abutment pressure peak was far from the solid coal side,making it more beneficial for roadway stability.The deformation of AFR surrounding rock was also smaller than the deformation of the gob-side entry driving by the overload test.The former was more beneficial for roadway stability than the latter under higher stress conditions.Field application tests showed that the new technology can effectively control roadway deformation.Moreover,the technology reduced roadway excavation and avoided resource waste caused by reserved coal pillars.
