The simulation precision of the classic load model(CLM)is affected by the increasing proportion of installed energy storage capacity in the grid.This paper studies the all-vanadium redox flow battery(VRB)and proposes ...The simulation precision of the classic load model(CLM)is affected by the increasing proportion of installed energy storage capacity in the grid.This paper studies the all-vanadium redox flow battery(VRB)and proposes an equivalent model based on the measurement-based load modeling method,which can simulate the maximum output of the VRB energy storage system and fit the external characteristic of the system precisely in the occurrence of large disturbance and continuous small disturbance.The equivalent model is connected to CLM to form a generalized synthesis load model(GSLM),which considers the parameters of distribution network and reactive power compensation.Compared with CLM,GSLM has better structures and can describe the load characteristics of distribution network with energy storage system more precisely.Simulation results validate the effectiveness and good parameter stability of GSLM,and show that the higher the proportion of energy storage in the grid is the better description ability GSLM has.展开更多
To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)netwo...To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)method.The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the dynamics.The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters.The proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.展开更多
Xigeda formation is a type of hundredmeter-thick lacustrine sediments of being prone to triggering landslides along the trunk channel and tributaries of the upper Yangtze River in China. The Yonglang landslide located...Xigeda formation is a type of hundredmeter-thick lacustrine sediments of being prone to triggering landslides along the trunk channel and tributaries of the upper Yangtze River in China. The Yonglang landslide located near Yonglang Town of Dechang County in Sichuan Province of China, which was a typical Xigeda formation landslide, was stabilized by anti-slide piles. Loading tests on a loading-test pile were conducted to measure the displacements and moments. The uncertainty of the tested geomechanical parameters of the Yonglang landslide over certain ranges would be problematic during the evaluation of the landslide. Thus, uniform design was introduced in the experimental design,and by which, numerical analyses of the loading-test pile were performed using Fast Lagrangian Analysis of Continua(FLAC3D) to acquire a database of the geomechanical parameters of the Yonglang landslide and the corresponding displacements of the loadingtest pile. A three-layer back-propagation neural network was established and trained with the database, and then tested and verified for its accuracy and reliability in numerical simulations. Displacement back analysis was conducted by substituting the displacements of the loading-test pile to the well-trained three-layer back-propagation neural network so as to identify the geomechanical parameters of the Yonglang landslide. The neuralnetwork-based displacement back analysis method with the proposed methodology is verified to be accurate and reliable for the identification of the uncertain geomechanical parameters of landslides.展开更多
Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distribu...Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.展开更多
The multi- layers feedforward neural network is used for inversion ofmaterial constants of fluid-saturated porous media. The direct analysis of fluid-saturated porousmedia is carried out with the boundary element meth...The multi- layers feedforward neural network is used for inversion ofmaterial constants of fluid-saturated porous media. The direct analysis of fluid-saturated porousmedia is carried out with the boundary element method. The dynamic displacement responses obtainedfrom direct analysis for prescribed material parameters constitute the sample sets training neuralnetwork. By virtue of the effective L-M training algorithm and the Tikhonov regularization method aswell as the GCV method for an appropriate selection of regu-larization parameter, the inversemapping from dynamic displacement responses to material constants is performed. Numerical examplesdemonstrate the validity of the neural network method.展开更多
A complete study for the implementation of wireless sensor networks in the intelligent building is presented. We carry out some experiments to find out the factors affecting the network performance. Several vital para...A complete study for the implementation of wireless sensor networks in the intelligent building is presented. We carry out some experiments to find out the factors affecting the network performance. Several vital parameters which are related to the link quality are measured before deploying the actual system. And then, we propose an optimized routing protocol based on the analysis of the test data. We evaluate the deployment strategies to ensure the excellent performance of the wireless sensor networks under the real working conditions. And the evaluation results show that the presented system could satisfy the requirements of the applications in the intelligent building.展开更多
A new parameter coordination and robust optimization approach for multidisciplinary design is presented. Firstly, the constraints network model is established to support engineering change, coordination and optimizati...A new parameter coordination and robust optimization approach for multidisciplinary design is presented. Firstly, the constraints network model is established to support engineering change, coordination and optimization. In this model, interval boxes are adopted to describe the uncertainty of design parameters quantitatively to enhance the design robustness. Secondly, the parameter coordination method is presented to solve the constraints network model, monitor the potential conflicts due to engineering changes, and obtain the consistency solution space corresponding to the given product specifications. Finally, the robust parameter optimization model is established, and genetic arithmetic is used to obtain the robust optimization parameter. An example of bogie design is analyzed to show the scheme to be effective.展开更多
Dune networks are widely distributed in the world＇s deserts,which include primary ridges and secondary ridges.However,they have not been sufficiently studied in a systematic manner and their origins and spatial and m...Dune networks are widely distributed in the world＇s deserts,which include primary ridges and secondary ridges.However,they have not been sufficiently studied in a systematic manner and their origins and spatial and morphological characteristics remain unclear.To provide information on the geomorphology of dune networks,we analyze the software geomorphologic patterns of the dune networks in China＇s Tengger Desert using matrix and laboratory to process remote-sensing images.Based on analysis of image features and their layout in a topographic map,we identify two types of dune networks （square and rectangular dune networks） with different size and morphological structures in the Tengger Desert.Four important geomorphic pattern parameters,ridge length,spacing,orientation and defect density,are analyzed.The length of primary ridges of dune networks decreases from northwest of the desert to the southeast,resulting an increasing spacing and a transition from rectangular dune networks to square dune networks.Wind regime and sediment supply are responsible for the variation in pattern parameters.We use the spacing and defect density data to estimate the construction time of dune networks and found that the dune networks in the Tengger Desert formed since about 1.3 ka BP.展开更多
In large mines,single fan is usually not enough to ventilate all the working areas.Single mine-fan approach cannot be directly applied to multiple-fan networks because the present of multiple pressures and air quantit...In large mines,single fan is usually not enough to ventilate all the working areas.Single mine-fan approach cannot be directly applied to multiple-fan networks because the present of multiple pressures and air quantities associated with each fan in the network.Accordingly,each fan in a multiple-fan system has its own mine characteristic curve,or a subsystem curve.Under some consideration,the conventional concept of a mine characteristic curve of a single-fan system can be directly extended to that of a particular fan within a multiple-fan system.In this paper the mutual effect of the fans on each other and their effect on the stability of the ventilation network were investigated by Hardy Cross algorithm combined with a switching-parameters technique.To show the validity and reliability of this algorithm,the stability of the ventilation system of Abu-Tartur Mine(one of the largest underground mine in Egypt)has been studied.展开更多
A sequential diagnosis method is proposed based on a fuzzy neural network realized by ＂the partially-linearized neural network （PNN）＂, by which the fault types of rotating machinery can be precisely and effectivel...A sequential diagnosis method is proposed based on a fuzzy neural network realized by ＂the partially-linearized neural network （PNN）＂, by which the fault types of rotating machinery can be precisely and effectively distinguished at an early stage on the basis of the possibilities of symptom parameters. The non-dimensional symptom parameters in time domain are defined for reflecting the features of time signals measured for the fault diagnosis of rotating machinery. The synthetic detection index is also proposed to evaluate the sensitivity of non-dimensional symptom parameters for detecting faults. The practical example of condition diagnosis for detecting and distinguishing fault states of a centrifugal pump system, such as cavitation, impeller eccentricity which often occur in a centrifugal pump system, are shown to verify the efficiency of the method proposed in this paper.展开更多
This study is focused on the discussion of a modern GNSS network and datum in Uzbekistan. Considering the significance difference （up to 200 m） in positions of the local ellipsoidal datum and the global datum, the p...This study is focused on the discussion of a modern GNSS network and datum in Uzbekistan. Considering the significance difference （up to 200 m） in positions of the local ellipsoidal datum and the global datum, the precise transformation parameters between national geodetic datum CS-42, and the World Geodetic System 1984 （WGS84） global datum used by the GPS is estimated. This study aims to evaluate the ac- curacy of the currently used transformation parameters from different sources in the region, and give preliminary recommendations for using these sets also. The differences between transformed, original and WGS-84 coordinates were calculated and evaluated. On the basis of this difference, different zones for determination of transformation parameters have been proposed.This study is focused on the discussion of a modern GNSS network and datum in Uzbekistan. Considering the significance difference （up to 200 m） in positions of the local ellipsoidal datum and the global datum, the precise transformation parameters between national geodetic datum CS-42, and the World Geodetic System 1984 （WGS84） global datum used by the GPS is estimated. This study aims to evaluate the accuracy of the currently used transformation parameters from different sources in the region, and give preliminary recommendations for using these sets also. The differences between transformed, original and WGS-84 coordinates were calculated and evaluated. On the basis of this difference, different zones for determination of transformation parameters have been proposed.展开更多
Two parameterization schemes for vertical eddy diffusivity were utilized to investigate their impacts on both the daily and monthly mean concentrations of ozone and NOy, which are the major fractions of the sum of all...Two parameterization schemes for vertical eddy diffusivity were utilized to investigate their impacts on both the daily and monthly mean concentrations of ozone and NOy, which are the major fractions of the sum of all reactive nitrogen species, i.e., NOy=NO＋NO2＋HNO3＋PAN. Simulations indicate that great changes in the vertical diffusivity usually occur within the planetary boundary layer （PBL）. Daily and monthly mean concentrations of NOy are much more sensitive to changes in the vertical diffusivity than those of ozone and ozone and NOy levels only at or in （relatively） clean sites and areas, where long-range transport plays a crucial role, display roughly equivalent sensitivity. The results strongly suggest that a widely-accepted parameterization scheme be selected and the refinement of the model＇s vertical resolution in the PBL be required, even for regional and long-term studies, and ozone only being examined in an effort to judge the model＇s performance be unreliable, and NOy be included for model evaluations.展开更多
An adaptive repetitive control scheme is presented for a class of nonlinearly parameterized systems based on the fuzzy basis function network （FBFN）. The parameters of the fuzzy rules are tuned with adaptive schemes...An adaptive repetitive control scheme is presented for a class of nonlinearly parameterized systems based on the fuzzy basis function network （FBFN）. The parameters of the fuzzy rules are tuned with adaptive schemes. To attenuate chattering effectively, the discontinuous control term is approximated by an adaptive PI control structure. The bound of the discontinuous control term is assumed to be unknown and estimated by an adaptive mechanism. Based on the Lyapunov stability theory, an adaptive repetitive control law is proposed to guarantee the closed-loop stability and the tracking performance. By means of FBFNs, which avoid the nonlinear parameterization from entering into the adaptive repetitive control, the controller singularity problem is solved. The proposed approach does not require an exact structure of the system dynamics, and the proposed controller is utilized to control a model of permanent-magnet linear synchronous motor subject to significant disturbances and parameter uncertainties. The simulation results demonstrate the effectiveness of the proposed method.展开更多
针对废墟环境下红外图像人体检测任务中存在的图像分辨率低且人体特征不明显的问题,基于YOLO框架设计了一种包含重参数化(re-parameterization)和多尺度大核卷积(multi-scale large kernel convolution)的红外图像人体检测网络RML-YOLO(...针对废墟环境下红外图像人体检测任务中存在的图像分辨率低且人体特征不明显的问题,基于YOLO框架设计了一种包含重参数化(re-parameterization)和多尺度大核卷积(multi-scale large kernel convolution)的红外图像人体检测网络RML-YOLO(re-parameterization multi-scale large kernel convolution)。该网络通过空间和通道重构注意力模块,将注意值集中到对检测任务更重要的区域。通过Sobel算子强化边缘特征,提高对不同姿态人体的检测能力。RML-YOLO的有效性在自制数据集上得到验证。在只有1.8×10~6可学习参数的情况下,模型的AP50和AP50-75分别达到了91.2%和87.3%,与参数量相近的YOLOv8-n相比分别提高了4.4%和5.3%。结果表明,RML-YOLO显著提高了利用红外图像进行废墟环境下人体检测的精度。展开更多
基金This work was supported in part by the national natural science foundation of China(51677059)Guangdong Power Grid Company Limited Project.(GDKJXM00000025)。
文摘The simulation precision of the classic load model(CLM)is affected by the increasing proportion of installed energy storage capacity in the grid.This paper studies the all-vanadium redox flow battery(VRB)and proposes an equivalent model based on the measurement-based load modeling method,which can simulate the maximum output of the VRB energy storage system and fit the external characteristic of the system precisely in the occurrence of large disturbance and continuous small disturbance.The equivalent model is connected to CLM to form a generalized synthesis load model(GSLM),which considers the parameters of distribution network and reactive power compensation.Compared with CLM,GSLM has better structures and can describe the load characteristics of distribution network with energy storage system more precisely.Simulation results validate the effectiveness and good parameter stability of GSLM,and show that the higher the proportion of energy storage in the grid is the better description ability GSLM has.
基金co-supported by the National Natural Science Foundation of China(No.52192633)the Natural Science Foundation of Shaanxi Province,China(No.2022JC-03)the Fundamental Research Funds for the Central Universities,China(No.XJSJ23164)。
文摘To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)method.The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the dynamics.The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters.The proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.
基金supported by the "Light of West China" Program of Chinese Academy of Sciences (Grant No.Y6R2250250)the National Basic Research Program of China (973 Program, Grant No.2013CB733201)+2 种基金the One-Hundred Talents Program of Chinese Academy of Sciences (LijunSu)the Key Research Program of Frontier Sciences, Chinese Academy of Sciences (Grant No.QYZDB-SSW-DQC010)the Youth Fund of Institute of Mountain Hazards and Environment, Chinese Academy of Sciences (Grant No. Y6K2110110)
文摘Xigeda formation is a type of hundredmeter-thick lacustrine sediments of being prone to triggering landslides along the trunk channel and tributaries of the upper Yangtze River in China. The Yonglang landslide located near Yonglang Town of Dechang County in Sichuan Province of China, which was a typical Xigeda formation landslide, was stabilized by anti-slide piles. Loading tests on a loading-test pile were conducted to measure the displacements and moments. The uncertainty of the tested geomechanical parameters of the Yonglang landslide over certain ranges would be problematic during the evaluation of the landslide. Thus, uniform design was introduced in the experimental design,and by which, numerical analyses of the loading-test pile were performed using Fast Lagrangian Analysis of Continua(FLAC3D) to acquire a database of the geomechanical parameters of the Yonglang landslide and the corresponding displacements of the loadingtest pile. A three-layer back-propagation neural network was established and trained with the database, and then tested and verified for its accuracy and reliability in numerical simulations. Displacement back analysis was conducted by substituting the displacements of the loading-test pile to the well-trained three-layer back-propagation neural network so as to identify the geomechanical parameters of the Yonglang landslide. The neuralnetwork-based displacement back analysis method with the proposed methodology is verified to be accurate and reliable for the identification of the uncertain geomechanical parameters of landslides.
文摘Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.
基金the National Natural Science Foundation of China (Nos.19872002 and 10272003)Climbing Foundation of Northern Jiaotong University
文摘The multi- layers feedforward neural network is used for inversion ofmaterial constants of fluid-saturated porous media. The direct analysis of fluid-saturated porousmedia is carried out with the boundary element method. The dynamic displacement responses obtainedfrom direct analysis for prescribed material parameters constitute the sample sets training neuralnetwork. By virtue of the effective L-M training algorithm and the Tikhonov regularization method aswell as the GCV method for an appropriate selection of regu-larization parameter, the inversemapping from dynamic displacement responses to material constants is performed. Numerical examplesdemonstrate the validity of the neural network method.
基金supported by National Natural Science Foundation of China under Grant No.60802016, 60972010by China Next Generation Internet (CNGI) project under Grant No.CNGI-09-03-05
文摘A complete study for the implementation of wireless sensor networks in the intelligent building is presented. We carry out some experiments to find out the factors affecting the network performance. Several vital parameters which are related to the link quality are measured before deploying the actual system. And then, we propose an optimized routing protocol based on the analysis of the test data. We evaluate the deployment strategies to ensure the excellent performance of the wireless sensor networks under the real working conditions. And the evaluation results show that the presented system could satisfy the requirements of the applications in the intelligent building.
基金This project is supported by National Natural Science Foundation of China (No.60304015, No.50575142).
文摘A new parameter coordination and robust optimization approach for multidisciplinary design is presented. Firstly, the constraints network model is established to support engineering change, coordination and optimization. In this model, interval boxes are adopted to describe the uncertainty of design parameters quantitatively to enhance the design robustness. Secondly, the parameter coordination method is presented to solve the constraints network model, monitor the potential conflicts due to engineering changes, and obtain the consistency solution space corresponding to the given product specifications. Finally, the robust parameter optimization model is established, and genetic arithmetic is used to obtain the robust optimization parameter. An example of bogie design is analyzed to show the scheme to be effective.
基金funding from the Ministry of Science and Technology of the People’s Republic of China (2013CB956000)the National Natural Science Foundation of China (41130533)
文摘Dune networks are widely distributed in the world＇s deserts,which include primary ridges and secondary ridges.However,they have not been sufficiently studied in a systematic manner and their origins and spatial and morphological characteristics remain unclear.To provide information on the geomorphology of dune networks,we analyze the software geomorphologic patterns of the dune networks in China＇s Tengger Desert using matrix and laboratory to process remote-sensing images.Based on analysis of image features and their layout in a topographic map,we identify two types of dune networks （square and rectangular dune networks） with different size and morphological structures in the Tengger Desert.Four important geomorphic pattern parameters,ridge length,spacing,orientation and defect density,are analyzed.The length of primary ridges of dune networks decreases from northwest of the desert to the southeast,resulting an increasing spacing and a transition from rectangular dune networks to square dune networks.Wind regime and sediment supply are responsible for the variation in pattern parameters.We use the spacing and defect density data to estimate the construction time of dune networks and found that the dune networks in the Tengger Desert formed since about 1.3 ka BP.
文摘In large mines,single fan is usually not enough to ventilate all the working areas.Single mine-fan approach cannot be directly applied to multiple-fan networks because the present of multiple pressures and air quantities associated with each fan in the network.Accordingly,each fan in a multiple-fan system has its own mine characteristic curve,or a subsystem curve.Under some consideration,the conventional concept of a mine characteristic curve of a single-fan system can be directly extended to that of a particular fan within a multiple-fan system.In this paper the mutual effect of the fans on each other and their effect on the stability of the ventilation network were investigated by Hardy Cross algorithm combined with a switching-parameters technique.To show the validity and reliability of this algorithm,the stability of the ventilation system of Abu-Tartur Mine(one of the largest underground mine in Egypt)has been studied.
基金Sci-Tech Planning Projects of Chongqing City,China(No.CSTC2007AA7003).
文摘A sequential diagnosis method is proposed based on a fuzzy neural network realized by ＂the partially-linearized neural network （PNN）＂, by which the fault types of rotating machinery can be precisely and effectively distinguished at an early stage on the basis of the possibilities of symptom parameters. The non-dimensional symptom parameters in time domain are defined for reflecting the features of time signals measured for the fault diagnosis of rotating machinery. The synthetic detection index is also proposed to evaluate the sensitivity of non-dimensional symptom parameters for detecting faults. The practical example of condition diagnosis for detecting and distinguishing fault states of a centrifugal pump system, such as cavitation, impeller eccentricity which often occur in a centrifugal pump system, are shown to verify the efficiency of the method proposed in this paper.
基金supported by the research-applied project of Astronomical Institute,State Committee on Science and Technologyof Uzbekistan(FA-A5-F014)
文摘This study is focused on the discussion of a modern GNSS network and datum in Uzbekistan. Considering the significance difference （up to 200 m） in positions of the local ellipsoidal datum and the global datum, the precise transformation parameters between national geodetic datum CS-42, and the World Geodetic System 1984 （WGS84） global datum used by the GPS is estimated. This study aims to evaluate the ac- curacy of the currently used transformation parameters from different sources in the region, and give preliminary recommendations for using these sets also. The differences between transformed, original and WGS-84 coordinates were calculated and evaluated. On the basis of this difference, different zones for determination of transformation parameters have been proposed.This study is focused on the discussion of a modern GNSS network and datum in Uzbekistan. Considering the significance difference （up to 200 m） in positions of the local ellipsoidal datum and the global datum, the precise transformation parameters between national geodetic datum CS-42, and the World Geodetic System 1984 （WGS84） global datum used by the GPS is estimated. This study aims to evaluate the accuracy of the currently used transformation parameters from different sources in the region, and give preliminary recommendations for using these sets also. The differences between transformed, original and WGS-84 coordinates were calculated and evaluated. On the basis of this difference, different zones for determination of transformation parameters have been proposed.
基金the National Natural Science Foundation of China （Grant No. 40575068） the National Key Project of Basic Research of China （Grant No. 2005CB422205） the Knowledge Innovation Project of Chinese Academy of Sciences （Grant No. KZCX2-YW-205）.
文摘Two parameterization schemes for vertical eddy diffusivity were utilized to investigate their impacts on both the daily and monthly mean concentrations of ozone and NOy, which are the major fractions of the sum of all reactive nitrogen species, i.e., NOy=NO＋NO2＋HNO3＋PAN. Simulations indicate that great changes in the vertical diffusivity usually occur within the planetary boundary layer （PBL）. Daily and monthly mean concentrations of NOy are much more sensitive to changes in the vertical diffusivity than those of ozone and ozone and NOy levels only at or in （relatively） clean sites and areas, where long-range transport plays a crucial role, display roughly equivalent sensitivity. The results strongly suggest that a widely-accepted parameterization scheme be selected and the refinement of the model＇s vertical resolution in the PBL be required, even for regional and long-term studies, and ozone only being examined in an effort to judge the model＇s performance be unreliable, and NOy be included for model evaluations.
基金supported by the National Natural Science Foundation of China (61203041)the Chinese National Post-doctor Science Foundation (2011M500217)
文摘An adaptive repetitive control scheme is presented for a class of nonlinearly parameterized systems based on the fuzzy basis function network （FBFN）. The parameters of the fuzzy rules are tuned with adaptive schemes. To attenuate chattering effectively, the discontinuous control term is approximated by an adaptive PI control structure. The bound of the discontinuous control term is assumed to be unknown and estimated by an adaptive mechanism. Based on the Lyapunov stability theory, an adaptive repetitive control law is proposed to guarantee the closed-loop stability and the tracking performance. By means of FBFNs, which avoid the nonlinear parameterization from entering into the adaptive repetitive control, the controller singularity problem is solved. The proposed approach does not require an exact structure of the system dynamics, and the proposed controller is utilized to control a model of permanent-magnet linear synchronous motor subject to significant disturbances and parameter uncertainties. The simulation results demonstrate the effectiveness of the proposed method.
文摘针对废墟环境下红外图像人体检测任务中存在的图像分辨率低且人体特征不明显的问题,基于YOLO框架设计了一种包含重参数化(re-parameterization)和多尺度大核卷积(multi-scale large kernel convolution)的红外图像人体检测网络RML-YOLO(re-parameterization multi-scale large kernel convolution)。该网络通过空间和通道重构注意力模块,将注意值集中到对检测任务更重要的区域。通过Sobel算子强化边缘特征,提高对不同姿态人体的检测能力。RML-YOLO的有效性在自制数据集上得到验证。在只有1.8×10~6可学习参数的情况下,模型的AP50和AP50-75分别达到了91.2%和87.3%,与参数量相近的YOLOv8-n相比分别提高了4.4%和5.3%。结果表明,RML-YOLO显著提高了利用红外图像进行废墟环境下人体检测的精度。
