The spherical plain bearing test bench is a necessary detecting equipment in the research process of self?lubricating spherical plain bearings. The varying environmental temperatures cause the thermal deformation of t...The spherical plain bearing test bench is a necessary detecting equipment in the research process of self?lubricating spherical plain bearings. The varying environmental temperatures cause the thermal deformation of the wear?depth detecting system of bearing test benches and then a ect the accuracy of the wear?depth detecting data. However, few researches about the spherical plain bearing test benches can be found with the implementation of the detect?ing error compensation. Based on the self?made modular spherical plain bearing test bench, two main causes of ther?mal errors, the friction heat of bearings and the environmental temperature variation, are analysed. The thermal errors caused by the friction heat of bearings are calculated, and the thermal deformation of the wear?depth detecting sys?tem caused by the varying environmental temperatures is detected. In view of the above results, the environmental temperature variation is the main cause of the two error factors. When the environmental temperatures rise is 10.3 °C, the thermal deformation is approximately 0.01 mm. In addition, the comprehensive compensating model of the thermal error of the wear?depth detecting system is built by multiple linear regression(MLR) and time series analysis. Compared with the detecting data of the thermal errors, the comprehensive compensating model has higher fitting precision, and the maximum residual is only 1 μm. A comprehensive compensating model of the thermal error of the wear?depth detecting system is proposed, which provides a theoretical basis for the improvement of the real?time wear?depth detecting precision of the spherical plain bearing test bench.展开更多
Microstructured roll workpieces have been widely used as functional components in the precision industries. Current researches on quality control have focused on surface profile measurement of microstructured roll wor...Microstructured roll workpieces have been widely used as functional components in the precision industries. Current researches on quality control have focused on surface profile measurement of microstructured roll workpieces, and types of measurement systems and measurement methods have been developed. However, low measurement efficiency and low measurement accuracy caused by setting errors are the common disadvantages for surface profile measurement of microstructured roll workpieces. In order to shorten the measurement time and enhance the measurement accuracy, a method for self-calibration and compensation of setting errors is proposed for surface profile measurement of microstructured roll workpieces. A measurement system is constructed for the measurement, in which a precision spindle is employed to rotate the roll workpiece and an air-bearing displacement sensor with a micro-stylus probe is employed to scan the microstructured surface of the roll workpiece. The resolution of the displacement sensor is 0.14 nm and that of the rotary encoder of the spindle was 0.15r~. Geometrical and mathematical models are established for analyzing the influences of the setting errors of the roll workpiece and the displacement sensor with respect to the axis of the spindle, including the eccentric error of the roll workpiece, the offset error of the sensor axis and the zero point error of the sensor output. Measurement experiments are carded out on a roll workpiece on which periodic microstructures are a period of 133 i^m along the circumferential direction. Experimental results demonstrate the feasibility of the self-compensation method. The proposed method can be used to detect and compensate the setting errors without using any additional accurate artifact.展开更多
Polarization mode dispersion(PMD) is considered to be the ultimate limitation in high-speed optical fiber communication systems. Establishing an effective control algorithm for adaptive PMD compensation is a challengi...Polarization mode dispersion(PMD) is considered to be the ultimate limitation in high-speed optical fiber communication systems. Establishing an effective control algorithm for adaptive PMD compensation is a challenging task, because PMD possesses the time-varying and statistical properties. The particle swarm optimization(PSO) algorithm is introduced into self-adaptive PMD compensation as feedback control algorithm. The experiment results show that PSO-based control algorithm has some unique features of rapid convergence to the global optimum without being trapped in local sub-optima and good robustness to noise in the optical fiber transmission line that has never been achieved in PMD compensation before.展开更多
We propose a novel lumped time-delay compensation scheme for all-optical analog-to-digital conversion based on soliton self-frequency shift and optical interconnection techniques. A linearly chirped fiber Bragg gratin...We propose a novel lumped time-delay compensation scheme for all-optical analog-to-digital conversion based on soliton self-frequency shift and optical interconnection techniques. A linearly chirped fiber Bragg grating is optimally designed and used to compensate for the entire time-delays of the quantized pulses precisely. Simulation results show that the compensated coding pulses are well synchronized with a time difference less than 3.3 ps, which can support a maximum sampling rate of 151.52 GSa/s. The proposed scheme can efficiently reduce the structure complexity and cost of all-optical analog-to-digital conversion compared to the previous schemes with multiple optical time-delay lines.展开更多
Self-positioning of a shearer is the key technology for mining with a man-less working face. In an underground coal mine all radio navigation; satellite positioning or celestial navigation methods have their limitatio...Self-positioning of a shearer is the key technology for mining with a man-less working face. In an underground coal mine all radio navigation; satellite positioning or celestial navigation methods have their limitations. We analyzed an inertial navi-gation system intended to guide the movement a shearer and designed a self-positioning device for the shearer. Simulation tests were also performed on the system. We analyzed the errors observed in these tests to show that the main reason for the low preci-sion of the self-positioning system is accumulated error in the inertial sensor. A Kalman filtering algorithm used in combination with the shearer motion model effectively reduces the measurement errors of the self-positioning system by compensating for gyroscopic drift. Finally, we built an error compensation model to reduce accumulated errors using continuous correction to provide self-positioning of the shearer within a certain range of accuracy.展开更多
A new robust fault-tolerant controller scheme integrating a main controller and a compensator for the self-repairing flight control system is discussed.The main controller is designed for high performance of the origi...A new robust fault-tolerant controller scheme integrating a main controller and a compensator for the self-repairing flight control system is discussed.The main controller is designed for high performance of the original faultless system.The compensating controller can be seen as a standalone loop added to the system to compensate the effects of fault guaranteeing the stability of the system.A design method is proposed using nonlinear dynamic inverse control as the main controller and nonlinear extended state observer-based compensator.The stability of the whole closed-loop system is analyzed.Feasibility and validity of the new controller is demonstrated with an aircraft simulation example.展开更多
This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorith...This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.展开更多
The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the ...The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the properties of polyurethane,i.e.,dispersion stability,dynamical viscoelasticity and mechanical properties are discussed.It is found that the optimum molar ratio of epichlorohydrin and diethylenetriamine is 1:2.A mois-展开更多
The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative f...The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative for example,emphasizing the interpretation of the inheritance and development of Chinese culture so as to study the importance of Culture Self-Consciousness in Chinese Philosophy,in the context of English globalization. That is to say,this paper stresses the spirits and the stand of nation 's demonstration on pursuing peace,cooperation and sustainable development in the civilization continuity from traditional China to the contemporary China,with practical philosophic view.展开更多
Desktop 3D printers have revolutionized how designers and makers prototype and manufacture certain products.Highly popular fuse deposition modeling(FDM)desktop printers have enabled a shift to low-cost consumer goods ...Desktop 3D printers have revolutionized how designers and makers prototype and manufacture certain products.Highly popular fuse deposition modeling(FDM)desktop printers have enabled a shift to low-cost consumer goods markets,through reduced capital equipment investment and consumable material costs.However,with this drive to reduce costs,the computer numerical control(CNC)systems implemented in FDM printers are often compromised by poor accuracy and contouring errors.This condition is most critical as users begin to use 3D-printed components in load-bearing applications or to perform mechanical functions.Improved methods of low-cost 3D printer calibration are needed before their open-design potential can be realized in applications,including 3D-printed orthotics and prosthetics.This paper applies methodologies associated with high-precision CNC machining systems,namely,kinematic error modeling and compensation coupled with standardized test methods from ISO230-4,such as the ballbar for kinematic and dynamic error measurements,to examine the influence and feasibility for use on low-cost CNC/3D printing platforms.Recently,the U.S.Food and Drug Administration's"Technical considerations for additive manufactured medical devices"highlighted the need to develop standards specific to additive manufacturing in regulated manufacturing environments.This paper shows the benefits of the methods described within ISO230-4 for error assessment,alongside applying kinematic error modeling and compensation to the popular kinematic configuration of an Ultimaker 3D printer.A Renishaw ballbar QC10 is used to quantify the Ultimaker's errors and thereby populate the error model.This method quantifies machine errors and populates these in a mathematical model of the CNC system.Then,a post-processor can be used to compensate the printing code.Subsequently,the ballbar is used to demonstrate the dramatic impact of the error compensation model on the accuracy and contouring of the Ultimaker printer with 58%reduction in overall circularity error and 90%reduction in squareness error.展开更多
Thermal manikin plays important roles in simulating thethermal state of human bodies to facilitate the evaluationof thermal comfort properties of various clothing assem-blies.Based on the heat balance principle and an...Thermal manikin plays important roles in simulating thethermal state of human bodies to facilitate the evaluationof thermal comfort properties of various clothing assem-blies.Based on the heat balance principle and analysis ofrelated factors,the heat production rate of manikin isrecommended as an efficient evaluation index.Whereas,its inside heat production which occurs as a result of theexistence of temperature difference between its insidepart and outside surface,should not be ignored.Through a series of theoretical analysis and calculations,a compensative equation is deduced in this paper.展开更多
A new bipolar temperature-compensated current reference is proposed. The first-order temperature compensation is achieved by the idea of self temperature-compensation configuration exploiting the temperature coefficie...A new bipolar temperature-compensated current reference is proposed. The first-order temperature compensation is achieved by the idea of self temperature-compensation configuration exploiting the temperature coefficient of a combined resistor. The second-order compensation employs a VBE-tracking thermal-startup technique to obtain improved temperature performance. The proposed circuit can operate down to a 1-V supply. A temperature coefficient of 46.6×10?6/℃ [0, 100℃] at a 1-V supply and a supply regulation of 0.036%/V at 25℃ are achieved. Compared with present works, the proposed circuit shows better results of the temperature coefficient and supply regulation. The current matching issue frequently encountered in current references is also discussed in detail.展开更多
Renewable power generation is a suitable technology used to deliver energy locally to customers especially in remote regions. Wind energy based on induction generator situates in a foreground position in the total ene...Renewable power generation is a suitable technology used to deliver energy locally to customers especially in remote regions. Wind energy based on induction generator situates in a foreground position in the total energy produced using renewable sources. In the last few decades, a new self- excitation generator was based on multi-stator induction strongly emerges. This article presents a systematic modelling, a detailed analysis and the performance analysis of self-excitation dual stator winding induction generator (SE-DSWIG). The modelling of the SE-DSWIG was done with taking in account the common mutual leakage inductance between stators and the magnetizing inductance, which played a principal role in the stabilization of the output voltage in the steady state. The generator feeds the end user emulated by an inductive-resistive load. In order to simulate the weather conditions’ variation, a step change of the prime mover speed was applied on the SE-DSWIG. A passive series and shunt compensator was used to mitigate the voltage sag and swell appeared in the power system due to wind variation and the lack of reactive power consumed by the inductive load.展开更多
街道场景视频实例分割是无人驾驶技术研究中的关键问题之一,可为车辆在街道场景下的环境感知和路径规划提供决策依据.针对现有方法存在多纵横比锚框应用单一感受野采样导致边缘特征提取不充分以及高层特征金字塔空间细节位置信息匮乏的...街道场景视频实例分割是无人驾驶技术研究中的关键问题之一,可为车辆在街道场景下的环境感知和路径规划提供决策依据.针对现有方法存在多纵横比锚框应用单一感受野采样导致边缘特征提取不充分以及高层特征金字塔空间细节位置信息匮乏的问题,本文提出锚框校准和空间位置信息补偿视频实例分割(Anchor frame calibration and Spatial position information compensation for Video Instance Segmentation,AS-VIS)网络.首先,在预测头3个分支中添加锚框校准模块实现同锚框纵横比匹配的多类型感受野采样,解决目标边缘提取不充分问题.其次,设计多感受野下采样模块将各种感受野采样后的特征融合,解决下采样信息缺失问题.最后,应用多感受野下采样模块将特征金字塔低层目标区域激活特征映射嵌入到高层中实现空间位置信息补偿,解决高层特征空间细节位置信息匮乏问题.在Youtube-VIS标准库中提取街道场景视频数据集,其中包括训练集329个视频和验证集53个视频.实验结果与YolactEdge检测和分割精度指标定量对比表明,锚框校准平均精度分别提升8.63%和5.09%,空间位置信息补偿特征金字塔平均精度分别提升7.76%和4.75%,AS-VIS总体平均精度分别提升9.26%和6.46%.本文方法实现了街道场景视频序列实例级同步检测、跟踪与分割,为无人驾驶车辆环境感知提供有效的理论依据.展开更多
基金Supported by National Natural Science Foundation of China(Grant No.51405422)Hebei Provincial Natural Science Foundation of China(Grant No.E2015203113)Technological Innovation Fund of Aviation Industry of China(Grant No.2014E00468R)
文摘The spherical plain bearing test bench is a necessary detecting equipment in the research process of self?lubricating spherical plain bearings. The varying environmental temperatures cause the thermal deformation of the wear?depth detecting system of bearing test benches and then a ect the accuracy of the wear?depth detecting data. However, few researches about the spherical plain bearing test benches can be found with the implementation of the detect?ing error compensation. Based on the self?made modular spherical plain bearing test bench, two main causes of ther?mal errors, the friction heat of bearings and the environmental temperature variation, are analysed. The thermal errors caused by the friction heat of bearings are calculated, and the thermal deformation of the wear?depth detecting sys?tem caused by the varying environmental temperatures is detected. In view of the above results, the environmental temperature variation is the main cause of the two error factors. When the environmental temperatures rise is 10.3 °C, the thermal deformation is approximately 0.01 mm. In addition, the comprehensive compensating model of the thermal error of the wear?depth detecting system is built by multiple linear regression(MLR) and time series analysis. Compared with the detecting data of the thermal errors, the comprehensive compensating model has higher fitting precision, and the maximum residual is only 1 μm. A comprehensive compensating model of the thermal error of the wear?depth detecting system is proposed, which provides a theoretical basis for the improvement of the real?time wear?depth detecting precision of the spherical plain bearing test bench.
文摘Microstructured roll workpieces have been widely used as functional components in the precision industries. Current researches on quality control have focused on surface profile measurement of microstructured roll workpieces, and types of measurement systems and measurement methods have been developed. However, low measurement efficiency and low measurement accuracy caused by setting errors are the common disadvantages for surface profile measurement of microstructured roll workpieces. In order to shorten the measurement time and enhance the measurement accuracy, a method for self-calibration and compensation of setting errors is proposed for surface profile measurement of microstructured roll workpieces. A measurement system is constructed for the measurement, in which a precision spindle is employed to rotate the roll workpiece and an air-bearing displacement sensor with a micro-stylus probe is employed to scan the microstructured surface of the roll workpiece. The resolution of the displacement sensor is 0.14 nm and that of the rotary encoder of the spindle was 0.15r~. Geometrical and mathematical models are established for analyzing the influences of the setting errors of the roll workpiece and the displacement sensor with respect to the axis of the spindle, including the eccentric error of the roll workpiece, the offset error of the sensor axis and the zero point error of the sensor output. Measurement experiments are carded out on a roll workpiece on which periodic microstructures are a period of 133 i^m along the circumferential direction. Experimental results demonstrate the feasibility of the self-compensation method. The proposed method can be used to detect and compensate the setting errors without using any additional accurate artifact.
基金National Natural Science Foundation of China(60577046) Cooperation Building Project of Beijing EducationCommittee(XK100130437)
文摘Polarization mode dispersion(PMD) is considered to be the ultimate limitation in high-speed optical fiber communication systems. Establishing an effective control algorithm for adaptive PMD compensation is a challenging task, because PMD possesses the time-varying and statistical properties. The particle swarm optimization(PSO) algorithm is introduced into self-adaptive PMD compensation as feedback control algorithm. The experiment results show that PSO-based control algorithm has some unique features of rapid convergence to the global optimum without being trapped in local sub-optima and good robustness to noise in the optical fiber transmission line that has never been achieved in PMD compensation before.
基金Project supported by the National Basic Research Program,China(Grant Nos.2010CB327605 and 2010CB328300)the National High-Technology Research and Development Program of China(Grant No.2013AA031501)+7 种基金the National Natural Science Foundation of China(Grant No.61307109)the Specialized Research Fund for the Doctoral Program of Higher Education of China(Grant No.20120005120021)the Fundamental Research Funds for the Central Universities,China(Grant No.2013RC1202)the Program for New Century Excellent Talents in University,China(Grant No.NECT-11-0596)the Beijing Nova Program,China(Grant No.2011066)the Fund of State Key Laboratory of Information Photonics and Optical Communications(Beijing University of Posts and Telecommunications) Chinathe China Postdoctoral Science Foundation(Grant No.2012M511826)the Postdoctoral Science Foundation of Guangdong Province,China(Grant No.244331)
文摘We propose a novel lumped time-delay compensation scheme for all-optical analog-to-digital conversion based on soliton self-frequency shift and optical interconnection techniques. A linearly chirped fiber Bragg grating is optimally designed and used to compensate for the entire time-delays of the quantized pulses precisely. Simulation results show that the compensated coding pulses are well synchronized with a time difference less than 3.3 ps, which can support a maximum sampling rate of 151.52 GSa/s. The proposed scheme can efficiently reduce the structure complexity and cost of all-optical analog-to-digital conversion compared to the previous schemes with multiple optical time-delay lines.
基金Financial support for this work, provided by the National Natural Science Foundation of China (No.50504014), is gratefully acknowledged
文摘Self-positioning of a shearer is the key technology for mining with a man-less working face. In an underground coal mine all radio navigation; satellite positioning or celestial navigation methods have their limitations. We analyzed an inertial navi-gation system intended to guide the movement a shearer and designed a self-positioning device for the shearer. Simulation tests were also performed on the system. We analyzed the errors observed in these tests to show that the main reason for the low preci-sion of the self-positioning system is accumulated error in the inertial sensor. A Kalman filtering algorithm used in combination with the shearer motion model effectively reduces the measurement errors of the self-positioning system by compensating for gyroscopic drift. Finally, we built an error compensation model to reduce accumulated errors using continuous correction to provide self-positioning of the shearer within a certain range of accuracy.
基金supported by the National Natural Science Foundation of China (60874117)the 111 Project (B07009)
文摘A new robust fault-tolerant controller scheme integrating a main controller and a compensator for the self-repairing flight control system is discussed.The main controller is designed for high performance of the original faultless system.The compensating controller can be seen as a standalone loop added to the system to compensate the effects of fault guaranteeing the stability of the system.A design method is proposed using nonlinear dynamic inverse control as the main controller and nonlinear extended state observer-based compensator.The stability of the whole closed-loop system is analyzed.Feasibility and validity of the new controller is demonstrated with an aircraft simulation example.
基金Supported by the National 863 CIMS Project Foundation(863-511-010)Tianjin Natural Science Foundation(983602011)Backbone Young Teacher Project Foundation of Ministry of Education
文摘This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.
文摘The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the properties of polyurethane,i.e.,dispersion stability,dynamical viscoelasticity and mechanical properties are discussed.It is found that the optimum molar ratio of epichlorohydrin and diethylenetriamine is 1:2.A mois-
文摘The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative for example,emphasizing the interpretation of the inheritance and development of Chinese culture so as to study the importance of Culture Self-Consciousness in Chinese Philosophy,in the context of English globalization. That is to say,this paper stresses the spirits and the stand of nation 's demonstration on pursuing peace,cooperation and sustainable development in the civilization continuity from traditional China to the contemporary China,with practical philosophic view.
基金supported by Science Foundation Ireland through the I-Form Advanced Manufacturing Research Centre 16/RC/3872
文摘Desktop 3D printers have revolutionized how designers and makers prototype and manufacture certain products.Highly popular fuse deposition modeling(FDM)desktop printers have enabled a shift to low-cost consumer goods markets,through reduced capital equipment investment and consumable material costs.However,with this drive to reduce costs,the computer numerical control(CNC)systems implemented in FDM printers are often compromised by poor accuracy and contouring errors.This condition is most critical as users begin to use 3D-printed components in load-bearing applications or to perform mechanical functions.Improved methods of low-cost 3D printer calibration are needed before their open-design potential can be realized in applications,including 3D-printed orthotics and prosthetics.This paper applies methodologies associated with high-precision CNC machining systems,namely,kinematic error modeling and compensation coupled with standardized test methods from ISO230-4,such as the ballbar for kinematic and dynamic error measurements,to examine the influence and feasibility for use on low-cost CNC/3D printing platforms.Recently,the U.S.Food and Drug Administration's"Technical considerations for additive manufactured medical devices"highlighted the need to develop standards specific to additive manufacturing in regulated manufacturing environments.This paper shows the benefits of the methods described within ISO230-4 for error assessment,alongside applying kinematic error modeling and compensation to the popular kinematic configuration of an Ultimaker 3D printer.A Renishaw ballbar QC10 is used to quantify the Ultimaker's errors and thereby populate the error model.This method quantifies machine errors and populates these in a mathematical model of the CNC system.Then,a post-processor can be used to compensate the printing code.Subsequently,the ballbar is used to demonstrate the dramatic impact of the error compensation model on the accuracy and contouring of the Ultimaker printer with 58%reduction in overall circularity error and 90%reduction in squareness error.
文摘Thermal manikin plays important roles in simulating thethermal state of human bodies to facilitate the evaluationof thermal comfort properties of various clothing assem-blies.Based on the heat balance principle and analysis ofrelated factors,the heat production rate of manikin isrecommended as an efficient evaluation index.Whereas,its inside heat production which occurs as a result of theexistence of temperature difference between its insidepart and outside surface,should not be ignored.Through a series of theoretical analysis and calculations,a compensative equation is deduced in this paper.
文摘A new bipolar temperature-compensated current reference is proposed. The first-order temperature compensation is achieved by the idea of self temperature-compensation configuration exploiting the temperature coefficient of a combined resistor. The second-order compensation employs a VBE-tracking thermal-startup technique to obtain improved temperature performance. The proposed circuit can operate down to a 1-V supply. A temperature coefficient of 46.6×10?6/℃ [0, 100℃] at a 1-V supply and a supply regulation of 0.036%/V at 25℃ are achieved. Compared with present works, the proposed circuit shows better results of the temperature coefficient and supply regulation. The current matching issue frequently encountered in current references is also discussed in detail.
文摘Renewable power generation is a suitable technology used to deliver energy locally to customers especially in remote regions. Wind energy based on induction generator situates in a foreground position in the total energy produced using renewable sources. In the last few decades, a new self- excitation generator was based on multi-stator induction strongly emerges. This article presents a systematic modelling, a detailed analysis and the performance analysis of self-excitation dual stator winding induction generator (SE-DSWIG). The modelling of the SE-DSWIG was done with taking in account the common mutual leakage inductance between stators and the magnetizing inductance, which played a principal role in the stabilization of the output voltage in the steady state. The generator feeds the end user emulated by an inductive-resistive load. In order to simulate the weather conditions’ variation, a step change of the prime mover speed was applied on the SE-DSWIG. A passive series and shunt compensator was used to mitigate the voltage sag and swell appeared in the power system due to wind variation and the lack of reactive power consumed by the inductive load.
文摘街道场景视频实例分割是无人驾驶技术研究中的关键问题之一,可为车辆在街道场景下的环境感知和路径规划提供决策依据.针对现有方法存在多纵横比锚框应用单一感受野采样导致边缘特征提取不充分以及高层特征金字塔空间细节位置信息匮乏的问题,本文提出锚框校准和空间位置信息补偿视频实例分割(Anchor frame calibration and Spatial position information compensation for Video Instance Segmentation,AS-VIS)网络.首先,在预测头3个分支中添加锚框校准模块实现同锚框纵横比匹配的多类型感受野采样,解决目标边缘提取不充分问题.其次,设计多感受野下采样模块将各种感受野采样后的特征融合,解决下采样信息缺失问题.最后,应用多感受野下采样模块将特征金字塔低层目标区域激活特征映射嵌入到高层中实现空间位置信息补偿,解决高层特征空间细节位置信息匮乏问题.在Youtube-VIS标准库中提取街道场景视频数据集,其中包括训练集329个视频和验证集53个视频.实验结果与YolactEdge检测和分割精度指标定量对比表明,锚框校准平均精度分别提升8.63%和5.09%,空间位置信息补偿特征金字塔平均精度分别提升7.76%和4.75%,AS-VIS总体平均精度分别提升9.26%和6.46%.本文方法实现了街道场景视频序列实例级同步检测、跟踪与分割,为无人驾驶车辆环境感知提供有效的理论依据.