Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors ...Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.展开更多
Autonomous underwater vehicles(AUV) work in a complex marine environment. Its system reliability and autonomous fault diagnosis are particularly important and can provide the basis for underwater vehicles to take corr...Autonomous underwater vehicles(AUV) work in a complex marine environment. Its system reliability and autonomous fault diagnosis are particularly important and can provide the basis for underwater vehicles to take corresponding security policy in a failure. Aiming at the characteristics of the underwater vehicle which has uncertain system and modeling difficulty, an improved Elman neural network is introduced which is applied to the underwater vehicle motion modeling. Through designing self-feedback connection with fixed gain in the unit connection as well as increasing the feedback of the output layer node, improved Elman network has faster convergence speed and generalization ability. This method for high-order nonlinear system has stronger identification ability. Firstly, the residual is calculated by comparing the output of the underwater vehicle model(estimation in the motion state) with the actual measured values. Secondly, characteristics of the residual are analyzed on the basis of fault judging criteria. Finally, actuator fault diagnosis of the autonomous underwater vehicle is carried out. The results of the simulation experiment show that the method is effective.展开更多
The function-layer model and working model of collaborative remote fault diagnosis system （FDS）, which includes three layers： task layer, collaboration layer and diagnosing layer, are proposed. The running mechanis...The function-layer model and working model of collaborative remote fault diagnosis system （FDS）, which includes three layers： task layer, collaboration layer and diagnosing layer, are proposed. The running mechanism of the system is discussed. A collaborative FDS may consist of several subsystems running at different places and the subsystem consists of several fimction modules. A structure centered on data-bus is adopted in subsystem. All the function modules in subsystem are encapsulated into software intelligent chips （SICs） and SIC can but connect with data-bus. So, it is feasible to reuse these diagnosis fimction modules and the structure of subsystem in different diagnosis applications. With the reconfigurable SICs, several different function modules can reconstruct quickly some different diagnosis subsystems in different combinations, and some subsystems can also reconfigure a specified collaborative FDS.展开更多
This paper introduces the autonomous control technologies for a new generation launch vehicle for guidance and attitude control.Based on the iterative guidance mode(IGM)of Long March launch vehicles,the autonomous com...This paper introduces the autonomous control technologies for a new generation launch vehicle for guidance and attitude control.Based on the iterative guidance mode(IGM)of Long March launch vehicles,the autonomous compensation IGM(ACIGM)for the terminal attitude deviation during the coasting phase is proposed.Considering the characteristics of large static instability and weak bearing capacity,the attitude control technology based on active disturbance rejection control(ADRC)and a control method based on an accelerometer are proposed.Targeting at non-fatal failures that may occur during flights,autonomous guidance reconstruction technology,nozzle fault diagnosis and reconstruction technology in the coasting phase are studied.Some of the autonomous control technologies proposed in this paper have achieved good control results as seen through flight verification.展开更多
基金Supported by the National Natural Science Foundation of China(Grant U1964201,Grant 61790562 and Grant 61803120)by the Fundamental Research Fundsfor the Central Universities.
文摘Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.
基金Project(2012T50331)supported by China Postdoctoral Science FoundationProject(2008AA092301-2)supported by the High-Tech Research and Development Program of China
文摘Autonomous underwater vehicles(AUV) work in a complex marine environment. Its system reliability and autonomous fault diagnosis are particularly important and can provide the basis for underwater vehicles to take corresponding security policy in a failure. Aiming at the characteristics of the underwater vehicle which has uncertain system and modeling difficulty, an improved Elman neural network is introduced which is applied to the underwater vehicle motion modeling. Through designing self-feedback connection with fixed gain in the unit connection as well as increasing the feedback of the output layer node, improved Elman network has faster convergence speed and generalization ability. This method for high-order nonlinear system has stronger identification ability. Firstly, the residual is calculated by comparing the output of the underwater vehicle model(estimation in the motion state) with the actual measured values. Secondly, characteristics of the residual are analyzed on the basis of fault judging criteria. Finally, actuator fault diagnosis of the autonomous underwater vehicle is carried out. The results of the simulation experiment show that the method is effective.
文摘The function-layer model and working model of collaborative remote fault diagnosis system （FDS）, which includes three layers： task layer, collaboration layer and diagnosing layer, are proposed. The running mechanism of the system is discussed. A collaborative FDS may consist of several subsystems running at different places and the subsystem consists of several fimction modules. A structure centered on data-bus is adopted in subsystem. All the function modules in subsystem are encapsulated into software intelligent chips （SICs） and SIC can but connect with data-bus. So, it is feasible to reuse these diagnosis fimction modules and the structure of subsystem in different diagnosis applications. With the reconfigurable SICs, several different function modules can reconstruct quickly some different diagnosis subsystems in different combinations, and some subsystems can also reconfigure a specified collaborative FDS.
文摘This paper introduces the autonomous control technologies for a new generation launch vehicle for guidance and attitude control.Based on the iterative guidance mode(IGM)of Long March launch vehicles,the autonomous compensation IGM(ACIGM)for the terminal attitude deviation during the coasting phase is proposed.Considering the characteristics of large static instability and weak bearing capacity,the attitude control technology based on active disturbance rejection control(ADRC)and a control method based on an accelerometer are proposed.Targeting at non-fatal failures that may occur during flights,autonomous guidance reconstruction technology,nozzle fault diagnosis and reconstruction technology in the coasting phase are studied.Some of the autonomous control technologies proposed in this paper have achieved good control results as seen through flight verification.
