Industrial Internet of Things(IoT)connecting society and industrial systems represents a tremendous and promising paradigm shift.With IoT,multimodal and heterogeneous data from industrial devices can be easily collect...Industrial Internet of Things(IoT)connecting society and industrial systems represents a tremendous and promising paradigm shift.With IoT,multimodal and heterogeneous data from industrial devices can be easily collected,and further analyzed to discover device maintenance and health related potential knowledge behind.IoT data-based fault diagnosis for industrial devices is very helpful to the sustainability and applicability of an IoT ecosystem.But how to efficiently use and fuse this multimodal heterogeneous data to realize intelligent fault diagnosis is still a challenge.In this paper,a novel Deep Multimodal Learning and Fusion(DMLF)based fault diagnosis method is proposed for addressing heterogeneous data from IoT environments where industrial devices coexist.First,a DMLF model is designed by combining a Convolution Neural Network(CNN)and Stacked Denoising Autoencoder(SDAE)together to capture more comprehensive fault knowledge and extract features from different modal data.Second,these multimodal features are seamlessly integrated at a fusion layer and the resulting fused features are further used to train a classifier for recognizing potential faults.Third,a two-stage training algorithm is proposed by combining supervised pre-training and fine-tuning to simplify the training process for deep structure models.A series of experiments are conducted over multimodal heterogeneous data from a gear device to verify our proposed fault diagnosis method.The experimental results show that our method outperforms the benchmarking ones in fault diagnosis accuracy.展开更多
In this study,the problem of time-optimal reconnaissance trajectory design for the aeroassisted vehicle is considered.Different from most works reported previously,we explore the feasibility of applying a high-order a...In this study,the problem of time-optimal reconnaissance trajectory design for the aeroassisted vehicle is considered.Different from most works reported previously,we explore the feasibility of applying a high-order aeroassisted vehicle dynamic model to plan the optimal flight trajectory such that the gap between the simulated model and the real system can be narrowed.A highly-constrained optimal control model containing six-degree-of-freedom vehicle dynamics is established.To solve the formulated high-order trajectory planning model,a pipelined optimization strategy is illustrated.This approach is based on the variable order Radau pseudospectral method,indicating that the mesh grid used for discretizing the continuous system experiences several adaption iterations.Utilization of such a strategy can potentially smooth the flight trajectory and improve the algorithm convergence ability.Numerical simulations are reported to demonstrate some key features of the optimized flight trajectory.A number of comparative studies are also provided to verify the effectiveness of the applied method as well as the high-order trajectory planning model.展开更多
基金supported in part by the National Key Research and Development Program of China(No.2018YFB1003700)in part by the National Natural Science Foundation of China(No.61836001)。
文摘Industrial Internet of Things(IoT)connecting society and industrial systems represents a tremendous and promising paradigm shift.With IoT,multimodal and heterogeneous data from industrial devices can be easily collected,and further analyzed to discover device maintenance and health related potential knowledge behind.IoT data-based fault diagnosis for industrial devices is very helpful to the sustainability and applicability of an IoT ecosystem.But how to efficiently use and fuse this multimodal heterogeneous data to realize intelligent fault diagnosis is still a challenge.In this paper,a novel Deep Multimodal Learning and Fusion(DMLF)based fault diagnosis method is proposed for addressing heterogeneous data from IoT environments where industrial devices coexist.First,a DMLF model is designed by combining a Convolution Neural Network(CNN)and Stacked Denoising Autoencoder(SDAE)together to capture more comprehensive fault knowledge and extract features from different modal data.Second,these multimodal features are seamlessly integrated at a fusion layer and the resulting fused features are further used to train a classifier for recognizing potential faults.Third,a two-stage training algorithm is proposed by combining supervised pre-training and fine-tuning to simplify the training process for deep structure models.A series of experiments are conducted over multimodal heterogeneous data from a gear device to verify our proposed fault diagnosis method.The experimental results show that our method outperforms the benchmarking ones in fault diagnosis accuracy.
文摘In this study,the problem of time-optimal reconnaissance trajectory design for the aeroassisted vehicle is considered.Different from most works reported previously,we explore the feasibility of applying a high-order aeroassisted vehicle dynamic model to plan the optimal flight trajectory such that the gap between the simulated model and the real system can be narrowed.A highly-constrained optimal control model containing six-degree-of-freedom vehicle dynamics is established.To solve the formulated high-order trajectory planning model,a pipelined optimization strategy is illustrated.This approach is based on the variable order Radau pseudospectral method,indicating that the mesh grid used for discretizing the continuous system experiences several adaption iterations.Utilization of such a strategy can potentially smooth the flight trajectory and improve the algorithm convergence ability.Numerical simulations are reported to demonstrate some key features of the optimized flight trajectory.A number of comparative studies are also provided to verify the effectiveness of the applied method as well as the high-order trajectory planning model.