摘要 :
This paper proposes a fault diagnosis method based on intelligent information processing technology. It first extracts the characteristics of the primary sample signals with wavelet transforms, then optimizes the key characteristi...
展开
This paper proposes a fault diagnosis method based on intelligent information processing technology. It first extracts the characteristics of the primary sample signals with wavelet transforms, then optimizes the key characteristics to be the input parameters of the neural network using the genetic algorithm, and finally recognizes the state and classifies the characteristics with the neural network. This method not only effectively decreases the neural training time and neural calculation, but also enhances the correctness and reliability of the characteristic classification and fault diagnosis. The performance of the proposed method is proven by the bearing fault diagnosis experiment.
收起
摘要 :
This paper proposes a fault diagnosis method based on intelligent information processing technology. It first extracts the characteristics of the primary sample signals with wavelet transforms, then optimizes the key characteristi...
展开
This paper proposes a fault diagnosis method based on intelligent information processing technology. It first extracts the characteristics of the primary sample signals with wavelet transforms, then optimizes the key characteristics to be the input parameters of the neural network using the genetic algorithm, and finally recognizes the state and classifies the characteristics with the neural network. This method not only effectively decreases the neural training time and neural calculation, but also enhances the correctness and reliability of the characteristic classification and fault diagnosis. The performance of the proposed method is proven by the bearing fault diagnosis experiment.
收起
摘要 :
Elderly fall detection aims at automatically detecting fall actions, a major public health problem for the elderly. Existing fall detection methods are cost-ineffective - a satisfactory performance is commonly traded by high costs...
展开
Elderly fall detection aims at automatically detecting fall actions, a major public health problem for the elderly. Existing fall detection methods are cost-ineffective - a satisfactory performance is commonly traded by high costs in device access/deployment and positive record acquirement. In this paper, we set out to devise a WiFi-based elderly fall detection approach in a cost-effective manner - being high in detection accuracy, and low in costs of device access and positively -annotated data. Specifically, our system builds on commercial WiFi, a ubiquitously available device, which greatly saves device access and deployment costs. To extract the nuanced and implicit features due to the low signal-to-noise ratio of WiFi signals, we propose symmetry Transformer networks, a variant of Transformer to facilitate better feature representation learning. Meanwhile, to overcome the positive scarcity and low inter-environment transferability brought by Transformer, we propose a novel two-stage training scheme, where the representation learning is performed in an unsupervised manner. This unveils a transferability property that reduces the requirements on positive instances in training the resulting model. Empirical evaluation demonstrates our cost-effective desideratum while achieving superior performance compared with state-of-the-art models.
收起
摘要 :
We adopt hexagonal optofluidic ring scatterers to built two-dimensional photonic crystal waveguide (PCW) with triangular lattice. By studying slow light effects of varieties of optical optofluidic rings, the thickness of optofluid...
展开
We adopt hexagonal optofluidic ring scatterers to built two-dimensional photonic crystal waveguide (PCW) with triangular lattice. By studying slow light effects of varieties of optical optofluidic rings, the thickness of optofluidic ring in X and Z direction, and the moving distance of the first row of scatterers near central waveguide, some relatively optimism results have been founded. In addition, in the process of research, we adopt PWE method to simulation calculation. When the thickness of optofluidic ring changes, the optimization results which n_g equals 47.2120, bandwidth Δλ is 28.5nm and the group velocity dispersion β_2 is 43.3418 ps~2/mm. When the moving distance changes, the optimization results we could get that n_g equals 15.6569, Δλ is 92.9nm and β_2 is 7.8202 ps~2/mm. This wideband and low dispersion slow light can be used for storage capacity with certain requirements of the optical buffer, optical sensors, etc.
收起
摘要 :
We adopt hexagonal optofluidic ring scatterers to built two-dimensional photonic crystal waveguide (PCW) with triangular lattice. By studying slow light effects of varieties of optical optofluidic rings, the thickness of optofluid...
展开
We adopt hexagonal optofluidic ring scatterers to built two-dimensional photonic crystal waveguide (PCW) with triangular lattice. By studying slow light effects of varieties of optical optofluidic rings, the thickness of optofluidic ring in X and Z direction, and the moving distance of the first row of scatterers near central waveguide, some relatively optimism results have been founded. In addition, in the process of research, we adopt PWE method to simulation calculation. When the thickness of optofluidic ring changes, the optimization results which n_g equals 47.2120, bandwidth Δλ is 28.5nm and the group velocity dispersion β_2 is 43.3418 ps~2/mm. When the moving distance changes, the optimization results we could get that n_g equals 15.6569, Δλ is 92.9nm and β_2 is 7.8202 ps~2/mm. This wideband and low dispersion slow light can be used for storage capacity with certain requirements of the optical buffer, optical sensors, etc.
收起
摘要 :
This paper proposes a fusion fault diagnosis method based on the wavelet transform, genetic algorithm and neural network. It first extracts the characteristics of the primary sample signals with wavelet transform, then optimizes t...
展开
This paper proposes a fusion fault diagnosis method based on the wavelet transform, genetic algorithm and neural network. It first extracts the characteristics of the primary sample signals with wavelet transform, then optimizes the key characteristics to be input parameters of neural network with the genetic algorithm, and finally recognizes the state and classifies the characteristics with neural network. This method not only effectively decreases the neural training time and neural calculation, but also enhances the correctness and reliability of the characteristic classification and fault diagnosis. The performance of the proposed method is proven by the bearing fault diagnosis experiment.
收起
摘要 :
In view of the lack of accuracy of INS/GNSS integrated navigation system under the condition of missing satellite navigation (GNSS) signals in specific environment, this paper proposes a DME+VOR/INS integrated navigation method, w...
展开
In view of the lack of accuracy of INS/GNSS integrated navigation system under the condition of missing satellite navigation (GNSS) signals in specific environment, this paper proposes a DME+VOR/INS integrated navigation method, which tightly coupled INS information and DME+VOR information. For the problem that DME+VOR positioning accuracy is not high and there is a great deal of uncertainty, DME+VOR navigation information is corrected by high dynamic INS navigation information in advance. In view of the existence of the integrate radio system, the information of DME+VOR is uncertain, such as the update time, the new cycle measurement, and the bad environmental interference. By introducing the Sigmoid confidence function, the confidence degree of the information calculated by DME+VOR is extracted. Finally, through the calculation of INS, DME+VOR and electronic compass, the state equation and measurement equation based on EKF are established. The simulation results show that DME+VOR/INS integrated navigation can significantly improve the navigation accuracy of the system, and to meet the navigation and location requirements of the aircraft in the absence of other auxiliary navigation sources such as GNSS signal.
收起
摘要 :
In view of the lack of accuracy of INS/GNSS integrated navigation system under the condition of missing satellite navigation (GNSS) signals in specific environment, this paper proposes a DME+VOR/INS integrated navigation method, w...
展开
In view of the lack of accuracy of INS/GNSS integrated navigation system under the condition of missing satellite navigation (GNSS) signals in specific environment, this paper proposes a DME+VOR/INS integrated navigation method, which tightly coupled INS information and DME+VOR information. For the problem that DME+VOR positioning accuracy is not high and there is a great deal of uncertainty, DME+VOR navigation information is corrected by high dynamic INS navigation information in advance. In view of the existence of the integrate radio system, the information of DME+VOR is uncertain, such as the update time, the new cycle measurement, and the bad environmental interference. By introducing the Sigmoid confidence function, the confidence degree of the information calculated by DME+VOR is extracted. Finally, through the calculation of INS, DME+VOR and electronic compass, the state equation and measurement equation based on EKF are established. The simulation results show that DME+VOR/INS integrated navigation can significantly improve the navigation accuracy of the system, and to meet the navigation and location requirements of the aircraft in the absence of other auxiliary navigation sources such as GNSS signal.
收起