Deep learning-based methods have shown their wide application prospects in the field of solid oxide fuel cell(SOFC)***,the irrationality of the prediction object and the lack of prediction accuracy have hindered the p...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
Deep learning-based methods have shown their wide application prospects in the field of solid oxide fuel cell(SOFC)***,the irrationality of the prediction object and the lack of prediction accuracy have hindered the progress of the prediction methods for SOFC ***,two algorithms are proposed in this study,a feature selection algorithm based on maximum information coefficient and Bayesian information criterion for identifying key variables that are sensitive to changes in the SOFC system,and a prediction model based on a genetic algorithm optimized for sequence to sequence *** M/BIC algorithm reduces the number of features by 62.5%(from 40 to 15),which contributes to the acceleration of the algorithm training and the subsequent sensor layout *** prediction model incorporates a two-dimensional convolutional neural network and a multi-head attention mechanism to capture more information in the input sequence,an encoder-decoder architecture and a Gated recurrent unit to better predict performance *** with real experimental data show significant changes in feature dimensionality reduction and prediction accuracy.
A nitrogen oxide sensor that can accurately and quickly detect the content of nitrogen oxides in exhaust gas plays a key role in the treatment of automotive exhaust gas. Due to the characteristics of gas diffusion and...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
A nitrogen oxide sensor that can accurately and quickly detect the content of nitrogen oxides in exhaust gas plays a key role in the treatment of automotive exhaust gas. Due to the characteristics of gas diffusion and chamber structure, nitrogen oxide sensors are difficult to achieve high-precision and fast measurement due to strong coupling. In order to solve this problem, this paper proposes a decoupling control strategy for nitrogen oxide sensors. On the one hand, the strategy uses fuzzy feedforward compensation, and on the other hand, it uses PID control based on particle swarm optimization to achieve control. This not only eliminates the coupling between loops, but also improves the control accuracy. The analysis shows that the design of the decoupling control strategy for nitrogen oxide sensors proposed in this paper is feasible, which allows the nitrogen oxide sensors to work in a stable and reliable state.
On basis of studying the fusion algorithm of multiple sensors, a new approach is presented to fuse the millimeter wave radiometric image and the optical-based simulated image by wavelet transform. The 8mm simulation r...
详细信息
ISBN:
(纸本)0780384016
On basis of studying the fusion algorithm of multiple sensors, a new approach is presented to fuse the millimeter wave radiometric image and the optical-based simulated image by wavelet transform. The 8mm simulation result shows that fusion image has more complementary information and possesses higher resolution than the measuring image. The fusion image can help to improve the scientific decision-making.
In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models ar...
详细信息
Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depends on the localization accuracy of a...
详细信息
We introduce a 3D instance representation, termed instance kernels, where instances are represented by one-dimensional vectors that encode the semantic, positional, and shape information of 3D instances. We show that ...
详细信息
3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed join...
详细信息
This paper investigates leaderless consensus (LLC) and leader-follower consensus (LFC) issues of multiple Euler-Lagrange systems (MELSs) with uncertain system parameters and input disturbances. Firstly, by utilizing e...
详细信息
Most experimental and decoding algorithm studies of brain neural signals assume that neurons transmit information as a rate coding, but recent studies on the fast cortical computations indicate that temporal coding is...
Most experimental and decoding algorithm studies of brain neural signals assume that neurons transmit information as a rate coding, but recent studies on the fast cortical computations indicate that temporal coding is probably a more biologically plausible scheme used by neurons. We introduce spiking neural networks (SNN) which consist of spiking neurons propagate information by the timing of spikes to analyze the cortical neural spike trains directly without temporal information lost. The SNN based temporal pattern classification is compared with the conventional artificial neural networks (ANN) based firing rate analysis. The results show that the SNN algorithm can achieve higher accuracy, which demonstrates that temporal coding is a viable code for fast neural information processing and the SNN approach is suitable for recognizing the temporal pattern in the cortical neural signals.
暂无评论