摘要：Convolutional neural networks(CNNs)have shown tremendous progress and performance in recent *** emergence,CNNs have exhibited excellent performance in most of classification and segmentation ***,the CNN family includes various architectures that dominate major vision-based recognition ***,building a neural network(NN)by simply stacking convolution blocks inevitably limits its optimization ability and introduces overfitting and vanishing gradient *** of the key reasons for the aforementioned issues is network singularities,which have lately caused degenerating manifolds in the loss *** situation leads to a slow learning process and lower *** this scenario,the skip connections turned out to be an essential unit of the CNN design to mitigate network *** proposed idea of this research is to introduce skip connections in NN architecture to augment the information flow,mitigate singularities and improve *** research experimented with different levels of skip connections and proposed the placement strategy of these links for any *** prove the proposed hypothesis,we designed an experimental CNN architecture,named as Shallow Wide ResNet or SRNet,as it uses wide residual network as a base network *** have performed numerous experiments to assess the validity of the proposed ***-10 and CIFAR-100,two well-known datasets are used for training and testing *** final empirical results have shown a great many of promising outcomes in terms of performance,efficiency and reduction in network singularities issues.

摘要：Increasing the robustness to the unknown uncertainty and simultaneously enhancing the sensibility to the faults is one of the important issues considered in the fault detection development. Considering the L2-gain of residual system, this paper deals the observer-based fault detection problem. By using of H∞ control theory,an LMI approach to design fault detection observer is given. A numerical example is used to illustrate the effectiveness of the proposed approach.

摘要：Problems related to the design of observer-based parametric fault detection(PFD) systems are studied. The core of our study is to first describe the faults occurring in systemactuators, sensors and components in the form of additive parameter deviations, then to transformthe PFD problems into a similar additive fault setup, based on which an optimal observer-basedoptimization fault detection approach is proposed. A constructive solution optimal in the sense ofminimizing a certain performance index is developed. The main results consist of defining parametricfault detectability, formulating a PFD optimization problem and its solution. A numerical exampleto demonstrate the effectiveness of the proposed approach is provided.