In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches. 相似文献
A considerable number of applications are running over IP networks. This increased the contention on the network resource, which ultimately results in congestion. Active queue management (AQM) aims to reduce the serious consequences of network congestion in the router buffer and its negative effects on network performance. AQM methods implement different techniques in accordance with congestion indicators, such as queue length and average queue length. The performance of the network is evaluated using delay, loss, and throughput. The gap between congestion indicators and network performance measurements leads to the decline in network performance. In this study, delay and loss predictions are used as congestion indicators in a novel stochastic approach for AQM. The proposed method estimates the congestion in the router buffer and then uses the indicators to calculate the dropping probability, which is responsible for managing the router buffer. The experimental results, based on two sets of experiments, have shown that the proposed method outperformed the existing benchmark algorithms including RED, ERED and BLUE algorithms. For instance, in the first experiment, the proposed method resides in the third-place in terms of delay when compared to the benchmark algorithms. In addition, the proposed method outperformed the benchmark algorithms in terms of packet loss, packet dropping, and packet retransmission. Overall, the proposed method outperformed the benchmark algorithms because it preserves packet loss while maintaining reasonable queuing delay. 相似文献
As an effective supplement to traditional security solutions, reputation mechanism, which can encourage cooperation among individual entities and minimize the damage mainly resulted from insider attacks, has received much concern by the research community. In this article, a negative multinomial reputation model for self-organized networks is proposed. Compared with binary parameter based binomial reputation model, our model is featured with multiple parameters which can depict objective facts more precisely and accurately. Moreover, free from fixed increment on parameters in binomial model, the increment in our model can be 2 or more, which makes our model flexible and suitable for more practical applications such as networks with sleep mechanisms. Through three metrics of measurement, i.e. convergence time to detecting malicious entities, success rate of malicious entities, and success rate of benign entities, our model shows a better performance in the simulations and excels in these three aspects. 相似文献
Changes in flow field around NACA23012 airfoil from a clean condition to a super-cooled large droplet (SLD) condition were simulated, and variations in aerodynamic parameters were calculated using FLUENT. In the case of numerical simulation for a clean airfoil, flow field characteristics simulated agreed well with theory analysis, indicating that turbulence models and parameters setting are feasible. Aerodynamic parameters for iced airfoil were calculated using the same method and agreed with those measured test data under the same environment in icing wind tunnels by S. Lee. Conclusion is made that the numerical simulation is valid, and it can be an alternative to study ice accretion effects at the SLD condition on airfoil aerodynamics, leading to reduction in research cycle time and cost.