Science China Technological Sciences - The single-photon absorption induced single event transient in the silicon-germanium heterojunction bipolar transistor is investigated. The laser wavelength... 相似文献
Advanced vehicular control technologies rely on accurate speed prediction to make ecological and safe decisions. This paper proposes a novel stochastic speed prediction method for connected vehicles by incorporating a Bayesian network (BN) and a Back Propagation (BP) neural network. A BN model is first designed for predicting the stochastic vehicular speed in a priori. To improve the accuracy of the BN-based speed prediction, a BP-based predicted speed error compensation module is constructed by formulating a mapping between the predicted speed and whose corresponding prediction error. In the end, a filtering algorithm is developed to smoothen the compensated stochastic vehicular speed. To validate the workings of the proposed approaches in experiments, two typical scenarios are considered: one predecessor vehicle in a double-vehicle scenario and two predecessor vehicles in a multi-vehicle scenario. Simulation results under the considered scenarios demonstrate that the proposed BN-BP fusion method outperforms the BN-based method with respect to the root mean square error, standardized residuals, R-squared, and the online prediction time of proposed fusion prediction can satisfy a real-time application requirement. The main highlighted contributions of this article are threefold: (1) We put forward an improved BN method, which is combined with a BP neural network, to construct a stochastic vehicular speed prediction method under connected driving; (2) different from existing methods, a unique interconnected framework that consists of a stochastic vehicular speed prediction module, a compensation module, and a speed smoothing module is proposed; (3) extensive simulation studies based on a set of evaluation metrics are illustrated to reveal the advantages and merits of the proposed approaches.
Different measurands from the different types of sensors can obtain different information regarding the structural behavior in a real structural health monitoring system.To enrich information and estimate the structural responses based on much more known information,the estimation on structural responses using multi scale measurements from multi-type sensors is proposed in this paper.Pattern identification is constructed with the pattern library given by strain measurements and deformation measurements.Considering the uncertainty of the measurements as well as to enhance the robustness of the proposed algorithm,more than one best pattern is selected to synthesize the finally estimated stress responses.To validate the capacity of the proposed acquisition method using multi scale measurements,finite element model analysis is conducted to estimate the structural stress response in Shenzhen Bay Stadium as an example.The performance of the pattern identifications,constructed by two kinds of pattern libraries captured by sole strain measurement,and multi scale measurements which are constructed by both kinds of strain measurements and deformation measurements,respectively,are compared in this paper to observe measurements constructed from strain measurements and deformation measurements outperformed others.Errors analysis for a series of parametric studies in which noise at different levels has also included in the measurements are further carried out,and robustness of the proposed information acquisition scheme under noisy measurement is demonstrated. 相似文献
The furnace process is very important in boiler operation,and furnace pressure works as an important parameter in furnace process.Therefore,there is a need to analyze and monitor the pressure signal in furnace.However,little work has been conducted on the relationship with the pressure sequence and boiler’s load under different working conditions.Since pressure sequence contains complex information,it demands feature extraction methods from multi-aspect consideration.In this paper,fuzzy c-means analysis method based on weighted validity index(VFCM)has been proposed for the working condition classification based on feature extraction.To deal with the fluctuating and time-varying pressure sequence,feature extraction is taken as nonlinear analysis based on entropy theory.Three kinds of entropy values,extracted from pressure sequence in time-frequency domain,are studied as the clustering objects for work condition classification.Weighted validity index,taking the close and separation degree into consideration,is calculated on the base of Silhouette index and Krzanowski-Lai index to obtain the optimal clustering number.Each time FCM runs,the weighted validity index evaluates the clustering result and the optimal clustering number will be obtained when it reaches the maximum value.Four datasets from UCI Machine Learning Repository are presented to certify the effectiveness in VFCM.Pressure sequences got from a 300 MW boiler are then taken for case study.The result of the pressure sequence case study with an error rate of 0.5332%shows the valuable information on boiler’s load and pressure sequence in furnace.The relationship between boiler’s load and entropy values extracted from pressure sequence is proposed.Moreover,the method can be considered to be a reference method for data mining in other fluctuating and time-varying sequences. 相似文献