Recent years have witnessed the top performances of integrating multi-level features from the pre-trained convolutional neural network (CNN) into correlation filters framework. However, they still suffer from background interference in detection stage due to the large search region and contamination of training samples caused by inaccurate tracking. In this paper, to suppress the interference of background features in target detection stage, an effective spatial attention map (SAM) is proposed to differently weight the multi-hierarchical convolutional features from search region to obtain the attentional features. This way helps to reduce the filter values corresponding to background features. Moreover, we construct multiple elementary correlation filter (ECF) models on multi-hierarchical deep features from CNN to track the target in parallel. To further improve the tracking stability, a multi-model adaptive response fusion (MAF) mechanism is presented. The mechanism can adaptively choose the outputs of reliable ECF models for adaptive weighted fusion by evaluating the confidences of response maps generated by attentional features convolved with ECF models. Finally, to adapt the target appearance changes in the following frames and avoid model corruption, we propose an adaptive updating strategy for the updates of the SAM and ECF models. We perform comprehensive experiments on OTB-2013 and OTB-2015 datasets and the experimental results show the superiority of our algorithm over other 12 state-of-the-art approaches.INDEX TERMS Adaptive updating strategy, convolutional neural network, correlation filter, multi-model adaptive response fusion mechanism, object tracking, spatial attention map.

-In the process of virtual inertia control (VIC), the frequency regulation capability of the directly-driven wind turbine with permanent-magnet synchronous generator (D-PMSG) on wind farm is related to its rotor kinetic energy and capacity margin. This paper proposes the method for assessing the D-PMSG frequency regulation capability and defining its coefficient according to the operating state of wind power generators. In addition, the calculating method of parameters in VIC is also discussed according to the principles of primary frequency regulation and inertia response of synchronous generators. Then, by introducing the capability coefficient into the proportion-differential virtual inertia control (PD-VIC) for power coordination, a coordinated virtual inertia control (C-VIC) strategy is developed, with the consideration of the difference in frequency regulation capability between wind power generators. The proposed control method can not only give full play to the frequency regulation capability of wind power generators, decrease the movements of the pitch angle control system but also bring some self-coordination capability to different wind power generators thus to avoid a secondary drop in system frequency. The simulations and experiments prove the proposed method to be effective and practicable.

As the energy management system (EMS) participates in the closed-loop control of shipboard integrated power system (IPS), the information network of EMS is closely coupled with the power system and its characteristics affect power system performance significantly. To study the close-coupling relationship between the two systems, a cyber–physical co-simulation platform based on the high level architecture (HLA) framework is constructed in this paper. The proposed platform uses PSCAD and OPNET to simulate shipboard power system and information network respectively, and utilizes OPNET HLA nodes and PSCAD user-defined modules to implement co-simulation interfaces. In order to achieve a higher co-simulation precision without impairing efficiency, an optimized event-driven co-simulation synchronization method is also proposed. By pre-defining power system synchronization points and detecting information network synchronization points in the co-simulation process, both systems can be synchronized in time and the synchronization error is eliminated. Furthermore, the co-simulation efficiency is also improved by optimizing the data transmission in the synchronization process. A co-simulation model of shipboard power distribution network protection based on CAN bus communication is built and analyzed. Simulation results show that the proposed co-simulation platform and synchronization method are feasible and effective.

Object tracking is a vital topic in computer vision. Although tracking algorithms have gained great development in recent years, its robustness and accuracy still need to be improved. In this paper, to overcome single feature with poor representation ability in a complex image sequence, we put forward a multifeature integration framework, including the gray features, Histogram of Gradient (HOG), color-naming (CN), and Illumination Invariant Features (IIF), which effectively improve the robustness of object tracking. In addition, we propose a model updating strategy and introduce a skewness to measure the confidence degree of tracking result. Unlike previous tracking algorithms, we judge the relationship of skewness values between two adjacent frames to decide the updating of target appearance model to use a dynamic learning rate. This way makes our tracker further improve the robustness of tracking and effectively prevents the target drifting caused by occlusion and deformation. Extensive experiments on large-scale benchmark containing 50 image sequences show that our tracker is better than most existing excellent trackers in tracking performance and can run at average speed over 43 fps.

No abstract

-The virtual inertia control (VIC) of wind turbine with directly-driven permanent-magnet synchronous generator (D-PMSG) can act similarly to the conventional synchronous generator in inertia response and frequency control, thereby supporting the system frequency stability. However, because the wind speed is inconstant and changeable to a certain extent and the D-PMSG is a complex nonlinear system, there are great difficulties in the virtual inertia optimal control of the D-PMSG. Based on the design principle of the active disturbance rejection control (ADRC), this paper presents a new VIC strategy for the D-PMSG from the perspective of power disturbance suppression in the system. The strategy helps fulfill the power grid disturbance estimation and compensation by means of the extended state observer (ESO) so as to improve the disturbance-resisting performance of the system. Compared with conventional proportional-derivative virtual inertia control (PDVIC), this method, which is of better adaptability and robustness, can not only improve the property of the D-PMSG responding to the system frequency but also reduce the influence of wind speed disturbance. The simulation and experiment results have verified the effectiveness and feasibility of the VIC based on the ADRC.

No abstract

Piston pumps are key components in construction machinery, the failure of which may cause long delay of the construction work and even lead to serious accident. Because construction machines are exposed to poor working conditions, multiple faults of piston pumps are most likely to occur simultaneously. When multiple faults occur together, it is difficult to detect. A multi-fault diagnosis method for piston pump based on information fusion and PSO-SVM is proposed in this thesis. Information fusion is used as fault feature extraction and PSO-SVM is applied as the fault mode classifier. According to the method, vibration signal and pressure signal of piston pump in normal state, single fault state and multi-fault state are collected at first. Then the empirical mode decomposition (EMD) is used to decompose vibration signals into different frequency band and energy features are extracted. These energy features extracted from vibration signals and time-domain features extracted from pressure signal are information fused at the feature layer and constitute the eigenvectors. Finally, these eigenvectors are put into support vector machine (SVM) and the working conditions of piston pump were classified. Particle swarm optimization (PSO) is applied to optimize two parameters of SVM. The experimental results show that the recognition accuracy of the normal state, three single failure modes and multi-fault modes are 98.3 %, 97.6 % and 94 % respectively. These recognition accuracies are higher than which using vibration signal or pressure signal alone. So, the proposed method can not only identify the single fault, but also effectively identify the multi-fault of piston pump.