Neutral Point Clamped (NPC) three-level inverter has been widely adopted in the industry, but it suffers from the issue of neutral voltage imbalance. This paper uses the FC leg to replace the DC capacitor leg and study the relationship between the switching frequencies of the FC leg and NPC inverter. A prediction method for the flying capacitor voltage ripple is proposed and the variable switching frequency PWM (VSFPWM) based on this prediction is proposed to control the flying capacitor voltage ripple. This utilizes the capacitor voltage ripple to reduce the switching frequency and minimize losses. Simulation and experimental verified the accuracy of the voltage ripple prediction method and the VSFPWM control scheme. Meanwhile, this scheme can reduce the average switching frequency and improve EMI.

In the security operation center, false positive alerts generated by security devices overwhelm security operators, leading to alert fatigue and inefficiency in identifying real threats. This paper introduces DEEPDRAC, a disposition recommendation method for alert clusters that is based on security event patterns. Our main idea is to reconstruct isolated alerts into security events and capture their essential threat characteristics as patterns. By recommending pattern information, we enable batch interpretable disposal of alerts. First, DEEPDRAC aggregates correlated alerts to a graph, representing a security event. Then, it extracts the features of the security event from two aspects: basic features via statistical methods and detailed features via a carefully designed Graph Neural Network (GNN) that focuses on edge features. Since many false alerts triggered by the same cause often recur in a fixed pattern, DEEPDRAC translates basic features into interpretable descriptors to define the basic pattern, whereas GNN embeddings complement detailed semantic information, serving as the detailed pattern, together forming the pattern of the security event. The pattern describes the critical information of the security event, so security events with the same pattern are clustered for batch processing. Finally, with few manually labeled security events, DEEPDRAC can conduct automatic disposition recommendations for newly arrived alerts, significantly reducing the workload of alert analysis. We evaluate our approach on two benchmark datasets (i.e., DARPA 1999 and CIC-IDS2017) and a real-world dataset from a large power company. The extensive experimental results demonstrate that our approach can alleviate alert fatigue more efficiently and accurately than the two state-of-the-art defense approaches can.

In this article, a novel task search and allocation strategy is developed for heterogeneous multiagent systems with limited search range and communication constraints, which includes three processes: 1) task search; 2) task allocation; and 3) formation recovery. In order to optimize task search efficiency under communication constraints, a multigroup task search strategy is proposed by minimizing the average overlap degree between agents’ search ranges, which divides agents into multiple groups and establishes intragroup communication links. According to the communication link and group allocation results, an optimal search formation is designed for each group to maximize their individual search ranges. For transmitting information between different groups, by employing the agent with the highest communication efficiency within the discovery agent’s group as the relay agent, a communication relay strategy is proposed to transmit the task information to other groups. Then, a task allocation strategy based on communication relays is designed to achieve global task allocation by using the estimated state information of all agents. Moreover, to ensure the sustainability of task search and allocation, an intergroup scheduling strategy is proposed to recover the optimal search formation after agents complete the task-related works. Simulation results verify the effectiveness of the proposed task search and allocation strategy.

This paper considers the distributed fault-tolerant consensus for heterogeneous nonlinear multiagent systems (HNMASs) with actuator faults and full-state constraints via adaptive dynamic programming (ADP). In order to handle the state constraint problem with multiple constraint types, a unified universal barrier function is introduced to convert the original constrained system into a non-constrained system. For the purpose of improving control efficiency and guaranteeing system reliability, a novel value function including fault estimations and control inputs is established. Considering the limitation of the computation and communication resources, a simplified ADP method incorporating the dynamic event-triggered strategy is developed to learn a distributed event-triggered fault-tolerant control policy. It is strictly proven that the HNMASs’ stability and the neural network weights’ convergence are guaranteed by the Lyapunov theory in the sense of uniform ultimate boundedness. Simulations are presented to verify the proposed control policy.

In this article, a novel approach of prescribed performance synchronization control is developed for heterogeneous nonlinear multiagent systems (MASs) subject to unknown actuator faults. Considering that not all followers are able to access the information of the leader, a distributed auxiliary perception system is proposed to estimate the state information of the leader to guarantee that the estimation errors converge to zero within fixed time. Then, based on the estimated states, a prescribed performance fault-tolerant control (FTC) approach is proposed, which achieves the user-defined performance specifications even in the presence of system faults. Moreover, as accurate system dynamic models are perhaps hard to acquire in practical engineering, a data-based method is proposed by using the reinforcement learning (RL) algorithm to design the fault-tolerant controller, which only needs the off-policy online data and is independent of the model dynamics of followers. The stability and synchronization with the prescribed behavior are guaranteed through the Lyapunov stability theorem. Finally, simulation results are presented to illustrate the effectiveness of the developed controller.

In this paper, we introduce NBNet, a novel framework for image denoising. Unlike previous works, we propose to tackle this challenging problem from a new perspective: noise reduction by image-adaptive projection. Specifically, we propose to train a network that can separate signal and noise by learning a set of reconstruction basis in the feature space. Subsequently, image denosing can be achieved by selecting corresponding basis of the signal subspace and projecting the input into such space. Our key insight is that projection can naturally maintain the local structure of input signal, especially for areas with low light or weak textures. Towards this end, we propose SSA, a non-local attention module we design to explicitly learn the basis generation as well as subspace projection. We further incorporate SSA with NBNet, a UNet structured network designed for end-to-end image denosing based. We conduct evaluations on benchmarks, including SIDD and DND, and NBNet achieves state-of-the-art performance on PSNR and SSIM with significantly less computational cost.

Visual question answering (VQA) that involves understanding an image and paired questions develops very quickly with the boost of deep learning in relevant research fields, such as natural language processing and computer vision. Existing works highly rely on the knowledge of the data set. However, some questions require more professional cues other than the data set knowledge to answer questions correctly. To address such an issue, we propose a novel framework named a knowledge-based augmentation network (KAN) for VQA. We introduce object-related open-domain knowledge to assist the question answering. Concretely, we extract more visual information from images and introduce a knowledge graph to provide the necessary common sense or experience for the reasoning process. For these two augmented inputs, we design an attention module that can adjust itself according to the specific questions, such that the importance of external knowledge against detected objects can be balanced adaptively. Extensive experiments show that our KAN achieves state-of-the-art performance on three challenging VQA data sets, i.e., VQA v2, VQA-CP v2, and FVQA. In addition, our open-domain knowledge is also beneficial to VQA baselines. Code is available at https://github.com/yyyanglz/KAN.