Kai ZhongZhengping DingHaifeng ZhangHongtian Chen...
1998-2009页
查看更多>>摘要：Federated learning (FL)-based fault diagnosis is being widely developed. However, most of the existing FL methods may suffer from two drawbacks: 1) they are limited to a single diagnosis task, and this may be insufficient when comprehensive health status information is needed and 2) most of them work offline, thus neglecting the useful information contained in newly collected operation data. For this end, this article proposes a multitask federated incremental learning (multitask-FIL) framework. First of all, a multitask feature sharing network is established by assigning the extracted general features to different downstream tasks, so that the joint loss function is obtained for subsequent collaborative training. Then, Q-learning algorithm is used to select the incremental sequences for all the parties from real-time running data, which can facilitate the model performance by involving additional data information and preferred parties. After that, the incremental weight of each party is dynamically adjusted according to the loss depth and sample size in each round of communication, so that the effects of different parties can be quantified throughout the model iteration and aggregation process. Finally, experiments on three challenging cases are performed to show that the proposed method has strong multitask collaboration capability.
查看更多>>摘要：Recently, network-on-chip (NoC)-based multiprocessor system-on-chips (MPSoCs) have become popular computing platforms for real-time applications due to high communication performance and energy efficiency over traditional bus-based MPSoCs. Due to the nature of network structures, network congestion along with transient faults, can significantly affect communication efficiency and system reliability. Most existing works have rarely focused on the concurrent optimization of network contention, reliability, and energy consumption. Here, we study the problem of contention and reliability-aware task mapping under real-time constraints for dynamic voltage and frequency scaling-enabled NoC. The problem entails optimizing voltage/frequency on cores and links to reduce energy consumption and ensure system reliability, while task mapping and slack time are adopted to alleviate network contention and reduce latency. We aim to minimize computation and communication energy and balance workload. This problem is formulated as a mixed-integer nonlinear programming, and we present an effective linearization scheme that equivalently transforms it into a mixed-integer linear programming to find the optimal solution. To reduce computation time, we propose a three-step heuristic, including task allocation, frequency scaling and edge scheduling, and communication contention management. Finally, we perform extensive simulations to evaluate the proposed method. The results show we can achieve 31.6% and 21.7% energy savings, with 95.5% and 98.6% less contention than the existing methods.
查看更多>>摘要：A reliable adaptive-memory-derivative (AMD) event-triggered quantized sliding mode load frequency control (QSMLFC) method is proposed for the multiarea interconnected wind power system under frequency-based deception attacks. An AMD event-trigger scheme is proposed to promote the wind power system operation while saving the network resources, and the reliable AMD event-triggered QSMLFC method aims to reduce the frequency deviations of the interconnected wind power systems. A frequency-based deception attack model is developed for analyzing the security issues in network communications for wind power systems. The hysteresis quantizer is used to lower the communication rate. To validate the correctness of the control method, a sufficient reliability criterion is derived to prove the applicability of the AMD event-triggered QSMLFC. Three numerical examples and an IEEE 39-bus system simulation are presented to demonstrate that the reliable AMD event-triggered QSMLFC method can provide satisfactory stability performance for the wind power system under frequency-based deception attacks.
查看更多>>摘要：The control room functions as the core nervous system of a nuclear power plant (NPP), emphasizing the crucial need for real-time monitoring of all activities inside to guarantee comprehensive safety. The maintenance of a high level of reliability in the real-time monitoring system within the control room of an NPP is of utmost importance in order to effectively mitigate any potential failures that may occur during the monitoring process. The software and hardware problems can both cause unplanned outages in a large-scale distributed monitoring system. To address the challenge of NPP control room monitoring, a particle filtering-based people tracking system for NPP control room monitoring is introduced to ensure the safety, security, and reliability of the NPP control room. In addition to tracking people for the monitoring of the NPP control room, the suggested technique also provides a reliability study of the large-distributed monitoring system.
查看更多>>摘要：Global navigation satellite systems (GNSS) often suffer from service interruptions or multipath errors in urban canyon environments, giving rise to reduced navigation accuracy. Therefore, it is necessary to develop effective fault-tolerant navigation systems to ensure a high-level accuracy despite GNSS failures. In this article, we present a novel fault detection framework based on the extended Kalman filter to address the problem of untimely fault detection and inaccurate positioning when GNSS fails. Specifically, we introduce the statistical process control technique of control charts to address the issue of slow-varying fault detection by constructing kernel multivariate exponentially weighted moving-average control charts instead of the conventional chi-square test. Simultaneously, we establish a corresponding criterion using EWMA-related statistics to mitigate the negative impact of uncertain noise and abnormal innovation, thereby ensuring the positioning accuracy of the navigation system. Finally, we validate the effectiveness and superiority of the proposed method through simulations and vehicle field data, demonstrating its ability to detect anomalies promptly and enhance the navigation and positioning accuracy while mitigating the adverse effects of GNSS lapse.
查看更多>>摘要：From the perspective of industrial production reliability, a robust event-triggered (ET) control strategy is presented for uncertain continuous stirred tank reactor (CSTR) system with asymmetric input constraints. To begin with, we propose a nonquadratic performance function to transform the robust control issue by constructing the relevant auxiliary dynamics. For effectively mitigating the pressure of data transmission and controller execution, a dynamic ET scheme (DETS) with an adjustable threshold function is adopted. Subsequently, we formulate the DETS-based Hamilton–Jacobi–Bellman (DET-HJB) equation according to optimality theory. In addition, a DETS-assisted reinforcement learning algorithm with a unique critic neural network can efficiently tackle the derived DET-HJB equation. Meanwhile, the corresponding critic weight is regulated on the basis of gradient descent technique and experience replay approach. By presenting a rigorous analysis under two situations, the uniform ultimate boundedness of auxiliary dynamics and weight approximation error can be ensured. Eventually, the feasibility of the proposed algorithm is demonstrated by experimental results of CSTR system.
查看更多>>摘要：The collected data of a pumping unit contain environmental noise, which significantly reduces the precision of fault diagnosis. The previous fault detection approach depends on manual feature extraction, which is time-consuming and laborious, and it cannot cope with high-noise conditions. Therefore, we propose a dual-branch time–frequency fusion deep learning model for fault diagnosis of the pumping unit. One branch extracts time-domain information, while the other branch extracts frequency-domain information by employing the fast Fourier transform. The branch information of these two branches is concatenated, and the gate-controlled channel transfer unit module automatically learns the competitive and cooperative relationships between each branch, making the key features more prominent in information fusion. Consequently, an accurate fault diagnosis of the pumping unit can be achieved under high-noise conditions. The results demonstrate that the proposed model outperforms the traditional schemes in terms of noise, with different signal-to-noise ratios.
NETL
NSTL
IEEE