In the industrial field, compound faults often occur on rolling bearings and it's difficult to diagnose them correctly. To solve this problem, this article proposes a CNN-ELM compound fault diagnosis method based ...
详细信息
With the industry becoming larger and more complicated, the technology of fault diagnosis becomes more and more important. Due to the strong coupling and non-stationarity of the compound fault, the existing fault diag...
详细信息
ISBN:
(纸本)9781665401166
With the industry becoming larger and more complicated, the technology of fault diagnosis becomes more and more important. Due to the strong coupling and non-stationarity of the compound fault, the existing fault diagnosis methods cannot accurately identify all single faults’ detailed information contained in the compound fault. This paper proposes a compound fault separation and diagnosis method based on FSACNN and DAN. Firstly, in order to highlight certain frequency segments, frequency segment attention module is added to CNN. Secondly, a compound fault feature separation framework based on DAN is proposed, which can separate compound fault to two fault components accurately. Thiredly, a signature matrix is introduced into ELM to improve the performance of the classifier. Finally, ablation experiments are designed to prove the advantage of the proposed method.
Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which...
详细信息
Heat dissipation is extremely important for electronic component such as CPU or GPU of the computer. Now most researchers only design optimal heat sink for CPU for better heat dissipation, while few of them consider w...
详细信息
ISBN:
(纸本)9781665426480
Heat dissipation is extremely important for electronic component such as CPU or GPU of the computer. Now most researchers only design optimal heat sink for CPU for better heat dissipation, while few of them consider waste heat recycling of CPU. The CPU can be used as the heat source, while the original system has fan and heat sink as the cooling system. Thus, the original CPU working condition is very suitable for thermoelectric power generation and will bring great benefit to system itself. However, adding thermoelectric generator will increase the temperature of CPU, which will decrease the performance of the computer. It is necessary to reduce the hot side temperature while generating energy as much as possible. To achieve this, this paper designed a kind of intelligent waste heat generation system based on thermoelectric power generator. Three different shape heat sinks are designed, contrasted, and tested. By building experimental platform and establishing simulation model, the power of thermoelectric power generation and temperature change of the three heat sink structures are compared. The fin shaped heat sink is considered has the best output performance while keeping the hot side temperature within the acceptance range. The maximum output power is 10.67mW, and the maximum hot side temperature is 72°C during the experiment.
Modern industrial devices often use multiple sensors to detect the status of system,which produce a large amount of multivariate time *** to the complex temporal dependency of intra-channel and inter-correlations amon...
详细信息
Modern industrial devices often use multiple sensors to detect the status of system,which produce a large amount of multivariate time *** to the complex temporal dependency of intra-channel and inter-correlations among different channels,few of proposed algorithms have addressed these challenges for anomaly detection in multivariate time ***,previous work does not consider future dependency,which has been shown to be critical for sequential data *** this paper,we develop an unsupervised anomaly detection algorithm TransAnomaly,which integrates Transformer,variational autoencoder(VAE) and nonlinear state space *** not only reduces the computational complexity and allows for more parallelization but also provides explainable *** the best of our knowledge,it is the first model that combines VAE and Transformer for multivariate time series anomaly *** experiments on several public real-world datasets show that TransAnomaly outperforms state-of-the-art baseline methods while training cost is reduced by nearly 80%.
Spintronic devices have the advantages of high endurance and energy efficiency for nonvolatile memory and emerging neuromorphic computing applications, especially with the spin-orbit torque (SOT) driven magnetization ...
详细信息
In sensor networks, due to inevitable sensor faults, malfunctions, or deliberate attacks, sensors may transmit erroneous, inaccurate, or misleading data, thereby degrading overall system performance. To address this i...
详细信息
In this letter, leader-following consensus of a nonlinear MASs satisfying Lipschitz conditions with partial actuator saturation constraints is investigated First of all, an impulse control protocol which only requires...
详细信息
In this letter, leader-following consensus of a nonlinear MASs satisfying Lipschitz conditions with partial actuator saturation constraints is investigated First of all, an impulse control protocol which only requires local information of agents and their neighbors is proposed. Then, using Lyapunov stability theory, impulse control theory, and algebraic graph theory, sufficient conditions for the consensus of multi-agent systems are provided. Ultimately, numerical simulations are employed to show that the research findings are accurate.
In this study, the memristor driven by spin-orbit torque (SOT) is realized in the bulk L1 0 FePt systems with high perpendicular magnetization anisotropy (PMA). Due to the domain nucleation and expansion driven by cur...
详细信息
This paper investigates the finite-time anti-synchronization problem of memristive neural networks(MNNs) with time-varying delays. First, a delayed-feedback controller is constructed to realize the anti-synchronizat...
详细信息
This paper investigates the finite-time anti-synchronization problem of memristive neural networks(MNNs) with time-varying delays. First, a delayed-feedback controller is constructed to realize the anti-synchronization. Then, by employing appropriate Lyapunov-Krasovskii functional and the designed controller, new sufficient criteria are derived for the finite-time anti-synchronization of MNNs. Finally, an example is given to demonstrate the effectiveness of the theoretical results.
暂无评论