Dongjing He

Fault diagnosis across sensor locations becomes difficult when vibration measurements contain strong noise and only a few labeled target samples are available. This study develops an Attention Mask-guided Optimal Transport (AM-OT) framework for this setting. A wide-kernel multi-scale network with channel attention extracts vibration representations, while supervised noise-contrastive pretraining encourages class discrimination across noise perturbations. During target adaptation, a joint source–target attention mask reweights feature differences in the optimal transport cost, reducing the influence of low-weight channels on alignment. In experiments using measured CWRU bearing signals from three sensor locations with controlled Gaussian noise, the reported five-shot comparison achieves an average accuracy of 71.40% across six spatial transfer tasks using 20 labeled target windows, or 0.5% of the target domain. These results demonstrate the effectiveness of AM-OT for few-shot cross-sensor diagnosis on the noisy CWRU benchmark.

The performance of centrifugal aviation fuel pumps can be crucial in determining aircraft efficiency and safety. Here, we delve into the intricate interplay between flight altitude and flow rate on pump performance. Employing the central composite design method, we characterized the relationship between these parameters and the pump’s head and efficiency. Our analysis, underpinned by response surface methodology, revealed distinct optimal operating conditions at 10,000 m and 12,000 m flight altitudes, pinpointed at flow rates of 1.1016 Q and 1.1222 Q, respectively. Moreover, the emergence and growth of cavitation regions with increasing flow rates underscore the challenges in pump operation. Significantly, we identify rotor–stator interactions as a dominant influence on pressure fluctuations, especially near the impeller exit. These findings not only elucidate the operational dynamics of aviation fuel pumps but also pave the way for advanced pump designs and optimizations.

Under the given initial discharge energy level, altering the electrode structural parameters of the Ablative Pulse Plasma Thruster (APPT) is an effective way to improve the performance of the thruster. The purpose of this study is to reveal the underlying mechanism of the effect of changing the electrode structure parameters on the performance of the APPT system and to offer targeted support for researchers to optimize the design of APPT structure. With rectangular and tongue-shaped electrode configurations at various electrode flare angles, electrode lengths, and electrode spacings, the discharge characteristics, propellant ablation characteristics, and thruster performance of the APPT are systematically investigated. The underlying mechanism of how changing the electrode’s configuration parameter affects the performance of the thruster is identified by fitting and predicting the parameters of the APPT discharge circuit and system performance under various operating conditions. The results show that using tongue-shaped electrodes is more effective than using rectangular electrodes in terms of enhancing the inductive gradient of the electrodes, transferring more energy to the discharge channel, and increasing the squared integral value of the discharge current. As a result, the tongue-shaped electrode APPT performs better than the APPT with rectangular electrodes, as a consequence. The thruster’s performance can be enhanced for the same electrode configuration by increasing the electrode flare angle within a certain angle range; however, the improvement is extremely limited. Additionally, in the case of small electrode spacing, increasing the electrode flare angle can enhance the thruster’s performance more effectively.