In this paper, a quadratic convolution neural network (QCNN) using both audio and vibration signals is utilized for bearing fault diagnosis. Specifically, to make use of multi-modal information for bearing fault diagnosis, the audio and vibration signals are first fused together using a 1 × 1 convolution. Then, a quadratic convolution neural network is applied for the fusion feature extraction. Finally, a decision module is designed for fault classification. The proposed method utilizes the complementary information of audio and vibration signals, and is insensitive to noise. The experimental results show that the accuracy of the proposed method can achieve high accuracies for both single and multiple bearing fault diagnosis in the noisy situations. Moreover, the combination of two-modal data helps improve the performance under all conditions.

In this paper, a graph convolutional network is constructed and applied for bearing fault diagnosis. Specifically, the constant-Q transform (CQT) is first adopted for spectral analysis of vibration signals, where the frequencies are distributed in the logarithmic scale. Varied frequency resolutions can be obtained to satisfy the spectral resolution requirement and reduce signal dimension. Afterwards, the CQT spectrum is modeled by a graph, where nodes are frequency bins and edges reflect the inner relationship of different bins. There are edges between the fundamental and harmonic components. Then, a two-layer graph convolutional network (GCN) is utilized to assess the significance of vibration sources within the mixed signals. Finally, the bearing faults are determined according to the output of the GCN. To the best of our knowledge, this is the first work to model the vibration signal in this graph structure. The advantage of this approach lies in the simplification of edge definitions, facilitating shared connectivity relationships between the fundamental frequency and harmonics. Its performance was compared with another state-of-the-art fault diagnosis model. Experimental results demonstrate that the proposed model obtains higher accuracy, and it is more effective in extracting discriminative features.

In this study, a preparation method of superhydrophobic composite coating based on a titanium alloy (Ti-6Al-4V) substrate is proposed. The micro-scale pit array structure was fabricated via laser etching technology. Utilizing the synergistic effects of epoxy resin (EP), polydimethylsiloxane (PDMS), and fluorinated nanosilica (F-SiO₂), we successfully prepared an EP@PDMS@F-SiO₂ composite coating. The effects of the contents of EP, PDMS, and F-SiO₂ on the surface wettability, mechanical stability, and UV durability were studied by optimizing the coating ratio through orthogonal experiments. The results show that the micro–nano composite structure formed by laser etching can effectively fix the coating particles and provide excellent superhydrophobicity on the surface. The coating retains high hydrophobicity after paper abrasion (1000 cm under a 200 g load), demonstrating the mechanical stability of the armor-like structure, High-content F-SiO₂ coatings exhibit greater UV durability. In addition, the coating surface has low droplet adhesion and self-cleaning capabilities for efficient contaminant removal. The research provides theoretical and technical support for the design and engineering application of a non-fluorinated, environmentally friendly superhydrophobic coating.

With the widespread application of sensor networks, traditional power supplies face limitations, especially in remote marine areas where battery replacement is challenging and lifespan is limited. As a clean and renewable energy source, wind energy offers a promising solution to this issue. But conventional turbines are bulky, costly, and inefficient at low wind speeds for micro sensors. This study proposes a hybrid triboelectric-electromagnetic wind energy harvester (H-TEWH) that integrates an electromagnetic generator (EMG) with a triboelectric nanogenerator (TENG) to enable synergistic energy harvesting across varying wind speeds. At 11 m/s, the device achieves a theoretical peak output of 12.08 mW. An efficient power management circuit, combining a gas-discharge-tube-based buck circuit and an LTC3588 module to ensure stable and continuous power output. Self-powered sensor experiments validated the practicality and reliability of the system in complex marine environments, providing a feasible technical solution for self-powered devices suitable for maritime monitoring applications.

In this paper, a method is proposed to accurately measure the torsional vibration of a ship’s propulsion shafting, and calculate its instantaneous torque based on instantaneous speed data. The instantaneous speed signal of a ship is measured by a data acquisition instrument indirectly under the deceleration condition, and then filtered by the five-point smoothing algorithm. The filtered instantaneous speed signal is further processed to calculate the maximum amplitude of the torsional vibration, along with the maximum torque of the propulsion shafting under specific operating conditions. The proposed method can effectively improve the calculation accuracy of the torsional vibration of the shafting, and provides reliable theoretical basis for setting the safe speed of the ship’s diesel engine.

For the traditional one-degree-of-freedom controller, there is a trade-off between the tracking performance and disturbance rejection performance. The traditional two-degree-of-freedom controller can achieve disturbance rejection and tracking simultaneously, when there are one tracking channel and one disturbance rejection channel. To overcome the limitations of the one-degree-of-freedom controller and the traditional two-degree-of-freedom controller, an improved two-degree-of-freedom controller is designed for the speed regulation system of a permanent-magnet synchronous motor (PMSM) for use in electric aircraft scenarios and PMSM control applications. This proposed controller includes three elements: a proportional forward element, a proportional–integral feedback element, and a linear extended state observer element. The proportional forward element is used for tracking, and the proportional–integral feedback element and linear extended state observer element are used for disturbance rejection. The controller can simultaneously achieve tracking and disturbance rejection. The proportional forward element guarantees tracking performance, while the proportional–integral feedback and linear extended state observer elements enhance disturbance rejection. The stability of the proposed controller is experimentally demonstrated, and the results show that the improved controller offers superior tracking and disturbance rejection compared to traditional 1-DoF and 2-DoF controllers.