This study develops an intelligent recognition and fault prediction model for mechanical system vibration signals based on deep learning to achieve automatic identification and early warning of equipment faults. This study proposes a hybrid deep learning framework integrating a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. CNN extracts spatial features from vibration signals; LSTM models their temporal dynamic characteristics, enabling continuous monitoring of equipment health status and prediction of fault trends. The proposed method achieves an accuracy of 92.1% in multi-type fault identification tasks. In regression prediction tasks, it yields a mean squared error of 0.059 and a coefficient of determination (R²) of 0.867, outperforming traditional models significantly. The proposed hybrid deep learning framework can simultaneously analyze the frequency-domain features and temporal evolution patterns of vibration signals, providing a new technical approach for fault diagnosis of mechanical systems. This method improves the accuracy and efficiency of fault identification; it also offers effective support for the realization of intelligent remote equipment health management. This is of great significance for promoting the transformation of industrial equipment maintenance toward intelligence and predictiveness. This study successfully develops a deep learning-based model for intelligent recognition of vibration signals and fault prediction of mechanical systems. This model features high accuracy, strong generalization capability, and promising engineering application prospects. A Chinese invention patent has been filed for the core algorithm (Application No.: 202510784326.8). These outcomes provide a scientific basis, technical support, and patent barriers for intelligent maintenance of industrial equipment.

Fe-based amorphous coatings are promising for corrosion protection in marine environments, yet their long-term performance after sealing treatment under salt-spray exposure remains unclear. In this study, two atmospheric plasma-sprayed Fe-based amorphous coatings, APS3 and APS5, prepared at different H ₂ flow rates, were sealed using a brush-applied nano-alumina sealant. The microstructure and corrosion behavior of the coatings, before and after sealing, were systematically evaluated by porosity analysis, scanning electron microscopy, x-ray diffraction, potentiodynamic polarization, and electrochemical impedance spectroscopy during 3 weeks of salt-spray exposure. The results showed that the as-sprayed coatings retained a predominantly amorphous structure and exhibited porous features. Sealing treatment reduced the porosity of APS3 and APS5 from (4.76 ± 0.5)% to (2.64 ± 0.5)% and from (3.32 ± 0.5)% to (1.58 ± 0.5)%, respectively. During the first two weeks of exposure, the sealed coatings showed higher corrosion potentials, lower corrosion current densities, and larger impedance responses than the corresponding unsealed coatings. APS5 consistently exhibited superior corrosion resistance, attributed to its lower porosity and denser microstructure. After 21 d, sealant degradation and detachment became evident, accompanied by a marked decline in corrosion resistance. These findings indicate that sealing treatment can effectively improve the salt-spray corrosion resistance of Fe-based amorphous coatings for approximately two weeks, and provide guidance for the design and durability evaluation of protective coating systems intended for marine service environments.

With the development of the low-altitude economy, industries such as general aviation, electric vertical takeoff and landing, and electric vehicle manufacturing are developing rapidly. Consequently, the requirements for forming processes of thin-walled components have become more stringent. As a process-optimization study aimed at industrial applications, this paper investigates a novel spatiotemporal energy control scheme for the electrohydraulic forming (EHF) of complex-shaped sheet metal components. A multi-contour discharge block and impulse current generator system is developed to achieve precise temporal and spatial regulation of energy flow, verifying the feasibility of implementing spatiotemporal control of energy flow on plastically deformed sheets. It is confirmed that energy flow can be concentrated in specific regions of the sheet; the energy concentration in the central region is significantly enhanced compared with traditional single-contour systems, and can be redirected to address hard-to-form edge regions via liquid jet interaction. Regulating the pre-discharge stage and discharge delays between multiple discharge chambers enables synchronous or differentiated energy release. The optimal discharge delay of 150–300 μ s maximizes energy release efficiency, with the central region achieving a plastic strain rate of 35 s ⁻¹ . Compared with traditional single-contour EHF equipment, the proposed technology reduces energy consumption via optimized energy distribution, improves forming efficiency by over 30%, and shortens the process cycle. This research provides a feasible technical solution for the efficient manufacturing of complex thin-walled sheet metal components, addressing the issues of energy loss and poor deformation uniformity in complex thin-walled sheet part forming and supporting the industrial upgrading of aviation and automotive manufacturing.