For practical mechanical systems, uncertainties/disturbances, such as unmodeled dynamics and frictions, are nonignorable factors. For existing control methods, these factors are usually neglected or addressed by a robust way. As a consequence, the nominal control performance of these methods is sacrificed. Moreover, there exists the chattering problem for some existing robust methods, such as sliding mode control laws. To deal with these drawbacks, a continuous global sliding mode controller along with a nonlinear disturbance observer is designed for the regulation and disturbance estimation control of the overhead crane system. Specifically, the original crane dynamic model is transformed into a quasi-integrator-chain form through some transformations. Then, a nonlinear disturbance observer is designed and a continuous global sliding mode control method is introduced on the basis of the constructed disturbance observer. The stability and convergence characteristics are proven through rigorous theoretical analysis. Finally, to demonstrate the performance of the designed controller, a series of experimental tests are performed, and a comparison study between the devised method here and an existing method is given.

Bearings are the key and important components of rotating machinery. Effective bearing fault diagnosis can ensure operation safety and reduce maintenance costs. This paper aims to develop a novel bearing fault diagnosis method via an improved multi-scale convolutional neural network (IMSCNN). In traditional convolutional neural network (CNN), a fixed convolutional kernel is often employed in the convolutional layer. Thus, informative features can not be fully extracted for fault diagnosis. In the proposed IMSCNN, a 1D dimensional convolutional layer is used to mitigate the effect of noise contained in vibration signals. Then, four dilated convolutional kernels with different dilation rates are integrated to extract multi-scale features through the inception structure. Experimental results from the popular CWRU and PU datasets show the superiority of the proposed method by comparison with other related methods.

In practice, various factors such as friction, unmodeled dynamics and uncertain external disturbances often affect overhead cranes. The existing crane control methods often neglect these factors or address these factors by robust techniques. Moreover, most of them do not take input saturation into account and require full-state feedback. In this paper, taking the practical issues of uncertain disturbances, input saturation and output feedback into account, we propose an input-saturated output feedback control strategy for the underactuated two-dimensional (2-D) overhead crane systems with uncertain disturbances. Specifically, we first design a disturbance observer that can accurately estimate the external disturbance. Then, the virtual horizontal location signal is introduced and the new energy storage function is constructed. A novel composite control method for overhead crane systems is proposed based on the developed disturbance observer and the new energy storage function. The stability and convergence analysis are given through Lyapunov techniques and LaSalle’s invariance theorem. In order to verify the performance of the proposed controller, we perform a series of simulation tests and compare the proposed method with some existing control methods.

Floating debris detection in complex aquatic environments holds significant importance for water resource protection and maritime safety monitoring. However, this task faces three core challenges: severe background interference leading to blurred target textures, significant non-rigid deformations, and the frequent loss of small targets at long distances. To address these issues, we propose a high-performance lightweight detection algorithm, termed High-Efficiency Edge-Aware Multi-Scale Real-Time Detection Transformer (HEMS-RTDETR), built upon the Real-Time Detection Transformer (RT-DETR) architecture. First, to suppress disturbances induced by water surface ripples and specular reflections, a Cross-Stage Partial Multi-Scale Edge Information Enhancement (CSP-MSEIE) module is introduced to reconstruct the backbone network. By removing computational redundancy while incorporating explicit edge enhancement, feature extraction capability and noise robustness for weak-texture targets are significantly improved. Second, to handle irregular debris morphology, a Deformable Attention Transformer (DAT) module is integrated, enabling adaptive attention focusing on geometrically deformed regions. Finally, an Efficient Multi-Scale Bidirectional Feature Pyramid Network (EMBSFPN) is constructed to enhance cross-scale semantic interaction and alleviate small-target signal loss. Experimental results demonstrate that, compared with RTDETR-r18, HEMS-RTDETR reduces parameters to 12.57 M, improves mAP@0.5 and mAP@0.5:0.95 by 2.44% and 3.05%, respectively, and maintains real-time inference at 93 FPS, indicating strong robustness and application potential in dynamic aquatic environments.