2026-02-27
C, h, u, n, x, u, e, W, e, i
Journal of Vibroengineering, (in Press). Chunxue Wei Deep learning-based intelligent fault diagnosis methods have been widely applied in industrial production. However, in practical scenarios, the non-stationary characteristics and strong noise interference of bearing vibration signals significantly constrain the improvement of diagnostic accuracy. To address this issue, this paper proposes an intelligent fault diagnosis framework based on Variational Mode Decomposition (VMD) and Transformer-SVM. This method first employs the Osprey-Cauchy-Sparrow Search Algorithm (OCSSA), with minimum envelope entropy as the optimization objective, to adaptively determine and optimize VMD's mode number K and penalty factor α, thereby obtaining the optimal signal decomposition result. Multi-dimensional indicators are then extracted from the reconstructed signal to construct feature vectors. Subsequently, leveraging the transformer's powerful capability for modeling global dependencies, it mines the deep nonlinear relationships among features. Combined with the Support Vector Machine's strong generalization performance in classification tasks, it achieves accurate classification of bearing faults under complex operating conditions. Comparative experiments on two public datasets show that the proposed method outperforms several existing methods in terms of both classification accuracy and robustness, verifying its effectiveness and advancement.
2026-02-27
D, o, n, g, S, h, a, o, h, u, a, ,, Z, h, a, n, g, J, u, n, h, u, i
Journal of Vibroengineering, (in Press). Dong Shaohua, Zhang Junhui The rapid expansion of offshore wind energy underscores the critical need for reliable gearbox monitoring, especially for failure-prone planetary gearboxes in harsh marine environments. To address this, we propose two novel, physics-informed diagnostic parameters: the Filtered Root Mean Square (FRMS) and the Normalized Summation of the positive amplitudes of the Difference Spectrum (NSDS). These parameters enhance fault detection by isolating fault-related vibrations from healthy gearbox modulation. Furthermore, an integrated, real-time diagnosis system implementing these parameters is developed using LabVIEW. Experimental validation on a dedicated test bench demonstrates the system's effectiveness, achieving a diagnostic accuracy of 95.4 % and outperforming traditional methods. This work provides a practical and efficient solution for condition monitoring of offshore wind turbine gearboxes.
2026-02-25
Z, h, e, n, g, w, e, i, M, a
Journal of Vibroengineering, Vol. 28, Issue 2, 2026, p. 344-359 . Zhengwei Ma There are deficiencies in the optimization of the seismic performance of high-rise building shear walls, such as weak integrity and collapse resistance. Aiming at this problem, this study innovatively combines the partial replacement of concrete and steel pipe reinforcement technology, and proposes a method of locally adding steel pipe reinforcement shear walls. The experimental results showed that the specimens reinforced by the studied method exhibited better ductility and toughness when subjected to a vertical load of 840.84 kN as compared to the low-strength concrete specimens that were not reinforced by the studied method. The overall structure of the wall was able to maintain its load-bearing capacity despite the fact that the concrete at its base also suffered from crushing and spalling. In addition, the cracking displacement of the specimens (JGC-2, JGC-4, JGC-6) with localized steel pipe reinforcement was only 3.0 mm, 2.1 mm, 2.4 mm, respectively. The limit displacement was only 27.0 mm, 24.0 mm, 25.0 mm, and 45.0 mm, 47.0 mm, and 36.0 mm, respectively. The destructive displacement was only 45.0 mm, 47.0 mm, and 36.0 mm. The superiority of partial replacement of concrete and steel pipe reinforcement in improving the performance of high-rise building shear wall structures was further confirmed. It can be concluded that the research method can not only provide new ideas for the seismic strengthening of existing high-rise buildings, but also is expected to play an important role in a wider range of engineering applications. In turn, this will contribute to the improvement of the seismic performance of high-rise building structures and the protection of people's lives and property safety.
2026-02-21
C, h, u, n, J, i, n, ,, S, h, u, o, Q, i, a, n, ,, Z, h, e, n, y, u, W, a, n, g, ,, C, h, u, n, y, u, T, i, a, n, ,, Y, a, n, j, i, a, n, g, S, u, ,, S, h, e, n, g, y, u, Z, h, o, u, ,, Y, a, n, h, u, a, S, h, e, n
Journal of Vibroengineering, Vol. 28, Issue 2, 2026, p. 326-343 . Chun Jin, Shuo Qian, Zhenyu Wang, Chunyu Tian, Yanjiang Su, Shengyu Zhou, Yanhua Shen With the rapid development of construction industrialization, modular construction has been widely applied due to its advantages such as high efficiency and environmental friendliness. As the core hoisting equipment, the crane hoisting system faces issues like poor stability and low intelligence, which have become key technical bottlenecks restricting construction efficiency. To address the above problems, this study aims at the anti-swing control of the lifting and traveling mechanism, and establishes a dynamic model of the lifting and traveling mechanism with a double-pendulum effect. Based on this model, a nonlinear model predictive controller (NMPC) is designed, followed by simulation analysis and experimental verification. The simulation results show that the designed controller can effectively suppress the load swing during the movement of the trolley (the tilt angle is controlled within ±1°) and exhibits good robustness under different working conditions. In addition, by building a scaled-down experimental platform, the accuracy of the simulation model and the actual performance of the controller are further verified. This research provides an efficient and accurate hoisting solution for improving the precision and efficiency of tower crane systems in modular building construction, and is of great significance for promoting the development of modern construction technology.
2026-02-21
Y, i, y, i, n, g, W, a, n, g, ,, F, u, l, u, S, u, i, ,, X, i, a, o, l, i, n, g, L, i, ,, X, i, a, o, x, i, n, Z, h, a, n, g, ,, M, i, n, g, x, i, a, n, L, i, u, ,, C, h, e, n, L, i, u, ,, J, i, e, W, u
Journal of Vibroengineering, Vol. 28, Issue 2, 2026, p. 219-239 . Yiying Wang, Fulu Sui, Xiaoling Li, Xiaoxin Zhang, Mingxian Liu, Chen Liu, Jie Wu In this study, a novel deep transfer learning method, termed the Universal Domain Alignment and Multi-level Alignment Network (UDAM-Net), is established to address the significant feature distribution discrepancy between the source and target domains caused by the difficulty of feature extraction for rolling bearings under complex operating conditions. In the feature extraction stage, a one-dimensional convolutional neural network is integrated with a Transformer-based multi-head attention mechanism to effectively enhance the feature representation capability of raw signals. Additionally, the complementary advantages of Joint Maximum Mean Discrepancy (JMMD), Multi-kernel Maximum Mean Discrepancy (MK-MMD), and a domain discriminator are explored by designing a collaborative mechanism combining distribution metrics and adversarial learning in conjunction with transfer learning. Furthermore, an uncertainty-based weighting strategy is introduced to adaptively adjust the loss function and dynamically balance the contributions of different alignment modules. Finally, the Adam optimizer is employed to accelerate model convergence. Experimental results on the CWRU public dataset and a laboratory-built test rig dataset demonstrate that UDAM-Net achieves classification accuracies of 96.67 % and 96.17 %, respectively. This study enlightens fault diagnosis based on feature extraction and cross-domain feature alignment.
2026-02-20
X, i, a, o, r, o, n, g, Q, i, u, ,, Y, e, X, u
Journal of Vibroengineering, Vol. 28, Issue 2, 2026, p. 270-299 . Xiaorong Qiu, Ye Xu In this paper, a simulation data-driven intelligent fault diagnosis algorithm based on attention mechanism and transfer learning is proposed to address insufficient fault data, low diagnostic accuracy, and inefficiency in rolling bearing monitoring under cross-condition and cross-location scenarios. To overcome the lack of real fault data, a dynamic vibration-response model is constructed through analysis of bearing and fault dynamics, generating high-fidelity fault signals across multiple operating conditions. Based on this, a diagnostic model is developed using a self-attention–assisted weighted autoencoder, where the proposed weighted autoencoder integrates a self-attention mechanism and a weight allocation mechanism and the former captures inter-feature dependencies while the latter adaptively reweighting feature contributions to enhance fault-discriminative representations. Therefore, the diagnostic model can assign corresponding weights to different importance features according to the constructed self-attention mechanism-assisted weighted self-encoding feature extraction model, effectively avoiding the problems of insufficient diagnostic accuracy and low diagnostic efficiency caused by feature redundancy and difficulty in distinguishing the importance of rolling bearing faults. Furthermore, the local maximum mean discrepancy (LMMD) method is applied to align both global and sub-domain distributions between simulated and measured data. By synthesizing cross-condition and cross-location simulated signals with real measurements, an LMMD-based intelligent transfer diagnosis model is built to enhance generalization and robustness against large distribution discrepancies. Finally, the stability and robustness of the proposed method are validated by analyzing the transfer learning performance and anti-noise disturbance ability across different operating conditions and locations.
2026-02-18
C, h, e, n, g, y, u, S, h, a, ,, P, i, n, g, b, o, W, u, ,, J, i, e, H, u
Journal of Vibroengineering, Vol. 28, Issue 2, 2026, p. 431-449 . Chengyu Sha, Pingbo Wu, Jie Hu Gear transmission has a non-negligible influence on the dynamic responses and wheel wear of high-speed motor cars. This work analyzes the influence of the driving system on dynamic responses and wheel wear of high-speed motor cars during acceleration. Firstly, a fully nonlinear multibody system(MBS) is developed and various nonlinear factors, such as various types of dampers and wheel-rail contact relation, are considered, and the detailed gear transmission is also introduced to obtain the accurate dynamic responses. Secondly, a wheel wear prediction model integrating the Archard wear model and the vehicle dynamics system is established based on wheel tread update strategy of target speed, and wheel wear evolution of high-speed motor car is obtained in one re-profiling cycle, and simulation results are compared with the field measured data respectively to validate vehicle model and wheel wear prediction procedure. Finally, the effects of gearbox suspension rod stiffness and vertical motor suspension joint stiffness on dynamic responses and wheel wear during acceleration process are simulated respectively. The results show that as the gearbox suspension rod stiffness increases, the gearbox suspension force gradually increases, which not only suppresses the nodding motion of the gearbox but also reduces the absolute value of the longitudinal wheel creepage, resulting in the reduction of wear depth. Moreover, the difference between the dynamic response of high-speed motor cars with and without gear transmission is huge, which indicates that gear transmission is not negligible in the process of dynamics simulation and wheel wear prediction.
2026-02-06
J, o, e, l, S, a, m
Journal of Vibroengineering, Vol. 28, Issue 2, 2026, p. 373-385 . Joel Sam Soft rock tunnels excavated under high ground stress are particularly vulnerable to seismic loading due to their low stiffness and complex rock-lining interaction. This study presents a performance-based seismic evaluation of a deep-buried soft-rock tunnel using Incremental Dynamic Analysis (IDA) implemented in MIDAS GTS NX. A two-dimensional numerical model of a semicircular tunnel with a diameter of 10 m and a burial depth of 500 m is subjected to incrementally scaled earthquake records representing moderate and strong seismic excitations. Key engineering demand parameters, including displacement, base shear, and drift ratio are evaluated, and IDA-based fragility curves are developed to quantify damage exceedance probability. Unlike most exciting tunnel seismic studies that rely on linear or single-intensity dynamic analyses, this study integrates IDA with fragility assessment to systematically capture nonlinear response evolution and record-to-record variability of deep-buried soft rock tunnels under high ground stress. The results indicate pronounced nonlinear deformation and amplification of internal forces with increasing seismic intensity, with maximum displacement and base shear increasing by approximately 90 % and 50 %, respectively. The findings demonstrate the effectiveness of IDA as a vibration-based performance evaluation tool for underground structures and provide new insights for the seismic design of tunnels in high-stress and seismically active regions.
2026-01-25
Z, h, i, k, u, n, W, a, n, g, ,, F, e, n, g, m, e, i, Z, h, a, n, g, ,, L, u, m, e, n, g, H, u, a, n, g
Journal of Vibroengineering, Vol. 28, Issue 1, 2026, p. 17-31 . Zhikun Wang, Fengmei Zhang, Lumeng Huang In the event that a floating drilling platform is struck suddenly by a typhoon, preventing the complete retrieval of the riser, a compensation system is required to alleviate the considerable dynamic loads on the riser resulting from platform movement, thus keeping the riser tension within safe limits. Evaluation of the mathematical model for the conventional vibration isolation system indicated unsatisfactory performance under conditions of large displacement and ultra-low-frequency vibration. To address this, a new dynamic load compensation system for the riser has been developed, along with a dedicated experimental platform. In this setup, platform heave is simulated via the extension and retraction of a hydraulic cylinder, while the riser load is represented using multiple mass blocks. The experimental platform supports both manual and automatic control modes. Utilizing Visual Basic (VB) programming integrated with an Access database, the monitoring and control software provides capabilities for parameter configuration, data monitoring, and data archiving. Experiments performed on this platform, including heavy simulation and dynamic load compensation, demonstrated a compensation effect of 27.4 %. The successful mitigation of dynamic loads on the riser presents a novel approach for drilling platforms to cope with typhoon emergencies and suggests valuable applications for vibration isolation technology in other domains.
2026-01-14
Y, o, n, g, g, a, n, g, W, a, n, g
Journal of Vibroengineering, Vol. 28, Issue 1, 2026, p. 105-123 . Yonggang Wang Under the premise of ensuring modal and strength characteristics, achieving lightweight design of the structure simultaneously has become a key issue of concern for major automobile manufacturers and research institutions. To reduce the mass redundancy of the bus chassis frame, save production costs and energy consumption, a multi-objective optimization scheme based on surrogate model technology was proposed, which could maximize weight reduction without reducing the natural frequency or increasing the peak stress. According to the working principle, load characteristics and composition of the chassis frame, a parametric coupling model for modal and strength was constructed, and the stress, deformation, natural frequency and vibration mode characteristics of the overall structure were obtained. The dimensions of H-steel were determined as design variables, and the discrete mapping data sets of maximum stress, first-order natural frequency and mass were obtained through the Latin square design scheme. Parameters such as the coefficient of determination, adjusted coefficient of determination and root mean square error were selected as the standard evaluation indicators for the accuracy of the response surface model. The reliability of different surrogate models was compared and analyzed, and finally the Kriging model was adopted as the approximation function in the construction of the mathematical model. An optimized mathematical model was constructed to convert the modal and strength objectives into boundary conditions. The design variables meeting the optimization objectives were derived through the sequential quadratic programming algorithm. The results showed that, without reducing the requirements for strength and stiffness indicators, this optimization scheme could reduce the weight of the chassis frame by 9.94 %, which has good economic benefits and engineering value.