Mechanical Systems and Signal Processing最新文献_第5页

Vehicle-based bridge health monitoring with limited data: a physics-guided TimeGAN and multi-view feature fusion framework 基于有限数据的车辆桥梁健康监测：物理引导的TimeGAN和多视图特征融合框架

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-03 DOI: 10.1016/j.ymssp.2026.113949

Yifu Lan , Robert Corbally , Flavio Bono , Daniel Tirelli , Abdollah Malekjafarian

In recent years, indirect bridge health monitoring (iBHM) using vehicle-mounted sensors has gained increasing attention due to its low-carbon footprint and cost-efficiency. The rapid development of artificial intelligence (AI) has further promoted its potential for industrial deployment and scalability. However, the limited availability and high noise levels of drive-by measurements often hinder its practical implementation. To address these, this study proposes a hybrid framework that integrates physics-informed data augmentation with multi-view data fusion and unsupervised learning strategies. PyTiGAN, a physics-guided time-series GAN, is developed to synthesize high-fidelity drive-by data using a physics vehicle-bridge interaction (VBI) kernel. These generated data are then combined with real measurements for structural state identification. A multi-view dimensionality reduction and fusion scheme is designed to extract discriminative features from various sensors and embed them into a compact fused space. The framework was validated using field-test data from a testbed bridge structure and a vehicle at the testing site in Ispra, Italy, as part of the MITICA (MonItoring Transport Infrastructures with Connected and Automated Vehicles) project. The results confirm that the framework can accurately detect both minor and moderate bridge damage using only limited drive-by data. Sensitivity analyses further examine how synthetic data volume, physics-based kernels, embedding dimensions, and sensor placement influence damage detection performance. The proposed method demonstrates a promising solution for iBHM under data scarcity.

近年来，基于车载传感器的桥梁间接健康监测（iBHM）因其低碳足迹和成本效益而受到越来越多的关注。人工智能（AI）的快速发展进一步提升了其产业部署和可扩展性的潜力。然而，驾驶测量的有限可用性和高噪声水平经常阻碍其实际实施。为了解决这些问题，本研究提出了一个混合框架，该框架将物理信息数据增强与多视图数据融合和无监督学习策略相结合。PyTiGAN是一种物理引导的时间序列GAN，用于使用物理车桥交互（VBI）内核合成高保真的行车数据。然后将这些生成的数据与实际测量数据相结合，用于结构状态识别。设计了一种多视图降维融合方案，从各种传感器中提取判别特征，并将其嵌入到紧凑的融合空间中。作为MITICA（连接和自动车辆监控交通基础设施）项目的一部分，该框架使用来自意大利Ispra试验场的试验台桥梁结构和车辆的现场测试数据进行了验证。结果表明，该框架仅使用有限的驱动数据就能准确地检测出桥梁的轻微和中度损伤。灵敏度分析进一步研究了合成数据量、基于物理的核、嵌入维度和传感器位置如何影响损伤检测性能。该方法为数据稀缺条件下的iBHM提供了一个很好的解决方案。

{"title":"Vehicle-based bridge health monitoring with limited data: a physics-guided TimeGAN and multi-view feature fusion framework","authors":"Yifu Lan , Robert Corbally , Flavio Bono , Daniel Tirelli , Abdollah Malekjafarian","doi":"10.1016/j.ymssp.2026.113949","DOIUrl":"10.1016/j.ymssp.2026.113949","url":null,"abstract":"<div><div>In recent years, indirect bridge health monitoring (iBHM) using vehicle-mounted sensors has gained increasing attention due to its low-carbon footprint and cost-efficiency. The rapid development of artificial intelligence (AI) has further promoted its potential for industrial deployment and scalability. However, the limited availability and high noise levels of drive-by measurements often hinder its practical implementation. To address these, this study proposes a hybrid framework that integrates physics-informed data augmentation with multi-view data fusion and unsupervised learning strategies. PyTiGAN, a physics-guided time-series GAN, is developed to synthesize high-fidelity drive-by data using a physics vehicle-bridge interaction (VBI) kernel. These generated data are then combined with real measurements for structural state identification. A multi-view dimensionality reduction and fusion scheme is designed to extract discriminative features from various sensors and embed them into a compact fused space. The framework was validated using field-test data from a testbed bridge structure and a vehicle at the testing site in Ispra, Italy, as part of the MITICA (MonItoring Transport Infrastructures with Connected and Automated Vehicles) project. The results confirm that the framework can accurately detect both minor and moderate bridge damage using only limited drive-by data. Sensitivity analyses further examine how synthetic data volume, physics-based kernels, embedding dimensions, and sensor placement influence damage detection performance. The proposed method demonstrates a promising solution for iBHM under data scarcity.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113949"},"PeriodicalIF":8.9,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vibration isolation capability with interval uncertainty and optimization of semi-active suspension based on self-powered magneto-rheological damper 基于自供电磁流变阻尼器的半主动悬架隔振性能及优化

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-03 DOI: 10.1016/j.ymssp.2026.113969

Xiang Gao , Qiang Zhao , Hui Ming , Zihao Zhou , Junchuan Niu , Zhonglong Wang , Zhen Qin

In order to explore the vibration isolation performance of semi-active suspension based on self-powered Magneto-Rheological (MR) damper with interval uncertainty, the electromechanical coupling dynamic model of quarter vehicle suspension with key parameters perturbation is established. The vibration isolation capability is investigated in time and frequency domain with key parameters perturbation respectively. The non-probabilistic reliability of the proposed suspension is deduced by shortest distance method. The balance index reflecting the comprehensive performance of energy harvesting characteristic and vibration isolation capability simultaneously is proposed by dynamical programming theory. The adjustment of structural parameters of damper is much more effective to improve the comprehensive performance. The optimized key parameters are obtained by calculating the Nash equilibrium point of the balance index, meanwhile, the validation of the proposed optimized approach with NSGA-II algorithm is conducted. The optimized MR damper and energy harvesting part are fabricated and tested. The experimental results are similar to the simulating results, which indicates the effectiveness and correctness of the proposed optimized method.

为了研究具有区间不确定性的自供电磁流变阻尼器半主动悬架的隔振性能，建立了考虑关键参数摄动的四分之一汽车悬架机电耦合动力学模型。在时域和频域分别研究了关键参数摄动的隔振性能。采用最短距离法推导了悬架的非概率可靠性。利用动态规划理论，提出了同时反映能量收集特性和隔振能力综合性能的平衡指标。调整阻尼器的结构参数对提高阻尼器的综合性能更为有效。通过计算平衡指标的纳什平衡点得到了优化后的关键参数，同时利用NSGA-II算法对所提出的优化方法进行了验证。制作并测试了优化后的MR阻尼器和能量收集部件。实验结果与仿真结果基本一致，验证了所提优化方法的有效性和正确性。

{"title":"Vibration isolation capability with interval uncertainty and optimization of semi-active suspension based on self-powered magneto-rheological damper","authors":"Xiang Gao , Qiang Zhao , Hui Ming , Zihao Zhou , Junchuan Niu , Zhonglong Wang , Zhen Qin","doi":"10.1016/j.ymssp.2026.113969","DOIUrl":"10.1016/j.ymssp.2026.113969","url":null,"abstract":"<div><div>In order to explore the vibration isolation performance of semi-active suspension based on self-powered Magneto-Rheological (MR) damper with interval uncertainty, the electromechanical coupling dynamic model of quarter vehicle suspension with key parameters perturbation is established. The vibration isolation capability is investigated in time and frequency domain with key parameters perturbation respectively. The non-probabilistic reliability of the proposed suspension is deduced by shortest distance method. The balance index reflecting the comprehensive performance of energy harvesting characteristic and vibration isolation capability simultaneously is proposed by dynamical programming theory. The adjustment of structural parameters of damper is much more effective to improve the comprehensive performance. The optimized key parameters are obtained by calculating the Nash equilibrium point of the balance index, meanwhile, the validation of the proposed optimized approach with NSGA-II algorithm is conducted. The optimized MR damper and energy harvesting part are fabricated and tested. The experimental results are similar to the simulating results, which indicates the effectiveness and correctness of the proposed optimized method.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113969"},"PeriodicalIF":8.9,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Signal-based online acceleration and strain data fusion using B-splines and Kalman filter for full-field dynamic displacement estimation 基于b样条和卡尔曼滤波的加速度和应变数据在线融合，用于全场动态位移估计

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-03 DOI: 10.1016/j.ymssp.2026.113951

Aniruddha Das , Ashish Pal , Satish Nagarajaiah , M. Mohamed Sajeer , Suparno Mukhopadhyay

Displacement plays a crucial role in structural health monitoring (SHM) and damage detection of structural systems subjected to dynamic loads. However, due to the inconvenience associated with the direct measurement of displacement during dynamic loading and the high cost of displacement sensors, the use of displacement measurements often gets restricted. In recent years, indirect estimation of displacement from acceleration and strain data has gained popularity. Several researchers have developed data fusion techniques to estimate displacement from acceleration and strain data. However, existing data fusion techniques mostly rely on system properties like mode shapes or finite element models and require accurate knowledge about the system for successful implementation. Hence, they have the inherent limitation of their applicability being restricted to relatively simple structures where such information is easily available. In this article, B-spline basis functions have been used to formulate a Kalman filter-based algorithm for acceleration and strain data fusion using only elementary information about the system, such as the geometry and boundary conditions, which is the major advantage of this method. Also, the proposed algorithm enables us to monitor the full-field displacement of the system online with only a limited number of sensors. The method has been numerically validated with both simple and complex numerical models. Later, the proposed data fusion technique was applied to an experimental benchmark test of a wind turbine blade under dynamic load to estimate the displacement time history. In all cases, the reconstructed displacement from strain and acceleration was found to match well with the response from the FE model.

位移在结构健康监测和结构损伤检测中起着至关重要的作用。然而，由于在动加载过程中直接测量位移的不便和位移传感器的高成本，位移测量的使用往往受到限制。近年来，从加速度和应变数据中间接估计位移的方法得到了广泛的应用。一些研究人员开发了数据融合技术，从加速度和应变数据中估计位移。然而，现有的数据融合技术主要依赖于模态振型或有限元模型等系统属性，并且需要对系统有准确的了解才能成功实现。因此，它们具有固有的局限性，即它们的适用性仅限于相对简单的结构，在这些结构中容易获得此类信息。在本文中，利用b样条基函数建立了一种基于卡尔曼滤波的加速和应变数据融合算法，该算法只使用系统的基本信息，如几何和边界条件，这是该方法的主要优点。此外，所提出的算法使我们能够仅使用有限数量的传感器在线监测系统的全场位移。用简单和复杂的数值模型对该方法进行了数值验证。随后，将所提出的数据融合技术应用于某风力机叶片动载荷下的试验基准测试，估计叶片位移时程。在所有情况下，应变和加速度的重建位移与有限元模型的响应匹配良好。

{"title":"Signal-based online acceleration and strain data fusion using B-splines and Kalman filter for full-field dynamic displacement estimation","authors":"Aniruddha Das , Ashish Pal , Satish Nagarajaiah , M. Mohamed Sajeer , Suparno Mukhopadhyay","doi":"10.1016/j.ymssp.2026.113951","DOIUrl":"10.1016/j.ymssp.2026.113951","url":null,"abstract":"<div><div>Displacement plays a crucial role in structural health monitoring (SHM) and damage detection of structural systems subjected to dynamic loads. However, due to the inconvenience associated with the direct measurement of displacement during dynamic loading and the high cost of displacement sensors, the use of displacement measurements often gets restricted. In recent years, indirect estimation of displacement from acceleration and strain data has gained popularity. Several researchers have developed data fusion techniques to estimate displacement from acceleration and strain data. However, existing data fusion techniques mostly rely on system properties like mode shapes or finite element models and require accurate knowledge about the system for successful implementation. Hence, they have the inherent limitation of their applicability being restricted to relatively simple structures where such information is easily available. In this article, B-spline basis functions have been used to formulate a Kalman filter-based algorithm for acceleration and strain data fusion using only elementary information about the system, such as the geometry and boundary conditions, which is the major advantage of this method. Also, the proposed algorithm enables us to monitor the full-field displacement of the system online with only a limited number of sensors. The method has been numerically validated with both simple and complex numerical models. Later, the proposed data fusion technique was applied to an experimental benchmark test of a wind turbine blade under dynamic load to estimate the displacement time history. In all cases, the reconstructed displacement from strain and acceleration was found to match well with the response from the FE model.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113951"},"PeriodicalIF":8.9,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic characteristics analysis of a spalled bearing-rotor system for high-speed trains under combined excitations 联合激励下高速列车剥落轴承-转子系统动态特性分析

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-02 DOI: 10.1016/j.ymssp.2026.113943

Yuewei Yu , Guokai Jiao , Bo Li , Leilei Zhao , Chuanbo Ma

With the continuous increase in the operating speed of high-speed trains, faults for rotor-bearing systems have become increasingly prominent, posing a serious threat to train’s operation safety. Among the various faults of rotor-bearing systems, bearing spalling not only affects the normal operation of the bearing itself but also alters the dynamic characteristics of the rotor-bearing system, thereby inducing additional frequency components and super-harmonic resonances, which greatly increase the difficulty of fault identification in train rotor-bearing systems. This paper focuses on spalling in deep-groove ball bearings of traction-motor rotor-bearing systems. Based on an analysis of the coupling among multiple excitations, a dynamic model is developed that simultaneously accounts for rotor unbalanced magnetic pull, mechanical unbalance forces, rubbing forces, gravity, the nonlinear supporting forces of a cylindrical roller bearing and the nonlinear supporting forces of deep-groove ball bearing with spalling. The model is validated against test-rig experiments. Quantitative analysis in the speed range of 1 000–5 000 rpm shows that outer-race, inner-race and rolling-element spalling generate clearly distinguishable fault characteristic bands and modulation sidebands. When rolling elements pass over a local spall, the contact force exhibits instantaneous jumps and intermittent loss, so that the RMS value of the nonlinear supporting force becomes about 2.4–3.4 times that of the corresponding healthy bearing. As the spall width increases, the RMS acceleration and supporting force grow monotonically at all speeds, with the amplification especially pronounced at 5 000 rpm. These quantitative findings provide a modeling reference and theoretical basis for fault diagnosis of rotor-bearing systems in high-speed trains.

随着高速列车运行速度的不断提高，转子轴承系统故障日益突出，对列车运行安全构成严重威胁。在转子-轴承系统的各种故障中，轴承剥落不仅影响轴承本身的正常运行，还会改变转子-轴承系统的动态特性，从而诱发附加频率分量和超谐波共振，大大增加了列车转子-轴承系统故障识别的难度。本文主要研究牵引电机转子-轴承系统中深沟球轴承的剥落问题。在分析多种激励耦合的基础上，建立了同时考虑转子不平衡磁拉力、机械不平衡力、摩擦力、重力、圆柱滚子轴承的非线性支撑力和带剥落深沟球轴承的非线性支撑力的动力学模型。通过试验验证了模型的有效性。在1 000 ~ 5 000 rpm转速范围内的定量分析表明，外圈、内圈和滚动元件剥落产生了明显可区分的故障特征带和调制边带。当滚动体通过局部小块时，接触力表现出瞬时跳跃和间歇性损失，使得非线性支撑力的均方根值约为相应健康轴承的2.4-3.4倍。随着小片宽度的增加，在所有速度下，RMS加速度和支撑力单调增长，在5000rpm时放大尤为明显。这些定量研究结果为高速列车转子轴承系统的故障诊断提供了建模参考和理论依据。

{"title":"Dynamic characteristics analysis of a spalled bearing-rotor system for high-speed trains under combined excitations","authors":"Yuewei Yu , Guokai Jiao , Bo Li , Leilei Zhao , Chuanbo Ma","doi":"10.1016/j.ymssp.2026.113943","DOIUrl":"10.1016/j.ymssp.2026.113943","url":null,"abstract":"<div><div>With the continuous increase in the operating speed of high-speed trains, faults for rotor-bearing systems have become increasingly prominent, posing a serious threat to train’s operation safety. Among the various faults of rotor-bearing systems, bearing spalling not only affects the normal operation of the bearing itself but also alters the dynamic characteristics of the rotor-bearing system, thereby inducing additional frequency components and super-harmonic resonances, which greatly increase the difficulty of fault identification in train rotor-bearing systems. This paper focuses on spalling in deep-groove ball bearings of traction-motor rotor-bearing systems. Based on an analysis of the coupling among multiple excitations, a dynamic model is developed that simultaneously accounts for rotor unbalanced magnetic pull, mechanical unbalance forces, rubbing forces, gravity, the nonlinear supporting forces of a cylindrical roller bearing and the nonlinear supporting forces of deep-groove ball bearing with spalling. The model is validated against test-rig experiments. Quantitative analysis in the speed range of 1 000–5 000 rpm shows that outer-race, inner-race and rolling-element spalling generate clearly distinguishable fault characteristic bands and modulation sidebands. When rolling elements pass over a local spall, the contact force exhibits instantaneous jumps and intermittent loss, so that the RMS value of the nonlinear supporting force becomes about 2.4–3.4 times that of the corresponding healthy bearing. As the spall width increases, the RMS acceleration and supporting force grow monotonically at all speeds, with the amplification especially pronounced at 5 000 rpm. These quantitative findings provide a modeling reference and theoretical basis for fault diagnosis of rotor-bearing systems in high-speed trains.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113943"},"PeriodicalIF":8.9,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient rolling element bearing fault diagnostics in the presence of highly leptokurtic non-Gaussian noise 高细峰非高斯噪声存在下滚动轴承故障的有效诊断

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-02 DOI: 10.1016/j.ymssp.2026.113852

Mahsa Yazdanianasr , Radosław Zimroz , Agnieszka Wyłomańska , Konstantinos Gryllias

Reliable and efficient fault diagnosis of rolling element bearings is essential for condition monitoring of machinery operating in harsh environments, where signals are often contaminated by heavy-tailed, non-Gaussian impulsive noise. Bearing fault signatures exhibit both impulsiveness and cyclostationary behavior, making it challenging to prioritize one over the other when selecting the optimal frequency band for fault detection, especially amidst highly leptokurtic non-Gaussian noise. This paper addresses this question by evaluating the performance of the recently proposed Improved Envelope Spectrum via Feature Optimization-gram (IESFOgram) in the presence of heavy-tailed non-Gaussian noise. Moreover, the method is evaluated and compared against well established techniques, including the Fast Kurtogram (FK), the Infogram based on the Squared Envelope (Infogram-SE), and the Infogram based on the Squared Envelope Spectrum (Infogram-SES), highlighting the challenges of bearing diagnostics under the presence of non-Gaussian noise and the limitations of the mentioned state-of-the-art techniques. Using Monte-Carlo simulations and real-world industrial data from a copper ore crusher and a belt conveyor idler, it is clearly demonstrated that the IESFOgram outperforms the abovementioned state-of-the-art methods, detecting bearing defects earlier across different Signal-to-Noise Ratios (SNR), even in the presence of highly leptokurtic non-Gaussian noise.

滚动轴承可靠、高效的故障诊断对于在恶劣环境中运行的机械的状态监测至关重要，在恶劣环境中，信号经常被重尾、非高斯脉冲噪声污染。轴承故障特征表现出冲动性和循环平稳性，这使得在选择故障检测的最佳频段时优先考虑一个而不是另一个具有挑战性，特别是在高度细峰的非高斯噪声中。本文通过评估最近提出的基于特征优化图（IESFOgram）的改进包络谱在重尾非高斯噪声存在下的性能来解决这个问题。此外，对该方法进行了评估并与现有技术进行了比较，包括快速峰度图（FK）、基于平方包络线的信息图（Infogram- se）和基于平方包络谱的信息图（Infogram- ses），突出了在非高斯噪声存在下轴承诊断的挑战以及上述最新技术的局限性。使用蒙特卡罗模拟和来自铜矿破碎机和带式输送机托辊的真实工业数据，可以清楚地证明IESFOgram优于上述最先进的方法，即使在存在高度细峰的非高斯噪声的情况下，也可以在不同的信噪比（SNR）中更早地检测到轴承缺陷。

{"title":"Efficient rolling element bearing fault diagnostics in the presence of highly leptokurtic non-Gaussian noise","authors":"Mahsa Yazdanianasr , Radosław Zimroz , Agnieszka Wyłomańska , Konstantinos Gryllias","doi":"10.1016/j.ymssp.2026.113852","DOIUrl":"10.1016/j.ymssp.2026.113852","url":null,"abstract":"<div><div>Reliable and efficient fault diagnosis of rolling element bearings is essential for condition monitoring of machinery operating in harsh environments, where signals are often contaminated by heavy-tailed, non-Gaussian impulsive noise. Bearing fault signatures exhibit both impulsiveness and cyclostationary behavior, making it challenging to prioritize one over the other when selecting the optimal frequency band for fault detection, especially amidst highly leptokurtic non-Gaussian noise. This paper addresses this question by evaluating the performance of the recently proposed Improved Envelope Spectrum via Feature Optimization-gram (IESFOgram) in the presence of heavy-tailed non-Gaussian noise. Moreover, the method is evaluated and compared against well established techniques, including the Fast Kurtogram (FK), the Infogram based on the Squared Envelope (Infogram-SE), and the Infogram based on the Squared Envelope Spectrum (Infogram-SES), highlighting the challenges of bearing diagnostics under the presence of non-Gaussian noise and the limitations of the mentioned state-of-the-art techniques. Using Monte-Carlo simulations and real-world industrial data from a copper ore crusher and a belt conveyor idler, it is clearly demonstrated that the IESFOgram outperforms the abovementioned state-of-the-art methods, detecting bearing defects earlier across different Signal-to-Noise Ratios (SNR), even in the presence of highly leptokurtic non-Gaussian noise.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113852"},"PeriodicalIF":8.9,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synergistic flow control in airfoil guider seals for broadband rotordynamic stability 宽频旋翼动稳定性的翼型导向器密封件协同流动控制

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-02 DOI: 10.1016/j.ymssp.2026.113952

Qianlei Gu , Wanfu Zhang , Weirong Wu , Qidong Zhang , Hang Yin , Jiangang Yang

Rotordynamic instability induced by annular seals widely exists in turbomachinery. Conventional sealing technologies, including anti-swirl methods and damper seals, improve effective damping in specific frequency ranges, struggling to enhance broadband stability. To overcome this limitation, we introduce airfoil guider seals (AGS) that passively control the intra-cavity flow. By circumferentially embedding airfoil vanes, the AGS generates pressure-difference-driven circumferential flow reversal, altering the energy transfer dynamics between the fluid and the whirling rotor. To reveal its rotordynamic stabilization mechanism, a transient CFD method based on the accelerating sweep frequency excitation model is adopted with experimental validation. Results demonstrate that the airfoil-induced circumferential flow reversal shifts the cross-coupled stiffness to negative values, while the independent sub-cavities enhance direct damping. This dual mechanism ensures positive effective damping C_eff over the entire frequency band. Parametric studies reveal that this stability is further amplified by increasing the vane inclination angle and number, which intensify flow reversal and cavity partitioning. The AGS also demonstrates exceptional operational robustness, showing minimal sensitivity (C_eff variation < 10%) to rotational speed (3000–15000 rpm) and inlet preswirl (0–50 m/s), alongside enhanced stability at higher inlet pressures. In a direct performance comparison, the AGS provides an order-of-magnitude higher C_eff than the labyrinth seal with swirl brakes across the entire frequency band. Notably, it eliminates the low-frequency instability inherent to pocket damper seals while achieving 6–11 times higher C_eff within their optimal frequency range. These findings position AGS as a prominent solution for suppressing rotordynamic instability in turbomachinery.

由环形密封引起的转子动力失稳在涡轮机械中广泛存在。传统的密封技术，包括防旋方法和阻尼器密封，在特定频率范围内提高了有效的阻尼，难以提高宽带的稳定性。为了克服这一限制，我们引入了被动控制腔内流动的翼型导流密封（AGS）。通过周向嵌入翼型叶片，AGS产生压力差驱动的周向流动反转，改变流体与旋转转子之间的能量传递动力学。为了揭示其转子动态稳定机理，采用了一种基于加速扫频激励模型的瞬态CFD方法，并进行了实验验证。结果表明，翼型诱导的周向流动反转使交叉耦合刚度变为负值，而独立的子腔增强了直接阻尼。这种双重机制确保了整个频带内的正有效阻尼Ceff。参数研究表明，增加叶片倾角和数量会进一步增强这种稳定性，从而加剧流动逆转和空腔分配。AGS还表现出了出色的运行稳健性，对转速（3000-15000 rpm）和进气道预旋（0-50 m/s）的敏感性极小（Ceff变化<； 10%），同时在较高的进气道压力下也增强了稳定性。在直接的性能比较中，AGS在整个频段内提供的Ceff比带涡流制动器的迷宫密封高一个数量级。值得注意的是，它消除了袋式阻尼器密封固有的低频不稳定性，同时在最佳频率范围内实现6-11倍的高Ceff。这些发现表明AGS是抑制涡轮机械转子动力学不稳定性的重要解决方案。

{"title":"Synergistic flow control in airfoil guider seals for broadband rotordynamic stability","authors":"Qianlei Gu , Wanfu Zhang , Weirong Wu , Qidong Zhang , Hang Yin , Jiangang Yang","doi":"10.1016/j.ymssp.2026.113952","DOIUrl":"10.1016/j.ymssp.2026.113952","url":null,"abstract":"<div><div>Rotordynamic instability induced by annular seals widely exists in turbomachinery. Conventional sealing technologies, including anti-swirl methods and damper seals, improve effective damping in specific frequency ranges, struggling to enhance broadband stability. To overcome this limitation, we introduce airfoil guider seals (AGS) that passively control the intra-cavity flow. By circumferentially embedding airfoil vanes, the AGS generates pressure-difference-driven circumferential flow reversal, altering the energy transfer dynamics between the fluid and the whirling rotor. To reveal its rotordynamic stabilization mechanism, a transient CFD method based on the accelerating sweep frequency excitation model is adopted with experimental validation. Results demonstrate that the airfoil-induced circumferential flow reversal shifts the cross-coupled stiffness to negative values, while the independent sub-cavities enhance direct damping. This dual mechanism ensures positive effective damping C<sub>eff</sub> over the entire frequency band. Parametric studies reveal that this stability is further amplified by increasing the vane inclination angle and number, which intensify flow reversal and cavity partitioning. The AGS also demonstrates exceptional operational robustness, showing minimal sensitivity (C<sub>eff</sub> variation < 10%) to rotational speed (3000–15000 rpm) and inlet preswirl (0–50 m/s), alongside enhanced stability at higher inlet pressures. In a direct performance comparison, the AGS provides an order-of-magnitude higher C<sub>eff</sub> than the labyrinth seal with swirl brakes across the entire frequency band. Notably, it eliminates the low-frequency instability inherent to pocket damper seals while achieving 6–11 times higher C<sub>eff</sub> within their optimal frequency range. These findings position AGS as a prominent solution for suppressing rotordynamic instability in turbomachinery.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113952"},"PeriodicalIF":8.9,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Target-free measurement of cable forces based on video motion magnification and high-order mode shapes 基于视频运动放大和高阶模态振型的无目标索力测量

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-02-02 DOI: 10.1016/j.ymssp.2026.113966

Kui Luo , Xuan Kong , Shitang Ke , Jiexuan Hu , Lu Deng

Cables are crucial components of cable-supported bridges, and cable force measurement is essential for assessing bridge safety. While the frequency method is widely used to estimate cable forces, it faces challenges in determining boundary conditions and bending stiffness, especially for short cables. Therefore, this study proposes a cable force measurement method based on computer vision (CV) and high-order mode shapes. The broad-band phase-based video motion magnification (BPVMM) technique is first used to magnify small vibrations of the cable, and then the line tracking algorithm is employed to identify cable displacement from the magnified video to obtain high-order mode shapes. Additionally, a theoretical formula for calculating the cable force based on the high-order mode shapes is proposed. The proposed method is verified through laboratory cable tests and field tests of cable-stayed bridges. The results indicate that the cable forces calculated using the proposed method align closely with the measured values, with the maximum error within 3%. This method effectively eliminates the effects of boundary conditions and bending stiffness, significantly improves the accuracy of cable force identification. This study provides technical support for cable force identification when boundary conditions and bending stiffness are unknown.

索是索桥的重要组成部分，索力测量是评估桥梁安全性的重要手段。虽然频率法被广泛应用于索力估算，但它在确定边界条件和弯曲刚度方面面临挑战，特别是对于短索。因此，本研究提出了一种基于计算机视觉（CV）和高阶振型的索力测量方法。首先利用宽带基于相位的视频运动放大技术（BPVMM）放大电缆的微小振动，然后利用线路跟踪算法从放大后的视频中识别电缆位移，获得高阶模态振型。此外，还提出了基于高阶振型计算索力的理论公式。通过斜拉桥室内试验和现场试验验证了该方法的有效性。结果表明，该方法计算的索力与实测值吻合较好，最大误差在3%以内。该方法有效地消除了边界条件和弯曲刚度的影响，显著提高了索力识别的精度。该研究为边界条件和弯曲刚度未知情况下的索力识别提供了技术支持。

{"title":"Target-free measurement of cable forces based on video motion magnification and high-order mode shapes","authors":"Kui Luo , Xuan Kong , Shitang Ke , Jiexuan Hu , Lu Deng","doi":"10.1016/j.ymssp.2026.113966","DOIUrl":"10.1016/j.ymssp.2026.113966","url":null,"abstract":"<div><div>Cables are crucial components of cable-supported bridges, and cable force measurement is essential for assessing bridge safety. While the frequency method is widely used to estimate cable forces, it faces challenges in determining boundary conditions and bending stiffness, especially for short cables. Therefore, this study proposes a cable force measurement method based on computer vision (CV) and high-order mode shapes. The broad-band phase-based video motion magnification (BPVMM) technique is first used to magnify small vibrations of the cable, and then the line tracking algorithm is employed to identify cable displacement from the magnified video to obtain high-order mode shapes. Additionally, a theoretical formula for calculating the cable force based on the high-order mode shapes is proposed. The proposed method is verified through laboratory cable tests and field tests of cable-stayed bridges. The results indicate that the cable forces calculated using the proposed method align closely with the measured values, with the maximum error within 3%. This method effectively eliminates the effects of boundary conditions and bending stiffness, significantly improves the accuracy of cable force identification. This study provides technical support for cable force identification when boundary conditions and bending stiffness are unknown.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113966"},"PeriodicalIF":8.9,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic characteristics of composite beam-plate coupled structures under hygrothermal conditions for hydrogen-electric aircraft: analytical and experimental investigation 氢能飞机复合梁-板耦合结构在湿热条件下的动力特性：分析与实验研究

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-01-31 DOI: 10.1016/j.ymssp.2026.113929

Ye-Wei Zhang , Ji Zhang , Jian Zang , Li-Qun Chen

Hygrothermal exposure significantly alters the dynamic characteristics of composite beam-plate frames supporting cryogenic hydrogen tanks. Accurate characterization of hygrothermal effects on structural dynamics is essential for ensuring safety and achieving lightweight designs of hydrogen-electric aircraft. This paper presents an analytical framework based on improved orthogonal polynomials within a Rayleigh-Ritz formulation to characterize the dynamic behavior of composite beam-plate coupled systems (CBPCSs) under the hygrothermal environment and elastic boundary constraints. By integrating Kirchhoff thin-plate theory with the Euler-Bernoulli beam assumption, the method yields closed-form expressions for the potential, kinetic, elastic, and hygrothermal potentials of the CBPCSs. Interfacial flexibility at laminate-beam-plate junctions is modeled via an equivalent spring system to capture elastic restraint effects. Validation against laboratory modal tests and high-fidelity finite-element simulations demonstrates excellent convergence and computational accuracy. Parametric analyses reveal how boundary stiffness, coupling interfaces, and hygrothermal conditions influence natural frequencies and mode shapes with nonlinear trends. This work presents a reliable theoretical approach for the vibration optimization and structural design of composite support frames in hydrogen-electric aircraft, with experimental and numerical validation confirming its applicability to practical engineering scenarios.

湿热暴露显著改变了支撑低温氢气罐的复合梁-板框架的动态特性。准确表征湿热效应对结构动力学的影响，对于保证氢动力飞机的安全性和实现轻量化设计至关重要。本文提出了一种基于Rayleigh-Ritz公式中的改进正交多项式的分析框架，用于表征复合梁-板耦合系统在湿热环境和弹性边界约束下的动力特性。通过将Kirchhoff薄板理论与欧拉-伯努利梁假设相结合，该方法得到了CBPCSs的势、动、弹性和湿热势的封闭表达式。层压板-梁-板连接处的界面柔性通过等效弹簧系统建模，以捕获弹性约束效应。通过实验室模态试验和高保真有限元模拟验证了该方法具有良好的收敛性和计算精度。参数分析揭示了边界刚度、耦合界面和湿热条件如何影响具有非线性趋势的固有频率和模态振型。本文为氢动力飞机复合材料支撑架的振动优化和结构设计提供了可靠的理论方法，并通过实验和数值验证了其在实际工程场景中的适用性。

{"title":"Dynamic characteristics of composite beam-plate coupled structures under hygrothermal conditions for hydrogen-electric aircraft: analytical and experimental investigation","authors":"Ye-Wei Zhang , Ji Zhang , Jian Zang , Li-Qun Chen","doi":"10.1016/j.ymssp.2026.113929","DOIUrl":"10.1016/j.ymssp.2026.113929","url":null,"abstract":"<div><div>Hygrothermal exposure significantly alters the dynamic characteristics of composite beam-plate frames supporting cryogenic hydrogen tanks. Accurate characterization of hygrothermal effects on structural dynamics is essential for ensuring safety and achieving lightweight designs of hydrogen-electric aircraft. This paper presents an analytical framework based on improved orthogonal polynomials within a Rayleigh-Ritz formulation to characterize the dynamic behavior of composite beam-plate coupled systems (CBPCSs) under the hygrothermal environment and elastic boundary constraints. By integrating Kirchhoff thin-plate theory with the Euler-Bernoulli beam assumption, the method yields closed-form expressions for the potential, kinetic, elastic, and hygrothermal potentials of the CBPCSs. Interfacial flexibility at laminate-beam-plate junctions is modeled via an equivalent spring system to capture elastic restraint effects. Validation against laboratory modal tests and high-fidelity finite-element simulations demonstrates excellent convergence and computational accuracy. Parametric analyses reveal how boundary stiffness, coupling interfaces, and hygrothermal conditions influence natural frequencies and mode shapes with nonlinear trends. This work presents a reliable theoretical approach for the vibration optimization and structural design of composite support frames in hydrogen-electric aircraft, with experimental and numerical validation confirming its applicability to practical engineering scenarios.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113929"},"PeriodicalIF":8.9,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146095826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient simulation of conditional random fields by Karhunen–Loève expansion karhunen - lo<e:1>展开对条件随机场的有效模拟

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-01-31 DOI: 10.1016/j.ymssp.2026.113938

Zhao Zhao , Teng-Fei Xu , Zhao-Hui Lu , Yan-Gang Zhao

The conditional random fields, by integrating on-site measured data information, provide a more practical and realistic tool for the engineering analysis of phenomena that exhibit random characteristics in both space and time across multiple dimensions. However, traditional simulation methods of conditional random fields still face significant computational bottlenecks when dealing with large-scale problems. To this end, this paper proposes a novel and efficient simulation technique for conditional random fields. The core of the proposed method lies in a refined approach to the Karhunen-Loève (K-L) expansion. Instead of approximating the full conditional covariance function, we directly compute or more accurately approximate the dominant eigenvalues and eigenfunctions of the theoretically exact conditional covariance function. This computation is achieved by using the Nyström approximation, conditional multivariate Gaussian distribution, and selected quadrature points. This streamlined process allows us to directly generate conditional random field realizations within the K-L expansion framework. The effectiveness and robustness of the proposed method are demonstrated through three numerical examples, including one-dimensional, two-dimensional, and large-scale three-dimensional conditional random field simulations. Results confirm that the proposed approach achieves an optimal balance between computational efficiency and simulation accuracy, providing a powerful tool for data-inform probabilistic engineering analysis.

条件随机场通过整合现场实测数据信息，为跨多维空间和时间随机性现象的工程分析提供了更为实用和现实的工具。然而，传统的条件随机场模拟方法在处理大规模问题时仍然面临着显著的计算瓶颈。为此，本文提出了一种新的、高效的条件随机场仿真技术。该方法的核心是对karhunen - lo (K-L)展开的一种改进方法。我们不是逼近完整的条件协方差函数，而是直接计算或更精确地逼近理论上精确的条件协方差函数的主导特征值和特征函数。这个计算是通过使用Nyström近似，条件多元高斯分布和选择的正交点来实现的。这个简化的过程允许我们在K-L扩展框架内直接生成条件随机场实现。通过一维、二维和大尺度三维条件随机场模拟，验证了该方法的有效性和鲁棒性。结果表明，该方法在计算效率和仿真精度之间达到了最佳平衡，为数据信息概率工程分析提供了有力的工具。

{"title":"Efficient simulation of conditional random fields by Karhunen–Loève expansion","authors":"Zhao Zhao , Teng-Fei Xu , Zhao-Hui Lu , Yan-Gang Zhao","doi":"10.1016/j.ymssp.2026.113938","DOIUrl":"10.1016/j.ymssp.2026.113938","url":null,"abstract":"<div><div>The conditional random fields, by integrating on-site measured data information, provide a more practical and realistic tool for the engineering analysis of phenomena that exhibit random characteristics in both space and time across multiple dimensions. However, traditional simulation methods of conditional random fields still face significant computational bottlenecks when dealing with large-scale problems. To this end, this paper proposes a novel and efficient simulation technique for conditional random fields. The core of the proposed method lies in a refined approach to the Karhunen-Loève (K-L) expansion. Instead of approximating the full conditional covariance function, we directly compute or more accurately approximate the dominant eigenvalues and eigenfunctions of the theoretically exact conditional covariance function. This computation is achieved by using the Nyström approximation, conditional multivariate Gaussian distribution, and selected quadrature points. This streamlined process allows us to directly generate conditional random field realizations within the K-L expansion framework. The effectiveness and robustness of the proposed method are demonstrated through three numerical examples, including one-dimensional, two-dimensional, and large-scale three-dimensional conditional random field simulations. Results confirm that the proposed approach achieves an optimal balance between computational efficiency and simulation accuracy, providing a powerful tool for data-inform probabilistic engineering analysis.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113938"},"PeriodicalIF":8.9,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel frequency-domain health indicator for bearing RUL estimation using adaptive Wiener process degradation modeling 基于自适应维纳过程退化模型的轴承RUL估计频域健康指标

IF 8.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Mechanical Systems and Signal Processing

Pub Date : 2026-01-31 DOI: 10.1016/j.ymssp.2026.113955

Afshin Nagheli, Mehrdad Poursina, Hossein Karimpour

Accurate and reliable estimation of bearing health conditions requires the construction of a suitable Health Indicator (HI). In this study, the Modified Total Harmonic Distribution (MTHD) health indicator is developed based on advanced frequency domain analysis to describe the bearing health status effectively. It has also been validated that MTHD demonstrated desirable properties of monotonicity, robustness, and trendability. To accurately identify the First Prediction Time (FPT), a linear combination of the mean and variance of the MTHD curve is employed. However, due to variations in operating conditions and loading, the degradation process of bearings may differ. As a result, a single fixed model cannot accurately characterize the occurrence of different degradation processes. To address this issue, an adaptive Wiener model is proposed. In this framework, the Remaining Useful Life (RUL) prediction is achieved using either an appropriate linear or nonlinear Wiener model selected through a model adaptive algorithm. Finally, the effectiveness of the proposed model is validated using the XJTU-SY bearing dataset as well as the laboratory’s own generated dataset.

准确可靠地估计轴承健康状况需要构建合适的健康指标（HI）。为了有效地描述轴承的健康状态，提出了基于先进频域分析的修正总谐波分布（MTHD）健康指标。结果表明，MTHD具有单调性、鲁棒性和趋势性。为了准确地识别第一次预测时间（FPT），采用了MTHD曲线均值和方差的线性组合。然而，由于操作条件和载荷的变化，轴承的退化过程可能不同。因此，单一的固定模型不能准确表征不同退化过程的发生。为了解决这一问题，提出了一种自适应维纳模型。在该框架中，剩余使用寿命（RUL）预测是通过模型自适应算法选择适当的线性或非线性维纳模型来实现的。最后，使用XJTU-SY轴承数据集以及实验室自己生成的数据集验证了所提出模型的有效性。

{"title":"A novel frequency-domain health indicator for bearing RUL estimation using adaptive Wiener process degradation modeling","authors":"Afshin Nagheli, Mehrdad Poursina, Hossein Karimpour","doi":"10.1016/j.ymssp.2026.113955","DOIUrl":"10.1016/j.ymssp.2026.113955","url":null,"abstract":"<div><div>Accurate and reliable estimation of bearing health conditions requires the construction of a suitable Health Indicator (HI). In this study, the Modified Total Harmonic Distribution (MTHD) health indicator is developed based on advanced frequency domain analysis to describe the bearing health status effectively. It has also been validated that MTHD demonstrated desirable properties of monotonicity, robustness, and trendability. To accurately identify the First Prediction Time (FPT), a linear combination of the mean and variance of the MTHD curve is employed. However, due to variations in operating conditions and loading, the degradation process of bearings may differ. As a result, a single fixed model cannot accurately characterize the occurrence of different degradation processes. To address this issue, an adaptive Wiener model is proposed. In this framework, the Remaining Useful Life (RUL) prediction is achieved using either an appropriate linear or nonlinear Wiener model selected through a model adaptive algorithm. Finally, the effectiveness of the proposed model is validated using the XJTU-SY bearing dataset as well as the laboratory’s own generated dataset.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"247 ","pages":"Article 113955"},"PeriodicalIF":8.9,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146095827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0