Mechanical Systems and Signal Processing最新文献

{"title":"An adaptive monitoring method for SMA wires by integrating dual resistance signals and machine learning","authors":"Qiang Zou ,&nbsp;Yong-Chen Pei ,&nbsp;Bin-Cheng Yang ,&nbsp;Wang-Wang Yuan ,&nbsp;Huiqi Lu","doi":"10.1016/j.ymssp.2025.112954","DOIUrl":"10.1016/j.ymssp.2025.112954","url":null,"abstract":"<div><div>The state monitoring of shape memory alloy (SMA) wires is crucial for enhancing their intelligent actuation and sensing capabilities. However, existing methods face challenges such as temperature measurement difficulties, limited accuracy, and poor environmental adaptability. The dual-resistance monitoring approach, which integrates the electrical resistance signals of the SMA wire and the auxiliary temperature-sensing wire through a constitutive model, addresses these issues but remains constrained by strong parameter dependency, complex modeling, and limited predictive accuracy. This study proposes an innovative machine learning-based dual-resistance monitoring method, directly predicting the state of the SMA wire using neural networks without traditional equation-based modeling. Four neural network architectures are designed and compared to address key challenges, including long-term dependency modeling, bidirectional information capture, local feature extraction, and global attention allocation. Experimental results demonstrate that the proposed convolutional neural networks &amp; bidirectional long short-term memory networks &amp; self-attention mechanisms (CBLS) model achieves the best performance, with an average stress prediction error of 1.13% and an average strain prediction error of 0.46%. Moreover, it exhibits excellent robustness and adaptability under low strain rates and complex environmental conditions. This method provides a novel intelligent solution for high-precision, adaptive SMA wire monitoring, potentially accelerating its engineering applications and expanding its use in smart structures and advanced manufacturing.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112954"},"PeriodicalIF":7.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222154","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}

{"title":"Design and validation of a low-cost vehicle driver monitoring device","authors":"María Garrosa ,&nbsp;Marco Ceccarelli ,&nbsp;Susana Sanz Sánchez ,&nbsp;Matteo Russo","doi":"10.1016/j.ymssp.2025.112939","DOIUrl":"10.1016/j.ymssp.2025.112939","url":null,"abstract":"<div><div>This paper presents the design and experimental validation of a novel low-cost, wearable device for continuous monitoring of the motion and physiological state of vehicle drivers. The system strategically integrates Inertial Measurement Units (IMUs) on the driver’s head, neck, and torso to accurately capture body dynamics while driving. It also incorporates physiological sensors to capture electrocardiography (ECG) and body temperature signals, providing objective indicators of the driver’s physical and emotional state. The device’s architecture enables real-time data processing, which is essential for early detection of risky behaviors such as distracted or aggressive driving. Validation of the device was conducted through an experimental protocol in a controlled urban driving environment, evaluating common maneuvers such as straight-line driving, braking, roundabouts, and lane changes. The results obtained demonstrate the feasibility of the device to characterize significant changes in posture and physiological parameters, demonstrating its potential application as a low-cost tool for driver monitoring in Advanced Driver Assistance Systems (ADAS), accident prevention campaigns, and epidemiological studies of driving behavior.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112939"},"PeriodicalIF":7.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222140","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}

{"title":"Comparative analysis of data-driven autoencoder networks for full-field expansion from sparse measurements","authors":"Nitin Nagesh Kulkarni,&nbsp;J.Hunter Mack,&nbsp;Alessandro Sabato","doi":"10.1016/j.ymssp.2025.112957","DOIUrl":"10.1016/j.ymssp.2025.112957","url":null,"abstract":"<div><div>Condition monitoring relies on data collected from a system with sensors to extract information about its state. The difficulty in deploying highly dense distributions of sensors hinders the detection of local damage in the system. To address this issue, domain-specific techniques have been developed that can expand measurements from a discrete subset of data (i.e., sparse measurements) to full-field. However, these domain-specific expansion techniques have shown limitations when used with non-linear dynamic systems. Recent advancements in machine learning algorithms, particularly autoencoder (AE) networks, can improve the robustness of expansion techniques to non-linear systems as well as generalize their applicability to other domains. In this research, three AE architectures, based on feed-forward networks, convolutional neural networks, and long short-term memory (LSTM) networks, are proposed to reconstruct the full-field response of a targeted dynamic system when only sparse measurements are available. The performance of the three architectures is compared as a function of i) the location of measurement points, <strong>ii)</strong> the spatial density of the measurement points, and <strong>iii)</strong> the noise present in the signal collected at each measurement point. Tests performed on analytical and experimental datasets indicate that all three architectures successfully expanded to full-field data from sparse measurements, with LSTM exhibiting errors below 0.85% in the expansion process. Advancements of this research could lead to the application of AE-based expansion techniques for condition monitoring of dynamic systems when only a limited number of measurements are available.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112957"},"PeriodicalIF":7.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222156","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}

{"title":"Task similarity-based continual learning for multi-phase environments and its application in few-shot fault diagnosis","authors":"Hewei Gao ,&nbsp;Xin Huo ,&nbsp;Chao Zhu ,&nbsp;Changchun He ,&nbsp;Jiao Meng","doi":"10.1016/j.ymssp.2025.112862","DOIUrl":"10.1016/j.ymssp.2025.112862","url":null,"abstract":"<div><div>During the operation of industrial machinery, few-shot faults that are difficult to diagnose due to data scarcity and task heterogeneity are frequently encountered. Traditional deep learning methods struggle with these challenges, as they require large labeled datasets and lack adaptability to evolving fault patterns. Continual learning provides a promising solution by enabling models to learn sequentially while mitigating catastrophic forgetting. A task similarity-based continual learning (TSCL) fault diagnosis framework that incorporates feature replay and loss allocation strategies is proposed, enhancing knowledge retention and transfer across tasks in multi-phase environments. The feature replay mechanism identifies key samples from the previous phase based on feature similarity and replays them, projecting all samples into the feature space of the same probability distribution. Additionally, a loss allocation mechanism based on parameter importance is proposed that evaluates the significance of each parameter in previous phases and assigns appropriate update magnitudes, thereby enhancing the ability to retain previous task knowledge of the model. Experimental validations on four public datasets demonstrate that, in few-shot learning and multi-stage scenarios, the proposed method outperforms mainstream comparative approaches. In particular, on the excavator dataset from an industrial application, TSCL exhibits excellent stability and high accuracy in multi-phase learning, with a marked improvement in memory retention for previous tasks.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112862"},"PeriodicalIF":7.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213420","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}

{"title":"Vibration analysis of beams coupled with evenly spaced acoustic black hole pillars: Experimental and numerical insights","authors":"Daniel Martins ,&nbsp;Mahmoud Karimi ,&nbsp;Laurent Maxit","doi":"10.1016/j.ymssp.2025.112855","DOIUrl":"10.1016/j.ymssp.2025.112855","url":null,"abstract":"<div><div>Stiffened structures are commonly used in engineering applications such as aerospace, marine, automotive and civil engineering. Vibration control of these structures is a critical area of research that aims to enhance their reliability and durability by effectively mitigating vibrations. This work aims to demonstrate the potential of integrating acoustic black holes (ABHs) into stiffened structures by altering only the shape of the stiffeners without adding mass to the host structure or compromising structural integrity. Towards this aim, experimental and numerical analyses are conducted on finite beams coupled with ABH or rectangular pillars. The ABH design has the same mass and moment of inertia at the contact point as the rectangular pillars to establish a comparison. Three configurations are tested for both cases: without damping layers, with viscoelastic damping layers, and constrained viscoelastic damping layers. Experimental results revealed that the beam with ABH pillars, particularly when paired with constrained viscoelastic damping layers, exhibited higher vibration mitigation (up to 33 dB) compared to the vibrational response of a beam with the rectangular pillar with the same constrained viscoelastic damping layers. Numerical simulations using finite element models supported the experimental findings, and provided insight into the vibration mitigation mechanism by examining the mode shapes of the two considered beams. The combined experimental and numeral results highlight the potential of ABH stiffeners as an innovative solution for vibration control in stiffened structures.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112855"},"PeriodicalIF":7.9,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144204161","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}

{"title":"Dynamic behavior and kinematic joint wear characteristics study of rigid-flexible hybrid mechanism considering spatial revolute joint clearance","authors":"Yuechuan Xin ,&nbsp;Mingyang Cai ,&nbsp;Siyuan Zheng ,&nbsp;Yilin Wang ,&nbsp;Jianuo Zhu ,&nbsp;Shuai Jiang ,&nbsp;Hongchang Ding ,&nbsp;Guangwei Liu","doi":"10.1016/j.ymssp.2025.112853","DOIUrl":"10.1016/j.ymssp.2025.112853","url":null,"abstract":"<div><div>As industrial production increasingly demands higher precision, performance and stability requirements for advanced mechanisms have intensified exponentially, making the investigation of their dynamic behaviors critically important. Among the predominant factors compromising the precision and robustness of mechanism actuators, elastic deformation of structural components and kinematic joint clearances have been identified as significant contributors. While current research on clearance-induced dynamic behaviors predominantly focuses on planar multi-link mechanisms or simple spatial parallel mechanisms. Studies addressing hybrid mechanism containing three-dimensional(3D) revolute joint clearances remain remarkably limited, and even fewer studies consider the flexible effects of components alongside the wear characteristics of kinematic joints clearance in such hybrid systems. To address these research gaps, this paper investigates the dynamic response, reliability and wear characteristics of kinematic joints in a 3-<u>P</u>RPaR-RUPUR spatial redundant rigid-flexible hybrid mechanism. Firstly, a 3D revolute joint clearance model is established. Next, a 3D two-node spatial beam element model is developed using the absolute nodal coordinate form(ANCF). Subsequently, a wear model for revolute joint clearances is given based on the Archard model. Finally, a dynamic model of the rigid-flexible hybrid mechanism, considering spatial revolute joint clearances, is formulated utilizing the Lagrange multiplier method. This investigation systematically quantifies the effects of component flexibility, clearance size, and multi-clearance configurations on the dynamic response, reliability of the moving platform and wear characteristics of clearance joints in the rigid-flexible hybrid mechanism. The findings aim to establish a systematic theoretical foundation for the study of high-precision, high-performance mechanism dynamics, reliability and the wear characteristics of kinematic joints with clearances.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112853"},"PeriodicalIF":7.9,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213418","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}

{"title":"Nonlinear ultrasonic Rayleigh wave detection of wear characteristics in TC4 titanium alloy: Correlation with residual stress","authors":"Xiangyan Ding ,&nbsp;Qinghui Zhang ,&nbsp;Bo Yang ,&nbsp;Jishuo Wang ,&nbsp;Chunmei Xu ,&nbsp;Xiaoyang Bi ,&nbsp;Zhengpan Qi ,&nbsp;Mingxi Deng ,&nbsp;Ning Hu","doi":"10.1016/j.ymssp.2025.112936","DOIUrl":"10.1016/j.ymssp.2025.112936","url":null,"abstract":"<div><div>TC4 titanium alloy, widely utilized in mechanical systems due to its exceptional performance characteristics, faces inevitable challenges from frictional wear that results in volume loss and residual stresses, ultimately compromising system performance and reliability. This investigation systematically detects the dry friction wear behavior of TC4 titanium alloy under different conditions of normal load (0–100 N), wear cycles (0–6000 cycle), and displacement amplitudes (0–4 mm) by nonlinear ultrasonic Rayleigh wave technology in combination with white light interferometric detection and X-ray diffraction detection. Results demonstrate that surface morphology characteristics, wear volume, wear depth, and residual stress exhibit proportional increases with normal load, wear cycles, and displacement amplitude by white light interferometric detection and X-ray diffraction detection. These parameters correlate with enhanced nonlinear Rayleigh effects, manifesting in second/third harmonic (4 MHz/6 MHz) and zero frequency components with fundamental wave of 2 MHz. The ultrasonic nonlinear coefficients of the second and third harmonics increase monotonically with the increase of the wear parameter. And second/third harmonic components demonstrate superior sensitivity compared to zero frequency measurements. Significantly, the nonlinear coefficient is predominantly influenced by residual stress rather than wear depth or volume. Numerical simulations of nonlinear ultrasonics with indentation depth parameters (0/40/55/65/80 μm) and the 2–5 times material nonlinearity as the different wear residual stress state corroborate these experimental findings. The study establishes that ultrasonic nonlinear coefficients serve as effective indicators of residual stress during wear processes, thereby enabling quantitative wear severity assessment and facilitating in-situ nondestructive evaluation through nonlinear ultrasonic techniques.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112936"},"PeriodicalIF":7.9,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213421","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}

{"title":"Adaptive weighted data fusion-driven multi-layer discriminative dictionary learning method for intelligent fault diagnosis of rotating machinery","authors":"Zhichao Jiang ,&nbsp;Dongdong Liu ,&nbsp;Lingli Cui","doi":"10.1016/j.ymssp.2025.112888","DOIUrl":"10.1016/j.ymssp.2025.112888","url":null,"abstract":"<div><div>Dictionary learning is an effective intelligent diagnosis model to achieve fault classification of rotating machinery. However, existing dictionary learning methods mostly employ a single-layer architecture for dictionary learning, which hinders the learning of deeper discriminative features. Besides, due to limited feature information and noise interference, dictionary learning models learned from single-domain data cannot guarantee that the vibration signals achieve a satisfactory sparse representation. In this paper, an adaptive weighted data fusion-driven multi-layer discriminative dictionary learning method (AWDF-MLDDL) is proposed for intelligent fault diagnosis of rotating machinery. First, a multi-layer discriminative dictionary learning framework is proposed to learn discriminative dictionaries with a deep architecture, in which a structured incoherence term is employed to improve the independence of sub-dictionaries associated with different categories, while still enabling feature sharing between categories. Second, an adaptive weighted fusion method applied to dictionary learning is proposed to improve the representation capability of the category-associated discriminative sub-dictionaries. Finally, a sparse recognition method with an adjustable decision fusion strategy is designed to realize jointly intelligent fault diagnosis. Two datasets are used to quantitatively verify the superiority and effectiveness of the developed AWDF-MLDDL under small-sample and noise scenarios, indicating that the AWDF-MLDDL has superiority for intelligent fault diagnosis of rotating machinery.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112888"},"PeriodicalIF":7.9,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213419","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}

{"title":"Transfer learning and Bayesian calibration addressing data scarcity and uncertainty for structural health monitoring of twin concrete bridges","authors":"Leonardo Ferreira ,&nbsp;Marcus Omori Yano ,&nbsp;Laura Souza ,&nbsp;Ionut Moldovan ,&nbsp;Samuel da Silva ,&nbsp;Rômulo Lopes ,&nbsp;Carlos Alberto Cimini Jr. ,&nbsp;João C.W.A. Costa ,&nbsp;Eloi Figueiredo","doi":"10.1016/j.ymssp.2025.112845","DOIUrl":"10.1016/j.ymssp.2025.112845","url":null,"abstract":"<div><div>This paper applies transfer learning in the context of structural health monitoring (SHM) to two almost identical bridges located side-by-side, whose construction dates are separated by almost three decades. The uniqueness of this study is enhanced by the fact that the newer bridge has been reported as damaged for almost one decade, with no monitoring data available from its undamaged condition. To overcome data scarcity and uncertainty in the training of machine learning algorithms, this paper proposes a multidisciplinary framework to reuse monitoring data in the undamaged condition from the older bridge to address damage detection in the new one. A numerical model solved by the finite element method is developed to simulate the undamaged condition of the new bridge. The model is calibrated to account for sources of epistemic uncertainty using Bayesian inference through Markov-Chain Monte Carlo simulations with the Metropolis–Hastings algorithm. During the Bayesian updating process, a global sensitivity analysis using Sobol indices is proposed to identify the main parameters influencing the model’s outputs. The results show that the numerical model is capable of simulating the dynamics of the new bridge in its undamaged condition, and transfer learning through domain adaptation is capable of adapting the data from the old bridge so that it can be reused to train a machine learning algorithm to classify observations from the new bridge, taking into account random uncertainty. This framework provides substantial benefits in addressing data scarcity and uncertainty, model updating, and machine learning challenges in the context of SHM but also reveals some limitations of unsupervised transfer learning.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112845"},"PeriodicalIF":7.9,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144204160","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}

{"title":"New methodology for adaptive sliding mode control with self-tuning threshold based on chattering detection","authors":"Jonathan Rodriguez ,&nbsp;Vincent Lechappe ,&nbsp;Simon Chesne","doi":"10.1016/j.ymssp.2025.112854","DOIUrl":"10.1016/j.ymssp.2025.112854","url":null,"abstract":"<div><div>Control of systems and structures with uncertainties is one of the major challenges in modern control. To guarantee finite-time convergence, robust control methods such as sliding mode control (SMC) have been widely investigated during the last 20 years. Since the chattering phenomenon is considered the main drawback of SMC, adaptive SMC methods have also been developed to avoid overestimation of the control gains. Nevertheless, the majority of the adaptive sliding mode control (ASMC) methods demand arbitrary tuning of the real sliding mode boundaries, which in practice depend on the structure’s uncertainty and also the unknown exogenous perturbation, both with the possibility of evolving with time. The following paper proposes a new method for ASMC with real-time boundary adaptation of the adaptive gain based on chattering detection. The method is explored numerically and experimentally within the context of active vibration control using a hybrid mass damper.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"235 ","pages":"Article 112854"},"PeriodicalIF":7.9,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195497","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}