Mechanical Systems and Signal Processing最新文献

筛选
英文 中文
Predictive control of single pendulum cranes under actuated/underactuated state constraints: A higher-order fully actuated approach 驱动/欠驱动状态下单摆起重机的预测控制:一种高阶全驱动方法
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-27 DOI: 10.1016/j.ymssp.2025.113411
Heng Zhang , Weili Ding , Changchun Hua , Biao Lu
{"title":"Predictive control of single pendulum cranes under actuated/underactuated state constraints: A higher-order fully actuated approach","authors":"Heng Zhang ,&nbsp;Weili Ding ,&nbsp;Changchun Hua ,&nbsp;Biao Lu","doi":"10.1016/j.ymssp.2025.113411","DOIUrl":"10.1016/j.ymssp.2025.113411","url":null,"abstract":"<div><div>The single pendulum crane (SPC), as a typical nonlinear underactuated system, presents challenges in directly implementing control and imposing constraints on underactuated states. To address these challenges, this paper proposes a predictive control method for the SPC system based on a high-order fully actuated (HOFA) system framework. Specifically, the underactuated SPC is converted into a HOFA system, and a disturbance observer is designed to estimate the uncertainty term. Then, a model predictive controller is designed to convert the control problem into a quadratic programming(QP) problem, which realizes the control of the SPC and the constraints on the actuated/underactuated states. Finally, we propose an online physics-informed preset-time solver that guarantees bounded-time convergence for the QP problem. In experiments, two types of SPC systems are considered, with payloads connected by a sling and by a rigid rod, respectively. This demonstrates the universality of the method proposed in this paper. Results show that the payload maximum swing angles of the two systems are reduced by 78.81% and 64.29% compared with PD-like control, 75.96% and 59.75% compared with partially linearized HOFA control, and 13.48% and 27.48% compared with linearized model predictive control, respectively. Moreover, the constraints on the actuated/underactuated states are achieved. Finally, cases involving system parameter uncertainties and external disturbances are also considered, and the proposed method still exhibits good control performance.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113411"},"PeriodicalIF":8.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145182907","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
Interpolation between plant responses in a head-tracked local active noise control headrest system 头部跟踪局部主动噪声控制头枕系统中植物响应间的插值
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-26 DOI: 10.1016/j.ymssp.2025.113401
Francesco Veronesi, Chung Kwan Lai, Jordan Cheer
{"title":"Interpolation between plant responses in a head-tracked local active noise control headrest system","authors":"Francesco Veronesi,&nbsp;Chung Kwan Lai,&nbsp;Jordan Cheer","doi":"10.1016/j.ymssp.2025.113401","DOIUrl":"10.1016/j.ymssp.2025.113401","url":null,"abstract":"<div><div>Active Noise Control (ANC) headrest systems reduce noise at the listener’s ears, but their performance can degrade with user movement. Integrating head-tracking into Local ANC systems improves performance over a wider frequency range by updating the controller for different head positions and orientations. However, practical implementations often rely on a limited set of pre-calibrated system response models, resulting in mismatches between actual and modelled head positions. Increasing the resolution of the measurement grid can mitigate this, but increases the complexity of pre-calibration. This study investigates interpolation strategies – such as inverse distance weighting, high-degree and cubic spline interpolation – to estimate plant responses between pre-calibrated positions and improve control performance. The effects of interpolation are analysed by evaluating the condition number and noise reduction achieved, with separate interpolation applied for head translations and rotations. The findings show that accurate methods, such as cubic spline and high-degree interpolation, produce more accurate plant models, which improve controller robustness, particularly at higher frequencies. In addition, frequency-dependent regularisation maximises control performance, with accurate interpolation requiring less regularisation to achieve greater noise reduction. These findings highlight the importance of selecting appropriate interpolation methods and strategic pre-calibration grid designs to ensure effective ANC system performance.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113401"},"PeriodicalIF":8.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159968","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
Coiled sonic black hole based contactless sensor for physical signal processing and its application in mechanical fault diagnosis 基于螺旋声波黑洞的非接触式物理信号处理传感器及其在机械故障诊断中的应用
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-26 DOI: 10.1016/j.ymssp.2025.113421
Zuanbo Zhou , Niaoqing Hu , Yi Yang , Zhengyang Yin , Jiangtao Hu
{"title":"Coiled sonic black hole based contactless sensor for physical signal processing and its application in mechanical fault diagnosis","authors":"Zuanbo Zhou ,&nbsp;Niaoqing Hu ,&nbsp;Yi Yang ,&nbsp;Zhengyang Yin ,&nbsp;Jiangtao Hu","doi":"10.1016/j.ymssp.2025.113421","DOIUrl":"10.1016/j.ymssp.2025.113421","url":null,"abstract":"<div><div>Closely related to equipment condition, acoustic based sensing method becomes the one of the most effective tools for state monitoring, but application is still restricted by challenges arise from attenuation in long-distance propagation and environmental noise interference. In response to the shortcomings of traditional acoustic signal sensing methods, a coiled sonic black hole (CSBH) is proposed in this paper. The acoustic rainbow trapping phenomenon in CSBH is observed and theoretically derived, and the correctness of theoretical analysis is proved by numerical simulation and experiment. Differ from common idea in sound absorption, CSBH is designed as a sensor for acoustic signal amplification and filtering in a completely physical way. Based on the characteristics of CSBH, feature extraction and enhancement of weak signals as well as mechanical fault diagnosis are studied comparatively, and experimental results show that the signal quality and intensity from CSBH are improved significantly. Acting as a physical amplifier and filter, the features in acoustic signals are well reserved by CSBH from strong background noise pollution. The methods proposed in this paper provide a brand-new perspective in acoustic signal enhancement, and it has the promising application in remote contactless condition sensing.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113421"},"PeriodicalIF":8.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160036","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-based structural anomaly detection in real-time with piezoelectric patches on a tension rod assembly 基于振动的张力杆组件压电片结构异常实时检测
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-26 DOI: 10.1016/j.ymssp.2025.113352
Ahmad Rababah , Osama Abdeljaber , Onur Avci
{"title":"Vibration-based structural anomaly detection in real-time with piezoelectric patches on a tension rod assembly","authors":"Ahmad Rababah ,&nbsp;Osama Abdeljaber ,&nbsp;Onur Avci","doi":"10.1016/j.ymssp.2025.113352","DOIUrl":"10.1016/j.ymssp.2025.113352","url":null,"abstract":"<div><div>This paper introduces a novel framework for real-time, local-level condition assessment of structural members using vibration-based anomaly detection. The approach employs a pair of piezoelectric patches: one acting as an actuator to excite the structural member and another as a sensor to capture the resulting vibration response. These signals are processed by four different machine learning models: two supervised and two unsupervised. Supervised models are a one-dimensional Convolutional Neural Network (1D CNN) and a hybrid Long Short-Term Memory model (1D CNN-LSTM). The unsupervised models are a one-dimensional Convolutional Autoencoder (1D CAE) and a hybrid 1D CAE-LSTM. The supervised algorithm basically classifies each signal segment as either “undamaged” or “damaged”. By aggregating the classification outputs across multiple segments, a structural health index is derived to quantify deviations from the baseline response of an undamaged member. In the unsupervised models, anomaly detection is based on reconstruction errors, which compute a similar health index by measuring deviation from the undamaged baseline response. The developed methods have been experimentally validated on a tension rod assembly, with damage simulated by reducing the applied tension. In this setup, the rod is threaded through a hollow steel section, and tensile force is adjusted via wing nuts at both ends. The fully tightened assembly represents the “undamaged” state, while the loosened conditions are considered as the “damaged” states. The system effectively identifies and quantifies damage severity in real-time, generating a visual graph for intuitive tracking of structural health changes. These applications demonstrate the potential of this method for practical use in monitoring real-world structures, such as suspension bridge cables and prestressed concrete elements. Experimental results confirm that the health indices derived from the proposed method closely align with the actual damage severity applied to the assembly, highlighting their accuracy and reliability.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113352"},"PeriodicalIF":8.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159959","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
Quantitative study on far-field magnetic signal response of steel pipe girth welds with weak magnetic excitation 弱磁激励下钢管环焊缝远场磁信号响应的定量研究
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-26 DOI: 10.1016/j.ymssp.2025.113404
Tengjiao He , Jiancheng Liao , Kexi Liao , Huaixin Zhang , Xiaolong Shi , Feilong Zhou , Linxiang Wang , Guoqiang Xia , Yutong Jiang , Jing Tang
{"title":"Quantitative study on far-field magnetic signal response of steel pipe girth welds with weak magnetic excitation","authors":"Tengjiao He ,&nbsp;Jiancheng Liao ,&nbsp;Kexi Liao ,&nbsp;Huaixin Zhang ,&nbsp;Xiaolong Shi ,&nbsp;Feilong Zhou ,&nbsp;Linxiang Wang ,&nbsp;Guoqiang Xia ,&nbsp;Yutong Jiang ,&nbsp;Jing Tang","doi":"10.1016/j.ymssp.2025.113404","DOIUrl":"10.1016/j.ymssp.2025.113404","url":null,"abstract":"<div><div>Unequal wall thickness welds are weaknesses in pipelines, which require stress monitoring. The magnetic-based overground stress testing method avoids excavation costs and risks during strain gauge installation. However, magnetic signals excited by the geomagnetic field lack sufficient strength and stability to meet online stress monitoring requirements. Enhancing signal strength and stability via the excitation of magnetic fields is proposed as a solution to this problem. The study of response law of magnetic signals to stress in girth welds with nonlinear material and structures under excitation magnetic fields and the effect of hysteresis on the sensitivity of magnetic signal response is meaningful. In this paper, a full-size pipeline multi-scale experimental system with unequal wall thickness girth weld is established to reveal the enhancement mechanism of excitation magnetic field on the magnetic signal and the effect of hysteresis on the sensitivity of magnetic signal. Drawing on finite element theory, a forward model for the multi-zone far-field magnetic field of girth welds is developed and validated. The results indicate that under excitation magnetic fields, magnetic signals respond rapidly to stress with excellent repeatability. The stress sensitivity of magnetic signals in X80 steel with unequal wall thickness is 6.8 (nT/m)/MPa. The forward model accurately quantifies the magnetic signal response to stress, and on-site applications confirm the feasibility of technology.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113404"},"PeriodicalIF":8.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160035","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
Risk assessment of block random rocking on nonlinear foundation subject to evolutionary seismic ground motion 演化地震动作用下非线性地基块体随机摇摆风险评估
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-26 DOI: 10.1016/j.ymssp.2025.113397
Ioannis P. Mitseas , Yuanjin Zhang , Vasileios C. Fragkoulis
{"title":"Risk assessment of block random rocking on nonlinear foundation subject to evolutionary seismic ground motion","authors":"Ioannis P. Mitseas ,&nbsp;Yuanjin Zhang ,&nbsp;Vasileios C. Fragkoulis","doi":"10.1016/j.ymssp.2025.113397","DOIUrl":"10.1016/j.ymssp.2025.113397","url":null,"abstract":"<div><div>This study develops an approximate semi-analytical framework for assessing the toppling survival probability of a rigid block subject to stochastic seismic excitation defined in accordance with modern aseismic codes provisions. The rocking system incorporates a nonlinear flexible foundation model that allows for uplifting and nonlinear damping, reflecting realistic soil–structure interaction effects. A nonlinear contact force of the Hunt and Crossley’s kind is employed. Using a stochastic averaging approach, the proposed method accounts for the unbounded response behavior associated with toppling, paralleling challenges observed in systems with negative stiffness. The nonstationary probability density function (PDF) of the rocking amplitude is formulated to quantify the survival probability over time efficiently. This technique offers significant computational advantages over traditional numerical simulations while capturing the effects of time-dependent excitation intensity and frequency content. Numerical examples, including rigid blocks rocking on various nonlinear flexible foundations under evolutionary seismic excitations, validate the proposed framework. Comparisons with Monte Carlo simulations confirm the accuracy and reliability of the method, emphasizing its utility for probabilistic assessment in seismic engineering contexts.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113397"},"PeriodicalIF":8.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159862","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
Research on the control of the grinding force of spiral bevel gear by neural network system based on model reference adaptive algorithm 基于模型参考自适应算法的神经网络控制螺旋锥齿轮磨削力的研究
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-26 DOI: 10.1016/j.ymssp.2025.113410
Nan Liu , Jiang Han , Xiaoqing Tian , Lian Xia , Minglei Li , Rui Xue
{"title":"Research on the control of the grinding force of spiral bevel gear by neural network system based on model reference adaptive algorithm","authors":"Nan Liu ,&nbsp;Jiang Han ,&nbsp;Xiaoqing Tian ,&nbsp;Lian Xia ,&nbsp;Minglei Li ,&nbsp;Rui Xue","doi":"10.1016/j.ymssp.2025.113410","DOIUrl":"10.1016/j.ymssp.2025.113410","url":null,"abstract":"<div><div>This article designs a neural network model based on model reference adaptive (MRA) control, which outputs the control voltage of the X, Y, and A-axis permanent magnet synchronous motor (PMSM) of the machine tool, so that the motor speed always follows the expected value. By changing the grinding speed, the goal is to control the main grinding force and reduce the roughness of the gear engagement surface. Firstly, a main grinding force model for spiral bevel gears was established, and the height parameters of the gear meshing surface roughness were scanned. The analysis indicates that the Pearson correlation between the main grinding force and roughness is 81.58 %. To reduce tooth surface roughness, set a grinding force threshold and calculate the expected angular velocities of the axes. Secondly, the state equation of the PMSM is established, and the Lyapunov second method is applied to design an MRA control algorithm. It is found that the model output can follow the reference model well and adapt to changes in load torque. However, there is an overshoot, and the model requires many feedback signals. Finally, to further optimize the control system, a generalized regression neural network (GRNN) was established. Founded on the output voltage of the MRA control system, training samples were established to complete the speed control of the machine tool PMSM. The results indicate that there is a strong correlation between grinding force and tooth surface roughness, and the GRNN system has good force control performance, which can indirectly improve grinding quality.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113410"},"PeriodicalIF":8.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160033","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
PhyGNN: Physics guided graph neural network for complex industrial power system modeling 用于复杂工业电力系统建模的物理引导图神经网络
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-25 DOI: 10.1016/j.ymssp.2025.113380
Yi Di , Fujin Wang , Zhi Zhai , Zhibin Zhao , Xuefeng Chen
{"title":"PhyGNN: Physics guided graph neural network for complex industrial power system modeling","authors":"Yi Di ,&nbsp;Fujin Wang ,&nbsp;Zhi Zhai ,&nbsp;Zhibin Zhao ,&nbsp;Xuefeng Chen","doi":"10.1016/j.ymssp.2025.113380","DOIUrl":"10.1016/j.ymssp.2025.113380","url":null,"abstract":"<div><div>In multi-dimension time series (MTS) tasks within industrial scenarios, several challenges arise due to the difficulty of establishing physical models, the scarcity of high-quality data, and the high demands for model accuracy, robustness, and interpretability. Traditional physical models and pure neural networks exhibit certain limitations in dealing with these challenges. Physics informed neural networks (PINN) have emerged to alleviate these issues. However, in complex industrial power systems (CIPS), classical PINNs present new challenges. The physical laws governing CIPS are vast and extremely intricate. If these laws are converted into loss terms, the loss function becomes complex, redundant, and hard to optimize, even generates conflicting gradient directions and pathological optimization curvature. To address this challenge, we propose a physics guided graph neural network (PhyGNN). One advantage of graph structures is their natural representation of complex systems like CIPS. PhyGNN utilizes this capability as a bridge to integrate physical information directly into the model architecture rather than embedding it into the loss function. Specifically, the spacecraft power system (SPS) is selected as a case study, which is a typical CIPS. First, its physical model is constructed, which includes eight subsystems and deploys diverse fidelity strategies. Then, the physical knowledge of this model is embedded into the proposed PhyGNN. Finally, various comparative experiments and visual analyses are performed on our dataset XJTU-SPS. Overall, the core contribution of this work lies in a physics guided GNN method. Meanwhile, it also contributes a comprehensive physical simulation model for power systems, and a dataset of spacecraft power systems.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113380"},"PeriodicalIF":8.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159963","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
Model updating hybrid testing method based on dual adaptive unscented Kalman filter algorithm 基于双自适应无气味卡尔曼滤波算法的模型更新混合测试方法
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-25 DOI: 10.1016/j.ymssp.2025.113348
Yutong Jiang , Guoshan Xu , Jiedun Hao
{"title":"Model updating hybrid testing method based on dual adaptive unscented Kalman filter algorithm","authors":"Yutong Jiang ,&nbsp;Guoshan Xu ,&nbsp;Jiedun Hao","doi":"10.1016/j.ymssp.2025.113348","DOIUrl":"10.1016/j.ymssp.2025.113348","url":null,"abstract":"<div><div>Model updating hybrid testing method provides crucial technical support for assessing the seismic performance of engineering structures. The model-based unscented Kalman filter (UKF) algorithm and its improved variants have become the mainstream identification choice for hybrid testing due to their high practicality and precision. However, when the statistical characteristics of system noise involve uncertainties, existing UKF-based identification algorithms may suffer from filter divergence, reduced accuracy, and decreased efficiency in MUHTM. To address these issues, this paper proposes a novel model updating hybrid testing method based on dual adaptive UKF algorithm (MUHTM-DAUKF). Firstly, the DAUKF algorithm is proposed, which integrates a Sage-Husa adaptive noise estimator module to dynamically adjust statistical characteristics of the noise and an adaptive variance module to diminish the risk of filter divergence. Furthermore, the MUHTM-DAUKF is proposed, which utilizes the DAUKF algorithm to identify and update the constitutive model parameters based on measured data from experimental substructures. This enhances the accuracy of numerical substructures and improves the overall reliability of MUHTM. Lastly, the effectiveness and accuracy of the proposed methods are validated by numerical simulations and experimental tests. It is shown from the numerical simulation results that the DAUKF algorithm is feasible for parameter identification, whilst the MUHTM-DAUKF exhibits superior accuracy and computational efficiency compared to the MUHTM based on adaptive UKF algorithm (MUHTM-AUKF) and the MUHTM based on dual adaptive filter approach (MUHTM-DAFA). The experimental results further validate the effectiveness and reliability of the MUHTM-DAUKF and the superiority of the MUHTM-DAUKF over the MUHTM-AUKF and the MUHTM-DAFA. These findings indicate that the proposed MUHTM-DAUKF has strong potential for seismic performance assessment of complex engineering structures.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113348"},"PeriodicalIF":8.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159965","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
Debonding imaging in fibre reinforced concrete columns by deep learning assisted-guided wave technique 基于深度学习辅助导波技术的纤维混凝土柱脱粘成像
IF 8.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-09-25 DOI: 10.1016/j.ymssp.2025.113409
Chang Jiang , Ching-Tai Ng , Mingxi Deng , Weibin Li
{"title":"Debonding imaging in fibre reinforced concrete columns by deep learning assisted-guided wave technique","authors":"Chang Jiang ,&nbsp;Ching-Tai Ng ,&nbsp;Mingxi Deng ,&nbsp;Weibin Li","doi":"10.1016/j.ymssp.2025.113409","DOIUrl":"10.1016/j.ymssp.2025.113409","url":null,"abstract":"<div><div>This study proposes a novel deep learning-assisted framework for detecting interfacial debonding defects in fibre-reinforced polymer (FRP)-wrapped concrete columns using ultrasonic guided waves. Traditional non-destructive testing methods face significant challenges in curved and anisotropic structures due to complex wave dispersion and multimodal propagation characteristics. To overcome these limitations, we developed an advanced hybrid deep neural network (DNN) architecture that synergistically combines time-domain ultrasonic signals with an enhanced elliptical imaging algorithm (ELIA) to achieve superior defect localization accuracy. A finite element (FE) model was established to simulate guided wave propagation in FRP-strengthened concrete columns, generating synthetic training samples that capture diverse debonding scenarios. The proposed DNN employs a dual-encoder structure to extract both temporal and spatial features, followed by a decoder with skip connections for precise damage reconstruction. Experimental validation on FRP-retrofitted concrete specimens with artificially induced debonding demonstrated the model’s robust performance, achieving accurate defect localization and shape prediction despite variations in real-world conditions. Comparative analysis revealed significant improvements over conventional ELIA, particularly in suppressing imaging artifacts and enhancing edge definition. This research contributes an efficient, cost-effective solution for structural health monitoring (SHM) by leveraging simulated data to minimize experimental requirements while maintaining high detection reliability. The framework shows promising potential for practical implementation in civil infrastructure monitoring systems.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"240 ","pages":"Article 113409"},"PeriodicalIF":8.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159964","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信