Mechanical Systems and Signal Processing最新文献

筛选
英文 中文
Diagnosis of composite faults for complex industrial machinery: A label-assisted self-supervised clustering approach
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-17 DOI: 10.1016/j.ymssp.2025.112509
Hewei Gao , Xin Huo , Chao Zhu , Changchun He , Jiao Meng
{"title":"Diagnosis of composite faults for complex industrial machinery: A label-assisted self-supervised clustering approach","authors":"Hewei Gao ,&nbsp;Xin Huo ,&nbsp;Chao Zhu ,&nbsp;Changchun He ,&nbsp;Jiao Meng","doi":"10.1016/j.ymssp.2025.112509","DOIUrl":"10.1016/j.ymssp.2025.112509","url":null,"abstract":"<div><div>Early detection of faults is crucial to ensure the effective operation of industrial machinery. Incipient faults are hard to detect because the fault signals are weak, lack sufficient labels, and there is interference caused by multiple sensor signals and a large amount of noise background. Once a fault occurs, it will usually lead to composite faults that are coupled together, seriously affecting the accuracy of fault diagnosis. To overcome these challenges, this paper proposes a Label-assisted Self-supervised Clustering (LASSC) approach, which consists of two stages. The first stage is to mine the coupling characteristics of multi-sensor signals, and the second stage is to judge the composite fault states. Due to significant differences in magnitude, some fault features are ignored when learning from multi-sensor signals. To cope with this, constraint boundaries-based normalization is employed. Unlabeled data are projected onto a weight matrix through feature clustering, and the composite fault features are mined through unsupervised clustering. With the constraint of the assistance labels, self-supervised clustering integrates information from all channels to diagnose composite faults. Experiments are conducted using the proposed LASSC approach on the CWRU dataset to validate the accuracy and computational efficiency of the model. In addition, a series of experiments are designed on the excavator dataset, such as sample imbalance and limited labeled data, to verify the adaptability of the model in practical industrial applications. In addition, the application of this method in excavator cases revealed the causes of composite fault through interpretability analysis, enabling more targeted maintenance recommendations for industrial machinery faults.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"230 ","pages":"Article 112509"},"PeriodicalIF":7.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642630","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
Reweighted periodic overlapping group lasso for impulsive feature extraction and its application to spiral bevel gear local fault diagnosis
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-17 DOI: 10.1016/j.ymssp.2025.112572
Keyuan Li , Junjiang Liu , Zhibin Zhao , Benyuan Ye , Baijie Qiao , Xuefeng Chen
{"title":"Reweighted periodic overlapping group lasso for impulsive feature extraction and its application to spiral bevel gear local fault diagnosis","authors":"Keyuan Li ,&nbsp;Junjiang Liu ,&nbsp;Zhibin Zhao ,&nbsp;Benyuan Ye ,&nbsp;Baijie Qiao ,&nbsp;Xuefeng Chen","doi":"10.1016/j.ymssp.2025.112572","DOIUrl":"10.1016/j.ymssp.2025.112572","url":null,"abstract":"<div><div>Gear localized faults, such as pitting, spalling and crack, are one of the most common fault manifestations for spiral bevel gear (SBG). However, it is a challenge to extract the fault information submerged in the intensive background noise. To address this issue, a novel reweighted periodic overlapping group lasso (Re-POGL) method for SBG fault diagnosis is proposed in this study. The algorithm utilizes the sparsity within and across groups (SWAG) of the impulsive feature of SBG faults to construct penalty term. An exponential nonconvex penalty function is chosen for SWAG to enhance the sparsity. Moreover, a reweighted coefficient is formed based on the <span><math><msub><mi>l</mi><mn>2</mn></msub></math></span>−norm of the periodic groups to enhance the amplitude of reconstructed fault characteristic signal. By virtue of SWAG and nonconvex regularizer, the Re-POGL model is established. The convex condition is proved to ensure that the objective function remains convex even with nonconvex penalty terms. The majorization-minimization (MM) is used to derive the solution of the proposed model. Additionally, the setting strategy of the regularization parameters is also provided. Finally, the performance of Re-POGL is validated by numerical simulations and the diagnosis experiments of SBGs. The results indicate that the impulsive fault characteristic can be extracted plainly and the amplitude of the fault impulses is enhanced.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"230 ","pages":"Article 112572"},"PeriodicalIF":7.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642631","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
Differential time-frequency mode decomposition and its application in rotating machinery fault diagnosis
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-16 DOI: 10.1016/j.ymssp.2025.112571
Bin Sun , Hongkun Li , Junxiang Wang , Shuai Lv , Zhenhui Ma
{"title":"Differential time-frequency mode decomposition and its application in rotating machinery fault diagnosis","authors":"Bin Sun ,&nbsp;Hongkun Li ,&nbsp;Junxiang Wang ,&nbsp;Shuai Lv ,&nbsp;Zhenhui Ma","doi":"10.1016/j.ymssp.2025.112571","DOIUrl":"10.1016/j.ymssp.2025.112571","url":null,"abstract":"<div><div>Mode decomposition methods, such as Empirical Mode Decomposition (EMD), Empirical Wavelet Transform (EWT), Variational Mode Decomposition (VMD), and Singular Value Decomposition (SVD), are widely used in signal denoising. However, these methods essentially act as band-pass filter banks, decomposing signals into different frequency bands. This leads to two key challenges: on the one hand, they cannot remove noise within the frequency band; on the other hand, extracting sensitive components requires precise quantitative criteria, and the design principles of these methods may not apply to all signals. In practical industrial applications, most of the signals collected are from normal operating conditions. To address the aforementioned issues, this paper proposes a novel adaptive mode decomposition method—Differential Time-Frequency Mode Decomposition (DTFMD). This method decomposes signals into sensitive components (SC), reference components (RC), and noise. First, normalized time–frequency amplitude spectra (NTFAS) from easily acquired normal signals in industrial settings are used as reference signals, while the NTFAS from fault signals serve as mixed signals. A large-margin convex optimization model is then applied to identify the optimized weights time–frequency spectrum (OWTFS). Next, an adaptive thresholding strategy is developed to locate the time–frequency positions of the SC, RC, and noise on the OWTFS. Time-frequency inverse transformation techniques are then used to reconstruct the components. Finally, simulations, bearing experiments, and industrial truck gearbox data are used to validate the effectiveness and advantages of the proposed method, with comparisons made against existing mode decomposition techniques.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112571"},"PeriodicalIF":7.9,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632027","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
On the use of reliability methods and Hamiltonian Monte Carlo for complex identification problems in structural dynamics
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-15 DOI: 10.1016/j.ymssp.2025.112547
Héctor A. Jensen, Danko J. Jerez, Cristóbal Figueroa
{"title":"On the use of reliability methods and Hamiltonian Monte Carlo for complex identification problems in structural dynamics","authors":"Héctor A. Jensen,&nbsp;Danko J. Jerez,&nbsp;Cristóbal Figueroa","doi":"10.1016/j.ymssp.2025.112547","DOIUrl":"10.1016/j.ymssp.2025.112547","url":null,"abstract":"<div><div>This contribution focuses on the solution of complex Bayesian model updating problems related to structural dynamical systems. By adopting the paradigm of Bayesian model updating with structural reliability methods (BUS), the problem of sampling the posterior distribution is restated as that of generating samples conditional on an especially devised failure event. To address the latter, the well-established subset simulation method is appropriately integrated with a Hamiltonian Monte Carlo technique to obtain samples at each simulation level. In this setting, a candidate state is first determined by simulating the trajectory of an auxiliary dynamical system, and then accepted or rejected based on the traditional Metropolis-Hastings rule. Such an approach has proven efficient in drawing samples from complex target distributions, and thus, it is adopted as an effective tool to explore involved domains related to challenging model updating problems. To assess the performance of the method, two test problems as well as one application example associated with a nonlinear structural dynamical model are investigated. Numerical results indicate that the proposed approach can be regarded as a viable alternative to address a class of complex identification problems in structural dynamics, including locally identifiable cases, models that are strictly unidentifiable based on available data, and cases with a large number of model parameters.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112547"},"PeriodicalIF":7.9,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628214","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
Reference-free remaining fatigue life prediction for notched aluminum 6061-T6 plates without preliminary fatigue tests
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-15 DOI: 10.1016/j.ymssp.2025.112569
Ohjun Kwon , Hyung Jin Lim , Hoon Sohn
{"title":"Reference-free remaining fatigue life prediction for notched aluminum 6061-T6 plates without preliminary fatigue tests","authors":"Ohjun Kwon ,&nbsp;Hyung Jin Lim ,&nbsp;Hoon Sohn","doi":"10.1016/j.ymssp.2025.112569","DOIUrl":"10.1016/j.ymssp.2025.112569","url":null,"abstract":"<div><div>Fatigue crack is a primary cause of failure in metallic structures, and it gradually grows and suddenly fails at the fatigue life. Thus, predicting the remaining fatigue life is crucial<!--> <!-->for the practical and economical maintenance of the metallic structures. However, the major challenge in predicting the remaining fatigue life using the fatigue crack growth model, requires preliminary fatigue tests to estimate its parameters. To tackle this issue, this study proposes a reference-free remaining fatigue life prediction technique under varying-amplitude uniaxial cyclic loading conditions based on the Walker equation without using any preliminary fatigue tests. First, the absolute cyclic strain was measured using ultrasonic waves and relative strain without using the data obtained under zero-loading conditions. Next, the Walker equation parameters and cumulative number of strain cycles were estimated from the absolute cyclic strain without preliminary fatigue tests. Subsequently, the measured absolute cyclic strain under varying-amplitude uniaxial cyclic loading conditions was converted into an equivalent uniform cyclic strain. Finally, the fatigue crack growth was predicted using the Walker equation, and the remaining fatigue life was estimated using the cumulative number of strain cycles and the equivalent uniform cyclic strain. The uniqueness of the proposed technique includes (1) estimation of the Walker equation parameters and fatigue life without any preliminary fatigue tests, (2) remaining fatigue life prediction only using the data acquired after installing sensors, and (3) experimental validation by predicting the remaining fatigue life under varying-amplitude uniaxial cyclic loading conditions using notched aluminum 6061-T6 plate specimens.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112569"},"PeriodicalIF":7.9,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628216","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
On the influence of attributes for assessing similarity and sharing knowledge in heterogeneous populations of structures
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-14 DOI: 10.1016/j.ymssp.2025.112554
Giulia Delo , Aidan J. Hughes , Cecilia Surace , Keith Worden
{"title":"On the influence of attributes for assessing similarity and sharing knowledge in heterogeneous populations of structures","authors":"Giulia Delo ,&nbsp;Aidan J. Hughes ,&nbsp;Cecilia Surace ,&nbsp;Keith Worden","doi":"10.1016/j.ymssp.2025.112554","DOIUrl":"10.1016/j.ymssp.2025.112554","url":null,"abstract":"<div><div>The effectiveness of data-driven Structural Health Monitoring methods, which require dynamic response data from undamaged and damaged states within the same domain, is often hindered by the scarcity of data. The population-based approach to Structural Health Monitoring (PBSHM) aims to overcome this challenge by exploiting the transfer of damage-state knowledge across a population of structures via transfer-learning algorithms — specifically domain adaptation. However, meaningful inference through data sharing is possible only when the structures and their datasets are sufficiently similar. This study advances PBSHM by focusing on its two main phases: assessing structural similarity and developing effective transfer-learning strategies for heterogeneous populations. Furthermore, it explores the interdependence of these phases by addressing the role of structural attributes – such as material properties, geometry, and dimensions – in the performance of domain adaptation and similarity metrics. The proposed methodology employs Normal Condition Alignment (NCA) and Joint Distribution Adaptation (JDA) as domain-adaptation techniques across a population of laboratory-scale aircraft, considering tasks of increasing complexity. Additionally, the effect of material properties, geometry or dimensional differences in similarity assessment is investigated, comparing Graph Matching Networks and correlation-based distance metrics.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112554"},"PeriodicalIF":7.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A model predictive control method for 7-DoF tower cranes with distributed mass payloads and variable rope lengths
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-14 DOI: 10.1016/j.ymssp.2025.112513
Yaxuan Wu , Qingxiang Wu , Menghua Zhang , Shudong Guo , Meng Zhai , Ruiping Pang , Ning Sun
{"title":"A model predictive control method for 7-DoF tower cranes with distributed mass payloads and variable rope lengths","authors":"Yaxuan Wu ,&nbsp;Qingxiang Wu ,&nbsp;Menghua Zhang ,&nbsp;Shudong Guo ,&nbsp;Meng Zhai ,&nbsp;Ruiping Pang ,&nbsp;Ning Sun","doi":"10.1016/j.ymssp.2025.112513","DOIUrl":"10.1016/j.ymssp.2025.112513","url":null,"abstract":"<div><div>Existing research on tower cranes mainly focuses on single pendulum and double pendulum models with point mass payloads. However, in the hoisting and transportation of large payloads, such as rockets, bridge boxes, and structural steel materials, the volume and shape of the payloads cannot be ignored. These characteristics introduce complex dynamic behaviors and make it challenging to directly apply existing control methods. Inspired by the above considerations, this paper presents a model predictive control (MPC) method for 7-degrees-of-freedom (DoF) tower cranes with distributed mass payloads (DMPs). Firstly, a dynamic model is established for 7-DoF tower cranes, considering DMPs, variable rope lengths, and the three-dimensional swing angles of hooks and payloads. Then, MPC methods with actuator saturation constraints are designed to achieve accurate positioning and payload swing suppression for 7-DoF tower cranes, while enhancing robustness in dynamic environments. It can also efficiently handle system parameter uncertainties and disturbances. Finally, experiments conducted on the tower crane experiment platform provide a more intuitive demonstration of the proposed method’s ability to efficiently suppress the swing of DMPs while ensuring the positioning accuracy of jibs, trolleys, and hoisting ropes.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112513"},"PeriodicalIF":7.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619497","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
Diagnosis indicator for blade-casing rubbing faults based on multi-harmonic phases
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-14 DOI: 10.1016/j.ymssp.2025.112550
Tao Zhou , Yuanshuang Bi , Hao Wang , Limin Zou , Minghui Hu
{"title":"Diagnosis indicator for blade-casing rubbing faults based on multi-harmonic phases","authors":"Tao Zhou ,&nbsp;Yuanshuang Bi ,&nbsp;Hao Wang ,&nbsp;Limin Zou ,&nbsp;Minghui Hu","doi":"10.1016/j.ymssp.2025.112550","DOIUrl":"10.1016/j.ymssp.2025.112550","url":null,"abstract":"<div><div>Blade-casing rubbing is a typical fault of aero-engines. Due to its scattered features and primarily caused by other faults, diagnosing it remains a challenge. This paper proposes a diagnosis indicator based on multi-harmonic phases for real-time monitoring of rubbing faults in aero-engines. Firstly, through the theoretical derivation, we find that the multi-harmonic phases can reflect the occurrence of rubbing faults. Secondly, a rubbing fault diagnosis indicator, <em>PKLM</em>, is constructed by weighted incorporation of multi-harmonic phases, with Kullback–Leibler divergence employed to amplify the differences between the fault and normal conditions. An optimal harmonic number criterion, <em>S</em>, is established for constructing the indicator, along with a threshold, <em>PKLH</em>, to determine the system’s condition. Thirdly, the measured harmonic phases are processed to serve as effective inputs for the indicator. Finally, model simulations and experimental results confirm that the proposed indicator can isolate interference from other rotor faults and effectively quantitatively diagnose aero-engine rubbing faults.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112550"},"PeriodicalIF":7.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628215","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
Successive Nonlinear Chirp Component Analysis
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-14 DOI: 10.1016/j.ymssp.2025.112548
Xujun Peng, Zhiyu Shi, Jinyan Li, Pengfei Jin, Hao Shen
{"title":"Successive Nonlinear Chirp Component Analysis","authors":"Xujun Peng,&nbsp;Zhiyu Shi,&nbsp;Jinyan Li,&nbsp;Pengfei Jin,&nbsp;Hao Shen","doi":"10.1016/j.ymssp.2025.112548","DOIUrl":"10.1016/j.ymssp.2025.112548","url":null,"abstract":"<div><div>Nonlinear Component Chirp Analysis (NCCA) is designed to extract non-stationary source signals and mixing vectors from instantaneous linear mixing model, which is commonplace in blind source separation (BSS) problems. However, several challenges limit its practical application: (i) the number of source signals must be predetermined; (ii) computation time increases significantly with the number of source signals; and (iii) the bandwidth parameter remains fixed throughout the entire process. To address these issues, this paper proposes Successive NCCA. In this approach, source signals are treated as Nonlinear Chirp Modes (NCMs) and are sequentially captured by Successive NCCA in a recursive framework, continuing until the energy ratio of the residual signal falls below a set threshold. This method eliminates the need to predetermine the number of source signals and significantly reduces computation time. Additionally, the Index of Orthogonality (IO) between the source signal and the residual signal is used to adaptively adjust the bandwidth parameter. A series of synthetic signals is employed to evaluate the performance of Successive NCCA, including its mode alignment capability, underdetermined blind source separation (UBSS) ability, filter-bank structure, computational efficiency, and convergence properties. Finally, Successive NCCA is applied to the separation of <span><math><mi>α</mi></math></span>-rhythms in multichannel electroencephalogram (EEG) data and the analysis of time-varying vibration systems.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112548"},"PeriodicalIF":7.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619495","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
Calibrated source-free adaptation for intelligent diagnosis
IF 7.9 1区 工程技术
Mechanical Systems and Signal Processing Pub Date : 2025-03-14 DOI: 10.1016/j.ymssp.2025.112582
Hao Li, Zongyang Liu, Jing Lin, Jinyang Jiao, Tian Zhang, Hu Pan
{"title":"Calibrated source-free adaptation for intelligent diagnosis","authors":"Hao Li,&nbsp;Zongyang Liu,&nbsp;Jing Lin,&nbsp;Jinyang Jiao,&nbsp;Tian Zhang,&nbsp;Hu Pan","doi":"10.1016/j.ymssp.2025.112582","DOIUrl":"10.1016/j.ymssp.2025.112582","url":null,"abstract":"<div><div>The domain adaptation-based fault diagnosis method has achieved an appealing cross-domain fault diagnosis performance. However, source domain data is often inaccessible due to data privacy concerns or the need to reduce the burden of data storage and transmission. Additionally, the credibility of diagnosis results is rarely considered, which is indispensable for decision-making, especially in critical safety scenarios. To address these challenges, this paper proposes a novel cross-domain fault diagnosis method called Calibrated Source-free Adaptation Diagnosis (CSAD). Specifically, a pseudo-label learning-based model adaptation diagnosis framework without the assistance of source data is formulated, where a determinant-based mutual information regular is developed to mitigate the adverse impact of noisy pseudo labels. Furthermore, an unsupervised target-mimic-oriented model calibration method is devised for more credible diagnosis results in source-free scenarios. Comparative experiments are conducted to validate the effectiveness and superiority of the proposed method. In terms of diagnosis accuracy, CSAD achieved average accuracies of 99.42%, 99.60%, and 98.61% on the three datasets, respectively, surpassing other methods. Regarding model calibration performance, our approach reduced ECE by 4.56%, 5.58%, and 4.62% on the three datasets compared to the uncalibrated models.</div></div>","PeriodicalId":51124,"journal":{"name":"Mechanical Systems and Signal Processing","volume":"229 ","pages":"Article 112582"},"PeriodicalIF":7.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619496","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:481959085
Book学术官方微信