Xiao-Wei Dong , Zhen-Ao Li , Jia-Hao Liang , Qing-Long Li , Chun-Yan Zhu , Ming Wang , Wei-Kai Li
{"title":"基于协同移动回归的结构低周疲劳寿命可靠性评估代理建模框架","authors":"Xiao-Wei Dong , Zhen-Ao Li , Jia-Hao Liang , Qing-Long Li , Chun-Yan Zhu , Ming Wang , Wei-Kai Li","doi":"10.1016/j.cma.2025.118213","DOIUrl":null,"url":null,"abstract":"<div><div>To achieve low-cycle fatigue (LCF) life prediction and reliability assessment for mechanical structures, a collaborative moving regression-based surrogate modeling (CMR-SM) framework is proposed by fusing the collaborative moving regression (CMR) strategy, heuristic algorithm, adaptive hybrid surrogate modeling method, and matrix analysis theory. In this framework, the CMR strategy is developed from the decomposition-coordination (DC) method and moving least squares (MLS) technique to reduce model nonlinearity and acquire effective samples; the optimal radius for compact support region is determined through quadratic interpolation optimization (QIO); Matrix analysis theory is applied to construct vectors and cell arrays of unknown parameters, synchronously establishing the mathematical model. Under this concept, the CMR-based response surface method (CMR-RSM), CMR-based Kriging model (CMR-KM), CMR-based support vector machine (CMR-SVM), and CMR-based artificial neural network (CMR-ANN) are further developed. Considering the robustness of model, an adaptive weighting technique is employed to further develop the collaborative moving regression-based adaptive hybrid surrogate modeling (CMR-AHSM) method. The excellent modeling capabilities and simulation performance of the proposed method are validated through a numerical case (i.e., the probability analysis of a nested nonlinear function) and an engineering case (i.e., the LCF life reliability assessment of turbine blisk). The proposed method provides new insights for LCF life reliability assessment in engineering structures.</div></div>","PeriodicalId":55222,"journal":{"name":"Computer Methods in Applied Mechanics and Engineering","volume":"445 ","pages":"Article 118213"},"PeriodicalIF":7.3000,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Collaborative moving regression-based surrogate modeling framework for structural low cycle fatigue life reliability assessment\",\"authors\":\"Xiao-Wei Dong , Zhen-Ao Li , Jia-Hao Liang , Qing-Long Li , Chun-Yan Zhu , Ming Wang , Wei-Kai Li\",\"doi\":\"10.1016/j.cma.2025.118213\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>To achieve low-cycle fatigue (LCF) life prediction and reliability assessment for mechanical structures, a collaborative moving regression-based surrogate modeling (CMR-SM) framework is proposed by fusing the collaborative moving regression (CMR) strategy, heuristic algorithm, adaptive hybrid surrogate modeling method, and matrix analysis theory. In this framework, the CMR strategy is developed from the decomposition-coordination (DC) method and moving least squares (MLS) technique to reduce model nonlinearity and acquire effective samples; the optimal radius for compact support region is determined through quadratic interpolation optimization (QIO); Matrix analysis theory is applied to construct vectors and cell arrays of unknown parameters, synchronously establishing the mathematical model. Under this concept, the CMR-based response surface method (CMR-RSM), CMR-based Kriging model (CMR-KM), CMR-based support vector machine (CMR-SVM), and CMR-based artificial neural network (CMR-ANN) are further developed. Considering the robustness of model, an adaptive weighting technique is employed to further develop the collaborative moving regression-based adaptive hybrid surrogate modeling (CMR-AHSM) method. The excellent modeling capabilities and simulation performance of the proposed method are validated through a numerical case (i.e., the probability analysis of a nested nonlinear function) and an engineering case (i.e., the LCF life reliability assessment of turbine blisk). The proposed method provides new insights for LCF life reliability assessment in engineering structures.</div></div>\",\"PeriodicalId\":55222,\"journal\":{\"name\":\"Computer Methods in Applied Mechanics and Engineering\",\"volume\":\"445 \",\"pages\":\"Article 118213\"},\"PeriodicalIF\":7.3000,\"publicationDate\":\"2025-07-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Methods in Applied Mechanics and Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0045782525004852\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Methods in Applied Mechanics and Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0045782525004852","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
Collaborative moving regression-based surrogate modeling framework for structural low cycle fatigue life reliability assessment
To achieve low-cycle fatigue (LCF) life prediction and reliability assessment for mechanical structures, a collaborative moving regression-based surrogate modeling (CMR-SM) framework is proposed by fusing the collaborative moving regression (CMR) strategy, heuristic algorithm, adaptive hybrid surrogate modeling method, and matrix analysis theory. In this framework, the CMR strategy is developed from the decomposition-coordination (DC) method and moving least squares (MLS) technique to reduce model nonlinearity and acquire effective samples; the optimal radius for compact support region is determined through quadratic interpolation optimization (QIO); Matrix analysis theory is applied to construct vectors and cell arrays of unknown parameters, synchronously establishing the mathematical model. Under this concept, the CMR-based response surface method (CMR-RSM), CMR-based Kriging model (CMR-KM), CMR-based support vector machine (CMR-SVM), and CMR-based artificial neural network (CMR-ANN) are further developed. Considering the robustness of model, an adaptive weighting technique is employed to further develop the collaborative moving regression-based adaptive hybrid surrogate modeling (CMR-AHSM) method. The excellent modeling capabilities and simulation performance of the proposed method are validated through a numerical case (i.e., the probability analysis of a nested nonlinear function) and an engineering case (i.e., the LCF life reliability assessment of turbine blisk). The proposed method provides new insights for LCF life reliability assessment in engineering structures.
期刊介绍:
Computer Methods in Applied Mechanics and Engineering stands as a cornerstone in the realm of computational science and engineering. With a history spanning over five decades, the journal has been a key platform for disseminating papers on advanced mathematical modeling and numerical solutions. Interdisciplinary in nature, these contributions encompass mechanics, mathematics, computer science, and various scientific disciplines. The journal welcomes a broad range of computational methods addressing the simulation, analysis, and design of complex physical problems, making it a vital resource for researchers in the field.