The fatigue behavior of large wind turbine blades is complex and stochastic due to their complex structure and operating environment. This paper focuses on developing a probabilistic fatigue life assessment method for wind turbine blades considering the uncertainties from wind velocity, material mechanical properties, pitch angle, and layer thickness. To improve the efficiency of stochastic fatigue behavior analysis of wind turbine blade, unidirectional fluid‐structure coupling (UFSC) and bidirectional fluid‐structure coupling (BFSC) analysis are employed to analyze the stochastic response. Then, Gaussian process regression (GPR) and Bayesian updating are combined to establish the stochastic fatigue behavior prediction model for wind turbine blade. On this basis, a modified S‐N curve formulation is proposed, and the fatigue life of wind turbine blade is analyzed by the modified S‐N curve and compared with the three‐parameter Weibull model. The results indicate that the proposed method for fatigue life assessment has better accuracy. The proposed probabilistic fatigue life assessment method with high accuracy and high efficiency, which is beneficial for the fatigue reliability design of wind turbine blades.
{"title":"A probabilistic fatigue life assessment method for wind turbine blade based on Bayesian GPR with the effects of pitch angle","authors":"Xiaoling Zhang, Kejia Zhang, Zhongzhe Chen","doi":"10.1002/qre.3575","DOIUrl":"https://doi.org/10.1002/qre.3575","url":null,"abstract":"The fatigue behavior of large wind turbine blades is complex and stochastic due to their complex structure and operating environment. This paper focuses on developing a probabilistic fatigue life assessment method for wind turbine blades considering the uncertainties from wind velocity, material mechanical properties, pitch angle, and layer thickness. To improve the efficiency of stochastic fatigue behavior analysis of wind turbine blade, unidirectional fluid‐structure coupling (UFSC) and bidirectional fluid‐structure coupling (BFSC) analysis are employed to analyze the stochastic response. Then, Gaussian process regression (GPR) and Bayesian updating are combined to establish the stochastic fatigue behavior prediction model for wind turbine blade. On this basis, a modified S‐N curve formulation is proposed, and the fatigue life of wind turbine blade is analyzed by the modified S‐N curve and compared with the three‐parameter Weibull model. The results indicate that the proposed method for fatigue life assessment has better accuracy. The proposed probabilistic fatigue life assessment method with high accuracy and high efficiency, which is beneficial for the fatigue reliability design of wind turbine blades.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"82 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140937397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hierarchical Bayes, or E‐Bayes, is frequently used to estimate the failure probability when solving a zero‐failure reliability evaluation model; however, the accuracy of the reliability estimation using these methods is not very good in practice. Due to this, a novel double‐modified hierarchical Bayes (DMH‐Bayes) is proposed for Weibull characteristic data in this study to enhance failure probability estimation and improve reliability point estimation accuracy. Meanwhile, in order to guarantee the preservation of the assessment findings' consistency and confidence level, the parametric Bootstrap method (P‐Bootstrap) and the L‐moment estimation method based on point estimation are introduced to obtain reliability confidence interval estimates. Based on Monte–Carlo simulation testing and analysis of a gyroscope bearing, the new model is confirmed to have better applicability and robustness while improving the accuracy of reliability assessment.
{"title":"Reliability evaluation in the zero‐failure Weibull case based on double‐modified hierarchical Bayes","authors":"Bo Zheng, Zuteng Long, Yang Ning, Xin Ma","doi":"10.1002/qre.3572","DOIUrl":"https://doi.org/10.1002/qre.3572","url":null,"abstract":"Hierarchical Bayes, or E‐Bayes, is frequently used to estimate the failure probability when solving a zero‐failure reliability evaluation model; however, the accuracy of the reliability estimation using these methods is not very good in practice. Due to this, a novel double‐modified hierarchical Bayes (DMH‐Bayes) is proposed for Weibull characteristic data in this study to enhance failure probability estimation and improve reliability point estimation accuracy. Meanwhile, in order to guarantee the preservation of the assessment findings' consistency and confidence level, the parametric Bootstrap method (P‐Bootstrap) and the L‐moment estimation method based on point estimation are introduced to obtain reliability confidence interval estimates. Based on Monte–Carlo simulation testing and analysis of a gyroscope bearing, the new model is confirmed to have better applicability and robustness while improving the accuracy of reliability assessment.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"45 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140937398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The lifetime data collected from the field are usually heavily censored, in which case, getting an accurate reliability evaluation based on heavily censored data is challenging. For heavily Type‐II censored data, the parameters estimation bias of traditional methods (i.e., maximum likelihood estimation (MLE) and least squares estimation (LSE)) are still large, and Bayesian methods are hard to specify the priors in practice. Therefore, considering the existing range of shape parameter for Weibull distribution, this study proposes two novel parameter estimation methods, the three‐step MLE method and the hybrid estimation method. For the three‐step MLE method, the initial estimates of shape and scale parameters are first respectively derived using MLE, then are updated by the single parameter MLE method with the range constraint of shape parameter. For the hybrid estimation method, the shape parameter is estimated by the LSE method with the existing range constraint of shape parameter, then the scale parameter estimate can be obtained by MLE. On this basis, two numerical examples are performed to demonstrate the consistency and effectiveness of the proposed methods. Finally, a case study on turbine engines is given to verify the effectiveness and applicability of the proposed methods.
{"title":"Reliability evaluation for Weibull distribution with heavily Type II censored data","authors":"Mengyu Liu, Huiling Zheng, Jun Yang","doi":"10.1002/qre.3570","DOIUrl":"https://doi.org/10.1002/qre.3570","url":null,"abstract":"The lifetime data collected from the field are usually heavily censored, in which case, getting an accurate reliability evaluation based on heavily censored data is challenging. For heavily Type‐II censored data, the parameters estimation bias of traditional methods (i.e., maximum likelihood estimation (MLE) and least squares estimation (LSE)) are still large, and Bayesian methods are hard to specify the priors in practice. Therefore, considering the existing range of shape parameter for Weibull distribution, this study proposes two novel parameter estimation methods, the three‐step MLE method and the hybrid estimation method. For the three‐step MLE method, the initial estimates of shape and scale parameters are first respectively derived using MLE, then are updated by the single parameter MLE method with the range constraint of shape parameter. For the hybrid estimation method, the shape parameter is estimated by the LSE method with the existing range constraint of shape parameter, then the scale parameter estimate can be obtained by MLE. On this basis, two numerical examples are performed to demonstrate the consistency and effectiveness of the proposed methods. Finally, a case study on turbine engines is given to verify the effectiveness and applicability of the proposed methods.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"81 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140937602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Establishing an accurate accelerated degradation model is paramount for ensuring precise reliability evaluation results. Unfortunately, current accelerated degradation tests often lack test groups for investigating multi‐stress coupled phenomena. Consequently, existing multi‐stress accelerated models fail to adequately consider the impact of stress coupling when data with stress coupling information is absent. This limitation leads to the development of inaccurate models, ultimately affecting the precision of reliability assessment. To address this challenge, this paper introduces a new modeling method for multi‐stress accelerated degradation models that takes into account stress coupling effects. The proposed modeling method aims to improve the accuracy of reliability assessment under multi‐stress conditions. In the proposed model, the main effect function of stress is determined based on existing single‐stress accelerated models. The coupling effect is first examined through the Multivariate Analysis of Variance (MANOVA), and then the functional form of the coupling effect function is determined from the given candidate functions through correlation analysis. Next, the coupling effect is incorporated into a Wiener process to establish a multi‐stress accelerated degradation model, and the two‐step estimation method combining Least Squares Method (LSM) and Differential Evolution Algorithm (DEA) is proposed. The accuracy and effectiveness of the coupling effect test method, model establishment, and parameter estimation method were validated using two Monte Carlo simulation experimental data sets. Finally, the superiority of the proposed model is demonstrated through examples, providing feasible ideas and technical support for the research on multi‐stress accelerated degradation modeling considering stress coupling.
{"title":"Acceleration model considering multi‐stress coupling effect and reliability modeling method based on nonlinear Wiener process","authors":"Xiaojian Yi, Zhezhe Wang, Shulin Liu, Qing Tang","doi":"10.1002/qre.3565","DOIUrl":"https://doi.org/10.1002/qre.3565","url":null,"abstract":"Establishing an accurate accelerated degradation model is paramount for ensuring precise reliability evaluation results. Unfortunately, current accelerated degradation tests often lack test groups for investigating multi‐stress coupled phenomena. Consequently, existing multi‐stress accelerated models fail to adequately consider the impact of stress coupling when data with stress coupling information is absent. This limitation leads to the development of inaccurate models, ultimately affecting the precision of reliability assessment. To address this challenge, this paper introduces a new modeling method for multi‐stress accelerated degradation models that takes into account stress coupling effects. The proposed modeling method aims to improve the accuracy of reliability assessment under multi‐stress conditions. In the proposed model, the main effect function of stress is determined based on existing single‐stress accelerated models. The coupling effect is first examined through the Multivariate Analysis of Variance (MANOVA), and then the functional form of the coupling effect function is determined from the given candidate functions through correlation analysis. Next, the coupling effect is incorporated into a Wiener process to establish a multi‐stress accelerated degradation model, and the two‐step estimation method combining Least Squares Method (LSM) and Differential Evolution Algorithm (DEA) is proposed. The accuracy and effectiveness of the coupling effect test method, model establishment, and parameter estimation method were validated using two Monte Carlo simulation experimental data sets. Finally, the superiority of the proposed model is demonstrated through examples, providing feasible ideas and technical support for the research on multi‐stress accelerated degradation modeling considering stress coupling.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"25 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140937472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When monitoring risk in public health, count data commonly exhibit an excessive number of zero, and the zero‐inflated Poisson (ZIP) model is often used to fit this type of data. Most previous methods for monitoring of the ZIP model have focused on the changes in the location parameter and the existence of the scale parameter and usually assumed that the scale parameter is zero in the H0 stage. However, in an objective environment, data often have certain fluctuations, meaning that the scale parameter always exists. Therefore, it is more meaningful to monitor the changes in the scale parameter on top of the predefined baseline than to monitor its existence. In this study, we derive a score test statistic based on the generalized Henderson's joint likelihood function, construct a risk‐adjusted exponentially weighted moving average (EWMA) control chart to monitor the variability of the random effects variance component in the ZIP mixed‐effects model. And the convergence property of the score test statistic is proved through derivation, which shows that the new method has theoretical reliability. The simulation results Indicate that when the scale parameter has different predefined baselines and different variation amplitudes, the proposed method is more effective than the existing RA‐ZIP and PR‐ZIP control charts. In addition, the proposed method is applied to real data from a Hong Kong hospital for online influenza surveillance to demonstrate its practicability.
在监测公共卫生风险时，计数数据通常会出现过多的零，零膨胀泊松（ZIP）模型通常用于拟合这类数据。以往对 ZIP 模型的监测方法大多侧重于位置参数的变化和规模参数的存在，通常假设规模参数在 H0 阶段为零。然而，在客观环境中，数据往往具有一定的波动性，这意味着标度参数始终存在。因此，在预定义基线的基础上监测标度参数的变化比监测其是否存在更有意义。在本研究中，我们基于广义亨德森联合似然函数推导出了一个得分检验统计量，并构建了一个风险调整指数加权移动平均（EWMA）控制图来监测 ZIP 混合效应模型中随机效应方差分量的变化。并通过推导证明了得分检验统计量的收敛性，表明新方法具有理论可靠性。仿真结果表明，当尺度参数具有不同的预定义基线和不同的变化幅度时，所提出的方法比现有的 RA-ZIP 和 PR-ZIP 控制图更有效。此外，建议的方法还应用于香港一家医院在线流感监测的真实数据，以证明其实用性。
{"title":"Control chart for detecting the scale parameter of the zero‐inflated Poisson model","authors":"Aijun Zhao, Liu Liu, Xin Lai, Ka Chun Chong","doi":"10.1002/qre.3574","DOIUrl":"https://doi.org/10.1002/qre.3574","url":null,"abstract":"When monitoring risk in public health, count data commonly exhibit an excessive number of zero, and the zero‐inflated Poisson (ZIP) model is often used to fit this type of data. Most previous methods for monitoring of the ZIP model have focused on the changes in the location parameter and the existence of the scale parameter and usually assumed that the scale parameter is zero in the <jats:italic>H</jats:italic><jats:sub>0</jats:sub> stage. However, in an objective environment, data often have certain fluctuations, meaning that the scale parameter always exists. Therefore, it is more meaningful to monitor the changes in the scale parameter on top of the predefined baseline than to monitor its existence. In this study, we derive a score test statistic based on the generalized Henderson's joint likelihood function, construct a risk‐adjusted exponentially weighted moving average (EWMA) control chart to monitor the variability of the random effects variance component in the ZIP mixed‐effects model. And the convergence property of the score test statistic is proved through derivation, which shows that the new method has theoretical reliability. The simulation results Indicate that when the scale parameter has different predefined baselines and different variation amplitudes, the proposed method is more effective than the existing RA‐ZIP and PR‐ZIP control charts. In addition, the proposed method is applied to real data from a Hong Kong hospital for online influenza surveillance to demonstrate its practicability.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"136 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140937536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, several control charts have been proposed in the statistical process monitoring literature based on a belief statistic. In this article we compare the zero‐state average run‐lengths and conditional expected delay profiles of the exponentially weighted moving average (EWMA) and belief statistic‐based (BSB) charts. We show that an ordinary EWMA chart is far better than the BSB chart when detecting delayed shifts in the mean of a normally distributed process.
{"title":"A critique on the use of the belief statistic for process monitoring","authors":"Abdul Haq, William H. Woodall","doi":"10.1002/qre.3573","DOIUrl":"https://doi.org/10.1002/qre.3573","url":null,"abstract":"Recently, several control charts have been proposed in the statistical process monitoring literature based on a belief statistic. In this article we compare the zero‐state average run‐lengths and conditional expected delay profiles of the exponentially weighted moving average (EWMA) and belief statistic‐based (BSB) charts. We show that an ordinary EWMA chart is far better than the BSB chart when detecting delayed shifts in the mean of a normally distributed process.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"162 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140889102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bo Zhang, Changhua Hu, Hao Zhang, Jianfei Zheng, Jianxun Zhang, Hong Pei
It is difficult to effectively predict remaining useful life (RUL) due to limited training samples and lack of life labels in some operating conditions of practical engineering. When existing deep learning methods predict the RUL of equipment in such operating conditions using a model trained on other operating conditions, the poor generalization of the model caused by large distribution differences cannot be ignored. In this study, an RUL prediction method based on integrated dilated convolution transfer is proposed. This method jointly adjusts the model parameters by inverting the loss function of the RUL prediction module and the domain adaptive module, and then realizes the extraction of domain‐invariant features between different operating condition data through the feature extraction module, which provides support for transfer RUL prediction between different operating conditions. In the feature extraction module, a one‐dimensional convolution network with a large‐size kernel reduces noise in the original data, which reduces the erroneous effect of noise on the trending expression of the original data, and a hybrid dilated convolution network extracts the features of the different sensory fields of the noise‐reduced data, which increases the richness of the extracted features and thus improves the accuracy of the modeling. Next, the extracted features are fed into the RUL prediction module to predict RUL; into the classification model in the domain adaptation module to divide the source and target domains; and into the distribution difference measurement model in the domain adaptation module to identify the feature distribution differences between the source and target domains, and inversely adjust the model parameters by reducing the distribution differences. Furthermore, domain invariant characteristics of the features in different receptive fields under multiple operating conditions are obtained to enhance the model's generalization ability and achieve RUL prediction across various operating conditions. Monte Carlo (MC) dropout simulation technology is used to quantify the uncertainty of prediction results. Finally, the effectiveness and superiority of the proposed method are verified using the prognostics and health management (PHM) 2012 bearing dataset.
{"title":"Remaining useful life prediction method for rolling bearings based on hybrid dilated convolution transfer","authors":"Bo Zhang, Changhua Hu, Hao Zhang, Jianfei Zheng, Jianxun Zhang, Hong Pei","doi":"10.1002/qre.3563","DOIUrl":"https://doi.org/10.1002/qre.3563","url":null,"abstract":"It is difficult to effectively predict remaining useful life (RUL) due to limited training samples and lack of life labels in some operating conditions of practical engineering. When existing deep learning methods predict the RUL of equipment in such operating conditions using a model trained on other operating conditions, the poor generalization of the model caused by large distribution differences cannot be ignored. In this study, an RUL prediction method based on integrated dilated convolution transfer is proposed. This method jointly adjusts the model parameters by inverting the loss function of the RUL prediction module and the domain adaptive module, and then realizes the extraction of domain‐invariant features between different operating condition data through the feature extraction module, which provides support for transfer RUL prediction between different operating conditions. In the feature extraction module, a one‐dimensional convolution network with a large‐size kernel reduces noise in the original data, which reduces the erroneous effect of noise on the trending expression of the original data, and a hybrid dilated convolution network extracts the features of the different sensory fields of the noise‐reduced data, which increases the richness of the extracted features and thus improves the accuracy of the modeling. Next, the extracted features are fed into the RUL prediction module to predict RUL; into the classification model in the domain adaptation module to divide the source and target domains; and into the distribution difference measurement model in the domain adaptation module to identify the feature distribution differences between the source and target domains, and inversely adjust the model parameters by reducing the distribution differences. Furthermore, domain invariant characteristics of the features in different receptive fields under multiple operating conditions are obtained to enhance the model's generalization ability and achieve RUL prediction across various operating conditions. Monte Carlo (MC) dropout simulation technology is used to quantify the uncertainty of prediction results. Finally, the effectiveness and superiority of the proposed method are verified using the prognostics and health management (PHM) 2012 bearing dataset.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"6 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140889105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper develops two novel process monitoring schemes for the mean of a Gaussian process: the Bayes factor (BF) and the improved Bayes factor (IBF) schemes. Conjugate priors are used to construct the plotting statistics. The performance of the proposed schemes is evaluated in terms of average run length (ARL), standard deviation of run length (SDRL), and several percentiles, and these performance metrics across different hyper‐parameters and various sample sizes are evaluated via Monte Carlo simulations. Both zero‐state and steady‐state out‐of‐control (OOC) performances are investigated comprehensively. The simulation results show that the IBF scheme outperforms the existing Bayesian exponentially weighted moving average (EWMA) schemes under different loss functions in zero‐state. In steady‐state conditions, the IBF scheme outperforms for small shifts. Finally, we present two examples to illustrate the practical application of the proposed schemes.
{"title":"Two Bayesian approaches of monitoring mean of Gaussian process using Bayes factor","authors":"Yaxin Tan, Amitava Mukherjee, Jiujun Zhang","doi":"10.1002/qre.3567","DOIUrl":"https://doi.org/10.1002/qre.3567","url":null,"abstract":"This paper develops two novel process monitoring schemes for the mean of a Gaussian process: the Bayes factor (BF) and the improved Bayes factor (IBF) schemes. Conjugate priors are used to construct the plotting statistics. The performance of the proposed schemes is evaluated in terms of average run length (ARL), standard deviation of run length (SDRL), and several percentiles, and these performance metrics across different hyper‐parameters and various sample sizes are evaluated via Monte Carlo simulations. Both zero‐state and steady‐state out‐of‐control (OOC) performances are investigated comprehensively. The simulation results show that the IBF scheme outperforms the existing Bayesian exponentially weighted moving average (EWMA) schemes under different loss functions in zero‐state. In steady‐state conditions, the IBF scheme outperforms for small shifts. Finally, we present two examples to illustrate the practical application of the proposed schemes.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"28 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140833849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applying evidence theory to structural reliability analysis under epistemic uncertainty, it is necessary to consider the correlation of evidence variables. Among them, solving the joint basic probability assignment (BPA) of the evidence variables is a crucial link. In this study, a solution method of joint BPA based on neural network copula function is proposed. This method is to automatically construct copula function through neural network, which avoids the process of selecting the optimal copula function. Firstly, the neural network copula function is constructed based on the sample set of evidence variables. Then, the expression for solving the joint BPA using the neural network copula function is derived through vectors. Furthermore, the expression is used to map the marginal BPA of evidence variables to joint BPA, thus realizing the solution of joint BPA. Finally, the effectiveness of this method is verified by three examples. The results show that the neural network copula function describes the data distribution better than the optimal copula function selected by the traditional method. In addition, there is actually an error in solving the reliability intervals using the traditional optimal copula function method, whereas the results of this paper's neural network copula function method are more accurate and better for decision making.
{"title":"A neural network copula function approach for solving joint basic probability assignment in structural reliability analysis","authors":"Rui‐Shi Yang, Li‐Jun Sun, Hai‐Bin Li, Yong Yang","doi":"10.1002/qre.3568","DOIUrl":"https://doi.org/10.1002/qre.3568","url":null,"abstract":"Applying evidence theory to structural reliability analysis under epistemic uncertainty, it is necessary to consider the correlation of evidence variables. Among them, solving the joint basic probability assignment (BPA) of the evidence variables is a crucial link. In this study, a solution method of joint BPA based on neural network copula function is proposed. This method is to automatically construct copula function through neural network, which avoids the process of selecting the optimal copula function. Firstly, the neural network copula function is constructed based on the sample set of evidence variables. Then, the expression for solving the joint BPA using the neural network copula function is derived through vectors. Furthermore, the expression is used to map the marginal BPA of evidence variables to joint BPA, thus realizing the solution of joint BPA. Finally, the effectiveness of this method is verified by three examples. The results show that the neural network copula function describes the data distribution better than the optimal copula function selected by the traditional method. In addition, there is actually an error in solving the reliability intervals using the traditional optimal copula function method, whereas the results of this paper's neural network copula function method are more accurate and better for decision making.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"10 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140833784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mixed shock model is an explicit construction method of failure probability model based on component independent failure, system nonfatal shock, and fatal shock failure, which considers common cause failure (CCF) in redundant system. For aerospace systems, a modified mixed shock model is proposed, which considers several components may fail independently and simultaneously in operation. In order to solve the issue that the parameters of the mixed shock model cannot be solved directly based on the failure probability data, a parameter solving method based on particle swarm optimization (PSO) algorithm is proposed. Additionally, the relationship between the failure probability and the gradient of the parameter change is deduced, and the reduced‐order (RO) solution based on the gradient of the parameter change is proposed to improve the efficiency of the solution. A fitness function construction method based on the relative error of the solution probability and the true probability is proposed to improve the probability solution accuracy of multicomponent failure. The nonlinear inertia factor optimization method combined with fitness change is studied to improve the particle swarm dynamics. The accuracy of the results of different parameters solving sequence and different PSO methods are compared, and the effectiveness of the RO solution is verified. The results of the mixed shock model before and after modification are compared with the different CCF data, which verifies the effectiveness and wide applicability of the modified mixed shock model. The results show that the modified mixed shock model for CCF and its parameter solution method can significantly improve the probability solution accuracy of all components failure, and also provide a new theoretical basis and solution method for the quantitative analysis of multiredundant system failure.
{"title":"Research and verification on parameter solution of mixed shock model for common cause failure based on particle swarm algorithm","authors":"Yinxiao Hu, Hongjuan Ge, Pei He, Hui Jin, Huang Li, Chunran Zou","doi":"10.1002/qre.3569","DOIUrl":"https://doi.org/10.1002/qre.3569","url":null,"abstract":"Mixed shock model is an explicit construction method of failure probability model based on component independent failure, system nonfatal shock, and fatal shock failure, which considers common cause failure (CCF) in redundant system. For aerospace systems, a modified mixed shock model is proposed, which considers several components may fail independently and simultaneously in operation. In order to solve the issue that the parameters of the mixed shock model cannot be solved directly based on the failure probability data, a parameter solving method based on particle swarm optimization (PSO) algorithm is proposed. Additionally, the relationship between the failure probability and the gradient of the parameter change is deduced, and the reduced‐order (RO) solution based on the gradient of the parameter change is proposed to improve the efficiency of the solution. A fitness function construction method based on the relative error of the solution probability and the true probability is proposed to improve the probability solution accuracy of multicomponent failure. The nonlinear inertia factor optimization method combined with fitness change is studied to improve the particle swarm dynamics. The accuracy of the results of different parameters solving sequence and different PSO methods are compared, and the effectiveness of the RO solution is verified. The results of the mixed shock model before and after modification are compared with the different CCF data, which verifies the effectiveness and wide applicability of the modified mixed shock model. The results show that the modified mixed shock model for CCF and its parameter solution method can significantly improve the probability solution accuracy of all components failure, and also provide a new theoretical basis and solution method for the quantitative analysis of multiredundant system failure.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"60 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140833725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：