Cyber‐Physical Systems (CPS) are at the forefront of the intersection between information technology and physical operations, revolutionizing industries such as communication, automation, control, and intelligent transportation. However, evaluating the reliability of CPS, especially in the presence of multilateral random attacks, poses a complex challenge. This paper introduces an inventive probabilistic modeling approach to enhance the analysis of CPS reliability under the influence of multilateral random attacks. We provide an overview of fundamental CPS concepts and their significant role in modern society, followed by a comprehensive exploration of multilateral random attacks. Our novel probabilistic modeling approach is presented as a means to improve the accuracy and robustness of CPS reliability assessments when faced with multilateral random attacks. Numerical experiments and simulations validate the effectiveness of our innovative approach, emphasizing its potential to fortify the reliability of Cyber‐Physical Systems.
{"title":"A novel probabilistic modeling for multilateral random attacks in cyber‐physical system reliability analysis","authors":"Jiayue Huang, Jianfeng Yang, Zhoutao Zheng, Zhengxia Qiu","doi":"10.1002/qre.3533","DOIUrl":"https://doi.org/10.1002/qre.3533","url":null,"abstract":"Cyber‐Physical Systems (CPS) are at the forefront of the intersection between information technology and physical operations, revolutionizing industries such as communication, automation, control, and intelligent transportation. However, evaluating the reliability of CPS, especially in the presence of multilateral random attacks, poses a complex challenge. This paper introduces an inventive probabilistic modeling approach to enhance the analysis of CPS reliability under the influence of multilateral random attacks. We provide an overview of fundamental CPS concepts and their significant role in modern society, followed by a comprehensive exploration of multilateral random attacks. Our novel probabilistic modeling approach is presented as a means to improve the accuracy and robustness of CPS reliability assessments when faced with multilateral random attacks. Numerical experiments and simulations validate the effectiveness of our innovative approach, emphasizing its potential to fortify the reliability of Cyber‐Physical Systems.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"21 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140198286","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}
Rongqiao Wang, Weihan Kong, Guanjie Cao, Xi Liu, Jianxing Mao, Haihe Sun, Dianyin Hu
In this research, A zone‐based failure risk assessment (FRA) method of fatigue crack growth (FCG) caused by initial defects in the FGH96 alloy turbine disc is developed. Firstly, the initial defects distribution in the FGH96 alloy turbine disc is calculated based on the defect data. Subsequently, a probabilistic short FCG life model is established, taking into account the dispersion in grain size. Meanwhile, a probabilistic long FCG life model is established, incorporating the life dispersion factor. To calculate the Stress Intensity Factor (SIF) at any position of the disc, the general weight function method and the rectangular plate model are established. Finally, the zoning process is established, enabling a FRA that considers the FCG due to initial defects. The results indicate that the number of cycles corresponding to a 0.13% failure probability of the turbine disc is 7150, and the percentage of failures in each zone is analyzed.
{"title":"Zone‐based failure risk assessment of fatigue crack growth caused by initial defects in powder turbine disc","authors":"Rongqiao Wang, Weihan Kong, Guanjie Cao, Xi Liu, Jianxing Mao, Haihe Sun, Dianyin Hu","doi":"10.1002/qre.3542","DOIUrl":"https://doi.org/10.1002/qre.3542","url":null,"abstract":"In this research, A zone‐based failure risk assessment (FRA) method of fatigue crack growth (FCG) caused by initial defects in the FGH96 alloy turbine disc is developed. Firstly, the initial defects distribution in the FGH96 alloy turbine disc is calculated based on the defect data. Subsequently, a probabilistic short FCG life model is established, taking into account the dispersion in grain size. Meanwhile, a probabilistic long FCG life model is established, incorporating the life dispersion factor. To calculate the Stress Intensity Factor (SIF) at any position of the disc, the general weight function method and the rectangular plate model are established. Finally, the zoning process is established, enabling a FRA that considers the FCG due to initial defects. The results indicate that the number of cycles corresponding to a 0.13% failure probability of the turbine disc is 7150, and the percentage of failures in each zone is analyzed.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"30 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140198232","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}
Due to the noise interference and the weak characterization ability of the fault vibration signal of rotation vector (RV) reducer crankshaft bearing, it is difficult to obtain satisfactory results for the available fault diagnosis methods. For that, this paper proposes a variable-speed-condition fault diagnosis method with WSO-VMD and ResNet-SWIN. A signal reconstruction method with WSO-VMD was carried out, Firstly, the performance of VMD algorithm is improved by using war strategy optimization algorithm to select parameters adaptively. Then the signal is reconstructed considering the fault characteristic frequency, so as to realize the noise reduction of the signal. By using the residual network module and attention mechanism to replace the first stage of the original SWIN model, a novel ResNet-SWIN fault diagnosis model is established to enhance the feature extraction ability for the weak signal. The experiments with the constant-operating-condition and the variable-operating-condition are carried out to verify the effectiveness of the proposed method. The results show that, whether at variable-speed or constant-speed conditions, WSO algorithm has been proven to be the fastest convergence speed compared with WOA, SSA, and NGO optimization algorithms, and by the signal reconstruction with WSO-VMD, the variance evaluation indicator of the reconstructed signal has 36%, 21%, 46%, and 40%, respectively. ResNet-SWIN model has achieved the optimal diagnosis accuracy compared with SWIN, VIT, and CNN-SVM models in both variable-speed and constant-speed conditions.
{"title":"A variable-speed-condition fault diagnosis method for crankshaft bearing in the RV reducer with WSO-VMD and ResNet-SWIN","authors":"Guangqi Qiu, Yu Nie, Yulong Peng, Peng Huang, Junjie Chen, Yingkui Gu","doi":"10.1002/qre.3538","DOIUrl":"https://doi.org/10.1002/qre.3538","url":null,"abstract":"Due to the noise interference and the weak characterization ability of the fault vibration signal of rotation vector (RV) reducer crankshaft bearing, it is difficult to obtain satisfactory results for the available fault diagnosis methods. For that, this paper proposes a variable-speed-condition fault diagnosis method with WSO-VMD and ResNet-SWIN. A signal reconstruction method with WSO-VMD was carried out, Firstly, the performance of VMD algorithm is improved by using war strategy optimization algorithm to select parameters adaptively. Then the signal is reconstructed considering the fault characteristic frequency, so as to realize the noise reduction of the signal. By using the residual network module and attention mechanism to replace the first stage of the original SWIN model, a novel ResNet-SWIN fault diagnosis model is established to enhance the feature extraction ability for the weak signal. The experiments with the constant-operating-condition and the variable-operating-condition are carried out to verify the effectiveness of the proposed method. The results show that, whether at variable-speed or constant-speed conditions, WSO algorithm has been proven to be the fastest convergence speed compared with WOA, SSA, and NGO optimization algorithms, and by the signal reconstruction with WSO-VMD, the variance evaluation indicator of the reconstructed signal has 36%, 21%, 46%, and 40%, respectively. ResNet-SWIN model has achieved the optimal diagnosis accuracy compared with SWIN, VIT, and CNN-SVM models in both variable-speed and constant-speed conditions.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"65 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140182312","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}
Ke Wang, Hua‐Ming Qian, Jinhua Mi, Tianlong Xu, Hong‐Zhong Huang
This study delves into the factors that affect the reliability of satellite antenna deployment mechanisms. It employs the Kolmogorov–Smirnov (K‐S) test to quantify uncertainty characteristics, leading to the acquisition of pertinent stochastic parameters. Subsequently, three‐dimensional models and finite element models of the satellite antenna deployment mechanism are established using SOLIDWORKS and ANSYS software. Modal distribution, harmonic response analysis, random vibration analysis, and deployment process simulation are conducted. Parameterized modeling of the deployment mechanism's dynamics simulation process is performed, taking into consideration parameter uncertainty. Finally, a Kriging surrogate model is utilized to formulate an approximate expression between the factors influencing the reliability of the antenna deployment mechanism and its dynamic response. Based on the general stress‐strength interference theory, a reliability analysis model is constructed. Combined with active learning algorithms, this approach achieves efficient and precise calculations of the reliability of the satellite antenna deployment mechanism.
{"title":"Dynamic modeling and reliability analysis of satellite antenna deployment mechanism based on parameter uncertainty","authors":"Ke Wang, Hua‐Ming Qian, Jinhua Mi, Tianlong Xu, Hong‐Zhong Huang","doi":"10.1002/qre.3534","DOIUrl":"https://doi.org/10.1002/qre.3534","url":null,"abstract":"This study delves into the factors that affect the reliability of satellite antenna deployment mechanisms. It employs the Kolmogorov–Smirnov (K‐S) test to quantify uncertainty characteristics, leading to the acquisition of pertinent stochastic parameters. Subsequently, three‐dimensional models and finite element models of the satellite antenna deployment mechanism are established using SOLIDWORKS and ANSYS software. Modal distribution, harmonic response analysis, random vibration analysis, and deployment process simulation are conducted. Parameterized modeling of the deployment mechanism's dynamics simulation process is performed, taking into consideration parameter uncertainty. Finally, a Kriging surrogate model is utilized to formulate an approximate expression between the factors influencing the reliability of the antenna deployment mechanism and its dynamic response. Based on the general stress‐strength interference theory, a reliability analysis model is constructed. Combined with active learning algorithms, this approach achieves efficient and precise calculations of the reliability of the satellite antenna deployment mechanism.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"51 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140165770","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 study develops a Bayesian method to analyze optimal burn-in policy for heterogeneous components with minimal repair. We use the non-homogeneous Poisson processes with different power law intensity functions to model the minimal repair processes for heterogeneous components. Since the component from the weak subpopulation may fail more frequently, the total number of minimal repairs can be used for establishing a screening rule. By screening, we can decide whether the component after burn-in should be eliminated or not. Considering the uncertainty of model parameters, we generate a minimally repaired data set of components by simulation. Then, we obtain the model parameters estimators by using Bayesian method combined with the existing data. We further analyze and get the optimal burn-in settings under cost and performance optimization model. A numerical example is used to verify the effectiveness of the Bayesian method.
{"title":"Bayesian analysis of optimal burn-in policy for heterogeneous components with minimal repair","authors":"Xiaoliang Ling, Ruijie Yin, Ping Li","doi":"10.1002/qre.3535","DOIUrl":"https://doi.org/10.1002/qre.3535","url":null,"abstract":"This study develops a Bayesian method to analyze optimal burn-in policy for heterogeneous components with minimal repair. We use the non-homogeneous Poisson processes with different power law intensity functions to model the minimal repair processes for heterogeneous components. Since the component from the weak subpopulation may fail more frequently, the total number of minimal repairs can be used for establishing a screening rule. By screening, we can decide whether the component after burn-in should be eliminated or not. Considering the uncertainty of model parameters, we generate a minimally repaired data set of components by simulation. Then, we obtain the model parameters estimators by using Bayesian method combined with the existing data. We further analyze and get the optimal burn-in settings under cost and performance optimization model. A numerical example is used to verify the effectiveness of the Bayesian method.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"84 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140198323","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 two dependent competing risks are soft failure due to aging degradation and fragmentation caused by shocks and hard failure due to spring breakage caused by the same shock process. Considering the complexity of the product itself and the instability of the working environment, this study proposed a generalized reliability model for systems experiencing dependent competing failure processes (DCFPs) of degradation and random shocks, which considered two kinds of DCFP: (1) shock process could affect soft failure thresholds; (2) degradation process could affect hard failure thresholds. In case (1), we considered the effect that a cumulative number of shocks above a certain magnitude could have on the change in the soft failure threshold. In case (2), we considered not only the shock process's impact on the soft failure threshold but also the total degradation (including continuous degradation and sudden degradation caused by shock) on the hard failure threshold. The model captures the features that the shocks experienced by the system affect the degradation process, accelerating the system degradation and causing soft failures; the degradation process of the system affects the shock process, making the system more susceptible to failure from external shocks. Finally, an example using micro‐electro‐mechanical systems devices illustrates the effectiveness of the proposed approach with sensitivity analysis.
{"title":"Reliability assessment models for competing failure processes with two types of correlative thresholds","authors":"Qingbiao Song, Jiayin Tang, Honglei Wei, Yong Li","doi":"10.1002/qre.3529","DOIUrl":"https://doi.org/10.1002/qre.3529","url":null,"abstract":"The two dependent competing risks are soft failure due to aging degradation and fragmentation caused by shocks and hard failure due to spring breakage caused by the same shock process. Considering the complexity of the product itself and the instability of the working environment, this study proposed a generalized reliability model for systems experiencing dependent competing failure processes (DCFPs) of degradation and random shocks, which considered two kinds of DCFP: (1) shock process could affect soft failure thresholds; (2) degradation process could affect hard failure thresholds. In case (1), we considered the effect that a cumulative number of shocks above a certain magnitude could have on the change in the soft failure threshold. In case (2), we considered not only the shock process's impact on the soft failure threshold but also the total degradation (including continuous degradation and sudden degradation caused by shock) on the hard failure threshold. The model captures the features that the shocks experienced by the system affect the degradation process, accelerating the system degradation and causing soft failures; the degradation process of the system affects the shock process, making the system more susceptible to failure from external shocks. Finally, an example using micro‐electro‐mechanical systems devices illustrates the effectiveness of the proposed approach with sensitivity analysis.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"150 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140170019","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}
Yan Ran, Jingjie Chen, Nafis Jawyad Sagor, Genbao Zhang
Highly reliable mechanical systems can lead to significant losses in the event of failure, and the lack of comprehensive failure data presents challenges for developing techniques such as critical part identification and failure prediction. In light of this, this paper proposes a meta-action-based fault prediction method that effectively addresses the issue of limited fault data. Initially, the mechanical system is decomposed utilizing the “Function-Motion-Action” (FMA) methodology to derive individual meta-action units (MAUs). Subsequently, the limited sample of fault data from the mechanical system is combined with processed expert knowledge to construct the corresponding fault propagation-directed graph. Furthermore, the key MAUs are determined by applying the Decision–Making Trial and Evaluation Laboratory (DEMATEL) method. Last, the degradation data of the key MAUs is acquired by monitoring them, and a non-homogeneous discrete grey model (DNGM) integrated with an improved BP neural network is proposed to facilitate the fault prediction of MAUs. Using an industrial robot as a case study, the prediction results demonstrate the superiority of the method proposed in this paper over a single gray model and neural network, thereby providing a reliable prediction approach for anticipating the future trends of data-deficient mechanical systems.
高可靠性的机械系统一旦发生故障就会造成重大损失，而缺乏全面的故障数据给关键部件识别和故障预测等技术的开发带来了挑战。有鉴于此，本文提出了一种基于元动作的故障预测方法，可有效解决故障数据有限的问题。首先，利用 "功能-运动-动作"（FMA）方法对机械系统进行分解，从而得出各个元动作单元（MAU）。随后，将来自机械系统的有限故障数据样本与经过处理的专家知识相结合，构建相应的故障传播导向图。此外，通过应用决策试验和评估实验室（DEMATEL）方法确定关键 MAU。最后，通过监测关键 MAU 获取其退化数据，并提出了一种与改进型 BP 神经网络相结合的非均质离散灰色模型（DNGM），以促进 MAU 的故障预测。以工业机器人为例，预测结果表明本文提出的方法优于单一灰色模型和神经网络，从而为预测缺乏数据的机械系统的未来趋势提供了一种可靠的预测方法。
{"title":"Failure prediction of mechanical system based on meta-action","authors":"Yan Ran, Jingjie Chen, Nafis Jawyad Sagor, Genbao Zhang","doi":"10.1002/qre.3537","DOIUrl":"https://doi.org/10.1002/qre.3537","url":null,"abstract":"Highly reliable mechanical systems can lead to significant losses in the event of failure, and the lack of comprehensive failure data presents challenges for developing techniques such as critical part identification and failure prediction. In light of this, this paper proposes a meta-action-based fault prediction method that effectively addresses the issue of limited fault data. Initially, the mechanical system is decomposed utilizing the “Function-Motion-Action” (FMA) methodology to derive individual meta-action units (MAUs). Subsequently, the limited sample of fault data from the mechanical system is combined with processed expert knowledge to construct the corresponding fault propagation-directed graph. Furthermore, the key MAUs are determined by applying the Decision–Making Trial and Evaluation Laboratory (DEMATEL) method. Last, the degradation data of the key MAUs is acquired by monitoring them, and a non-homogeneous discrete grey model (DNGM) integrated with an improved BP neural network is proposed to facilitate the fault prediction of MAUs. Using an industrial robot as a case study, the prediction results demonstrate the superiority of the method proposed in this paper over a single gray model and neural network, thereby providing a reliable prediction approach for anticipating the future trends of data-deficient mechanical systems.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"45 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140182313","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}
Akilu Yunusa‐Kaltungo, Srija Ray, Shaikha AlSanad, Idowu Sokunbi, Patrick Manu, Clara Man Cheung, Saeed Reza Mohandes
Maintenance activities are used to sustain the reliability of physical industrial assets. However, studies indicate that some of the most devastating industrial accidents are attributable to poor safety perceptions of maintenance workers, especially during major overhauls, outages, shutdowns or turnarounds (MoOSTs). Typical MoOSTs involve the harmonisation of regular maintenance endeavours on a large scale, which in turn heighten risks of accidents and costs. Furthermore, MoOSTs are performed over short durations thereby necessitating parallel high‐risk activities by different organisations that have different perceptions of safety and possess different safety cultures. Understanding safety climate can immensely benefit MoOSTs organisations by improving the understanding of attitudes and perceptions that alleviate workplace incidents. This study aimed to establish safety climate that would boost safety culture and positively impact perceived safety performance during MoOSTs. Safety climate questionnaire survey was deployed to MoOSTs workers of leading cement plants in Nigeria. Through exploratory factor analysis, three underlying safety climate factors were identified, which helped to determine that factors such as ‛training and learning from incidents’, ‛commitment of senior management towards ensuring safety and its protocol development process’ and ‛effectiveness of incident reporting systems during MoOSTs’ were significant predictors of workers’ perceptions of safety performance. The findings also pointed out that the inter‐relationship between perceived safety performance, MoOSTs safety training and organisational commitment were positively correlated.
{"title":"Assessment of safety climate perception of maintenance workers during major overhauls, outages, shutdowns or turnarounds (MoOSTs)","authors":"Akilu Yunusa‐Kaltungo, Srija Ray, Shaikha AlSanad, Idowu Sokunbi, Patrick Manu, Clara Man Cheung, Saeed Reza Mohandes","doi":"10.1002/qre.3532","DOIUrl":"https://doi.org/10.1002/qre.3532","url":null,"abstract":"Maintenance activities are used to sustain the reliability of physical industrial assets. However, studies indicate that some of the most devastating industrial accidents are attributable to poor safety perceptions of maintenance workers, especially during major overhauls, outages, shutdowns or turnarounds (MoOSTs). Typical MoOSTs involve the harmonisation of regular maintenance endeavours on a large scale, which in turn heighten risks of accidents and costs. Furthermore, MoOSTs are performed over short durations thereby necessitating parallel high‐risk activities by different organisations that have different perceptions of safety and possess different safety cultures. Understanding safety climate can immensely benefit MoOSTs organisations by improving the understanding of attitudes and perceptions that alleviate workplace incidents. This study aimed to establish safety climate that would boost safety culture and positively impact perceived safety performance during MoOSTs. Safety climate questionnaire survey was deployed to MoOSTs workers of leading cement plants in Nigeria. Through exploratory factor analysis, three underlying safety climate factors were identified, which helped to determine that factors such as ‛training and learning from incidents’, ‛commitment of senior management towards ensuring safety and its protocol development process’ and ‛effectiveness of incident reporting systems during MoOSTs’ were significant predictors of workers’ perceptions of safety performance. The findings also pointed out that the inter‐relationship between perceived safety performance, MoOSTs safety training and organisational commitment were positively correlated.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"27 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140169884","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}
Web service composition (WSC), a distributed architecture, creates new services atop existing ones. Ensuring trust and assessing performance and dependability in online services coordination is essential. In this paper, “Web Service Reliability and Scalability Determination Using Depth Wise Separable Convolutional Neural Network” (WSRS‐DWSCNN) is proposed to assess the trustworthiness of online service compositions, particularly focusing on performance and dependability. This work addresses the need to predict the reliability and scalability of Business Process Execution Language (BPEL) composite web services. The proposed approach transforms the BPEL specification into a Depth Wise Separable Convolutional Neural Network (DWSCNN) and annotates it with probabilistic properties for prediction. The DWSCNN model classifies the outcomes as correct or incorrect, and to enhances the prediction of web service composition scalability and reliability, we optimize the DWSCNN's weight parameters using the Adolescent Identity Search Algorithm (AISA). The proposed technique is activated in Python and its efficacy is analyzed under some metrics, such as reliability, scalability, accuracy, sensitivity, specificity, precision, F‐measure. The proposed method provides 12.36%, 45.39%, and 25.97% better reliability, 41.39%, 11.39%, 34.16% better accuracy compared with existing methods like, Web service reliability prediction depending on machine learning (WSRS‐K‐means), reliability prediction method for multiple state cloud/edge‐basis network utilizing deep neural network (WSRS‐DNN‐BO), and improving reliability of mobile social cloud computing utilizing machine learning in content addressable network (WSRS‐CAN), respectively.
{"title":"Web service reliability and scalability determination using optimized depth wise separable convolutional neural network","authors":"Gokulakrishnan Dhakshnamoorthy, Jeyabal Sridhar, Ramakrishnan Ramanathan, Muruga Radha Devi Dharmalingam","doi":"10.1002/qre.3530","DOIUrl":"https://doi.org/10.1002/qre.3530","url":null,"abstract":"Web service composition (WSC), a distributed architecture, creates new services atop existing ones. Ensuring trust and assessing performance and dependability in online services coordination is essential. In this paper, “Web Service Reliability and Scalability Determination Using Depth Wise Separable Convolutional Neural Network” (WSRS‐DWSCNN) is proposed to assess the trustworthiness of online service compositions, particularly focusing on performance and dependability. This work addresses the need to predict the reliability and scalability of Business Process Execution Language (BPEL) composite web services. The proposed approach transforms the BPEL specification into a Depth Wise Separable Convolutional Neural Network (DWSCNN) and annotates it with probabilistic properties for prediction. The DWSCNN model classifies the outcomes as correct or incorrect, and to enhances the prediction of web service composition scalability and reliability, we optimize the DWSCNN's weight parameters using the Adolescent Identity Search Algorithm (AISA). The proposed technique is activated in Python and its efficacy is analyzed under some metrics, such as reliability, scalability, accuracy, sensitivity, specificity, precision, F‐measure. The proposed method provides 12.36%, 45.39%, and 25.97% better reliability, 41.39%, 11.39%, 34.16% better accuracy compared with existing methods like, Web service reliability prediction depending on machine learning (WSRS‐K‐means), reliability prediction method for multiple state cloud/edge‐basis network utilizing deep neural network (WSRS‐DNN‐BO), and improving reliability of mobile social cloud computing utilizing machine learning in content addressable network (WSRS‐CAN), respectively.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"22 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140155234","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}
Bearings are foundational supporting components in diverse mechanical systems, essential for the reliable operation of these systems through real‐time monitoring and precise health state assessment. However, vibration signals from bearings in practical equipment often contain excessive noise and redundant information, complicating health state assessment. To address this challenge, this paper proposes a neural network‐based method named parallel encoder‐decoder (PED). This method features a parallel architecture that combines the long short‐term memory network and the temporal convolutional network for the encoder, along with a self‐attention module for the decoder. PED is adept at learning the temporal representations hidden in original signals and filtering vibration signals to remove noise and redundant information. Additionally, a multi‐objective loss function is developed to enhance the prediction results. A normalized Mahalanobis distance‐based metric is then employed to compare residual signals during bearing operation with those under normal conditions. The case study evaluates the PED observer's proficiency in accurately predicting vibration signals and assessing the performance of health indicator curves, demonstrating the proposed PED observer's superiority over conventional networks.
{"title":"Real‐time assessment on health state for bearing based on parallel encoder‐decoder observer","authors":"Kunpeng Li, Jinhua Mi, Zhiguo Wang, Shengjie Yin, Libing Bai, Gen Qiu","doi":"10.1002/qre.3531","DOIUrl":"https://doi.org/10.1002/qre.3531","url":null,"abstract":"Bearings are foundational supporting components in diverse mechanical systems, essential for the reliable operation of these systems through real‐time monitoring and precise health state assessment. However, vibration signals from bearings in practical equipment often contain excessive noise and redundant information, complicating health state assessment. To address this challenge, this paper proposes a neural network‐based method named parallel encoder‐decoder (PED). This method features a parallel architecture that combines the long short‐term memory network and the temporal convolutional network for the encoder, along with a self‐attention module for the decoder. PED is adept at learning the temporal representations hidden in original signals and filtering vibration signals to remove noise and redundant information. Additionally, a multi‐objective loss function is developed to enhance the prediction results. A normalized Mahalanobis distance‐based metric is then employed to compare residual signals during bearing operation with those under normal conditions. The case study evaluates the PED observer's proficiency in accurately predicting vibration signals and assessing the performance of health indicator curves, demonstrating the proposed PED observer's superiority over conventional networks.","PeriodicalId":56088,"journal":{"name":"Quality and Reliability Engineering International","volume":"85 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140155135","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：