Health management permits the reliability of a system and plays a increasingly important role for achieving efficient system-level maintenance.It has been used for remaining useful life（RUL） prognostics of electroni...Health management permits the reliability of a system and plays a increasingly important role for achieving efficient system-level maintenance.It has been used for remaining useful life（RUL） prognostics of electronics-rich system including avionics.Prognostics and health management（PHM） have become highly desirable to provide avionics with system level health management.This paper presents a health management and fusion prognostic model for avionics system,combining three baseline prognostic approaches that are model-based,data-driven and knowledge-based approaches,and integrates merits as well as eliminates some limitations of each single approach to achieve fusion prognostics and improved prognostic performance of RUL estimation.A fusion model built upon an optimal linear combination forecast model is then utilized to fuse single prognostic algorithm representing the three baseline approaches correspondingly,and the presented case study shows that the fusion prognostics can provide RUL estimation more accurate and more robust than either algorithm alone.展开更多
Fault degradation prognostic, which estimates the time before a failure occurs and process breakdowns, has been recognized as a key component in maintenance strategies nowadays. Fault degradation processes are, in gen...Fault degradation prognostic, which estimates the time before a failure occurs and process breakdowns, has been recognized as a key component in maintenance strategies nowadays. Fault degradation processes are, in general,slowly varying and can be modeled by autoregressive models. However, industrial processes always show typical nonstationary nature, which may bring two challenges: how to capture fault degradation information and how to model nonstationary processes. To address the critical issues, a novel fault degradation modeling and online fault prognostic strategy is developed in this paper. First, a fault degradation-oriented slow feature analysis(FDSFA) algorithm is proposed to extract fault degradation directions along which candidate fault degradation features are extracted. The trend ability assessment is then applied to select major fault degradation features. Second, a key fault degradation factor(KFDF) is calculated to characterize the fault degradation tendency by combining major fault degradation features and their stability weighting factors. After that, a time-varying regression model with temporal smoothness regularization is established considering nonstationary characteristics. On the basis of updating strategy, an online fault prognostic model is further developed by analyzing and modeling the prediction errors. The performance of the proposed method is illustrated with a real industrial process.展开更多
Implementing an efficient real-time prognostics and health management (PHM) framework improves safety and reduces maintenance costs in complex engineering systems.However, research on PHM framework development for rad...Implementing an efficient real-time prognostics and health management (PHM) framework improves safety and reduces maintenance costs in complex engineering systems.However, research on PHM framework development for radar systems is limited. Furthermore, typical PHM approaches are centralized, do not scale well, and are challenging to implement.This paper proposes an integrated PHM framework for radar systems based on system structural decomposition to enhance reliability and support maintenance actions. The complexity challenge associated with implementing PHM at the system level is addressed by dividing the radar system into subsystems. Subsequently, optimal measurement point selection and sensor placement algorithms are formulated for effective data acquisition. Local modules are developed for each subsystem health assessment, fault diagnosis, and fault prediction without a centralized controller. Maintenance decisions are based on each local module’s fault diagnosis and prediction results. To further improve the effectiveness of the prognostics stage, the feasibility of integrating deep learning (DL) models is also investigated.Several experiments with different degradation patterns are performed to evaluate the effectiveness of the framework’s DLbased prognostics model. The proposed framework facilitates transitioning from traditional reactive maintenance practices to a predictive maintenance approach, thereby reducing downtime and improving the overall availability of radar systems.展开更多
Objective:Albumin-globulin ratio(AGR),prognostic nutritional index(PNI),and platelet to-lymphocyte ratio(PLR)have been validated as prognostic factors for gastric cancer(GC).However,significant gender differences exis...Objective:Albumin-globulin ratio(AGR),prognostic nutritional index(PNI),and platelet to-lymphocyte ratio(PLR)have been validated as prognostic factors for gastric cancer(GC).However,significant gender differences exist in albumin levels and inflammatory cell counts,and further research is required to understand how these differences influence GC prognosis.This study aims to investigate the prognostic impact of nutritional and inflammatory indicators on GC patients undergoing radical surgery,as well as the influence of gender on these indicators’prognostic value.Methods:The study included 596 patients with advanced GC hospitalized in the Department of Gastrointestinal Surgery,General Surgery,Xiangya Hospital of Central South University from January 2012 to December 2016.Receiver operating characteristic(ROC)analysis was performed to determine cutoff values for nutritional and inflammatory factors.Univariate analysis was used to identify factors significantly affecting survival in GC patients,while multivariate and Kaplan-Meier analyses determined independent prognostic factors for GC.Results:Multivariate analysis revealed that postsurgical tumor node metastasis(pTNM)stage[stage II:hazard ratio(HR)=3.284,P=0.012;stage III:HR:8.062,P<0.001],low preoperative AGR(HR=1.499,P=0.012),and postoperative PNI(HR=1.503,P=0.008)were risk factors for overall survival in male patients after radical GC surgery.For female patients,pN2-3(HR=3.185,P<0.001),total gastrectomy(HR=2.286,P=0.004),low preoperative PLR(HR=1.702,P=0.027),and postoperative PNI(HR=1.943,P=0.011)were identified as risk factors for overall survival.Conclusion:Postoperative PNI is an independent risk factor for all advanced GC patients.Preoperative PLR is an independent prognostic factor only for female patients,while preoperative AGR is an independent prognostic factor only for male patients.Further research is warranted to investigate the gender-specific differences in GC prognosis.展开更多
Objective Triple-negative breast cancer(TNBC)is the breast cancer subtype with the worst prognosis,and lacks effective therapeutic targets.Colony stimulating factors(CSFs)are cytokines that can regulate the production...Objective Triple-negative breast cancer(TNBC)is the breast cancer subtype with the worst prognosis,and lacks effective therapeutic targets.Colony stimulating factors(CSFs)are cytokines that can regulate the production of blood cells and stimulate the growth and development of immune cells,playing an important role in the malignant progression of TNBC.This article aims to construct a novel prognostic model based on the expression of colony stimulating factors-related genes(CRGs),and analyze the sensitivity of TNBC patients to immunotherapy and drug therapy.Methods We downloaded CRGs from public databases and screened for differentially expressed CRGs between normal and TNBC tissues in the TCGA-BRCA database.Through LASSO Cox regression analysis,we constructed a prognostic model and stratified TNBC patients into high-risk and low-risk groups based on the colony stimulating factors-related genes risk score(CRRS).We further analyzed the correlation between CRRS and patient prognosis,clinical features,tumor microenvironment(TME)in both high-risk and low-risk groups,and evaluated the relationship between CRRS and sensitivity to immunotherapy and drug therapy.Results We identified 842 differentially expressed CRGs in breast cancer tissues of TNBC patients and selected 13 CRGs for constructing the prognostic model.Kaplan-Meier survival curves,time-dependent receiver operating characteristic curves,and other analyses confirmed that TNBC patients with high CRRS had shorter overall survival,and the predictive ability of CRRS prognostic model was further validated using the GEO dataset.Nomogram combining clinical features confirmed that CRRS was an independent factor for the prognosis of TNBC patients.Moreover,patients in the high-risk group had lower levels of immune infiltration in the TME and were sensitive to chemotherapeutic drugs such as 5-fluorouracil,ipatasertib,and paclitaxel.Conclusion We have developed a CRRS-based prognostic model composed of 13 differentially expressed CRGs,which may serve as a useful tool for predicting the prognosis of TNBC patients and guiding clinical treatment.Moreover,the key genes within this model may represent potential molecular targets for future therapies of TNBC.展开更多
以BIM(Building Information Modeling)、物联网、云计算等为代表的新一代信息技术与传统行业的不断融合促使智慧桥梁应运而生。本文分析了智慧桥梁理念的内涵,阐述了智慧桥梁的总体架构,将智慧桥梁划分为智慧设计、智慧建造和智慧管养...以BIM(Building Information Modeling)、物联网、云计算等为代表的新一代信息技术与传统行业的不断融合促使智慧桥梁应运而生。本文分析了智慧桥梁理念的内涵,阐述了智慧桥梁的总体架构,将智慧桥梁划分为智慧设计、智慧建造和智慧管养三个阶段,研究了不同阶段的主要功能及关键技术,指出了智慧桥梁是智慧产业在桥梁工程领域发展的必然结果。展开更多
As the central component of rotating machine,the performance reliability assessment and remaining useful lifetime prediction of bearing are of crucial importance in condition-based maintenance to reduce the maintenanc...As the central component of rotating machine,the performance reliability assessment and remaining useful lifetime prediction of bearing are of crucial importance in condition-based maintenance to reduce the maintenance cost and improve the reliability.A prognostic algorithm to assess the reliability and forecast the remaining useful lifetime(RUL) of bearings was proposed,consisting of three phases.Online vibration and temperature signals of bearings in normal state were measured during the manufacturing process and the most useful time-dependent features of vibration signals were extracted based on correlation analysis(feature selection step).Time series analysis based on neural network,as an identification model,was used to predict the features of bearing vibration signals at any horizons(feature prediction step).Furthermore,according to the features,degradation factor was defined.The proportional hazard model was generated to estimate the survival function and forecast the RUL of the bearing(RUL prediction step).The positive results show that the plausibility and effectiveness of the proposed approach can facilitate bearing reliability estimation and RUL prediction.展开更多
The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuse...The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuses on fault detection and isolation, but they cannot provide an effective guide for the design for testability （DFT） to improve the PHM performance level. To solve the problem, a model of TSO for PHM systems is proposed. Firstly, through integrating the characteristics of fault severity and propa- gation time, and analyzing the test timing and sensitivity, a testability model based on failure evolution mechanism model （FEMM） for PHM systems is built up. This model describes the fault evolution- test dependency using the fault-symptom parameter matrix and symptom parameter-test matrix. Secondly, a novel method of in- herent testability analysis for PHM systems is developed based on the above information. Having completed the analysis, a TSO model, whose objective is to maximize fault trackability and mini- mize the test cost, is proposed through inherent testability analysis results, and an adaptive simulated annealing genetic algorithm （ASAGA） is introduced to solve the TSO problem. Finally, a case of a centrifugal pump system is used to verify the feasibility and effectiveness of the proposed models and methods. The results show that the proposed technology is important for PHM systems to select and optimize the test set in order to improve their performance level.展开更多
Condition assessment is one of the most significant techniques of the equipment’s health management.Also,in PHM methodology cycle,which is a developed form of CBM,condition assessment is the most important step of th...Condition assessment is one of the most significant techniques of the equipment’s health management.Also,in PHM methodology cycle,which is a developed form of CBM,condition assessment is the most important step of this cycle.In this paper,the remaining useful life of the equipment is calculated using the combination of sensor information,determination of degradation state and forecasting the proposed health index.The combination of sensor information has been carried out using a new approach to determining the probabilities in the Dempster-Shafer combination rules and fuzzy c-means clustering method.Using the simulation and forecasting of extracted vibration-based health index by autoregressive Markov regime switching(ARMRS)method,final health state is determined and the remaining useful life(RUL)is estimated.In order to evaluate the model,sensor data provided by FEMTO-ST Institute have been used.展开更多
Remaining useful life （RUL） estimation is termed as one of the key issues in prognostics and health management （PHM）. To achieve RUL estimation for individual equipment, we present a degradation data-driven RUL es...Remaining useful life （RUL） estimation is termed as one of the key issues in prognostics and health management （PHM）. To achieve RUL estimation for individual equipment, we present a degradation data-driven RUL estimation approach under the collaboration between Bayesian updating and expectation maximization （EM） algorithm. Firstly, we utilize an exponential-like degradation model to describe equipment degradation process and update stochastic parameters in the model via Bayesian approach. Based on the Bayesian updating results, both probability distribution of the RUL and its point estimation can be derived. Secondly, based on the monitored degradation data to date, we give a parameter estimation approach for non-stochastic parameters in the degradation model and prove that the obtained estimation is unique and optimal in each iteration. Finally, a numerical example and a practical case study for global positioning system （GPS） receiver are provided to show that the presented approach can model degradation process and achieve RUL estimation effectively and generate better results than a previously reported approach in literature.展开更多
Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of...Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.展开更多
Background Increased levels of inflammatory markers have been documented in various settings of coronary artery disease. The vulnerability of coronary lesions in acute myocardial infarction(AMI) at the time of onset m...Background Increased levels of inflammatory markers have been documented in various settings of coronary artery disease. The vulnerability of coronary lesions in acute myocardial infarction(AMI) at the time of onset may be related to serum levels of C reactive protein(CRP) on admission, before CRP levels are affected by myocardial damage.Objective This study assessed the predictive value of CRP levels within six hours after the onset of acute anterior myocardial infarction with primary percutaneous coronary intervention(PCI).Methods The plasma CRP of 76 patients with first acute anterior myocardial infarction was measured within 6 hours after onset. They were divided into 2 groups: group 1( n =20) with elevated CRP( ≥0.3mg/dl ) on admission within 6 hours after onset and group 2( n =56) with normal CRP( <0.3mg/dl ) within 6 hours after onset. All patients were treated by primary PCI. The primary combined end points, including death due to cardiac causes, re MI related to the infarction artery(RIA) and repeat intervention of the RIA, and the restenosis rate were assessed in relation to CRP levels within 6 hours after onset. Left ventricular end diastolic volume index(EDVI),end systolic volume index(ESVI),and ejection fraction(EF) on admission and 6 month after the onset were assessed by left ventriculography. Changes in EDVI(ΔEDVI),ESVI(ΔESVI), and EF(ΔEF) were obtained by subtracting respective on admission values from corresponding 6 month follow up values. Results There were no significant differences in baseline characteristics between the two groups. The primary combined end points were significantly more frequent in group 1(20%) than those in group 2( 1.79% , P <0.01 ).In addition, restenosis rates were significantly higher in group 1 than in group 2(41.18% vs 16.07%, P<0.05). Group 1 showed greater increases in left ventricular volume and less improvement in EF compared with group 2(ΔEDVI 6.31 ±2.17 vs 3.29 ±9.46ml/m 2 , ΔESVI 5.92 ±2.31 vs 3.86 ±1.08ml/m 2 , ΔEF 1.92 ±0.47 vs 4.79 ±1.73% , P <0.05 , respectively).Conclusions CRP levels within 6 hours after the onset of AMI might predict adverse outcome after primary PCI and progressive ventricular remodeling within 6 month of AMI.展开更多
Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real...Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging.This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data.We begin by identifying relevant parameters that influence the construction of a spectrogram.We leverage the uncertainty principle in processing time-frequency domain signals,making it impossible to simultaneously achieve good time and frequency resolutions.A key determinant of this phenomenon is the window function's choice and length used in implementing the shorttime Fourier transform.The Gaussian,Kaiser,and rectangular windows are selected in the experimentation due to their diverse characteristics.The overlap parameter's size also influences the outcome and resolution of the spectrogram.A 50%overlap is used in the original data transformation,and±25%is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance.The best model reaches an accuracy of 99.98%and a cross-domain accuracy of 92.54%.When combined with data augmentation,the proposed model yields cutting-edge results.展开更多
Systems with a hidden degradation process are perva- sive in the real world. Degrading critical components will under- mine system performance and pose potential failures in the future. Prognostic aims at predicting p...Systems with a hidden degradation process are perva- sive in the real world. Degrading critical components will under- mine system performance and pose potential failures in the future. Prognostic aims at predicting potential failures before it evolves into faults. A prognostic procedure based on expectation maxi- mization and unscented Kalman filter is proposed. System state, sensor measurement and hidden degradation process are viewed as data （incomplete or missing） in the expectation maximization method. System state and hidden degradation process are esti- mated by a unscented Kalman filter upon sensor measurements. Component-specific parameters in a degradation process are iden- tified on the estimation of the degradation process. Residual life is measured by the median of estimated residual life distribution. The proposed procedure is verified by simulations on a first-order capacitor-resistance circuit with degrading resistance. Residual life estimation consists conservatively with the trend and is evalu- ated in terms of relative errors. Simulation results are reasonable. The proposed prognostic method expects applications in practice.展开更多
文摘Health management permits the reliability of a system and plays a increasingly important role for achieving efficient system-level maintenance.It has been used for remaining useful life（RUL） prognostics of electronics-rich system including avionics.Prognostics and health management（PHM） have become highly desirable to provide avionics with system level health management.This paper presents a health management and fusion prognostic model for avionics system,combining three baseline prognostic approaches that are model-based,data-driven and knowledge-based approaches,and integrates merits as well as eliminates some limitations of each single approach to achieve fusion prognostics and improved prognostic performance of RUL estimation.A fusion model built upon an optimal linear combination forecast model is then utilized to fuse single prognostic algorithm representing the three baseline approaches correspondingly,and the presented case study shows that the fusion prognostics can provide RUL estimation more accurate and more robust than either algorithm alone.
基金Project(U1709211) supported by NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization,ChinaProject(ICT2021A15) supported by the State Key Laboratory of Industrial Control Technology,Zhejiang University,ChinaProject(TPL2019C03) supported by Open Fund of Science and Technology on Thermal Energy and Power Laboratory,China。
文摘Fault degradation prognostic, which estimates the time before a failure occurs and process breakdowns, has been recognized as a key component in maintenance strategies nowadays. Fault degradation processes are, in general,slowly varying and can be modeled by autoregressive models. However, industrial processes always show typical nonstationary nature, which may bring two challenges: how to capture fault degradation information and how to model nonstationary processes. To address the critical issues, a novel fault degradation modeling and online fault prognostic strategy is developed in this paper. First, a fault degradation-oriented slow feature analysis(FDSFA) algorithm is proposed to extract fault degradation directions along which candidate fault degradation features are extracted. The trend ability assessment is then applied to select major fault degradation features. Second, a key fault degradation factor(KFDF) is calculated to characterize the fault degradation tendency by combining major fault degradation features and their stability weighting factors. After that, a time-varying regression model with temporal smoothness regularization is established considering nonstationary characteristics. On the basis of updating strategy, an online fault prognostic model is further developed by analyzing and modeling the prediction errors. The performance of the proposed method is illustrated with a real industrial process.
基金National Natural Science Foundation of China (42027805)。
文摘Implementing an efficient real-time prognostics and health management (PHM) framework improves safety and reduces maintenance costs in complex engineering systems.However, research on PHM framework development for radar systems is limited. Furthermore, typical PHM approaches are centralized, do not scale well, and are challenging to implement.This paper proposes an integrated PHM framework for radar systems based on system structural decomposition to enhance reliability and support maintenance actions. The complexity challenge associated with implementing PHM at the system level is addressed by dividing the radar system into subsystems. Subsequently, optimal measurement point selection and sensor placement algorithms are formulated for effective data acquisition. Local modules are developed for each subsystem health assessment, fault diagnosis, and fault prediction without a centralized controller. Maintenance decisions are based on each local module’s fault diagnosis and prediction results. To further improve the effectiveness of the prognostics stage, the feasibility of integrating deep learning (DL) models is also investigated.Several experiments with different degradation patterns are performed to evaluate the effectiveness of the framework’s DLbased prognostics model. The proposed framework facilitates transitioning from traditional reactive maintenance practices to a predictive maintenance approach, thereby reducing downtime and improving the overall availability of radar systems.
基金supported by the National Natural Science Foundation of China(8197103463).
文摘Objective:Albumin-globulin ratio(AGR),prognostic nutritional index(PNI),and platelet to-lymphocyte ratio(PLR)have been validated as prognostic factors for gastric cancer(GC).However,significant gender differences exist in albumin levels and inflammatory cell counts,and further research is required to understand how these differences influence GC prognosis.This study aims to investigate the prognostic impact of nutritional and inflammatory indicators on GC patients undergoing radical surgery,as well as the influence of gender on these indicators’prognostic value.Methods:The study included 596 patients with advanced GC hospitalized in the Department of Gastrointestinal Surgery,General Surgery,Xiangya Hospital of Central South University from January 2012 to December 2016.Receiver operating characteristic(ROC)analysis was performed to determine cutoff values for nutritional and inflammatory factors.Univariate analysis was used to identify factors significantly affecting survival in GC patients,while multivariate and Kaplan-Meier analyses determined independent prognostic factors for GC.Results:Multivariate analysis revealed that postsurgical tumor node metastasis(pTNM)stage[stage II:hazard ratio(HR)=3.284,P=0.012;stage III:HR:8.062,P<0.001],low preoperative AGR(HR=1.499,P=0.012),and postoperative PNI(HR=1.503,P=0.008)were risk factors for overall survival in male patients after radical GC surgery.For female patients,pN2-3(HR=3.185,P<0.001),total gastrectomy(HR=2.286,P=0.004),low preoperative PLR(HR=1.702,P=0.027),and postoperative PNI(HR=1.943,P=0.011)were identified as risk factors for overall survival.Conclusion:Postoperative PNI is an independent risk factor for all advanced GC patients.Preoperative PLR is an independent prognostic factor only for female patients,while preoperative AGR is an independent prognostic factor only for male patients.Further research is warranted to investigate the gender-specific differences in GC prognosis.
文摘Objective Triple-negative breast cancer(TNBC)is the breast cancer subtype with the worst prognosis,and lacks effective therapeutic targets.Colony stimulating factors(CSFs)are cytokines that can regulate the production of blood cells and stimulate the growth and development of immune cells,playing an important role in the malignant progression of TNBC.This article aims to construct a novel prognostic model based on the expression of colony stimulating factors-related genes(CRGs),and analyze the sensitivity of TNBC patients to immunotherapy and drug therapy.Methods We downloaded CRGs from public databases and screened for differentially expressed CRGs between normal and TNBC tissues in the TCGA-BRCA database.Through LASSO Cox regression analysis,we constructed a prognostic model and stratified TNBC patients into high-risk and low-risk groups based on the colony stimulating factors-related genes risk score(CRRS).We further analyzed the correlation between CRRS and patient prognosis,clinical features,tumor microenvironment(TME)in both high-risk and low-risk groups,and evaluated the relationship between CRRS and sensitivity to immunotherapy and drug therapy.Results We identified 842 differentially expressed CRGs in breast cancer tissues of TNBC patients and selected 13 CRGs for constructing the prognostic model.Kaplan-Meier survival curves,time-dependent receiver operating characteristic curves,and other analyses confirmed that TNBC patients with high CRRS had shorter overall survival,and the predictive ability of CRRS prognostic model was further validated using the GEO dataset.Nomogram combining clinical features confirmed that CRRS was an independent factor for the prognosis of TNBC patients.Moreover,patients in the high-risk group had lower levels of immune infiltration in the TME and were sensitive to chemotherapeutic drugs such as 5-fluorouracil,ipatasertib,and paclitaxel.Conclusion We have developed a CRRS-based prognostic model composed of 13 differentially expressed CRGs,which may serve as a useful tool for predicting the prognosis of TNBC patients and guiding clinical treatment.Moreover,the key genes within this model may represent potential molecular targets for future therapies of TNBC.
文摘以BIM(Building Information Modeling)、物联网、云计算等为代表的新一代信息技术与传统行业的不断融合促使智慧桥梁应运而生。本文分析了智慧桥梁理念的内涵,阐述了智慧桥梁的总体架构,将智慧桥梁划分为智慧设计、智慧建造和智慧管养三个阶段,研究了不同阶段的主要功能及关键技术,指出了智慧桥梁是智慧产业在桥梁工程领域发展的必然结果。
基金Project(61174115)supported by the National Natural Science Foundation of ChinaProject(L2013001)supported by Scientific Research Program of Liaoning Provincial Education Department,China
文摘As the central component of rotating machine,the performance reliability assessment and remaining useful lifetime prediction of bearing are of crucial importance in condition-based maintenance to reduce the maintenance cost and improve the reliability.A prognostic algorithm to assess the reliability and forecast the remaining useful lifetime(RUL) of bearings was proposed,consisting of three phases.Online vibration and temperature signals of bearings in normal state were measured during the manufacturing process and the most useful time-dependent features of vibration signals were extracted based on correlation analysis(feature selection step).Time series analysis based on neural network,as an identification model,was used to predict the features of bearing vibration signals at any horizons(feature prediction step).Furthermore,according to the features,degradation factor was defined.The proportional hazard model was generated to estimate the survival function and forecast the RUL of the bearing(RUL prediction step).The positive results show that the plausibility and effectiveness of the proposed approach can facilitate bearing reliability estimation and RUL prediction.
基金supported by the National Natural Science Foundation of China(51175502)
文摘The test selection and optimization （TSO） can improve the abilities of fault diagnosis, prognosis and health-state evalua- tion for prognostics and health management （PHM） systems. Traditionally, TSO mainly focuses on fault detection and isolation, but they cannot provide an effective guide for the design for testability （DFT） to improve the PHM performance level. To solve the problem, a model of TSO for PHM systems is proposed. Firstly, through integrating the characteristics of fault severity and propa- gation time, and analyzing the test timing and sensitivity, a testability model based on failure evolution mechanism model （FEMM） for PHM systems is built up. This model describes the fault evolution- test dependency using the fault-symptom parameter matrix and symptom parameter-test matrix. Secondly, a novel method of in- herent testability analysis for PHM systems is developed based on the above information. Having completed the analysis, a TSO model, whose objective is to maximize fault trackability and mini- mize the test cost, is proposed through inherent testability analysis results, and an adaptive simulated annealing genetic algorithm （ASAGA） is introduced to solve the TSO problem. Finally, a case of a centrifugal pump system is used to verify the feasibility and effectiveness of the proposed models and methods. The results show that the proposed technology is important for PHM systems to select and optimize the test set in order to improve their performance level.
文摘Condition assessment is one of the most significant techniques of the equipment’s health management.Also,in PHM methodology cycle,which is a developed form of CBM,condition assessment is the most important step of this cycle.In this paper,the remaining useful life of the equipment is calculated using the combination of sensor information,determination of degradation state and forecasting the proposed health index.The combination of sensor information has been carried out using a new approach to determining the probabilities in the Dempster-Shafer combination rules and fuzzy c-means clustering method.Using the simulation and forecasting of extracted vibration-based health index by autoregressive Markov regime switching(ARMRS)method,final health state is determined and the remaining useful life(RUL)is estimated.In order to evaluate the model,sensor data provided by FEMTO-ST Institute have been used.
基金supported by the National Natural Science Foundation of China(6117403061104223+1 种基金61174113)the Natural Science Fund of Guangdong Province(S2011020002735)
文摘Remaining useful life （RUL） estimation is termed as one of the key issues in prognostics and health management （PHM）. To achieve RUL estimation for individual equipment, we present a degradation data-driven RUL estimation approach under the collaboration between Bayesian updating and expectation maximization （EM） algorithm. Firstly, we utilize an exponential-like degradation model to describe equipment degradation process and update stochastic parameters in the model via Bayesian approach. Based on the Bayesian updating results, both probability distribution of the RUL and its point estimation can be derived. Secondly, based on the monitored degradation data to date, we give a parameter estimation approach for non-stochastic parameters in the degradation model and prove that the obtained estimation is unique and optimal in each iteration. Finally, a numerical example and a practical case study for global positioning system （GPS） receiver are provided to show that the presented approach can model degradation process and achieve RUL estimation effectively and generate better results than a previously reported approach in literature.
基金supported by the National Natural Science Foundation of China (42027805)National Aeronautical Fund (ASFC-2017 2080005)National Key R&D Program of China (2017YFC03 07100)。
文摘Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.
文摘Background Increased levels of inflammatory markers have been documented in various settings of coronary artery disease. The vulnerability of coronary lesions in acute myocardial infarction(AMI) at the time of onset may be related to serum levels of C reactive protein(CRP) on admission, before CRP levels are affected by myocardial damage.Objective This study assessed the predictive value of CRP levels within six hours after the onset of acute anterior myocardial infarction with primary percutaneous coronary intervention(PCI).Methods The plasma CRP of 76 patients with first acute anterior myocardial infarction was measured within 6 hours after onset. They were divided into 2 groups: group 1( n =20) with elevated CRP( ≥0.3mg/dl ) on admission within 6 hours after onset and group 2( n =56) with normal CRP( <0.3mg/dl ) within 6 hours after onset. All patients were treated by primary PCI. The primary combined end points, including death due to cardiac causes, re MI related to the infarction artery(RIA) and repeat intervention of the RIA, and the restenosis rate were assessed in relation to CRP levels within 6 hours after onset. Left ventricular end diastolic volume index(EDVI),end systolic volume index(ESVI),and ejection fraction(EF) on admission and 6 month after the onset were assessed by left ventriculography. Changes in EDVI(ΔEDVI),ESVI(ΔESVI), and EF(ΔEF) were obtained by subtracting respective on admission values from corresponding 6 month follow up values. Results There were no significant differences in baseline characteristics between the two groups. The primary combined end points were significantly more frequent in group 1(20%) than those in group 2( 1.79% , P <0.01 ).In addition, restenosis rates were significantly higher in group 1 than in group 2(41.18% vs 16.07%, P<0.05). Group 1 showed greater increases in left ventricular volume and less improvement in EF compared with group 2(ΔEDVI 6.31 ±2.17 vs 3.29 ±9.46ml/m 2 , ΔESVI 5.92 ±2.31 vs 3.86 ±1.08ml/m 2 , ΔEF 1.92 ±0.47 vs 4.79 ±1.73% , P <0.05 , respectively).Conclusions CRP levels within 6 hours after the onset of AMI might predict adverse outcome after primary PCI and progressive ventricular remodeling within 6 month of AMI.
基金supported by the National Natural Science Foundation of China(42027805)the National Aeronautical Fund(ASFC-20172080005)。
文摘Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging.This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data.We begin by identifying relevant parameters that influence the construction of a spectrogram.We leverage the uncertainty principle in processing time-frequency domain signals,making it impossible to simultaneously achieve good time and frequency resolutions.A key determinant of this phenomenon is the window function's choice and length used in implementing the shorttime Fourier transform.The Gaussian,Kaiser,and rectangular windows are selected in the experimentation due to their diverse characteristics.The overlap parameter's size also influences the outcome and resolution of the spectrogram.A 50%overlap is used in the original data transformation,and±25%is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance.The best model reaches an accuracy of 99.98%and a cross-domain accuracy of 92.54%.When combined with data augmentation,the proposed model yields cutting-edge results.
文摘Systems with a hidden degradation process are perva- sive in the real world. Degrading critical components will under- mine system performance and pose potential failures in the future. Prognostic aims at predicting potential failures before it evolves into faults. A prognostic procedure based on expectation maxi- mization and unscented Kalman filter is proposed. System state, sensor measurement and hidden degradation process are viewed as data （incomplete or missing） in the expectation maximization method. System state and hidden degradation process are esti- mated by a unscented Kalman filter upon sensor measurements. Component-specific parameters in a degradation process are iden- tified on the estimation of the degradation process. Residual life is measured by the median of estimated residual life distribution. The proposed procedure is verified by simulations on a first-order capacitor-resistance circuit with degrading resistance. Residual life estimation consists conservatively with the trend and is evalu- ated in terms of relative errors. Simulation results are reasonable. The proposed prognostic method expects applications in practice.
