The reliable,rapid,and accurate Remaining Useful Life(RUL)prognostics of aircraft power supply and distribution system are essential for enhancing the reliability and stability of system and reducing the life-cycle co...The reliable,rapid,and accurate Remaining Useful Life(RUL)prognostics of aircraft power supply and distribution system are essential for enhancing the reliability and stability of system and reducing the life-cycle costs.To achieve the reliable,rapid,and accurate RUL prognostics,the balance between accuracy and computational burden deserves more attention.In addition,the uncertainty is intrinsically present in RUL prognostic process.Due to the limitation of the uncertainty quantification,the point-wise prognostics strategy is not trustworthy.A Dual Adaptive Sliding-window Hybrid(DASH)RUL probabilistic prognostics strategy is proposed to tackle these deficiencies.The DASH strategy contains two adaptive mechanisms,the adaptive Long Short-Term Memory-Polynomial Regression(LSTM-PR)hybrid prognostics mechanism and the adaptive sliding-window Kernel Density Estimation(KDE)probabilistic prognostics mechanism.Owing to the dual adaptive mechanisms,the DASH strategy can achieve the balance between accuracy and computational burden and obtain the trustworthy probabilistic prognostics.Based on the degradation dataset of aircraft electromagnetic contactors,the superiority of DASH strategy is validated.In terms of probabilistic,point-wise and integrated prognostics performance,the proposed strategy increases by 66.89%,81.73% and 25.84%on average compared with the baseline methods and their variants.展开更多
1. Introduction Prognostics, known as ‘Remaining Useful Life(RUL) prediction', plays a crucial role in health management of critical systems, which is vital for maintaining the operating safety and reliability, a...1. Introduction Prognostics, known as ‘Remaining Useful Life(RUL) prediction', plays a crucial role in health management of critical systems, which is vital for maintaining the operating safety and reliability, and reducing the management costs.1Here, the RUL is usually defined as the length from the current time to the end of the useful life.展开更多
Current research on Digital Twin(DT)based Prognostics and Health Management(PHM)focuses on establishment of DT through integration of real-time data from various sources to facilitate comprehensive product monitoring ...Current research on Digital Twin(DT)based Prognostics and Health Management(PHM)focuses on establishment of DT through integration of real-time data from various sources to facilitate comprehensive product monitoring and health management.However,there still exist gaps in the seamless integration of DT and PHM,as well as in the development of DT multi-field coupling modeling and its dynamic update mechanism.When the product experiences long-period degradation under load spectrum,it is challenging to describe the dynamic evolution of the health status and degradation progression accurately.In addition,DT update algorithms are difficult to be integrated simultaneously by current methods.This paper proposes an innovative dual loop DT based PHM framework,in which the first loop establishes the basic dynamic DT with multi-filed coupling,and the second loop implements the PHM and the abnormal detection to provide the interaction between the dual loops through updating mechanism.The proposed method pays attention to the internal state changes with degradation and interactive mapping with dynamic parameter updating.Furthermore,the Independence Principle for the abnormal detection is proposed to refine the theory of DT.Events at the first loop focus on accurate modeling of multi-field coupling,while the events at the second loop focus on real-time occurrence of anomalies and the product degradation trend.The interaction and collaboration between different loop models are also discussed.Finally,the Permanent Magnet Synchronous Motor(PMSM)is used to verify the proposed method.The results show that the modeling method proposed can accurately track the lifecycle performance changes of the entity and carry out remaining life prediction and health management effectively.展开更多
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
In this paper,we propose an approach for diagnostics and prognostics of damaged aircraft structures,by combing high-performance fatigue mechanics with filtering theories.Fast&accurate deterministic analyses of fat...In this paper,we propose an approach for diagnostics and prognostics of damaged aircraft structures,by combing high-performance fatigue mechanics with filtering theories.Fast&accurate deterministic analyses of fatigue crack propagations are carried out,by using the Finite Element Alternating Method(FEAM)for computing SIFs,and by using the newly developed Moving Least Squares(MLS)law for computing fatigue crack growth rates.Such algorithms for simulating fatigue crack propagations are embedded in the computer program Safe-Flaw,which is called upon as a subroutine within the probabilistic framework of filter theories.Both the extended Kalman as well as particle filters are applied in this study,to obtain the statistically optimal and semi-optimal estimates of crack lengths,from a series of noisy measurements of crack-lengths over time.For the specific problem,a simple modification to the particle filter,which can drastically reduce the computational burden,is also proposed.Based on the results of such diagnostic analyses,the prognostics of aerospace structures are thereafter achieved,to estimate the probabilistic distribution of the remaining useful life.By using a simple example of a single-crack near a fastener hole,we demonstrate the concept and effectiveness of the proposed framework.This paper thus forms the scientific foundation for the recently proposed concepts of VRAMS(Virtual Risk-Informed Agile Maneuver Sustainment)and Digital Twins of aerospace vehicles.展开更多
Machine components and systems, such as gears, bearings, pipes, cutting tools and turbines, may experience various types of faults, such as breakage, crack, pitting, wear, corrosion. If not being properly monitored an...Machine components and systems, such as gears, bearings, pipes, cutting tools and turbines, may experience various types of faults, such as breakage, crack, pitting, wear, corrosion. If not being properly monitored and treated, such faults can propagate and lead to machinery perfor- mance degradation, malfunction, or even severe compo- nent/system failure. It is significant to reliably detect machinery defects, evaluate their severity, predict the fault propagation trends, and schedule optimized maintenance and inspection activities to prevent unexpected failures. Advances in these areas will support ensuring equipment and production reliability, safety, quality and productivity.展开更多
This paper proposes a model-based prognostics method that couples the Extended Kalman Filter(EKF) and a new developed linearization method. The proposed prognostics method is developed in the context of fatigue crack ...This paper proposes a model-based prognostics method that couples the Extended Kalman Filter(EKF) and a new developed linearization method. The proposed prognostics method is developed in the context of fatigue crack propagation in fuselage panels where the model parameters are unknown and the crack propagation is affected by different types of uncertainties. The coupled method is composed of two steps. The first step employs EKF to estimate the unknown model parameters and the current damage state. In the second step, the proposed efficient linearization method is applied to compute analytically the statistical distribution of the damage evolution path in some future time. A numerical case study is implemented to evaluate the performance of the proposed method. The results show that the coupled EKF-linearization method provides satisfactory results: the EKF algorithm well identifies the model parameters, and the linearization method gives comparable prediction results to Monte Carlo(MC) method while leading to very significant computational cost saving. The proposed prognostics method for fatigue crack growth can be used for developing predictive maintenance strategy for an aircraft fleet, in which case, the computational cost saving is significantly meaningful.展开更多
The prognostics health management(PHM)fromthe systematic viewis critical to the healthy continuous operation of processmanufacturing systems(PMS),with different kinds of dynamic interference events.This paper proposes...The prognostics health management(PHM)fromthe systematic viewis critical to the healthy continuous operation of processmanufacturing systems(PMS),with different kinds of dynamic interference events.This paper proposes a three leveled digital twinmodel for the systematic PHMof PMSs.The unit-leveled digital twinmodel of each basic device unit of PMSs is constructed based on edge computing,which can provide real-time monitoring and analysis of the device status.The station-leveled digital twin models in the PMSs are designed to optimize and control the process parameters,which are deployed for the manufacturing execution on the fog server.The shop-leveled digital twin maintenancemodel is designed for production planning,which gives production instructions fromthe private industrial cloud server.To cope with the dynamic disturbances of a PMS,a big data-driven framework is proposed to control the three-level digital twin models,which contains indicator prediction,influence evaluation,and decisionmaking.Finally,a case study with a real chemical fiber system is introduced to illustrate the effectiveness of the digital twin model with edge-fog-cloud computing for the systematic PHM of PMSs.The result demonstrates that the three-leveled digital twin model for the systematic PHM in PMSs works well in the system’s respects.展开更多
Remaining useful life（RUL） prognostics is a fundamental premise to perform conditionbased maintenance（CBM） for a system subject to performance degradation. Over the past decades,research has been conducted in RUL ...Remaining useful life（RUL） prognostics is a fundamental premise to perform conditionbased maintenance（CBM） for a system subject to performance degradation. Over the past decades,research has been conducted in RUL prognostics for aeroengine. However, most of the prognostics technologies and methods simply base on single parameter, making it hard to demonstrate the specific characteristics of its degradation. To solve such problems, this paper proposes a novel approach to predict RUL by means of superstatistics and information fusion. The performance degradation evolution of the engine is modeled by fusing multiple monitoring parameters, which manifest non-stationary characteristics while degrading. With the obtained degradation curve,prognostics model can be established by state-space method, and then RUL can be estimated when the time-varying parameters of the model are predicted and updated through Kalman filtering algorithm. By this method, the non-stationary degradation of each parameter is represented, and multiple monitoring parameters are incorporated, both contributing to the final prognostics. A case study shows that this approach enables satisfactory prediction evolution and achieves a markedly better prognosis of RUL.展开更多
As an important and necessary part in the intelligent battery management systems(BMS),the prognostics and remaining useful life(RUL)estimation for lithium-ion batteries attach more and more attractions.Especially,the ...As an important and necessary part in the intelligent battery management systems(BMS),the prognostics and remaining useful life(RUL)estimation for lithium-ion batteries attach more and more attractions.Especially,the data-driven approaches use only the monitoring data and historical data to model the performance degradation and assess the health status,that makes these methods flexible and applicable in actual lithium-ion battery applications.At first,the related concepts and definitions are introduced.And the degradation parameters identification and extraction is presented,as the health indicator and the foundation of RUL prediction for the lithium-ion batteries.Then,data-driven methods used for lithium-ion battery RUL estimation are summarized,in which several statistical and machine learning algorithms are involved.Finally,the future trend for battery prognostics and RUL estimation are forecasted.展开更多
Transportation electrification is essential for decarbonizing transport. Currently, lithium-ion batteries are the primary power source for electric vehicles (EVs). However, there is still a significant journey ahead b...Transportation electrification is essential for decarbonizing transport. Currently, lithium-ion batteries are the primary power source for electric vehicles (EVs). However, there is still a significant journey ahead before EVs can establish themselves as the dominant force in the global automotive market. Concerns such as range anxiety, battery aging, and safety issues remain significant challenges.展开更多
In the present research, the model of mortality prognostics during the first 24 hours due to ACA （acute cerebrovascular accident） was developed. Eleven characteristics, developed by logistic regression method, were ...In the present research, the model of mortality prognostics during the first 24 hours due to ACA （acute cerebrovascular accident） was developed. Eleven characteristics, developed by logistic regression method, were offered. The present model allows to predict the result ＂died/survived＂ for every adult patient with cerebral stroke, who was delivered to hospital to choose individual approach. And in such way, it raised the effectiveness of treatment and lowered the frequency of fatal case. External causes among solar, geomagnetic and meteorological were defined, which reflected the varied impact of environment and raised of fatal case probability during the first 24 hours.展开更多
In view of class imbalance in data-driven modeling for Prognostics and Health Management(PHM),existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train ...In view of class imbalance in data-driven modeling for Prognostics and Health Management(PHM),existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train control equipment.A virtual sample generation solution based on Generative Adversarial Network(GAN)is proposed to overcome this shortcoming.Aiming at augmenting the sample classes with the imbalanced data problem,the GAN-based virtual sample generation strategy is embedded into the establishment of fault prediction models.Under the PHM framework of the on-board train control system,the virtual sample generation principle and the detailed procedures are presented.With the enhanced class-balancing mechanism and the designed sample augmentation logic,the PHM scheme of the on-board train control equipment has powerful data condition adaptability and can effectively predict the fault probability and life cycle status.Practical data from a specific type of on-board train control system is employed for the validation of the presented solution.The comparative results indicate that GAN-based sample augmentation is capable of achieving a desirable sample balancing level and enhancing the performance of correspondingly derived fault prediction models for the Condition-based Maintenance(CBM)operations.展开更多
Scientific research frequently involves the use of computational tools and methods.Providing thorough documentation,open-source code,and data–the creation of reproducible computational research(RCR)–helps others und...Scientific research frequently involves the use of computational tools and methods.Providing thorough documentation,open-source code,and data–the creation of reproducible computational research(RCR)–helps others understand a researcher’s work.In this study,we investigate the state of reproducible computational research,broadly,and from within the field of prognostics and health management(PHM).In a text mining survey of more than 300 articles,we show that fewer than 1%of PHM researchers make their code and data available to others.To promote the RCR further,our work also highlights several personal benefits for those engaged in the practice.Finally,we introduce an open-source software tool,called PyPHM,to assist PHM researchers in accessing and preprocessing common industrial datasets.展开更多
Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination...Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination of transferred deep learning and Gaussian process regression.General health indicators are extracted from the partial discharge process.The sequential degradation model of the health indicator is developed based on a deep learning framework and is migrated for the battery pack degradation prediction.The future degraded capacities of both battery pack and each battery cell are probabilistically predicted to provide a comprehensive lifetime prognostic.Besides,only a few separate battery cells in the source domain and early data of battery packs in the target domain are needed for model construction.Experimental results show that the lifetime prediction errors are less than 25 cycles for the battery pack,even with only 50 cycles for model fine-tuning,which can save about 90%time for the aging experiment.Thus,it largely reduces the time and labor for battery pack investigation.The predicted capacity trends of the battery cells connected in the battery pack accurately reflect the actual degradation of each battery cell,which can reveal the weakest cell for maintenance in advance.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
As one of the key technologies to maintain the safety and reliability of stochastic degrading systems,remaining useful life(RUL)prediction,also known as prognostics,has been attached great importance in recent years.P...As one of the key technologies to maintain the safety and reliability of stochastic degrading systems,remaining useful life(RUL)prediction,also known as prognostics,has been attached great importance in recent years.Particularly,with the rapid development of industrial 4.0 and internet-of-things(IoT),prognostics for stochastic degrading systems under big data have been paid much attention in recent years and various prognosis methods have been reported.However,there has not been a critical review particularly focused on the strengths and weaknesses of these methods to provoke the new ideas for the prognostics research.To fill this gap,facing the realistic demand of prognostics of stochastic degrading systems under the background of big data,this paper profoundly analyzes the basic research ideas,development trends,and common problems of various data-driven prognostics methods,mainly including statistical data-driven methods,machine learning(ML)based methods,hybrid prognostics of statistical data-driven methods and ML based methods.Particularly,this paper discusses the emerging topic of prognosis under incomplete big data and the possible opportunities in the future are highlighted.Through discussing the pros and cons of existing methods,we provide discussions on challenges and possible opportunities to steer the future development of prognostics for stochastic degrading systems under big data.While an exhaustive review on prognostics methods remains elusive,we hope that the perspectives and discussions in this paper can serve as a stimulus for new prognostics research in the era of big data.展开更多
As the fundamental and key technique to ensure the safe and reliable operation of vital systems,prognostics with an emphasis on the remaining useful life(RUL)prediction has attracted great attention in the last decade...As the fundamental and key technique to ensure the safe and reliable operation of vital systems,prognostics with an emphasis on the remaining useful life(RUL)prediction has attracted great attention in the last decades.In this paper,we briefly discuss the general idea and advances of various prognostics and RUL prediction methods for machinery,mainly including data-driven methods,physics-based methods,hybrid methods,etc.Based on the observations fromthe state of the art,we provide comprehensive discussions on the possible opportunities and challenges of prognostics and RUL prediction of machinery so as to steer the future development.展开更多
As battery deployments in electric vehicles and energy storage systems grow, ensuring homogeneous performance across units is crucial. We propose a multi-derivative imaging fusion(MDIF) model, employing advanced imagi...As battery deployments in electric vehicles and energy storage systems grow, ensuring homogeneous performance across units is crucial. We propose a multi-derivative imaging fusion(MDIF) model, employing advanced imaging and machine learning to predict battery aging trajectories from minimal initial data, thus facilitating effective performance grouping before deployment. Utilizing a derivative strategy and Gramian Angular Difference Field for dimensional enhancement, the MDIF model uncovers subtle predictive features from discharge curve data after only ten cycles. The architecture includes a parallel convolutional neural network with lateral connections to enhance feature integration and extraction.Tested on a self-developed dataset, the model achieves an average root-mean-square error of 0.047 Ah and an average mean absolute percentage error of 1.60%, demonstrating high precision and reliability.Its robustness is further validated through transfer learning on two publicly available datasets, adapting with minimal retraining. This approach significantly reduces the testing cycles required, lowering both time and costs associated with battery testing. By enabling precise battery behavior predictions with limited data, the MDIF model optimizes battery utilization and deployment strategies, enhancing system efficiency and sustainability.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
基金co-supported by the National Natural Science Foundation of China(Nos.52272403,52402506)Natural Science Basic Research Program of Shaanxi,China(Nos.2022JC-27,2023-JC-QN-0599)。
文摘The reliable,rapid,and accurate Remaining Useful Life(RUL)prognostics of aircraft power supply and distribution system are essential for enhancing the reliability and stability of system and reducing the life-cycle costs.To achieve the reliable,rapid,and accurate RUL prognostics,the balance between accuracy and computational burden deserves more attention.In addition,the uncertainty is intrinsically present in RUL prognostic process.Due to the limitation of the uncertainty quantification,the point-wise prognostics strategy is not trustworthy.A Dual Adaptive Sliding-window Hybrid(DASH)RUL probabilistic prognostics strategy is proposed to tackle these deficiencies.The DASH strategy contains two adaptive mechanisms,the adaptive Long Short-Term Memory-Polynomial Regression(LSTM-PR)hybrid prognostics mechanism and the adaptive sliding-window Kernel Density Estimation(KDE)probabilistic prognostics mechanism.Owing to the dual adaptive mechanisms,the DASH strategy can achieve the balance between accuracy and computational burden and obtain the trustworthy probabilistic prognostics.Based on the degradation dataset of aircraft electromagnetic contactors,the superiority of DASH strategy is validated.In terms of probabilistic,point-wise and integrated prognostics performance,the proposed strategy increases by 66.89%,81.73% and 25.84%on average compared with the baseline methods and their variants.
基金supported by the National Natural Science Foundation of China (Nos. 62450056 and 62233017).
文摘1. Introduction Prognostics, known as ‘Remaining Useful Life(RUL) prediction', plays a crucial role in health management of critical systems, which is vital for maintaining the operating safety and reliability, and reducing the management costs.1Here, the RUL is usually defined as the length from the current time to the end of the useful life.
基金co-supported by the National Natural Science Foundation of China(Nos.U223321251875014)+1 种基金the Beijing Natural Science Foundation,China(No.L221008)the China Scholarship Council(No.202106020001).
文摘Current research on Digital Twin(DT)based Prognostics and Health Management(PHM)focuses on establishment of DT through integration of real-time data from various sources to facilitate comprehensive product monitoring and health management.However,there still exist gaps in the seamless integration of DT and PHM,as well as in the development of DT multi-field coupling modeling and its dynamic update mechanism.When the product experiences long-period degradation under load spectrum,it is challenging to describe the dynamic evolution of the health status and degradation progression accurately.In addition,DT update algorithms are difficult to be integrated simultaneously by current methods.This paper proposes an innovative dual loop DT based PHM framework,in which the first loop establishes the basic dynamic DT with multi-filed coupling,and the second loop implements the PHM and the abnormal detection to provide the interaction between the dual loops through updating mechanism.The proposed method pays attention to the internal state changes with degradation and interactive mapping with dynamic parameter updating.Furthermore,the Independence Principle for the abnormal detection is proposed to refine the theory of DT.Events at the first loop focus on accurate modeling of multi-field coupling,while the events at the second loop focus on real-time occurrence of anomalies and the product degradation trend.The interaction and collaboration between different loop models are also discussed.Finally,the Permanent Magnet Synchronous Motor(PMSM)is used to verify the proposed method.The results show that the modeling method proposed can accurately track the lifecycle performance changes of the entity and carry out remaining life prediction and health management effectively.
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.
文摘In this paper,we propose an approach for diagnostics and prognostics of damaged aircraft structures,by combing high-performance fatigue mechanics with filtering theories.Fast&accurate deterministic analyses of fatigue crack propagations are carried out,by using the Finite Element Alternating Method(FEAM)for computing SIFs,and by using the newly developed Moving Least Squares(MLS)law for computing fatigue crack growth rates.Such algorithms for simulating fatigue crack propagations are embedded in the computer program Safe-Flaw,which is called upon as a subroutine within the probabilistic framework of filter theories.Both the extended Kalman as well as particle filters are applied in this study,to obtain the statistically optimal and semi-optimal estimates of crack lengths,from a series of noisy measurements of crack-lengths over time.For the specific problem,a simple modification to the particle filter,which can drastically reduce the computational burden,is also proposed.Based on the results of such diagnostic analyses,the prognostics of aerospace structures are thereafter achieved,to estimate the probabilistic distribution of the remaining useful life.By using a simple example of a single-crack near a fastener hole,we demonstrate the concept and effectiveness of the proposed framework.This paper thus forms the scientific foundation for the recently proposed concepts of VRAMS(Virtual Risk-Informed Agile Maneuver Sustainment)and Digital Twins of aerospace vehicles.
文摘Machine components and systems, such as gears, bearings, pipes, cutting tools and turbines, may experience various types of faults, such as breakage, crack, pitting, wear, corrosion. If not being properly monitored and treated, such faults can propagate and lead to machinery perfor- mance degradation, malfunction, or even severe compo- nent/system failure. It is significant to reliably detect machinery defects, evaluate their severity, predict the fault propagation trends, and schedule optimized maintenance and inspection activities to prevent unexpected failures. Advances in these areas will support ensuring equipment and production reliability, safety, quality and productivity.
基金partially funded by the National Natural Science Foundation of China (No.51805262)
文摘This paper proposes a model-based prognostics method that couples the Extended Kalman Filter(EKF) and a new developed linearization method. The proposed prognostics method is developed in the context of fatigue crack propagation in fuselage panels where the model parameters are unknown and the crack propagation is affected by different types of uncertainties. The coupled method is composed of two steps. The first step employs EKF to estimate the unknown model parameters and the current damage state. In the second step, the proposed efficient linearization method is applied to compute analytically the statistical distribution of the damage evolution path in some future time. A numerical case study is implemented to evaluate the performance of the proposed method. The results show that the coupled EKF-linearization method provides satisfactory results: the EKF algorithm well identifies the model parameters, and the linearization method gives comparable prediction results to Monte Carlo(MC) method while leading to very significant computational cost saving. The proposed prognostics method for fatigue crack growth can be used for developing predictive maintenance strategy for an aircraft fleet, in which case, the computational cost saving is significantly meaningful.
基金supported by the Fundamental Research Funds for The Central Universities(Grant No.2232021A-08)National Natural Science Foundation of China(GrantNo.51905091)Shanghai Sailing Program(Grand No.19YF1401500).
文摘The prognostics health management(PHM)fromthe systematic viewis critical to the healthy continuous operation of processmanufacturing systems(PMS),with different kinds of dynamic interference events.This paper proposes a three leveled digital twinmodel for the systematic PHMof PMSs.The unit-leveled digital twinmodel of each basic device unit of PMSs is constructed based on edge computing,which can provide real-time monitoring and analysis of the device status.The station-leveled digital twin models in the PMSs are designed to optimize and control the process parameters,which are deployed for the manufacturing execution on the fog server.The shop-leveled digital twin maintenancemodel is designed for production planning,which gives production instructions fromthe private industrial cloud server.To cope with the dynamic disturbances of a PMS,a big data-driven framework is proposed to control the three-level digital twin models,which contains indicator prediction,influence evaluation,and decisionmaking.Finally,a case study with a real chemical fiber system is introduced to illustrate the effectiveness of the digital twin model with edge-fog-cloud computing for the systematic PHM of PMSs.The result demonstrates that the three-leveled digital twin model for the systematic PHM in PMSs works well in the system’s respects.
基金co-supported by the State Key Program of National Natural Science of China (No. 61232002)the Joint Funds of the National Natural Science Foundation of China (No. 60939003)+3 种基金China Postdoctoral Science Foundation (Nos. 2012M521081, 2013T60537)the Fundamental Research Funds for the Central Universities of China (No. NS2014066)Postdoctoral Science Foundation of Jiangsu Province of China (No. 1301107C)Philosophy and Social Science Research Projects in Colleges and Universities in Jiangsu of China (No. 2014SJD041)
文摘Remaining useful life（RUL） prognostics is a fundamental premise to perform conditionbased maintenance（CBM） for a system subject to performance degradation. Over the past decades,research has been conducted in RUL prognostics for aeroengine. However, most of the prognostics technologies and methods simply base on single parameter, making it hard to demonstrate the specific characteristics of its degradation. To solve such problems, this paper proposes a novel approach to predict RUL by means of superstatistics and information fusion. The performance degradation evolution of the engine is modeled by fusing multiple monitoring parameters, which manifest non-stationary characteristics while degrading. With the obtained degradation curve,prognostics model can be established by state-space method, and then RUL can be estimated when the time-varying parameters of the model are predicted and updated through Kalman filtering algorithm. By this method, the non-stationary degradation of each parameter is represented, and multiple monitoring parameters are incorporated, both contributing to the final prognostics. A case study shows that this approach enables satisfactory prediction evolution and achieves a markedly better prognosis of RUL.
基金supported partly by National Natural Science Foundation of China(Grant No.61301205)Research Fund for the Doctoral Program of Higher Education of China(Grant No.20112302120027)+1 种基金Natural Scientific Research Innovation Foundation in Harbin Institute of Technology(Grant No.HIT.NSRIF.2014017)China Scholarship Council.,2155-0875/Copyright C 2010 Binary Information Press July 2010
文摘As an important and necessary part in the intelligent battery management systems(BMS),the prognostics and remaining useful life(RUL)estimation for lithium-ion batteries attach more and more attractions.Especially,the data-driven approaches use only the monitoring data and historical data to model the performance degradation and assess the health status,that makes these methods flexible and applicable in actual lithium-ion battery applications.At first,the related concepts and definitions are introduced.And the degradation parameters identification and extraction is presented,as the health indicator and the foundation of RUL prediction for the lithium-ion batteries.Then,data-driven methods used for lithium-ion battery RUL estimation are summarized,in which several statistical and machine learning algorithms are involved.Finally,the future trend for battery prognostics and RUL estimation are forecasted.
文摘Transportation electrification is essential for decarbonizing transport. Currently, lithium-ion batteries are the primary power source for electric vehicles (EVs). However, there is still a significant journey ahead before EVs can establish themselves as the dominant force in the global automotive market. Concerns such as range anxiety, battery aging, and safety issues remain significant challenges.
文摘In the present research, the model of mortality prognostics during the first 24 hours due to ACA （acute cerebrovascular accident） was developed. Eleven characteristics, developed by logistic regression method, were offered. The present model allows to predict the result ＂died/survived＂ for every adult patient with cerebral stroke, who was delivered to hospital to choose individual approach. And in such way, it raised the effectiveness of treatment and lowered the frequency of fatal case. External causes among solar, geomagnetic and meteorological were defined, which reflected the varied impact of environment and raised of fatal case probability during the first 24 hours.
基金supported by National Natural Science Foundation of China(U2268206,T2222015)Beijing Natural Science Foundation(4232031)+1 种基金Key Fields Project of DEGP(2021ZDZX1110)Shenzhen Science and Technology Program(CJGJZD20220517141801004).
文摘In view of class imbalance in data-driven modeling for Prognostics and Health Management(PHM),existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train control equipment.A virtual sample generation solution based on Generative Adversarial Network(GAN)is proposed to overcome this shortcoming.Aiming at augmenting the sample classes with the imbalanced data problem,the GAN-based virtual sample generation strategy is embedded into the establishment of fault prediction models.Under the PHM framework of the on-board train control system,the virtual sample generation principle and the detailed procedures are presented.With the enhanced class-balancing mechanism and the designed sample augmentation logic,the PHM scheme of the on-board train control equipment has powerful data condition adaptability and can effectively predict the fault probability and life cycle status.Practical data from a specific type of on-board train control system is employed for the validation of the presented solution.The comparative results indicate that GAN-based sample augmentation is capable of achieving a desirable sample balancing level and enhancing the performance of correspondingly derived fault prediction models for the Condition-based Maintenance(CBM)operations.
文摘Scientific research frequently involves the use of computational tools and methods.Providing thorough documentation,open-source code,and data–the creation of reproducible computational research(RCR)–helps others understand a researcher’s work.In this study,we investigate the state of reproducible computational research,broadly,and from within the field of prognostics and health management(PHM).In a text mining survey of more than 300 articles,we show that fewer than 1%of PHM researchers make their code and data available to others.To promote the RCR further,our work also highlights several personal benefits for those engaged in the practice.Finally,we introduce an open-source software tool,called PyPHM,to assist PHM researchers in accessing and preprocessing common industrial datasets.
基金Supported by National Natural Science Foundation of China(Grant Nos.51875054,U1864212)Graduate Research and Innovation Foundation of Chongqing+2 种基金China(Grant No.CYS20018)Chongqing Municipal Natural Science Foundation for Distinguished Young Scholars of China(Grant No.cstc2019jcyjjq X0016)Chongqing Science and Technology Bureau of China。
文摘Aging diagnosis of batteries is essential to ensure that the energy storage systems operate within a safe region.This paper proposes a novel cell to pack health and lifetime prognostics method based on the combination of transferred deep learning and Gaussian process regression.General health indicators are extracted from the partial discharge process.The sequential degradation model of the health indicator is developed based on a deep learning framework and is migrated for the battery pack degradation prediction.The future degraded capacities of both battery pack and each battery cell are probabilistically predicted to provide a comprehensive lifetime prognostic.Besides,only a few separate battery cells in the source domain and early data of battery packs in the target domain are needed for model construction.Experimental results show that the lifetime prediction errors are less than 25 cycles for the battery pack,even with only 50 cycles for model fine-tuning,which can save about 90%time for the aging experiment.Thus,it largely reduces the time and labor for battery pack investigation.The predicted capacity trends of the battery cells connected in the battery pack accurately reflect the actual degradation of each battery cell,which can reveal the weakest cell for maintenance in advance.
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supported by grants from the National Natural Science Foundation of China(62233017,62373369,and 62073336).
文摘As one of the key technologies to maintain the safety and reliability of stochastic degrading systems,remaining useful life(RUL)prediction,also known as prognostics,has been attached great importance in recent years.Particularly,with the rapid development of industrial 4.0 and internet-of-things(IoT),prognostics for stochastic degrading systems under big data have been paid much attention in recent years and various prognosis methods have been reported.However,there has not been a critical review particularly focused on the strengths and weaknesses of these methods to provoke the new ideas for the prognostics research.To fill this gap,facing the realistic demand of prognostics of stochastic degrading systems under the background of big data,this paper profoundly analyzes the basic research ideas,development trends,and common problems of various data-driven prognostics methods,mainly including statistical data-driven methods,machine learning(ML)based methods,hybrid prognostics of statistical data-driven methods and ML based methods.Particularly,this paper discusses the emerging topic of prognosis under incomplete big data and the possible opportunities in the future are highlighted.Through discussing the pros and cons of existing methods,we provide discussions on challenges and possible opportunities to steer the future development of prognostics for stochastic degrading systems under big data.While an exhaustive review on prognostics methods remains elusive,we hope that the perspectives and discussions in this paper can serve as a stimulus for new prognostics research in the era of big data.
基金The work in Section III was supported by the National Science Foundation of China(NSFC)(Nos.52025056,52005387)the work in Section IV was supported by the National Science Foundation of China(NSFC)(Nos.62233017,62073336).
文摘As the fundamental and key technique to ensure the safe and reliable operation of vital systems,prognostics with an emphasis on the remaining useful life(RUL)prediction has attracted great attention in the last decades.In this paper,we briefly discuss the general idea and advances of various prognostics and RUL prediction methods for machinery,mainly including data-driven methods,physics-based methods,hybrid methods,etc.Based on the observations fromthe state of the art,we provide comprehensive discussions on the possible opportunities and challenges of prognostics and RUL prediction of machinery so as to steer the future development.
基金National Natural Science Foundation of China (Grant No. 52225705)。
文摘As battery deployments in electric vehicles and energy storage systems grow, ensuring homogeneous performance across units is crucial. We propose a multi-derivative imaging fusion(MDIF) model, employing advanced imaging and machine learning to predict battery aging trajectories from minimal initial data, thus facilitating effective performance grouping before deployment. Utilizing a derivative strategy and Gramian Angular Difference Field for dimensional enhancement, the MDIF model uncovers subtle predictive features from discharge curve data after only ten cycles. The architecture includes a parallel convolutional neural network with lateral connections to enhance feature integration and extraction.Tested on a self-developed dataset, the model achieves an average root-mean-square error of 0.047 Ah and an average mean absolute percentage error of 1.60%, demonstrating high precision and reliability.Its robustness is further validated through transfer learning on two publicly available datasets, adapting with minimal retraining. This approach significantly reduces the testing cycles required, lowering both time and costs associated with battery testing. By enabling precise battery behavior predictions with limited data, the MDIF model optimizes battery utilization and deployment strategies, enhancing system efficiency and sustainability.
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.
