Although opportunistic maintenance strategies are widely used for multi-component systems, all opportunistic mainte- nance strategies only consider economic dependence and do not take structural dependence into accoun...Although opportunistic maintenance strategies are widely used for multi-component systems, all opportunistic mainte- nance strategies only consider economic dependence and do not take structural dependence into account. An opportunistic main- tenance strategy is presented for a multi-component system that considers both structural dependence and economic dependence. The cost relation and time relation among components based on structural dependence are developed. The maintenance strategy for each component of a multi-component system involves one of five maintenance actions, namely, no-maintenance, a minimal maintenance action, an imperfect maintenance action, a perfect maintenance action, and a replacement action. The maintenance action is determined by the virtual age of the component, the life expectancy of the component, and the age threshold values. Monte Carlo simulation is designed to obtain the optimal oppor- tunistic maintenance strategy of the system over its lifetime. The simulation result reveals that the minimum maintenance cost with a strategy that considers structural dependence is less than that with a strategy that does not consider structural dependence. The availability with a strategy that considers structural dependence is greater than that with a strategy that does not consider structural dependence under the same conditions.展开更多
Avionics （aeronautics and aerospace） industries must rely on components and systems of demonstrated high reliability. For this, handbook-based methods have been traditionally used to design for reliability, develop ...Avionics （aeronautics and aerospace） industries must rely on components and systems of demonstrated high reliability. For this, handbook-based methods have been traditionally used to design for reliability, develop test plans, and define maintenance requirements and sustainment logistics, However, these methods have been criticized as flawed and leading to inaccurate and mis- leading results. In its recent report on enhancing defense system reliability, the U.S. National Academy of Sciences has recently discredited these methods, judging the Military Handbook （MIL- HDBK-217） and its progeny as invalid and inaccurate. This paper discusses the issues that arise with the use of handbook-based methods in commercial and military avionics applications. Alter- native approaches to reliability design （and its demonstration） are also discussed, including similarity analysis, testing, physics-of-failure, and data analytics for prognostics and systems health management.展开更多
Partial discharge(PD)activity is an indicator of insulation deterioration and by extension,the reliability of power lines.Existing data-driven methods,while helpful,treat PD detection as a binary classification proble...Partial discharge(PD)activity is an indicator of insulation deterioration and by extension,the reliability of power lines.Existing data-driven methods,while helpful,treat PD detection as a binary classification problem,thereby failing to provide physical information(e.g.,filter PD pulse),and often provide results that conradict physical knowledge.To tackle this challenge,this paper develops a physics-informed temporal convolutional network(PITCN)for PD diagnosis(i.e.,PD detection and PD pulse filtering).During training,physical knowledge of the background noise and PD pulse identification is integrated into a learning model.Once the model is trained,the PITCN can automatically detect PD activity from time-series voltage signals with different background noises and filter PD pulses.Experimental results demonstrate that the developed PITCN outperforms the rest of the data-driven methods implemented,and in particular,the Matthews correlation coefficient of PITCN surpasses the conventional temporal convolutional network by 0.21.展开更多
The Boeing 787 Dreamliner,launched in 2011,was presented as a game changer in air travel.With the aim of producing an efficient,mid-size,wide-body plane,Boeing initiated innovations in product and process design,suppl...The Boeing 787 Dreamliner,launched in 2011,was presented as a game changer in air travel.With the aim of producing an efficient,mid-size,wide-body plane,Boeing initiated innovations in product and process design,supply chain operation,and risk management.Nevertheless,there were reliability issues from the start,and the plane was grounded by the U.S.Federal Aviation Administration(FAA)in 2013,due to safety problems associated with Li-ion battery fires.This paper chronicles events associated with the aircraft’s initial reliability challenges.The manufacturing,supply chain,and organizational factors that contributed to these problems are assessed based on FAA data.Recommendations and lessons learned are provided for the benefit of engineers and managers who will be engaged in future complex systems development.展开更多
In practical mechanical fault detection and diagnosis,it is difficult and expensive to collect enough large-scale supervised data to train deep networks.Transfer learning can reuse the knowledge obtained from the sour...In practical mechanical fault detection and diagnosis,it is difficult and expensive to collect enough large-scale supervised data to train deep networks.Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task,which performs well on small data and reduces the demand for high computation power.However,the detection performance is significantly reduced by the direct transfer due to the domain difference.Domain adaptation(DA)can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data.In this survey,we review various current DA strategies combined with deep learning(DL)and analyze the principles,advantages,and disadvantages of each method.We also summarize the application of DA combined with DL in the field of fault diagnosis.This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.展开更多
Lithium-ion batteries have been rapidly developed as clean energy sources in many industrial fields,such as new energy vehicles and energy storage.The core issues hindering their further promotion and application are ...Lithium-ion batteries have been rapidly developed as clean energy sources in many industrial fields,such as new energy vehicles and energy storage.The core issues hindering their further promotion and application are reliability and safety.A digital twin model that maps onto the physical entity of the battery with high simulation accuracy helps to monitor internal states and improve battery safety.This work focuses on developing a digital twin model via a mechanism-data-driven parameter updating algorithm to increase the simulation accuracy of the internal and external characteristics of the full-time domain battery under complex working conditions.An electrochemical model is first developed with the consideration of how electrode particle size impacts battery characteristics.By adding the descriptions of temperature distribution and particle-level stress,a multi-particle size electrochemical-thermal-mechanical coupling model is established.Then,considering the different electrical and thermal effect among individual cells,a model for the battery pack is constructed.A digital twin model construction method is finally developed and verified with battery operating data.展开更多
Empirical wavelet transform(EWT)based on the scale space method has been widely used in rolling bearing fault diagnosis.However,using the scale space method to divide the frequency band,the redundant components can ea...Empirical wavelet transform(EWT)based on the scale space method has been widely used in rolling bearing fault diagnosis.However,using the scale space method to divide the frequency band,the redundant components can easily be separated,causing the band to rupture and making it difficult to extract rolling bearing fault characteristic frequency effectively.This paper develops a method for optimizing the frequency band region based on the frequency domain feature parameter set.The frequency domain feature parameter set includes two characteristic parameters:mean and variance.After adaptively dividing the frequency band by the scale space method,the mean and variance of each band are calculated.Sub-bands with mean and variance less than the main frequency band are combined with surrounding bands for subsequent analysis.An adaptive empirical wavelet filter on each frequency band is established to obtain the corresponding empirical mode.The margin factor sensitive to the shock pulse signal is introduced into the screening of empirical modes.The empirical mode with the largest margin factor is selected to envelope spectrum analysis.Simulation and experiment data show this method avoids over-segmentation and redundancy and can extract the fault characteristic frequency easier compared with only scale space methods.展开更多
This paper proposes a novel nondestructive diagnostic method for flip chips based on an improved semi-supervised deep extreme learning machine(ISDELM)and vibration signals.First,an ultrasonic transducer is used to gen...This paper proposes a novel nondestructive diagnostic method for flip chips based on an improved semi-supervised deep extreme learning machine(ISDELM)and vibration signals.First,an ultrasonic transducer is used to generate and focus ultrasounds on the surface of the flip chip to excite it,and a laser scanning vibrometer is applied to acquire the chip’s vibration signals.Then,an extreme learning machine-autoencoder(ELM-AE)structure is adopted to extract features from the original vibration signals layer by layer.Finally,the study proposes integrating the ELM with sparsity neighboring reconstruction to diagnose defects based on unlabeled and labeled data.The ISDELM algorithm is applied to experimental vibration data of flip chips and compared with several other algorithms,such as semi-supervised ELM(SS-ELM),deep ELM,stacked autoencoder,convolutional neural network,and ordinary SDELM.The results show that the proposed method is superior to the several currently available algorithms in terms of accuracy and stability.展开更多
Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is consi...Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is considered a significant evaluation index that greatly affects the degradation of battery pack.This paper proposes a novel joint inconsistency and SOH estimation method under cycling,which fills the gap of joint estimation based on the fast-charging process for electric vehicles.First,fifteen features are extracted from current change points during the partial charging process.Then,a joint estimation system is designed,where fusion weights are obtained by the analytic hierarchy process and multi-scale sample entropy to evaluate inconsistency.A wrapper is used to select the optimal feature subset,and Gaussian process regression is implemented to estimate the SOH.Finally,the estimation performance is assessed by the test data.The results show that the inconsistency evaluation can reflect the aging conditions,and the inconsistency does affect the aging process.The wrapper selection method improves the accuracy of SOH estimation by about 75.8%compared to the traditional filter method when only 10%of data is used for model training.The maximum absolute error and root mean square error are 2.58%and 0.93%,respectively.展开更多
To early detect symptoms of defective rolling element bearings, this paper introduces discrete wavelet packet transform （DWPT）-based sub-band analysis. The objective of this analysis is to explore the impacts of mul...To early detect symptoms of defective rolling element bearings, this paper introduces discrete wavelet packet transform （DWPT）-based sub-band analysis. The objective of this analysis is to explore the impacts of multiple sub-band signals by 4-level DWPTusing proper Daubechies mother wavelet on a 2.5-second acoustic emission signal. In particular, the DWPT-based sub-bandanalysis determines the most informative sub-band signal involving intrinsic information about bearing defects among theaforementioned multiple sub-band signals based on the ratio of spectral magnitudes at harmonics of the bearing＇s characteristicfrequency to those around the harmonics. This paper also verifies the efficacy of the DWPT-based sub-band analysis for seededbearing defects （i.e., a crack on the inner race, the outer race, or a roller）.展开更多
基金supported by the Postdoctoral Science Foundation of China(20080431380)
文摘Although opportunistic maintenance strategies are widely used for multi-component systems, all opportunistic mainte- nance strategies only consider economic dependence and do not take structural dependence into account. An opportunistic main- tenance strategy is presented for a multi-component system that considers both structural dependence and economic dependence. The cost relation and time relation among components based on structural dependence are developed. The maintenance strategy for each component of a multi-component system involves one of five maintenance actions, namely, no-maintenance, a minimal maintenance action, an imperfect maintenance action, a perfect maintenance action, and a replacement action. The maintenance action is determined by the virtual age of the component, the life expectancy of the component, and the age threshold values. Monte Carlo simulation is designed to obtain the optimal oppor- tunistic maintenance strategy of the system over its lifetime. The simulation result reveals that the minimum maintenance cost with a strategy that considers structural dependence is less than that with a strategy that does not consider structural dependence. The availability with a strategy that considers structural dependence is greater than that with a strategy that does not consider structural dependence under the same conditions.
文摘Avionics （aeronautics and aerospace） industries must rely on components and systems of demonstrated high reliability. For this, handbook-based methods have been traditionally used to design for reliability, develop test plans, and define maintenance requirements and sustainment logistics, However, these methods have been criticized as flawed and leading to inaccurate and mis- leading results. In its recent report on enhancing defense system reliability, the U.S. National Academy of Sciences has recently discredited these methods, judging the Military Handbook （MIL- HDBK-217） and its progeny as invalid and inaccurate. This paper discusses the issues that arise with the use of handbook-based methods in commercial and military avionics applications. Alter- native approaches to reliability design （and its demonstration） are also discussed, including similarity analysis, testing, physics-of-failure, and data analytics for prognostics and systems health management.
基金supported by the Centre for Advances in Reliability and Safety(CAiRS)admitted under AIR@InnoHK Research Cluster。
文摘Partial discharge(PD)activity is an indicator of insulation deterioration and by extension,the reliability of power lines.Existing data-driven methods,while helpful,treat PD detection as a binary classification problem,thereby failing to provide physical information(e.g.,filter PD pulse),and often provide results that conradict physical knowledge.To tackle this challenge,this paper develops a physics-informed temporal convolutional network(PITCN)for PD diagnosis(i.e.,PD detection and PD pulse filtering).During training,physical knowledge of the background noise and PD pulse identification is integrated into a learning model.Once the model is trained,the PITCN can automatically detect PD activity from time-series voltage signals with different background noises and filter PD pulses.Experimental results demonstrate that the developed PITCN outperforms the rest of the data-driven methods implemented,and in particular,the Matthews correlation coefficient of PITCN surpasses the conventional temporal convolutional network by 0.21.
文摘The Boeing 787 Dreamliner,launched in 2011,was presented as a game changer in air travel.With the aim of producing an efficient,mid-size,wide-body plane,Boeing initiated innovations in product and process design,supply chain operation,and risk management.Nevertheless,there were reliability issues from the start,and the plane was grounded by the U.S.Federal Aviation Administration(FAA)in 2013,due to safety problems associated with Li-ion battery fires.This paper chronicles events associated with the aircraft’s initial reliability challenges.The manufacturing,supply chain,and organizational factors that contributed to these problems are assessed based on FAA data.Recommendations and lessons learned are provided for the benefit of engineers and managers who will be engaged in future complex systems development.
基金supported by the National Natural Science Foundation of China(Grant Nos.52175096,51775243,11902124),the fellowship of China Postdoctoral Science Foundation(Grant No.2021T140279)111 Project(Grant No.B18027).
文摘In practical mechanical fault detection and diagnosis,it is difficult and expensive to collect enough large-scale supervised data to train deep networks.Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task,which performs well on small data and reduces the demand for high computation power.However,the detection performance is significantly reduced by the direct transfer due to the domain difference.Domain adaptation(DA)can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data.In this survey,we review various current DA strategies combined with deep learning(DL)and analyze the principles,advantages,and disadvantages of each method.We also summarize the application of DA combined with DL in the field of fault diagnosis.This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.
基金support by Shandong Province National Natural Science Foundation of China(No.ZR2023QE036).
文摘Lithium-ion batteries have been rapidly developed as clean energy sources in many industrial fields,such as new energy vehicles and energy storage.The core issues hindering their further promotion and application are reliability and safety.A digital twin model that maps onto the physical entity of the battery with high simulation accuracy helps to monitor internal states and improve battery safety.This work focuses on developing a digital twin model via a mechanism-data-driven parameter updating algorithm to increase the simulation accuracy of the internal and external characteristics of the full-time domain battery under complex working conditions.An electrochemical model is first developed with the consideration of how electrode particle size impacts battery characteristics.By adding the descriptions of temperature distribution and particle-level stress,a multi-particle size electrochemical-thermal-mechanical coupling model is established.Then,considering the different electrical and thermal effect among individual cells,a model for the battery pack is constructed.A digital twin model construction method is finally developed and verified with battery operating data.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.51705203,51775243)the Natural Science Foundation of Jiangsu Province(Grant No.BK20160183)+2 种基金the Open Foundation of State Key Lab of Digital Manufacturing Equipment Technology(Grant No.DMETKF2018022)the Key Project of Industry Foresight and Common Key Technologies of Jiangsu Province(Grant No.BE2017002)and the 111 Project(Grant No.B18027).
文摘Empirical wavelet transform(EWT)based on the scale space method has been widely used in rolling bearing fault diagnosis.However,using the scale space method to divide the frequency band,the redundant components can easily be separated,causing the band to rupture and making it difficult to extract rolling bearing fault characteristic frequency effectively.This paper develops a method for optimizing the frequency band region based on the frequency domain feature parameter set.The frequency domain feature parameter set includes two characteristic parameters:mean and variance.After adaptively dividing the frequency band by the scale space method,the mean and variance of each band are calculated.Sub-bands with mean and variance less than the main frequency band are combined with surrounding bands for subsequent analysis.An adaptive empirical wavelet filter on each frequency band is established to obtain the corresponding empirical mode.The margin factor sensitive to the shock pulse signal is introduced into the screening of empirical modes.The empirical mode with the largest margin factor is selected to envelope spectrum analysis.Simulation and experiment data show this method avoids over-segmentation and redundancy and can extract the fault characteristic frequency easier compared with only scale space methods.
基金supported by the fellowship of China Postdoctoral Science Foundation(Grant No.2021T140279)the National Natural Science Foundation of China(Grant Nos.51705203,51775243 and 11902124)“111”Project(Grant No.B18027)。
文摘This paper proposes a novel nondestructive diagnostic method for flip chips based on an improved semi-supervised deep extreme learning machine(ISDELM)and vibration signals.First,an ultrasonic transducer is used to generate and focus ultrasounds on the surface of the flip chip to excite it,and a laser scanning vibrometer is applied to acquire the chip’s vibration signals.Then,an extreme learning machine-autoencoder(ELM-AE)structure is adopted to extract features from the original vibration signals layer by layer.Finally,the study proposes integrating the ELM with sparsity neighboring reconstruction to diagnose defects based on unlabeled and labeled data.The ISDELM algorithm is applied to experimental vibration data of flip chips and compared with several other algorithms,such as semi-supervised ELM(SS-ELM),deep ELM,stacked autoencoder,convolutional neural network,and ordinary SDELM.The results show that the proposed method is superior to the several currently available algorithms in terms of accuracy and stability.
基金This work was supported in part by the National Natural Science Foundation of China(Grant No.51875054 and Grant No.U1864212)Graduate research and innovation foundation of Chongqing,China(Grant No.CYS20018)Chongqing Natural Science Foundation for Distinguished Young Scholars(Grant No.cstc2019jcyjjq0010),and Chongqing Science and Technology Bureau,China.
文摘Battery packs are applied in various areas(e.g.,electric vehicles,energy storage,space,mining,etc.),which requires the state of health(SOH)to be accurately estimated.Inconsistency,also known as cell variation,is considered a significant evaluation index that greatly affects the degradation of battery pack.This paper proposes a novel joint inconsistency and SOH estimation method under cycling,which fills the gap of joint estimation based on the fast-charging process for electric vehicles.First,fifteen features are extracted from current change points during the partial charging process.Then,a joint estimation system is designed,where fusion weights are obtained by the analytic hierarchy process and multi-scale sample entropy to evaluate inconsistency.A wrapper is used to select the optimal feature subset,and Gaussian process regression is implemented to estimate the SOH.Finally,the estimation performance is assessed by the test data.The results show that the inconsistency evaluation can reflect the aging conditions,and the inconsistency does affect the aging process.The wrapper selection method improves the accuracy of SOH estimation by about 75.8%compared to the traditional filter method when only 10%of data is used for model training.The maximum absolute error and root mean square error are 2.58%and 0.93%,respectively.
文摘To early detect symptoms of defective rolling element bearings, this paper introduces discrete wavelet packet transform （DWPT）-based sub-band analysis. The objective of this analysis is to explore the impacts of multiple sub-band signals by 4-level DWPTusing proper Daubechies mother wavelet on a 2.5-second acoustic emission signal. In particular, the DWPT-based sub-bandanalysis determines the most informative sub-band signal involving intrinsic information about bearing defects among theaforementioned multiple sub-band signals based on the ratio of spectral magnitudes at harmonics of the bearing＇s characteristicfrequency to those around the harmonics. This paper also verifies the efficacy of the DWPT-based sub-band analysis for seededbearing defects （i.e., a crack on the inner race, the outer race, or a roller）.
