A Possibilistic Approach for Uncertainty Representation and Propagation in Similarity-Based Prognostic Health Management Solutions

In this paper, a data-driven prognostic model capable to deal with different sources of uncertainty is proposed. The main novelty factor is the application of a mathematical framework, namely a Random Fuzzy Variable (RFV) approach, for the representation and propagation of the different uncertainty sources affecting Prognostic Health Management (PHM) applications: measurement, future and model uncertainty. In this way, it is possible to deal not only with measurement noise and model parameters uncertainty due to the stochastic nature of the degradation process, but also with systematic effects, such as systematic errors in the measurement process, incomplete knowledge of the degradation process, subjective belief about model parameters. Furthermore, the low analytical complexity of the employed prognostic model allows to easily propagate the measurement and parameters uncertainty into the RUL forecast, with no need of extensive Monte Carlo loops, so that low requirements in terms of computation power are needed. The model has been applied to two real application cases, showing high accuracy output, resulting in a potentially effective tool for predictive maintenance in different industrial sectors.

An Edge-Fog-Cloud Computing-Based Digital Twin Model for Prognostics Health Management of Process Manufacturing Systems

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.

Battery prognostics and health management for electric vehicles under industry 4.0

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.

Virtual sample generation for model-based prognostics and health management of on-board high-speed train control system

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.

Computational Reproducibility Within Prognostics and Health Management

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.

Health management based on fusion prognostics for avionics systems

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.

Overview of the Importance of Intelligent Approaches on Machinery Faults Diagnosis and Prediction Based on Prognostic and Health Management/Condition-Based Maintenance

Condition monitoring is increasingly used to anticipate and detect failures of industrial machines.Failures of machines can cause high maintenance or replacement costs.If neglected,it may result in catastrophic accidents leading to production shrinkage.The potential failure would negatively affect the profitability of the company,including production shut down,cost of spare parts,cost of labor,damage of reputation,risk of injury to people and the environment.In recent years,condition-based maintenance( CBM) and prognostic and health management( PHM) are developed and formed a strong connection among science,engineering,computer,reliability,communication,management,etc.Computerized maintenance management systems( CMMS) store a lot of data regarding the fault diagnosis and life prediction of the machinery equipment.It's too necessary to uncover useful knowledge from the huge amount of data.It's vital to find the ways to obtain useful and concise information from these data.This information can be of great influence in the decision making of managers.This article is a review of intelligent approaches in machinery faults diagnosis and prediction based on PHM and CBM.

Dynamically updated digital twin for prognostics and health management:Application in permanent magnet synchronous motor

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.

Boosting battery state of health estimation based on self-supervised learning

State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.

Review on Lithium-ion Battery PHM from the Perspective of Key PHM Steps

Prognostics and health management(PHM)has gotten considerable attention in the background of Industry 4.0.Battery PHM contributes to the reliable and safe operation of electric devices.Nevertheless,relevant reviews are still continuously updated over time.In this paper,we browsed extensive literature related to battery PHM from 2018to 2023 and summarized advances in battery PHM field,including battery testing and public datasets,fault diagnosis and prediction methods,health status estimation and health management methods.The last topic includes state of health estimation methods,remaining useful life prediction methods and predictive maintenance methods.Each of these categories is introduced and discussed in details.Based on this survey,we accordingly discuss challenges left to battery PHM,and provide future research opportunities.This research systematically reviews recent research about battery PHM from the perspective of key PHM steps and provide some valuable prospects for researchers and practitioners.

Prognostics and health management of alkaline water electrolyzer: Techno-economic analysis considering replacement moment

Recently,considerable attention has been paid to the installation of renewable energy capacity to mitigate global CO_(2) emissions.H_(2) produced using water electrolysis and renewable energy is regarded as a clean energy carrier,generating electricity without CO_(2) emissions,called‘Green H 2’.In this paper,a prognostics and health man-agement model for an alkaline water electrolyzer was proposed to predict the load voltage on the electrolyzer to obtain the state of health information.The prognostics and health management model was developed by training historical operating data via machine learning models,support vector machine and gaussian process regression,showing the root mean square error of 1.28×10^(−3) and 8.03×10^(−6).In addition,a techno-economic analysis was performed for a green H_(2) production system,composed of 1 MW of photovoltaic plant and 1 MW of alkaline water electrolyzer,to provide economic insights and feasibility of the system.A levelized cost of H_(2) of$6.89 kgH_(2)−1 was calculated and the potential to reach the levelized cost of H_(2) from steam methane reforming with carbon capture and storage was shown by considering the learning rate of the photovoltaic module and elec-trolyzer.Finally,the replacement of the alkaline water electrolyzer at around 10 years was preferred to increase the net present value from the green H_(2) production system when capital expenditure and replacement cost are low enough.

Deep neural network based classification of rolling element bearings and health degradation through comprehensive vibration signal analysis

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.

Rolling bearing fault diagnostics based on improved data augmentation and ConvNet

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.

Research on Active Safety Methodologies for Intelligent Railway Systems

Safety is essential when building a strong transportation system.As a key development direction in the global railway system,the intelligent railway has safety at its core,making safety a top priority while pursuing the goals of efficiency,convenience,economy,and environmental friendliness.This paper describes the state of the art and proposes a system architecture for intelligent railway systems.It also focuses on the development of railway safety technology at home and abroad,and proposes the active safety method and technology system based on advanced theoretical methods such as the in-depth integration of cyber–physical systems(CPS),data-driven models,and intelligent computing.Finally,several typical applications are demonstrated to verify the advancement and feasibility of active safety technology in intelligent railway systems.

An ontological modelling of multi-attribute criticality analysis to guide Prognostics and Health Management program development

Digital technologies are becoming more pervasive and industrial companies are exploiting them to enhance the potentialities related to Prognostics and Health Management(PHM).Indeed,PHM allows to evaluate the health state of the physical assets as well as to predict their future behaviour.To be effective in developing PHM programs,the most critical assets should be identified so to direct modelling efforts.Several techniques could be adopted to evaluate asset criticality;in industrial practice,criticality analysis is amongst the most utilised.Despite the advancement of artificial intelligence for data analysis and predictions,the criticality analysis,which is built upon both quantitative and qualitative data,has not been improved accordingly.It is the goal of this work to propose an ontological formalisation of a multi-attribute criticality analysis in order to i)fix the semantics behind the terms involved in the analysis,ii)standardize and uniform the way criticality analysis is performed,and iii)take advantage of the reasoning capabilities to automatically evaluate asset criticality and associate a suitable maintenance strategy.The developed ontology,called MOCA,is tested in a food company featuring a global footprint.The application shows that MOCA can accomplish the prefixed goals;specifically,high priority assets towards which direct PHM programs are identified.In the long run,ontologies could serve as a unique knowledge base that integrate multiple data and information across facilities in a consistent way.As such,they will enable advanced analytics to take place,allowing to move towards cognitive Cyber Physical Systems that enhance business performance for companies spread worldwide.

Remaining Useful Life Prediction for a Roller in a Hot Strip Mill Based on Deep Recurrent Neural Networks

Accurate estimation of the remaining useful life(RUL)and health state for rollers is of great significance to hot rolling production.It can provide decision support for roller management so as to improve the productivity of the hot rolling process.In addition,the RUL prediction for rollers is helpful in transitioning from the current regular maintenance strategy to conditional-based maintenance.Therefore,a new method that can extract coarse-grained and fine-grained features from batch data to predict the RUL of the rollers is proposed in this paper.Firstly,a new deep learning network architecture based on recurrent neural networks that can make full use of the extracted coarsegrained fine-grained features to estimate the heath indicator(HI)is developed,where the HI is able to indicate the health state of the roller.Following that,a state-space model is constructed to describe the HI,and the probabilistic distribution of RUL can be estimated by extrapolating the HI degradation model to a predefined failure threshold.Finally,application to a hot strip mill is given to verify the effectiveness of the proposed methods using data collected from an industrial site,and the relatively low RMSE and MAE values demonstrate its advantages compared with some other popular deep learning methods.

Test selection and optimization for PHM based on failure evolution mechanism model

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.

A model to determining the remaining useful life of rotating equipment,based on a new approach to determining state of degradation

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.

A novel testability model for health management of heading attitude system

Prognostics and health management （PHM） is very important to guarantee the reliability and safety of aerospace systems, and sensing and test are the precondition of PHM. Integrating design for testability into early design stage of system early design stage is deemed as a fundamental way to improve PHM performance, and testability model is the base of testability analysis and design. This paper discusses a hierarchical model-based approach to testability modeling and analysis for heading attitude system health management. Quantified directed graph, of which the nodes represent components and tests and the directed edges represent fault propagation paths, is used to describe fault-test dependency, and quantitative testability information is assigned to nodes and directed edges. The fault dependencies between nodes can be obtained by functional fault analysis methodology that captures the physical architecture and material flows such as energy, heat, data, and so on. By incorporating physics of failure models into component, the dynamic process of a failing or degrading component can be projected onto system behavior, i.e., system symptoms. Then, the analysis of extended failure modes, mechanisms and effects is utilized to construct fault evolution-test dependency. Using this integrated model, the designers and system analysts can assess the test suite＇s fault detectability, fault isolability and fault predictability. And heading attitude system application results show that the proposed model can support testability analysis and design for PHM very well.

Physics-Informed Deep Neural Network for Bearing Prognosis with Multisensory Signals

Prognosis of bearing is critical to improve the safety,reliability,and availability of machinery systems,which provides the health condition assessment and determines how long the machine would work before failure occurs by predicting the remaining useful life(RUL).In order to overcome the drawback of pure data-driven methods and predict RUL accurately,a novel physics-informed deep neural network,named degradation consistency recurrent neural network,is proposed for RUL prediction by integrating the natural degradation knowledge of mechanical components.The degradation is monotonic over the whole life of bearings,which is characterized by temperature signals.To incorporate the knowledge of monotonic degradation,a positive increment recurrence relationship is introduced to keep the monotonicity.Thus,the proposed model is relatively well understood and capable to keep the learning process consistent with physical degradation.The effectiveness and merit of the RUL prediction using the proposed method are demonstrated through vibration signals collected from a set of run-to-failure tests.