Prognostics and Remaining Useful Life Prediction of Machinery:Advances,Opportunities,and Challenges

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.

Gas liquid cylindrical cyclone flow regime identification using machine learning combined with experimental mechanism explanation

The flow regimes of GLCC with horizon inlet and a vertical pipe are investigated in experiments,and the velocities and pressure drops data labeled by the corresponding flow regimes are collected.Combined with the flow regimes data of other GLCC positions from other literatures in existence,the gas and liquid superficial velocities and pressure drops are used as the input of the machine learning algorithms respectively which are applied to identify the flow regimes.The choosing of input data types takes the availability of data for practical industry fields into consideration,and the twelve machine learning algorithms are chosen from the classical and popular algorithms in the area of classification,including the typical ensemble models,SVM,KNN,Bayesian Model and MLP.The results of flow regimes identification show that gas and liquid superficial velocities are the ideal type of input data for the flow regimes identification by machine learning.Most of the ensemble models can identify the flow regimes of GLCC by gas and liquid velocities with the accuracy of 0.99 and more.For the pressure drops as the input of each algorithm,it is not the suitable as gas and liquid velocities,and only XGBoost and Bagging Tree can identify the GLCC flow regimes accurately.The success and confusion of each algorithm are analyzed and explained based on the experimental phenomena of flow regimes evolution processes,the flow regimes map,and the principles of algorithms.The applicability and feasibility of each algorithm according to different types of data for GLCC flow regimes identification are proposed.

Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant

Fault diagnostics is important for safe operation of nuclear power plants(NPPs). In recent years, data-driven approaches have been proposed and implemented to tackle the problem, e.g., neural networks, fuzzy and neurofuzzy approaches, support vector machine, K-nearest neighbor classifiers and inference methodologies. Among these methods, dynamic uncertain causality graph(DUCG)has been proved effective in many practical cases. However, the causal graph construction behind the DUCG is complicate and, in many cases, results redundant on the symptoms needed to correctly classify the fault. In this paper, we propose a method to simplify causal graph construction in an automatic way. The method consists in transforming the expert knowledge-based DCUG into a fuzzy decision tree(FDT) by extracting from the DUCG a fuzzy rule base that resumes the used symptoms at the basis of the FDT. Genetic algorithm(GA) is, then, used for the optimization of the FDT, by performing a wrapper search around the FDT: the set of symptoms selected during the iterative search are taken as the best set of symptoms for the diagnosis of the faults that can occur in the system. The effectiveness of the approach is shown with respect to a DUCG model initially built to diagnose 23 faults originally using 262 symptoms of Unit-1 in the Ningde NPP of the China Guangdong Nuclear Power Corporation. The results show that the FDT, with GA-optimized symptoms and diagnosis strategy, can drive the construction of DUCG and lower the computational burden without loss of accuracy in diagnosis.

Development of an integrated dynamic model for supply security and resilience analysis of natural gas pipeline network systems

An integrated dynamic model of natural gas pipeline networks is developed in this paper.Components for gas supply,e.g.,pipelines,junctions,compressor stations,LNG terminals,regulation stations and gas storage facilities are included in the model.These components are firstly modeled with respect to their properties and functions and,then,integrated at the system level by Graph Theory.The model can be used for simulating the system response in different scenarios of operation,and evaluate the consequences from the perspectives of supply security and resilience.A case study is considered to evaluate the accuracy of the model by benchmarking its results against those from literature and the software Pipeline Studio.Finally,the model is applied on a relatively complex natural gas pipeline network and the results are analyzed in detail from the supply security and resilience points of view.The main contributions of the paper are:firstly,a novel model of a complex gas pipeline network is proposed as a dynamic state-space model at system level;a method,based on the dynamic model,is proposed to analyze the security and resilience of supply from a system perspective.

Hierarchical Modeling by Recursive Unsupervised Spectral Clustering and Network Extended Importance Measures to Analyze the Reliability Characteristics of Complex Network Systems

The complexity of large-scale network systems made of a large number of nonlinearly interconnected components is a restrictive facet for their modeling and analysis. In this paper, we propose a framework of hierarchical modeling of a complex network system, based on a recursive unsupervised spectral clustering method. The hierarchical model serves the purpose of facilitating the management of complexity in the analysis of real-world critical infrastructures. We exemplify this by referring to the reliability analysis of the 380 kV Italian Power Transmission Network (IPTN). In this work of analysis, the classical component Importance Measures (IMs) of reliability theory have been extended to render them compatible and applicable to a complex distributed network system. By utilizing these extended IMs, the reliability properties of the IPTN system can be evaluated in the framework of the hierarchical system model, with the aim of providing risk managers with information on the risk/safety significance of system structures and components.

A Modified Generative Adversarial Network for Fault Diagnosis in High-Speed Train Components with Imbalanced and Heterogeneous Monitoring Data

Data-driven methods are widely considered for fault diagnosis in complex systems.However,in practice,the between-class imbalance due to limited faulty samples may deteriorate their classification performance.To address this issue,synthetic minority methods for enhancing data have been proved to be effective in many applications.Generative adversarial networks(GANs),capable of automatic features extraction,can also be adopted for augmenting the faulty samples.However,the monitoring data of a complex system may include not only continuous signals but also discrete/categorical signals.Since the current GAN methods still have some challenges in handling such heterogeneous monitoring data,a Mixed Dual Discriminator GAN(noted as M-D2GAN)is proposed in this work.In order to render the expanded fault samples more aligned with the real situation and improve the accuracy and robustness of the fault diagnosis model,different types of variables are generated in different ways,including floating-point,integer,categorical,and hierarchical.For effectively considering the class imbalance problem,proper modifications are made to the GAN model,where a normal class discriminator is added.A practical case study concerning the braking system of a high-speed train is carried out to verify the effectiveness of the proposed framework.Compared to the classic GAN,the proposed framework achieves better results with respect to F-measure and G-mean metrics.

A STAMP-Game model for accident analysis in oil and gas industry

Accidents in engineered systems are usually generated by complex socio-technical factors.It is beneficial to investigate the increasing complexity and coupling of these factors from the perspective of system safety.Based on system and control theories,System-Theoretic Accident Model and Processes(STAMP)is a widely recognized approach for accident analysis.In this paper,we propose a STAMP-Game model to analyze accidents in oil and gas storage and transportation systems.Stakeholders in accident analysis by STAMP can be regarded as players of a game.Game theory can,thus,be adopted in accident analysis to depict the competition and cooperation between stakeholders.Subsequently,we established a game model to study the strategies of both supervisory and supervised entities.The obtained results demonstrate that the proposed game model allows for identifying the effectiveness deficiency of the supervisory entity,and the safety and protection altitudes of the supervised entity.The STAMP-Game model can generate quantitative parameters for supporting the behavior and strategy selections of the supervisory and supervised entities.The quantitative data obtained can be used to guide the safety improvement,to reduce the costs of safety regulation violation and accident risk.

Measuring reliability under epistemic uncertainty:Review on non-probabilistic reliability metrics

In this paper, a systematic review of non-probabilistic reliability metrics is conducted to assist the selection of appropriate reliability metrics to model the influence of epistemic uncertainty. Five frequently used non-probabilistic reliability metrics are critically reviewed, i.e., evidence- theory-based reliability metrics, interval-analysis-based reliability metrics, fuzzy-interval-analysis- based reliability metrics, possibility-theory-based reliability metrics （posbist reliability） and uncertainty-theory-based reliability metrics （belief reliability）. It is pointed out that a qualified reli- ability metric that is able to consider the effect of epistemic uncertainty needs to （ 1 ） compensate the conservatism in the estimations of the component-level reliability metrics caused by epistemic uncertainty, and （2） satisfy the duality axiom, otherwise it might lead to paradoxical and confusing results in engineering applications. The five commonly used non-probabilistic reliability metrics are compared in terms of these two properties, and the comparison can serve as a basis for the selection of the appropriate reliability metrics.

Application of reliability technologies in civil aviation: Lessons learnt and perspectives

We consider reliability engineering in modern civil aviation industry, and the related engineering activities and methods. We consider reliability in a broad sense, referring to other system characteristics that are related to it, like availability, maintainability, safety and durability. We covered the entire lifecycle of the equipment, including reliability requirement identification, reliability analysis and design, verification and validation of reliability requirements(typically involved in the equipment design and development phase), quality assurance(which typically enters in the manufacturing phase), and fault diagnosis and prognosis and maintenance(which are connected to the operation phase). Lessons learnt from reliability engineering practices in civil aviation industry are given, which might serve as reference for reliability managers and engineers, also from other industries with high reliability requirements.

Data-driven reliability analysis of Boeing 787 Dreamliner

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.

A compositional method to model dependent failure behavior based on PoF models

In this paper, a new method is developed to model dependent failure behavior among failure mechanisms. Unlike the existing methods, the developed method models the root cause of the dependency explicitly, so that a deterministic model, rather than a probabilistic one, can be established. Three steps comprise the developed method. First, physics-of-failure（PoF） models are utilized to model each failure mechanism. Then, interactions among failure mechanisms are modeled as a combination of three basic relations, competition, superposition and coupling. This is the reason why the method is referred to as ＂compositional method＂. Finally, the PoF models and the interaction model are combined to develop a deterministic model of the dependent failure behavior. As a demonstration, the method is applied on an actual spool and the developed failure behavior model is validated by a wear test. The result demonstrates that the compositional method is an effective way to model dependent failure behavior.

Integrated fault estimation and fault-tolerant control for a flexible regional aircraft

The article focuses on the design and application of an active reconfigurable controller that mitigates the effects of gust load and actuator faults on a flexible aircraft.A novel integrated adaptive output feedback scheme is investigated to address the actuator faults.The real-time fault values provided by the fault estimation module are considered in the reconfigurable control law to improve the fault-tolerant capability.The estimate values of faults and control gains are calculated by analyzing the stability of the overall system.The proposed controller is simulated using a flexible aircraft model with a discrete‘1-cosine’gust,and the results show that it can effectively mitigate the wing root moments and recover the flight maneuver stability after the aircraft suffered from gusts.

A critique of reliability prediction techniques for avionics applications

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.

Modeling and analysis of mover gaps in tubular moving-magnet linear oscillating motors

A tubular moving-magnet linear oscillating motor（TMMLOM） has merits of high efficiency and excellent dynamic capability. To enhance the thrust performance, quasi-Halbach permanent magnet（PM） arrays are arranged on its mover in the application of a linear electro-hydrostatic actuator in more electric aircraft. The arrays are assembled by several individual segments, which lead to gaps between them inevitably. To investigate the effects of the gaps on the radial magnetic flux density and the machine thrust in this paper, an analytical model is built considering both axial and radial gaps. The model is validated by finite element simulations and experimental results.Distributions of the magnetic flux are described in condition of different sizes of radial and axial gaps. Besides, the output force is also discussed in normal and end windings. Finally, the model has demonstrated that both kinds of gaps have a negative effect on the thrust, and the linear motor is more sensitive to radial ones.

An energy-based coupling degradation propagation model and its application to aviation actuation system

The degradation of components in complex mechatronic systems involves multiple physical processes which will cause coupling interactions among nodes in the system.The interaction of nodes may be carried out not only by physical connections but also by the environment which cannot be described by single network using the traditional methods.In order to give out a unified model to quantitatively describe the coupling degradation spreading by both physical connections and environment,a novel Energy-Flow-Field Network(EFFN)and a coupling degradation model based on EFFN are proposed in this paper.The EFFN is driven by energy flow and the state transition of spatially related nodes is triggered by the dissipation energy.An application is conducted on aviation actuation system in which the degradation spreading by fluid-thermal-solid interaction is considered.The degradation path and the most probable fault reason can be obtained by combining the state transition and energy output of nodes,which is consistent with the given scenario.