Search

This article proposes a novel deep learning based fusion prognostic method for remaining useful life (RUL) prediction of engineering systems. The proposed framework strategically combines the advantages of bidirectional long short-term memory (BLSTM) networks and particle filter (PF) method and meanwhile mitigates their limitations. In the proposed framework, BLSTM networks are applied for further extracting, selecting, and fusing discriminative features to form predicted measurements of the identified degradation indicator. Simultaneously, PF is utilized to estimate system state and identify unknown parameters of the degradation model for RUL prediction. Hence, the proposed fusion prognostic framework has two innovative features: first, the preprocessed features from raw multisensor data can be intelligently extracted, selected, and fused by the BLSTM networks without specific domain knowledge of feature engineering; second, the predicted measurements with uncertainties obtained from the BLSTM networks will be properly represented by the PF in a transparent manner. Moreover, the developed approach is experimentally validated with machining tool wear tests on a computer numerical control (CNC) milling machine. In addition, the popular techniques employed in this field are also investigated to compare with the proposed method. [ABSTRACT FROM AUTHOR]

Modern engineered systems generally work under complex operational conditions. However, most of the existing artificial intelligence (AI)-based prognostic methods still lack an effective model that can utilize operational conditions data for remaining useful life (RUL) prediction. This paper develops a novel prognostic method based on bidirectional long short-term memory (BLSTM) networks. The method can integrate multiple sensors data with operational conditions data for RUL prediction of engineered systems. The proposed architecture based on BLSTM networks includes three main parts: first, one BLSTM network is used to directly extract features hidden in the multiple raw sensors signals; second, another BLSTM network is employed to learn higher features from operational conditions signals and the learned features from the sensors signals; and, third, fully connected layers and a linear regression layer are stacked to generate the target output of the RUL prediction. Unlike other AI-based prognostic methods, the developed method can simultaneously model both sensors data and operational conditions data in a consolidated framework. The proposed approach is demonstrated through a case study on aircraft turbofan engines, and comparisons with other popular state-of-the-art methods are also presented. [ABSTRACT FROM AUTHOR]

Degradation observations of modern engineering systems, such as manufacturing systems, turbine engines, and high-speed trains, often demonstrate various patterns of time-varying degradation rates. General degradation process models are mainly introduced for constant degradation rates, which cannot be used for time-varying situations. Moreover, the issue of sparse degradation observations and the problem of evolving degradation observations both are practical challenges for the degradation analysis of modern engineering systems. In this paper, parametric inverse Gaussian process models are proposed to model degradation processes with constant, monotonic, and S-shaped degradation rates, where physical meaning of model parameters for time-varying degradation rates is highlighted. Random effects are incorporated into the degradation process models to model the unit-to-unit variability within product population. A general Bayesian framework is extended to deal with the degradation analysis of sparse degradation observations and evolving observations. An illustrative example derived from the reliability analysis of a heavy-duty machine tool's spindle system is presented, which is characterized as the degradation analysis of sparse degradation observations and evolving observations under time-varying degradation rates. [ABSTRACT FROM AUTHOR]

We design and investigate the optical properties of a novel hollow-core antiresonant fiber with nested elliptical cladding elements. This new structure shows low confinement loss even with a relatively small core. The lowest confinement loss of this structure is more than two orders of magnitude smaller than its circular-element counterparts. When the size of the cladding elements is properly designed, higher order core modes resonantly couple with the cladding modes effectively, resulting in an extremely high higher order-mode extinction ratio ( $>$ $10^4$). This good single mode performance can be achieved for a wide range of cladding element parameters, which would increase the fabrication tolerance. The new fiber also shows low bending loss for a wide range of bend radii. Moreover, dispersion properties of the new structure are also investigated under both unfilled and filled conditions. Numerical results show that antiresonant structures with the same core diameter and strut thickness have similar dispersion curves. The zero dispersion wavelength within the fundamental antiresonant transmission band can be tuned over tens of nanometers by increasing the pressure up to 50 bar when the fiber is filled with argon. [ABSTRACT FROM PUBLISHER]

Modern engineering systems are generally composed of multicomponents and are characterized as multifunctional. Condition monitoring and health management of these systems often confronts the difficulty of degradation analysis with multiple performance characteristics. Degradation observations generally exhibit an s-dependent nature and sometimes experience incomplete measurements. These issues necessitate investigating multiple s-dependent degradations analysis with incomplete observations. In this paper, a new type of bivariate degradation model based on inverse Gaussian processes and copulas is proposed. A two-stage Bayesian method is introduced to implement parameter estimation for the bivariate degradation model by treating the degradation processes and copula function separately. Degradation inferences for missing observation points, and for future observation points are investigated. A simulation study is presented to study the effectiveness of the dependence modeling and degradation inference of the proposed method. For demonstration, a bivariate degradation analysis of positioning accuracy and output power of heavy machine tools subject to incomplete measurements is provided. [ABSTRACT FROM AUTHOR]

In order to arrange maintenance resources according to system condition, the lead time needs to be considered within the context of condition-based maintenance (CBM). Therefore, a scheduling threshold is introduced to replace the time to schedule, which is used as a decision variable in combination with a maintenance threshold and a failure threshold. The long-run expected cost rate for maintenance considers the maintenance cost, the cost of the waiting time of suppliers and customers. In this way, suppliers can schedule maintenance services in advance when the system condition reaches the scheduling threshold, and perform maintenance when the system condition exceeds the maintenance threshold. Furthermore, the optimal maintenance plan is updated dynamically in the framework of Prognostics and Health Management (PHM). Finally, a numerical example is provided to demonstrate the effectiveness and the dynamic nature of the proposed method. [ABSTRACT FROM AUTHOR]

Traditionally, degradation testing and condition monitoring are used separately to investigate field reliability. Barriers are naturally formed between these two types of methods due to condition-discrepancies between lab testing and field monitoring, as well as time-varying missions among product population groups. In this paper, a joint framework for field reliability analysis is presented by integrating degradation testing data as well as mission operating information with condition monitoring observations. A coherent modeling strategy is introduced for the information integration by gradually adopting random effects, dynamic covariates, and marker processes into a baseline stochastic degradation model. In detail, random effects are introduced to cope with the inherent unit-to-unit variation. Dynamic covariates are adopted to deal with the external condition heterogeneity. Marker processes are used to account for the time-varying missions. To facilitate information integration and reliability analysis, the Bayesian method is used to implement parameter estimation and degradation analysis. The reliability assessment of products' populations, degradation prediction, and residual life prediction of individual products are investigated. Finally, an illustrative example for field degradation analysis of oil debris in a lubrication system of a machine tool's spindle system is presented. The effectiveness of information integration and the capability of degradation inference are demonstrated through this example. [ABSTRACT FROM PUBLISHER]

Because of the complexity of engineering systems, and the fact that insufficient data are only available to obtain the precise state probability of components, an extended universal generating function (UGF) based on belief function theory is introduced in this paper to conduct the reliability analysis of multi-state systems (MSSs) with epistemic uncertainty. The behavior of common cause failures (CCFs) is further incorporated, and the occurrence probability of CCFs is evaluated using a weighted impact vector method. A numerical example is used to illustrate how the proposed method works. In addition, a global optimization method is used to obtain the truth interval of the system reliability, and the results are compared with those obtained by using some existing methods. The case study shows that the belief UGF method can effectively avoid the interval expansion problem and the overestimation problem involved in the interval UGF method, and the proposed method can be used to provide a reliable way to evaluate the reliability of MSSs with interval data and CCFs. [ABSTRACT FROM PUBLISHER]

Traditional time-based reliability assessment methods evaluate the reliability of a multi-state system (MSS) from a population or a statistical perspective that the reliability of a system is computed purely based upon historical time-to-failure data collected from a large population of identical components or systems. These methods, however, fail to characterize the stochastic behaviors of a specific individual system. In this paper, by utilizing system-level observation history, a dynamic reliability assessment method for MSSs is put forth. The proposed recursive Bayesian formula is able to dynamically update the reliability function of a specific MSS over time by incorporating system-level inspection data. The dynamic reliability function, state probabilities, and remaining useful life distribution of an MSS in residual lifetime are derived for two common cases: the degradation of components follows a homogeneous continuous time Markov process, and a non-homogeneous continuous time Markov process. The effectiveness and accuracy of the proposed method are demonstrated via two numerical examples. [ABSTRACT FROM PUBLISHER]

In this letter, a 40-Gb/s optical modulator driver in 90-nm CMOS technology is presented. The design is based on the distributed amplifier (DA) topology with the proposed modified cascode stage to obtain high gain and large bandwidth, while also capable of protecting the MOS transistor under large output voltage swing. The modified cascode stage DA with enhanced high-voltage driving capability can reach an operating data rate up to 40 Gb/s with an differential output voltage swing of 4 Vpp (~3-V eye amplitude), which can be used for driving 50- $\Omega $ silicon modulators. [ABSTRACT FROM PUBLISHER]

This paper develops a Bayesian framework to assess the reliability and performance of multi-state systems (MSSs). An MSS consists of multiple multi-state components of which the degradation follows a Markov process. Due to the lack of sufficient data, and only vague knowledge from experts, the transition intensities of multi-state components between any pair of states and the state probabilities cannot be precisely estimated. The proposed Bayesian method can merge prior knowledge from experts' judgments with continuous and discontinuous inspection data to obtain posterior distributions of transition intensities. A simulation method embedded with the universal generating function (UGF) is developed to estimate the posterior state probabilities, the reliability, and the performance of the entire MSS. Two numerical experiments are presented to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]