An improved prognostics model with its application to the remaining useful life of turbofan engine

2021 ◽  
pp. 095441002110504
Author(s):  
Jia-Jun He ◽  
Yong-Ping Zhao
Keyword(s):  
Prior Knowledge ◽  
Health Management ◽  
Remaining Useful Life ◽  
Maintenance Cost ◽  
Actual System ◽  
Health States ◽  
Estimation Errors ◽  
Turbofan Engine ◽  
Useful Life

Machinery prognostics play a crucial role in upgrading machinery service and optimizing machinery operation and maintenance schedule by forecasting the remaining useful life (RUL) of the monitored equipment, which has become more and more popular in recent years. The safety of aviation is one of the issues that people are most concerned about in the field of transportation, since it might cause disastrous loss of life and property once accident happened. The turbofan engine is an important part of the aircraft that provides thrust for plane. With aging, the turbofan engine becomes prone to failures. As a result, it would be worth studying prognostics in turbofan engine to improve the reliability of machinery and reduce unnecessary maintenance cost. Recently, a data-driven prognostics modeling strategy called the classification of predictions strategy (CPS) was proposed, in which the continuous signal and the discrete modes of an actual system come together to achieve RUL estimation. However, machine health states measured from classification rarely have just one potential situation, and this strategy cannot determine whether the fault occurs or not by a certain probability which comes closer to reality. Moreover, since there is no information and prior knowledge of prognostics application, it is hard to obtain the probability of various situations from raw measured data. Hence, based on previous work, this paper proposes an improved prognostics modeling method named the classification of predictions strategy with decision probability (CPS-DP), whose key innovations mainly include three parts: (1) decision probability process (DPP) where each step of multi-step prediction obeys geometric distribution and can judge whether the failure state occurs using the decision probability; (2) decision probability calculation (DPC) algorithm, which is first proposed by this paper and can calculate the values of decision probability without prior knowledge of prognostics application; and (3) withdrawal mechanism optimizer (WMO), which is specially designed to compensate for the shortcomings of DPP and further enhance the performance of the prognostics model. In brief, first, CPS is used to build a basic prognostics model to acquire RUL estimation results, in which the information applied to find the probability has been contained. Later, the mean of RUL estimation errors is figured from the results, which is further employed to calculate the probability using DPC algorithm. Then, CPS-DP can be achieved by means of integrating two parts: DPP and CPS. Furthermore, to further improve the performance, WMO is utilized to optimize CPS-DP with rolling back predictions. Ultimately, an enhanced prognostic model based on CPS-DP is set up through uniting CPS, DPP, and WMO. To validate the proposed method, experimental results on the turbofan engine in 2008 prognostics and health management competition are investigated.

scholarly journals Remaining Useful Life Prediction of Bearing with Vibration Signals Based on a Novel Indicator

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Bo Wu ◽  
Wei Li ◽  
Ming-quan Qiu
Keyword(s):  
Neural Network ◽  
Health Management ◽  
Rbf Neural Network ◽  
Degradation Process ◽  
Rate Function ◽  
Remaining Useful Life ◽  
Maintenance Cost ◽  
Failure Rate Function ◽  
Useful Life ◽  
The Time Domain

Aiming at reducing the production downtime and maintenance cost, prognostics and health management (PHM) of rotating machinery often includes the remaining useful life (RUL) prediction of bearings. In this paper, a method combining the generalized Weibull failure rate function (WFRF) and radial basis function (RBF) neural network is developed to deal with the RUL prediction of bearings. A novel indicator, namely, the power value on the sensitive frequency band (SFB), is proposed to track bearing degradation process. Generalized WFRF is used to fit the degradation indicator series to reduce the effect of noise and avoid areas of fluctuation in the time domain. RBF neural network is employed to predict the RUL of bearings with times and fitted power values at present and previous inspections as input. Meanwhile, the life percentage is selected as output. The performance of the proposed method is validated by an accelerated bearing run-to-failure experiment, and the results demonstrate the advantage of this method in achieving more accurate RUL prediction.

Statistical Health Diagnostics for Water-Cooled Power Generator Stator Winding Against Water Absorption

2014 ◽  
Author(s):  
Kyung Min Park ◽  
Byeng D. Youn ◽  
Joung Taek Yoon ◽  
Hee Soo Kim ◽  
Beom Chan Jang
Keyword(s):  
Water Absorption ◽  
Health Management ◽  
Health Condition ◽  
Remaining Useful Life ◽  
Maintenance Cost ◽  
Stator Winding ◽  
Power Generator ◽  
Reasoning System ◽  
Useful Life ◽  
Generator Stator

One of most important components in power generator is a stator winding since an unexpected failure of the water absorbed-winding leads to plant shut-down and substantial loss. Typically the stator winding is maintained with a time- or usage-based strategy, which could result in substantial waste of remaining life, high maintenance cost and low plant availability. Recently, the field of prognostics and health management offers general diagnostic and prognostic techniques to precisely assess the health condition and robustly predict the remaining useful life of an engineered system, with an aim to address the aforementioned deficiencies. This research aims at developing health reasoning system of power generator stator winding with physical and statistical analysis against water absorption. And it is based upon the capacitance measurements on winding insulations. In particular, a new health measure, Directional Mahalanobis Distance (DMD), is proposed to quantify the health condition. In addition, the empirical health grade system based upon the proposed technique, DMD, is carried out with the maintenance history. The smart health reasoning system is validated using eight years’ field data from eight generators, each of which contains forty two windings.

Remaining useful life estimation: a review on stochastic process-based approaches

2020 ◽  
Vol 14 ◽  
Author(s):  
Dangbo Du ◽  
Jianxun Zhang ◽  
Xiaosheng Si ◽  
Changhua Hu
Keyword(s):  
Stochastic Process ◽  
Health Management ◽  
Remaining Useful Life ◽  
Future Trends ◽  
Prognostics And Health Management ◽  
Inverse Gaussian ◽  
Life Estimation ◽  
Inverse Gaussian Process ◽  
Pros And Cons ◽  
Useful Life

Background: Remaining useful life (RUL) estimation is the central mission to the complex systems’ prognostics and health management. During last decades, numbers of developments and applications of the RUL estimation have proliferated. Objective: As one of the most popular approaches, stochastic process-based approach has been widely used for characterizing the degradation trajectories and estimating RULs. This paper aimed at reviewing the latest methods and patents on this topic. Methods: The review is concentrated on four common stochastic processes for degradation modelling and RUL estimation, i.e., Gamma process, Wiener process, inverse Gaussian process and Markov chain. Results: After a briefly review of these four models, we pointed out the pros and cons of them, as well as the improvement direction of each method. Conclusion: For better implementation, the applications of these four approaches on maintenance and decision-making are systematically introduced. Finally, the possible future trends are concluded tentatively.

scholarly journals A Genetic Algorithm Optimized RNN-LSTM Model for Remaining Useful Life Prediction of Turbofan Engine

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 285
Author(s):  
Kwok Tai Chui ◽  
Brij B. Gupta ◽  
Pandian Vasant
Keyword(s):  
Genetic Algorithm ◽  
Feature Extraction ◽  
Prediction Model ◽  
Prediction Models ◽  
Remaining Useful Life ◽  
Prediction Algorithm ◽  
Short Term ◽  
Turbofan Engine ◽  
Term Prediction ◽  
Useful Life

Understanding the remaining useful life (RUL) of equipment is crucial for optimal predictive maintenance (PdM). This addresses the issues of equipment downtime and unnecessary maintenance checks in run-to-failure maintenance and preventive maintenance. Both feature extraction and prediction algorithm have played crucial roles on the performance of RUL prediction models. A benchmark dataset, namely Turbofan Engine Degradation Simulation Dataset, was selected for performance analysis and evaluation. The proposal of the combination of complete ensemble empirical mode decomposition and wavelet packet transform for feature extraction could reduce the average root-mean-square error (RMSE) by 5.14–27.15% compared with six approaches. When it comes to the prediction algorithm, the results of the RUL prediction model could be that the equipment needs to be repaired or replaced within a shorter or a longer period of time. Incorporating this characteristic could enhance the performance of the RUL prediction model. In this paper, we have proposed the RUL prediction algorithm in combination with recurrent neural network (RNN) and long short-term memory (LSTM). The former takes the advantages of short-term prediction whereas the latter manages better in long-term prediction. The weights to combine RNN and LSTM were designed by non-dominated sorting genetic algorithm II (NSGA-II). It achieved average RMSE of 17.2. It improved the RMSE by 6.07–14.72% compared with baseline models, stand-alone RNN, and stand-alone LSTM. Compared with existing works, the RMSE improvement by proposed work is 12.95–39.32%.

Application of Prognostics and Health Management (PHM) to Software System Fault and Remaining Useful Life (RUL) Prediction

2021 ◽  
Author(s):  
Mohammad Rubyet Islam ◽  
Peter Sandborn
Keyword(s):  
Health Management ◽  
Standard Test ◽  
Remaining Useful Life ◽  
Software Systems ◽  
Prognostics And Health Management ◽  
Performance Parameters ◽  
Statistical Validation ◽  
Useful Life ◽  
Test Beds

Abstract Prognostics and Health Management (PHM) is an engineering discipline focused on predicting the point at which systems or components will no longer perform as intended. The prediction is often articulated as a Remaining Useful Life (RUL). RUL is an important decision-making tool for contingency mitigation, i.e., the prediction of an RUL (and its associated confidence) enables decisions to be made about how and when to maintain the system. PHM is generally applied to hardware systems in the electronics and non-electronics application domains. The application of PHM (and RUL) concepts has not been explored for application to software. Today, software (SW) health management is confined to diagnostic assessments that identify problems, whereas prognostic assessment potentially indicates when in the future a problem will become detrimental to the operation of the system. Relevant areas such as SW defect prediction, SW reliability prediction, predictive maintenance of SW, SW degradation, and SW performance prediction, exist, but all represent static models, built upon historical data — none of which can calculate an RUL. This paper addresses the application of PHM concepts to software systems for fault predictions and RUL estimation. Specifically, we wish to address how PHM can be used to make decisions for SW systems such as version update, module changes, rejuvenation, maintenance scheduling and abandonment. This paper presents a method to prognostically and continuously predict the RUL of a SW system based on usage parameters (e.g., numbers and categories of releases) and multiple performance parameters (e.g., response time). The model is validated based on actual data (on performance parameters), generated by the test beds versus predicted data, generated by a predictive model. Statistical validation (regression validation) has been carried out as well. The test beds replicate and validate faults, collected from a real application, in a controlled and standard test (staging) environment. A case study based on publicly available data on faults and enhancement requests for the open-source Bugzilla application is presented. This case study demonstrates that PHM concepts can be applied to SW systems and RUL can be calculated to make decisions on software version update or upgrade, module changes, rejuvenation, maintenance schedule and total abandonment.

Prognostics Health Management Model for LED Package Failure Under Contaminated Environment

2015 ◽  
Author(s):  
Pradeep Lall ◽  
Hao Zhang ◽  
Lynn Davis
Keyword(s):  
Health Management ◽  
Luminous Flux ◽  
The State ◽  
Remaining Useful Life ◽  
Integrating Sphere ◽  
State Estimator ◽  
Acceptable Error ◽  
Color Shift ◽  
Useful Life ◽  
The Impact

The reliability consideration of LED products includes both luminous flux drop and color shift. Previous research either talks about luminous maintenance or color shift, because luminous flux degradation usually takes very long time to observe. In this paper, the impact of a VOC (volatile organic compound) contaminated luminous flux and color stability are examined. As a result, both luminous degradation and color shift had been recorded in a short time. Test samples are white, phosphor-converted, high-power LED packages. Absolute radiant flux is measured with integrating sphere system to calculate the luminous flux. Luminous flux degradation and color shift distance were plotted versus aging time to show the degradation pattern. A prognostic health management (PHM) method based on the state variables and state estimator have been proposed in this paper. In this PHM framework, unscented kalman filter (UKF) was deployed as the carrier of all states. During the estimation process, third order dynamic transfer function was used to implement the PHM framework. Both of the luminous flux and color shift distance have been used as the state variable with the same PHM framework to exam the robustness of the method. Predicted remaining useful life is calculated at every measurement point to compare with the tested remaining useful life. The result shows that state estimator can be used as the method for the PHM of LED degradation with respect to both luminous flux and color shift distance. The prediction of remaining useful life of LED package, made by the states estimator and data driven approach, falls in the acceptable error-bounds (20%) after a short training of the estimator.

scholarly journals Remaining Useful Life Prediction for Rotating Machinery Based on Optimal Degradation Indicator

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Aisong Qin ◽  
Qinghua Zhang ◽  
Qin Hu ◽  
Guoxi Sun ◽  
Jun He ◽  
...  
Keyword(s):  
Health Management ◽  
Rotating Machinery ◽  
Remaining Useful Life ◽  
Programming Algorithm ◽  
Wiener Model ◽  
New Approach ◽  
Degradation Modeling ◽  
Proposed Model ◽  
Useful Life ◽  
Degradation Indicator

Remaining useful life (RUL) prediction can provide early warnings of failure and has become a key component in the prognostics and health management of systems. Among the existing methods for RUL prediction, the Wiener-process-based method has attracted great attention owing to its favorable properties and flexibility in degradation modeling. However, shortcomings exist in methods of this type; for example, the degradation indicator and the first predicting time (FPT) are selected subjectively, which reduces the prediction accuracy. Toward this end, this paper proposes a new approach for predicting the RUL of rotating machinery based on an optimal degradation indictor. First, a genetic programming algorithm is proposed to construct an optimal degradation indicator using the concept of FPT. Then, a Wiener model based on the obtained optimal degradation indicator is proposed, in which the sensitivities of the dimensionless parameters are utilized to determine the FPT. Finally, the expectation of the predicted RUL is calculated based on the proposed model, and the estimated mean degradation path is explicitly derived. To demonstrate the validity of this model, several experiments on RUL prediction are conducted on rotating machinery. The experimental results indicate that the method can effectively improve the accuracy of RUL prediction.

Aircraft Fleet Maintenance Planning Using Combined Cost Benefit Model and Branch and Bound

2013 ◽  
Author(s):  
Behnam Razavi ◽  
Farrokh Sassani
Keyword(s):  
Branch And Bound ◽  
Health Management ◽  
Cost Benefit ◽  
Remaining Useful Life ◽  
Maintenance Planning ◽  
Flight Delays ◽  
Engine Operation ◽  
Maintenance And Repair ◽  
Flight Schedules ◽  
Useful Life

The tasks of maintenance and repair without optimal planning can be costly and result in prolonged maintenance times, reduced availability and possible flight delays. Aircraft manufacturers and maintainers see significant benefits in constantly improving Health Management and Maintenance (HMM) practices by deploying the most effective maintenance planning strategies. The planning of the maintenance and repair is a complex task due to chain dependency of engines to aircraft, and aircraft to the flight schedules. This paper presents a scheduling method for determining the time of maintenance based on the historical engine operation data in order to maximize the use of estimated remaining useful life of the engines as well as lowering the cost and duration of the downtime. The Time-on-Wing (TOW) data is used in conjunction with probability density functions to determine the shape of the respective distribution of the time of maintenance to minimize the loss of expected remaining useful life. Data from each engine with most chance of failure is then selected and fed into an extended Branch and Bound (B&B) routine to determine the best optimum sequence for entering the facility in order to minimize the waiting time.

scholarly journals Remaining Useful Life Estimation of Aircraft Engines Using a Joint Deep Learning Model Based on TCNN and Transformer

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Hai-Kun Wang ◽  
Yi Cheng ◽  
Ke Song
Keyword(s):  
Deep Learning ◽  
Working Conditions ◽  
Health Management ◽  
Remaining Useful Life ◽  
Aircraft Engines ◽  
Key Technology ◽  
Life Estimation ◽  
Useful Life ◽  
New Generation ◽  
Deep Learning Model

The remaining useful life estimation is a key technology in prognostics and health management (PHM) systems for a new generation of aircraft engines. With the increase in massive monitoring data, it brings new opportunities to improve the prediction from the perspective of deep learning. Therefore, we propose a novel joint deep learning architecture that is composed of two main parts: the transformer encoder, which uses scaled dot-product attention to extract dependencies across distances in time series, and the temporal convolution neural network (TCNN), which is constructed to fix the insensitivity of the self-attention mechanism to local features. Both parts are jointly trained within a regression module, which implies that the proposed approach differs from traditional ensemble learning models. It is applied on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset from the Prognostics Center of Excellence at NASA Ames, and satisfactory results are obtained, especially under complex working conditions.

Sign in / Sign up

Export Citation Format

Share Document