Developing health indicators and RUL prognostics for systems with few failure instances and varying operating conditions using a LSTM autoencoder

Pater, Ingeborg de; Mitici, Mihaela

doi:10.1016/j.engappai.2022.105582

Cited by 47 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data-driven, model-based as well as hybrid solutions will be taken into consideration with specific literature reviews to select appropriate Machine Learning (ML) methodologies and computational approaches. Promising strategies include particle filtering, Long Short-Term Memory (LSTM) [12] or even Physics Informed Neural Networks (PNN) combined with classification algorithms like Support Vector Machines (SVMs) or random forests. Moreover, the approaches should take into consideration the "few-shot" phenomenon, which lead to the substantially unbalanced healthy-unhealthy datasets typical of PHM tasks [12,13].…”

Section: Methodsmentioning

confidence: 99%

Condition-based-maintenance for fleet management

Baldo

2023

Materials Research Proceedings

View full text Add to dashboard Cite

Abstract. New “enlightened” and holistic maintenance strategies are shaping the industrial world from the inside, providing intelligent and focused solutions where high availability, reliability and safety are required. Maintenance planning and scheduling is an extremely daunting and multi-faceted task which involves competences from fairly different fields: customer support, quality, engineering, production, RAMS, cost estimation etc. In the aerospace sector, a significant percentage of Life Cycle Costs (LCCs) and, in particular, operating costs, are determined by Maintenance, Repair and Overhaul (MRO) activities and the relative asset unavailability due to down-time or turn-around-time [1,2]. This is the reason why currently there is an ongoing intense effort in the research community and in the industry towards new maintenance strategies which could overcome the limitations of preventive maintenance thus streamlining operations, without jeopardizing mission safety. This research project is hence spot on and focuses on the development of optimized maintenance strategies, built around the system health status.

show abstract

Section: Methodsmentioning

confidence: 99%

Condition-based-maintenance for fleet management

Baldo

2023

Materials Research Proceedings

View full text Add to dashboard Cite

show abstract

“…Combining the input X t at the current time step and the hidden state h t−1 transmitted from the previous time step, the two activation vectors I t and G t can be obtained through the above two activation functions. Here, G t is also called a candidate memory cell, and its information is added to the cell state C t medium [31,32]. The calculation formulas of activation vector I t and G t are as follows:…”

Section: Input Gatementioning

confidence: 99%

Long Short-Term Memory Network for Predicting Wind-Induced Vibration Response of Lightning Rod Structures

et al. 2023

View full text Add to dashboard Cite

Lightning rod structures are susceptible to wind loads due to their high slenderness ratio, high flexibility, and light weight. The wind-induced dynamic response of a lightning rod is critical for structural safety and reliability. The traditional methods for this response, including observation and simulation, focus on structural health monitoring (SHM), wind tunnel tests (WTTs), or fluid–structure interaction (FSI) simulations. However, all these approaches require considerable financial or computational investment. Additionally, problems such as data loss or data anomalies in the sensor monitoring process often occur during SHM or WTTs. This paper proposes an algorithm based on a long short-term memory (LSTM) network to predict the wind-induced dynamic response and to solve the problem of data link fracture caused by abnormal sensor data transmission or wind-induced damage to lightning rod structures under different wind speeds. The effectiveness and applicability of the proposed framework are demonstrated using actual monitoring data. Root-mean-squared error (RMSE), determination of coefficient (R2), variance accounted for (VAF), and the refined Willmott index (RWI) are employed as performance assessment indices for the proposed network model. At the same time, the random forest algorithm is adopted to analyze the correlation between the data of the different measurement points on the lightning rod structure. The results show that the LSTM method proposed in this paper has a high accuracy for the prediction of “missing” strain data during lightning rod strain monitoring under wind speeds of 15.81~31.62 m/s. Even under the extreme wind speed of 31.62 m/s, the values of RMSE, MAE, R2, RWI and VAF are 0.24053, 0.18213, 0.94539, 0.88172 and 0.94444, respectively, which are within the acceptable range. Using the data feature importance analysis function, it is found that the predicted strain data of the measurement point on the top part of the lightning rod structure are closely related to the test strain data of the two adjacent sections of the structure, and the effect of the test strain data of the measurement points that are far from the predicted measurement point can be ignored.

show abstract

“…Typically, data fusion models are usually included three categories, i.e., data-hierarchy fusion, decision-hierarchy fusion and feature-hierarchy fusion. Data-hierarchy fusion directly combines multiple sensory data that measure relevant operation parameters for constructing the health index [8]. Song improved the linear fusion function by applying kernel methods to characterize the degradation process of the system [9].…”

Section: Introductionmentioning

confidence: 99%

Measurement of aero-engine feature-hierarchy fusion degradation trend based on parameter-adaptive VMD method and improved transformer model

Lu,

Jiang,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The accumulation of operational time in aero-engines leads to irreversible mechanical wear and tear, necessitating accurate measurement of the health evolution trend for effective predictive maintenance, thus reducing the risk of accidents and ensuring personnel safety. In this paper, a parameter-adaptive variational mode decomposition (VMD) method and improved transformer model are proposed to forecast the degradation trend of aero-engine feature hierarchy fusion. Firstly, in order to quantitatively evaluate the engine health evolution process, the health state aggregate indicator (HSAI) is innovatively constructed by employing the deep blend auto-encoder and self-organizing map network, which facilitate the feature-hierarchy fusion of multi-source sensory data. Secondly, for the significant characteristics with nonlinearity and stochastic fluctuation of the HSAI sequence, the multiscale frequency features are extracted by the parameter-adaptive VMD method with the improved gray wolf optimizer, which analyzes the inherent degradation law. Finally, considering the problem of parameter sharing in the transformer model, a simplified mixture of experts routing algorithm is introduced to implement the switch transformer model to further measure the future aero-engine health trends. Extensive experiments on the multi-source dataset of aero-engine confirm that the proposed method accomplishes the more superior performance for health evolution measurement compared with other available methods.

show abstract

Developing health indicators and RUL prognostics for systems with few failure instances and varying operating conditions using a LSTM autoencoder

Cited by 47 publications

References 23 publications

Condition-based-maintenance for fleet management

Condition-based-maintenance for fleet management

Long Short-Term Memory Network for Predicting Wind-Induced Vibration Response of Lightning Rod Structures

Measurement of aero-engine feature-hierarchy fusion degradation trend based on parameter-adaptive VMD method and improved transformer model

Contact Info

Product

Resources

About