EAI Endorsed Transactions

on Internet of Things Research Article

Artificial Intelligence Application on Aircraft

Maintenance: A Systematic Literature Review
Erna Shevilia Agustian 1,*, Zastra Alfarezi Pratama 2

1
Aeronautical Engineering, The Air Marshal Suryadarma Aerospace University, Indonesia
2
Informatic Engineering, Insan Cita Indonesia University, Indonesia

Abstract

Maintenance is an essential aspect of supporting aircraft operations. However, there are still several obstacles and
challenges in the process, such as incomplete technical record data, irregular maintenance schedules, unscheduled
component replacement, unavailability of tools or components, recurring problems, and a long time for troubleshooting.
Digitalization and the massive use of artificial intelligence (AI) in various sectors have been widely carried out in the
industry 5.0 era today, especially in the aviation industry. It offers several advantages to optimize aircraft maintenance
and operations, such as predictive maintenance, fault detection, failure diagnosis, and intelligent monitoring systems. The
utilization of AI has the potential to solve obstacles and challenges in aircraft maintenance activities, such as improving
aircraft reliability, reducing aircraft downtime, improving safety, and reducing maintenance costs. This research uses the
Systematic Literature Review method, which aims to review and provide an understanding of objectives, strategies,
methods, and equipment objects involved in the application of AI in aircraft maintenance and repair scope. The findings
and understanding from this research can be used as a basis for utilizing or adopting AI in aircraft maintenance to be more
targeted and efficient in the future. This study reviews and presents research trends from reputable journals and
proceedings screened using a unique protocol.

Keywords: Artificial intelligence, Aircraft maintenance, Industry 5.0

Received on 11 02 2024, accepted on 02 07 2024 published on 15 08 2024

Copyright © 2024 Agustian et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA
4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the
original work is properly cited.

doi: 10.4108/eetiot.6938
of news information worldwide is also high. In the last
two decades, Indonesia has had 45 fatal airplane crashes.
1. Introduction A total of 30 fatal accidents occurred during 2002-
2011, while another 15 fatal accidents in 2012-2021 [2].
Indonesia is the largest archipelago in the world. Outside these records, there are still technical problems
Therefore, the Indonesian people need aircraft such as aircraft derailments, engine problems, wing
transportation that connects between islands quickly. damage, etc. One of the causes is related to maintenance.
According to data from BPS (Indonesian Statistic The factor causing aircraft accidents related to
Institution), in 2018, the number of airplane passengers in maintenance includes maintenance activities that do not
Indonesia was around 101 million for domestic flights in solve problems and repeated errors that are not resolved.
one year [1]. Aircraft can be the safest mode of There is the use of tools that are not by procedures and
transportation compared to other transportation, but if a misinterpretation of inspection intervals [3]. Whereas with
the need to use aircraft as a means of transportation for the
plane has an accident, the impact is very high, and the
flow
*
Corresponding author. Email: ernashevilia@unsurya.ac.id

EAI Endorsed Transactions

1 on
Internet of
E. S. Agustian and Z. A. Pratama

community, the aircraft must be considered in its narrowed [6]. It can even help researchers find new
condition and state so that it is always in a flightworthy findings or points in previous research plans. To achieve
state and the best performance, so it requires good this, conducting a systematic literature review must follow
maintenance as well. Aircraft maintenance is defined by the seven key principles of the literature review [7], that
ICAO (International Civil Aviation Organization) as is: (1) Transparency, (2) Clarity, (3) Integration, (4) Focus,
tasks that need to be performed on aircraft to ensure (5) Equality, (6) Accessibility dan (7) Coverage.
their continued airworthiness. Aircraft maintenance In conducting a systematic literature review, three main
involves several activities, such as repairing, inspecting, stages must be carried out: planning, conducting, and
overhauling, troubleshooting, and modifying various reporting [8].
aircraft components, sub-systems, or systems [4]. These
actions are to keep the equipment in it so that it is
always in a serviceable condition and can be used
properly according to its function.
The era of Industry 4.0 and Society 5.0 has
transformed various fields, including the aviation
industry. Various technologies have emerged, such as
artificial intelligence, the Internet of Things, big data,
virtual reality, augmented reality, and so on. With the
emergence of these technologies, there are also new
maintenance concepts such as Predictive maintenance,
Prescriptive maintenance, maintenance 4.0, and others.
These concepts provide added value, such as increasing
availability, reducing downtime, increasing safety, and
reducing costs. The existence of the maintenance 4.0
concept is inseparable from artificial intelligence. That is
because artificial intelligence is used as decision support.
Artificial intelligence is a field of science that has many
branches. Machine learning, deep learning, expert
systems, computer vision, and NLP are branches of Figure 1. Process of systematic literature review [8].
artificial intelligence. In addition, there are still divisions
within these types of artificial intelligence. At the planning stage, the researcher identifies the
The problems that still arise in the aircraft need to conduct a review, then determines the research
maintenance area, it is hoped that artificial intelligence question and creates a protocol for the search. At this
can support decisions, planning, and analysis related to stage, the researcher briefly searched similar studies to
maintenance problems, as in the new concept of ascertain whether other researchers had answered the
maintenance 4.0, which offers several benefits and research questions. A research protocol is needed to make
conveniences. This research is expected to be an initial the search process effective and on target so that the
reference for researchers who want to approach artificial search process is focused and does not widen.
intelligence technology in the aircraft maintenance area. Furthermore, in the conducting process, the search
process is carried out in several reputable databases or
journals relevant to artificial intelligence and aviation,
2. Methodology such as IEEE, Science Direct, MDPI, Hindawi, and
SpringerLink. Furthermore, the researchers conducted
2.1. Systematic Literature Review screening by reviewing the abstract title, as well as
several predetermined criteria. After obtaining several
The methodology used in this research is a Systematic main articles from the screening results, extraction,
Literature Review (SLR). SLR has been widely used in analysis, and synthesis were carried out by exploring
various fields of research, which was originally used in article by article to find the points needed to answer
the health sector. Researchers usually use SLR to assist in research questions. The last process is to make a report in
compiling and analyzing information to support future the form of an article with a format following the
research plans. SLR is a methodology used to collect, publication publisher's standards. In the review process,
identify, and critically analyze relevant previous studies according to Fig.2, it is allowed to do the iteration process.
[5]. This is done if several problems arise that ultimately
SLR produces answers and findings compiled from require modification to maximize results. For example,
various studies so that conducting SLR can provide the problems that require iteration, such as problems that are
findings needed in future research. This is because starting still too broad, errors in the preparation of inappropriate
research requires an initial idea, namely by conducting a keywords, or criteria that complicate the process of
literature review. SLR can help with the initial search for finding the required articles.
relevant literature. A relevant literature review can help
determine whether the topic is too broad to cover in a
given timeframe adequately and whether the focus needs
to be

EAI Endorsed Transactions

2 on
Internet of
 Artificial Intelligence Application on Aircraft Maintenance: A Systematic Literature Review

Artificial intelligence is a field of study with a broad

2.2. Research Question scope. Artificial intelligence encompasses many theories,
methods, and technologies, and there are sub-fields
The research question is the purpose of this research, underneath. Therefore, alternative keywords were used to
so the research question is determined at the beginning of find more articles on artificial intelligence and its
the research. Research questions are defined to make derivatives to make the research more comprehensive.
the research direction more focused so that the essence of This was also used for the alternative keyword for
conducting a literature review will be more precise and "aircraft," as shown in Table 2.
efficient in answering research
gaps. The research question and its search motivation can Table 2. Alternative Keyword
be seen in Table 1. Keyword Alternative Keyword
Artificial Machine learning, Deep learning, Expert
Table 1. Research Question (RQ). Intelligence (AI) Systems, Neural network
Aircraft Aviation, Airplane
ID Research Question Motivation
RQ1 What parts or To find out the
components use artificial system, object, or
intelligence aircraft In formulating the search formula, the "AND" OR "
the most in aircraft component that keywords automatically facilitate the query or search
maintenance most used artificial process in the journal database. The string formulas used
research? intelligence in the are:
aircraft (Aircraft OR Aviation OR Airplane) AND (Artificial
RQ2 What are the goals and maintenance
To determine the Intelligence OR Machine Learning OR Deep Learning
objectives of using purpose and end goal OR Expert System OR Neural Network) AND
artificial intelligence of using artificial
in intelligence in (Maintenance)
aircraft aircraft maintenance.
RQ3 maintenance
What data sources are To find out where the Other string formula combinations can be an alternative
used in artificial data sources used by because some journal databases have different search or
intelligence research artificial intelligence query capabilities. In addition, there is also a limit to the
in in number of keywords that can be entered in the article
the aircraft the aircraft search field. However, alternative string formulas must
RQ4 maintenance
What are the area?
most maintenance
To identify thearea come
most still use the main keywords and not go outside the scope
widely used methods in the
used methods of aircraft maintenance.
use of artificial
when intelligence Next, a search is conducted using a string formula
implementing AI in the aircraft based on the keywords that have been compiled. This
in maintenance area. process is done by considering several aspects, including
2.3 Result Finding subject area (Engineering, Computer Science, Aviation),
publication type (journal and conference), document type
To collect the various articles needed, a search strategy (.pdf), and year of publication (2015-2023). The
is needed. The process of collecting research articles is mechanism in this process will be adjusted to the
intended to be precise and efficient. Some important Advanced Search in each journal database. The search
things to do in this process are determining the journal results using the string formula can be seen in Table 3.
database, creating keywords and keyword alternatives,
and determining criteria. After identifying the fields Table 3. Result From Journal Database.
related to aircraft maintenance, several reputable journal
Database Journal Articles Found
databases were determined, such as:
IEEE Xplore 275
MDPI 20
1. IEEE Xplore (Institute of Electrical and Electronics Hindawi 117
Engineers), Access: https://ieeexplore.ieee.org/
Science Direct 628
2. MDPI (Multidisciplinary Digital Publishing Institute),
ACM 669
Access: https://www.mdpi.com/
SpringerLink 500
3. Hindawi, Access: https://www.hindawi.com/ IOP Science 156
4. Science Direct, Access:
Total 2365
https://www.sciencedirect.com/
5. ACM (Association for Computing Machinery),
Access: https://dl.acm.org/ Several articles were found, but screening was required to
6. SpringerLink, Access: https://link.springer.com/ find articles relevant to the research questions and
7. IOP Science, Access: https://iopscience.iop.org/ objectives. The title, abstract, publication date, type, and

EAI Endorsed Transactions

3 on
Internet of
E. S. Agustian and Z. A. Pratama

article access were identified in this process. The After a deeper study of 25 research articles, it was
screening of articles based on the criteria can be seen in found that most research on the use of artificial
Table 4. intelligence was carried out on the engine part of the
aircraft (10 articles). As for some turbofan components (5
Table 4. Specific Criteria. Articles), it is a sub of the aircraft engine. The results can
be seen in Table 6.
Inclusion Criteria Exclusion Criteria
− Article published − White paper, book,
before August 2023 conference review,
− discussion related to conference abstract, 3.2 RQ 2 - What are the goals and
aircraft components Encyclopedia, and
and maintenance scope magazine or newsletter objectives of using artificial intelligence in
− article-related keyword − discussion out of the aircraft maintenance research?
with string formula aviation industry area
− subscription journal − similar articles but from
and full-access or open- different databased
access − not written in English The results show that the objectives of using artificial
intelligence in the aircraft maintenance area are prediction,
estimation, classification, detection, prediction, and
After filtering articles using specific criteria, several combination. Prediction is the most common goal in
key articles were obtained that will be studied more artificial intelligence research on aircraft maintenance.
deeply. These main articles will be used to answer the Some studies want to achieve more than one goal, such as
research question. Some articles used alternative in [13], [24], [25]. The results of each goal also have
combinations of string formulas, but others were found several types of their own, for example, in predictions
outside the database list mentioned earlier. However, the with several different types of goals such as for RUL
articles must be based on the criteria and included in the (Remaining Useful Life), Performance, and failure. The
quartile (Q1-Q4). The final results of the number of results of the article review can be seen in Table 7.
article findings in this study can be seen in Table 5.

Table 5. Result of Specific Criteria

Articles Table 7. Objective of research AI in aircraft

Category
8 maintenance
Q1
Q2 9
Q3 3
Q - Objective/goal
4 Proceeding 5 Prediction/ Classification Detection Prognostic Combination
Conference Estimation
T o ta l 25
Remaining Failure Corrosion Remaining Identification
Useful Life Classification: detection: Useful Life and Prediction:
Prediction: [9] [31] Prognostics: [25]
[19], [21]
3. Result and Discussion [20],[11],[27],[
28],
[22],[23],[17],[
33]
3.1 RQ 1 - What parts or components Performance
Prediction: [29]
Classification
state: [18]
Fault
detection:
Classification
and anomaly
use artificial intelligence the most in aircraft Estimation:
[32] detection: [24]
Predictive and
maintenance research? [10],
[14],[15],[16]
Prognostic:
[13]
Predict the
evolution: [12]
Prediction of
replacement:
Table 6. Object Research based on the part of aircraft [26]
Failure rate
prediction: [30]

No Par Reference
1 Engin [9],[10],[11],[12],[13],
e [14], [15],[16], [17],[18]
2 Turbofan Engine [19],[20],[21],[22], [23]
There are 4 main objectives of using artificial
3 Rivet aircraft [24]
4 Aircraft in General [25],[26] intelligence for aircraft maintenance based on the findings
5 Landing Gear [27] in a number of papers, namely prediction/estimation,
6 Cooling System [28] classification, detection and combination:
7 Win [29]
8 g System
Aircraft Fuel [30]
9 Aircraft Fuselage [31]
10 Aircraft control system [32]
11 Auxiliary power unit [33]

EAI Endorsed Transactions

4 on
Internet of
 Artificial Intelligence Application on Aircraft Maintenance: A Systematic Literature Review

1. Prediction algorithms are computational procedures or Table 8. Data sources

steps used to predict future values or events based on
available data. Prediction algorithms can be used in No Data Sources Reference
various fields, including statistics, machine learning, [19],[20],[21],[11],[13],
and data mining. 1 C-MAPSS Dataset
[22],[15 ,[16],[17]
ACARS (Aircraft
2. Classification algorithms are mathematical methods or Communications
2 Addressing and [25]
procedures used to group or classify data into specific
classes or categories. The main goal of a classification Reporting System)
algorithm is to create a model that can predict the class Google Smart Glass
3 Video (Take video & [24]
or label of data based on information learned from picture)
previous training data. 4 Data Sensor [29], [33],[18]
CFD (Computational
3. Detection algorithms are used to identify the presence 5 Fluid Dynamics) [29]
or characteristics of certain objects or patterns in data. Simulation Software
The type of detection algorithm used will depend on QAR (Quick Access
6 Recorder) Data [9], [32]
the context and purpose of the detection.
Health monitoring
7 information [10]
4. Prognostic algorithms are used to predict future
8 PHM08 Dataset [11]
developments or events based on historical data and FDR (Flight Data
identified trends. Prognosis is an attempt to estimate 9 Recorder) [27]
how a condition or situation will develop over time. 10 Flight Phases Data [28]
Run to Failure
5. While combination is a mixture of several objectives, 11 data/Historical failure [28],[30]
for example, it can combine prediction and detection data
or identification and prediction such as research [25], 12 N-CMAPSS Databased [12]
classification and detection [24] and prediction and 13 FD001 Dataset [23]
DAIS (D-Sight Aircraft
prognostic [13]. 14 Inspection System) [31]
ACMS (Aircraft Central
Maintenance
15 System)/Log [26]
Maintenance
3.3 RQ 3 - What data sources are used
in artificial intelligence research in the
aircraft maintenance area?
3.4 RQ 4 - What are the most widely
used methods when implementing AI in
aircraft maintenance?
An important aspect of using artificial intelligence is
the availability and how to collect data. The findings in
this research question review show that using the C- The review found that LSTM (Long Short-Term
MAPSS public dataset from NASA (National Aeronautics Memory) and CNN (Convolutional Neural Network) are
and Space Administration) is the most widely used data the most widely used methods. LSTM is generally used
source in artificial intelligence research in the aircraft for prediction, while CNN is used for classification and
maintenance area. There are 15 types of data sources detection. LSTM and CNN can also be combined as in
found. This is because there are differences in the [14]. Some studies also use layered methods such as in
objectives and needs of using artificial intelligence in the [19], [25], [9], [21]. Some methods are also basically not
aircraft maintenance area and the availability or included in the artificial intelligence sub but use statistical
capabilities of MRO systems in several research methods, but can be used to make predictions, such as in
locations. The findings can be seen in Table 8. [27] and [30], which use the ARIMA (Autoregressive
Integrated Moving Average) method. The results of the
review can be seen in Table 9.

EAI Endorsed Transactions

5 on
Internet of
E. S. Agustian and Z. A. Pratama

Table 9. Method 1. The utilization of artificial intelligence in the aircraft

maintenance area is most widely used for aircraft
No Method Reference engines. Artificial intelligence is most widely used to
1 SAE (Stacked [19] predict several things, such as Remaining Useful Life
Autoencoder) Prediction, Failure prediction, performance prediction,
2 TCN (Temporal [19] etc.
Convolutional Network) 2. Most researchers utilize the C-MAPSS public dataset
3 LSTM (Long Short- [20],[25],[10],[14],[16], because the dataset has several parameters that are
Term Memory) [33] much needed and easily accessible for research
4 Bi-LSTM (Bidirectional [9]
Long Short-Term
purposes. In addition, it should also be remembered
Memory) that aircraft have a very complex system, so
5 PSO-SVM (Particle [25] conducting research in aircraft maintenance must be
Swarm Optimization- careful and prepared if the research results are used in
Support Vector real decisions in the aircraft maintenance process.
Machine) 3. Several support systems are needed for the application
6 CNN (Convolutional [24],[9],[21],[13],[14],[ of artificial intelligence in aircraft maintenance, such
Neural Network) 31] as Health monitoring systems, Aircraft inspection
7 ANN (Artificial Neural [29] systems, sensor systems, and reporting systems. The
Network) basic ones needed are historical failure logs and
8 DRL (Deep [21] historical maintenance logs.
Reinforcement learning) 4. LSTM (Long Short Term Memory Network), a
9 DL-RNN (Deep Layer [11]
Recurrent Neural technique that is widely used for prediction, can
Networks) process, predict, and classify information based on
10 ARIMA [27], [30] time series data. The idea behind LSTM allows it to
(Autoregressive remember and delete old data that is no longer
Integrated Moving relevant. Thus, information management will be more
Average) complete as well as up-to-date.
11 GAM (generalized [12]
additive model) For further research is to be able to determine the
12 GA (Genetic [22]
object of research in advance such as engines, wings,
Algorithm)
13 ELM (Extreme [23] turbo fans, and so on. This is needed to minimize the
Learning Machine) scope of future research. It is also necessary to consider
14 DCNN (Deep [15] the source of data to be used whether the aircraft system
Convolution Neural has a data storage log or not, if not then it can use the
Network) available open data, but it is ideal to use your own data to
15 NSA (Negative [32] match the character of the aircraft industry environment to
selection Algorithm) be studied.
16 DNN (Deep neural [18]
networks)
17 OS-ELM (Online [17]
Sequential Extreme
References
Learning Machine)
[1] Badan Pusat Statistik: Statistik Transportasi Udara 2018.,
Jakarta (2019)
[2] katadata.co.id: Kecelakaan pesawat di Indonesia,
These methods are algorithms used in aircraft https://databoks.katadata.co.id/datapublish/2022/03/22/ha
maintenance research. It can be seen that research on mpir-tiap-tahun-ada-kecelakaan-pesawat-di-indonesia-ini-
aircraft maintenance involving artificial intelligence can datanya
use various and different algorithms. This depends on the [3] Muhammad Fransyah: Human Factor Analysis Using the
object of research, data and objectives. For example, the EEAM Method From Investigation Reports of Aircraft
research objectives are for detection, diagnosis, prediction Accidents Related To The Maintenance Side, (2023)
[4] Wild, G.: A Quantitative Study of Aircraft Maintenance
and classification will use different algorithms.
Accidents in Commercial Air Transport. Aerospace. 10,
689 (2023). https://doi.org/10.3390/aerospace10080689
3. Conclusion [5] Pati, D., Lorusso, L.N.: How to Write a Systematic Review
of the Literature. HERD: Health Environments Research &
Design Journal. 11, 15–30 (2018).
The conclusion of this article has 4 points which are https://doi.org/10.1177/1937586717747384
the results of the findings and answers to the research [6] Carrera-Rivera, A., Ochoa, W., Larrinaga, F., Lasa, G.:
questions. How to conduct a systematic literature review: A quick
guide for computer science research. MethodsX. 9, 101895
(2022). https://doi.org/10.1016/j.mex.2022.101895

EAI Endorsed Transactions

6 on
Internet of
 Artificial Intelligence Application on Aircraft Maintenance: A Systematic Literature Review

[7] Luke Pittway: Systematic literature reviews. The SAGE engine degradation using semi-supervised deep
dictionary of qualitative management research. 216–2018 architecture. Reliab Eng Syst Saf. 183, 240–251 (2019).
(2008) https://doi.org/10.1016/j.ress.2018.11.027
[8] Xiao, Y., Watson, M.: Guidance on Conducting a [23] Zheng, C., Liu, W., Chen, B., Gao, D., Cheng, Y., Yang,
Systematic Literature Review, (2019) Y., Zhang, X., Li, S., Huang, Z., Peng, J.: A Data-driven
[9] Li, J.-H., Gao, X.-Y., Lu, X., Liu, G.-D.: Multi-Head Approach for Remaining Useful Life Prediction of Aircraft
Attention-Based Hybrid Deep Neural Network for Engines. In: 2018 21st International Conference on
Aeroengine Risk Assessment. IEEE Access. 11, 113376– Intelligent Transportation Systems (ITSC). pp. 184–189.
113389 (2023). IEEE (2018)
https://doi.org/10.1109/ACCESS.2023.3323843 [24] Zhu, X.B.: Aviation Rivet Classification and Anomaly
[10] Ullah, S., Li, S., Khan, K., Khan, S., Khan, I., Eldin, S.M.: Detection Based on Deep Learning. International Journal of
An Investigation of Exhaust Gas Temperature of Aircraft Aerospace Engineering. 2023, (2023).
Engine Using LSTM. IEEE Access. 11, 5168–5177 (2023). https://doi.org/10.1155/2023/3546838
https://doi.org/10.1109/ACCESS.2023.3235619 [25] Zhou, D., Zhuang, X., Zuo, H., Wang, H., Yan, H.: Deep
[11] Thakkar, U., Chaoui, H.: Remaining Useful Life Prediction Learning-Based Approach for Civil Aircraft Hazard
of an Aircraft Turbofan Engine Using Deep Layer Identification and Prediction. IEEE Access. 8, 103665–
Recurrent Neural Networks. Actuators. 11, (2022). 103683 (2020).
https://doi.org/10.3390/act11030067 https://doi.org/10.1109/ACCESS.2020.2997371
[12] Apostolidis, A., Bouriquet, N., Stamoulis, K.P.: AI-Based [26] Dangut, M.D.: Rescaled-LSTM for Predicting Aircraft
Exhaust Gas Temperature Prediction for Trustworthy Component Replacement Under Imbalanced Dataset
Safety-Critical Applications. Aerospace. 9, (2022). Constraint. (2020)
https://doi.org/10.3390/aerospace9110722 [27] Hsu, T.H., Chang, Y.J., Hsu, H.K., Chen, T.T., Hwang,
[13] de Pater, I., Reijns, A., Mitici, M.: Alarm-based predictive P.W.: Predicting the Remaining Useful Life of Landing
maintenance scheduling for aircraft engines with imperfect Gear with Prognostics and Health Management (PHM).
Remaining Useful Life prognostics. Reliab Eng Syst Saf. Aerospace. 9, (2022).
221, (2022). https://doi.org/10.3390/aerospace9080462
https://doi.org/10.1016/j.ress.2022.108341 [28] Rosero, R.L., Silva, C., Ribeiro, B.: Remaining Useful Life
[14] Hermawan, A.P., Kim, D.-S., Lee, J.-M.: Predictive Estimation of Cooling Units via Time-Frequency Health
Maintenance of Aircraft Engine using Deep Learning Indicators with Machine Learning. Aerospace. 9, (2022).
Technique. In: 2020 International Conference on https://doi.org/10.3390/aerospace9060309
Information and Communication Technology Convergence [29] Abdelghany, E.S., Farghaly, M.B., Almalki, M.M., Sarhan,
(ICTC). pp. 1296–1298. IEEE (2020) H.H., Essa, M.E.S.M.: Machine Learning and IoT Trends
[15] Liu, L., Wang, L., Yu, Z.: Remaining Useful Life for Intelligent Prediction of Aircraft Wing Anti-Icing
Estimation of Aircraft Engines Based on Deep Convolution System Temperature. Aerospace. 10, (2023).
Neural Network and LightGBM Combination Model. https://doi.org/10.3390/aerospace10080676
International Journal of Computational Intelligence [30] Li, W., Hou, N.: Aircraft Failure Rate Prediction Method
Systems. 14, (2021). https://doi.org/10.1007/s44196-021- Based on CEEMD and Combined Model. Sci Program.
00020-1 2022, (2022). https://doi.org/10.1155/2022/8455629
[16] Boujamza, A., Lissane Elhaq, S.: Attention-based LSTM [31] Brandoli, B., de Geus, A.R., Souza, J.R., Spadon, G.,
for Remaining Useful Life Estimation of Aircraft Engines. Soares, A., Rodrigues, J.F., Komorowski, J., Matwin, S.:
In: IFAC-PapersOnLine. pp. 450–455. Elsevier B.V. Aircraft fuselage corrosion detection using artificial
(2022) intelligence. Sensors. 21, (2021).
[17] Berghout, T., Mouss, L.H., Kadri, O., Saïdi, L., Benbouzid, https://doi.org/10.3390/s21124026
M.: Aircraft engines remaining useful life prediction with [32] Chen, J., Chen, S., Ma, C., Jing, Z., Xu, Q.: Fault Detection
an improved online sequential extreme learning machine. of Aircraft Control System Based on Negative Selection
Applied Sciences (Switzerland). 10, (2020). Algorithm. International Journal of Aerospace Engineering.
https://doi.org/10.3390/app10031062 2020, (2020). https://doi.org/10.1155/2020/8833825
[18] Kulagin, V.P., Akimov, D.A., Pavelyev, S.A., Potapov, [33] Liu, X., Liu, L., Liu, D., Wang, L., Guo, Q., Peng, X.: A
D.A.: Automated Identification of Critical Malfunctions of Hybrid Method of Remaining Useful Life Prediction for
Aircraft Engines Based on Modified Wavelet Transform Aircraft Auxiliary Power Unit. IEEE Sens J. 20, 7848–
and Deep Neural Network Clustering. In: IOP Conference 7858
Series: Materials Science and Engineering. Institute of (2020). https://doi.org/10.1109/JSEN.2020.2979797
Physics Publishing (2020)
[19] Liu, X., Xiong, L., Zhang, Y., Luo, C.: Remaining Useful
Life Prediction for Turbofan Engine Using SAE-TCN
Model †. Aerospace. 10, (2023).
https://doi.org/10.3390/aerospace10080715
[20] Asif, O., Haider, S.A.L.I., Naqvi, S.R., Zaki, J.F.W., Kwak,
K.S., Islam, S.M.R.: A Deep Learning Model for
Remaining Useful Life Prediction of Aircraft Turbofan
Engine on C- MAPSS Dataset. IEEE Access. 10, 95425–
95440 (2022).
https://doi.org/10.1109/ACCESS.2022.3203406
[21] Lee, J., Mitici, M.: Deep reinforcement learning for
predictive aircraft maintenance using probabilistic
Remaining-Useful-Life prognostics. Reliab Eng Syst Saf.
230, (2023).
https://doi.org/10.1016/j.ress.2022.108908
[22] Listou Ellefsen, A., Bjørlykhaug, E., Æsøy, V., Ushakov,
S., Zhang, H.: Remaining useful life predictions for
turbofan

EAI Endorsed Transactions

7 on
Internet of