A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions

Trend forecasting and early anomaly warnings are important for avoiding aircraft engine failures or accidents. This study proposes a trend forecasting method based on enhanced Slice-level Adaptive Normalization (SAN) using a Long Short-Term Memory (LSTM) neural network under multi-operating conditio...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiantao Lu, Kuangzhi Yang, Peng Zhang, Wei Wu, Shunming Li
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2066
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188933389877248
author Jiantao Lu
Kuangzhi Yang
Peng Zhang
Wei Wu
Shunming Li
author_facet Jiantao Lu
Kuangzhi Yang
Peng Zhang
Wei Wu
Shunming Li
author_sort Jiantao Lu
collection DOAJ
description Trend forecasting and early anomaly warnings are important for avoiding aircraft engine failures or accidents. This study proposes a trend forecasting method based on enhanced Slice-level Adaptive Normalization (SAN) using a Long Short-Term Memory (LSTM) neural network under multi-operating conditions. Firstly, a condition recognition technology is constructed to automatically identify the operating conditions based on the predetermined judgment conditions, and vibration signal features are adaptively divided into three typical operating conditions, namely, the idling operating condition, the starting operating condition and the utmost operating condition. The features of original signals are extracted to reduce the impacts of signal fluctuations and noise preliminarily. Secondly, enhanced SAN is used to normalize and denormalize the features to alleviate non-stationary factors. To improve prediction accuracy, an <i>L</i><sub>1</sub> filter is adopted to extract the trend term of the features, which can effectively reduce the overfitting of SAN to local information. Moreover, the slice length is quantitatively estimated by the fixed points in <i>L</i><sub>1</sub> filtering, and a tail amendment technology is added to expand the applicable range of enhanced SAN. Finally, an LSTM-based forecasting model is constructed to forecast the normalized data from enhanced SAN, serving as input during denormalization. The final results under different operating conditions are the output from denormalization. The validity of the proposed method is verified using the test data of an aircraft engine. The results show that the proposed method can achieve higher forecasting accuracy compared to other methods.
format Article
id doaj-art-bfdfc29d52744879a2c521b4e019764f
institution OA Journals
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-bfdfc29d52744879a2c521b4e019764f2025-08-20T02:15:46ZengMDPI AGSensors1424-82202025-03-01257206610.3390/s25072066A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating ConditionsJiantao Lu0Kuangzhi Yang1Peng Zhang2Wei Wu3Shunming Li4College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, ChinaCollege of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, ChinaAECC Guiyang Engine Design Research Institute, Guiyang 550081, ChinaCollege of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, ChinaSchool of Automotive Engineering, Nantong Institute of Technology, Nantong 226002, ChinaTrend forecasting and early anomaly warnings are important for avoiding aircraft engine failures or accidents. This study proposes a trend forecasting method based on enhanced Slice-level Adaptive Normalization (SAN) using a Long Short-Term Memory (LSTM) neural network under multi-operating conditions. Firstly, a condition recognition technology is constructed to automatically identify the operating conditions based on the predetermined judgment conditions, and vibration signal features are adaptively divided into three typical operating conditions, namely, the idling operating condition, the starting operating condition and the utmost operating condition. The features of original signals are extracted to reduce the impacts of signal fluctuations and noise preliminarily. Secondly, enhanced SAN is used to normalize and denormalize the features to alleviate non-stationary factors. To improve prediction accuracy, an <i>L</i><sub>1</sub> filter is adopted to extract the trend term of the features, which can effectively reduce the overfitting of SAN to local information. Moreover, the slice length is quantitatively estimated by the fixed points in <i>L</i><sub>1</sub> filtering, and a tail amendment technology is added to expand the applicable range of enhanced SAN. Finally, an LSTM-based forecasting model is constructed to forecast the normalized data from enhanced SAN, serving as input during denormalization. The final results under different operating conditions are the output from denormalization. The validity of the proposed method is verified using the test data of an aircraft engine. The results show that the proposed method can achieve higher forecasting accuracy compared to other methods.https://www.mdpi.com/1424-8220/25/7/2066trend forecasting<i>L</i><sub>1</sub> filteringenhanced SANLSTMmulti-operating condition
spellingShingle Jiantao Lu
Kuangzhi Yang
Peng Zhang
Wei Wu
Shunming Li
A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions
Sensors
trend forecasting
<i>L</i><sub>1</sub> filtering
enhanced SAN
LSTM
multi-operating condition
title A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions
title_full A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions
title_fullStr A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions
title_full_unstemmed A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions
title_short A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions
title_sort trend forecasting method for the vibration signals of aircraft engines combining enhanced slice level adaptive normalization using long short term memory under multi operating conditions
topic trend forecasting
<i>L</i><sub>1</sub> filtering
enhanced SAN
LSTM
multi-operating condition
url https://www.mdpi.com/1424-8220/25/7/2066
work_keys_str_mv AT jiantaolu atrendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT kuangzhiyang atrendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT pengzhang atrendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT weiwu atrendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT shunmingli atrendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT jiantaolu trendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT kuangzhiyang trendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT pengzhang trendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT weiwu trendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions
AT shunmingli trendforecastingmethodforthevibrationsignalsofaircraftenginescombiningenhancedsliceleveladaptivenormalizationusinglongshorttermmemoryundermultioperatingconditions