Bidirectional Spectral-Based Transformer for Remaining Useful Life Prediction

Kin Man Lam; Ka Chun Fung; Cheung Ming Lai; Kwan Ho Lin; Ka Hong Loo; Kam Chuen Yung

Bidirectional Spectral-Based Transformer for Remaining Useful Life Prediction

Kin Man Lam (Inventor), Ka Chun Fung (Inventor), Cheung Ming Lai (Inventor), Kwan Ho Lin (Inventor), Ka Hong Loo (Inventor), Kam Chuen Yung (Inventor)

Research output: Patents, agreements, assignments and companies › Patents granted

Abstract

The present invention discloses a method for predicting the remaining useful life of an engine based on a bidirectional spectral-based Transformer model (200) comprising: obtaining sensor data from at least one sensor; filtering sensor data; normalizing the sensor data; inputting the normalized data into a bidirectional spectral-based Transformer model (200) by adopting Discrete Cosine Transform (DCT); training the bidirectional spectral-based Transformer model (200) based on a pre-set training data set; and predicting the remaining useful life (108) of the engine based on the trained bidirectional spectral-based Transformer model (200).

Original language	English
Patent number	HK30079023
Filing date	30/12/22
Publication status	Published - 6 Apr 2023

Cite this

@misc{1eb77dccf7154bc5808fec65c1b485b2,

title = "Bidirectional Spectral-Based Transformer for Remaining Useful Life Prediction",

abstract = "The present invention discloses a method for predicting the remaining useful life of an engine based on a bidirectional spectral-based Transformer model (200) comprising: obtaining sensor data from at least one sensor; filtering sensor data; normalizing the sensor data; inputting the normalized data into a bidirectional spectral-based Transformer model (200) by adopting Discrete Cosine Transform (DCT); training the bidirectional spectral-based Transformer model (200) based on a pre-set training data set; and predicting the remaining useful life (108) of the engine based on the trained bidirectional spectral-based Transformer model (200). ",

author = "Lam, {Kin Man} and Fung, {Ka Chun} and Lai, {Cheung Ming} and Lin, {Kwan Ho} and Loo, {Ka Hong} and Yung, {Kam Chuen}",

year = "2023",

month = apr,

day = "6",

language = "English",

type = "Patent",

note = "HK30079023",

}

TY - PAT

T1 - Bidirectional Spectral-Based Transformer for Remaining Useful Life Prediction

AU - Lam, Kin Man

AU - Fung, Ka Chun

AU - Lai, Cheung Ming

AU - Lin, Kwan Ho

AU - Loo, Ka Hong

AU - Yung, Kam Chuen

PY - 2023/4/6

Y1 - 2023/4/6

N2 - The present invention discloses a method for predicting the remaining useful life of an engine based on a bidirectional spectral-based Transformer model (200) comprising: obtaining sensor data from at least one sensor; filtering sensor data; normalizing the sensor data; inputting the normalized data into a bidirectional spectral-based Transformer model (200) by adopting Discrete Cosine Transform (DCT); training the bidirectional spectral-based Transformer model (200) based on a pre-set training data set; and predicting the remaining useful life (108) of the engine based on the trained bidirectional spectral-based Transformer model (200).

AB - The present invention discloses a method for predicting the remaining useful life of an engine based on a bidirectional spectral-based Transformer model (200) comprising: obtaining sensor data from at least one sensor; filtering sensor data; normalizing the sensor data; inputting the normalized data into a bidirectional spectral-based Transformer model (200) by adopting Discrete Cosine Transform (DCT); training the bidirectional spectral-based Transformer model (200) based on a pre-set training data set; and predicting the remaining useful life (108) of the engine based on the trained bidirectional spectral-based Transformer model (200).

M3 - Patents granted

M1 - HK30079023

Y2 - 2022/12/30

ER -

Bidirectional Spectral-Based Transformer for Remaining Useful Life Prediction

Abstract

Fingerprint

Cite this