For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
This paper focuses on the problem of aircraft fuel measurement, a visual measurement method is introduced, which uses the optical camera to collect the fuel level images and calculate the fuel from the image data. Considering the redundant information in the image will reduce the processing speed, a contour extraction method based on HSV color model is proposed to simplify the image. The Convolution Neural Network (CNN) is used to extract the fuel image features, and the fuel prediction model based on Long Short-Term Memory (LSTM) network is constructed. The effectiveness of the visual measurement method is verified by simulation.
Inspec keywords: fuel systems; convolutional neural nets; recurrent neural nets; aircraft; mechanical engineering computing; computer vision; image colour analysis; feature extraction
Subjects: Neural nets; Measurement; Image recognition; Civil and mechanical engineering computing; Mechanical engineering applications of IT; Mechanical components; Computer vision and image processing techniques; Engines