Experimental Training and Validation of a System for Aircraft Acoustic Signature Identification

Quaranta, Vincenzo; Dimino, Ignazio

doi:10.2514/6.2006-2696

Cited by 4 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although our previous study [13] was targeted mainly at the sound sources of rotorcraft, the classification of rotorcraft noise is relatively easy because rotorcraft sound has characteristic frequency components with a dominant tonal sound, as suggested by Quaranta and Dimino [7,8]. In the present paper, we show the results of identifying jet aircraft models in two case studies conducted near Narita International Airport and Osaka International Airport.…”

Section: Purposementioning

confidence: 82%

“…Identification was conducted for three types of jet fighter aircraft model, and the identification accuracy was approximately 90%. In another study, Quaranta and Dimino [7] used a neural network to classify four types of sound source consisting of takeoff and landing sounds of two turboprop aircraft and one jet aircraft; they reported a total identification accuracy of 95%. However, using the same method, Quaranta and Dimino [8] reported that the accuracy rate decreased to no more than 90% when classifying nine sound sources comprising takeoff and landing jet aircraft sounds.…”

Section: Previous Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Identification of jet aircraft model based on frequency characteristics of noise by convolutional neural network

Morinaga

Mori

Matsui

et al. 2019

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

We have been developing an aircraft model identification system that uses a convolutional neural network (CNN). The assumption is that this identification system would be used to estimate the number of flights to create noise maps. In our previous study, we used the CNN model to classify five aircraft comprising three rotorcraft, one turboprop, and one jet aircraft, and the accuracy reached 99%. In the present study, to examine whether this method is also effective for identifying the sound sources of jet aircraft, we conducted two case studies using frequency characteristics of aircraft noise obtained from field measurements around Osaka International Airport and Narita International Airport. Targeting 7 and 18 types of sound source at Osaka and Narita, respectively, an identification rate of 98% was obtained in both cases. This suggests that the present system can estimate the number of jet aircraft flights for each engine type or each aircraft model with very high accuracy.

show abstract

Section: Purposementioning

confidence: 82%

Section: Previous Studiesmentioning

confidence: 99%

Identification of jet aircraft model based on frequency characteristics of noise by convolutional neural network

Morinaga

Mori

Matsui

et al. 2019

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

show abstract

“…We have been developing an aircraft model identification system that uses field measurements and machine learning, the aim being to use the frequency characteristics of aircraft noise to automatically classify the aircraft model associated with aircraft noise events. In Morinaga et al (2019) [2], we summarized the results of our previous studies [3][4][5] and those of studies conducted in other countries [6][7][8][9][10][11][12][13]. We also reported the results of two case studies that were conducted in the vicinity of airports, each of which identified a different model of jet aircraft.…”

Section: Previous Studiesmentioning

confidence: 99%

Aircraft model identification using convolutional neural network trained by those noises in a wide area around an airfield

Morinaga

Mori

Yamamoto

2023

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

We have developed an aircraft model identification system that uses a convolutional neural network (CNN). Our previous study used the CNN model to classify seven and eighteen models of jet aircraft by using training based on measured data taken directly under their flight paths near airports, reaching an accuracy of 98%. However, there were some limitations, such as the study results being obtained at only three sites, the measurements being taken only directly under the flight path, and the season being limited to winter. In this study, we examine if this method is also effective for identifying sound sources over a wider area not directly under the flight path. We conducted aircraft type identification by using the frequency characteristics of aircraft noise obtained at 90 measurement sites located within an area of approximately 30 km north-south and 6 km east-west, in summer and winter. We were able to achieve an identification rate of 98% for four types of sound sources. The results suggest that this system can identify measurement data over a wider area around airfields and can be applied to more practical issues, such as generating noise maps and validating predictions in the noise maps.

show abstract

“…Results are also validated with previous experimental study conducted with same airship. Quaranta et al 18 identified acoustic signatures of the aeroplanes with ANN. In the procedure, ascending and descending noise of five different aircraft are used.…”

Section: Introductionmentioning

confidence: 99%

Development of a method for maximum structural response prediction of a store externally carried by a jet fighter

Kaplan

Acar

Özer

2021

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

Experimental structural response of equipment mounted in store carried externally by jet type aircraft is investigated, predicted and compared with responses suggested by military standards in this study. A representative store which is similar to Mark-83 warhead with guidance units in terms of mass and geometry is used in this study. The main scope of this study is to evaluate the structural response proposed by military standards with real test conditions and also suggest a new method with an artificial neural network to predict the maximum response. Seventy-five different flight conditions are used to train the network for low and high frequency components. Also, eight flight conditions apart from the training set of flight conditions are used to test the approach. Acceleration levels are collected in real flight conditions by the data storage system. In signal processing, vibration response is expressed as power spectral density functions in the frequency domain. Procedures to predict the maximum response from measurements are determined with statistical limits in the literature. Besides the well-known limits in literature, third-order polynomial normal and logarithmic transform is used, and the performance of the different limits is compared. It is found that the military standard vibration spectrum is conservative. Distribution-free and normal tolerance limits predicted low frequency acceleration spectral density magnitudes more accurately. Their prediction performances were better than those of the other tolerance limits and that of the military standard. Third-order polynomial transform predictions are found to be reasonable with respect to normal prediction limit and envelope approach. Finally, it can be concluded that the response prediction method proposed in this article works well for Mark-83 warheads with guidance unit carried externally by jet fighter.

show abstract

Experimental Training and Validation of a System for Aircraft Acoustic Signature Identification

Cited by 4 publications

References 1 publication

Identification of jet aircraft model based on frequency characteristics of noise by convolutional neural network

Identification of jet aircraft model based on frequency characteristics of noise by convolutional neural network

Aircraft model identification using convolutional neural network trained by those noises in a wide area around an airfield

Development of a method for maximum structural response prediction of a store externally carried by a jet fighter

Contact Info

Product

Resources

About