Using ground penetrating radar time-frequency analysis methods to recognise thin-layer

Abstract Application of signal processing techniques to nondestructive evaluation (NDE) in general and acoustic emission (AE) studies in particular has become a standard tool in determining the frequency characteristics of the signals and relating these characteristics to the integrity of the structure under consideration. Recent studies have shown that the frequency characteristics of ultrasonic signals from evolving damage during cyclic (fatigue) and dynamic loads change with time; in other words, the signals are nonstationary, and that these changes can be related to the nature of the damage taking place during loading. A joint time-frequency analysis such as Short Time Fourier Transform (STFT) and Wigner-Ville distribution (WVD), can in principle be used to determine the time dependent frequency characteristics of nonstationary signals in presence of background noise. In this study these techniques are applied to analyze AE signals from fatigue crack propagation in 5083 aluminum alloys and ultrasonic signals in degraded austenitic 316 stainless steels, to study the evolution of damage in these materials. It is demonstrated that the nonstationary characteristics of both AE and ultrasonic signals could be analyzed effectively by these methods. STFT was found to be more effective in analyzing AE signals, and WVD was more effective for analyzing the attenuation and frequency characteristics of degraded materials through ultrasonics. It is indicated that the time-frequency analysis methods should also be useful in evaluating crack propagation and final fracture process resulting from various damages and defects in structural members.

Download Full-text

SEMG Feature Extraction Based on Stockwell Transform Improves Hand Movement Recognition Accuracy

Sensors ◽

10.3390/s19204457 ◽

2019 ◽

Vol 19 (20) ◽

pp. 4457 ◽

Cited By ~ 3

Author(s):

She ◽

Zhu ◽

Tian ◽

Wang ◽

Yokoi ◽

...

Keyword(s):

Feature Extraction ◽

Frequency Analysis ◽

Recognition Accuracy ◽

Hand Movement ◽

Analysis Method ◽

Time Frequency Analysis ◽

Time Frequency ◽

Analysis Methods ◽

Movement Recognition ◽

S Transform

Feature extraction, as an important method for extracting useful information from surfaceelectromyography (SEMG), can significantly improve pattern recognition accuracy. Time andfrequency analysis methods have been widely used for feature extraction, but these methods analyzeSEMG signals only from the time or frequency domain. Recent studies have shown that featureextraction based on time-frequency analysis methods can extract more useful information fromSEMG signals. This paper proposes a novel time-frequency analysis method based on the Stockwelltransform (S-transform) to improve hand movement recognition accuracy from forearm SEMGsignals. First, the time-frequency analysis method, S-transform, is used for extracting a feature vectorfrom forearm SEMG signals. Second, to reduce the amount of calculations and improve the runningspeed of the classifier, principal component analysis (PCA) is used for dimensionality reduction of thefeature vector. Finally, an artificial neural network (ANN)-based multilayer perceptron (MLP) is usedfor recognizing hand movements. Experimental results show that the proposed feature extractionbased on the S-transform analysis method can improve the class separability and hand movementrecognition accuracy compared with wavelet transform and power spectral density methods.

Download Full-text