Angular and axial evaluation of superficial defects on non-accessible pipes by wavelet transform and neural network-based classification

Quantitative Detection of Pipeline Cracks Based on Ultrasonic Guided Waves and Convolutional Neural Network

In this study, a quantitative detection method of pipeline cracks based on a one-dimensional convolutional neural network (1D-CNN) was developed using the time-domain signal of ultrasonic guided waves and the crack size of the pipeline as the input and output, respectively. Pipeline ultrasonic guided wave detection signals under different crack defect conditions were obtained via numerical simulations and experiments, and these signals were input as features into a multi-layer perceptron and one-dimensional convolutional neural network (1D-CNN) for training. The results revealed that the 1D-CNN performed better in the quantitative analysis of pipeline crack defects, with an error of less than 2% in the simulated and experimental data, and it could effectively evaluate the size of crack defects from the echo signals under different frequency excitations. Thus, by combining the ultrasonic guided wave detection technology and CNN, a quantitative analysis of pipeline crack defects can be effectively realized.

Ultrasonic based concrete defects identification via wavelet packet transform and GA-BP neural network

Concrete is the main material in building. Since its poor structural integrity may cause accidents, it is significant to detect defects in concrete. However, it is a challenging topic as the unevenness of concrete would lead to the complex dynamics with uncertainties in the ultrasonic diagnosis of defects. Note that the detection results mainly depend on the direct parameters, e.g., the time of travel through the concrete. The current diagnosis accuracy and intelligence level are difficult to meet the design requirement for automatic and increasingly high-performance demands. To solve the mentioned problems, our contribution of this paper can be summarized as establishing a diagnosis model based on the GA-BPNN method and ultrasonic information extracted that helps engineers identify concrete defects. Potentially, the application of this model helps to improve the working efficiency, diagnostic accuracy and automation level of ultrasonic testing instruments. In particular, we propose a simple and effective signal recognition method for small-size concrete hole defects. This method can be divided into two parts: (1) signal effective information extraction based on wavelet packet transform (WPT), where mean value, standard deviation, kurtosis coefficient, skewness coefficient and energy ratio are utilized as features to characterize the detection signals based on the analysis of the main frequency node of the signals, and (2) defect signal recognition based on GA optimized back propagation neural network (GA-BPNN), where the cross-validation method has been used for the stochastic division of the signal dataset and it leads to the BPNN recognition model with small bias. Finally, we implement this method on 150 detection signal data which are obtained by the ultrasonic testing system with 50 kHz working frequency. The experimental test block is a C30 class concrete block with 5, 7, and 9 mm penetrating holes. The information of the experimental environment, algorithmic parameters setting and signal processing procedure are described in detail. The average recognition accuracy is 91.33% for the identification of small size concrete defects according to experimental results, which verifies the feasibility and efficiency.

Carburization level identification in industrial HP pipes using ultrasonic evaluation and machine learning

Ultrasound nondestructive testing is commonly applied in industry to guarantee structural integrity. HP steel pyrolysis furnaces are used in petrochemical industry for lightweight hydrocarbon production. HP steel chromium content may be reduced in high-temperatures due to carbon diffusion. This characterizes the carburization phenomenon, which modifies magnetic properties, reduces mechanical resistance and may lead to structural rupture. For safe operation it is required to frequently determine carburizing level in pyrolysis furnace pipes. This is traditionally performed manually using magnetic evaluation. This work proposes a novel procedure for carburizing level estimation using ultrasonic evaluation associated to signal processing and machine learning techniques. Experimental data from pulse-echo ultrasonic tests performed in HP steel pipes are used. Discrete Fourier transform was applied for feature extraction and different classification systems (neural networks, k-nearest neighbors and decision trees) are applied and compared in terms of carburizing level identification efficiency.

Structural health monitoring using polymer-based capacitive micromachined ultrasonic transducers (CMUTs)

Transducers based on a capacitive micromachined ultrasonic transducer (CMUT) design have been fabricated using a rapid prototyping technique. This results in a device that is constructed principally from polymers, in a process which is simple and inexpensive. The resultant devices can be attached to the surfaces of solids. Their peak sensitivity is in the 80-100 kHz range, making them ideal for applications such as acoustic emission and structural health monitoring. Good low frequency sensitivity leads to applications in vibration monitoring.