Classification of Micro-Damage in Piezoelectric Ceramics Using Machine Learning of Ultrasound Signals

Intelligent recognition of composite material damage based on deep learning and infrared testing

Composite materials are commonly used in aircraft, and the integrity of these materials affects both flight and safety performance. Damage detection technology involving infrared nondestructive testing has played an important role in damage detection in aircraft composite materials. Traditional manual detection methods are inefficient, and the use of intelligent detection methods can effectively improve detection efficiency. Due to the diverse types of damage that can occur in composite materials, this damage is difficult to distinguish solely from infrared images. The introduction of infrared signals, which is temporal signals, provides the possibility of judging the type of damage. In this paper, a 1D-YOLOv4 network is established. The network is based on the YOLOv4 network and adds a changing neck and a 1D-CNN for improvement. Testing shows that the algorithm can identify infrared images and infrared signals in composite materials. Its recognition accuracy is 98.3%, with an AP of 91.9%, and a kappa of 0.997. Comparing the network in this paper with networks such as YOLOv3, YOLOv4 and YOLOv4+Neck, the results show that the proposed network is more effective. At the same time, the detection effects of the original data, the fitted data, the first derivative data and the second derivative data are studied, and the detection effect of the first derivative data has the best outcome.

Machine learning and big data provide crucial insight for future biomaterials discovery and research

Machine learning have been widely adopted in a variety of fields including engineering, science, and medicine revolutionizing how data is collected, used, and stored. Their implementation has led to a drastic increase in the number of computational models for the prediction of various numerical, categorical, or association events given input variables. We aim to examine recent advances in the use of machine learning when applied to the biomaterial field. Specifically, quantitative structure properties relationships offer the unique ability to correlate microscale molecular descriptors to larger macroscale material properties. These new models can be broken down further into four categories: regression, classification, association, and clustering. We examine recent approaches and new uses of machine learning in the three major categories of biomaterials: metals, polymers, and ceramics for rapid property prediction and trend identification. While current research is promising, limitations in the form of lack of standardized reporting and available databases complicates the implementation of described models. Herein, we hope to provide a snapshot of the current state of the field and a beginner's guide to navigating the intersection of biomaterials research and machine learning. STATEMENT OF SIGNIFICANCE: Machine learning and its methods have found a variety of uses beyond the field of computer science but have largely been neglected by those in realm of biomaterials. Through the use of more computational methods, biomaterials development can be expediated while reducing the need for standard trial and error methods. Within, we introduce four basic models that readers can potentially apply to their current research as well as current applications within the field. Furthermore, we hope that this article may act as a "call to action" for readers to realize and address the current lack of implementation within the biomaterials field.

Damage localization in piezo-ceramic using ultrasonic waves excited by dual point contact excitation and detection scheme

A novel experimental technique based on point contact and Coulomb coupling is devised and optimized for ultrasonic imaging of bulk and guided waves propagation in piezo-ceramics. The Coulomb coupling technique exploits the coupling and transfer of electric field to mechanical vibrations by excitation of phonons. The point contact excitation and detection technique facilitates the spatial-temporal imaging of ultrasonic waves. The motivation of this research is the diagnosis and localization of surface cracks in the piezoelectric sensors and actuators. The underlying principle of the detection scheme is that any discontinuity on the surface causes high localization of electric gradient. The localized electric field at the defect boundaries enables then to behave as secondary passive ultrasonic sources resulting in strong back reflections. However, due to the interference between transmitted and reflected wave components from rigid boundaries and defect, the resolution on the localization of the damage is challenging. Therefore, an algorithm based on the two-dimensional spectral decomposition is utilized for selective suppression of the transmitted wave. The algorithm includes data transformation and vectorization in polar coordinates for efficient spectral decomposition. In the spectral domain, the complex wave component (phase and amplitude) are suppressed for the transmitted wave field. The reflected wave component in the spectral domain is retained and retrieved back using inverse spectral transformation. The algorithm is successful in retaining and exemplifying only the reflected wave sources arising from the strong scattering of ultrasonic waves from the surface and sub-surface defects. In summary, a novel experimental technique based on Coulomb coupling and spectral decomposition technique has been implemented for localization of surface defect in piezo-ceramic structures.

A Data-Driven Damage Identification Framework Based on Transmissibility Function Datasets and One-Dimensional Convolutional Neural Networks: Verification on a Structural Health Monitoring Benchmark Structure

Vibration-based data-driven structural damage identification methods have gained large popularity because of their independence of high-fidelity models of target systems. However, the effectiveness of existing methods is constrained by critical shortcomings. For example, the measured vibration responses may contain insufficient damage-sensitive features and suffer from high instability under the interference of random excitations. Moreover, the capability of conventional intelligent algorithms in damage feature extraction and noise influence suppression is limited. To address the above issues, a novel damage identification framework was established in this study by integrating massive datasets constructed by structural transmissibility functions (TFs) and a deep learning strategy based on one-dimensional convolutional neural networks (1D CNNs). The effectiveness and efficiency of the TF-1D CNN framework were verified using an American Society of Civil Engineers (ASCE) structural health monitoring benchmark structure, from which dynamic responses were captured, subject to white noise random excitations and a number of different damage scenarios. The damage identification accuracy of the framework was examined and compared with others by using different dataset types and intelligent algorithms. Specifically, compared with time series (TS) and fast Fourier transform (FFT)-based frequency-domain signals, the TF signals exhibited more significant damage-sensitive features and stronger stability under excitation interference. The utilization of 1D CNN, on the other hand, exhibited some unique advantages over other machine learning algorithms (e.g., traditional artificial neural networks (ANNs)), particularly in aspects of computation efficiency, generalization ability, and noise immunity when treating massive, high-dimensional datasets. The developed TF-1D CNN damage identification framework was demonstrated to have practical value in future applications.