Search

Acoustic emission (AE) is an effective method to monitor and control the quality in different technical processes, including tribology and fracture mechanics. However, in highly dynamic processes, the processing of AE signals is very burdensome. At the same time, artificial intelligence (AI) has been considered as a new and powerful tool to overcome both: the complexity of the large data processing with a reasonable computational time. In this contribution, we will present two examples from completely different process where AE techniques are combined with AI in order to make a significant step forward in process monitoring and quality control. To start with, in additive manufacturing, which has been at the center of attention in recent years, we will demonstrate that the combination of AE with AI makes possible to detect several types of defects, including pores.. With the second example, we will prove that the combination of AE with AI is a very promising approach for in situ and real-time monitoring of electrical discharge inside natural rocks. [ABSTRACT FROM AUTHOR]

Laser processing is an important technology in industrial manufacture. Today, a standard quality monitoring of the processed workpieces mainly relies on costly X-ray or time consuming post mortem methods. The commercially available in situ and real-time monitoring units are also accessible and rely on optical measurements or high resolution imaging of the process zone. Unfortunately, their performance is greatly affected by the plume, formed during the overheating of the material. This limits the detection of defects (e.g. pores) formed inside the workpiece. To bypass the aforementioned limits, we focus on acoustic measurements that are the derivatives of the shockwaves, generated inside the workpiece directly during processing. The measurements are conducted using a high sensitive piezo sensor. The acoustic signals are analysed further by state-of-the-art signal processing. This included a compartment of wavelets and Fourier decompositions, followed by machine learning. The developed methodology is realized in a hardware unit that operates in pseudo real-time. The unit was tested on real welds with various materials. The welding experiments were performed using spot weld, Stepless High-speed Accurate and Discrete One-pulse Weld (SHADOW). The tests were carried out at different laser powers that are closely related to the weld quality. The in situ quality control unit demonstrated the capability to classify the weld quality with a confidence level ranged between 82% and 95%. Due to the similar light-matter interaction phenomena, the presented approach and apparatus can also be applied for monitoring other laser-processing technologies, namely: ablation, cutting, drilling and additive manufacturing. [ABSTRACT FROM AUTHOR]

Smart laser technologies are desired that can accurately cut and characterize tissues, such as bone and muscle, with minimal thermal damage and fast healing. Using a long-pulsed laser with a 0.5–10 ms pulse width at a wavelength of 1.07 µm, we investigated the optimum laser parameters for producing craters with minimal thermal damage under both wet and dry conditions. In different tissues (bone and muscle), we analyzed craters of various morphologies, depths, and volumes. We used a two-way Analysis of Variance (ANOVA) test to investigate whether there are significant differences in the ablation efficiency in wet versus dry conditions at each level of the pulse energy. We found that bone and muscle tissue ablated under wet conditions produced fewer cracks and less thermal damage around the craters than under dry conditions. In contrast to muscle, the ablation efficiency of bone under wet conditions was not higher than under dry conditions. Tissue differentiation was carried out based on measured acoustic waves. A Principal Component Analysis of the measured acoustic waves and Mahalanobis distances were used to differentiate bone and muscle under wet conditions. Bone and muscle ablated in wet conditions demonstrated a classification error of less than 6.66% and 3.33%, when measured by a microphone and a fiber Bragg grating, respectively. [ABSTRACT FROM AUTHOR]