Hermann Seitz

In ultrashort-pulsed laser processing, surface modification is subject to complex laser and scanning parameter studies. In addition, quality assurance systems for monitoring surface modification are still lacking. Automated laser processing routines featuring machine learning (ML) can help overcome these limitations, but they are largely absent in the literature and still lack practical applications. This paper presents a new methodology for machine learning classification of self-organized surface structures based on light microscopic images. For this purpose, three application-relevant types of self-organized surface structures are fabricated using a 300 fs laser system on hot working tool steel and stainless-steel substrates. Optical images of the hot working tool steel substrates were used to learn a classification algorithm based on the open-source tool Teachable Machine from Google. The trained classification algorithm achieved very high accuracy in distinguishing the surface types for the hot working steel substrate learned on, as well as for surface structures on the stainless-steel substrate. In addition, the algorithm also achieved very high accuracy in classifying the images of a specific structure class captured at different optical magnifications. Thus, the methodology proposed represents a simple and robust automated classification of surface structures that can be used as a basis for further development of quality assurance systems, automated process parameter recommendation, and inline laser parameter control.

This paper delves into the application of vibration-based energy harvesting to power environmental sensor nodes, a critical component of modern data collection systems. These sensor nodes play a crucial role in structural health monitoring, providing essential data on external conditions that can affect the health and performance of structures. We investigate the feasibility and efficiency of utilizing piezoelectric vibration energy harvesters to sustainably power environmental wireless sensor nodes on the one hand. On the other hand, we exploit different approaches to minimize the sensor node’s power consumption and maximize its efficiency. The investigations consider various sensor node platforms and assess their performance under different voltage levels and broadcast frequencies. The findings reveal that optimized harvester designs enable real-time data broadcasting with short intervals, ranging from 1 to 3 s, expanding the horizons of environmental monitoring, and show that in case the system includes a battery as a backup plan, the battery’s lifetime can be extended up to 9 times. This work underscores the potential of vibration energy harvesting as a viable solution for powering sensor nodes, enhancing their autonomy, and reducing maintenance costs in remote and challenging environments. It opens doors to broader applications of sustainable energy sources in environmental monitoring and data collection systems.