Integration of artificial intelligence with a customized Four-Probe station for I-V characteristic classification and prediction

Abstract

The incorporation of Artificial Intelligence (AI) is pivotal in automating intricate technical tasks, significantly enhancing accuracy and efficiency while alleviating the burdens of repetitive monitoring traditionally borne by technicians. This study focuses on developing a customized four-probe station integrated with sophisticated AI models aimed at classifying current–voltage ($I-V$) characteristics and extracting essential parameters. Our methodology encompasses the fabrication of precision-engineered gold-plated probes, meticulously assembled with a three-dimensional (3D) moving head to ensure optimal contact and measurement fidelity across a variety of electronic and optoelectronic devices. Data acquisition is executed via a source meter unit, followed by rigorous post-processing utilizing advanced algorithms, including convolutional neural networks and random forest techniques. Notably, the gold-plated contacts enhance measurement accuracy by providing superior conductivity and minimizing contact resistance, while the movable head allows for dynamic adjustment, facilitating precise probe alignment for consistent data retrieval. The results demonstrate a remarkable capability in classifying $I-V$ characteristics with a root-mean-square (RMS) error of less than 1%, underscoring the system’s reliability and accuracy. Moreover, our predictive models effectively utilize previously recorded measurements to forecast the degradation profiles of devices, thus offering significant insights into device longevity and performance.