{"title":"Integration of artificial intelligence with a customized Four-Probe station for I-V characteristic classification and prediction","authors":"","doi":"10.1016/j.measurement.2024.115676","DOIUrl":null,"url":null,"abstract":"<div><p>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 (<span><math><mrow><mi>I</mi><mo>-</mo><mi>V</mi></mrow></math></span>) 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 <span><math><mrow><mi>I</mi><mo>-</mo><mi>V</mi></mrow></math></span> 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.</p></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":null,"pages":null},"PeriodicalIF":5.2000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0263224124015616","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
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 () 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 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.
期刊介绍:
Contributions are invited on novel achievements in all fields of measurement and instrumentation science and technology. Authors are encouraged to submit novel material, whose ultimate goal is an advancement in the state of the art of: measurement and metrology fundamentals, sensors, measurement instruments, measurement and estimation techniques, measurement data processing and fusion algorithms, evaluation procedures and methodologies for plants and industrial processes, performance analysis of systems, processes and algorithms, mathematical models for measurement-oriented purposes, distributed measurement systems in a connected world.