Application of the Deep CNN-Based Method in Industrial System for Wire Marking Identification

Industry 4.0, a term invented by Wolfgang Wahlster in Germany, is celebrating its 10th anniversary 2021. Still, the digitalization of production environment one hottest topics computer science departments at universities and companies. Optimization processes or redefinition concepts meaningful light current industrial research agendas. Both mentioned optimization are considered numerous subtopics technologies. One most significant these areas newest findings applications artificial intelligence (AI)—machine learning (ML) deep convolutional neural networks (DCNNs). The authors method device that supports wiring assembly control cabinet process, namely, Wire Label Reader (WLR) system. implementation this was big technical challenge. It required very advanced IT technologies, ML, image recognition, DCNN as well. This paper focuses on an in-depth description underlying methodology device, construction, foremostly, processes, through which implemented. for to validate usability within express both advantages challenges connected such process development. noted studies effects AI presented area sparse. Further, idea WLR while also including results training (with recognition 99.7% although challenging conditions), wire users’ opinions. have analyzed how affects time energy consumption, accordingly, device. Among impressive can be mentioned—the ensures reduction regardless number characters printed wire.