Summary
This case study outlines how TOFAŞ, an automotive manufacturer, implemented KNIME to automate quality control and predictive maintenance processes. The challenge faced by TOFAŞ was the manual monitoring of spot welding processes, which was time-consuming and prone to errors, leading to quality control delays and increased maintenance costs. By integrating IoT sensor data and historical fault records into KNIME, TOFAŞ developed a centralized system that utilized deep learning and logistic regression for real-time fault detection. The results of this implementation included annual savings of over €1.3 million, an increase in production efficiency with 28 additional vehicles produced daily, and a 2.9% rise in Overall Equipment Effectiveness. The automated system significantly reduced manual work, improved tracking, and facilitated faster decision-making on the production floor. This success story highlights the effectiveness of KNIME in enhancing operational efficiency and quality assurance in manufacturing environments.
