The use of a digital twin to improve resource efficiency in manufacturing [in Ukrainian]

Abstract

The aim of the work is to determine the role of digital twins as an integration platform for overcoming the limitations of traditional methods of increasing resource efficiency in industry. Comparative and system analysis methods were used to compare the functionality of classical management systems (Lean Six Sigma, REC, SCADA) with the capabilities of cyber-physical systems based on IoT. Classical resource management systems are characterized by reactivity, discrete data collection and fragmented analysis. The integration of digital twins transforms these approaches into proactive systems thanks to a continuous flow of IoT data and machine learning algorithms. The concept of Lean Six Sigma 4.0 based on digital twins replaces discrete audits with continuous analytics, preventing defects before they occur. Unlike SCADA systems, which only signal when parameters exceed the norm, digital twins aggregate data from sensors and machine vision systems to build a live production model, independently detecting the root causes of deviations. The technology overcomes the limitations of static computer modeling (DES, FEA, CFD) by creating a two-way connection between the digital master and the digital shadow, which ensures automatic updating of the model with real operational data. The practical application of digital twins minimizes energy and raw material consumption through automatic adjustment of technological parameters in real time. Predictive modeling allows you to safely test optimization scenarios, prevent equipment downtime and reduce the level of defects without physical consumption of materials for full-scale experiments. Digital twin is a conceptual transition from static resource efficiency audits to continuous cyber-physical systems of intelligent production management.