Abstract
This paper presents the development of a digital model of the production process at a mechanical engineering enterprise, aimed at improving management efficiency using Big Data technologies and multi-criteria optimization methods. The structure of a machine shop was formalized, identifying the main functional elements of the production system, including production areas, buffers, product flow routes, and intra-shop logistics. Parametric models of production units were developed, enabling the assessment of throughput, equipment utilization, work-in-progress volumes, and operating costs. The study analyzed the influence of machining process parameters on surface quality indicators. Predictive dependences of machining quality on cutting speed, feed rate, vibration level, spindle power, and tool wear were constructed. Three-dimensional models of surface roughness variations and heat maps of equipment utilization were developed, enabling the identification of bottlenecks in the production process. An intelligent methodology for optimizing a production system is proposed, based on machine learning, multi-criteria analysis, and digital modeling. The obtained results confirm the possibility of applying the developed approach to creating digital twins of production processes and improving the management efficiency of mechanical engineering enterprises