This paper deals with the design and implementation of a universal cyber-physical model capable of simulating any production process in order to optimize its logistics systems. The basic idea is the direct possibility of testing and debugging advanced logistics algorithms using a digital twin outside the production line. Since the digital twin requires a physical connection to a real line for its operation, this connection is substituted by a modular cyber-physical system (CPS), which replicates the same physical inputs and outputs as a real production line. Especially in fully functional production facilities, there is a trend towards optimizing logistics systems in order to increase efficiency and reduce idle time. Virtualization techniques in the form of a digital twin are standardly used for this purpose. The possibility of an initial test of the physical implementation of proposed optimization changes before they are fully implemented into operation is a pragmatic question that still resonates on the production side. Such concerns are justified because the proposed changes in the optimization of production logistics based on simulations from a digital twin tend to be initially costly and affect the existing functional production infrastructure. Therefore, we created a universal CPS based on requirements from our cooperating manufacturing companies. The model fully physically reproduces the real conditions of simulated production and verifies in advance the quality of proposed optimization changes virtually by the digital twin. Optimization costs are also significantly reduced, as it is not necessary to verify the optimization impact directly in production, but only in the physical model. To demonstrate the versatility of deployment, we chose a configuration simulating a robotic assembly workplace and its logistics.

The article deals with aspects of identifying industrial products in motion based on their color. An automated robotic workplace with a conveyor belt, robot and an industrial color sensor is created for this purpose. Measured data are processed in a database and then statistically evaluated in form of type A standard uncertainty and type B standard uncertainty, in order to obtain combined standard uncertainties results. Based on the acquired data, control charts of RGB color components for identified products are created. Influence of product speed on the measuring process identification and process stability is monitored. In case of identification uncertainty i.e., measured values are outside the limits of control charts, the K-nearest neighbor machine learning algorithm is used. This algorithm, based on the Euclidean distances to the classified value, estimates its most accurate iteration. This results into the comprehensive system for identification of product moving on conveyor belt, where based on the data collection and statistical analysis using machine learning, industry usage reliability is demonstrated.