Answers are grounded in this paper and cite their sources.
The study demonstrates a digital twin integrating adaptive control and forecasting in agricultural machinery, suggesting significant resource optimization.
The purpose of this article is to develop a functional architecture of a digital twin as a component of a cyber- physical system for washing agricultural machinery, taking into account the real condition of the object being cleaned. Special attention is paid to ensuring adaptive control of the washing process based on current sensor data and forecasting of cleaning parameters to improve energy efficiency, optimize resource consumption, and reduce operator workload. The research presents the functional interaction scheme of the system's core levels – physical, sensor, control (PLC), supervisory (SCADA), and digital twin level. A mathematical model is proposed based on the assessment of surface contamination level, machinery dimensions, temperature, and pressure. These input parameters form a feature vector, which is processed by a forecasting model that determines the optimal cleaning time and generates control signals for actuators. In the software implementation, the model consists of three key modules – input data processing, numerical integration of equations, and adaptive logic. To determine the optimal washing cycle duration, a neural network module trained on historical data is applied. The study confirms the feasibility of using a digital twin within a cyber-physical system for the efficient and intelligent cleaning of agricultural equipment. The application of the forecasting model allows real-time adaptation of the process, significantly reducing water, electricity, and detergent consumption. The proposed approach facilitates the transition from conventional to intelligent technologies integrated into the digital manufacturing infrastructure and contributes to the implementation of Industry 4.0 principles in Ukrainian mechanical engineering.
No takes yet. Share an insight, caveat, or question.
Filkin et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: