2026-10-15T08:48:39Z https://www.scidb.cn/oai

10.57760/sciencedb.0119e 2026-09-03T11:11:30Z

2026-09-03 Energy Consumption Prediction for Hydraulic Systems Based on the Fusion of Mechanistic Models and Graph Neural Networks doi:10.57760/sciencedb.0119e en Accurate energy-consumption prediction in hydraulic systems is crucial for optimizing control strategies and economic efficiency. However, owing to complex energy-transfer stages and loss mechanisms, mathematical models yield limited prediction accuracy due to time-varying parameters, whereas data-driven approaches lack physical interpretability generalization. This study proposes an energy-consumption prediction model that integrates an AMESim simulation with a heterogeneous graph neural network (HGNN). First, the system configuration and drive principle are analyzed, and a mechanistic model describing the evolution of energy consumption in the hydraulic drive system is established from the perspective of energy flow. A physics-based simulation model is then developed in AMESim together with a communication interface for external algorithms, thereby ensuring broad applicability at the mechanistic level. Next, the component and circuit topology of the hydraulic system and the relationships among key state variables are represented by a graph neural network. A Transformer-integrated data-driven compensation model (THGNN) is constructed to map the circuit topology and component nodes, and is trained using experimental data to correct errors in the mechanistic simulation. Under mechanistic constraints, the model fully exploits the temporal and graph-structural characteristics of the data, thereby improving the accuracy of hydraulic-system energy-consumption prediction. For the cumulative energy losses of the main pump and control-valve assembly, the proposed method achieves MAPE values of 1.773% and 2.144%, respectively, with R2 values of 0.999 for both. Compared with the standalone AMESim model, the MAPE values are reduced by 51.59% and 87.488%, respectively, while R2 increases by 0.604 and 1.495. Energy consumption prediction; Hydraulic system; Transformer; HGNN Yifei Zhai PUBLIC https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset Science Data Bank