In this paper, a strategy for online monitoring of a double-acting pneumatic actuation system is presented. The proposed approach employs the operating point method to evaluate the operating condition of the system in terms of energy efficiency and system robustness. A set of six diagnostic features based on user input data, chamber pressures, and displacement time is used as inputs for a hybrid machine learning model, which is composed of two regression models and one multi-class classification model. The hybrid machine learning model aims to predict corrective actions that should be applied on the system to improve its operating condition. The proposed monitoring system was evaluated in 50 different working conditions, where parameters such as load force, supply pressure, displacement time and stroke were randomly created and an uncertainty factor was applied to the load force to simulate the uncertainties that are commonly present during the design of pneumatic actuation systems. The results evidenced the monitoring system’s ability to effectively set the supply pressure and sonic conductance of flow control valves, ensuring an operation with optimal energy efficiency and robustness.