A pump-driven actuator, which usually called an electro-hydrostatic actuator (EHA), is widely used in aerospace and industrial applications. It is interesting to optimize both its static and dynamic performances, such as weight, energy consumption, rise time, and dynamic stiffness, in the design phase. It is difficult to decide the parameters, due to the high number of objectives to be taken into consideration simultaneously. This paper proposes a simulation-based multi-objective optimization (MOO) design method for EHA with AMESim and a python script The model of an EHA driving a flight control surface is carried out by AMESim. The python script generates design parameters by using an intelligent search method and transfers them to the AMESim model. Then, the script can run a simulation of the AMESim model with a pre-set motion and load scenario of the control surface. The python script can also obtain the results when the simulation is finished, which can then be used to evaluate performance as the objective of optimization. There are four objectives considered in the present study, which are weight, energy consumption, rise time, and dynamic stiffness. The weight is predicted by the scaling law, based on the design parameters. The performances of dynamic response energy efficiency and dynamic stiffness are obtained by the simulation model. A multi-objective particle swarm optimization (MOPSO) algorithm is applied to search for the parameter solutions at the Pareto-front of the desired objectives. The optimization results of an EHA, based on the proposed methodology, are demonstrated. The results are very useful for engineers, to help determine the design parameters of the actuator in the design phase. The proposed method and platform are valuable in system design and optimization.

With the development of precision sensing instruments and data storage devices, the fusion of multi-sensor data in gearbox fault diagnosis has attracted much attention. However, existing methods have difficulty in capturing the local temporal dependencies of multi-sensor monitoring information, and the inescapable noise severely decreases the accuracy of multi-sensor information fusion diagnosis. To address these issues, this paper proposes a fault diagnosis method based on dynamic graph convolutional neural networks and hard threshold denoising. Firstly, considering that the relationships between monitoring data from different sensors change over time, a dynamic graph structure is adopted to model the temporal dependencies of multi-sensor data, and, further, a graph convolutional neural network is constructed to achieve the interaction and feature extraction of temporal information from multi-sensor data. Secondly, to avoid the influence of noise in practical engineering, a hard threshold denoising strategy is designed, and a learnable hard threshold denoising layer is embedded into the graph neural network. Experimental fault datasets from two typical gearbox fault test benches under environmental noise are used to verify the effectiveness of the proposed method in gearbox fault diagnosis. The experimental results show that the proposed DDGCN method achieves an average diagnostic accuracy of up to 99.7% under different levels of environmental noise, demonstrating good noise resistance.