The resolution of the Poisson equation is usually one of the most computationally intensive steps for incompressible fluid solvers. Lately, DeepLearning, and especially convolutional neural networks (CNNs), has been introduced to solve this equation, leading to significant inference time reduction at the cost of a lack of guarantee on the accuracy of the solution.This drawback might lead to inaccuracies, potentially unstable simulations and prevent performing fair assessments of the CNN speedup for different network architectures. To circumvent this issue, a hybrid strategy is developed, which couples a CNN with a traditional iterative solver to ensure a user-defined accuracy level. The CNN hybrid method is tested on two flow cases: (a) the flow around a 2D cylinder and (b) the variable-density plumes with and without obstacles (both 2D and 3D), demonstrating remarkable generalization capabilities, ensuring both the accuracy and stability of the simulations. The error distribution of the predictions using several network architectures is further investigated in the plume test case. The introduced hybrid strategy allows a systematic evaluation of the CNN performance at the same accuracy level for various network architectures. In particular, the importance of incorporating multiple scales in the network architecture is demonstrated, since improving both the accuracy and the inference performance compared with feedforward CNN architectures. Thus, in addition to the pure networks’ performance evaluation, this study has also led to numerous guidelines and results on how to build neural networks and computational strategies to predict unsteady flows with both accuracy and stability requirements.

This paper presents a hybrid strategy-based coordinate controller with a novel nonlinear disturbance observer for autonomous underwater vehicle manipulator systems (UVMSs). This method can reduce the influence from external unknown disturbances, inner coupling effects and model uncertainties by using a modified disturbance observer. Considering the natural redundancy property of the UVMS, the redundancy resolution algorithm is often utilized to give desired trajectories in the vehicle–joint space. However, because of the calibration errors, assembling errors and numerical errors, these desired trajectories may not lead the end-effector to the goal point accurately. To realize accurate motion control even when small errors exist in the planning phase, a hybrid strategy is introduced to transform the controller in the joint–vehicle space to the controller in the task space. Numerical simulations based on a UVMS have been carried out to testify the effectiveness of the proposed coordinate controller and the hybrid strategy. During the simulations, unknown disturbances are exerted upon the system. The trajectory tracking and error fixing performances are discussed in comparative analyses. The controller also maintains robust characteristics in comparison with the passivity-based controller and the proposed controller but without the disturbance observer. Experiments are also carried out to test its performance.