To correct wavefront aberrations, commonly employing proportional-integral control in adaptive optics (AO) systems, the control process depends strictly on the response matrix of the deformable mirror. The alignment error between the Hartmann–Shack wavefront sensor and the deformable mirror is caused by various factors in AO systems. In the conventional control method, the response matrix can be recalibrated to reduce the impact of alignment error, but the impact cannot be eliminated. This paper proposes a control method based on a deep learning control model (DLCM) to compensate for wavefront aberrations, eliminating the dependence on the deformable mirror response matrix. Based on the wavefront slope data, the cost functions of the model network and the actor network are defined, and the gradient optimization algorithm improves the efficiency of the network training. The model network guarantees the stability and convergence speed, while the actor network improves the control accuracy, realizing an online identification and self-adaptive control of the system. A parameter-sharing mechanism is adopted between the model network and the actor network to control the system gain. Simulation results show that the DLCM has good adaptability and stability. Through self-learning, it improves the convergence accuracy and iterations, as well as the adjustment tolerance of the system.

In this letter, we proposed a Multi-Stage phase-shifting network (MSPS-Net) based on Multi-Stage Progressive Image Restoration for one-shot phase retrieval interferometry. This network generates three interferograms with specific phase shifts from interferograms recorded in a single frame excellently, metrics such as PSNR and SSIM indicate that the generated phase shift interferograms have high similarity to the real one. Further, By analyzing different types of aberrations, RMS value of error map retrieved by the proposed method is less than, which shows higher accuracy than latest phase-shifting network method built by Encoder and Decoder. All the experiment results show that our solution is available for the problem of high-accuracy dynamic phase measurement and has excellent generalization ability.

We report on an aberration correction algorithm for wavefront sensorless adaptive optics (WFSless AO) system based on deep reinforcement learning. Firstly, it’s verified that reinforcement learning theory can be applied in our system. In addition, the deep deterministic policy gradient (DDPG) algorithm is introduced to build the control structure. After that, deep learning is used to deal with the messy raw images of far-field intensity distribution. We emphatically present how to design a feature extraction with the Convolutional Neural Network (CNN) in the control structure. To demonstrate the performance of this structure, some comparisons are made with stochastic parallel gradient descent (SPGD) algorithm and the WFSless AO based on general modes (AOG) algorithm. The results indicate that the correction speed of our method improves about 9 times and 2.5 times respectively for the similar correction effect.

We present the first model-based parameter identification method in the power distribution network to successfully achieve parameter identification directly based on sequential model-based optimization. This method is building a model with a posteriori probability to optimize an objective function. Furthermore, to achieve an efficient exploration, three different acquisition functions, i.e., random search, tree-structured Parzen estimator approach, and simulated annealing, were proposed. We applied our three models and the conventional model-free method to the actual feeder data with no adjustment of the other conditions. The experiment shows that our method achieves at least 25% and 70% improvements in accuracy and convergence speed, respectively.

Precise dynamic single-frame interferometry based on virtual phase shifting technique remains challenging due to the difficulty in satisfying the requirements for the quality and amount of fine-grained fringe’s interferograms. Here we introduce a novel deep learning architecture, the Transformer Encoder-Convolution Decoder Phase Shift Network (TECD-PSNet), that achieves high-fidelity interferogram reconstruction. TECD-PSNet seamlessly integrates the strengths of transformer blocks in capturing global descriptions and convolution blocks in efficient feature extraction. A key process is the incorporation of a residual local negative feedback enhancement mechanism that adaptively amplifies losses in high-error regions to boost fine-grained detail sensitivity. This approach enables accurate phase retrieval for diverse pupil shapes, enhancing adaptability to various optical setups, while significantly reducing the amount of training data required. Experiments demonstrate a 22.9% improvement in PSNR for reconstructed interferograms and a 36.7% reduction in RMS error for retrieved phases compared to state-of-the-art methods.