Abstract The methods of building a model like Markov chain Monte‐Carlo (MCMC) and sequential model‐based global optimization (SMBO) in power distribution network (PDN) have achieved parameter identification successfully without extra measurement devices. However, the data processing focused on the feeder data is not concerned yet. In this study, the authors present a dynamic data prepossessing method for parameter identification in PDN to successfully obtain a more accurate result. This method considers the similarities of feeder data in both spatial relationship and statistical theory, and then realizes a dynamic aggregation process for new coming data and obtains a set of data with tighter higher dimensional relationship for following identification task. In experiments, the authors applied this data processing method to the actual feeder data with no adjustment of the other condition; identification results with the authors’ processing achieve a 5.3% improvement in accuracy at most.
Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI
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 the applications of wave-front detection using second-harmonic generation, the spatial phase distribution needs to calculate accurately before and after frequency doubling in real-time. This letter presents a learning-based method called extreme learning machine to fit the corresponding relationship of phase between the fundamental frequency wave and the second-harmonic. The Zernike coefficients of the fundamental frequency wave wave-front and the second-harmonic wave-front are used as input data for Extreme Learning Machine model training and testing. The effects of the intensity-dependent phase shift and walk-off are also considered. The reliability of the trained Extreme Learning Machine model was accessed based on simulation results. The proposed method has shown distinct competitive advantages in real-time calculation efficiency. The well-trained Extreme Learning Machine model only needs 0.026 seconds to accurately predict the phase distribution of the fundamental frequency wave. The runtime is three orders of magnitude smaller than the traditional numerical calculation method.
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 a wavefront sensorless adaptive optics (WFSless AO) system based on deep reinforcement learning. First, it is verified that the reinforcement learning theory can be applied in our system. In addition, the deep deterministic policy gradient 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 in the control structure. To demonstrate the performance of this structure, some comparisons are made with the stochastic parallel gradient descent algorithm and the WFSless AO based on general modes 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.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)