arXiv subjects

Xiaoying Zhao

Publications and source records attributed to Xiaoying Zhao.

7 recordsLinked to original sources

arXiv2023

Trend-Based SAC Beam Control Method with Zero-Shot in Superconducting Linear Accelerator

The superconducting linear accelerator is a highly flexiable facility for modern scientific discoveries, necessitating weekly reconfiguration and tuning. Accordingly, minimizing setup time proves essential in affording users with ample experimental time. We propose a trend-based soft actor-critic(TBSAC) beam control method with strong robustness, allowing the agents to be trained in a simulated environment and applied to the real accelerator directly with zero-shot. To validate the effectiveness of our method, two different typical beam control tasks were performed on China Accelerator Facility for Superheavy Elements (CAFe II) and a light particle injector(LPI) respectively. The orbit correction tasks were performed in three cryomodules in CAFe II seperately, the time required for tuning has been reduced to one-tenth of that needed by human experts, and the RMS values of the corrected orbit were all less than 1mm. The other transmission efficiency optimization task was conducted in the LPI, our agent successfully optimized the transmission efficiency of radio-frequency quadrupole(RFQ) to over $85\%$ within 2 minutes. The outcomes of these two experiments offer substantiation that our proposed TBSAC approach can efficiently and effectively accomplish beam commissioning tasks while upholding the same standard as skilled human experts. As such, our method exhibits potential for future applications in other accelerator commissioning fields.

physics.acc-ph↗

arXiv2023

Eeg2vec: Self-Supervised Electroencephalographic Representation Learning

Recently, many efforts have been made to explore how the brain processes speech using electroencephalographic (EEG) signals, where deep learning-based approaches were shown to be applicable in this field. In order to decode speech signals from EEG signals, linear networks, convolutional neural networks (CNN) and long short-term memory networks are often used in a supervised manner. Recording EEG-speech labeled data is rather time-consuming and laborious, while unlabeled EEG data is abundantly available. Whether self-supervised methods are helpful to learn EEG representation to boost the performance of EEG auditory-related tasks has not been well explored. In this work, we first propose a self-supervised model based on contrastive loss and reconstruction loss to learn EEG representations, and then use the obtained pre-trained model as a feature extractor for downstream tasks. Second, for two considered downstream tasks, we use CNNs and Transformer networks to learn local features and global features, respectively. Finally, the EEG data from other channels are mixed into the chosen EEG data for augmentation. The effectiveness of our method is verified on the EEG match-mismatch and EEG regression tasks of the ICASSP2023 Auditory EEG Challenge.

eess.AS↗

arXiv2022

Learning Incrementally to Segment Multiple Organs in a CT Image

There exists a large number of datasets for organ segmentation, which are partially annotated and sequentially constructed. A typical dataset is constructed at a certain time by curating medical images and annotating the organs of interest. In other words, new datasets with annotations of new organ categories are built over time. To unleash the potential behind these partially labeled, sequentially-constructed datasets, we propose to incrementally learn a multi-organ segmentation model. In each incremental learning (IL) stage, we lose the access to previous data and annotations, whose knowledge is assumingly captured by the current model, and gain the access to a new dataset with annotations of new organ categories, from which we learn to update the organ segmentation model to include the new organs. While IL is notorious for its `catastrophic forgetting' weakness in the context of natural image analysis, we experimentally discover that such a weakness mostly disappears for CT multi-organ segmentation. To further stabilize the model performance across the IL stages, we introduce a light memory module and some loss functions to restrain the representation of different categories in feature space, aggregating feature representation of the same class and separating feature representation of different classes. Extensive experiments on five open-sourced datasets are conducted to illustrate the effectiveness of our method.

eess.IV↗

arXiv2022

Coordinated Frequency Control through Safe Reinforcement Learning

With widespread deployment of renewables, the electric power grids are experiencing increasing dynamics and uncertainties, with its secure operation being threatened. Existing frequency control schemes based on day-ahead offline analysis and minute-level online sensitivity calculations are difficult to adapt to rapidly changing system states. In particular, they are unable to facilitate coordinated control of system frequency and power flows. A refined approach and tools are urgently needed to assist system operators to make timely decisions. This paper proposes a novel model-free coordinated frequency control framework based on safe reinforcement learning, with multiple control objectives considered. The load frequency control problem is modeled as a constrained Markov decision process, which can be solved by an AI agent continuously interacting with the grid to achieve sub-second decision making. Extensive numerical experiments conducted at East China Power Grid demonstrate the effectiveness and promise of the proposed method.

eess.SY↗

arXiv2021

An Unconditionally Stable Conformal LOD-FDTD Method For Curved PEC Objects and Its Application to EMC Problems

The traditional finite-difference time-domain (FDTD) method is constrained by the Courant-Friedrich-Levy (CFL) condition and suffers from the notorious staircase error in electromagnetic simulations. This paper proposes a three-dimensional conformal locally-one-dimensional FDTD (CLOD-FDTD) method to address the two issues for modeling perfectly electrical conducting (PEC) objects. By considering the partially filled cells, the proposed CLOD-FDTD method can significantly improve the accuracy compared with the traditional LOD-FDTD method and the FDTD method. At the same time, the proposed method preserves unconditional stability, which is analyzed and numerically validated using the Von-Neuman method. Significant gains in Central Processing Unit (CPU) time are achieved by using large time steps without sacrificing accuracy. Two numerical examples include a PEC cylinder and a missile are used to verify its accuracy and efficiency with different meshes and time steps. It can be found from these examples, the CLOD-FDTD method show better accuracy and can improve the efficiency compared with those of the traditional FDTD method and the traditional LOD-FDTD method.

cs.CE↗

arXiv2019

Adaptive Online Learning with Momentum for Contingency-based Voltage Stability Assessment

Voltage stability refers to the ability of a power system to maintain acceptable voltages among all buses under normal operating conditions and after a disturbance. In this paper, a measurement-based voltage stability assessment (VSA) framework using online deep learning is developed. Since the topology changes induced by transmission contingencies may significantly reduce the voltage stability margin, different network topologies under different operating conditions are involved in our training dataset. To achieve high accuracy in the training process, a gradient-based adaptive learning algorithms is adopted. Numerical results based on the NETS-NYPS 68-bus system demonstrate the effectiveness of the proposed VSA approach. Moreover, with the proximal function modified adaptively, the adaptive algorithm with momentum outperforms traditional nonadaptive algorithms whose learning rate is constant.

eess.SY↗

arXiv2018

Model Predictive Control of H5 Inverter for Transformerless PV Systems with Maximum Power Point Tracking and Leakage Current Reduction

Transformerless grid-connected solar photovoltaic (PV) systems have given rise to more research and commercial interests due to their multiple merits, e.g., low leakage current and small size. In this paper, a model-predictive-control (MPC)-based strategy for controlling transformerless H5 inverter for single-phase PV distributed generation system is proposed. The method further reduces the PV leakage current in a cost-effective and safe manner and it shows a satisfactory fault-ride-through capability. Moreover, for the first of its kind, PV maximum power point tracking is implemented in the single-stage H5 inverter using MPC-based controllers. Various case studies are carried out, which provide the result comparisons between the proposed and conventional control methods and verify the promising performance of the proposed method.

math.OC↗