Complex assembly tasks remain huge challenge for robots because the traditional control methods rely on complicated contact state analysis. Reinforcement learning (RL) becomes one of the preferred embodiments to const...
详细信息
ISBN:
(纸本)9781728196817
Complex assembly tasks remain huge challenge for robots because the traditional control methods rely on complicated contact state analysis. Reinforcement learning (RL) becomes one of the preferred embodiments to construct the control strategy of complex tasks. In this paper, the method of model-driven RL (MDRL) is employed to construct the control strategy. Then a completely innovative action dimension extension (ADE) mechanism is proposed to further accelerate the training process of RL. The simulation and experiment results demonstrate that the control strategy obtained through combining MDRL and ADE guarantees a more compliant assembly process. Besides, ADE method will enhance the data-efficiency of RL algorithms greatly (about 30%similar to 40%) as well as increase the stable reward.
With the increasing penetration of inverter based renewable energy and distributed energy storages in nowadays’ power systems, the system status and operation conditions are hard to track with traditional scheduling-...
详细信息
ISBN:
(数字)9798350367676
ISBN:
(纸本)9798350378467
With the increasing penetration of inverter based renewable energy and distributed energy storages in nowadays’ power systems, the system status and operation conditions are hard to track with traditional scheduling-based power system transient analysis approach, and more fast and efficient transient analysis methods are needed to address the power system dynamic security problems. This paper proposed a graph computing based power system transient analysis approach to achieve efficient and accurate solution for power system stability analysis. To overcome the data management challenges, a spatiotemporal graph model is constructed for efficient data management in power system transient analysis. Then, a graph computing based transient analysis method is proposed to leverage the parallel computing power to speed up the computational process. Finally, a power system transient analysis software is developed based on the graph computing based transient analysis method to validate the proposed approach.
This paper conducts fundamental research to apply several widely used data-driven models to automate the quality inspection of Tempcore-processed steel rebar and design a prediction model for rebar mechanical properti...
详细信息
The proceedings contain 49 papers. The topics discussed include: modeling operational risk to improve reliability of unmanned aerial vehicles;research on visual detection methods and development trends of surface defe...
ISBN:
(纸本)9798350346251
The proceedings contain 49 papers. The topics discussed include: modeling operational risk to improve reliability of unmanned aerial vehicles;research on visual detection methods and development trends of surface defects of urban tunnels;bearing fault detection and fault size estimation using an integrated PVDF transducer;a support tensor machine-based fault diagnosis method for railway turnout;airborne sound analysis for the detection of bearing faults in railway vehicles with real-world data;optimizing flight control of unmanned aerial vehicles with physics-based reliability models;generative adversarial network for state of health estimation of lithium-ion batteries;reliable thermal monitoring of electric machines through machine learning;a distributed fault detection and estimation for formation of clusters of small satellites;optimizing data training quantity for bearing condition monitoring;and a class-added continual learning method for motor fault diagnosis based on knowledge distillation of representation proximity behavior.
In the new era, big data, cloud computing and other technologies have penetrated into the power industry, providing strong support for power data collection and quality improvement. In this regard, this paper analyzes...
详细信息
The stabilization of second order time delay process with proportional-integral-derivative (PID) controllers is investigated in the paper. The t decomposition method is utilized to decompose and characterize the contr...
详细信息
The 18O Oxygen Isotope Separation process is critical for various scientific, industrial, and medical applications, including climate research and biomedical studies. Given the high value and sensitivity of isotopic m...
详细信息
The proceedings contain 34 papers. The topics discussed include: power insulator defect detection based on multi-scale dense adaptive sensing;abnormal line loss identification of distributed PV low-voltage distributio...
The proceedings contain 34 papers. The topics discussed include: power insulator defect detection based on multi-scale dense adaptive sensing;abnormal line loss identification of distributed PV low-voltage distribution area based on data driven;an improved optimal tracking rotor algorithm of wind turbine based on dynamic adjustment of compensation coefficient;flexible adaptive integrated compensation strategy for voltage sag;control strategy of three-level active neutral point clamped grid connected inverters in unbalanced power grid;analysis of minimum rotational inertia requirements for power system frequency stability;a fault diagnosis approach for wind turbine gearbox based on ensemble learning model and dung beetle optimization algorithm;power-impact-harmonic characteristics analysis and modeling of diversified power loads in urban power grid;and transmission section search method based on variable scale nearest neighbor propagation clustering.
Radio channel modeling is one of the most fundamental aspects in the process of designing, optimizing, and simulating wireless communication networks. In this field, long-established approaches such as analytical chan...
详细信息
ISBN:
(纸本)9781665442664
Radio channel modeling is one of the most fundamental aspects in the process of designing, optimizing, and simulating wireless communication networks. In this field, long-established approaches such as analytical channel models and ray tracing techniques represent the de-facto standard methodologies. However, as demonstrated by recent results, there remains an untapped potential to innovate this research field by enriching model-based approaches with machine learning techniques. In this paper, we present Deep RAdio channel modeling from GeOinformatioN (DRaGon) as a novel machine learning-enabled method for automatic generation of Radio Environmental Maps (REMs) from geographical data. For achieving accurate path loss prediction results, DRaGon combines determining features extracted from a three-dimensional model of the radio propagation environment with raw images of the receiver area within a deep learning model. In a comprehensive performance evaluation and validation campaign, we compare the accuracy of the proposed approach with real world measurements, ray tracing analyses, and well-known channel models. It is found that the combination of expert knowledge from the communications domain and the dataanalysis capabilities of deep learning allows to achieve a significantly higher prediction accuracy than the reference methods.
Last December 2019, health officials in Wuhan, a province from China, identified a novel coronavirus called SARS-CoV-2 causing pneumonia. In March 2020, World Health Organization (WHO) declared COVID-19 disease being ...
详细信息
暂无评论