检索结果-内蒙古大学图书馆

Deep Learning-Based Prediction of Subsurface Oil Reservoir Pressure Using Spatio-Temporal Data

学校读者我要写书评

暂无评论

Deep Learning-Based Prediction of Subsurface Oil Reservoir P...

Annual Conference of Industrial Electronics Society

作者： Haibo Cheng Yunpeng He Peng Zeng Shichao Li Valeriy Vyatkin State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Automation Aalto University Helsinki Finland

Prediction of subsurface oil reservoir pressure are critical to hydrocarbon production. However, the accurate pressure estimation faces great challenges due to the complexity and uncertainty of reservoir. The underground seepage flow and petrophysical parameters (permeability and porosity) are important but difficult to measure in oilfield. Deep learning methods have been successfully used in reservoir engineering and oil & gas production process. In this study, the effective but inaccessible subsurface seepage fields are not used, only the spatial coordinates and temporal information are selected as model input to predict reservoir pressure. A stacked GRU-based deep learning model is proposed to map the relationship between spatio-temporal data and reservoir pressure. The proposed deep learning method is verified by using a three-dimensional reservoir model, and compared with commonly-used methods. The results show that the stacked GRU model has a better performance and higher accuracy than other deep learning or machine learning methods in pressure prediction.

关键词：

Pseudo-LiDAR for Visual Odometry

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Deng, Huiying Wang, Guangming Feng, Zhiheng Jiang, Chaokang Wu, Xinrui Miao, Yanzi Wang, Hesheng Advanced Robotics Research Center AI Research Institute School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

As one of the important tasks in the field of robotics and machine vision, LiDAR/visual odometry provides tremendous help for various applications such as navigation, location, etc. In the existing methods, LiDAR odometry shows superior performance, but visual odometry is still widely used for its price advantage. Conventionally, the task of visual odometry mainly rely on the input of continuous images. However, it is very complicated for the odometry network to learn the epipolar geometry information provided by the images. In this paper, the concept of pseudo-LiDAR is introduced into the odometry to solve this problem. The pseudo-LiDAR point cloud back-projects the depth map generated by the image into the 3D point cloud, which changes the way of image representation. Compared with the stereo images, the pseudo-LiDAR point cloud generated by the stereo matching network can get the explicit 3D coordinates. Since the 6 Degrees of Freedom (DoF) pose transformation occurs in 3D space, the 3D structure information provided by the pseudo-LiDAR point cloud is more direct than the image. Compared with sparse LiDAR, the pseudo-LiDAR has a denser point cloud. In order to make full use of the rich point cloud information provided by the pseudo-LiDAR, a projection-aware dense odometry pipeline is adopted. Most previous LiDAR-based algorithms sampled 8192 points from the point cloud as input to the odometry network. The projection-aware dense odometry pipeline takes all the pseudo-LiDAR point clouds generated from the images except for the error points as the input to the network. While making full use of the 3D geometric information in the images, the semantic information in the images is also used in the odometry task. The fusion of 2D-3D is achieved in an image-only based odometry. Experiments on the KITTI dataset prove the effectiveness of our method. To the best of our knowledge, this is the first visual odometry method using pseudo-LiDAR. Copyright © 2022, The Authors. A

关键词： Pipelines

Robust Output Synchronization of Discrete-Time Linear-Time-Invariant Multi-Agent systems Using Phase Tool

学校读者我要写书评

暂无评论

Robust Output Synchronization of Discrete-Time Linear-Time-I...

European Control Conference (ECC)

作者： Xin Mao Dan Wang Wei Chen Li Qiu School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Mechanics and Engineering Science State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China Southern University of Science and Technology Shenzhen China Hong Kong University of Science and Technology Hong Kong S.A.R. China

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

In this paper, the output synchronization in large-scale discrete-time networks is examined by utilizing the novel phase tool, where the agent dynamics are allowed to be significantly heterogeneous. The synchronization synthesis problem is formulated and thoroughly investigated, with the goal of characterizing the allowable heterogeneity among the agents to ensure synchronization under a uniform controller. The solvability condition is provided in terms of the phases of the residue matrices of the agents at the persistent modes. When the condition is satisfied, a design procedure is given, producing a low-gain synchronizing controller. Numerical examples are given to illustrate the results.

关键词： Sufficient conditions Europe Heterogeneous networks Synchronization Multi-agent systems

Controlling unstable vehicular motions by exploiting linearized feedback law under delay-tolerance: stability, gain-scheduling, and validation

学校读者我要写书评

暂无评论

Research Square

Research Square 2024年

作者： Lu, Hangyu Wu, Xiaodong Zhao, Sheng Yan, Liang Lu, Jianwei Institute of Intelligent Vehicles Shanghai Jiao Tong University China Department of Applied Mechanics Faculty of Mechanical Engineering Budapest University of Technology and Economics Műegyetem rkp. 3. BudapestH-1111 Hungary State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University China School of Automotive and Transportation Engineering Hefei University of Technology China

automation of the transportation system inevitably encounters the difficulty of improving the passenger vehicle’s safety and intelligence. In the halfway of automation, the advanced driver assistance system (ADAS) plays a significant role in bridging that difference. A crucial part of ADAS is the vehicle stability control (VSC) system avoiding motion instability in nonlinear handling maneuvers. In this paper, focusing on the system nonlinearity generated in critical conditions and loop delays in the feedback processes, we present a delay-tolerant feedback structure of VSC that only captures the linearized properties alongside the maneuvers, where the maximal target-tracking performance is designed to be achieved. A nonlinear vehicular model is first established, and the open-loop nonlinear characteristics are investigated through equilibrium analysis and local linearization. Time delays originating from sampling and actuating control loops are generalized into the feedback control torque forming a delayed nonlinear system. A semi-discretized method is conducted that constructs the stability chart of the tunable control gains in the feedback law, where the concatenation of those charts finally offers a conservative delay-tolerant domain. Two methods for gain scheduling w.r.t maximal target-tracking performance are developed to suit for either real-time (RT) or offline applicability, respectively. The proposed methodology for stably tracking the dynamic motion targets in nonlinear conditions is further summarized and then validated within experimental data-based simulations, which indicates that a linearized control law can achieve high-performance VSC with transferability to other control loops with different delays. © 2024, CC BY.

关键词： Advanced driver assistance systems

An Efficient Planning and Control Framework for Quadrotors Based on Heuristic Search and Data-Driven Model Predictive Control

学校读者我要写书评

暂无评论

IEEE Transactions on Industrial Electronics 2025年

作者： Wang, Sifei Wang, Yaonan Miao, Zhiqiang Wang, Xiangke He, Wei Wang, Hesheng Hunan University College of Electrical and Information Engineering Changsha 410082 China National Engineering Research Center for Robot Visual Perception and Control Changsha 410082 China National University of Defense Technology College of Intelligence Science and Technology Changsha 410073 China Beijing Information Science and Technology University School of Automation Institute of Artificial Intelligence Beijing 100083 China University of Science and Technology School of Intelligence Science and Technology Beijing 100083 China Shanghai Jiao Tong University Department of Automation Shanghai 200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai 200240 China Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin 150001 China

This article presents a framework for quadrotors that integrate planning and control, which employs a heuristic depth-first search (HDFS) with data-driven model predictive control (MPC). The proposed framework intends to enable multiquadrotor systems to traverse cluttered environments containing obstacles and disturbances. The heuristic function enables quadrotors to identify a secure route in a timely manner. The heuristic function setup employed by HDFS results in a reduction in the number of rasters accessed, particularly in scenarios that are not labyrinthine. This consequently leads to an enhancement in computational speed for multiquadrotor systems when compared to the A* algorithm. Furthermore, data-driven MPC enhances the nominal model of the quadrotor by modeling the disturbance while tracking the desired states. Consequently, data-driven MPC is capable of attaining superior tracking precision in a disturbance environment when compared to MPC without data-driven. The transformation from the path to the desired states of the quadrotor is achieved through the utilization of B-splines and differential flatness. Simulations and experiments substantiate the efficacy of the proposed approach. © 1982-2012 IEEE.

关键词： Collision avoidance data-driven depth-first search model predictive control multiquadrotor systems

Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lan, Zhengxing Li, Hongbo Liu, Lingshan Fan, Bo Lv, Yisheng Ren, Yilong Cui, Zhiyong The School of Transportation Science and Engineering Beihang University Beijing100191 China The State Key Lab of Intelligent Transportation System Beijing100191 China The Research Institute for Frontier Science Beihang University Beijing100191 China The Beijing Key Laboratory of Traffic Engineering College of Metropolitan Transportation Beijing University of Technology Beijing100124 China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The Zhongguancun Laboratory Beijing100194 China The Beihang Hangzhou Innovation Institute Yuhang Hangzhou310023 China

Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of the complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) without explicit prompt engineering to generate future motion from agents’ past/observed trajectories and scene semantics. Traj-LLM starts with sparse context joint coding to dissect the agent and scene features into a form that LLMs understand. On this basis, we innovatively explore LLMs’ powerful comprehension abilities to capture a spectrum of high-level scene knowledge and interactive information. Emulating the human-like lane focus cognitive function and enhancing Traj-LLM’s scene comprehension, we introduce lane-aware probabilistic learning powered by the pioneering Mamba module. Finally, a multi-modal Laplace decoder is designed to achieve scene-compliant multi-modal predictions. Extensive experiments manifest that Traj-LLM, fortified by LLMs’ strong prior knowledge and understanding prowess, together with lane-aware probability learning, outstrips state-of-the-art methods across evaluation metrics. Moreover, the few-shot analysis further substantiates Traj-LLM’s performance, wherein with just 50% of the dataset, it outperforms the majority of benchmarks relying on complete data utilization. This study explores equipping the trajectory prediction task with advanced capabilities inherent in LLMs, furnishing a more universal and adaptable solution for forecasting agent motion in a new way. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation. © 2022, CC BY.

关键词： Three dimensional computer graphics

An Assembly Sequence Planning Method Using Ant Colony Algorithm for Arbitrary Placed Workpieces

学校读者我要写书评

暂无评论

An Assembly Sequence Planning Method Using Ant Colony Algori...

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Ruiming Hou Sheng Xu Chenguang Yang Bing Zhu Jianghua Duan Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Science Beijing China Shandong Institute of Advanced Technology CAS Shandong China College of Automation Science and Engineering South China University of Technology Guangzhou China Department of Mechanical and Aerospace Engineering Hong Kong University of Science and Technology Hong Kong

This paper proposes a particular and effective online sequence planning method to help manipulators complete complex assembly tasks. In many existing studies, the workpiece is constrained to be placed at a particular initial position. To overcome this drawback, we combine the ant colony algorithm with a target detection algorithm, which could get the positions of the workpieces in real time for online sequence planning. In addition, the constraint and obstacle avoidance of different workpieces in the assembly process is also considered. According to the experiment results, an observation is found that the new method is superior to the general way in terms of efficiency and cost function value. Furthermore, the proposed method effectively solves different practical and feasible assembly sequence planning problems.

关键词：

Multi-Objective Sizing Optimization Method of Microgrid Considering Cost and Carbon Emissions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Xiang Ruan, Guangchun Geng, Hua Liu, Honghai Bai, Mingfei Peng, Chao The Department of Automation Tsinghua University Beijing10084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing10084 China MIT BostonMA02139 United States The State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Electrical & Electronic Engineering North China Electric Power University Beijing102206 China The School of Automation Engineering University of Electronics and Technology of China Chengdu611731 China

Microgrid serves as a promising solution to integrate and manage distributed renewable energy resources. In this paper, we establish a stochastic multi-objective sizing optimization (SMOSO) model for microgrid planning, which fully captures the battery degradation characteristics and the total carbon emissions. The microgrid operator aims to simultaneously maximize the economic benefits and minimize carbon emissions, and the degradation of the battery energy storage system (BESS) is modeled as a nonlinear function of power throughput. A self-adaptive multi-objective genetic algorithm (SAMOGA) is proposed to solve the SMOSO model, and this algorithm is enhanced by pre-grouped hierarchical selection and self-adaptive probabilities of crossover and mutation. Several case studies are conducted to determine the microgrid size by analyzing Pareto frontiers, and the simulation results validate that the proposed method has superior performance over other algorithms on the solution quality of optimum and diversity. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization