To evaluate and improve the real-time performance of Ethernet for plant automation（EPA） industrial Ethernet,the real-time performance of EPA periodic data transmission was theoretically and experimentally studied.By...To evaluate and improve the real-time performance of Ethernet for plant automation（EPA） industrial Ethernet,the real-time performance of EPA periodic data transmission was theoretically and experimentally studied.By analyzing information transmission regularity and EPA deterministic scheduling mechanism,periodic messages were categorized as different modes according to their entering-queue time.The scheduling characteristics and delivery time of each mode and their interacting relations were studied,during which the models of real-time performance of periodic information transmission in EPA system were established.On this basis,an experimental platform is developed to test the delivery time of periodic messages transmission in EPA system.According to the analysis and the experiment,the main factors that limit the real-time performance of EPA periodic data transmission and the improvement methods were proposed.展开更多
In the process of railway construction, because of the inconvenience ofgeological condition, water bursting and mud surging happen frequently, and the laterdeformation of support structure on the happening geology sec...In the process of railway construction, because of the inconvenience ofgeological condition, water bursting and mud surging happen frequently, and the laterdeformation of support structure on the happening geology section would threaten thenormal running of railway. The limit difference of deformation control value of thesupport structure section where geological accidents frequently happen, is small, andartificial half-automatic supervisory technology cannot get the health condition of tunnelin time, resulting many cars speed-down accidents due to deformation of supportstructure. Through design innovation, we introduce TGMIS in the later period ofYanzishan railway construction to quickly capture the deformation of support structure,the strain of lining concrete, the strain of steel frame, stress of surrounding soil, stress ofsurrounding water, strain of second lining steel bar and other situ data. Also we setobservation prism and measuring robot device in specific position inside tunnel, androbot laser locator laser spot is projected onto reflection target surface, by graphicprocessing algorithm, the receiver calculates the measured value and standard value ofthe 3D coordinates of the laser spot. Then the information is transmitted throughtransmitting device, transducer and USB-485 to computer to predict and evaluate thehealth condition of the support structure of the tunnel so as to provide safety warninginformation. Provide timely and reliable data for the operation company to avoid theoccurrence of vicious accidents.展开更多
Modern approach to artificial intelligence(Al)aims to design algorithms that learn directly from data.This approach has achieved impressive results and has contributed significantly to the progress of Al,particularly ...Modern approach to artificial intelligence(Al)aims to design algorithms that learn directly from data.This approach has achieved impressive results and has contributed significantly to the progress of Al,particularly in the sphere of supervised deep learning.It has also simplified the design of machine learning systems as the learning process is highly automated.However,not all data processing tasks in conventional deep learning pipelines have been automated.In most cases data has to be manually collected,preprocessed and further extended through data augmentation before they can be effective for training.Recently,special techniques for automating these tasks have emerged.The automation of data processing tasks is driven by the need to utilize large volumes of complex,heterogeneous data for machine learning and big data applications.Today,end-to-end automated data processing systems based on automated machine learning(AutoML)techniques are capable of taking raw data and transforming them into useful features for big data tasks by automating all intermediate processing stages.In this work,we present a thorough review of approaches for automating data processing tasks in deep learning pipelines,including auto-mated data preprocessing-e.g.,data cleaning,labeling,missing data imputation,and categorical data encoding-as well as data augmentation(including synthetic data generation using gener-ative Al methods)and feature engineering-specifically,automated feature extraction,feature construction and feature selection.In addition to automating specific data processing tasks,we discuss the use of AutoML methods and tools to simultaneously optimize all stages of the machine.展开更多
Origin-destination(OD)modeling facilitates effective demand-responsive public transportation planning in order to meet emergent needs.Given recent advances in transit information and personal communications technology...Origin-destination(OD)modeling facilitates effective demand-responsive public transportation planning in order to meet emergent needs.Given recent advances in transit information and personal communications technology,transit OD estimation methods have evolved from relying on limited survey sources to automated big data sources.Innovative modeling approaches have also been developed over several decades to estimate trip ODs,not only for single routes,but also for full networks,including transfers.In this paper,we synthesize a review of the state of the art in research and practice,along with descriptions of key data types and methodological approaches,indicating how they interact.We also discuss current research gaps and opportunities for further innovation.This review provides a comprehensive resource that should facilitate the application of these methods to various transit systems,thus enabling planners and policymakers to gain insights from new and improved model estimates in various transit systems.展开更多
基金Supported by the National High Technology Research and Development Program of China (2006AA040301-4,2007AA041301-6)
文摘To evaluate and improve the real-time performance of Ethernet for plant automation（EPA） industrial Ethernet,the real-time performance of EPA periodic data transmission was theoretically and experimentally studied.By analyzing information transmission regularity and EPA deterministic scheduling mechanism,periodic messages were categorized as different modes according to their entering-queue time.The scheduling characteristics and delivery time of each mode and their interacting relations were studied,during which the models of real-time performance of periodic information transmission in EPA system were established.On this basis,an experimental platform is developed to test the delivery time of periodic messages transmission in EPA system.According to the analysis and the experiment,the main factors that limit the real-time performance of EPA periodic data transmission and the improvement methods were proposed.
文摘In the process of railway construction, because of the inconvenience ofgeological condition, water bursting and mud surging happen frequently, and the laterdeformation of support structure on the happening geology section would threaten thenormal running of railway. The limit difference of deformation control value of thesupport structure section where geological accidents frequently happen, is small, andartificial half-automatic supervisory technology cannot get the health condition of tunnelin time, resulting many cars speed-down accidents due to deformation of supportstructure. Through design innovation, we introduce TGMIS in the later period ofYanzishan railway construction to quickly capture the deformation of support structure,the strain of lining concrete, the strain of steel frame, stress of surrounding soil, stress ofsurrounding water, strain of second lining steel bar and other situ data. Also we setobservation prism and measuring robot device in specific position inside tunnel, androbot laser locator laser spot is projected onto reflection target surface, by graphicprocessing algorithm, the receiver calculates the measured value and standard value ofthe 3D coordinates of the laser spot. Then the information is transmitted throughtransmitting device, transducer and USB-485 to computer to predict and evaluate thehealth condition of the support structure of the tunnel so as to provide safety warninginformation. Provide timely and reliable data for the operation company to avoid theoccurrence of vicious accidents.
文摘Modern approach to artificial intelligence(Al)aims to design algorithms that learn directly from data.This approach has achieved impressive results and has contributed significantly to the progress of Al,particularly in the sphere of supervised deep learning.It has also simplified the design of machine learning systems as the learning process is highly automated.However,not all data processing tasks in conventional deep learning pipelines have been automated.In most cases data has to be manually collected,preprocessed and further extended through data augmentation before they can be effective for training.Recently,special techniques for automating these tasks have emerged.The automation of data processing tasks is driven by the need to utilize large volumes of complex,heterogeneous data for machine learning and big data applications.Today,end-to-end automated data processing systems based on automated machine learning(AutoML)techniques are capable of taking raw data and transforming them into useful features for big data tasks by automating all intermediate processing stages.In this work,we present a thorough review of approaches for automating data processing tasks in deep learning pipelines,including auto-mated data preprocessing-e.g.,data cleaning,labeling,missing data imputation,and categorical data encoding-as well as data augmentation(including synthetic data generation using gener-ative Al methods)and feature engineering-specifically,automated feature extraction,feature construction and feature selection.In addition to automating specific data processing tasks,we discuss the use of AutoML methods and tools to simultaneously optimize all stages of the machine.
文摘Origin-destination(OD)modeling facilitates effective demand-responsive public transportation planning in order to meet emergent needs.Given recent advances in transit information and personal communications technology,transit OD estimation methods have evolved from relying on limited survey sources to automated big data sources.Innovative modeling approaches have also been developed over several decades to estimate trip ODs,not only for single routes,but also for full networks,including transfers.In this paper,we synthesize a review of the state of the art in research and practice,along with descriptions of key data types and methodological approaches,indicating how they interact.We also discuss current research gaps and opportunities for further innovation.This review provides a comprehensive resource that should facilitate the application of these methods to various transit systems,thus enabling planners and policymakers to gain insights from new and improved model estimates in various transit systems.
