Zobrazit v EDS

A deep neural network inverse solution to recover pre-crash impact data of car collisions.

Uloženo v:
Podrobná bibliografie
Název: A deep neural network inverse solution to recover pre-crash impact data of car collisions.
Autoři: Chen, Qijun1 (AUTHOR), Xie, Yuxi1 (AUTHOR), Ao, Yu1,2 (AUTHOR), Li, Tiange1 (AUTHOR), Chen, Guorong1,3 (AUTHOR), Ren, Shaofei1,2 (AUTHOR), Wang, Chao1 (AUTHOR), Li, Shaofan1 (AUTHOR) shaofan@berkeley.edu
Zdroj: Transportation Research Part C: Emerging Technologies. May2021, Vol. 126, pN.PAG-N.PAG. 1p.
Témata: *ARTIFICIAL neural networks, *ARTIFICIAL intelligence, *BIG data, MACHINE learning, AUTONOMOUS vehicles, MATERIAL plasticity, VEHICLE routing problem, TRAFFIC accidents
Abstrakt: • We developed an artificial neural network to predict pre-crash condition of passenger cars in traffic accidents. By using virtual car crash data generated by finite element simulations, we demonstrated the proof of concept of machine-learning method and its feasibility in car crashworthiness inverse solution. • It is shown that by using plastic deformation signature one can practically uniquely determine carcrash inverse solution of pre-crash data with high accuracy and precision. • We developed a large scale parallel machine learning Python code that has mega data capacity, and it can process inelastic deformation in more that 70,000 × 50,000 data points. In this work, we have successfully developed a data-driven artificial intelligence (AI) inverse problem solution for traffic collision reconstruction. In specific, we have developed and implemented a machine learning computational algorithm and built a deep neural network to determine and identify the initial impact conditions of car crash based on its final material damage state and permanently deformed structure configuration (wreckage). In this work, we have demonstrated that the developed machine learning algorithm as an inverse problem solver can accurately identify initial collision conditions in an inverse manner, which are practically unique if we use permanent plastic deformation as the forensic data signatures. In other words, we think that the massive plastic energy dissipation process and the related big data will make final structure damage state insensitive to the initial car collision conditions. Thus, it provides an inverse solution for car crash forensic analysis by reconstructing the initial failure load parameters and conditions based on the permanent plastic deformation distribution of cars. This approach has general significance in solving the inverse problem for engineering failure analysis and vehicle crashworthiness analysis, which provides a key contribution for the unmanned autonomous vehicle and the related technology. [ABSTRACT FROM AUTHOR]
Copyright of Transportation Research Part C: Emerging Technologies is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Business Source Index
Popis
Abstrakt:• We developed an artificial neural network to predict pre-crash condition of passenger cars in traffic accidents. By using virtual car crash data generated by finite element simulations, we demonstrated the proof of concept of machine-learning method and its feasibility in car crashworthiness inverse solution. • It is shown that by using plastic deformation signature one can practically uniquely determine carcrash inverse solution of pre-crash data with high accuracy and precision. • We developed a large scale parallel machine learning Python code that has mega data capacity, and it can process inelastic deformation in more that 70,000 × 50,000 data points. In this work, we have successfully developed a data-driven artificial intelligence (AI) inverse problem solution for traffic collision reconstruction. In specific, we have developed and implemented a machine learning computational algorithm and built a deep neural network to determine and identify the initial impact conditions of car crash based on its final material damage state and permanently deformed structure configuration (wreckage). In this work, we have demonstrated that the developed machine learning algorithm as an inverse problem solver can accurately identify initial collision conditions in an inverse manner, which are practically unique if we use permanent plastic deformation as the forensic data signatures. In other words, we think that the massive plastic energy dissipation process and the related big data will make final structure damage state insensitive to the initial car collision conditions. Thus, it provides an inverse solution for car crash forensic analysis by reconstructing the initial failure load parameters and conditions based on the permanent plastic deformation distribution of cars. This approach has general significance in solving the inverse problem for engineering failure analysis and vehicle crashworthiness analysis, which provides a key contribution for the unmanned autonomous vehicle and the related technology. [ABSTRACT FROM AUTHOR]
ISSN:0968090X
DOI:10.1016/j.trc.2021.103009