CrashNet: an encoder–decoder architecture to predict crash test outcomes

Destructive car crash tests are an elaborate, time-consuming, and expensive necessity of the automotive development process. Today, finite element method (FEM) simulations are used to reduce costs by simulating car crashes computationally. We propose CrashNet, an encoder–decoder deep neural network...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Data mining and knowledge discovery Ročník 35; číslo 4; s. 1688 - 1709
Hlavní autori:	Belaid, Mohamed Karim, Rabus, Maximilian, Krestel, Ralf
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York Springer US 01.07.2021 Springer Nature B.V
Predmet:	Artificial Intelligence Artificial neural networks Chemistry and Earth Sciences Coders Computer Science Computer simulation Cost reduction Crashworthiness Data Mining and Knowledge Discovery Destructive testing Finite element method Information Storage and Retrieval Machine learning Mathematical models Neural networks Physics Safety management Scalars Special Issue of the Journal Track of ECML PKDD 2021 Statistics for Engineering Time series Traffic accidents Traffic accidents & safety Predictive models Car safety management Time series analysis Supervised deep neural networks
ISSN:	1384-5810, 1573-756X
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Destructive car crash tests are an elaborate, time-consuming, and expensive necessity of the automotive development process. Today, finite element method (FEM) simulations are used to reduce costs by simulating car crashes computationally. We propose CrashNet, an encoder–decoder deep neural network architecture that reduces costs further and models specific outcomes of car crashes very accurately. We achieve this by formulating car crash events as time series prediction enriched with a set of scalar features. Traditional sequence-to-sequence models are usually composed of convolutional neural network (CNN) and CNN transpose layers. We propose to concatenate those with an MLP capable of learning how to inject the given scalars into the output time series. In addition, we replace the CNN transpose with 2D CNN transpose layers in order to force the model to process the hidden state of the set of scalars as one time series. The proposed CrashNet model can be trained efficiently and is able to process scalars and time series as input in order to infer the results of crash tests. CrashNet produces results faster and at a lower cost compared to destructive tests and FEM simulations. Moreover, it represents a novel approach in the car safety management domain.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	1384-5810 1573-756X
DOI:	10.1007/s10618-021-00761-9