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

Abstract

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.

Knowledge discovery assistants for crash simulations with graph algorithms and energy absorption features

“…There are two main applications of ML in crash analysis. First, it predicts the crash behavior to replace/support the FE simulation; see [2]. Second, using dimensionality reduction on the vehicle components' data during crash deformation to explore FE simulations, e.g., by identifying clusters [18].…”

“…We investigate filtering methods from SciPy.signal. From lfilt 1 , filtfilt 2 and sosfilt 3 we select the FIR filter (lfilt, sample number n=75, b=1/n a=1), which smoothens the curve without any time shift, Fig. 4a.…”

“…Filter data along one-dimension with an IIR or FIR filter2 A digital filter forward and backward to a signal.…”

Imitating Emergencies: Generating Thermal Surveillance Fall Data Using Low-Cost Human-like Dolls

“…Using mannequins and dummies for gathering testing data has been an important part of the research and development in many fields. In the automotive industry, test dummies are used for gathering data from crashes to make vehicles safer [ 44 , 45 ]. In medicine and the healthcare industry, mannequins are used for simulating emergency situations, such as falls of senior citizens [ 21 ] and medical patients [ 20 , 46 ], through the use of both camera systems and wearable sensors.…”