Feasibility of a Neural Network-Based Virtual Sensor for Vehicle Unsprung Mass Relative Velocity Estimation

Abstract

With the automotive industry moving towards automated driving, sensing is increasingly important in enabling technology. The virtual sensors allow data fusion from various vehicle sensors and provide a prediction for measurement that is hard or too expensive to measure in another way or in the case of demand on continuous detection. In this paper, virtual sensing is discussed for the case of vehicle suspension control, where information about the relative velocity of the unsprung mass for each vehicle corner is required. The corresponding goal can be identified as a regression task with multi-input sequence input. The hypothesis is that the state-of-art method of Bidirectional Long–Short Term Memory (BiLSTM) can solve it. In this paper, a virtual sensor has been proposed and developed by training a neural network model. The simulations have been performed using an experimentally validated full vehicle model in IPG Carmaker. Simulations provided the reference data which were used for Neural Network (NN) training. The extensive dataset covering 26 scenarios has been used to obtain training, validation and testing data. The Bayesian Search was used to select the best neural network structure using root mean square error as a metric. The best network is made of 167 BiLSTM, 256 fully connected hidden units and 4 output units. Error histograms and spectral analysis of the predicted signal compared to the reference signal are presented. The results demonstrate the good applicability of neural network-based virtual sensors to estimate vehicle unsprung mass relative velocity.

Virtual Commissioning of Distributed Systems in the Industrial Internet of Things

“…A second use case is the development and testing of virtual sensors by means of simulation. Different methods for virtual sensors, among others neural networks, are used [ 85 , 86 ]. Thus, if virtual sensors are identified, training of the algorithms is required.…”

Vehicle State Estimation Combining Physics-Informed Neural Network and Unscented Kalman Filtering on Manifolds

“…However, due to the IMU drift, the integration error of this model was relatively . The "Dynamics represented the longitudinal/lateral dynamics model based on tions (15) and (17), which is commonly used for vehicle control. In this paper, "Lineonstrained least square and "Dynamics were established based on the IMU measent data.…”

Intelligent Agent-based Metaheuristic for Predicting Vibration Response of a Catamaran Digital Twin

“…Artificial intelligence (AI) techniques have been studied exhaustively due to its online applications. Machine learning, deep learning and reinforcement learning models are widely used for modelling social dynamics [18], autonomous car driver [19], structural monitoring [20,21] and others. Concerning structural monitoring application, some reviews of the use of artificial intelligence are presented in [22,23,20].…”