A Novel Artificial Neural Network Biodynamic Model for Prediction Seated Human Body Head Acceleration in Vertical Direction

Abstract

Nowadays, usage of vehicles increases due to modern lifestyles, and many people are exposed to vibrations in vehicles. Vibrations in low frequency range cause some serious long-term diseases in both aspects physically and psychologically. Vibration model helps researchers to have better interpretation of vibrations transmitting to human organs. Lumped models are very popular in this field, and different types of models with various degrees of freedom have been introduced. The main disadvantage of lumped models is that due to its fixed weight, some modifications need to be made to new subjects. Therefore, a new biodynamic model with artificial neural network method was constructed to simulate transmitted vibration to head for seated human body by conducting indoor vertical vibration experiments. Five healthy males participated in the tests. They were subjected to vertical vibration, and their responses were recorded. A neural network model was trained by input-output accelerations. The developed model was able to predict head acceleration from exciting vibration at the pelvic. In addition, weight and height of human body were considered as input factors. The comparison between the model evaluation results and the experimental and other lumped models affirmed high accuracy of the achieved artificial neural network biodynamic model.

Investigation and Application on the Vertical Vibration Models of the Seated Human Body

“…3. This model is different from the four-DOF models proposed by other scholars [6,7]. The derived mathematical expressions of the AM, DPM and STH in the four-DOF model are as follows: Fig.…”

“…Therefore, the vertical vibration characteristics of the seated human body are studied, and a dynamic model of human-vehicle-road system has been established to contribute to the development of vehicle ride comfort. Seated human body models mainly include the centralized mass parameter model [3], the finite element model [4,5], the multi-body dynamics model [6] and the neural network model [7]. As the centralized mass parameter model is simple and practical, it has been studied often.…”

Off-Road Vehicle Seat Suspension Optimisation, Part I: Derivation of an Artificial Neural Network Model to Predict Seated Human Spine Acceleration in Vertical Vibration

“…Although the proposed ANN model has acceptable accuracy, the human height and body weight are not adjustable in the model, and they were assumed fixed. Gohari et al [26] employed this technique to simulate head dynamical behaviour from three inputs; excitation signal, height and weight of body. Also, another ANN model for prediction of head acceleration from seat and hand vibration was represented [27].…”

Neural Network and Training Strategy Design for Train Drivers’ Vibration Dose Simulation

“…Thus, this paper explores the possibility of using ANN for the prediction of the vibration received in the driver's seat. Few works have been found regarding the use of ANN for this application [17][18][19][20][21][22][23] so we believe that the methodology presented and the results obtained in this work can be useful for the assessment of the vibrational environment at driver's place.…”