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

Gohari, Mohammad; Rahman, Roslan Abdul; Tahmasebi, Mona; Nejat, Peyman

doi:10.1260/0263-0923.33.4.429

Cited by 28 publications

(21 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Introductionmentioning

confidence: 97%

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

Muñoz-Guijosa¹,

Riesco²,

Olmedo³

2017

Int. j. simul. model.

View full text Add to dashboard Cite

Vibration can cause professional illnesses in train drivers, giving also rise to lawsuits to the employer. A possible cause may be the lack of systematic vibration estimation processes, due to operational complexities, subjectivities involved and the cost of dedicated tests. Estimation quality may be improved by using a driver seat model along with cabin floor vibration data acquired during the train dynamic approval tests. However, due to the nonlinearities present, analytical models frequently show inaccurate results. This work deals with the design of an appropriate neural network for predicting the seat-driver interface vibration, based on selected and processed cabin floor acceleration data obtained during the dynamic approval tests. Network type, input signals set and signal conditioning have considerable impact on the simulation accuracy. Results show good correlation between simulated and experimental data, even better between simulated and measured standard vibration dose indicators, being RMS errors between 3.9 % and 9.4 % and peak factor errors between 0.8 % and 9.6 %.

show abstract

Section: Introductionmentioning

confidence: 97%

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

Muñoz-Guijosa¹,

Riesco²,

Olmedo³

2017

Int. j. simul. model.

View full text Add to dashboard Cite

show abstract

“…8,9 Consequently, the design of seat suspension systems can be treated as an optimisation problem. 10,11 The main goal of the multi-criteria optimisation approach is to find the compromising solutions between several conflicted criteria. Such compromising solutions guarantee the best system performance for the opposite objectives.…”

Section: Introductionmentioning

confidence: 99%

Shaping the vibro-isolation properties of horizontal seat suspension

Maciejewski

Krzyżyński

Meyer³

et al. 2017

Journal of Low Frequency Noise, Vibration and Active Control

View full text Add to dashboard Cite

In this paper, an effective procedure of shaping the vibro-isolation properties of seat suspension system is presented. The simulation model is created to determine the dependence of evaluation criteria to the design parameters by means of which the system characteristics are formed. The developed optimisation procedure allows to find Pareto-optimal system configuration for the conflicted vibro-isolating criteria, i.e. the frequency weighted transmissibility factor used to evaluate dynamic seat comfort based on acceleration signals and the suspension travel. In order to optimise both the conflicted vibro-isolation criteria, a minimising of the transmissibility factor (primary criterion) is proposed taking into account the suspension travel that is transferred to a non-linear inequality constraint. The correctness of proposed procedure is evaluated using experimental research of the best solution of horizontal seat suspension. This research is performed using the passive system with optimal visco-elastic characteristics, which are selected especially for the welldefined input vibration. The satisfactory agreement of experimental and numerical results is obtained for the analysed vibration reduction system.

show abstract

“…Many investigations used FE models, lumped parameters or multibody models, and artificial neural network models to study biodynamic characteristics of the human spine. Kitazaki and Griffin proposed a FE model of the entire human spine to perform a modal analysis.…”

Section: Introductionmentioning

confidence: 99%

“…Gohari et al constructed a new biodynamic model with artificial neural network method. The developed model was able to predict head acceleration from exciting vibration at the pelvic, and the accuracy of model was 96% …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human body modeling method to simulate the biodynamic characteristics of spine in vivo with different sitting postures

Dong

Guo

2017

Numer Methods Biomed Eng

View full text Add to dashboard Cite

The aim of this study is to model the computational model of seated whole human body including skeleton, muscle, viscera, ligament, intervertebral disc, and skin to predict effect of the factors (sitting postures, muscle and skin, buttocks, viscera, arms, gravity, and boundary conditions) on the biodynamic characteristics of spine. Two finite element models of seated whole body and a large number of finite element models of different ligamentous motion segments were developed and validated. Static, modal, and transient dynamic analyses were performed. The predicted vertical resonant frequency of seated body model was in the range of vertical natural frequency of 4 to 7 Hz. Muscle, buttocks, viscera, and the boundary conditions of buttocks have influence on the vertical resonant frequency of spine. Muscle played a very important role in biodynamic response of spine. Compared with the vertical posture, the posture of lean forward or backward led to an increase in stress on anterior or lateral posterior of lumbar intervertebral discs. This indicated that keeping correct posture could reduce the injury of vibration on lumbar intervertebral disc under whole-body vibration. The driving posture not only reduced the load of spine but also increased the resonant frequency of spine.

show abstract

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

Cited by 28 publications

References 28 publications

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

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

Shaping the vibro-isolation properties of horizontal seat suspension

Human body modeling method to simulate the biodynamic characteristics of spine in vivo with different sitting postures

Contact Info

Product

Resources

About