Ride comfort is a key factor in vehicle performance, yet traditional evaluations often rely on subjective methods, leading to inconsistencies. This study presents a deep neural network (DNN)-based model trained on real-world driving data to objectively assess ride comfort. The model’s accuracy is validated using RMS, VDV, and Crest Factor based on ISO 2631. Results show that the DNN effectively captures nonlinear vibration characteristics and offers reliable predictions. This highlights the potential of AI in improving ride comfort assessment.

This study explores structural dynamics using experimental modal analysis with tri-axial accelerometers and advanced signal processing. By improving the accuracy of modal parameters such as natural frequencies and damping ratios, the research enhances vibration analysis techniques. The findings have applications in structural health monitoring, predictive maintenance, and mechanical system optimization.

Vibrations on the floor in a car are transmitted to the foot, hip, and back from the seat. Human body recognizes these vibrations, but the sensitivity for each vibration is different. To evaluate these vibrations, RMS(root mean square) of accelerations, VDV(vibration does value) are commonly used. The ride comfort evaluation is usually carried out by experiments of real cars which are expensive. The purpose of this paper is to briefly review the status of several ride vibration standards and criteria having relevance to construction machinery vehicles and to suggest recommendations for the effective use of such criteria in vehicle / component development.