# DB-MLP: A Lightweight Dual-Branch MLP for Road Roughness Classification Using Vehicle Sprung Mass Acceleration

## TL;DR

This paper introduces DB-MLP, a lightweight neural network for classifying road roughness using vehicle acceleration data, achieving high accuracy with low computational cost.

## Contribution

The novel DB-MLP architecture efficiently captures multi-scale dependencies with dual-domain feature transformation for real-time road roughness classification.

## Key findings

- DB-MLP achieves 98.5% accuracy with only 0.58 million parameters.
- The model reduces inference latency by 20 times compared to leading baselines.
- A co-simulation platform generates realistic vibration data for training and testing.

## Abstract

Accurate identification of road roughness is pivotal for optimizing vehicle suspension control and enhancing passenger comfort. However, existing data-driven methods often struggle to balance classification accuracy with the strict computational constraints of real-time onboard monitoring. To address this challenge, this paper proposes a lightweight and robust road roughness classification framework utilizing a single sprung mass accelerometer. First, to overcome the scarcity of labeled real-world data and the limitations of linear models, a high-fidelity co-simulation platform combining CarSim and Simulink is established. This platform generates physically consistent vibration datasets covering ISO A–F roughness levels, effectively capturing nonlinear suspension dynamics. Second, we introduce DB-MLP, a novel Dual-Branch Multi-Layer Perceptron architecture. In contrast to computationally intensive Transformer or RNN-based models, DB-MLP employs a dual-branch strategy with multi-resolution temporal projection to efficiently capture multi-scale dependencies, and integrates dual-domain (time and position-wise) feature transformation blocks for robust feature extraction. Experimental results demonstrate that DB-MLP achieves a superior accuracy of 98.5% with only 0.58 million parameters. Compared to leading baselines such as TimeMixer and InceptionTime, our model reduces inference latency by approximately 20 times (0.007 ms/sample) while maintaining competitive performance on the specific road classification task. This study provides a cost-effective, high-precision solution suitable for real-time deployment on embedded vehicle systems.