This paper presents an advanced vibration control method for vehicle suspension systems operating on non-Gaussian random road surfaces. The proposed approach integrates deep learning for precise road surface recognition with fuzzy logic control to dynamically adjust the suspension system’s stiffness and damping parameters. A dynamic model of the suspension system is developed, capturing the non-linear characteristics of the vehicle’s response to external disturbances. The deep learning model, based on Convolutional Neural Networks (CNN), predicts road surface conditions, including slope and curvature, using image data. The fuzzy logic controller then utilizes these predictions to optimize the suspension system in real-time, enhancing ride comfort and vehicle stability. Extensive simulations and real-vehicle tests demonstrate that the proposed method significantly reduces vibrations, improves ride quality, and ensures vehicle safety across diverse road conditions, showcasing its adaptability and robustness in fluctuating environments.
Lara-MolinaFADumurD. Fuzzy-interval approach and sensitivity analysis to assess dimensional tolerances of parallel manipulators. Proc IMechE, Part C: J Mechanical Engineering Science2024; 238: 108–122.
2.
McNeilAParksKLiuX, et al. Artificial intelligence recognition of cutaneous chronic graft-versus-host disease by a deep learning neural network. Br J Haematol2022; 197: e69–e72.
3.
ZhouCZhangYXinH, et al. Complex multiphase predicting of additive manufactured high entropy alloys based on data augmentation deep learning. J Mater Res Technol2024; 28: 2388–2401.
4.
GuoFChengGYangZ, et al. Deep learning algorithm to predict friction coefficient of matching pairs at different temperature domains based on friction sound. Tribol Int2023; 188: 621–630.
5.
GaoXTangYXuH, et al. Vertical load distribution strategy of amphibious wheel-track vehicle using neural network and particle swarm optimization. Proc IMechE, Part D: J Automobile Engineering2024; 238: 563–586.
6.
LiGSunHHeJ, et al. Deep learning, numerical, and experimental methods to reveal hydrodynamics performance and cavitation development in centrifugal pump. Expert Syst Appl2024; 237: 81–90.
7.
KumarGJamesATChoudharyK, et al. Investigation and analysis of implementation challenges for autonomous vehicles in developing countries using hybrid structural modeling. Technol Forecast Soc Change2022; 185: 261–269.
8.
TaghavifarH. Robust AISMC-neural network observer-based control of high-speed autonomous vehicles with unknown dynamics. Proc IMechE, Part D: J Automobile Engineering2023; 237: 3397–3407.
9.
WeiJWenhanDGaochengY, et al. Robust stabilization control of live working robot under wind load based on angular momentum conservation principle. Proc IMechE, Part C: J Mechanical Engineering Science2023; 237: 5205–5217.
10.
WangJHuangZLiJ, et al. Analysis of rigid-flexible coupled torsional vibration and vibration suppression of crankshaft system under multiple working conditions. Proc IMechE, Part K: J Multi-body Dynamics2023; 237: 710–721.
11.
WeiHZhangKZhangH, et al. Resilient and constrained consensus against adversarial attacks: a distributed MPC framework. Automatica2024; 160: 111417.
12.
WeiHZhangHAI-HaddadK, et al. Ensuring secure platooning of constrained intelligent and connected vehicles against byzantine attacks: a distributed MPC framework. Engineering2023; 33: 35–46.
13.
BaltaGHiäsarÇAltinN. Artificial intelligence based switching frequency regulation with fast terminal sliding mode control for DC–DC step-down converters. Expert Syst Appl2023; 228: 120331.
14.
WangJZhangWChenZ, et al. Model predictive control-based active suspension system for improving ride comfort and handling stability. Mechatronics2021; 78: 102563.
15.
LiHLiuYWangJ, et al. Backstepping control of vehicle suspension system under complex road conditions. J Dyn Syst Meas Control2022; 144: 021004.
16.
ZhangYWangJLiX, et al. Road surface displacement estimation based on vehicle dynamics and sensor fusion. J Dyn Syst Meas Control2020; 137: 106564.
17.
KongFZhangWYangZ, et al. Curvature estimation of road surface using vehicle vibration signals. Int J Softw Innov2021; 70: 9631–9640.
18.
KhouloudEAliZ. Linear controller design approach for nonlinear systems by integrating gap metric and stability margin. Proc IMechE, Part I: J Systems and Control Engineering2023; 237: 1800–1811.
19.
DonziaSKYKimHK. A study on autonomous driving simulation using a deep learning process model. Int J Softw Innov2022; 10: 1–11.
20.
PangJL. Adaptive fault prediction and maintenance in production lines using deep learning. Int J Simul Model2023; 22: 734–745.
21.
LiDWangSFangX, et al. Research progress of temperature field calculation of disc brake braking interface based on numerical analysis. Proc IMechE, Part D: J Automobile Engineering2024; 238: 320–333.
22.
ForootanMMLarkiIZahediR, et al. Machine learning and deep learning in energy systems: a review. Sustainability2022; 14: 4832–4832.
23.
VijayarajAVasanth RajPTJebakumarR, et al. Deep learning image classification for fashion design. Wirel Commun Mob Comput2022; 2022: 1–45.
24.
ChenLLiuJZhangW, et al. Road surface condition classification using convolutional neural networks and image processing techniques. Int J Simul Model2021; 33: 8595–8606.
25.
ZhaoXLiYLiZ, et al. A CNN-based approach for real-time road surface condition prediction using vehicle-mounted cameras. J Comput Sci2020; 146: 04020058.
26.
ShinS-YJoGWangG. A novel method for fashion clothing image classification based on deep learning. J Inf Commun Technol2023; 22: 127–148.
27.
PuSZhangFShuY, et al. Microscopic image recognition of diatoms based on deep learning. J Phycol2023; 59: 1166–1178.
28.
BorovykhAOosterleeCWBohtéSM. Generalization in fully-connected neural networks for time series forecasting. J Comput Sci2019; 36: 101020.
29.
BarodiABajitAZemmouriA, et al. Improved deep learning performance for real-time traffic sign detection and recognition applicable to intelligent transportation systems. Int J Adv Comput Sci Appl2022; 13: 100–111.
30.
ZhangHLiJLiW, et al. Comparison of deep learning models for image-based road surface condition prediction. J Comput Sci2021; 173: 114712.
31.
LiXYangXZhouZ, et al. A deep convolutional neural network for road surface prediction: comparison with traditional models. Neurocomputing2020; 398: 175–186.
32.
GillMAndersonRHuH, et al. Machine learning models outperform deep learning models, provide interpretation and facilitate feature selection for soybean trait prediction. BMC Plant Biol2022; 22: 180–180.
33.
OngPJohn KoshyALaiKH, et al. A deep learning approach for health monitoring in rotating machineries using vibrations and thermal features. Decis Anal J2024; 10: 100399–100406.
34.
PatelSRaoSLiY, et al. Comparative analysis of defuzzification techniques in fuzzy control systems. Decis Anal J2023; 25.
35.
YangXZhangLWuK, et al. Optimizing fuzzy logic controllers for renewable energy systems using max-min defuzzification. Renew Energy2024; 174: 14–19.
36.
ReddyASAkashdeepSHarshvardhanR, et al. Stacking deep learning and machine learning models for short-term energy consumption forecasting. Adv Eng Inform2022; 52: 110–121.
37.
YangXHeTShenY, et al. Research on predictive coordinated control of ride comfort and road friendliness for heavy vehicle ISD suspension based on the hybrid-hook damping strategy. Proc IMechE, Part D: J Automobile Engineering2024; 238: 443–456.
38.
YinWXiaHHuangX, et al. A fault diagnosis method for nuclear power plants rotating machinery based on deep learning under imbalanced samples. Ann Nucl Energy2024; 199: 110340–110351.
39.
ChenYZhangDKarimiHR, et al. A new deep learning framework based on blood pressure range constraint for continuous cuffless BP estimation. Neur Netw2022; 152: 181–190.
40.
YunZZhangW. Design and analysis of a vibration suppression system for vehicle suspension under varying road conditions and speeds. Chin J Mech Eng2023; 59(3): 245–256.
41.
LiuYWangHTanH. A study on vibration reduction performance of suspension systems under different road conditions and vehicle speeds. Chin J Mech Eng2023; 15(8): 1294–1305.
42.
WangXLiuHZhangT, et al. A hybrid control method combining fuzzy logic and deep learning for vibration suppression of automotive suspension systems. Veh Syst Dyn2023; 61(5): 837–857.
43.
ZhaoLZhangZGuoY, et al. Adaptive fuzzy logic and deep learning control for active suspension systems under stochastic road excitations. Nonlinear Dyn2022; 110(3): 2337–2357.
44.
ZhangNYangSWuG, et al. Fast distributed model predictive control method for active suspension systems. Sensors2023; 23(6): 3357.
45.
ShiQWangMHeZ, et al. A fuzzy-based sliding mode control approach for acceleration slip regulation of battery electric vehicle. Chin J Mech Eng2022; 35: 215–225.
