Control of an active suspension system based on long short-term memory (LSTM) learning

Dridi, Issam; Hamza, Asma; Yahia, Noureddine Ben

doi:10.1177/16878132231156789

Cited by 9 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The superior performance of the reinforcement learning controller significantly outperforms that of 63 ANN and AFFOPID, attributed to the constant improvement in RMS values (from 0:342 for ANN to 0:180 for RL), leading to a considerable reduction in vibrations experienced by the driver. Additionally, our controller has the advantage of achieving these comfort results without integrating the driver seat suspension.…”

Section: Reward Function Rmsmentioning

confidence: 99%

A new approach to controlling an active suspension system based on reinforcement learning

Dridi

Hamza

Yahia

2023

Advances in Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

Active suspension provides better vehicle control and safety on the road with optimal driving comfort compared to passive suspension. Achieving this requires a good control system that can adapt to any environment. This article uses a deep reinforcement learning method to develop an optimal neural network that meets the comfort requirements according to ISO 2631-5 standards. The algorithm trains the agent without any prior knowledge of the environment. Various simulations were performed, and the results were validated with the literature and the standard until the appropriate reward function was found. Simple and consistent road profiles were used while maintaining constant system parameters during training. The results show that suspension based on deep reinforcement learning reduces vehicle body acceleration and improves ride comfort without sacrificing suspension deflection and dynamic tire loading. The controller expects the RMS value of the acceleration to be 0.228 with a minimum overrun of the suspended mass.

show abstract

Section: Reward Function Rmsmentioning

confidence: 99%

A new approach to controlling an active suspension system based on reinforcement learning

Dridi

Hamza

Yahia

2023

Advances in Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…The neural networks [15] by adding feedback connections between output and input layers can effectively applied as a part of vehicle system model to accurately predict road excitations and tire dynamics behavior. The Recurrent Neural Network and Long short-term memory neural network [16] were employed the to ensure the stability of vehicles suspension under all external or internal conditions.…”

mentioning

confidence: 99%

Variable Universe Fuzzy PID Control for Active Suspension System With Combination of Chaotic Particle Swarm Optimization and Road Recognition

Yu,

Zhu,

2024

IEEE Access

View full text Add to dashboard Cite

The traditional active suspension system controlled by fuzzy PID fails to consider external road information adaptively, lending to low control precision. To solve this problem, this novel variable universe fuzzy PID control strategy, which combines road recognition and chaotic particle swarm optimization (CPSO), is proposed. Firstly, a dynamic model of four degree of freedom vehicle suspension is established based on the half-vehicle model. Secondly, the Back Propagation (BP) neural network is optimized by Tent Sparrow Search Algorithm (Tent-SSA) to construct a road recognition model. When the road recognition module is constructed, the suspension control system can convert the suspension vibration signal into road information, and dynamically adjust the scaling factors of the variable universe fuzzy controller based on the road information. Thirdly, a modified coefficient is added to adjust the parameters obtained from the road recognition model, and the CPSO algorithm is used to optimize it to enhance control precision. Passive suspension, FPID control, and this novel control are constructed and simulated in MATLAB. The results indicate that this novel control strategy has improved in comprehensive performance by 28.47% compared to fuzzy PID control strategies.

show abstract

“…Zeng et al [81] achieved a 38.6% optimization of AVB 2 (k). Dridi et al [82] achieved a 50% optimization in AVB 2 (k) using intelligent neural network control. the impact of fractional-order PID control on improving suspension performance indicators is verified through comparative analysis with passive suspension and integer-order PID control active suspension.…”

mentioning

confidence: 99%

Fractional-Order PIλDμ Control to Enhance the Driving Smoothness of Active Vehicle Suspension in Electric Vehicles

Yin,

Wang,

et al. 2024

WEVJ

View full text Add to dashboard Cite

The suspension system is a crucial part of an electric vehicle, which directly affects its handling performance, driving comfort, and driving safety. The dynamics of the 8-DoF full-vehicle suspension with seat active control are established based on rigid-body dynamics, and the time-domain stochastic excitation model of four tires is constructed by the filtered white noise method. The suspension dynamics model and road surface model are constructed on the Matlab/Simulink simulation software platform, and the simulation study of the dynamic characteristics of active suspension based on the fractional-order PIλDµ control strategy is carried out. The three performance indicators of acceleration, suspension dynamic deflection, and tire dynamic displacement are selected to construct the fitness function of the genetic algorithm, and the structural parameters of the fractional-order PIlDm controller are optimized using the genetic algorithm. The control effect of the optimized fractional-order PIlDm controller based on the genetic algorithm is analyzed by comparing the integer-order PID control suspension and passive suspension. The simulation results show that for optimized fractional-order PID control suspension, compared with passive suspension, the average optimization of the root mean square (RMS) of acceleration under random road conditions reaches over 25%, the average optimization of suspension dynamic deflection exceeds 30%, and the average optimization of tire dynamic displacement is 5%. However, compared to the integer-order PID control suspension, the average optimization of the root mean square (RMS) of acceleration under random road conditions decreased by 5%, the average optimization of suspension dynamic deflection increased by 3%, and the average optimization of tire dynamic displacement increased by 2%.

show abstract

Control of an active suspension system based on long short-term memory (LSTM) learning

Cited by 9 publications

References 36 publications

A new approach to controlling an active suspension system based on reinforcement learning

A new approach to controlling an active suspension system based on reinforcement learning

Variable Universe Fuzzy PID Control for Active Suspension System With Combination of Chaotic Particle Swarm Optimization and Road Recognition

Fractional-Order PIλDμ Control to Enhance the Driving Smoothness of Active Vehicle Suspension in Electric Vehicles

Contact Info

Product

Resources

About