Robust Force Estimation for Magnetorheological Damper Based on Complex Value Convolutional Neural Network

Abstract

Recent developments in semiactive control technologies enhance the possibility of an effective response reduction during a wide range of dynamic loading conditions. Most semiactive control schemes employ magnetorheological dampers (MRDs) as actuators. These devices exhibit nonlinear and hysterical behavior that complicates reactive force estimation to compensate for disturbances. In this paper, we present a novel robust schema to estimate MRD forces using a complex value convolutional neural network (CVCNN) to overcome these problems. CVCNN utilizes random complex value convolutional filters as parameters to reduce the measured noise by combining the training stage and the maxbymagnitude operation. Furthermore, CVCNN is a hysteresismodelfree strategy that overcomes the parameterization in nonlinear systems. The proposed CVCNN only requires displacement and voltage measurements for force estimation. Different metrics are used to compare results between the CVCNN, genetic algorithm (GA), particle swarm optimization (PSO), and shallow neural network (SNN). Experimental results show the potential of the proposed CV CNN for practical applications due to its simplicity and robustness. The CVCNN computational time is less than that of GA and PSO. In the training stage, the CVCNN uses 0.7% of GA's time and 1.4% of PSO. Although SNN uses 5.5% of the time consumed by the CVCNN, the latter performs the force estimation for MRD better; its mean square error is 78.3% lower than the GA's and PSO's, and 71.4% lower than SNN's.