Neuro-fuzzy Hysteresis Modeling of Magnetorheological Dampers

This paper presents the neuro-fuzzy modeling approach to analyze the test results of MR damper. Every Electric current in provides to MR Fluid will have a different output. On the other hand, the meandering type valve has a different output and calculation. Therefore, the prototype of MR Damper that has been made was taken to a laboratory to test using Dynamic Testing Machine. The data test result will be analyzed using Neuro-Fuzzy. This paper aims to find a correlation between every variable is there in the testing of MR Damper. For the hysteresis modeling purpose, some parts of the data are taken as the training data source for the optimization parameters in the Neuro-Fuzzy model. The performance of the trained Neuro-Fuzzy model is assessed by validating the model output with the remaining measurement data and benchmarking. The assigned membership function results in a minimum error of 0.16 from 3000 epoch from 3 sets of data given as training data. © 2020, Springer Nature Singapore Pte Ltd.