Hadi Mehdipour - Department of Mechanical Engineering, Faculty of Shahid Chamran, Kerman Branch, Technical and Vocational University (TVU), Kerman, Iran

Mechanical vibration is defined as the measurement of a periodic process of fluctuations with respect to a balance point. Uncertainty in execution environment imposes the amount of computation error in the estimation of vibration value. Here, we specially have noticed a vibration in rotating machinery and equipment. Use of different approaches for analyzing and solving the engineering problems depends on nature and amount of uncertainty of problems. In this article, we propose a new neuro-fuzzy technique for the composite materials, in order to have a better estimation of actual vibration. To construct a neuro-fuzzy system, we have presented a new approach. In order to evaluate the proposed approach, we perform experiments on a dataset of actual vibration. We have compared the ability and precision of the ANFIS method in estimation. Results show that the ANFIS has a proper precision in the estimation of vibration.

Mechanical vibration, neural network, fuzzy logic