Vibration Fault Detection and Class faction Based on The Fit and Fuzzy Logic

Abstract

Vibration fault exhibit a multifaceted and nonlinear behavior generation in rotated machines, for example in a steam turbine (ST). Vibration fault (VF) is collected in the form of acceleration, velocity, and displacement via the vibration sensor. This fault damages the turbines if it strays into the danger zone. This paper first models the VF in a time domain to transfer the frequency domain via an FFT technique. The signals were applied to the fuzzy system to be used by the VF for classification via Sugeno and Mamdani Fuzzy Inference System (FIS) to generate the signal that will reflect the VF in the event it is embedded into the protection system. The Membership Function (MF) sets depends on practical work in a power plant, and the ISO is interested in ST vibration zones. The outcomes of the Sugeno fuzzy property is the generation of stable and usable signals that can be used within the protection system, mostly owing to its efficiency in detecting vibrational faults. The results from this work can be utilized to prevent VF from generating on ST via increased processing that will feed signals for ST controls.