Fault Diagnosis For Exhaust Fan Using Experimental Predictive Maintenance Method

Abstract

Unexpected machine failures cause a decrease in production and increase in cost so that predictive maintenance methods have everyday importance. The main principle of predictive maintenance methods is to decide maintenance time of machines by monitoring machine performance during operations and resolving the failure when the machines stop.In this study, failures of the exhaust fan system used in Afsin-Elbistan B Thermal Power Plant were monitored by using predictive maintenance methods that rely on vibration analysis. The failures were periodically measured from four points on the bearings of fans and motors with a vibration analyzer. Identified failures on the system have been respectively removed with analysis of measurements. After all failures have been removed, it has been noted that vibration values decreased when measured again from the aforementioned four point. With using the predictive maintenance method, failures can be identified before the failures cause negative results whereby both unnecessary machine stops can be prevented and the cost of operation can be decreased.

Intelligent Vibration Analysis of Industrial Cooling Fans

“…While the purpose of this paper is to compare vibration analysis techniques of industrial fans, experiments for this comparative study had to be done using a regular table fan. It is important to remember that when a cooling fan suffers from a defect, its vibration will change [1]. With the intent to experiment, we manually changed the fan speed to simulate the failure conditions.…”

“…Thus, industrial cooling fans are required to operate at optimum levels to maintain proper temperatures for industrial machines. However, fans can be victims of sudden failures [1]. Should a cooling system failure occur, it may result in machine instability or downtime, as well as a reduction of manufacturing yield.…”

“…Therefore, this paper presents a novel comparative study on vibration analysis of industrial cooling fans to identify faults. The study compares the performance of three vibration analysis techniques: (1) image encoding and convolutional neural network (CNN), (2) moving average and (3) fuzzy logic.…”

Predictive Maintenance Neural Control Algorithm for Defect Detection of the Power Plants Rotating Machines Using Augmented Reality Goggles

“…Many other examples of predictive maintenance are based on the direct measurement of vibrations using electrical sensors. The authors of [21] conducted a measurement of thermal power plant fans using vibration analysis. Measurements were conducted from four different points of the examined bearing that proved to be faulty after the previous examination.…”