No abstract

No abstract

No abstract

PurposeTo improve the application neural networks predictors on bearing systems and to investigate the exact neural model of the ball‐bearing system.Design/methodology/approachA feed forward neural network is designed to model‐bearing system. Two results are compared for finding the exact model of the system.FindingsThe results of the proposed neural network predictor gives superior performance for analysing the behaviour of ball bearing undergoing loading deformation.Research limitations/implicationsThe results of the proposed neural network exactly follows desired results of the system. Neural network predictor can be employed in practical applications.Practical implicationsAs theoretical and practical study is evaluated together, it is hoped that ball‐bearing designers and researchers will obtain significant results in this area.Originality/valueThis paper fulfils an identified research results need and offers practical investigation for an academic career and research. Also, It should be very helpful for industrial application of ball‐bearing systems.

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.