An unexpected failure of the gear pump may cause significant effect on its
performance and structure, consequently there will be economic losses. For this
reason, fault diagnosis in meshed gears has been the subject of serious research.
Vibration analysis is one of the pumps on condition monitoring techniques that
determines a suitable maintenance action. Generally, an increased vibration level
can be considered as a warning form before failure or breakdown. By measuring,
processing, and analyzing the frequencies of vibration signal, it is possible to
determine both the type and severity of the defect, and hence predict the machine's
failure. The vibration signal of a gear pump contains the signature of the defects in
the gears, and early fault detection of the gear pump is possible by analyzing the
vibration signal using different signal processing techniques (Frequency Spectrum,
Envelop and Power Spectrum Density). This research experimentally, shows the
external gear pump signature for normal and faulty gear at different rotational
speeds (1080, 1200 and 1439 RPM). The considered faults herein are one missing
tooth and two missing teeth in a single gear of the pump. The Faulty gear signature
due to missing one tooth and two missing teeth and at different rotational speeds
are identified. The amplitude of vibration increases by increasing the rotational
speed. When the two missing teeth are facing each other results in decreasing the
vibration amplitude than one missing teeth size.