A gear motor pair is one of the most popular components of mechanical systems thanks to its efficientpower transmission and adjustable velocity ratios. Vibrations usually could be generated from thetooth contact that propagates to the entire gear motorbox through shafts and bearings. Excessivemanufacturing tolerances or design errors could end up with gear motor faults that generate severe wear andcrack damage on its teeth. These faults on teeth not only generate audible noise but also shorten life ofthe machinery. It is therefore required to suggest a successful way detecting the fault in its early stagein order to prevent the costly system shut down. Since a power train is composed of many gear motor pairs,it is very difficult to sort out damaged gear motor pairs. The misalignment of shafts or unbalanced masscould also be another source of faults as well as damaged gear motor tooth. Even worse, the vibration signalgenerated from the fault pairs can be modulated as it propagates that hampers to locate a certainfaulted tooth during the normal operation. Many studies have been published for the detection of faultgear motor pairs. A two stage adaptive algorithm that could successfully filter out impulsive signals fromnoise and a moving window procedure were suggested . A cracked gear motor was identified by usingan adaptive amplitude and phase modulation. A study applying a time-frequency analysiscombined with wavelet was tried for the purposes. The beta kurtosis and the continuous wavelettransform were used to improve doubling problem in multistage printing presses owing toimperfections in gear motor system. Recently, an autoregressive based linear prediction fault detectiontechnique was proposed to detect localized faults in gear motors .
         This paper suggests an efficient method for the successful identification of a damaged gear motor pair andclassification of the fault types by analyzing vibration signals measured from an experimental set-up.
        Three pairs of geared motors were adopted for the experiment. An adaptive interference canceling was used forthe identification of faults. In addition it is shown that the fault could be well located by the wavelettechnique.

        Geared motor driving experimentSignals tapped from the running geared motored motor are analyzed in this work. Fig. 1(a) showsschematics for the geared motored motor assembly and detailed geared motor pairs in it. The assembly is incorporatingthree geared motor pairs providing 40 to 1 velocity scale. Fig. 1 (b) shows a schematic diagram of theexperimental set-up used in this work. Table 1 shows the theoretical calculations of geared motored motormeshing frequencies used in this work for the rated input 90V at 75rpm. An accelerometer attached onthe top surface of the geared motorbox is used to measure vibration signals and the rotational velocity at theoutput end is measured by a magnetic pick-up that generates a pulse on each revolution. Besides a DCcontroller is used at the DC motor power supply for the variable rotating input speed. A simulatedload also attached as a form of coupled power brake. The measured signal by the accelerometer is fedinto a digital computer through an A/D converter and it is analyzed with MATLAB.
        Diagnosis of geared motor pair faultsFirst vibration patterns of the DC geared motored motor are characterized with various loading conditions.
        Second a tooth of a new geared motor pair is cracked in order to produce an impulsive signal when the toothgets engaged in.
        The adaptive interference canceling is applied for the steady state vibration signals coming from anew and a cracked gear motor pair in order to determine geared motored motor faults. In Fig. 2 (a, b) vibration signalsare measured from new geared motors and cracked one, respectively. Increased level of impulsive signal is ofcourse monitored in Fig. 2(b). In addition, small peaks neighboring to the impulsive signals imply thatmore teeth might be damaged other than the one intentionally cracked. From the visual inspection atooth located twelfth in backward from the initially cracked is found damaged. It corresponds to thecalculated geared motor position by using the information retrieved from Fig. 2(b). Since the time interval forevery tooth is 20ms that is calculated by time for one revolution (75rpm) divided by the number ofteeth (40), the time duration for the twelve teeth is 140ms.