This study aims to identify the outer race bearing needed to protect an induction motor from severe damage. Faults are diagnosed using a non-invasive technique through the sound signal from an induction motor. The diagnosis aims to assess the damage to the bearings on the fan or main shaft. Moreover, this study discusses the type of damage, loading variations, and the diagnostic accuracy with the damage to the outer race bearing placed on the fan or main shaft rotor. The disturbance detection approach is used to analyze the sound spectrum to identify the harmonic components near the disturbance frequency. The damage frequency characteristics are also calculated to determine the sound spectrum peak value. The results show that the detection is slightly affected by the damage severity and the incorrect placement of the bearings on the rotor shaft. The lowest detection accuracy in testing the outer race bearing damage on the fan shaft is 91.66%. However, the accuracy percentage is 100% with the outer race bearing damage on the main shaft.

The induction motor is a type of electric machine that is widely used for industrial operations in this modern era. It is an alternating current electric machine with several advantages, namely cheap, simple construction, and not requiring excessive maintenance, but has the biggest percentage of motor fault in the bearings. Therefore, this study aims to identify the inner race-bearing fault detection system based on sound signal frequency analysis. The sound signal processing was carried out using the Fast Fourier Transform (FFT) algorithm to analyze the condition of the inner race-bearing. The sound signal was used because it does not require direct contact with the bearing (non-invasive). The fault detection system was tested with two defects, namely scratched inner race and perforated inner race bearing. The results gave a successful detection of the condition of the inner race bearing with a percentage of 81.24%. This showed that the fault detection system using sound signals with FFT signal processing was carried out with high accuracy.

Bearing is an induction motor component that helps the rotor to move freely, in industrial applications it is important to maintain bearing performance in induction motors. In its use, bearing damage is one of the biggest types of damage that is often found in induction motors. Bearing damage can lead to increased vibration, increased noise, increased working temperature, and decreased efficiency. Efficiency reduction can be used as information on the condition of the motor so that this information can be used to detect damage before more serious damage occurs. This research discusses the stator current analysis method and the efficiency of damage to the motor through two harmonic amplitude ratios equipped with the fast Fourier transform (FFT) algorithm in detecting damage to the outer race bearing. It is hoped that this efficiency can be used as an evaluation of the extent to which motor energy waste occurs before more severe damage. The efficiency results on the damage to the outer race bearing using the FFT method get the highest efficiency value of 1.47 and the lowest value of 0.66.

Almost all industries use induction motors as production aids, this is due to several reasons, namely, the resulting rotational speed is constant, the induction motor does not have a brush so that the friction loss can be reduced, and easy maintenance. In this study is to detect damage to the stator winding caused by lamination of the windings so that a short circuit occurs in one phase, which is also called a turn fault. The Fast Fourier Transform (FFT) method is used to detect currents with a load of 0%, and 100% which will later be detected for classification on the Neural Network (NN). Categorizing the level of loading and the level of damage experienced by induction motors, namely turn to turn u1, turn to turn u1 and v1, and turn to turn u1, v1 and w1. The reading of the test results conducted on the Neural Network has good prediction results because the Mean Squared Error (MSE) produced does not exceed the specified 5% erracy level.

In applications in the industrial world, the use of induction motors has been widely used in operation because induction motors have many advantages, although they have many advantages, induction motors themselves also have disadvantages, namely having high starting currents. In many cases the damage to the induction motor, the damage to the stator due to a short circuit, is a frequent failure, this damage can cause considerable losses because the motor can stop operation So this research will discuss about the detection of short circuit faults in the stator winding through leaky flux using a flux sensor that is placed outside the motor and placed radially and using the Fast Fourier Transform (FFT) method. Damage to the short circuit is done by reconstructing the stator winding of the induction motor. There are two variations of short circuit damage, namely short circuit winding 1 to winding 3 and short circuit winding 2 to winding 10 on an induction motor. The short circuit data is then processed using the Fast Fourier Transform method which produces data in the form of voltage to frequency. The results of the percentage of success of short circuit fault detection seen from the loaders have an average percentage of 50%, at no load conditions can detect short circuit faults by 100%. In conditions of short circuit interruption 1-3 has a success percentage of 30% and short circuit fault 2-10 by 70%. The existence of this system is expected to be able to anticipate any damage that can cause considerable and fatal losses.