Develop an Abnormal Detection System of Rotating Equipment by Edge Computing

This research utilizes edge computing technology to analyze the signal by MPU-6050 three-axis accelerometer and Raspberry Pi. We collect the rotating equipment’s vibration signal through the fast Fourier transform to discover the relationship between the control signal and the corresponding frequency spectrum under different operating conditions. First, we take a general indoor fan as an example. Then we find a suitable location for installing the accelerometer on the motor housing, and then collect the vibration signal when the motor is running through the MPU-6050. Then, Python is used to transform the processed data and store it in the database. The neural algorithm retrieves the relationship between the frequency spectrum signal and the fan control signal. Finally, write the rules back to the Raspberry Pi to monitor the status.After performing the test of rotating equipment, the results express that several experiments are required to locate the best measurement position when collecting vibration signals. The signal is converted to the frequency spectrum and then calculated by the proposed algorithm, which effectively discovers the characteristic value related to the control signal and allows the Raspberry Pi to detect the operating state of the device quickly. As a result, the system can immediately respond to abnormal conditions, such as sending an alert e-mail or displaying warning lights.