IoT-Based System for Health Care of Textile Machines

Yarn breakage is a major problem in the textile mills as it leads to reduced production. Breakages occur when the spindle speed increases and is more than the ideal range. The spindle speed increases when the machine deteriorates. Health monitoring is an important aspect which has to be taken care of. An IoT-based system is designed and validated in this paper. The designed system will be able to predict the condition of the machine by means of artificial neural networks. This data would be used by the maintenance team to take preventive measures. The embedded system is interfaced with temperature and vibration sensors to monitor the functioning of the machine. The sensor data is fed to the neural network continuously. A Wi-Fi interface enables data transfer. The yarn breakages are also observed for a spindle speed of 24,000 rpm. On training the neural network using the sensor data, the yarn breakages are predicted for any data captured real time. The simulation results show a mean squared error of .002. This would prevent the machines from breakdown and hence save downtime.