Cloud Internet of Things Based Machine Monitoring Analysis of Energy Parameters Using Novel Techniques

In remote area industrial systems, energy consumption monitoring is a crucial challenge. As the conventional monitoring methods lack an intelligent approach, the finest energy consumption monitoring is not possible. Hence, Internet of Things (IoT) based monitoring methods have been developed by recent industrial systems. Therefore, in this research, a novel cloud with IoT based energy monitoring technique is developed. The energy parameters of the Computer Numerical Control based milling machine has been gathered using IoT based Current Transducers , Voltage Transducers , and power sensors. The IoT device includes Zigbee or Bluetooth for managing communication between the machine and the monitoring system. Then the obtained data is stored in the cloud storage platform for large scale machine energy data in the windows platform. Later on, the obtained data from cloud storage is processed by the novel Normalized Recursive Least Kalman Filter for event detection processing. Moreover, the feature extraction has been done using the proposed Simplified Principal Component Analysis method. Furthermore, the energy utilization of the machine is monitored over various situations using the proposed novel Dynamic Self-evolving Reasoning based Fuzzy Neural algorithm. The Median Absolute Deviation is estimated for the conditional inference of the system. The software implementation of this work is done in MATLAB. The power consumption of the machine is validated under various cases. Besides, the proposed simulation outcomes are compared with various existing energy monitoring systems for verifying the significance of the developed method.