Application of an Artificial Neural Network to Improve the Accuracy of the PZEM-004T Current Sensor
Abstract
The PZEM-004T sensor is used for monitoring the electrical current consumed by electronic devices. However, the data generated by these sensors is still inaccurate and requires optimization. In this study, the Artificial Neural Network (ANN) method was used to optimize the PZEM-004T sensor system using ammeter data as a learning target. The ANN architecture used is 1-10-1. Matlab simulation results show that the architecture is very effective with an error difference of 0.0027. Then, ANN parameters such as weights and bias were applied to the system and succeeded in increasing accuracy with an average error difference of 0.0075. Even though there is a difference between the error values in the Matlab simulation and the Arduino implementation, the error values can still be minimized and the system can be used in several applications. Thus, the use of the PZEM-004T sensor optimization system with 1-10-1 architecture and ANN parameters on Arduino can be an effective solution in increasing the accuracy of electric current measurements.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International license.