Real Time NILM Based Power Monitoring of Identical Induction Motors Representing Cutting Machines in Textile Industry

TL;DR

The paper targets real-time energy monitoring in textile manufacturing by applying NILM to identical motor-driven cutting machines. It develops a hardware-software pipeline using Arduino Mega and ESP8266 to collect aggregate and per-line data, stores it on cloud services, and evaluates the MATNILM model under industrial conditions with a newly created dataset of three identical induction motors. Results show reasonable aggregate energy estimation but limited per-appliance disaggregation when identical machines operate concurrently, highlighting key challenges in industrial NILM. The work demonstrates practical remote monitoring via the Blynk app and points to improvements such as higher-frequency sensing, larger datasets, and advanced deep learning approaches to handle identical loads in industrial settings.

Abstract

The textile industry in Bangladesh is one of the most energy-intensive sectors, yet its monitoring practices remain largely outdated, resulting in inefficient power usage and high operational costs. To address this, we propose a real-time Non-Intrusive Load Monitoring (NILM)-based framework tailored for industrial applications, with a focus on identical motor-driven loads representing textile cutting machines. A hardware setup comprising voltage and current sensors, Arduino Mega and ESP8266 was developed to capture aggregate and individual load data, which was stored and processed on cloud platforms. A new dataset was created from three identical induction motors and auxiliary loads, totaling over 180,000 samples, to evaluate the state-of-the-art MATNILM model under challenging industrial conditions. Results indicate that while aggregate energy estimation was reasonably accurate, per-appliance disaggregation faced difficulties, particularly when multiple identical machines operated simultaneously. Despite these challenges, the integrated system demonstrated practical real-time monitoring with remote accessibility through the Blynk application. This work highlights both the potential and limitations of NILM in industrial contexts, offering insights into future improvements such as higher-frequency data collection, larger-scale datasets and advanced deep learning approaches for handling identical loads.

Figures (8)

• Figure 1: Design Approach of the System
• Figure 2: Hardware Setup of the System
• Figure 3: Working Flow of System
• Figure 4: Performance Metrics vs Number of Machines On
• Figure 5: Performance Metrics by Machine ON/OFF State