Automatic Testing Technology of BTB Liquid Crystal Display Advanced Fault Detection in Smart Meter for Smart Machine

Abstract

In smart meter technology, the reliability of Backplane to Bezel (BTB) Liquid Crystal Displays (LCDs) is crucial for efficient functioning within intelligent grid systems. Defects in these LCD screens can significantly impact overall smart meter performance, necessitating effective detection methods for proper management and utilization. Current detection approaches, which combine manual and automatic methods based on machine vision, have shown unsatisfactory performance. This research addresses this challenge by proposing a novel method for advanced fault detection in BTB LCDs of smart meters, Automatic Testing Technology of BTB Liquid Crystal Display Advanced Fault Detection in Smart Meter for smart machine (BTB-LCD-FD- MCDSGAN) is proposed. The study begins by collecting datasets specifically tailored for LCD screen localization and defect detection. To enhance data quality, a Window Adaptive Extended Kalman Filter (WAEKF) is applied during preprocessing for noise removal. Feature extraction follows, utilizing Parameterized Multi Synchrosqueezing Transforms (PMST) with a primary focus on Gray Level Co-occurrence Matrix features. These extracted features serve as input for classification by a Multimodal Contrastive Domain Sharing Generative Adversarial Network (MCDSGAN), categorizing defects into five types likes normal display, no display, abnormal display, liquid crystal rupture, and incomplete display. Furthermore, the proposed method optimizes the MCDSGAN weight parameter using the Red Fox Optimization Algorithm (RFOA) to achieve accurate LCD fault defect prediction. The entire approach is implemented in Python, performance metrics likes accuracy, precision, recall, F-score, computational time are thoroughly analyzed. Performance of proposed BTB-LCD-FD-MCDSGAN approach attains 20.89%, 33.67% and 25.98% high accuracy, and 17.98%, 23.78% and 33.45% higher recall compared with existing methods such as automatic detection of display defects for smart meters depend on deep learning (AD-AM-DL), deep learning-enabled image content-adaptive field sequential color LCDs by mini-LED backlight (DL-AFSC-LCD) and new multi category defect detection method depend on convolutional neural network technique for TFT-LCD panels (MDF-CNN-LCD), methods respectively.