Ventilation Diagnosis of Angle Grinder Using Thermal Imaging.

Adam Glowacz

doi:10.3390/s21082853

Abstract

The paper presents an analysis and classification method to evaluate the working condition of angle grinders by means of infrared (IR) thermography and IR image processing. An innovative method called BCAoMID-F (Binarized Common Areas of Maximum Image Differences—Fusion) is proposed in this paper. This method is used to extract features of thermal images of three angle grinders. The computed features are 1-element or 256-element vectors. Feature vectors are the sum of pixels of matrix V or PCA of matrix V or histogram of matrix V. Three different cases of thermal images were considered: healthy angle grinder, angle grinder with 1 blocked air inlet, angle grinder with 2 blocked air inlets. The classification of feature vectors was carried out using two classifiers: Support Vector Machine and Nearest Neighbor. Total recognition efficiency for 3 classes (TRAG) was in the range of 98.5–100%. The presented technique is efficient for fault diagnosis of electrical devices and electric power tools.

Highlights

IntroductionThe use of power tools (electric impact drills, angle grinders, cordless screwdrivers, etc.) can be found in the construction industry
The use of power tools can be found in the construction industry
Effective diagnosis techniques of electric power tools can decrease the number of accidents and economical losses

Summary

Introduction

The use of power tools (electric impact drills, angle grinders, cordless screwdrivers, etc.) can be found in the construction industry. Effective diagnosis techniques of electric power tools can decrease the number of accidents and economical losses. For these reasons investigation of fault diagnosis of electric power tools is essential. The development of new methods and techniques of fault diagnosis is profitable. The development of fault diagnosis techniques is related to signal analysis for example: acoustic and vibration signals. The fault diagnosis technique of angle grinders is shown. The BCAoMID−F extracted feature vectors from thermal images. The paper has the following sections: (1) Introduction, (2) Theoretical background (3) Processing and recognition of the thermal image (4) Analyzed states of the angle grinder (5) Results of the analysis of thermal images (6) Conclusions

Theoretical Background

Analyzed States of the Angle Grinder

Support Vector Machine

Results of the Analysis of Thermal Images

Conclusions