A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle.

Kuo-Yi Huang,Yu-Ting Ye

doi:10.3390/s150715326

Abstract

In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

Highlights

Nozzles are a common mechanical component and are widely used in agriculture, manufacturing and the service industry
The internal defects of micro-spray nozzles usually result during cutting procedures with a CNC machine
Possible defect regions are segmented by the circle inspection (CI) algorithm

Summary

Introduction

Nozzles are a common mechanical component and are widely used in agriculture, manufacturing and the service industry. A micro-spray nozzle is an important component in an agricultural sprayer, which is used to spray water, pesticides and nutrients. Real-time flow uniformity depends on the Sensors 2015, 15 internal quality of the micro-spray nozzle. Unstable flow will be created because of internal defects. The price and quality of micro-spray nozzles are down due to such defects. The internal defects of micro-spray nozzles usually result during cutting procedures with a CNC (computer numerical control) machine. Chang and Yu [1] proposed a triangular-pitch shell-and-tube spray evaporator featuring an interior spray technique. Micro-spray nozzles have to be sorted manually, because the surface of the micro-spray nozzle is heterogeneous, which makes auto-detection very difficult

Objectives

Methods

Results

Conclusion