Fault diagnosis method of mechanical power system based on image processing technology

Xiao Zhou,Lei Qiu ,Liangtao Qi

doi:10.1177/1729881420914093

Abstract

Fault detection and diagnosis become one of today’s hot spots, which describes that image information is an important form of fault information, it can quickly through the image processing technique, and can accurately extract the characteristic signal. This article selects the color of the particle image, the integrated use of digital image processing, pattern recognition theory, the characteristic parameters of tribology knowledge, as well as the extraction, optimization, and digital; verifies the feasibility of iron spectrum of abrasive fault recognition, and provides a new efficient ferrographic wear particle image recognition method. Firstly, the grindstone image of the original color diesel engine was preprocessed, and the grindstone image of the ferrograph was identified by directly selecting grindstone from the preprocessed ferrograph image and selecting the target grindstone. According to the two types of abrasive particles, the characteristic parameters were first classified, and then the values of the characteristic parameters were obtained through the training and learning of the sample abrasive particles. In view of the large number of characteristic parameters of ferro-spectrum abrasive particles, this article determined the characteristic parameters suitable for the identification of abrasive particles in this article through the feature optimization and proved the correctness of the identification of characteristic parameters of abrasive particles through the test.

Highlights

With the development of science, technology, and productivity, modern mechanical equipment has become increasingly large and complicated, especially with the emergence of mechatronics, automation, and intelligence, making the scale of the production system larger and larger, the performance indicators in various aspects higher and higher, and the functions more perfect.[1]
Oil analysis technology is a kind of abrasive particle analysis technology in essence, which includes two categories: one is the analysis of the deterioration degree of oil; the other is the analysis of the number, size, shape, color, composition, and changes of abrasive particles in the oil.[6]
Iron spectrum technology of the 1970s is a new wear particle analysis technology; the spectral analysis is mainly used for analysis of mechanical lubrication metal content in the power system, and it is mainly used for judging the wear condition of mechanical equipment, but the spectral analysis of serious deficiencies,[9] for example, could not tell the sensitivity to large-sized particles, could not observe grinding-grain morphology, and could not observe quantitative analysis of the different grinding particle size distribution and other equipment is expensive

Summary

Introduction

With the development of science, technology, and productivity, modern mechanical equipment has become increasingly large and complicated, especially with the emergence of mechatronics, automation, and intelligence, making the scale of the production system larger and larger, the performance indicators in various aspects higher and higher, and the functions more perfect.[1]. Monitoring the navy’s development using LaserNetFines optical grits can be done by online monitoring, and off-line analysis can be its principle to use the laser diode after exposure to oil in electronic camera, which will generate the image principle used for grinding-grain recognition, and to determine the oil characteristics of the reflected.[13] The monitor USES laser diodes that capture texture features under a microscope that are not fully reflected It provides information about the type and severity of equipment failure by analyzing benign and active abrasive particles in the oil. Ferrographic image recognition technology is the computer image processing technology to join ferrographic quantitative analysis calculation; a piece of iron spectrum of single abrasive grain characteristic parameters is analyzed, based on the related theory of pattern recognition; the design of typical wear particle classifier using statistical parameter values can grind grain of automatic recognition and classification.[25].

A Digital Camera

Conclusions