On-line solid debris analysis of oil using vision technology on open computing platform

• This article describes a case-study related to on-line condition monitoring measurements in process industry. A platform for on-line, real-time and remotely operated condition monitoring has been developed. The system consists of an open source based embedded and cost effective DSP computing platform, a machine vision sensor for solid debris analysis of oils, and interfaces for other measurement technologies (e.g. vibration analysis and/or temperature measurements). In addition, the platform is equipped with data transmission interface that enables remote operation and control. Real-time analysis of solid particles in oil is useful in many preventive condition monitoring applications, for example, in the lubrication circuit of a paper machine or with cold rolling lubrication oils. In the case of a paper machine the generated information can be used to pinpoint upcoming failures in the machine elements (e.g. bearings, gears etc.). Whereas in the case of cold rolling applications the information is useful to prevent quality problems in the rolled metal product. In the both applications the presented system enables also monitoring failures in the filtration system. Preliminary results and designs show that the system is able to detect and analyse size and shape for particles larger than 50 micrometers continuously with a frame rate of 5 Hz from the oil flow volume of 13.8 ml/s and flow speed of 60 mm/s. The system is in progress of being further developed in collaboration with the industry. Easy integration of different sensors and real-time measurements make the system a powerful tool for making maintenance decisions in process industry

Ämnesord

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)

Nyckelord

Signalbehandling

Signal Processing

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)