Application of Image Color Analysis for the Assessment of Injector Nozzle Deposits in Internal Combustion Engines
ISSN: 1946-3952, e-ISSN: 1946-3960
Published January 18, 2022 by SAE International in United States
Citation: Monieta, J., "Application of Image Color Analysis for the Assessment of Injector Nozzle Deposits in Internal Combustion Engines," SAE Int. J. Fuels Lubr. 15(2):2022, https://doi.org/10.4271/04-15-02-0010.
The article contains the results of operational investigations of deposit formation on external and internal surfaces of injector nozzles of the marine self-ignition engines during their operational use. The aim of this article is to introduce an image analysis method for global assessment of the quantity and quality of injector nozzle deposits in piston internal combustion engines. The components of medium-speed marine engines fueled with distillation and residual fuels were investigated. Digital images of new and used injector nozzles without deposits and with random deposits formed after natural operation on marine ships, respectively, were taken. Macro and microscopy images of external surfaces were taken in a shadowless tent and were illuminated with low-temperature lamps. The characteristic surfaces of the injector nozzles were virtually separated from the white background. The amount and quality of the resulting deposits on individual injector nozzles was determined by means of a global analysis of the blackening degree of gray images and the share of basic RGB (red, green, blue) colors. Basic central statistical measures were applied to assess the deposits of the investigated injector nozzles, and models of wear were developed. There have been archived photographs of the distinguished surfaces of various types of bodies and needles of injector nozzles and results of images analysis performed.
This method is an innovative, nondestructive diagnostic technique for the characterization of deposits in internal combustion engines with the use of symptoms expressed in numerical form. Digital images were analyzed with basic central statistical measures, which were calculated from a sample of random pixel variables.