Lasernet Fines Q200 – A Solution to Oil Analysis Including Particle Count and Particle Shape Classification

LNF Technology
Jointly developed by Lockheed Martin and the Naval Research Laboratory with the Office of Naval Research. LNF is a particle shape classifier that also provides a highly accurate particle count for particles greater than 4 um using laser imaging techniques and advanced image processing software. Silhouette images of all particles larger than 20 um in major dimension are automatically classified into the following categories:

• Cutting
• Severe sliding
• Fatigue
• Nonmetallic
• Fibers
• Water droplets

The instrument counts these particles and provides a quantitative measure of active machine wear. Bitmap images are saved and printed on report for review. Reliability engineers can make more informed decisions using LNF data by trending both the total particle size distribution and the sub category particles. In addition to solid particles, the percent of free water is estimated based on the calculated volume of the detected water droplets greater than 20 gm while air bubbles greater than 20 um are recognized and eliminated from the count. The instrument automatically corrects for the color of the fluid, making it accurate for intrinsically light and dark-colored fluids such as in service engine oils.

The role of IR spectrum analysis
The basic operating principle of LNF is illustrated in Figure 1 below.

1. A representative oil sample is drawn from the lubricating system and brought to the unit.
2. The oil is drawn through a patented viewing cell that is back-illu minated with a pulsed laser diode to freeze the particle motion.
3. The coherent light is transmitted through the fluid and imaged onto an electronic camera.
4. Each resulting image is analyzed for particles.

For wear particles in lubricating oil, the instrument displays particle size in terms of maximum chord. For particles in hydraulics, it displays the size in equivalent circular diameter for compatibility with ISO cleanliness codes. In either fluid, shape characteristics are calculated for particles greater than 20pm, and the particle is classified into either a wear category or contaminant category.

Classification is performed with an artificial neural network developed specifically for the LNF system. Shape features were chosen to provide optimal distinction between the assigned classes of fatigue, cutting, severe sliding, non-metallic particles, fibers, water bubbles, and air bubbles (Figure 2). An extensive library of particles, which were identified by human experts, was used to train the artificial neural network.
The next sections compare how LNF gathers and analyzes data compared to Optical Particle Counters and then traditional
ferrography methods.