Qualitative Classification of Lubricating Oil Wear Particle Morphology Based on Coaxial Capacitive Sensing Network and SVM

Abstract

In addition to lubricating and cooling, aero-engine lubricating oil is also a transport medium for wear particles generated by mechanical wear. Online identification of the number and shape of wear particles is an important means to directly determine the wear state of rotating parts, but most of the existing research focuses on the identification and counting of wear particles. In this paper, a qualitative classification method of wear particle morphology based on support vector machine is proposed by using the wear particle capacitance signal obtained by the coaxial capacitive sensing network. Firstly, the coaxial capacitive sensing network simulation model is used to obtain the capacitance signals of different shapes of wear particles entering the detection space of different electrode plates. In addition, a variety of intelligent optimization algorithms are used to optimize the relevant parameters of the support vector machine (SVM) model in order to improve the classification accuracy. By using the processed data and optimized parameters, a SVM-based qualitative classification model for wear particles is established. Finally, the validity of the classification model is verified by real wear particles of different sizes. The simulation and experimental results show that the qualitative classification of different wear particle morphologies can be achieved by using the coaxial capacitive sensing network signal and the SVM model.

The Design and Study of a Four-Coil Oil Multi-Pollutant Detection Sensor

“…In particular, the capacitive coupling effect of the solenoid coil mainly consists of the lead capacitance C L , the turn-to-turn capacitance C t , and the wiring's capacitance C s . The total capacitance value of the coil capacitive coupling effect is denoted as C1, which is the sum of the wiring's own capacitance Cs, the coil turn-to-turn capacitance Ct, and the load capacitance CL, as shown in Equation (8). The total capacitance value of the coil capacitive coupling effect is denoted as C 1 , which is the sum of the wiring's own capacitance C s , the coil turn-to-turn capacitance C t , and the load capacitance C L , as shown in Equation ( 8).…”

“…There is a capacitive edge effect at the ends of the capacitor pole plate, and the capacitive coupling effect of the electromagnetic coil needs to be considered [26]. The total capacitance value of the coil capacitive coupling effect is denoted as C1, which is the sum of the wiring's own capacitance Cs, the coil turn-to-turn capacitance Ct, and the load capacitance CL, as shown in Equation (8).…”

“…At the initial stage, the detection of oil fluid mainly relies on the method of particle counting, and later on, iron spectrum analysis is mostly used, but it cannot be widely applied because iron spectrum analysis requires a higher technical level of the staff. Currently, the detection of metallic wear particles in lubricating oils used by ships mainly includes optical detection [3,4], acoustic detection [5,6], capacitance detection [7,8], resistance detection [9,10], and inductance detection [11]. The optical method has high measurement accuracy, but the detection results are easily affected by the transmittance of the oil; the acoustic method can distinguish between solid and gaseous pollutants in the oil, but the stability of the detection results is greatly interfered with by the environmental noise; the inductance method is based on the principle of electromagnetic induction and distinguishes between metal particles with different magnetic properties according to the enhancement and weakening of the magnetic field by magnetization and eddy current effects [12].…”

A Critical Review of On-Line Oil Wear Debris Particle Detection Sensors

“…This experiment showcases the potential utilization of a microfluidic detection apparatus in the domain of identifying abrasive particles in low-conductivity lubricating oil. Zhu et al utilized a network of coaxial capacitive sensors to evaluate and classify the morphology of metallic wear particles in 2022 [75]. They optimized the parameters of a Support Vector Machine (SVM) model and enhanced its classification accuracy through the implementation of intelligent optimization techniques.…”