A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition

Aiming at solving the acquisition problems of wear particle data of large-modulus gear teeth and few training datasets, an integrated model of LCNNE based on transfer learning is proposed in this paper. Firstly, the wear particles are diagnosed and classified by connecting a new joint loss function and two pretrained models VGG19 and GoogLeNet. Subsequently, the wear particles in gearbox lubricating oil are chosen as the experimental object to make a comparison. Compared with the other four models’ experimental results, the model superiority in wear particle identification and classification is verified. Taking five models as feature extractors and support vector machines as classifiers, the experimental results and comparative analysis reveal that the LCNNE model is better than the other four models because its feature expression ability is stronger than that of the other four models.

Study and analysis of the morphology and composition of wear particle in the used engine oil of marine diesel engines

В статье представлены результаты исследования состава и морфологии частиц продуктов износа в работающем моторном масле судового двигателя внутреннего сгорания. Полученные данные базируется на результатах физико-химического и спектрального анализа работающего масла, идентификации дисперсного состава частиц загрязнения в нем и углубленном анализе элементного состава и формы продуктов износа пар трения судовых двигателей. Из представленных результатов следует, что основное количество частиц износа не превышает 3 мкм и представляет собой сложные сплавы, полученные в результате изнашивания трущихся сопряжений двигателя. Анализ формы частиц износа, выполненный с помощью сканирующего электронного микроскопа Lyra3 Tescan, показал что у более чем 90 % всех частиц величина Wr превышает значение 0,8. Показано на основе выполненного исследования, что спектральные методы анализа обеспечивают высокую достоверность трибомониторинга и трибодиагностики судовых дизелей. The article presents the results of a study of the composition and morphology of particles of wear products in used engine oil of a marine diesel engine. The obtained data are based on the results of physicochemical and spectral analysis of operating oil, identification of the dispersed composition of pollution particles in it, and in-depth analysis of the elemental composition and shape of wear products of friction pairs of ship engines. From results follow that the main amount of wear particles does not exceed 3 microns and they are complex alloys obtained as a result of engine wear of friction. The analysis of the shape of the wear particles, carried out using a Lyra3 Tescan scanning electron microscope, showed that more than 90% of all particles had a Wr value greater than 0.8. It is shown on the basis of the performed research that spectral methods of analysis provide high reliability of tribomonitoring and tribodiagnostics of marine diesel engines.

Research on 3D reconstruction method of wear particle dynamic image based on multi contour space mapping

Aiming at the problems of current image monitoring methods of lubrication oil wear particles, this paper designs and builds a dynamic monitoring system for oil wear particles based on microfluidic microscopic images. A contour-based 3D reconstruction method of debris particle images is proposed. The image sequences of rotating wear particles tracked by a single target are used as data, and the contour of the wear particle is extracted and the data is stored. The minimum area external rectangle method is used to correct the rotation of the particle images for the problem of deflection. And an algorithm based on cylindrical coordinate space conversion is used to convert the discrete contour point data into three-dimensional space. Complete the 3D model reconstruction of microfluidic wear particles. The ability to analyse wear particles in oil online monitoring technology is improved, which also shows new ideas for wear status monitoring and fault diagnosis technology.

Study on Wear Debris Characterization of Polycarbonate Urethane (PCU) as a Bearing of Artificial Hip Joint

As with all artificial joints, wear debris is of particular concern due to its effect on both implant life and the in vivo biological reactions that can occur. The purpose of the research is to study debris characterization of PCU. Wear particle is produced from testing the PCU material using a pin on disc wear tester within 50000 cycles. This study showed that the PCU wear debris gotten from the simulator had various different shapes, including laminar and spherical types. The morphology of worn surface and wear debris analysis showed that wear mechanism of PCU were fatigue wear. Thus we conclude that PCU is expected to be a lifetime implantation of artificial joint.

Curculigoside Protects against Titanium Particle-Induced Osteolysis through the Enhancement of Osteoblast Differentiation and Reduction of Osteoclast Formation

Wear particle-induced periprosthetic osteolysis is mainly responsible for joint replacement failure and revision surgery. Curculigoside is reported to have bone-protective potential, but whether curculigoside attenuates wear particle-induced osteolysis remains unclear. In this study, titanium particles (Ti) were used to stimulate osteoblastic MC3T3-E1 cells in the presence or absence of curculigoside, to determine their effect on osteoblast differentiation. Rat osteoclastic bone marrow stromal cells (BMSCs) were cocultured with Ti in the presence or absence of curculigoside, to evaluate its effect on osteoclast formation in vitro. Ti was also used to stimulate mouse calvaria to induce an osteolysis model, and curculigoside was administrated to evaluate its effect in the osteolysis model by micro-CT imaging and histopathological analyses. As the results indicated, in MC3T3-E1 cells, curculigoside treatment attenuated the Ti-induced inhibition on cell differentiation and apoptosis, increased alkaline phosphatase activity (ALP) and cell mineralization, and inhibited TNF-α, IL-1β, and IL-6 production and ROS generation. In BMSCs, curculigoside treatment suppressed the Ti-induced cell formation and suppressed the TNF-α, IL-1β, and IL-6 production and F-actin ring formation. In vivo, curculigoside attenuated Ti-induced bone loss and histological damage in murine calvaria. Curculigoside treatment also reversed the RANK/RANKL/OPG and NF-κB signaling pathways, by suppressing the RANKL and NF-κB expression, while activating the OPG expression. Our study demonstrated that curculigoside treatment was able to attenuate wear particle-induced periprosthetic osteolysis in in vivo and in vitro experiments, promoted osteoblastic MC3T3-E1 cell differentiation, and inhibited osteoclast BMSC formation. It suggests that curculigoside may be a potential pharmaceutical agent for wear particle-stimulated osteolysis therapy.

A Lubricating Oil Condition Monitoring System Based on Wear Particle Kinematic Analysis in Microfluid for Intelligent Aeroengine

Lubricating oil monitoring technology is a commonly used method in aeroengine condition monitoring, which includes particle counting technology, as well as spectral and ferrography technology in offline monitoring. However, these technologies only analyze the characteristics of wear particles and rely on physical and chemical analysis techniques to monitor the oil quality. In order to further advance offline monitoring technology, this paper explores the potential role of differences in wear particle kinematic characteristics in recognizing changes in wear particle diameter and oil viscosity. Firstly, a kinematic force analysis of the wear particles in the microfluid was carried out. Accordingly, a microfluidic channel conducive to observing the movement characteristics of particles was designed. Then, the wear particle kinematic analysis system (WKAS) was designed and fabricated. Secondly, a real-time tracking velocity measurement algorithm was developed by using the Gaussian mixture model (GMM) and the blob-tracking algorithm. Lastly, the WKAS was applied to a pin–disc tester, and the experimental results show that there is a corresponding relationship between the velocity of the particles and their diameter and the oil viscosity. Therefore, WKAS provides a new research idea for intelligent aeroengine lubricating oil monitoring technology. Future work is needed to establish a quantitative relationship between wear particle velocity and particle diameter, density, and oil viscosity.