Narrow Results

Ferrography analysis is one of main means to identify wear state of mechanical equipment, and its key is the intelligent recognition of wear debris ferrographic images. Ferrographic image acquisition is a complex and time-consuming work, so the direct deep learning cannot been carried out for the small tested samples. A virtual ferrographic image dataset is prepared firstly and then two-level transfer learning scheme is proposed to improve the identification rate of the tested samples based on the deep learning model trained by the virtual samples. A combined network of YOLOv3 and DarkNet53 is constructed, and the application effect of model is improved by two-level transfer learning of virtual dataset to open dataset and then open dataset to tested dataset, and the model errors before and after twice transfer learning are analyzed. The average identification accuracy of the model in the validation dataset is 86.1%, which is 44.5% higher than that without two-level transfer learning, and the average recall reaches 95.8%. The experimental results prove the proposed method have a high identification rate for the tested ferrographic images of an actual gearbox.

Our bodies deteriorate from wear and tear processes, which give rise to ache and pain. This degenerative process is medically referred to as osteoarthritis (OA) and it is estimated to affect a large portion of the population at some stage in their life. There is a need for research into new and improved techniques that might be developed into a schema to aid in the early diagnosis and prognosis of a patient's condition. This can be achieved by studying the morphology of the collagen fibers in the wear particles generated to gain an insight into the osteoarthritic condition exhibited by the joint. The study has been conducted in three phases. Firstly, an animal model has been used to generate samples of cartilage and wear particles for the study. A suitable staining technique has then been developed that allows the three-dimensional visualization and quantitative analysis of the structure of the collagen matrix of sheep cartilage and in wear particles. Finally, correlation of the changes in the collagen matrix as per OA severity has been studied. The study has identified key numerical parameters to characterize distinctive wear features of the cartilage and wear debris. A good correlation of the wear features of the cartilage and wear particle samples has been found. The positive results attained by this study suggest that with the aid of further research and development, it is distinctly possible to develop improved diagnostic procedures for clinical osteoarthritic assessment.

Wear debris–induced periprosthetic disease is a major concern after total joint replacement. The wear debris stimulates a cascade of inflammation, resulting in peri-implant osteoclastogenesis and osteolysis. Although in vitro studies have contributed considerably to our understanding of wear debris-induced adverse biological reactions, animal experiments are necessary to understand the more complex mechanisms in vivo. In this chapter, we describe a mouse model that allows the quantification of osteoclastogenesis and osteolysis. Ultrahigh molecular weight polyethylene (UHMWPE) particles are implanted onto calvariae in C57BL/J6 mice, which then develop greater levels of active inflammatory osteolysis than do the control species. The particles are washed in ethanol to remove surface-adherent endotoxin, thus reducing endotoxin interference. Osteolysis can be found in the middle sagittal suture and the adjacent region in mouse calvaria 1 week after implantation. Decalcified hematoxylin and eosin (H&E)-stained sections are used to quantify the osteolysis area. Osteoclastogenesis regions are identified and quantified in tartrate-resistant acid phosphatase (TRAP)-stained sections. Larger areas of osteolysis and TRAP-stained osteoclastic activity are found to be induced by UHMWPE particles than developed by the sham group.

A singular case of a patient with a systemic pathology is presented and discussed evaluating the analyses to which he was subjected. The SEM observations of liver’s and kidney’s bioptic slices and their x-ray microanalyses revealed that the disease was caused by debris of dental porcelain. They were released by worn dental bridges, ingested and espelled along with feces. Debris with diameters less than 20 μm passed the bowel epithelial barrier and went into the bloody stream. Liver filtered them, and they caused a granulomatous reaction. The relativity of the biocompatibility of materials is discussed.