Search results

It is a challenging task to analysis oxide wear particles when they are stuck together with other types of wear particles in complex ferrography images. Hence, this paper aims to propose a method of ferrography image segmentation to analysis oxide wear debris in complex ferrography images.

First, ferrography images are segmented with watershed transform. Then, two region merging rules are proposed to improve the initial segmentation results. Finally, the features of each particle are extracted to detect and assess the oxide wear particles.

The results show that the proposed method outperforms other methods of ferrography image segmentation, and the overlapping wear particles in complex ferrography images can be well separated. Moreover, the features of each separated wear particles can be easily extracted to analysis the oxide wear particles.

The proposed method provides a useful approach for the automatic detection and assessment of oxide wear particles in complex ferrography images.

The colours, edges and position information of wear debris are considered in the proposed method to improve the segmentation result. Moreover, the proposed method can not only detect oxide wear particles in ferrography images but also evaluate oxide wear severity in ferrography images.

The purpose of this paper is to identify smaller wear particles and improve the calculation speed, identify more abrasive particles and promote industrial applications.

This paper studies a new intelligent recognition method for equipment wear debris based on the YOLO V5S model released in June 2020. Nearly 800 ferrography pictures, 23 types of wear debris, about 5,000 wear debris were used to train and test the model. The new lightweight approach of wear debris recognition can be implemented in rapidly and automatically and also provide for the recognition of wear debris in the field of online wear monitoring.

An intelligent recognition method of wear debris in ferrography image based on the YOLO V5S model was designed. After the training, the GIoU values of the model converged steadily at about 0.02. The overall precision rate and recall rate reached 0.4 and 0.5, respectively. The overall MAP value of each type of wear debris was 40.5, which was close to the official recognition level of YOLO V5S in the MS COCO competition. The practicality of the model was approved. The intelligent recognition method of wear debris based on the YOLO V5S model can effectively reduce the sensitivity of wear debris size. It also has a good recognition effect on wear debris in different sizes and different scales. Compared with YOLOV. YOLOV, Mask R-CNN and other algorithms%2C, the intelligent recognition method based on the YOLO V5S model, have shown their own advantages in terms of the recognition effect of wear debris%2C the operation speed and the size of weight files. It also provides a new function for implementing accurate recognition of wear debris images collected by online and independent ferrography analysis devices.

To the best of the authors’ knowledge, the intelligent identification of wear debris based on the YOLO V5S network is proposed for the first time, and a large number of wear debris images are verified and applied.

The purpose of this paper is to adapt teachable machine as a web-based tool for recognition of wear pattern and type of wear by training a convolutional neural network (CNN) model. This helps to monitor the health of the lubricated system as a part of condition monitoring.

Ferrography technique is used for analysis of wear particles. It helps monitor the condition of lubricated mechanical system. In present paper, CNN model is developed for identifying the type of wear particles coming out of Gearbox system using teachable machine.

From the experimentation, it has been observed that the wear severity index has been increased due to increase in wear particle concentration. CNN model has achieved an accuracy of 95.4% to recognize five categories of wear particles.

Teachable machine is generally used for the prediction of images, gestures and sound features. An attempt is made to apply this model for micro and nano wear particles to classify them based on their characteristics.

Reports on the study of wear debris in the early 1980s organized by the Institution of Mechanical Engineers. Describes the use of Ferrography, spectrographic oil analysis, X‐ray fluorescence, inductive, magnetic and ultrasonic methods of debris detection with some examples of wear limits.

This paper sets out to develop a reliable analysis method based upon a low‐cost procedure to monitor the wear condition of low‐speed and heavily loaded rolling element bearing.

Special solvents for grease are invented and new test methods, including spectroscopy and ferrography of used grease, are developed to monitor the wear condition of a deferred bearing of ladle turret in continuous casting.

According to the analytical results, the service life of the ladle turret bearing in No. 1 continuous casting machine is extended to 14 years and significant expense is saved, which proved that it is feasible for grease analysis to be used in the condition monitoring of low speed and heavily loaded rolling element bearing, especially those deferrable bearings.

The fault mechanism of the huge bearing is not estimated.

One useful analysis method to monitor the wear condition of low speed and heavily loaded rolling element bearing is reported, and it can be used in other industrial fields.

This paper provides a way of studying condition monitoring of low‐speed and heavily loaded rolling element bearings.

This paper aims to optimize the operating condition of mechanical parts, whose working surfaces have macro-crack defects, and surface wear properties with macro-cracks are assessed through experimental investigation.

Macro-cracks perpendicular to the direction of sliding were manufactured on discs by electric discharge machining. Tribological tests under oil lubrication were conducted on a ball-on-disc test rig. Their wear processes were monitored with on-line visual ferrography. The cross-sectional profile and morphology of the wear track were analyzed using a T200 profilometer and a scanning electron microscope, respectively. Effects of different crack numbers and various applied normal loads on the wear behavior were studied.

The macro-cracks tend to promote plastic deformation on the contact disc surfaces, and material plastic deformation of the crack edges varies with the magnitude of applied normal loads. Relationship of the duration of running-in period and root mean square index of the particle coverage area with the numbers of crack is approximately linear.

The wear properties of surfaces with macro-cracks were assessed with various crack numbers and with different applied normal loads, and the relationship between the index of particle coverage area and the wear rate was established.

The purpose of this paper is to study the effect of particles on the wear of cylinder liner in internal combustion (IC) engine under some typical weather conditions.

Experiments were conducted under some typical dust weather which was simulated by the self‐built test‐bed with an actual diesel engine. Three‐dimensional surface morphology was applied to produce a comprehensive characterization of cylinder liner's wear. Ferrography and oil spectrum analysis were employed for further understanding of the abrasion of the cylinder liner caused by particles.

The presence of particles destroyed the lubricating condition of piston‐cylinder liner, speeded up the wear of liner, especially on the thrust side, and aggravated the local wear. Wear curves showed that greater wear volume occurred near bottom dead center on the thrust side under the dust condition. However, on the anti‐thrust side, wear volume of top dead center was greater than that of bottom dead center, similar to the wear pattern under the normal condition. Wear rate under dust condition was three to five times of that under normal condition.

The paper is restricted to the experimental findings based on single cylinder engine and theoretical researches are needed in the next step.

The results help to understand the wear of the cylinder liner from the presence of particles from outside the engine.

The paper concentrates on the effect of dust particles on the wear of cylinder liner under some dusty weather conditions simulated by a self‐built test‐bed, employing an actual IC engine. The results may bring about better understanding of the wear of cylinder liners.

The paper aims to monitor the condition of heavy Earth-moving machines (HEMMs) used in open cast mines by lube oil analysis.

Oil samples at periodic interval were collected from the HEMM engine (Model No: BEML BH50M). Ferrography and Field Emission Scanning Electron Microscopy have been used for the wear particle analysis present in oil samples. Viscosity analysis and Fourier transform infrared spectroscopy have been done to investigate the degradation in quality and changes as compared to the initial structural properties of the lubricants.

The results obtained indicates wear in cylinder liner and piston ring. Copper, cast iron, alloy steel and ferrous oxide have been found as rubbing wear particles and cutting wear particles. Contamination level has also been found to be increasing in consecutive older oil samples. Chemical properties degraded with usage time and variations in oxidation and soot level have also been observed in every sample.

The results will be very much useful to maintenance teams of mining industry for early prediction of any impending failure of the machines, for example, diesel dilution, severe wear of the piston or cylinder liner leading to seizure can be predicted.

The HEMMs are an important piece of equipment in coal mining. Proper condition monitoring of HEMM is required to reduce the break down and down time to increase production.

Using computer technology to realize ferrographic intelligent fault diagnosis technology is fundamental research to inspect the operation of mechanical equipment. This study aims to effectively improve the technology of deep learning technology in the field of ferrographic image recognition.

This paper proposes a binocular image classification model to solve ferrographic image classification problems.

This paper creatively proposes a binocular model (BesNet model). The model presents a more extreme situation. On the one hand, the model is almost unable to identify cutting wear particles. On the other hand, the model can achieve 100% accuracy in identifying Chunky and Nonferrous wear particles. The BesNet model is a bionic model of the human eye, and the used training image is a specially processed parallax image. After combining the MCECNN model, it is changed to BMECNN model, and its classification accuracy has reached the highest level in the industry.

The work presented in this thesis is original, except as acknowledged in the text. The material has not been submitted, either in whole or in part, for a degree at this or any other university. The BesNet model developed in this article is a brand new system for ferrographic image recognition. The BesNet model adopts a method of imitating the eyes to view ferrography images, and its image processing method is also unique. After combining the MCECNN model, it is changed to BMECNN model, and its classification accuracy has reached the highest level in the industry.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-05-2023-0150/

Ball bearings in gas turbine have played a critical role in supporting heavy radial loads but with higher failure rates and repair costs. Therefore, the purpose of this study is to introduce and study a method for their failure analysis with an actual industrial example to guarantee operation reliability and safety.

Spectrometric oil analysis was used as an early abnormal wear indicator, based on which emergent in-use oil replacement was carried out to reduce the wear rate. However, with wear deterioration, further wear failure investigation was conducted by LaserNet Fines and ferrography to detect the imminent wear failure. Finally, with the assistance of elemental analysis of the typical wear particles, the root cause and worn components were determined by scanning electronic microscope and energy-dispersive X-ray spectroscopy.

The results have shown that an extraneous source led to wear failure, which later caused overheat between the outer bearing ring and ball. It is in accordance with visual inspection of the disassembled engine.

This method has specified the occasion under which the suitable measurement can be taken. It can achieve the rapid wear condition assessment allowing for root cause and worn parts identification. In addition, wear rate reduction by change of oil can be efficient for most of the time to avoid premature disassemble, especially with the possibility of contamination. It has provided experience to address similar industry-level practical wear failure analysis problems.