Search results

The possibility of using a pattern recognition system for wear particle analysis without the need of a human expert holds great promise in the condition monitoring industry. Auto-segmentation of their images is a key to effective on-line monitoring system. Therefore, an unsupervised segmentation algorithm is required. The purpose of this paper is to present a novel approach based on a local color-texture feature. An algorithm is specially designed for segmentation of wear particles’ thin section images.

The wear particles were generated by three kinds of tribo-tests. Pin-on-disk test and pin-on-plate test were done to generate sliding wear particles, including severe sliding ones; four-ball test was done to generate fatigue particles. Then an algorithm base on local texture property is raised, it includes two steps, first, color quantization reduces the total quantity of the colors without missing too much of the detail; second, edge image is calculated and by using a region grow technique, the image can be divided into different regions. Parameters are tested, and a criterion is designed to judge the performances.

Parameters have been tested; the scale chosen has significant influence on edge image calculation and seeds generation. Different size of windows should be applied to varies particles. Compared with traditional thresholding method along with edge detector, the proposed algorithm showed promising result. It offers a relatively higher accuracy and can be used on color image instead of gray image with little computing complexity. A conclusion can be drawn that the present method is suited for wear particles’ image segmentation and can be put into practical use in wear particles’ identification system.

One major problem is when small particles with similar texture are attached, the algorithm will not take them as two but as one big particle. The other problem is when dealing with thin particles, mainly abrasive particles, the algorithm usually takes it as a single line instead of an area. These problems might be solved by introducing a smaller scale of 9 × 9 window or by making use of some edge enhance technique. In this way, the subtle edges between small particles or thin particles might be detected. But the effectiveness of a scale this small shall be tested. One can also magnify the original picture to double or even triple its size, but it will dramatically increase the calculating time.

A new unsupervised segmentation algorithm is proposed. Using the property of the edge image, we can get target out of its background, automatically. A rather complete research is done. The method is not only introduced but also completely tested. The authors examined parameters and found the best set of parameters for different kinds of wear particles. To ensure that the proposed method can work on images under different condition, three kinds of tribology tests have been carried out to simulate different wears. A criterion is designed so that the performances can be compared quantitatively which is quite valuable.

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/

This study aims to reconstruct the frictional vibration signal from noise and characterize the running-in process by frictional vibration.

There is a strong correlation between tangential frictional vibration and normal frictional vibration. On this basis, a new frictional vibration reconstruction method combining cross-correlation analysis with ensemble empirical mode decomposition (EEMD) was proposed. Moreover, the concept of information entropy of friction vibration is introduced to characterize the running-in process.

Compared with the wavelet packet method, the tangential friction vibration and the normal friction vibration reconstructed by the method presented in this paper have a stronger correlation. More importantly, during the running-in process, the information entropy of friction vibration gradually decreases until the equilibrium point is reached, which is the same as the changing trend of friction coefficient, indicating that the information entropy of friction vibration can be used to characterize the running-in process.

The study reveals that the application EEMD method is an appropriate approach to reconstruct frictional vibration and the information entropy of friction vibration represents the running-in process. Based on these results, a condition monitoring system can be established to automatically evaluate the running-in state of mechanical parts.

The EEMD method was applied to reconstruct the frictional vibration. Furthermore, the information entropy of friction vibration was used to analysis the running-in process.

The purpose of this paper is to develop a good calculation model to accurately predict the lubrication characteristic of main bearings of diesel engine and improve the service life.

Based on the coupling of the whole flexible engine block and the flexible crankshaft reduced by the Component Mode Synthesis (CMS) method, considering mass-conserving boundary conditions, the average flow model equation and Greenwood/Tripp asperity contact theory, an elastohydrodynamic (EHD)-mixed lubrication model of the main bearings for the diesel engine is developed and researched with the finite volume method and the finite element method.

Obviously, the mixed lubrication of bearings is normal, while full hydrodynamic lubrication is transient. The results show that under the whole flexible block model, maximum oil film pressure, maximum asperity contact pressure and radial shell deformation decrease, while minimum oil film thickness increases. Oil flow over edge decreases, and so does friction loss. Therefore, coordination deformation ability of whole engine block is favorable to mean load. In the whole block model, friction contact happens on both upper shell and lower shell positions. In addition, average oil film fill ratio at the key position becomes smaller in the whole engine block model, and consequently increases the chances of cavitations erosion more. So, wearing resistance of both upper and lower shells and anti-cavitations erosion ability must be enhanced simultaneously.

Based on the coupling of the whole flexible engine block and the flexible crankshaft reduced by the CMS method, considering mass-conserving boundary conditions, the average flow model equation and Greenwood/Tripp asperity contact theory, an EHD-mixed lubrication model of the main bearings for the diesel engine is built, which can predict the lubrication of journal bearings more accurately.

This study aims to use a deterministic tourist walk to build a system that can identify wear particles. Wear particles provide detailed information about the wear processes taking place between mechanical components. Identification of the type of wear particles by image processing and pattern recognition is key to effective online monitoring algorithm. There are three kinds of particles that are particularly difficult to distinguish: severe sliding wear particles, fatigue spall particles and laminar particles.

In this study, an identification method is tested using the deterministic tourist walking (DTW) method. This study examined whether this algorithm can be used in particle identification. If it does, can it outperform the traditional texture analysis methods such as Discrete wavelet transform or co-occurrence matrix. Different parameters such as walk’s memory size, size of image samples, different inputting vectors and different classifiers were compared.

The DTW algorithm showed promising result compared to traditional texture extraction methods: discrete wavelet transform and co-occurrence matrix. The DTW method offers a higher identification accuracy and a simple feature vector. A conclusion can be drawn that the DTW method is suited for particle identification and can be put into practical use in condition monitoring systems.

This paper combined DTW algorithm with wear particle identification problem.

The purpose of this paper is to propose a novel non-probabilistic reliability-based topology optimization (NRBTO) method for continuum structural design under interval uncertainties of load and material parameters based on the technology of 3D printing or additive manufacturing.

First, the uncertainty quantification analysis is accomplished by interval Taylor extension to determine boundary rules of concerned displacement responses. Based on the interval interference theory, a novel reliability index, named as the optimization feature distance, is then introduced to construct non-probabilistic reliability constraints. To circumvent convergence difficulties in solving large-scale variable optimization problems, the gradient-based method of moving asymptotes is also used, in which the sensitivity expressions of the present reliability measurements with respect to design variables are deduced by combination of the adjoint vector scheme and interval mathematics.

The main findings of this paper should lie in that new non-probabilistic reliability index, i.e. the optimization feature distance which is defined and further incorporated in continuum topology optimization issues. Besides, a novel concurrent design strategy under consideration of macro-micro integration is presented by using the developed RBTO methodology.

Uncertainty propagation analysis based on the interval Taylor extension method is conducted. Novel reliability index of the optimization feature distance is defined. Expressions of the adjoint vectors between interval bounds of displacement responses and the relative density are deduced. New NRBTO method subjected to continuum structures is developed and further solved by MMA algorithms.

This research aimed to examine the current status of artificial intelligence's (AI's) integration into Chinese adult education, by analyzing the influences that AI has had on current adult education practices in China and by discussing the opportunities and challenges that adult education in China is faced with under the rapid AI development in the past 12 years.

This research employed systematic literature analysis. CNKI (China National Knowledge Infrastructure) Chinese Journals Full-text Database was used to collect scholarly publications on the use of AI in adult education in China that was published in the past decade. Data analysis included the following steps: identifying key words and phrases, detecting underlying meanings, searching for logical connections and relationships, collecting and connecting evidence to the research questions, and drawing logical and credible conclusions.

The findings indicated that AI has been gradually integrated into Chinese adult education through innovations and explorations and AI's influence is broad and profound. More specifically, the following five main themes were identified. The field's understanding of AI technology and AI's influence on adult education has evolved and become more comprehensive; AI challenges traditional Chinese adult education practices by helping to actualize personalized learning and precision education; AI transforms adult learning resource development; AI helps to turn learning environment into an open intelligent learning system; and lastly, AI urges the shift of adult educator's role in adult learning.

This study is not without limitations. Contextualized in China, this study shares the limitations with other single country studies. One such limitation is “cumulation” issue. This study should be replicated in other country contexts to further validate the generalizability of the five main themes identified in this research.

The five themes identified in this study can help understand the promises and challenges that AI brings to the field of adult education in China. These five themes can also serve as an integrated lens through which one can make sense of AI's integration into other countries' adult education practices.

This paper fulfills an identified need of understanding the current status of AI's integration into and influence on the field of adult education in China.

The purpose of this paper is to focus on the influences of dynamic capability on breakthrough innovation and explores the essential mechanisms related to such influence. The impact of breakthrough innovation on organizational performance is also examined in conjunction with the manufacturing industry samples in China.

This paper follows an empirical design. Data are collected from a survey administered to manufacturing samples in China. Regression analysis is used to test the hypothesis.

Results show that the positive impact of breakthrough innovation on organization performance is verified. Technological breakthrough innovation affects both the organization’s financial performance and growth performance in a linear and positive way, while market breakthrough innovation affects organization performance positively with marginal increments.

This paper uses data of manufacturing industry of China, hence, an extended survey in depth and width is worthy of future investigation. In addition, more unique predisposing factors on breakthrough innovation should be considered in the context of China.

The research enriches the understanding of how the dynamic capability affects the enterprise’s breakthrough innovation, which helps entrepreneurs understand how to strategize to build dynamic capability during breakthrough innovation decisions and implementations.

Dynamic capability is uniquely viewed as a multi-dimensional concept from a perspective of modularity, while breakthrough innovation is composed of two constructs. It not only enriches the understanding of how dynamic capability affects breakthrough innovation but also discovers the non-linear impact of breakthrough innovation on enterprise’s organizational performance in the context of China’s manufacturing industry.