On-line images of wear debris contain important information for real-time condition monitoring, and a dynamic imaging technique can eliminate particle overlaps commonly found in static images, for instance, acquired using ferrography. However, dynamic wear debris images captured in a running machine are unavoidably blurred because the particles in lubricant are in motion. Hence, it is difficult to acquire reliable images of wear debris with an adequate resolution for particle feature extraction. In order to obtain sharp wear particle images, an image processing approach is proposed. Blurred particles were firstly separated from the static background by utilizing a background subtraction method. Second, the point spread function was estimated using power cepstrum to determine the blur direction and length. Then, the Wiener filter algorithm was adopted to perform image restoration to improve the image quality. Finally, experiments were conducted with a large number of dynamic particle images to validate the effectiveness of the proposed method and the performance of the approach was also evaluated. This study provides a new practical approach to acquire clear images for on-line wear monitoring.

Since wear particles usually contain valuable information about lubricant and wear condition of lubricated components, wear debris analysis is widely used to monitor machine/component wear. Current literature reports about the importance and necessity of 3-dimensional (3D) surface characterization of wear particles as opposed to 2D characterization. It may be borne in mind that traditional 3D analysis has been a synonym only for local surface morphologies for stationary particles. This results in large errors when irregular particles are under observation. A new 3D imaging methodology is proposed to reconstruct multi-view 3D surfaces for a moving particle whereby the target particle is passed through a micro-channel with rolling motion, and recorded via a digital microscope. The multiple moving particles are tracked based on Kalman filter to obtain different-view images. Sparse and dense reconstruction of the particle surfaces are enabled by these images using Structure from Motion (SfM) and Shape from Shading (SfS) methodologies, respectively. The method was verified using real particles and evaluated by the results of Laser Scanning Confocal Microscopy. The proposed method is able to reconstruct wear particles under various perspectives, and the errors from the characterization parameters of the Areal are less than 20%.

Because wear is one of the most typical causes of decreasing performance in running machines, monitoring wear is regarded as a crucial technology in maintaining the health of machines. However, monitoring wear is not a fully mature process because quantifying the development of wear in real time is a challenging task because there is no universal indicator. To meet this need, wear-oriented dynamic modeling with online ferrographic images was used to investigate and then describe a real-time wear state. This investigation was carried out by combining three wear indices to describe the wear rate, the wear mechanism, and the severity of wear. A binary classifier method is also proposed to classify these wear stages in the three extracted indices. A strategy to identify the dynamic transition of wear states with adaptive parameters is also developed and then a four-ball wear test is carried out to verify the method. The results indicate that this modeling strategy can accurately identify a developing wear state that is characterized by stages. This proposed method is better at monitoring the health evolution of a machine system than just detecting faults.

Wear debris analysis (WDA) enables the provision of essential information towards the monitoring of machine fault diagnosis and the analysis of wear mechanism. However, this experience-based technology has not yet been automated for the identification of similar particle types due to the small number of samples and highly dispersed features. To address this problem, a knowledge-guided convolutional neural network model is developed to focus on two representative severe wear particles: fatigue and severe sliding particles that have highly similar contours but weakly discriminative surfaces. The height images of particle surfaces are adopted as the initial objective. Characterized by typical particle features, the empirical WDA knowledge is represented into the feature-marked images, and further automatically learned by a U-Net-based knowledge extraction network. By weighting with the U-Net output, a knowledge-guided particle classification network is constructed to identify similar particles under a small number of samples. With this methodology, the empirical WDA knowledge is transferred to guide the classification network for locating the discriminative features in particle height images. Thirty sets of fatigue and severe sliding particles are acquired from wear tests as the training and testing samples. For verification, the network kernel is visualized to trace the particle feature propagation in the classification. Experimental results reveal that the proposed method can accurately identify fault particles that are acquired from wear tests.