Yeping Peng

Description of Wear Debris from On-Line Ferrograph Images by Their Statistical Color

Analytical ferrography has been proved to be one of the most popular methods for wear characterization. However, it is limited by the real-time requirement of condition-based monitoring. A new wear characterization by on-line ferrograph images is proposed. The color of wear debris was studied based on an on-line visual ferrograph (OLVF) sensor. Generally, the features of on-line ferrograph images included low resolution, high contamination, and wear debris chains. The weak color of the wear debris, especially nonferrous metal debris, in an on-line ferrograph image was unavoidably merged into the mass noises. Accordingly, the on-line images were converted from the initial red, green, blue (RGB) format into hue, saturation, intensity (HSI) for the description of color images. The transmitted image was binarized to locate all wear debris and the wear debris was extracted by their pixels from the corresponding reflected image. The distributions of two HSI components, hue and intensity, were used to characterize the color of on-line ferrograph images. Aiming at the global noise induced by uneven light during sampling, the distributions of the hue and intensity of the wear debris were subtracted by that of the reflected image. As a result, the statistical colors of wear debris were extracted with the hue and intensity from the on-line ferrograph images. A designed experiment with manually prepared oil samples revealed that the wear debris of three common metals could be well differentiated according to their colors via the on-line ferrograph images. The method provides a primary exploration on describing the color of wear debris by on-line ferrograph images.

Motion-Blurred Particle Image Restoration for On-Line Wear Monitoring

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.

Watershed-Based Morphological Separation of Wear Debris Chains for On-Line Ferrograph Analysis

Abstract Separation and characterization of wear debris from ferrograph images are demanded for on-line analysis. However, particle overlapping issue associated with wear debris chains has markedly limited this technique due to the difficulty in effectively segmenting individual particles from the chains. To solve this bottleneck problem, studies were conducted in this paper to establish a practical method for wear debris separation for on-line analysis. Two conventional watershed approaches were attempted. Accordingly, distance-based transformation had a problem with oversegmentation, which led to overcounting of wear debris. Another method, by integrating the ultimate corrosion and condition expansion (UCCE), introduced boundary-offset errors that unavoidably affected the boundary identification between particles, while varying the corrosion scales and adopting a low-pass filtering method improved the UCCE with satisfactory results. Finally, together with a termination criterion, an automatic identification process was applied with real on-line wear debris images sampled from a mineral scraper gearbox. With the satisfactory separation result, several parameters for characterization were extracted and some statistics were constructed to obtain an overall evaluation of existing particles. The proposed method shows a promising prospect in on-line wear monitoring with deep insight into wear mechanism.

Morphological Feature Extraction Based on Multiview Images for Wear Debris Analysis in On-line Fluid Monitoring

ABSTRACT Wear state is an important indicator of machinery operation condition that reveals whether faults have developed and maintenance should be scheduled. Among the available techniques, vision-based on-line monitoring of wear particles in the lubricant circuit is preferred, where three-dimensional particle characterizations can be obtained for wear mode analysis. This article presents the application of an imaging system that captures wear particles in lubricant flow and the development of image processing procedures for multiview feature extraction. In particular, a framework including background subtraction, object segmentation, and debris tracking was adopted. Particle features were then used in a comprehensive morphological description of wear debris. Experiments showed that the system is able to produce a feasible and reliable indication of wear debris characteristics for machine condition monitoring.

Intelligent identification of wear mechanism via on-line ferrograph images

Condition based maintenance(CBM) issues a new challenge of real-time monitoring for machine health maintenance. Wear state monitoring becomes the bottle-neck of CBM due to the lack of on-line information acquiring means. The wear mechanism judgment with characteristic wear debris has been widely adopted in off-line wear analysis; however, on-line wear mechanism characterization remains a big problem. In this paper, the wear mechanism identification via on-line ferrograph images is studied. To obtain isolated wear debris in an on-line ferrograph image, the deposition mechanism of wear debris in on-line ferrograph sensor is studied. The study result shows wear debris chain is the main morphology due to local magnetic field around the deposited wear debris. Accordingly, an improved sampling route for on-line wear debris deposition is designed with focus on the self-adjustment deposition time. As a result, isolated wear debris can be obtained in an on-line image, which facilitates the feature extraction of characteristic wear debris. By referring to the knowledge of analytical ferrograph, four dimensionless morphological features, including equivalent dimension, length-width ratio, shape factor, and contour fractal dimension of characteristic wear debris are extracted for distinguishing four typical wear mechanisms including normal, cutting, fatigue, and severe sliding wear. Furthermore, a feed-forward neural network is adopted to construct an automatic wear mechanism identification model. By training with the samples from analytical ferrograph, the model might identify some typical characteristic wear debris in an on-line ferrograph image. This paper performs a meaningful exploratory for on-line wear mechanism analysis, and the obtained results will provide a feasible way for on-line wear state monitoring.

A microfluidic device for three-dimensional wear debris imaging in online condition monitoring

Three-dimensional morphologies of wear particles are important information sources for machine condition assessment and fault diagnosis. However, existing three-dimensional image acquisition systems, such as laser scanning confocal microscopy and atomic force microscopy, cannot be directly applied in condition-based maintenance of machines. In order to automatically acquire three-dimensional information of wear debris for online condition monitoring, a microfluidic device consisting of an oil flow channel and a video imaging system is developed. This paper focuses on the control of particle motions. A microchannel is designed to ensure the continuous rotation of particles such that their three-dimensional features can be captured. The relationships between running torque and channel height and particle size are analysed to determine the channel height. An infinite fluid field is considered to make sure that the particles rotate around the same axis to capture 360 degree views. Based on this, the cross section of the microchannel is determined at 5 mm × 0.2 mm (height × width) to capture the wear debris under 200 µm. A CMOS sensor is used to image the particles in multiple views and then three-dimensional features of wear debris (e.g. thickness, height aspect ratio and sphericity) are obtained. Two experiments were carried out to evaluate the performances of the designed system. The results demonstrate that (1) the microfluidic device is effective in capturing multiple view images of wear particles various in sizes and shapes; (2) spatial morphological characteristics of wear particles can be constructed using a sequence of multi-view images.

Dimensional description of on-line wear debris images for wear characterization

As one of the most wear monitoring indicator, dimensional feature of individual particles has been studied mostly focusing on off-line analytical ferrograph. Recent development in on-line wear monitoring with wear debris images shows that merely wear debris concentration has been extracted from on-line ferrograph images. It remains a bottleneck of obtaining the dimension of on-line particles due to the low resolution, high contamination and particle’s chain pattern of an on-line image sample. In this work, statistical dimension of wear debris in on-line ferrograph images is investigated. A two-step procedure is proposed as follows. First, an on-line ferrograph image is decomposed into four component images with different frequencies. By doing this, the size of each component image is reduced by one fourth, which will increase the efficiency of subsequent processing. The low-frequency image is used for extracting the area of wear debris, and the high-frequency image is adopted for extracting contour. Second, a statistical equivalent circle dimension is constructed by equaling the overall wear debris in the image into equivalent circles referring to the extracted total area and premeter of overall wear debris. The equivalent circle dimension, reflecting the statistical dimension of larger wear debris in an on-line image, is verified by manual measurement. Consequently, two preliminary applications are carried out in gasoline engine bench tests of durability and running-in. Evidently, the equivalent circle dimension, together with the previously developed concentration index, index of particle coverage area (IPCA), show good performances in characterizing engine wear conditions. The proposed dimensional indicator provides a new statistical feature of on-line wear particles for on-line wear monitoring. The new dimensional feature conveys profound information about wear severity.

Single-scale center-surround Retinex based restoration of low-illumination images with edge enhancement

Restoring images captured under low-illuminations is an essential front-end process for most image based applications. The Center-Surround Retinex algorithm has been a popular approach employed to improve image brightness. However, this algorithm in its basic form, is known to produce color degradations. In order to mitigate this problem, here the Single-Scale Retinex algorithm is modified as an edge extractor while illumination is recovered through a non-linear intensity mapping stage. The derived edges are then integrated with the mapped image to produce the enhanced output. Furthermore, in reducing color distortion, the process is conducted in the magnitude sorted domain instead of the conventional Red-Green-Blue (RGB) color channels. Experimental results had shown that improvements with regard to mean brightness, colorfulness, saturation, and information content can be obtained.

Oscillatory Particle Swarm Optimizer

Abstract The Particle Swarm Optimization (PSO) algorithm is an attractive meta-heuristic approach for difficult optimization problems. It is able to produce satisfactory results when classical analytic methods cannot be applied. However, the design of PSO was usually based on ad-hoc attempts and its behavior could not be exactly specified. In this work, we propose to drive particle into oscillatory trajectories such that the search space can be covered more completely. A difference equation based analysis is conducted to reveal conditions that guarantee trajectory oscillation and solution convergence. The settings of cognitive and social learning factors and the inertia weight are then determined. In addition, a new strategy in directing these parameters to follow a linearly decreasing profile with a perturbation is formulated. Experiments on function optimizations are conducted and compared to currently available methods. Results have confirmed that the proposed Oscillatory Particle Swarm Optimizer (OSC-PSO) outperforms other recent PSO algorithms using adaptive inertia weights.

Man-Machine Interaction for an Unmanned Tower Crane Using Wireless Multi-Controller

Operator cab is one of the important components of a tower crane, which is used to obtain sufficient quality feedback information from tower crane and ground observers. However, there are two main drawbacks of the tower crane system, low efficiency and labor costs, because the tower crane need to work with the assistance of the ground observers. In particular, the work environment of the cap operators is extremely bad and dangerous. In order to reduce the manual intervention and increase the efficiency of the tower crane, this paper presents a man-machine interaction for an unmanned tower crane using wireless multi-controller. Images of the crane cab are captured by cameras and then are coded and transmitted to wireless controllers and a server terminal through wireless local area network (WLAN). In this stage, the programmable logic controller (PLC) is used as a tower crane controller to collect sensor data. The data is also transmitted to the wireless controllers and the server terminal through WLAN. In addition, control parameters are transmitted to the server terminal and the tower crane controller via wireless controller transmission. After that, the tower crane controllers obtain the control commands and then perform them. Finally, testing results indicate that the unmanned tower crane is effective when it works with the man-machine interaction.