Tonghai Wu

A New On-Line Visual Ferrograph

An on-line visual ferrograph (OLVF) characterized by direct reading and on-line analysis was developed based on magnetic deposition and image analysis. A digital sensor was integrated with a CMOS image sensor to obtain images of deposited wear debris under illumination conditions. An electromagnetic instrument was designed to deposit the wear debris flowing through an oil flow channel. The oil flow channel, fixed on the electromagnet, was arranged parallel to the magnetic flux in the air gap between two electromagnet poles. The deposition effect on wear debris was analyzed theoretically. The result shows that the wear debris in different sizes can be deposited in the same zone by controlling the oil flow rate and magnet field intensity. Corresponding application software for image sampling and processing was developed. An index of relative wear debris concentration, IPCA (Index of Particle Coverage Area), is given as an output in addition to wear debris images. Finally, two kinds of experiments were specified to assess the effect and validity of the OLVF. The results show that the OLVF has effective deposition and identification for both relatively large and small wear debris with rational control parameters. The validity examinations with the commercial particle quantifier (PQ) and direct reading ferrograph (DR) show that the OLVF has an approaching trend to the reference instruments in both heavily and lightly contaminated oil.

Image enhancement using the averaging histogram equalization (AVHEQ) approach for contrast improvement and brightness preservation

Display Omitted A histogram equalization method is proposed to preserve original image brightness.A histogram averaging technique is developed to recover image information lost.A histogram remapping technique is used to reduce artifacts introduced to images.An optimization minimizes the brightness change between input and output images.Results show that image brightness is preserved while image contrast is enhanced. Image contrast enhancement and brightness preservation are fundamental requirements for many vision based applications. However, these are two conflicting objectives when the image is processed by histogram equalization approaches. Current available methods may not provide results simultaneously satisfying both requirements. In this work, a pipelined approach including color channel stretching, histogram averaging and re-mapping is developed. By using stretching, color information from a scene is restored. Averaging against a uniform distribution enables the output image to recover the information lost. Furthermore, histogram re-mapping reduces artifacts that often arise from the equalization procedure. The technique also employs a search process to find optimal algorithmic parameters, such that the mean brightness difference between the input and output images is minimized. The effectiveness of the proposed method was tested with a set of images captured in adverse environments and compared against available methods. High performing qualitative and quantitative results were obtained.

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.

Journal Bearing Wear Monitoring via On-Line Visual Ferrography

Wear condition of journal bearing was experimentally monitored with an On-Line Visual Ferrograph (OLVF) system. The round bearing was made of 45# steel with babbitt alloy bushing and the bearing journal was made of 45# steel. High stress of the water content of 0%,1%,3% in lubricant, 10 times of a normal load of 2200 N, and the rotating speeds at 500, 1000, 2000 rpm were adopted in accelerated experiment. A quantitative index of particle coverage area (IPCA) together with wear debris ferro-image was used to characterize wear degree and wear mechanisms. Three wear stages with corresponding wear debris ferro-images were identified from IPCA variations characterized by bathtub curve trend. The first one was running-in stage characterized by the highest wear debris producing rate and higher large debris content. The second one was normal wear stage characterized by the lowest wear debris producing rate and small normal debris. The final one was failure initiation stage characterized by higher wear debris producing rate and higher large debris content. The corresponding dominant wear mechanisms were micro-ploughing and micro–cutting induced by rough initial surfaces in the running-in stage, local rub due to vibration in the normal stage, and fatigue and abrasive wear in the failure initiation stage.

Image contrast enhancement with brightness preservation using an optimal gamma correction and weighted sum approach

The enhancement of image contrast and preservation of image brightness are two important but conflicting objectives in image restoration. Previous attempts based on linear histogram equalization had achieved contrast enhancement, but exact preservation of brightness was not accomplished. A new perspective is taken here to provide balanced performance of contrast enhancement and brightness preservation simultaneously by casting the quest of such solution to an optimization problem. Specifically, the non-linear gamma correction method is adopted to enhance the contrast, while a weighted sum approach is employed for brightness preservation. In addition, the efficient golden search algorithm is exploited to determine the required optimal parameters to produce the enhanced images. Experiments are conducted on natural colour images captured under various indoor, outdoor and illumination conditions. Results have shown that the proposed method outperforms currently available methods in contrast to enhancement and brightness preservation.

Wear Characterization by an On-Line Ferrograph Image:

Wear characterization with ferrography is an effective off-line method for monitoring a machines wear condition. The new challenge of real-time wear reporting appeared in condition-based maintenances. Newly developed on-line technologies focus on wear debris concentration rather than on ferrograph images. However, wear rate and wear mechanism are two necessary aspects in describing the wear condition. An on-line ferrograph image provided by an on-line visual ferrograph sensor gives a new solution. By analysing the features of an on-line ferrograph image, new wear characterization with rapid and statistical analysis was investigated for on-line wear reporting. The focus of this method is wear debris chains rather than single wear debris as focused on in traditional ferrography. First, an on-line ferrograph image is preprocessed into a binary image with improved quality. Then the binary image is transformed into a projection curve by parallel radon transformation. The low-frequency component characterizing wear debris chains is extracted from the projection curve by wavelet transformation, which shifts the focus on wear debris chains other than single wear debris. Spectrum analysis is performed to extract the wear characteristics from the low-frequency component of the projection curve. As the main result, two statistical indexes are constructed, as value of point to point and equivalent diameter of larger wear debris, representing the statistical wear debris concentration and the equivalent diameter of larger wear debris, respectively. The indexes correspond qualitatively to wear rate and wear mechanism, respectively. The method was further examined with on-line images from the bench tests of the Eaton engine and the gear reducer of the mine scraper conveyor. The results show that the indexes are effective and independent in describing wear condition, which are promising prospects for on-line wear monitoring with ferrography.

Histogram equalization and optimal profile compression based approach for colour image enhancement

Display Omitted A pipeline approach to increase contrast and restore vividness to colour images.Pre-processing procedures include colour stretching, and histogram equalization.A magnitude compression and a saturation maximization stage as post processing.Image content based feedback provides optimal compression to reduce artefacts.Comprehensive assessment shows improvements on contrast and colour vividness. Many vision based applications depend on images with sufficiently high contrast and colourfulness so that ample amount of information is available to accurately describe objects captured in an image scene. Poor image capturing conditions are often unavoidable but can be compensated. Approaches based on intensity histogram equalization are popular to increase the information content within an image but over-enhancement often results in the production of unwanted artefacts. Furthermore, when constrained to only an intensity-based enhancement, insufficient enrichment on colourfulness and saturation is often observed. In order to address these limitations concurrently, a pipelined approach that incorporates a colour channel stretching process, a histogram equalization step, a magnitude compression procedure, and a saturation maximization stage is proposed. Quantitative and qualitative results obtained from experiments on a wide variety of natural scene images demonstrate the effectiveness of the proposed approach over other methods at reducing artefact while increasing image contrast and colourfulness.

A wavelet-analysis-based differential method for engine wear monitoring via on-line visual ferrograph

Wear over time affects engine’s reliability and efficiency. On-line wear monitoring could provide timely information about engine health condition. In the current study, on-line monitoring of engine wear via an on-line visual ferrograph was performed in reliability tests of gasoline engines, and a wavelet-analysis-based differential method of data analysis for wear condition estimation was proposed. The tests were designed for 220 h, which consist of a running-in stage of 20 h and a thermal shock cycle test stage of 200 h. One of the tests was terminated because of failures in the main bearings and crankshaft journal at 146th hour of thermal shock cycle test, while the other two completed successfully without failures. Index of particle coverage area, which represents wear-debris concentration in lube oil, was studied, and piecewise trend-extraction of index of particle coverage area was achieved by wavelet decomposition and reconstruction. The first-order differential of the index of particle coverage area trend was used to represent the wear rate or the generation rate of debris for health condition assessment of engines. Off-line oil analyses were performed in laboratory via an analytical ferrograph, and engine disassembly results of the engines were given to determine the causes of engine failures if it happened. It is found that favorable trend extraction from index of particle coverage area could be achieved by the segmented wavelet de-noising. Moreover, on-line visual ferrograph monitoring estimated the engine wear at macro-levels effectively, and it provided an advance warning for the failures after the continued deterioration of the engine wear. The study and application of this method can make early failure prediction of engine and avoid serious fault.

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.