Appearance Inspection Research Articles

Predictive Analytics of In‐Service Bridge Structural Performance from SHM Data Mining Perspective: A Case Study

In‐service bridge structural performance analysis and prediction are usually complicated and challenging because of many unknown and uncertain factors. Contrary to the traditional structural appearance inspections and load tests, structural health monitoring (SHM) can provide a perspective for online analysis, prediction, and early warning. So far, SHM has been widely used in many bridge structures, and a lot of bridge SHM data have also been collected. However, the existing studies usually focus on some independent and unsystematic analysis methods, which are hard to use widely in engineering applications to reveal the overall structural performance. This study focuses on the structural performance analysis and prediction of the highway in‐service bridge. The dynamic problems in bridge SHM are pointed out firstly, followed by a detailed analysis about the characteristics of bridge SHM data. With the consideration of different characteristics, three targeted analysis methods are proposed. An urban concrete‐filled steel tube (CFST) truss girder bridge (opened to traffic in 1995) is also presented, which once experienced some prominent vibration problems. The bridge SHM system is designed and stalled after several appearance inspections, load tests, and some reinforcement measures. The data mining methods proposed (distribution function, association analysis, and time‐series analysis) are employed for the analysis and prediction of structural response and deterioration extent. This study can provide some references for maintenance and management and can also build a foundation for further online analysis and early warning.

Study on wind turbine blade defect detection system based on imaging array

Currently in the process of wind farm inspection, wind turbine blade appearance inspection mainly adopts the telescope or high-definition cameras, low detection efficiency, labor intensity and the precision is limited, in order to solve this problem, a kind of wind turbine blades defect recognition system based on image array is proposed. Through the joint of array camera and image processing server, the functions of the image acquisition, processing, and defect recognition and detection results output are implemented. The software of artificial intelligence deep learning based on neural network algorithm is used to identify the defects of blade image, and output quality analysis report, to realize automatic detection of wind turbine blade surface defect. The field measurement results show that the system greatly improves the efficiency and accuracy of wind turbine blade defect detection.

4. Machine Vision for Appearance Inspection

4. Machine Vision for Appearance Inspection

Analysis of the effect of fretting wear on key structural components of TB6 titanium alloy with actual failure cases

As the main metal structure materials, titanium alloys have been widely applied in aerospace and other military industries. Titanium alloy develops on the way of high performance and functionalization. Compared with other materials, titanium alloy has high surface integrity and high fretting damage sensitivity. In this paper, the failure case of TB6 high strength titanium alloy key structural parts is taken as the breakthrough point to analyze the effect of surface fretting wear damage on its performance. The appearance inspection, macro and micro morphology observation and energy spectrum analysis were carried out, and the microstructure examination and hardness test were also adopted. The results showed that the fracture property of lug of TB6 high strength titanium alloy was fatigue fracture, and the fretting wear damage of the inner surface of lug hole was the main reason for the fatigue crack initiation. This case is a typical example of titanium alloy structure failure due to fretting wear, which provides reference for the prevention of the recurrence of such faults.

Application of diffractive elements for improving the efficiency of systems for cylindrical surface inspection

An improved method of structural lighting for increasing the efficiency of inspection of the cylindrical object surface appearance is considered. The method is based on using a diffractive optical element to reduce the amount of recorded data due to illuminating the test object at an angle to the image recording plane, which is normal to the inspected surface. Implementation of the proposed method implies the use of several identical channels. For this reason, one channel is considered in the present study. Calculations of diffractive elements, a description of the experimental setup, and results of experiments aimed at determining the depth of surface defects on objects simulating fuel pellets and fuel elements are presented. Implementation of the investigated method with defect depth determination in industrial systems of inspection of fuel pellets and fuel elements is expected to improve the quality of the fuel for atomic power stations.

Research on bridge appearance inspection technology and engineering application based on multi-rotor UAV

Research on bridge appearance inspection technology and engineering application based on multi-rotor UAV

Automated prediction of sensory scores for color and appearance in canned black beans (Phaseolus vulgaris L.) using machine vision

ABSTRACTEvaluation of canning quality of beans is commonly carried out by simple visual inspection that is time-consuming, resource intensive, and biased by the experience of the panelist. Moreover, there is not a standard scale to rate visual quality traits of canned beans. In this research, a machine vision system was implemented and tested for automatic inspection of color (COL) and appearance (APP) in canned black beans. Various color and textural image features (average, standard deviation, contrast, correlation, energy, and homogeneity from red, green, blue, lightness, red/green, yellow/blue, hue, saturation and value color scales) were extracted from beans and brine images, and evaluated to predict the quality rates for COL and APP of a group of bean panelists using multivariate statistics. Sixty-nine commercial canned black bean samples from different brands and markets were used for analysis. In spite of the “fair” agreement among the sensory panelists for COL and APP, as determined by multi-rater Kappa analysis, machine vision data based on partial least squares regression model showed high predictive performance for both COL and APP with correlation coefficients of 0.937 and 0.871, and standard errors of 0.26 and 0.38, respectively. When a classification was performed based on both COL and APP traits, a support vector machine model was able to sort the samples into two sensory quality categories of “acceptable” and “unacceptable” with an accuracy of 89.7%. Using simple color and texture image data, a machine vision system showed potential for the automatic evaluation of canned black beans by COL and/or appearance as a professional visual inspection.

Clinical evaluation in orbital tumors

SummaryThe ocular examination should include the best‐corrected visual acuity and intraocular pressure. A neuro‐ophthalmologic examination, including motor and sensory functions, pupillary examination should also be done. During biomicroscopy, the integrity of the corneal and conjunctiva should be checked. Fully dilated indirect ophthalmoscopy should be performed because many orbital diseases cause a wide variety of fundunscopic changes. The major fundal manifestations of a space‐occupying mass in the orbit include retinal folds, retinal vascular changes and optic disk edema and/or atrophyThe external examination of the patient should assess the facial features and critically evaluate the symmetry of ocular, eyelid, and orbital structures. Physical examination of the periorbital structures should include inspection of appearance and function, which are commonly altered by a space‐occupying lesion in the orbit. The most important structural feature to rate in the examination of an orbit is proptosis, which is also known as exophthalmos, protrusion, or the displacement of the globe beyond the orbital rim. The position of the visual axis in a proptotic eye may provide useful information.

Quantitative Appearance Inspection for Film Coated Tablets.

The decision criteria for the physical appearance of pharmaceutical products are subjective and qualitative means of evaluation that are based entirely on human interpretation. In this study, we have developed a comprehensive method for the quantitative analysis of the physical appearance of film coated tablets. Three different kinds of film coated tablets with considerable differences in their physical appearances were manufactured as models, and their surface roughness, contact angle, color measurements and physicochemical properties were investigated as potential characteristics for the quantitative analysis of their physical appearance. All of these characteristics were useful for the quantitative evaluation of the physical appearances of the tablets, and could potentially be used to establish decision criteria to assess the quality of tablets. In particular, the analysis of the surface roughness and film coating properties of the tablets by terahertz spectroscopy allowed for an effective evaluation of the tablets' properties. These results indicated the possibility of inspecting the appearance of tablets during the film coating process.

432 対象の姿勢に依存しない形状特徴量を用いた外観検査(GS4-4 センシング・欠陥検出)

432 対象の姿勢に依存しない形状特徴量を用いた外観検査(GS4-4 センシング・欠陥検出)

Visual dating of rockfall scars in Larix decidua trees

Dating past mass wasting with growth disturbances in trees is widely used in geochronology as the approach may yield dates of past process activity with up to subannual precision. Past work commonly focused on the extraction of increment cores, wedges, or stem cross sections. However, sampling has been shown to be constrained by sampling permissions, and the analysis of tree-ring samples requires considerable temporal efforts. To compensate for these shortcomings, we explore the potential of visual inspection of wound appearance for dating purposes. Based on a data set of 217 wood-penetrating wounds of known age inflicted to European larch (Larix decidua Mill.) by rockfall activity, we develop guidelines for the visual, noninvasive dating of wounds including (i) the counting of bark rings, (ii) a visual assessment of exposed wood and wound bark characteristics (such as the color and weathering status of wounds), and (iii) the relationship between wound age and tree diameter. A characterization of wounds based on photographs, randomly selected from the data set, reveals that young wounds typically can be dated with high precision, whereas dating errors gradually increase with increasing wound age. While visual dating does not reach the precision of dendrochronological dating, we clearly demonstrate that spatial patterns of and differences in rockfall activity can be reconstructed with both approaches. The introduction of visual dating approaches will facilitate fieldwork, especially in applied research, assist the conventional interpretation of tree-ring signals, and allow the reconstruction of geomorphic processes with considerably fewer temporal and financial efforts.

平判外観品質検査装置の開発

近年，どの産業分野においても，製品の安価化と品質要求の高度化が求められている。JFE電制株式会社ではこれらに対応するために，幾多の品質検査装置を開発し納入してきた。今回，製紙工場の仕上げライン向けに，積層紙の“折れ”“飛び出し・不揃い”“紙粉”の検査を行う装置の開発を行い実用化した。“折れ”の検出は，照明とカメラの配置に工夫を行い，折れ部が周囲よりも明るく輝く画像が撮影できるようにして，確実な検出を実現している。“飛び出し・不揃い”の検出では，レーザーマーカを利用した光切断法を採用することにより，飛び出しの位置・量を正確に把握できるようにした。また“紙粉”検査では，その形態より「毛羽立ち」と「粒」に分類し，毛羽立ちは存在することによって生じる模様を画像処理のテクスチャー解析を用いて面の状態を定量化し，粒は照明の照射方向から生じる特性を利用して正確に粒を抽出し面積の大小を評価した。開発した技術を用いた外観品質検査装置を，小判リーム用4ラインと大判スキッド用2ラインに納入し稼動している。いずれの装置も要員効率化と不良品流出防止の観点から，高い評価を受けている。これらの装置は“折れ”“飛び出し・不揃い”“紙粉”の不良を検出するようになっているが，今後は確立した検出技術や実機化の過程で得られた様々なノウハウをベースに，検出項目を絞ったより簡易な装置の提供を検討している。

The Effects of Additives on the Properties of Non-Cyanide Electroless Gold Plating Deposition

In order to improve the non-cyanide electroless gold plating deposition performance, the effects of the kinds of additives as well as its concentration on the deposition performance were investigated. The appearance inspection, deposition rate, adhesive force, surface morphology and corrosion resistance were evaluated. The results showed that the introduction of appropriate additives did improve the coating properties. The optimal concentration of polyethylene glycol and polycrylamide were 0.6~1.0 g·L-1 and 1.0~1.5 g·L-1, respectively. The corrosion resistance of the coating deposited in baths containing polyacrylamide was best.

Research on the Detection of Focusing Mechanisms

Since focusing mechanisms is essential equipment, which could compensate the difference between adjustment environments and working conditions of space optics remote sensors, the detection of it is very important. Based on engineering practice, this paper firstly introduces the basic detection of focusing mechanisms, that is the appearance inspection and the boundary dimension inspection, and then introduces several common performance test projects, that is the detection of stroke, step length, gravity inclination, rock, and empty back and the test of modal, self-locking performance and closed-loop accuracy, and also introduces relative detection methods and cautions. At last it briefs other derivative detection projects.

Failure analysis on abnormal wall thinning of heat-transfer titanium tubes of condensers in nuclear power plant Part I: Corrosion and wear

Titanium tubes used in condensers in a nuclear power plant in China encountered abnormal wall thinning, and was thus forced to temporarily stop operation or it could bring about catastrophic safety problems. Most of the wall thinning happened at quite regular positions on the tubes and these failure tubes were located similarly in the condensers, indicating some common problems. To find out the root cause and mechanism of the thinning failure, we conducted surface deposit analysis, appearance inspection, microstructure analysis and composition analysis of the samples by means of X-ray diffraction (XRD), stereo microscope, scanning electron microscope (SEM) and Energy Dispersive Spectrometer (EDS). The results revealed that the wall thinning was primarily caused by eccentric contact wear and three-body contact wear rooted in processing defect of internal borings, corrosion products deposit and sagging, and foreign particles. Finally, countermeasures were proposed for repair and prevention.

Objective Evaluation of Woven Fabrics Using Optical Sensors

Fabric surface appearance is one of the most important visible properties of fabrics determining their price and consumer satisfaction. This characteristic is routinely evaluated with reference to a set of visual standards in the textile industry. The visual evaluation is unreliable, time-consuming, inefficient, and, depends on many human factors. Machine vision techniques can overcome these difficulties and evaluate the fabric surface with high precision and high speed. Application of machine vision to evaluate woven fabric appearance such as seersucker effect, repetition, uniformity, disorder, wrinkling, and quality of printed patterns needs a lighting system, an image capturing device, a computer, and appropriate software for data processing. This paper introduces some new quantitative analysis methods for fabric appearance inspection and addresses the development of optical devices in evaluating textural features. The gray-level co-occurrence matrix, spectral density function, angular power spectrum function, distance matching function, and, normalized cross-correlation are the most important algorithms used in this new method. The method developed in this work makes the rapid and exact inspection of fabric surface possible. Objective results from these new methods were compared with subjective ones from human experts. The correlation between texture analysis and subjective evaluation was acceptable at 95% confidence interval for all cases.

Existing Concrete Girder Bridges' Bending Stiffness Assessment Based on Crack Characteristics Parameters

A lot of existing reinforced concrete girder bridges appeared cracks in the service phase. Because of the beam's cracks existing, the sectional bending stiffness of the beam decreased. It would reduce the structure's bearing capacity, so the bridges' structure performance urgently needs to be assessed by effective methods, so as to study further measures. In this paper, based on the indoor model test results of four pieces of model beams, regression analysis of the crack characteristics parameters and test's load-displacement curves has been carried out. The relationship between crack characteristics parameters and girder bridge's bending stiffness has been established. The qualitative assessment of structure crack's appearance inspection is transmitted to quantitative assessment, so it will make the assessment more objective and scientific.

鏡面反射特性を有する物体に対応した逆光線追跡による3次元形状計測法

An appearance inspection is one of the most suitable applications of a laser rangefinder. In such a field, many products are designed by 3-D CAD. Therefore, the appearance inspection of products validates the deviation between the designed 3-D data and the measured 3-D data. There are a lot of products of specular objects with shiny surface such as polished metals and plastic materials. However, conventional triangulation-based rangefinders are known to be difficult to apply to the 3-D shape measurement of such shiny objects. In this study, we propose an advanced laser rangefinder to be able to obtain the 3-D shape of specular objects and apply the rangefinder to an appearance inspection system.

Study and Application of Homogeneous Rare Earth IR/NR Blends in Tread Compound of All-Steel TBR Tire

The homogeneous rare earth IR/NR blend applied in tread compound of all-steel TBR tire was investigated,and compare to Russian SKI-3, SKI-5/NR blends and NR.The results showed homogeneous rare earth IR/NR blend had similar vulcanization characteristics, dynamic mechanical properties and heat-aging resistance or even better. It was inspected that the appearance, balance, air bubbles, X-ray and homogeneity inspection test of the tires produced by homogeneous rare earth IR/NR blend by the tire factory,all the indicators were qualified. The tires passed the China National Quality Supervision and Inspection Center of rubber tire certification. The tires met the requirements of all-steel TBR tire.The homogeneous rare earth IR prepared by Petro China Jilin Petrochemical Company could 40 phr instead of NR using in tread compound of all-steel TBR tire,which could extend tire life and reduce tire material costs.

Damage inspection and performance evaluation of Jilin highway double-curved arch concrete bridge in China

Jilin highway concrete bridge is located in the center of Jilin City, which is positioned in the middle part in Jilin Province in the east north of China. This bridge crosses the Songhua River and connects the north and the south of Jilin City. The main purpose of damages inspection of the bridge components is to ensure the safety of a bridge and to identify any maintenance, repair, or strengthening which that need to be carried out. The damages that occur in reinforced concrete bridges include different types of cracks, scalling and spalling of concrete, corrosion of steel reinforcement, deformation, excessive deflection, and stain. The main objectives of this study are to inspect the appearance of Jilin highway concrete bridge and describe all the damages in the bridge structural members, and to evaluate the structural performance of the bridge structure under dead and live loads. The tests adopted in this study are: (a) the depth of concrete carbonation test, (b) compressive strength of concrete test, (c) corrosion of steel test, (d) static load test, and (e) dynamic load test. According to the damages inspection of the bridge structure appearance, most components of the bridge are in good conditions with the exception arch waves, spandrel arch, deck pavement of new arch bridge, and corbel of simply supported bridge which suffer from serious damages. Load tests results show that the deflection, strain, and cracks development satisfy the requirements of the standards.