检索结果-内蒙古大学图书馆

Modelling of the hole quality characteristics by Extreme Learning Machine in fiber laser drilling of Ti-6Al-4V

JOURNAL OF MANUFACTURING PROCESSES 2018年 36卷 138-148页

作者： Ay, Mustafa Firat Univ Fac Technol Dept Mechatron Engn TR-23119 Elazig Turkey

The hole circularity, taper angle, and spatter formation area at drilling Ti-6AI-4V alloys by fiber laser are the basic properties that determine the quality of the product. These properties are directly related to cutting parameters such as laser power, cutting speed and gas pressure. In this study, a total of 27 experiments were performed with different cut parameter combinations to provide sufficient data at the level at which the parameters could determine the effect on product quality. Spatter field formed in uncontrolled diffused and complex shapes during cutting were calculated using image processing technique. The data obtained as a result of the measurements were modeled by using a new modeling method called Extreme Learning Machine (ELM) based on Artificial Intelligence (AI) and Artificial Neural Networks (ANN) to predict hole diameter, taper angle and spatter forming area on the fiber laser drilled surface. The estimation models of ELM were compared with ANN models. When both methods are compared in terms of modeling performances of training and test phases, it is found that ELM method performs faster than ANN method and shows higher performance with smaller error margin. As a result, ELM method has been demonstrated to be able to be used safely to develop a prediction model for studies in a variety of manufacturing areas where a large number of experiments are required.

关键词： Extreme Learning Machine (ELM) model Artificial Neural Network (ANN) model image processing technique Ti-6Al-4V alloys Fiber laser drilling

来源：评论

学校读者我要写书评

暂无评论

Semantic crack-image identification framework for steel structures using atrous convolution-based Deeplabv3+Network

引用

SMART STRUCTURES AND SYSTEMS 2022年第1期30卷 17-34页

作者： Ta, Quoc-Bao Ngoc-Loi Dang Kim, Yoon-Chul Kam, Hyeon-Dong Kim, Jeong-Tae Pukyong Natl Univ Dept Ocean Engn Busan 48513 South Korea Mien Tay Construct Univ Urban Infrastruct Fac Vinh Long 890000 Vietnam Yonsei Univ Dept Civil & Environm Engn Seoul 03722 South Korea

For steel structures, fatigue cracks are critical damage induced by long-term cycle loading and distortion effects. Vision-based crack detection can be a solution to ensure structural integrity and performance by continuous monitoring and non-destructive assessment. A critical issue is to distinguish cracks from other features in captured images which possibly consist of complex backgrounds such as handwritings and marks, which were made to record crack patterns and lengths during periodic visual inspections. This study presents a parametric study on image-based crack identification for orthotropic steel bridge decks using captured images with complicated backgrounds. Firstly, a framework for vision-based crack segmentation using the atrous convolution-based Deeplapv3+ network (ACDN) is designed. Secondly, features on crack images are labeled to build three databanks by consideration of objects in the backgrounds. Thirdly, evaluation metrics computed from the trained ACDN models are utilized to evaluate the effects of obstacles on crack detection results. Finally, various training parameters, including image sizes, hyper-parameters, and the number of training images, are optimized for the ACDN model of crack detection. The result demonstrated that fatigue cracks could be identified by the trained ACDN models, and the accuracy of the crack-detection result was improved by optimizing the training parameters. It enables the applicability of the vision-based technique for early detecting tiny fatigue cracks in steel structures.

关键词： atrous convolution Deeplabv3+network fatigue crack image processing technique semantic segmentation steel structures

来源：评论

学校读者我要写书评

暂无评论

A study on visual features of leaves in plant identification using artificial intelligence techniques

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2019年 156卷 369-377页

作者： Yigit, Enes Sabanci, Kadir Toktas, Abdurrahim Kayabasi, Ahmet Karamanoglu Mehmetbey Univ Dept Elect Elect Engn Engn Fac TR-70100 Karaman Turkey

In this paper, artificial intelligence techniques (AIT) such as artificial neural network, naive bayes algorithm, random forest algorithm, K-nearest neighborhood (KNN) and support vector machine (SVM) are implemented to design an automatic identifier for the plant leaves. For this purpose, data of 637 healthy leaves consisting of 32 different plant species are used. 22 visual features (VF) of each leaf are extracted by using image processing techniques. These 22 VF are considered in 4 groups including dimension (D#6), color (C#6), texture (T#5) and pattern (P#5). In order to investigate the effects of these groups on the classifying performance, 15 possible different combinations from the 4 groups are constituted. The models are then trained via the data of 510 leaves, and their accuracy are tested through the data of 127 leaves. From the results of the test, SVM model with the accuracy of 92.91% is found to be the most successful identifier for combination including all groups. The next best result is achieved with the accuracy of 87.40% for the combination of D#6, C#6 and P#5 groups. Since the most important issue in the classification process is the use of the minimum number of VF, 16 most effective VF on the identification are determined by means of correlation-based feature selection (CFS) method. The best result for these 16 VF is also achieved with the accuracy of 94.49% by the SVM model. Then the performance of the proposed method is tested to identify the diseased and defected leaves. Therefore, 637 healthy and 33 diseased/defected leaves are put together. Randomly selected 536 leaves corresponding to 80% of all leaves are used for training and the remaining 134 leaves are used for testing, and identified with the accuracy of 92.53% by the SVM model. With this study, it is numerically revealed that the P#5 is the most effective feature group. Moreover, it has been determined that the most effective feature in the P#5 group is the feature of edge Fourier tra

关键词： Plant species Identification image processing technique Artificial intelligence techniques Fourier Transform

来源：评论

学校读者我要写书评

暂无评论

Atomic force microscopy and the mechanism of fatigue crack growth

引用

FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES 2001年第12期24卷 831-842页

作者： Jono, M Sugeta, A Uematsu, Y Osaka Univ Dept Mech & Syst Engn Suita Osaka 5650871 Japan

Fatigue crack test was performed using a grain-orientated 3% silicon iron under constant amplitude loading. Growth behaviour of the fatigue crack and slip deformation behaviour near the crack tip, were observed in detail by using an atomic force microscope. In the lower K region, only one preferential slip system of this material operated and the fatigue crack grew along that slip plane. It was found that constraint of slip deformation due to cyclic strain hardening resulted in crack arrest and crack branching. The fatigue crack grew in a zigzag manner as a result of such successive crack branching and deflection. In the high K region, two preferential slip systems operated simultaneously to an almost identical extent and the fatigue crack grew in a direction perpendicular to the loading axis. The slipping distance in one loading cycle was measured quantitatively by using the image processing technique and the crack growth mechanism is discussed.

关键词： atomic force microscope crack branching fatigue crack growth image processing technique microscopic observation mode I slip deformation 3% silicon iron

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization of Pneumatic Mixing Systems for Anaerobic Digesters: A Hybrid technique of Statistical Modeling and Numerical Simulations

引用

WASTE AND BIOMASS VALORIZATION 2022年第6期13卷 2815-2830页

作者： Mahmoodi-Eshkaftaki, Mahmood Rahmanian-Koushkaki, Hossein Jahrom Univ Dept Mech Engn Biosyst POB 74135-111 Jahrom Iran

Development a suitable mixing system for biogas plants is one of the most important factors to degrade organic matters in digesters. Therefore, pneumatic and mechanical mixing systems were integrated with their optimum conditions to produce a suitable strategy for mixing slurry. Pneumatic mixing parameters were investigated using computational fluid dynamics and image processing techniques. The mixing characteristics and biogas compounds were modeled according to biogas injection parameters, and integrated into the desirability function to determine the optimum conditions. The models indicated that for lower injection repetition in different injection positions, a higher mass flow rate was needed to improve the mixing characteristics and CH4 content. Optimization of these parameters showed that the best amounts of injection mass rate, injection pressure and injection repetition were 0.02 g/s, 2.84 bar and 3 times, respectively, and their optimum ranges were 0.015-0.028 g/s, 1.5-4.7 bar and 1-4 times. However, the best injection was injection through mixer and injection in floor of digester for 2 or 3 times in 24 h. From the optimum ranges, some amounts were investigated in the digesters using the computational fluid dynamics, and the determined mixing characteristics were in agreement with findings of the image processing method. [GRAPHICS] .

关键词： Biogas injection parameters Computational fluid dynamics image processing technique Optimization Pneumatic mixer

来源：评论

学校读者我要写书评

暂无评论

Blend Time Measurement in the Confined Impeller Stirred Tank

引用

CHEMICAL ENGINEERING & TECHNOLOGY 2019年第8期42卷 1594-1601页

作者： Jairamdas, Khilesh Bhalerao, Akshay Machado, Marcio Bezerra Kresta, Suzanne M. Univ Alberta Dept Chem & Mat Engn 9211 116 St NW Edmonton AB T6G 1H9 Canada

An image processing technique is applied to measure the blend time in a confined impeller stirred tank (CIST). An acid-base reaction is used to track mixing. The blend time is defined as the time taken to 95 % or 99 % of the pixels change color from purple to yellow. Six sets of impellers are employed: Rushtons, A310s, pitched-blade turbines (PBTs;three different combinations of up- and down-pumping), and Intermigs. Variation of the Reynolds number Re showed that the blend time becomes shorter with increasing Re and longer with higher viscosity. As Re drops below 225, compartmentalization becomes apparent and the decolorization percentage increases suddenly when the acid reaches each communication point between the impellers.

关键词： Blend time Compartmentalization Confined impeller stirred tank image processing technique Mixing energy

来源：评论

学校读者我要写书评

暂无评论

Detection of vehicle wheels from images using a pseudo-wavelet filter for analysis of congested traffic

引用

IET image processing 2018年第12期12卷 2222-2228页

作者： OBrien, Eugene J. Caprani, Colin C. Blacoe, Serena Guo, Dong Malekjafarian, Abdollah Univ Coll Dublin Sch Civil Engn Dublin 4 Ireland Monash Univ Dept Civil Engn Melbourne Vic Australia

There is potential for significant savings if the safety of existing bridges can be more accurately assessed. For long-span bridges, congestion is the governing traffic load condition. The current methods of simulating congestion make assumptions about the axle-to-axle gaps maintained between vehicles. There is potential for improvement in congestion models if accurate data on axle-to-axle gaps can be obtained. In this study, the use of a camera to collect this information is put forward. A new image processing technique is proposed to detect wheels in variable light conditions. The method is based on a pseudo-wavelet filter that amplifies circles, in conjunction with an algorithm that weights features in the image according to their circularity. This new approach is compared with the Hough transform, template matching and the deformable part-based model (DPM) methods previously developed. In a sample set of 80 images, 96.9% of wheels are detected, considerably more than with the Hough transform and template matching methods. It also provides the same level of accuracy as DPM without requiring a training process.

关键词： image matching Hough transforms wheels bridges (structures) road traffic image filtering pseudowavelet filter deformable part-based model methods congested traffic long-span bridges governing traffic load condition axle-to-axle gaps image processing technique variable light conditions template matching vehicle wheel detection existing bridge safety Hough transform

来源：评论

学校读者我要写书评

暂无评论

The credit card visual authentication scheme based on GF(2⁸) field

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2015年第24期74卷 11451-11465页

作者： Wang, Feng Chang, Chin-Chen Lyu, Wan-Li Fujian Univ Technol Dept Math & Phys Fuzhou 350108 Fujian Peoples R China Feng Chia Univ Dept Informat Engn & Comp Sci Taichung 40724 Taiwan Asia Univ Dept Comp Sci & Informat Engn Taichung 41354 Taiwan Anhui Univ Sch Comp Sci & Technol Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230039 Peoples R China

Recently, with the popular use of the credit cards, credit card fraud has become a severe problem. Merchants suffer great losses from credit card fraud. In this paper, we focus on "chip and signature" card, propose a credit card visual authentication scheme to resist lost and stolen card attack and protect the benefits of merchants. Inspired from the QR decomposition, we introduce image processing techniques to credit card transactions at POS terminals in order to ensure that the payer is the real cardholder, which gives an approach for credit card authentication. Our proposed scheme combines a one-time credit card transaction number and image processing techniques without changing the cardholders' transaction habit. We use a hash function to generate a one-time credit card transaction number with the shared secret only known to the cardholder and the bank, and a mathematical method of GF(2(8)) to solve the image problem, which will provide a math tool on image research. Analysis and comparison show that our scheme is secure in practical applications.

关键词： Credit card Authentication One-time credit card transaction number image processing technique Binary field QR decomposition

来源：评论

学校读者我要写书评

暂无评论

Determination of the Plasma Density in a Plasma Antenna Based on image Analysis and LIVPD Graphs

引用

IEEE ACCESS 2023年 11卷 120721-120727页

作者： Dorbin, Mohammad-Reza Mohassel, Jalil A. Rashed Sadeghikia, Fatemeh Ja'afar, Hajar Binti Univ Tehran Coll Engn Sch ECE Tehran *** Iran Minist Sci Res & Technol ARI Wireless Telecommun Grp Tehran *** Iran Univ Teknol MARA Coll Engn Sch Elect Engn Shah Alam 40450 Malaysia

This paper introduces an innovative method for quantitatively determining plasma density in plasma columns, with particular applicability to reconfigurable antennas. This method significantly enhances the speed of capturing density variations, particularly in surface wave-excited antennas. By utilizing images of excited plasma tubes, the proposed approach extracts a light intensity versus plasma density (LIVPD) graph, creating a direct correspondence between visible light intensity and plasma density. The methodology, encompassing LIVPD graph extraction and plasma density evaluation, is comprehensively elucidated. Rigorous analytical and experimental validations confirm a minor deviation of approximately 8.5%. The versatility of the method is demonstrated through two practical applications, reaffirming its accuracy in challenging scenarios. Additionally, this study includes a comparative analysis that highlights the superiority of the method in terms of sampling rate, measurement points, and non-intrusiveness over conventional techniques. This paper thus presents a robust method with promising potential for accurate plasma density determination in diverse antenna applications.

关键词： Plasma antenna image processing technique plasma density determination of the plasma density surface wave

来源：评论

学校读者我要写书评

暂无评论

Isothermal oxidation behavior of NiAl and NiAl-(Cr,Mo) eutectic alloys

引用

CORROSION SCIENCE 2019年 151卷 27-34页

作者： Peng, Jian Fang, Xufei Qu, Zhe Wang, Junjun Max Planck Inst Eisenforsch GmbH Max Planck Str 1 D-40237 Dusseldorf Germany Tsinghua Univ Dept Engn Mech AML Beijing 10084 Peoples R China Karlsruhe Inst Technol Inst Funct Interfaces Hermann von Helmholtz Pl 1 D-76344 Eggenstein Leopoldshafen Germany

Isothermal oxidation behavior of NiAl, NiAl-34Cr, NiAl-28Cr-6Mo and NiAl-10Mo for up to 1000 hat 900 degrees C was studied. Post-mortem inspection was performed and the oxidation mechanism was analyzed. Surface coverage of the formed voids was quantitatively analyzed for the first time using image processing technique. Replacing 6 at. % Mo with Cr further enhanced the Cr effect, i.e. accelerating theta-alpha Al2O3 transformation, and led to a slower oxide growth rate that is comparable to NiAl. Cr(+ Mo) addition resulted in a much flatter interface and less voids. The present results suggest NiAl-28Cr-6Mo exhibits the best overall oxidation resistance.

关键词： NiAl NiAl-(Cr,Mo) eutectic alloys Oxidation Al2O3 image processing technique

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：