Anti-Distortion Image Contrast Enhancement Algorithm Based on Fuzzy Statistical Analysis of the Histogram Equalization

Yao Nan,Wang KaiSheng,Cai Yue 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.4

In order to solve such problems as excessive enhancement and chessboard effect, difficult image brightness keeping and distortion in the image enhancement algorithm based on histogram equalization, an anti-distortion image contrast enhancement algorithm based on fuzzy statistics and sub-histogram equalization is proposed in this article. Specifically, the fuzzy set theory is introduced therein to convert the image into fuzzy matrix; then, by virtue of the membership function and the probability of the image gradation, the weighting function is embedded to construct the weighted fuzzy histogram calculation model; then, the mid-value of the initial image is adopted to divide the fuzzy histogram into two sub-histograms, and the corresponding cumulative density functions are defined, and the transformation models thereof are also constructed; then, the inverse transformation function is established to realize defuzzification and output the enhanced image. The experimental data show: compared with the present image enhancement algorithm based on histogram equalization, this algorithm can significantly eliminate excessive enhancement and noise amplification, thus to not only have better visual enhancement quality and anti-distortion performance, but also have maximum AIC (Average Information Contents) value and minimum NIQE (Natural Image Quality Evaluator) value.

Image Denoising Algorithm Based on Non Related Dictionary Learning

Yao Nan,Wang KaiSheng,Cai Yue 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.3

In allusion to the partial texture information loss during image deniosing process, an image denoising algorithm based on non related dictionary learning is proposed in this article. In this algorithm, the noise image is firstly divided into mutually overlapped image blocks, and a certain quantity of these image blocks are randomly selected for subsequent dictionary learning; then, non related dictionary learning technology is adopted to obtain the redundant dictionary with relatively strong irrelevance; finally, the sparse encoding algorithm is adopted to obtain the sparse representation coefficient of each image block in the redundant dictionary, and such sparse representation coefficients are used to recover the original image. The experiment result shows: since the redundant dictionary obtained through non related dictionary learning technology can strongly represent the image texture information, PSNR (Peak Signal to Noise Ratio) of the algorithm proposed in this article is superior to that of the existing advanced algorithm, and the algorithm can well keep the image detail and texture information, thus to improve visual effect.

Application of Intelligent Video Monitoring System in Electric Power Construction

Yao Nan,Wang KaiSheng,Cai Yue 보안공학연구지원센터 2016 International Journal of u- and e- Service, Scienc Vol.9 No.4

Since the image based intelligent video monitoring system has limited viewing angle, the blind monitoring zone will easily appear when the target is not in the field range of the camera. In order to solve the above problem, an intelligent video monitoring system with auditory function is proposed in this article on the basis of the advantages of sound localization. Firstly, the linear microphone array is acquired and the time delay estimation technology is adopted for sound localization; secondly, the camera is driven to turn to the sound source position to acquire video information; finally, the image detection program is adopted to locate and track the target in a real-time manner, and meanwhile the system feasibility is verified through the simulation experiment. The result shows that the system has good localization and tracking accuracy.

Background Motion Video Tracking of the Memory Watershed Disc Gradient Expansion Template

Yao Nan,Shen Haiping 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.4

In order to further improve motion video target tracking and detection accuracy, a motion video tracking algorithm based on memory watershed disc gradient expansion template is proposed in this article. Firstly, heterodromous diffusion is executed to preprocess the motion video image in order to reduce the noise interference in the motion target tracking and detection process, and meanwhile the differential operation and the morphological operation are executed to extract and operate the outer profile of the motion object. Secondly, in allusion to the excessive division in the watershed algorithm, target marking and division of the watershed algorithm are realized on the basis of characteristic memory, and the accurate detection of the motion target is realized on the basis of the disc gradient expansion template. Finally, according to the experimental comparison, the algorithm proposed in this article can be applied in the complex background detection of the motion target, and such algorithm can not only improve the motion target detection accuracy, but also significantly improve computation speed.

Research on intelligent tool condition monitoring based on data-driven: a review

Yaonan Cheng,Rui Guan,Yingbo Jin,Xiaoyu Gai,Mengda Lu,Ya Ding 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.7

The tool condition monitoring (TCM) can sense the real-time conditions of the tool to a large extent and warn the tool failure as early as possible. It can effectively improve processing efficiency, reduce production cost, and ensure production safety. With the rise of artificial intelligence technology, whether digital images obtained based on direct method or physical signals obtained through sensors by the indirect method can be regarded as valuable data. Using the artificial intelligence method to extract and identify the effective features in the data, mining the relationship between the tool wear or breakage and data is the key technology and difficulty of the intelligent tool condition monitoring. In this paper, the data representing tool wear or breakage characteristics are divided into image data and signal data. Moreover, the way to obtain high-quality data through image acquisition technology and multi-sensor fusion technology is discussed. Then the key principles and methods of feature extraction and decision making in TCM are studied. Finally, the future research direction is prospected based on the application of tool condition monitoring.

Thermal deformation analysis and compensation of the direct-drive five-axis CNC milling head

Yaonan Cheng,Xianpeng Zhang,Guangxin Zhang,Wenqi Jiang,Baowei Li 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.9

The machining precision of the milling head is primarily affected by the thermal errors that originated from the thermal deformation. Thermal error compensation is an economical and efficient method to overcome these thermal errors. The milling head’s heat source is analyzed to calculate the thermal boundary load based on component parameters of the milling head. The milling head’s thermal deformation is then simulated using ANSYS software to achieve the milling head’s temperature distribution and the amount of thermal deformation. Through the design and construction of the milling head temperature and thermal deformation experiment platform, the thermal deformation experiment of the milling head is performed. Accordingly, the measuring point temperature and the tooltip offset are obtained. Finally, a thermal error compensation method is proposed based on the homogeneous transformation. The research results give a theoretical reference and technical support for the thermal error compensation, optimized design, and development of milling heads.

Tool wear intelligent monitoring techniques in cutting: a review

Yaonan Cheng,Xiaoyu Gai,Rui Guan,Yingbo Jin,Mengda Lu,Ya Ding 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.1

Tool wear is inevitable in cutting process. If tool wear failure is not detected in time, it will lead to abnormal cutting process and affect the machining efficiency and quality seriously. The intelligent monitoring of tool wear can make the machining system perceive the real-time status of tools in advance and make early warning and decision-making, which is an effective way to ensure the efficient operation of machining and manufacturing system. By reviewing the research status of intelligent monitoring of tool wear, the key technical principles and methods of multisource-correlation signal selection, feature extraction and pattern recognition are classified. On the basis, the current application status of tool wear monitoring is discussed. In view of its shortcomings, this paper puts forward the prospect of the future, in order to provide a theoretical basis and reference for the development of tool wear intelligent monitoring technology and intelligent manufacturing industry.

Design and Research on the Special System for High Efficient Manufacturing of Blisk Based on UG

Yaonan Cheng,Rui Guan,Diange Zuo,Tianqi Chen,Li Liu 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.10

As one of the most important parts of aeroengine, blisk has complex structure and its material is titanium alloy hard to machine. It results in some difficulties in modeling and NC programming. In this paper, from the perspective of application, the secondary development technology of UG/Open Grip is used to design and develop the CAD/CAM module of blisk after analyzing structure feature and milling process of blisk. Firstly, it completes parametric modeling of blisk by establishing CAD module through the optimization of the original data points in NUBRS curve fitting and node interpolation technology; secondly, the inner and outer tolerance algorithm are applied to calculate the cutting step, and the row spacing is determined based on constant scallop height. Besides, tool axis vector is defined. All of these things are done to complete the establishment of the CAM module and realize trajectory planning of semi-finish machining of the blisk. It greatly improves the efficiency of programming and machining in blisks; finally, the module of blisk designed is used to model and program in the machining experiments in five axis machining center to verify correctness and reliability of the system. The results show that this module greatly improves manufacturing efficiency of blisk.

Review on sodium corrosion evolution of nuclear-grade 316 stainless steel for sodium-cooled fast reactor applications

Dai, Yaonan,Zheng, Xiaotao,Ding, Peishan Korean Nuclear Society 2021 Nuclear Engineering and Technology Vol.53 No.11

Sodium-cooled fast reactor (SFR) is the preferred technology of the generation-IV fast neutron reactor, and its core body mainly uses nuclear-grade 316 stainless steel. In order to prolong the design life of SFRs to 60 years and more, it is necessary to summarize and analyze the anti-corrosion effect of nuclear grade 316 stainless steel in high temperature sodium environment. The research on sodium corrosion of nuclear grade 316 stainless steel is mainly composed of several important factors, including the microstructure of stainless steel (ferrite layer, degradation layer, etc.), the trace chemical elements of stainless steel (Cr, Ni and Mo, etc) and liquid impurity elements in sodium (O, C and N, etc), carburization and mechanical properties of stainless steel, etc. Through summarizing and constructing the sodium corrosion rate equations of nuclear grade 316 stainless steel, the stainless steel loss of thickness can be predicted. By analyzing the effects of temperature, oxygen content in sodium and velocity of sodium on corrosion rate, the basis for establishing integrity evaluation standard of SFR core components with sodium corrosion is provided.

Existence and exponential stability of almost periodic solution for shunting inhibitory cellular neural networks with distributed delays and large impulses

Yi Zuo,Yaonan Wang,Lihong Huang,Chunsheng Li 대한수학회 2009 대한수학회지 Vol.46 No.5

This paper considers the problem of existence and exponential stability of almost periodic solution for shunting inhibitory cellular neural networks with distributed delays and large impulses. Based on the contraction principle and Gronwall-Bellman's inequality, some sufficient conditions are obtained. The results of this paper are new and they complement previously known results. This paper considers the problem of existence and exponential stability of almost periodic solution for shunting inhibitory cellular neural networks with distributed delays and large impulses. Based on the contraction principle and Gronwall-Bellman's inequality, some sufficient conditions are obtained. The results of this paper are new and they complement previously known results.