In order to improve the accuracy of using visual methods to detect the quality of fluff fabrics,based on the previous research,this paper proposes a method of rapid classification detection using support vector machin...In order to improve the accuracy of using visual methods to detect the quality of fluff fabrics,based on the previous research,this paper proposes a method of rapid classification detection using support vector machine(SVM).The fabric image is acquired by the principle of light-cut imaging,and the region of interest is extracted by the method of grayscale horizontal projection.The obtained coordinates of the upper edge of the fabric are decomposed into high frequency information and low frequency information by wavelet transform,and the high frequency information is used as a data set for training.After experimental comparison and analysis,the detection rate of the SVM method proposed in this paper is higher than the previously proposed back propagation(BP)neural network and particle swarm optimization BP(PSO-BP)neural network detection methods,and the accuracy rate can reach 99.41%,which can meet the needs of industrial testing.展开更多
Considering the issue of misjudgment in railway bridge damage identification, a method combining the step- by-step damage detection method with the statistical pattern recognition is proposed to detect the structural ...Considering the issue of misjudgment in railway bridge damage identification, a method combining the step- by-step damage detection method with the statistical pattern recognition is proposed to detect the structural damage of a railway continuous girder bridge. The whole process of damage identification is divided into three identification sub- steps, namely, damage early warning, damage location, and damage extent identification. The multi-class pattern clas- sification algorithm of C-support vector machine and the regression algorithm of c-support vector machine are engagedto identify the damage location and damage extent, respectively. For verifying the proposed method, both of the pro- posed method and the optimization method are used to deal with the measured data obtained from a specific railway continuous girder model bridge. The results show that the proposed method can not only identify the damage location correctly, but also obtain the damage extent which is consistent with the experimental results accurately. By uncou- pling finite element analysis and damage identification, normalizing the index, and seeking the separation hyper plane with maximum margin, the proposed method has more favorable advantages in generalization and anti-noise. As a re- sult, it has the ability to identify the damage location and extent, and can be applied to the damage identification in real bridge structures.展开更多
基金National Natural Science Foundation of China(No.61701384)Natural Science Basic Research Plan in Shaanxi Province of China(No.2017JM5141)+5 种基金Shaanxi Provincial Education Department,China(No.17JK0334)Xi'an Polytechnic University Graduate Innovation Fund,China(No.chx2019083)Science Foundation for Doctorate Research of Xi'an Polytechnic University,China(No.BS1535)Key Research and Development Program of Shaanxi,China(No.2020GY-172)Technology Innovation Leading Program of Xi'an,China(No.201805030YD8CG14(5))Xi'an Key Laboratory of Modern Intelligent Textile Equipment,China(No.2019220614SYS021CG043)。
文摘In order to improve the accuracy of using visual methods to detect the quality of fluff fabrics,based on the previous research,this paper proposes a method of rapid classification detection using support vector machine(SVM).The fabric image is acquired by the principle of light-cut imaging,and the region of interest is extracted by the method of grayscale horizontal projection.The obtained coordinates of the upper edge of the fabric are decomposed into high frequency information and low frequency information by wavelet transform,and the high frequency information is used as a data set for training.After experimental comparison and analysis,the detection rate of the SVM method proposed in this paper is higher than the previously proposed back propagation(BP)neural network and particle swarm optimization BP(PSO-BP)neural network detection methods,and the accuracy rate can reach 99.41%,which can meet the needs of industrial testing.
基金supported by the National Science Foundation (No. 51078316)the Chinese Railway Ministry Scientific Research and Development Program (No. 2011G026-E)the Sichuan Science and Technology Program (No. 2011JY0032)
文摘Considering the issue of misjudgment in railway bridge damage identification, a method combining the step- by-step damage detection method with the statistical pattern recognition is proposed to detect the structural damage of a railway continuous girder bridge. The whole process of damage identification is divided into three identification sub- steps, namely, damage early warning, damage location, and damage extent identification. The multi-class pattern clas- sification algorithm of C-support vector machine and the regression algorithm of c-support vector machine are engagedto identify the damage location and damage extent, respectively. For verifying the proposed method, both of the pro- posed method and the optimization method are used to deal with the measured data obtained from a specific railway continuous girder model bridge. The results show that the proposed method can not only identify the damage location correctly, but also obtain the damage extent which is consistent with the experimental results accurately. By uncou- pling finite element analysis and damage identification, normalizing the index, and seeking the separation hyper plane with maximum margin, the proposed method has more favorable advantages in generalization and anti-noise. As a re- sult, it has the ability to identify the damage location and extent, and can be applied to the damage identification in real bridge structures.
