SVM-based information fusion for weld deviation extraction and weld groove state identification in rotating arc narrow gap MAG welding

Li, Wenhang; Gao, Kai; Wu, Jing; Hu, Ting; Wang, Jiayou

doi:10.1007/s00170-014-6079-x

Cited by 31 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Temko et al [11] proposed the fusion approach of different information sources with the fuzzy integral for the problem of classifying. Li et al [12] proposed a fusion method based on the arc sensing and vision sensing information. Jiang et al [13] proposed a fault diagnosis methodology for rotating machinery by using multisensor information fusion.…”

Section: Related Studiesmentioning

confidence: 99%

Study on a novel fault diagnosis method based on information fusion method

Zhao¹,

Deng²,

Yang³

et al. 2016

J. vibroeng.

View full text Add to dashboard Cite

For the low accuracy and calculation speed of traditional fault diagnosis methods, the chaos optimization algorithm (COA), quantum particle swarm optimization (QPSO) algorithm and support vector machine (SVM) are introduced into the fault diagnosis to propose a novel fault diagnosis (CQPSMFD) method in this paper. In the proposed CQPSMFD method, the COA is used to initialize the parameters of the QPSO algorithm in order to obtain the CQPSO algorithm with the better convergence speed. Then the CQPSO algorithm is used to optimize the parameters of the SVM model to construct a high-precision SVM model (CQPSM) with the higher accuracy and stronger generalization ability. Next, the CQPSMFD method based on CQPSM method is proposed for motor. Finally, the experiment data from Case Western bearing dataset and actual motor are selected to verify the CQPSMFD method. The results show that the CQPSO algorithm can obtain the optimal parameter combination and the CQPSMFD method can effectively improve the fault diagnosis accuracy and speed.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Study on a novel fault diagnosis method based on information fusion method

Zhao¹,

Deng²,

Yang³

et al. 2016

J. vibroeng.

View full text Add to dashboard Cite

show abstract

“…Obviously, the vision-based welding deviation was rarely affected by the groove's bottom shape. Details of the vision-based method can be found in a relative reference (Li et al, 2014).…”

Section: Vision Sensing Informationmentioning

confidence: 99%

“…Here, the minimum matching rate for rules in the RS model was 50 per cent. The definition of matching rate was shown as follows: (Li et al, 2014), where their prediction accuracy is 92.1098 per cent and 85.01 per cent, respectively. It showed that the RS model prediction accuracy was between that of the SVM model and the BP NN model.…”

Section: Model Reasoning and Validationmentioning

confidence: 99%

Rough set based modeling for welding groove bottom state in narrow gap MAG welding

et al. 2015

Industrial Robot: An International Journal

Self Cite

View full text Add to dashboard Cite

Purpose – This paper aim to build an information fusion model that can predict the bottom shape of welding groove for better welding quality control. Arc sensor is widely used in seam tracking due to its simplicity and good accessibility, but it heavily relies on the bottom shape of the groove. It is necessary to identify the welding groove bottom state. Therefore, arc sensor information and vision sensing information were fused by the rough set (RS) method to predict the groove state, which will lay the foundation for better welding quality control. Design/methodology/approach – First, a multi-sensor information system was established, which included an arc sensing component and a vision sensing component. For the arc sensing system, the current waveform in each rotating period was obtained and divided into 12 parts to calculate variables representing the variation of arc length. For the vision sensing system, images were obtained by passive vision when the arc was near the groove sidewall. The positions of the sidewall and the arc were calculated to get the weld deviation which was unrelated with the bottom groove state. Second, experimental data were generated by workpiece with various bottom shapes. At last, the RS method was adopted to fuse the arc sensing and the vision information, and a rule-based model with good prediction ability was obtained. Findings – By fusing arc sensing and vision sensing information, an RS-based model was built to predict the welding groove state. Originality/value – The RS modeling method was used to fuse arc sensing information and vision sensing information to build a model that predicts groove bottom state. The arc sensing information represented the arc length variation, while the vision sensing information contains the seam deviation which was unrelated with the bottom groove state. The RS model gives satisfactory prediction results and can be applied to weld quality control.

show abstract

“…And it is used to get the image or location information about the welding work pieces. During the much research work, the common sensors include arc sensors [4]- [6], ultrasonic sensors [7], magneto-optical sensors [8], [9], infrared sensors [10], vision sensors [11]- [13]. Compared…”

Section: Introductionmentioning

confidence: 99%

A Novel 3D Seam Extraction Method Based on Multi-Functional Sensor for V-Type Weld Seam

Yang

Liu

2019

IEEE Access

View full text Add to dashboard Cite

To meet the current flexible modern manufacturing mode, based on the idea from coarse to fine, a novel three-dimensional(3D) seam extraction algorithm is proposed in this paper which includes the global rough extraction and the local fine positioning. Firstly, a multi-functional vision system based on Digital Light Processing(DLP) projector is designed to adapt different 3D measurement tasks. Secondly, a global sensor based on DLP projector is constructed which is used to acquire the whole weld seam. Meanwhile, a new feature extraction algorithm based on 3D information of work pieces is proposed. Thirdly, a line structured light sensor based on DLP projector is to serve as local sensor. Based on the results of rough extraction, the close-range laser scanning is to improve the measurement precision. Finally, the 3D path model and pose estimation of weld seam are done which could be applied into the 3D path teaching of welding robots. The experiments show that the proposed algorithm could well finish the high-precision 3D seam path planning through the ''Global-Local'' method.

show abstract

SVM-based information fusion for weld deviation extraction and weld groove state identification in rotating arc narrow gap MAG welding

Cited by 31 publications

References 13 publications

Study on a novel fault diagnosis method based on information fusion method

Study on a novel fault diagnosis method based on information fusion method

Rough set based modeling for welding groove bottom state in narrow gap MAG welding

A Novel 3D Seam Extraction Method Based on Multi-Functional Sensor for V-Type Weld Seam

Contact Info

Product

Resources

About