Modeling of underwater wet welding process based on visual and arc sensor

2014 ◽  
Vol 41 (3) ◽  
pp. 311-317 ◽  
Author(s):  
Bo Chen ◽  
Jicai Feng
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Weld Seam ◽  
Back Propagation ◽  
Welding Process ◽  
Welding Quality ◽  
Welding Seam ◽  
Content Type ◽  
Underwater Welding ◽  
Underwater Wet Welding

Purpose – The purpose of this paper was to use visual and arc sensors to simultaneously obtain the underwater wet welding information, and a weld seam-forming model was made to predict the weld seam's geometric parameters. It is difficult to obtain a fine welding quality in underwater welding because of the intense disturbances of the water environment. To automatically control the welding quality, the weld seam-forming model should first be established. Thus, the foundation was laid for automatically controlling the underwater welding seam-forming quality. Design/methodology/approach – Visual and arc sensors were used simultaneously to obtain the weld seam image, current and voltage information; then signal algorithms were used to process the information, and the back propagation (BP) neural network was used to model the process. Findings – Experiment results showed that the BP neural network model could precisely predict the weld seam-forming parameters of underwater wet welding. Originality/value – A weld seam-forming model of underwater wet welding process was made; this laid the foundation for establishing a controller for controlling the underwater wet welding process automatically.

Analysis of Underwater Wet Welding Seam Forming Based on Arc Sensor Information

2013 ◽  
Vol 300-301 ◽  
pp. 500-503
Author(s):  
Bo Chen ◽  
Hong Tao Zhang ◽  
Ji Cai Feng
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Weld Seam ◽  
Water Environment ◽  
Welding Process ◽  
Welding Quality ◽  
Welding Seam ◽  
Underwater Welding ◽  
Arc Sensor ◽  
Sensor Information

It is difficult to obtain fine weld seam of underwater welding because of the water environment, this paper used arc sensor to obtain electrical information of the under water wet welding process, and BP neural network was used to model the process, experiment results showed the model could predict the process precisely, this laid the foundation for further controlling the welding quality automatically.

Classification of Weld Defects Based on Convolution Neural Network

2021 ◽  
pp. 23-36
Author(s):  
A.I. Gavrilov ◽  
M.Tr. Do
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Weld Seam ◽  
Control Process ◽  
Welding Process ◽  
Optimal Solution ◽  
Automatic Welding ◽  
Welding Seam ◽  
Noise Factors

Automatic welding technology has been widely applied in many industrial fields. It is a complex process with many nonlinear parameters and noise factors affecting weld quality. Therefore, it is necessary to inspect and evaluate the quality of the weld seam during welding process. However, in practice there are many types of welding seam defects, causes and the method of corrections are also different. Therefore, welding seam defects need to be classified to determine the optimal solution for the control process with the best quality. Previously, the welder used his experience to classify visually, or some studies proposed visual classification with image processing algorithms and machine learning. However, it requires a lot of time and accuracy is not high. The paper proposes a convolutional neural network structure to classify images of welding seam defects from automatic welding machines on pipes. Based on comparison with the classification results of some deep machine learning networks such as VGG16, Alexnet, Resnet-50, it shows that the classification accuracy is 99.46 %. Experimental results show that the structure of convolutional neural network is proposed to classify images of weld seam defects have availability and applicability

Prediction and analysis of compressive strength of recycled aggregate thermal insulation concrete based on GA-BP optimization network

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jinsong Tu ◽  
Yuanzhen Liu ◽  
Ming Zhou ◽  
Ruixia Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Compressive Strength ◽  
Thermal Insulation ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Training Sample ◽  
Recycled Aggregate ◽  
Generalization Performance ◽  
Content Type

Purpose This paper aims to predict the 28-day compressive strength of recycled thermal insulation concrete more accurately. Design/methodology/approach The initial weights and thresholds of BP neural network are improved by genetic algorithm on MATLAB 2014 a platform. Findings Genetic algorithm–back propagation (GA-BP) neural network is more stable. The generalization performance of the complex is better. Originality/value The GA-BP neural network based on the training sample data can better realize the strength prediction of recycled aggregate thermal insulation concrete and reduce the complex orthogonal experimental process. GA-BP neural network is more stable. The generalization performance of the complex is better.

Paste-filling weighing control system optimization based on neural network

2017 ◽  
Vol 14 (2) ◽  
pp. 155-158 ◽  
Author(s):  
Guimei Wang ◽  
Yong Shuo Zhang ◽  
Lijie Yang ◽  
Shuai Zhang
Keyword(s):  
Neural Network ◽  
Control System ◽  
Coal Mine ◽  
Bp Neural Network ◽  
Back Propagation ◽  
System Optimization ◽  
Filling Material ◽  
Content Type ◽  
Control Precision ◽  
Filling System

Purpose This paper aims to optimize the weighing control system and compensate weighing error for weighing control system of coal mine paste-filling weighing control system. Design/methodology/approach The process of the paste-filling weighing control system is analyzed and the mathematical model of the paste-filling material weight is established. Then, the back-propagation (BP) neural network is used to optimize the control system and compensate the weighing error. Findings Without the BP neural network, the weighing error of the paste-filling control system is more than 3 per cent, whereas after optimization with the BP neural network, the weighing error is less than 1 per cent. With the simulation results, it is seen that the weighing error of the paste-filling control system decreases and the accuracy of the weighing control system improves and optimizes. Originality/value The method can be further used to improve the control precision of the coal mine paste-filling system.

Estimation of construction project building cost by back-propagation neural network

2019 ◽  
Vol 18 (3) ◽  
pp. 601-609
Author(s):  
Qinghua Jiang
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Bp Neural Network ◽  
Cost Estimation ◽  
Back Propagation ◽  
Estimation Accuracy ◽  
Average Error ◽  
Estimation Model ◽  
Content Type ◽  
Building Cost

Purpose Building cost is an important part of construction projects, and its correct estimation has important guiding significance for the follow-up decision-making of construction units. Design/methodology/approach This study focused on the application of back-propagation (BP) neural network in the estimation of building cost. First, the influencing factors of building cost were analyzed. Six factors were selected as input of the estimation model. Then, a BP neural network estimation model was established and trained by ten samples. Findings According to the experimental results, it was found that the estimation model converged at about 85 times; compared with radial basis function (RBF), the estimation accuracy of the model was higher, and the average error was 5.54 per cent, showing a good reliability in cost estimation. Originality/value The results of this study provide a reliable basis for investment decision-making in the construction industry and also contribute to the further application of BP neural network in cost estimation.

Three-dimensional coordinate measurement algorithm by optimizing BP neural network based on GA

2019 ◽  
Vol 36 (6) ◽  
pp. 2066-2083 ◽  
Author(s):  
Xiaohong Lu ◽  
Yongquan Wang ◽  
Jie Li ◽  
Yang Zhou ◽  
Zongjin Ren ◽  
...  
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Three Dimensional ◽  
Measuring System ◽  
Content Type ◽  
Coordinate Measurement ◽  
World Coordinate System ◽  
Measurement Algorithm ◽  
Three Dimensional Coordinate

Purpose The purpose of this paper is to solve the problem that the analytic solution model of spatial three-dimensional coordinate measuring system based on dual-position sensitive detector (PSD) is complex and its precision is not high. Design/methodology/approach A new three-dimensional coordinate measurement algorithm by optimizing back propagation (BP) neural network based on genetic algorithm (GA) is proposed. The mapping relation between three-dimensional coordinates of space points in the world coordinate system and light spot coordinates formed on dual-PSD has been built and applied to the prediction of three-dimensional coordinates of space points. Findings The average measurement error of three-dimensional coordinates of space points at three-dimensional coordinate measuring system based on dual-PSD based on GA-BP neural network is relatively small. This method does not require considering the lens distortion and the non-linearity of PSD. It has simple structure and high precision and is suitable for three-dimensional coordinate measurement of space points. Originality/value A new three-dimensional coordinate measurement algorithm by optimizing BP neural network based on GA is proposed to predict three-dimensional coordinates of space points formed on three-dimensional coordinate measuring system based on dual-PSD.

Economic benefit of shale gas exploitation based on back propagation neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8823-8830
Author(s):  
Jiafeng Li ◽  
Hui Hu ◽  
Xiang Li ◽  
Qian Jin ◽  
Tianhao Huang
Keyword(s):  
Neural Network ◽  
Shale Gas ◽  
Bp Neural Network ◽  
Large Scale ◽  
Linear Prediction ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Economic Benefits ◽  
Gas Well ◽  
Well Production

Under the influence of COVID-19, the economic benefits of shale gas development are greatly affected. With the large-scale development and utilization of shale gas in China, it is increasingly important to assess the economic impact of shale gas development. Therefore, this paper proposes a method for predicting the production of shale gas reservoirs, and uses back propagation (BP) neural network to nonlinearly fit reservoir reconstruction data to obtain shale gas well production forecasting models. Experiments show that compared with the traditional BP neural network, the proposed method can effectively improve the accuracy and stability of the prediction. There is a nonlinear correlation between reservoir reconstruction data and gas well production, which does not apply to traditional linear prediction methods

Modeling and Analysis of Underwater Wet Weld Process Based on Regression Method

2013 ◽  
Vol 690-693 ◽  
pp. 2621-2624
Author(s):  
Bo Chen ◽  
Ji Cai Feng
Keyword(s):  
Weld Seam ◽  
Welding Process ◽  
Regression Method ◽  
Modeling And Analysis ◽  
Underwater Wet Welding ◽  
Underwater Environment ◽  
Arc Sensor ◽  
Weld Parameters ◽  
Automation Technology ◽  
Weld Automation

Underwater weld technology is urgently needed for the widely development of marine recourses, and weld automation technology is the inevitable choice because of the underwater environment. Because of the influence of the rigorous environment, the weld seam forming of underwater wet welding is very poor. To control the weld seam forming automatically, the model between the weld parameters and the weld seam shape must be built. This paper used arc sensor to monitor the electrical information of underwater wet welding process, and regression method was used to model the process, and the factors that influence the weld seam forming mostly were analyzed.

scholarly journals Assessment of water resource security in karst area of Guizhou Province, China

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Liying Liu
Keyword(s):  
Neural Network ◽  
Water Resources ◽  
Water Resource ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Water Shortage ◽  
Guizhou Province ◽  
Karst Area ◽  
Water Resource Security ◽  
Resource Security

AbstractThis paper presents the assessment of water resource security in the Guizhou karst area, China. A mean impact value and back-propagation (MIV-BP) neural network was used to understand the influencing factors. Thirty-one indices involving five aspects, the water quality subsystem, water quantity subsystem, engineering water shortage subsystem, water resource vulnerability subsystem, and water resource carrying capacity subsystem, were selected to establish an evaluation index of water resource security. In addition, a genetic algorithm and back-propagation (GA-BP) neural network was constructed to assess the water resource security of Guizhou Province from 2001 to 2015. The results show that water resource security in Guizhou was at a moderate warning level from 2001 to 2006 and a critical safety level from 2007 to 2015, except in 2011 when a moderate warning level was reached. For protection and management of water resources in a karst area, the modes of development and utilization of water resources must be thoroughly understood, along with the impact of engineering water shortage. These results are a meaningful contribution to regional ecological restoration and socio-economic development and can promote better practices for future planning.

Sign in / Sign up

Export Citation Format

Share Document