Penetration quality prediction of asymmetrical fillet root welding based on optimized BP neural network

Chang, Yushuo; Jianfeng, Yue; Guo, Rui; Liu, Wenji; Li, Liangyu

doi:10.1016/j.jmapro.2019.12.022

Cited by 44 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the designed detection system, various classification methods were used to detect the sample classes. The classification performance of learning classifiers based on the SVM, K-nearest neighbor (KNN), 20,21 and back propagation neural network (BPNN), 22,23 algorithms were compared with that of the proposed method. The input dataset in KNN classification was { S 4 , S 5 , S 6 , S 7 , S 8 }, and the output dataset in this classification was the class membership ({E}, {F}, {G}, {H}, {I}).…”

Section: Resultsmentioning

confidence: 99%

Dynamic weight-based learning method for data detection in manufacturing

Lin

2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

In this study, a dynamic weight-based method combined with principal component analysis (PCA) was developed for the first time for detecting measurement data in manufacturing. This weight-based learning technique can learn and train the measurement data sequence to isolate incorrect data sources for achieving high accuracy when detecting various types of data. Research has revealed that unsuitable image or data features might cause poor performance in industrial inspections. In contrast to the previous inspection methods, the weight-based learning method proposed in this study employs a dynamic learning algorithm for effectively and adaptively selecting optimal principle components to the support vector machine (SVM) algorithm and then establishes indicators. Finally, these PCA-based indicators act as substitutes for massive amounts of data in data processing and can be applied to timely detect data when the data contain redundant and incorrect inputs in a sequence. The experimental results indicate that the proposed method, which combines dynamic weight-based feature extraction with PCA, can provide useful indicators for detecting various types of manufacturing data and exhibited satisfactory performance in the data detection.

show abstract

Section: Resultsmentioning

confidence: 99%

Dynamic weight-based learning method for data detection in manufacturing

Lin

2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…A BP neural network is a kind of back propagation neural network. It has strong nonlinear mapping ability, self-learning ability, and self-adaptive ability and has been widely used in nonlinear problems in material engineering [ 38 – 40 ]. Deformation is one of the main typical problems in welding.…”

Section: Case Analysismentioning

confidence: 99%

Quality Prediction and Control of Assembly and Welding Process for Ship Group Product Based on Digital Twin

Liu

et al. 2020

Scanning

View full text Add to dashboard Cite

In view of the problems of lagging and poor predictability for ship assembly and welding quality control, the digital twin technology is applied to realize the quality prediction and control of ship group product. Based on the analysis of internal and external quality factors, a digital twin-based quality prediction and control process was proposed. Furthermore, the digital twin model of quality prediction and control was established, including physical assembly and welding entity, virtual assembly and welding model, the quality prediction and control system, and twin data. Next, the real-time data collection based on the Internet of Things and the twin data organization based on XML were used to create a virtual-real mapping mechanism. Then, the machine learning technology is applied to predict the process quality of ship group products. Finally, a small group is taken as an example to verify the proposed method. The results show that the established prediction model can accurately evaluate the welding angular deformation of group products and also provide a new idea for the quality control of shipbuilding.

show abstract

“…Vangalapati et al [23] also simulated friction stir welding using an ANN model. Chang et al [24] developed a backpropagation ANN model for predicting the penetration morphology of asymmetrical fillet welds and used a mind evolutionary algorithm to optimize the model. Joseph and Muthukumaran [25] used a genetic algorithm and simulated annealing technique to determine the optimal process parameters for activated tungsten inert gas.…”

Section: Introductionmentioning

confidence: 99%

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Tomaz

Colaço

Sarfraz

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Gas tungsten arc welding (GTAW) technology is widely used in industry and has advantages, including high precision, excellent welding quality, and low equipment cost. However, the inclusion of a large number of process parameters hinders its application on a wider scale. Therefore, there is a need to implement the prediction and optimization models that effectively enhance the process performance of the GTAW process in different applications. In this study, a five-factor five-level central composite design (CCD) matrix was used to conduct GTAW experiments. AISI 1020 steel blank was used as a substrate; UTP AF Ledurit 60 and UTP AF Ledurit 68 were used as the materials of two tubular wires. Further, an artificial neural network (ANN) was used to simulate the GTAW process and then combined with a genetic algorithm (GA) to determine welding parameters that can provide an optimal weld. In welding experiments, five different welding current levels, welding speed, distance to the nozzle, angle of movement, and frequency of the wire feed pulses were used. Using GA, optimal welding parameters were determined: welding current = 222 A, welding speed = 25 cm/min, nozzle deflection distance = 8 mm, travel angle = 25°, wire feed pulse frequency = 8 Hz. The determination coefficient (R2) and RMSE value of all response parameters are satisfactory, and the R2 of all the data remained higher than 0.65.

show abstract

Penetration quality prediction of asymmetrical fillet root welding based on optimized BP neural network

Cited by 44 publications

References 25 publications

Dynamic weight-based learning method for data detection in manufacturing

Dynamic weight-based learning method for data detection in manufacturing

Quality Prediction and Control of Assembly and Welding Process for Ship Group Product Based on Digital Twin

Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm

Contact Info

Product

Resources

About