*Data Analysis and Modeling Techniques of Welding Processes: The State-of-the-Art DOI: http://dx.doi.org/10.5772/intechopen.91184*

Results obtained using SOM has been compared with the Probability Density Distributions (PDDs) obtained during statistical analysis. Voltage and current data analyzed using the SOM technique can also be utilized to evaluate the arc welding process. These studies demonstrate that there are other potential algorithms for welding process analysis. For that reason, it is necessary to evaluate and compare several of them to be agreed upon in a real-time process.

Other comparison in 2016 by Di Wu is [54]. The article compared a prediction model for Plasma Arc Welding based on Extreme Learning Machine (ELM) with ANN and SVM techniques. The ELM model had better generalization performance and was faster than others. This potentiality was established too by Nandhitha in


#### **Table 2.** *Table articles with quality objective*

**Figure 6** shows a summary of articles analyzed. It shows that ANNs are one of

demonstrates the need to make comparisons between various modeling techniques in order to define the best result, in terms of efficiency and computational cost.

As it has been expressed in the previous sections, there are new techniques to analyze very complex systems. But they require expensive computational resources for their construction and sometimes for their execution. A comparison between models will allow to know which model has better results and which model can be the most effective to be utilized. This effectivity is measured in function of problem necessity, like the one shown in data mining (DM) methodologies and processes

An interesting comparison is Support Vector Machine (SVM) and ANN model, to identify weld groove state and weld deviation extraction in rotating arc narrow gap MAG welding (RANGMW) [96]. It presented SVM models with better results

One comparison with focus on time optimized was [97]. It utilized an ANN and

In the article [98], Response Surface Methodology (RSM) was compared with linear isotonic regression, regression (LR), regression trees, ANN, GP, and SVM, to evaluate mechanical properties in GMAW process. The results present that the DM models have poorer generalization on this research, because DM techniques require,

Sumesh in 2015 [99] compared Decision Trees (DT), ANN, Fuzzy Logic, SVM, and Random forest technique Weld Quality Monitoring in SMAW. The most efficient technique was Random forest. This shows that not always the most complex

One of the few comparative analysis algorithms is Kumar's paper in 2016 [100].

This paper explores Self-Organizing Maps (SOM) using as a mechanism for performing unsupervised learning, for comparing performance characteristics of various welding parameters which include welding power supplies and welders.

ANN with differential evolutionary algorithm (DEA) separately. The results obtained by ANN using DEA were closer to ANN, but the computational time of

the most used techniques, but they do not always offer the best result. This

**5.2 Comparison of different models**

*Comparison between ANNs and ANN variations.*

[16, 17].

**36**

**Figure 6.**

*Welding - Modern Topics*

than ANN model.

ANN using DEA was shorter.

techniques offer the best results.

to obtain acceptable results, a large amount dataset.

2016 [106]. He utilized GRNN and Radial Basis Networks (RBN) for torch current prediction in GTAW process. The torch current deviation was 98.95 % accuracy for the best result of GRNN.

Other quality welding article was Xiaodong Wan in 2017 [102]. It proposed a Probabilistic Neural Network (PNN) model for quality prediction in large scale RSW process. In this case, the PNN model was more appropriate in quality level

*Data Analysis and Modeling Techniques of Welding Processes: The State-of-the-Art*

The one of the last articles with direct DM techniques and welding relation is of Yiming Huang in 2017 [103]. This is an investigation of porosity on pulsed gas tungsten arc welding (P-GTAW) with an X-ray image analysis. To detect, an Empirical Mode Decomposition (EMD) and Spectral Analyses were made based on DM. In 2017, Petković [104] predicted the laser welding quality by training data for the computational intelligence methodologies and support vector regression (SVR). SVR is a novel variant of SVM for regression task. This article made a comparison between SVR, ANN, and GP. It is another example that in certain problems, less

**Table 2** presents a series of articles that were based on the monitoring and quality of the welding processes. The column *Preparation* defines the technique of processing the data obtained by the sensors; *Classic* for processes that do not use the latest techniques of image processing and DL for the use of deep learning; *Online* defines if the model was executed in real time; *Compare*, if in the research carried out in the article, a comparison is made between several algorithms; and *Modeling* defines the algorithms used in specific article. When a comparison exits, the first model before coma was the best quality result. As **Tables 2**–**4**, the best algorithm

Defining which of the techniques is more effective for our problem also helps in

**preparations**

Classic ANN-learning control

fuzzy

fuzzy

fuzzy

Standard Classic GRNN Yes No

fuzzy

Visual DL DL-RL Yes No

**Modeling Online Compare**

Yes Yes

Yes No

Yes No

Yes No

Yes No

**Sensors Data**

Chen [111] 2009 GTAW Visual Classic ANN-fuzzy Yes No Malviya [112] 2011 GMAW Standard Classic ANN-PSO Yes No

Santhana [75] 2016 GTAW Standard Classic RSM Yes No

Moghaddam [115] 2016 GMAW Visual Classic ANN-PSO Yes No Lv [56] 2017 GTAW Sound Classic ANN Yes No

visual

Hailin [105] 2012 GMAW Visual Classic ANN and

Cruz [113] 2015 GMAW Visual Classic ANN and

Sharma [114] 2016 SAW Standard Classic RSM and

Pengfei Hu [116] 2017 GMAW Standard Classic Math-model—

classification than the Back Propagation Neural Network.

the effectiveness of a future process of intelligent control.

**process**

welding

Welding

Chen [66] 2000 P-GTAW Double-

complex algorithms can offer better results.

*DOI: http://dx.doi.org/10.5772/intechopen.91184*

does not always match.

**Author Year Welding**

Günther [63] 2016 Laser

Rao [94] 2017 Vibratory

*Table articles with control objective.*

**Table 4.**

**39**

In 2016 too, Kyoung-Yun Kim [107] discusses that in Resistance Spot Welding (RSW) process. He examined the prediction performance with GRNN and k-Nearest Neighbor (kNN) algorithms. The results indicate that with smaller k of kNN, the prediction performance measured by mean acceptable error has increased.


#### **Table 3.** *Table articles with prediction objective.*

*Data Analysis and Modeling Techniques of Welding Processes: The State-of-the-Art DOI: http://dx.doi.org/10.5772/intechopen.91184*

Other quality welding article was Xiaodong Wan in 2017 [102]. It proposed a Probabilistic Neural Network (PNN) model for quality prediction in large scale RSW process. In this case, the PNN model was more appropriate in quality level classification than the Back Propagation Neural Network.

The one of the last articles with direct DM techniques and welding relation is of Yiming Huang in 2017 [103]. This is an investigation of porosity on pulsed gas tungsten arc welding (P-GTAW) with an X-ray image analysis. To detect, an Empirical Mode Decomposition (EMD) and Spectral Analyses were made based on DM.

In 2017, Petković [104] predicted the laser welding quality by training data for the computational intelligence methodologies and support vector regression (SVR). SVR is a novel variant of SVM for regression task. This article made a comparison between SVR, ANN, and GP. It is another example that in certain problems, less complex algorithms can offer better results.

**Table 2** presents a series of articles that were based on the monitoring and quality of the welding processes. The column *Preparation* defines the technique of processing the data obtained by the sensors; *Classic* for processes that do not use the latest techniques of image processing and DL for the use of deep learning; *Online* defines if the model was executed in real time; *Compare*, if in the research carried out in the article, a comparison is made between several algorithms; and *Modeling* defines the algorithms used in specific article. When a comparison exits, the first model before coma was the best quality result. As **Tables 2**–**4**, the best algorithm does not always match.


Defining which of the techniques is more effective for our problem also helps in the effectiveness of a future process of intelligent control.

#### **Table 4.** *Table articles with control objective.*

2016 [106]. He utilized GRNN and Radial Basis Networks (RBN) for torch current prediction in GTAW process. The torch current deviation was 98.95 % accuracy for

In 2016 too, Kyoung-Yun Kim [107] discusses that in Resistance Spot Welding

(RSW) process. He examined the prediction performance with GRNN and k-Nearest Neighbor (kNN) algorithms. The results indicate that with smaller k of kNN, the prediction performance measured by mean acceptable error has

**Sensors Data**

Bo Chen [84] 2009 GTAW Multiples Classic ANN-DS No No Bo Chen [91] 2010 GTAW Multiples Classic ANN-fuzzy No No Seyyedian [108] 2012 GTAW Standard Classic ANN Yes No Li [79] 2014 GTAW Visual Classic LR No No Bo Chen [89] 2014 UWW Visual Classic ANN Yes No Li [96] 2014 RANGMW Visual Classic SVM, ANN Yes Yes

2014 GMAW Standard Classic RSM, some

Dong [77] 2016 GTAW Standard Classic GPR Yes No

Rong [87] 2016 GTAW Standard Classic ANN Yes No

2016 GMAW Visual Classic ANN fuzzy

2016 GTAW Thermography Classic ELM, RBN,

2016 GMAW Visual Classic ANN-fuzzy Yes No

Standard Classic Taguchi-

**preparations**

DM

RSM

ANN, SVM

Adaboost

ANN

ARTMAP

GRNN

GRNN

DBN

Standard Classic ANN Yes No

Standard Classic ANN Yes No

Standard Classic DNN Yes No

**Modeling Online Compare**

Yes Yes

No No

Yes Yes

Yes Yes

Yes Yes

Yes No

Yes Yes

Yes Yes

No No

the best result of GRNN.

*Welding - Modern Topics*

**Author Year Welding**

**process**

GMAW

GMAW, GTAW

Wu [54] 2016 VPPAW Sound Classic ELM,

Lv [55] 2016 GTAW Sound Classic BP-

Sarkar [85] 2016 SAW Standard Classic MRA and

Kim [107] 2016 RSW Standard Classic kNN,

Di Wu [95] 2017 VP-PAW Visual, sound Classic t-SNE and

2017 GMAW CMT

welds

increased.

Escribano-García [98]

Rios-Cabrera [92]

Nandhitha [106]

Aviles-Viñas [109, 110]

Pavan Kumar [86]

**Table 3.**

**38**

Mathew [88] 2017 Girth

*Table articles with prediction objective.*

Sen [74] 2015 DP-

Keshmiri [93] 2015 SAW,
