Methods for Classifying Spot Welding Processes: A Comparative Study of Performance

Haapalainen, Eija; Laurinen, Perttu; Junno, Heli; Tuovinen, Lauri; Röning, Juha

doi:10.1007/11504894_58

Cited by 13 publications

(5 citation statements)

References 9 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SFS method is used since it has been successfully applied in a wide variety of feature selection problems yielding high performance values with minimal feature subsets: see [34], for example, for further discussion and application to the classification problem of process identification in resistance spot welding. On the other hand, the nBest method is used for comparative purposes being the most popular technique for feature selection.…”

Section: Feature Selectionmentioning

confidence: 99%

Game and Player Feature Selection for Entertainment Capture

Yannakakis

Hallam

2007

2007 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

The notion of constructing a metric of the degree to which a player enjoys a given game has been presented previously. In this paper, we attempt to construct such metric models of children's 'fun' when playing the Bug Smasher game on the Playware platform. First, a set of numerical features derived from a child's interaction with the Playware hardware is presented. Then the Sequential Forward Selection and the n-Best feature selection algorithms are employed together with a function approximator based on an artificial neural network to construct feature sets and function that model the child's notion of 'fun' for this game. Performance of the model is evaluated by the degree to which the preferences predicted by the model match those expressed by the children in a survey experiment. The results show that an effective model can be constructed using these techniques and that the Sequential Forward Selection method performs better in this task than n-Best. The model reveals differing preferences for game parameters between children who react fast to game events and those who react slowly. The limitations and the use of the methodology as an effective adaptive mechanism to entertainment augmentation are discussed.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Game and Player Feature Selection for Entertainment Capture

Yannakakis

Hallam

2007

2007 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

show abstract

“…The SFS method is tested since it has been successfully applied in a wide variety of feature selection problems yielding high-performance values with minimal feature subsets (see, for example, [36] for further discussion and application to the classification problem of process identification in resistance spot welding). On the other hand, the nBest method is included for comparative purposes, with it being the most popular technique for feature selection.…”

Section: Preference Learning With Feature Selectionmentioning

confidence: 99%

Preference Learning for Cognitive Modeling: A Case Study on Entertainment Preferences

Yannakakis

Μaragoudakis

Hallam

2009

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

Abstract-Learning from preferences, which provide means for expressing a subject's desires, constitutes an important topic in machine learning research. This paper presents a comparative study of four alternative instance preference learning algorithms (both linear and nonlinear). The case study investigated is to learn to predict the expressed entertainment preferences of children when playing physical games built on their personalized playing features (entertainment modeling). Two of the approaches are derived from the literature-the large-margin algorithm (LMA) and preference learning with Gaussian processes-while the remaining two are custom-designed approaches for the problem under investigation: meta-LMA and neuroevolution. Preference learning techniques are combined with feature set selection methods permitting the construction of effective preference models, given suitable individual playing features. The underlying preference model that best reflects children preferences is obtained through neuroevolution: 82.22% of cross-validation accuracy in predicting reported entertainment in the main set of game survey experimentation. The model is able to correctly match expressed preferences in 66.66% of cases on previously unseen data (p-value = 0.0136) of a second physical activity control experiment. Results indicate the benefit of the use of neuroevolution and sequential forward selection for the investigated complex case study of cognitive modeling in physical games.

show abstract

“…The second type is sensor measurements, or process curves, which are physical quantities measured along time, and are therefore referred to as time series (TS). Examples include dynamic resistance (Re) (Cho and Rhee 2000), electrode force (F) (Junno et al 2004), welding current (I) (Haapalainen et al 2005), electrode displacement (s) (Park and Cho 2004), welding voltage (U) (Haapalainen et al 2008), ultrasonic images (Martín et al 2007;Amiri et al 2020), power. Besides the two common types, Lee et al (2003) used images collected from Scanning Acoustic Microscopy (SAM).…”

Section: Data Collectionmentioning

confidence: 99%

“…Most of the methods used for machine learning modelling can be classified as classical machine learning methods (LaCasse et al 2019), like Linear Regression (LR) (Cho and Rhee 2002;Martín et al 2009;Panchakshari and Kadam 2013), Polynomial Regression (PolyR) (Pashazadeh et al 2016;, or Generalised Linear Models (GLM) Gavidel et al (2019), k-Nearest Neighbours (kNN) (Haapalainen et al 2005;Koskimaki et al 2007;Boersch et al 2016), Decision Trees (DT) (Zhang et al 2015;Kim and Ahmed 2018), Random Forests (RF) (Pereda et al 2015;Boersch et al 2016), Support Vector Machines (SVM), etc. Statistic methods like Linear or Quadratic Discriminate Analysis (LDA and QDA) are also used for classification.…”

Section: Modellingmentioning

confidence: 99%

Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding

et al. 2022

View full text Add to dashboard Cite

Digitalisation trends of Industry 4.0 and Internet of Things led to an unprecedented growth of manufacturing data. This opens new horizons for data-driven methods, such as Machine Learning (ML), in monitoring of manufacturing processes. In this work, we propose ML pipelines for quality monitoring in Resistance Spot Welding. Previous approaches mostly focused on estimating quality of welding based on data collected from laboratory or experimental settings. Then, they mostly treated welding operations as independent events while welding is a continuous process with a systematic dynamics and production cycles caused by maintenance. Besides, model interpretation based on engineering know-how, which is an important and common practice in manufacturing industry, has mostly been ignored. In this work, we address these three issues by developing a novel feature-engineering based ML approach. Our method was developed on top of real production data. It allows to analyse sequences of welding instances collected from running manufacturing lines. By capturing dependencies across sequences of welding instances, our method allows to predict quality of upcoming welding operations before they happen. Furthermore, in our work we strive to combine the view of engineering and data science by discussing characteristics of welding data that have been little discussed in the literature, by designing sophisticated feature engineering strategies with support of domain knowledge, and by interpreting the results of ML analysis intensively to provide insights for engineering. We developed 12 ML pipelines in two dimensions: settings of feature engineering and ML methods, where we considered 4 feature settings and 3 ML methods (linear regression, multi-layer perception and support vector regression). We extensively evaluated our ML pipelines on data from two running industrial production lines of 27 welding machines with promising results.

show abstract

Methods for Classifying Spot Welding Processes: A Comparative Study of Performance

Cited by 13 publications

References 9 publications

Game and Player Feature Selection for Entertainment Capture

Game and Player Feature Selection for Entertainment Capture

Preference Learning for Cognitive Modeling: A Case Study on Entertainment Preferences

Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding

Contact Info

Product

Resources

About