Ensemble of convolutional neural networks based on an evolutionary algorithm applied to an industrial welding process

Abstract This paper presents an approach for image classification based on an ensemble of convolutional neural networks and the application to a real case study of an industrial welding process. The ensemble consists of five convolutional neural networks, whose outputs are combined through a voting policy. In order to select appropriate network parameters (i.e., the number of convolutional layers and layers hyperparameters) and voting policy, an efficient search process was carried out by using an evolutionary algorithm. The proposed method is applied and validated in a case study focused on detecting misalignment of metal sheets to be joined through submerged arc welding process. After selecting the most convenient setup, the ensemble outperforms other seven strategies considered in a comparison in several metrics, while maintaining an adequate computational cost.

[1]  Alejandro Baldominos Gómez,et al.  Model Selection in Committees of Evolved Convolutional Neural Networks Using Genetic Algorithms , 2018, IDEAL.

[2]  Jiancheng Lv,et al.  Automatically Designing CNN Architectures Using Genetic Algorithm for Image Classification , 2018, ArXiv.

[3]  Catherine D. Schuman,et al.  Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design , 2020, Frontiers in Neuroscience.

[4]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[5]  Taimoor Akhtar,et al.  Efficient Hyperparameter Optimization for Deep Learning Algorithms Using Deterministic RBF Surrogates , 2016, AAAI.

[6]  David Bull,et al.  A supervised hierarchical segmentation of remote-sensing images using a committee of multi-scale convolutional neural networks , 2016 .

[7]  Rodolfo E. Haber,et al.  A classic solution for the control of a high-performance drilling process , 2007 .

[8]  Gerardo Beruvides,et al.  Computer Vision System for Welding Inspection of Liquefied Petroleum Gas Pressure Vessels Based on Combined Digital Image Processing and Deep Learning Techniques , 2020, Sensors.

[9]  José Ranilla,et al.  Hyper-parameter selection in deep neural networks using parallel particle swarm optimization , 2017, GECCO.

[10]  Claudiu Pozna,et al.  Applications of Signatures to Expert Systems Modelling , 2014 .

[11]  Yi Pan,et al.  Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm , 2020, ArXiv.

[12]  Qingquan Song,et al.  Auto-Keras: An Efficient Neural Architecture Search System , 2018, KDD.

[13]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[14]  Alejandro Baldominos Gómez,et al.  Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning , 2019, Complex..

[15]  Hakil Kim,et al.  A critical review on computer vision and artificial intelligence in food industry , 2020, Journal of Agriculture and Food Research.

[16]  Li Weihong,et al.  Ensemble of fine-tuned convolutional neural networks for urine sediment microscopic image classification , 2020 .

[17]  Quoc V. Le,et al.  Large-Scale Evolution of Image Classifiers , 2017, ICML.

[18]  Erez Shmueli,et al.  Beyond majority: Label ranking ensembles based on voting rules , 2019, Expert Syst. Appl..

[19]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[20]  Dong-Jin Choi,et al.  Hyperparameter Optimization Using a Genetic Algorithm Considering Verification Time in a Convolutional Neural Network , 2020 .

[21]  Gerardo Beruvides,et al.  A Simple Multi-Objective Optimization Based on the Cross-Entropy Method , 2017, IEEE Access.

[22]  Costin Badica,et al.  Evaluating the effect of voting methods on ensemble-based classification , 2017, 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA).

[23]  Svetha Venkatesh,et al.  Fast Hyperparameter Tuning using Bayesian Optimization with Directional Derivatives , 2019, Knowl. Based Syst..

[24]  Mayorkinos Papaelias,et al.  Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning , 2019, NDT & E International.

[25]  David Masip,et al.  Supervised Committee of Convolutional Neural Networks in Automated Facial Expression Analysis , 2018, IEEE Transactions on Affective Computing.

[26]  Sheikh Shanawaz Mostafa,et al.  Multi-Objective Hyperparameter Optimization of Convolutional Neural Network for Obstructive Sleep Apnea Detection , 2020, IEEE Access.

[27]  Tobias Senst,et al.  Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[28]  Razvan Andonie,et al.  Weighted Random Search for Hyperparameter Optimization , 2019, Int. J. Comput. Commun. Control.

[29]  Raymond W. Ptucha,et al.  Intelligent character recognition using fully convolutional neural networks , 2019, Pattern Recognit..

[30]  Ausif Mahmood,et al.  A Framework for Designing the Architectures of Deep Convolutional Neural Networks , 2017, Entropy.

[31]  Li Zhang,et al.  A High-Performance Deep Learning Algorithm for the Automated Optical Inspection of Laser Welding , 2020, Applied Sciences.

[32]  Shi Li,et al.  A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals , 2019, Comput. Ind..

[33]  Ayla Gülcü,et al.  Hyper-Parameter Selection in Convolutional Neural Networks Using Microcanonical Optimization Algorithm , 2020, IEEE Access.

[34]  André Thomas,et al.  Using a Classifier Ensemble for Proactive Quality Monitoring and Control: the impact of the choice of classifiers types, selection criterion, and fusion process , 2018, Comput. Ind..

[35]  Krzysztof Okarma,et al.  Applications of Computer Vision in Automation and Robotics , 2020, Applied Sciences.

[36]  Hector Rodriguez Rangel,et al.  Hyperparameter optimization in CNN for learning-centered emotion recognition for intelligent tutoring systems , 2019, Soft Computing.

[37]  Yulong Wang,et al.  cPSO-CNN: An efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks , 2019, Swarm Evol. Comput..

[38]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[39]  Alexander Brenning,et al.  Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data , 2019, Ecological Modelling.

[40]  Florian Huber,et al.  Mcfly: Automated deep learning on time series , 2020, SoftwareX.

[41]  Mauridhi Hery Purnomo,et al.  Welding defect classification based on convolution neural network (CNN) and Gaussian kernel , 2017, 2017 International Seminar on Intelligent Technology and Its Applications (ISITIA).

[42]  Asifullah Khan,et al.  A survey of the recent architectures of deep convolutional neural networks , 2019, Artificial Intelligence Review.

[43]  Gerardo Beruvides,et al.  Coping with Complexity When Predicting Surface Roughness in Milling Processes: Hybrid Incremental Model with Optimal Parametrization , 2017, Complex..

[44]  Mohammad Aminul Islam,et al.  Automatic Plant Detection Using HOG and LBP Features With SVM , 2019 .

[45]  Luca Maria Gambardella,et al.  Convolutional Neural Network Committees for Handwritten Character Classification , 2011, 2011 International Conference on Document Analysis and Recognition.

[46]  Jun Xu,et al.  Stacked-autoencoder-based model for COVID-19 diagnosis on CT images , 2020, Applied Intelligence.

[47]  Takayuki Okatani,et al.  A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks , 2019, Automation in Construction.

[48]  Ye Wei,et al.  Deep features based on a DCNN model for classifying imbalanced weld flaw types , 2019, Measurement.

[49]  Loris Nanni,et al.  Deep learning and transfer learning features for plankton classification , 2019, Ecol. Informatics.

[50]  Jie Zhang,et al.  Online defect recognition of narrow overlap weld based on two-stage recognition model combining continuous wavelet transform and convolutional neural network , 2019, Comput. Ind..

[51]  Yanling Xu,et al.  Strong noise image processing for vision-based seam tracking in robotic gas metal arc welding , 2018, The International Journal of Advanced Manufacturing Technology.

[52]  Soo-Young Lee,et al.  Hierarchical committee of deep convolutional neural networks for robust facial expression recognition , 2016, Journal on Multimodal User Interfaces.

[53]  Gerardo Beruvides,et al.  Cloud-Based Industrial Cyber–Physical System for Data-Driven Reasoning: A Review and Use Case on an Industry 4.0 Pilot Line , 2020, IEEE Transactions on Industrial Informatics.

[54]  Fei Han,et al.  Efficient network architecture search via multiobjective particle swarm optimization based on decomposition , 2019, Neural Networks.

[55]  Masaki Onishi,et al.  Effective hyperparameter optimization using Nelder-Mead method in deep learning , 2017, IPSJ Transactions on Computer Vision and Applications.

[56]  Guangrui Wen,et al.  Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding , 2019, Journal of Manufacturing Processes.

[57]  Diego Andrade,et al.  Reusing Trained Layers of Convolutional Neural Networks to Shorten Hyperparameters Tuning Time , 2020, ArXiv.

[58]  Shaista Hussain,et al.  Two-Stage Ensemble of Deep Convolutional Neural Networks for Object Recognition , 2018, 2018 International Conference on Intelligent Rail Transportation (ICIRT).

[59]  Alejandro Baldominos Gómez,et al.  Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments , 2018, Sensors.

[60]  Rodolfo E. Haber,et al.  A neural network-based model for the prediction of cutting force in milling process. A progress study on a real case , 2000, Proceedings of the 2000 IEEE International Symposium on Intelligent Control. Held jointly with the 8th IEEE Mediterranean Conference on Control and Automation (Cat. No.00CH37147).

[61]  Soo-Young Lee,et al.  Hierarchical Committee of Deep CNNs with Exponentially-Weighted Decision Fusion for Static Facial Expression Recognition , 2015, ICMI.

[62]  Fulei Chu,et al.  Ensemble deep learning-based fault diagnosis of rotor bearing systems , 2019, Comput. Ind..

[63]  Georgios Kostopoulos,et al.  A Soft-Voting Ensemble Based Co-Training Scheme Using Static Selection for Binary Classification Problems , 2020, Algorithms.

[64]  Rodolfo E. Haber,et al.  Fuzzy Logic-Based Torque Control System for Milling Process Optimization , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[65]  Răzvan Andonie,et al.  Hyperparameter optimization in learning systems , 2019, Journal of Membrane Computing.