Top

Soft Computing

Published in:

27-01-2022 | Application of soft computing

Recognition of shed damage on 11-kV polymer insulator using Bayesian optimized convolution neural network

Authors: B. Vigneshwaran, M. Willjuice Iruthayarajan, R. V. Maheswari

Published in: Soft Computing | Issue 14/2022

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Measurement and recognition of partial discharge (PD) in power apparatus are considered a protuberant tool for condition monitoring and assessing the state of a dielectric system. Several machine learning (ML) approaches are used for recognizing the status of the 11-kV high-voltage (HV) polymer insulator in the past decades. However, ML techniques mainly depend upon feature extraction by human experts. Recent advancement shows that usage of deep learning (DL) methods to predict the type of faults that occur in the power apparatus has attracted much attention. Compared to the machine learning (ML) algorithm, DL is very sensitive in choosing the hyperparameters. Two majors confront when applying the DL for shed damage prediction: First is very hard to find optimal network depth of convolution neural network (CNN) architecture, and second is a selection of hyperparameters during the training of the network. In this proposed work, Bayesian optimization (BO) is considered as the most popular technique for hyperparameters optimization (HO) in CNN. Meanwhile, the proposed algorithm with Nadam training optimizers shows the higher recognition rate of 99.68% compared to other training optimizers.

previous article Load-settlement response of a footing over buried conduit in a sloping terrain: a numerical experiment-based artificial intelligent approach

next article Enhanced heat transfer search and enriched replicated coronary circulation system optimization algorithms for real power loss reduction

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Allahbakhshi M, Akbari A (2011) A method for discriminating original pulses in online partial discharge measurement. Measurement 44(1):148–158CrossRef

Appana DK, Prosvirin A, Kim J (2018) Reliable fault diagnosis of bearings with varying rotational speeds using envelope spectrum and convolution neural networks. Soft Comput 22:6719–6729. https://doi.org/10.1007/s00500-018-3256-0CrossRef

Ardila-Rey JA, Martinez-Tarifa JM, Robles G (2015) Automatic selection of frequency bands for the power ratios separation technique in partial discharge measurements: part II, PD source recognition and applications. IEEE Trans Dielectr Electr Insul 22(4):2293–2301CrossRef

Ardila-Rey A, Martínez-Tarifa JM, Robles G, Rojas Moreno MV (2013) Partial discharge and noise separation by means of spectral power clustering techniques. IEEE Trans Dielectr Electr Insul 20(4):1436–1443CrossRef

Basharan V, Siluvairaj WIM, Ramasamy VM (2018) ‘Recognition of multiple partial discharge patterns by multi-class support vector machine using fractal image processing technique. IET Sci Meas Technol 12(8):1031–1038CrossRef

Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305MathSciNetMATH

Bhanja CC, Bisharad D, Laskar RH (2019) Deep residual networks for pre-classification based Indian language identification. J Intell Fuzzy Syst 36(3):2207–2218CrossRef

Bouti A, Mahraz MA, Riffi J et al (2020) A robust system for road sign detection and classification using LeNet architecture based on convolutional neural network. Soft Comput 24:6721–6733. https://doi.org/10.1007/s00500-019-04307-6CrossRef

Chen J, Xu X, Dang H (2019) Fault detection of insulators using second-order fully convolutional network model. Math Probl Eng Volume 2019, Article ID 6397905, pp. 1-10, https://doi.org/10.1155/2019/6397905

Cho H, Kim Y, Lee E, Choi D, Lee Y, Rhee W (2020) Basic enhancement strategies when using bayesian optimization for hyperparameter tuning of deep neural networks. IEEE Access Spec Sect Scalable Deep Learn Big Data 8:52588–52608

Darwish A, Ezzat D, Hassanien AE (2020) An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis. Swarm Evolut Comput 52:100616CrossRef

Ding L et al (2018) A deep hybrid learning model to detect unsafe behavior: integrating convolution neural networks and long short-term memory. Autom Constr 86:118–124CrossRef

Dozat T (2016) Incorporating Nesterov Momentum into Adam. In: Proceedings of the 4th international conference on learning representations, Workshop Track, San Juan, Puerto Rico, 2–4

Ezzat D, Hassanien AE, Ella HA (2020) An optimized deep learning architecture for the diagnosis of COVID-19 disease based on gravitational search optimization. Appl Soft Comput J. https://doi.org/10.1016/j.asoc.2020.106742CrossRef

Fradi M, Khriji L, Machhout M, Hossen A (2021) Automatic heart disease class detection using convolutional neural network architecture-based various optimizers-networks. IET Smart Cities 3:3–15CrossRef

Gao XW, Hui R, Tian Z (2017) Classification of ct brain images based on deep learning networks. Comput Methods Progr Biomed 138:49–56CrossRef

Gomathy M (2021) Optimal feature selection for speech emotion recognition using enhanced cat swarm optimization algorithm. Int J Speech Technol. https://doi.org/10.1007/s10772-020-09776-xCrossRef

Guo Y, Wang X, Xiao P et al (2020) An ensemble learning framework for convolutional neural network based on multiple classifiers. Soft Comput 24:3727–3735. https://doi.org/10.1007/s00500-019-04141-wCrossRef

Holland J (1975) Adaptation in Natural and Artificial Systems, University of Michigan Press.

Jadhav P, Rajguru G, Datta D, Mukhopadhyay S (2020) Automatic sleep stage classification using time–frequency images of CWT and transfer learning using convolution neural network. Bio Cybern Biomed Eng 40:494–504

Janani H, Kordi B (2018) Towards automated statistical partial discharge source classification using pattern recognition techniques. IET High Voltage 3(3):162–169CrossRef

Janani H, Kordi B, Jozani MJ (2017) Classification of simultaneous multiple partial discharge sources based on probabilistic interpretation using a two-step logistic regression algorithm. IEEE Trans Dielectr Electr Insul 24(1):54–65CrossRef

Janani H, Shahabi S, Kordi B (2020) Separation and classification of concurrent partial discharge signals using statistical-based feature analysis. IEEE Trans Dielectr Electr Insul 27(6):1933–1941CrossRef

Kandel I, Castelli M, Popovič A (2020) Comparative study of first order optimizers for image classification using convolutional neural networks on histopathology images. J Imaging 6(9):92. https://doi.org/10.3390/jimaging6090092CrossRef

Lan K, Liu L, Li T, Chen Y, Fong S, Marques JAL, Wong RK, Tang R (2020) Multi-view convolutional neural network with leader and long-tail particle swarm optimizer for enhancing heart disease and breast cancer detection. Neural Comput Appl. https://doi.org/10.1007/s00521-020-04769-yCrossRef

Li J, He D (2020) A Bayesian optimization AdaBN-DCNN method with self-optimized structure and hyperparameters for domain adaptation remaining useful life prediction. IEEE Access 8:41482–41501CrossRef

Lu S, Chai H, Sahoo A, Phung BT (2020) Condition Monitoring Based on Partial Discharge Diagnostics Using Machine Learning Methods: A Comprehensive State-of-the-Art Review. IEEE Trans Dielectr Electr Insul 27(6):1861–1888CrossRef

Maheswari RV, Subburaj P, Vigneshwaran B, Kalaivani L (2014) Non linear support vector machine based partial discharge patterns recognition using fractal features. J Intell Fuzzy Syst 27(5):2649–2664CrossRef

Peng C, Zhe Z, Rui L, Cheng C, Shaokang C (2020) A CNN recognition method for early stage of 10 kV single core cable based on sheath current. Electric Power Syst Res 184:1–9

Raymond WJK, Illias HA, Bakar AHA (2017) ‘High noise tolerance feature extraction for partial discharge classification in XLPE cable joints.’ IEEE Trans Dielectr Electr Insul 24(1):66–74CrossRef

Rostaminia R, Saniei M, Vakilian M, Mortazavi SS, Parvin V (2016) Accurate power transformer PD pattern recognition via its model. IET Sci Meas Technol 10(7):745–753CrossRef

Shahriari B, Swersky K, Wang Z, Adams RP, de Freitas N (2016) Taking the human out of the loop: A review of Bayesian optimization. Proc IEEE 104(1):148–175CrossRef

Silva GLF, da Silva Neto OP, Silva AC, de Paiva AC, Gattass M (2017) Lung nodules diagnosis based on evolutionary convolutional neural network. Multimed. Tools Appl. 76(18):19039–19055CrossRef

Singh P, Chaudhury S, Panigrahi BK (2021) Hybrid MPSO-CNN: Multi-level Particle Swarm optimized hyperparameters of Convolutional Neural Network. Swarm Evolut Comput 63:100863CrossRef

Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. In: Proc. Adv. Neural Inf. Process. Syst., pp. 2951_2959

Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958MathSciNetMATH

Strau S (2018) From big data to deep learning: a leap towards strong AI or “intelligentia obscura”? Big Data Cognit Comput 2(3):16. https://doi.org/10.3390/bdcc2030016CrossRef

Sulthana AR, Gupta M, Subramanian S et al (2020) Improvising the performance of image-based recommendation system using convolution neural networks and deep learning. Soft Comput. https://doi.org/10.1007/s00500-020-04803-0CrossRef

Sun Y, Xue B, Zhang M, Yen Gary G (2019) Evolving deep convolutional neural networks for image classification. IEEE Trans Evolut Comput 24(2):394–407CrossRef

Vigneshwaran B, Maheswari RV, Kalaivani L et al (2021) Recognition of pollution layer location in 11 kV polymer insulators used in smart power grid using dual-input VGG Convolutional Neural Network. Energy Rep. https://doi.org/10.1016/j.egyr.2020.12.044CrossRef

Vigneshwaran B, Willjuice Iruthayarajan M, Maheswari RV (2019) Partial discharge pattern analysis using multi-class support vector machine to estimate cavity size and position in solid insulation. Soft Comput. https://doi.org/10.1007/s00500-019-04570-7CrossRef

Yang H, Jiao S, Sun P (2020) Bayesian-convolutional neural network model transfer learning for image detection of concrete water-binder ratio. IEEE Access 8:35350–35367CrossRef

Yangke H, Zhiming W (2020) Multi-granularity pruning for deep residual networks. J Intell Fuzzy Syst 39(5):7403–7410CrossRef

Zatarain Cabada R, Rodriguez Rangel H, Barron Estrada ML et al (2020) Hyperparameter optimization in CNN for learning-centered emotion recognition for intelligent tutoring systems. Soft Comput 24:7593–7602. https://doi.org/10.1007/s00500-019-04387-4CrossRef

Zhou W, Liu Y, Li P, Wang Y, Tian Y (2017) Feature parameters extraction of power transformer PD signal based on texture features in TF representation. IET Sci Meas Technol 11(4):445–452CrossRef

Title: Recognition of shed damage on 11-kV polymer insulator using Bayesian optimized convolution neural network
Authors: B. Vigneshwaran
M. Willjuice Iruthayarajan
R. V. Maheswari
Publication date: 27-01-2022
Publisher: Springer Berlin Heidelberg
Published in: Soft Computing / Issue 14/2022
Print ISSN: 1432-7643
Electronic ISSN: 1433-7479
DOI: https://doi.org/10.1007/s00500-021-06629-w

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Other articles of this Issue 14/2022

A quantum system control method based on enhanced reinforcement learning

A method to determine the integrated weights of cross-efficiency aggregation

Comparison of subsidy strategies on the green supply chain under a behaviour-based pricing model

Regular and strongly regular relations induced by fuzzy subhypermodules

Identification of nonlinear discrete systems using a new Hammerstein model with Volterra neural network

Ramp loss KNN-weighted multi-class twin support vector machine

Premium Partner