{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:51:55Z","timestamp":1768809115718,"version":"3.49.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006565","name":"University of Johannesburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006565","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Reliable Intell Environ"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The efficacy of vibration-based fault diagnosis using CNN models could be improved through efficient image extraction from the vibration signals. This study proposed a time-frequency domain vibration image extraction framework based on spectral kurtogram to enhance the classification performance of a Bayesian-tuned CNN model in wind turbine gearbox fault diagnostics. Time-frequency domain kurtograms extracted from vibration signals of a wind turbine gearbox are employed to train a CNN model optimized by Bayesian optimization. Findings of the study show that the kurtogram-based CNN model performed better (recording 171 fewer alarms) than a comparable model trained on images extracted from the time domain vibration signals, highlighting the efficacy of the kurtogram method. In a similar fashion, the Bayesian-optimized CNN model with a classification accuracy of 99.1% recorded 79 fewer false alarms than its standalone counterpart which had an accuracy of 93.2%. It can be concluded that the optimized CNN model trained on Kurtograms is a potential tool for reliable vibration-based condition monitoring of the wind turbine gearbox, minimizing the incidence of false alarms.<\/jats:p>","DOI":"10.1007\/s40860-025-00247-1","type":"journal-article","created":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T02:05:36Z","timestamp":1742868336000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Spectral kurtograms for performance enhancement of Bayesian-tuned CNN in wind turbine gearbox fault diagnostics"],"prefix":"10.1007","volume":"11","author":[{"given":"Samuel M.","family":"Gbashi","sequence":"first","affiliation":[]},{"given":"Obafemi O.","family":"Olatunji","sequence":"additional","affiliation":[]},{"given":"Paul A.","family":"Adedeji","sequence":"additional","affiliation":[]},{"given":"Nkosinathi","family":"Madushele","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"247_CR1","unstructured":"Bhandari S (2023) Mechanical fault analysis and detection using Non-Stationary decomposition for vibration signals"},{"key":"247_CR2","unstructured":"Zare S, Ayati M, Ha\u2019iri MR, Yazdi, Anaraki AK (2022) Convolutional neural networks for wind turbine gearbox health monitoring. Energy Equip Syst, 10, 1"},{"key":"247_CR3","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.renene.2022.05.085","volume":"194","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Liu W, Wang X, Gu H (2022) A novel wind turbine fault diagnosis method based on compressed sensing and DTL-CNN. Renew Energy 194:249\u2013258","journal-title":"Renew Energy"},{"key":"247_CR4","doi-asserted-by":"crossref","unstructured":"Krichen M (2023) Convolutional neural networks: A survey. Computers 12. no. 810.3390\/computers12080151","DOI":"10.3390\/computers12080151"},{"key":"247_CR5","doi-asserted-by":"publisher","unstructured":"Gbashi SM, Olatunji OO, Adedeji PA, Madushele N (2023) Hyperparameter optimization on cnn using hyperband for fault identification in wind turbine high-speed shaft gearbox bearing. in Int Conf Electr Comput Energy Technol (ICECET), pp. 1\u20137. https:\/\/doi.org\/10.1109\/ICECET58911.2023.10389387","DOI":"10.1109\/ICECET58911.2023.10389387"},{"key":"247_CR6","doi-asserted-by":"crossref","unstructured":"Adedeji PA, Olatunji OO, Madushele N, Jen T-C (2021) Evolutionary-based hyperparameter tuning in machine learning models for condition monitoring in wind turbines\u2013a survey, in IEEE 12th Int Conf on Mech Intell Manuf Technol (ICMIMT), pp. 254\u2013258","DOI":"10.1109\/ICMIMT52186.2021.9476200"},{"key":"247_CR7","doi-asserted-by":"publisher","first-page":"192248","DOI":"10.1109\/ACCESS.2020.3032719","volume":"8","author":"X Zhang","year":"2020","unstructured":"Zhang X, Han P, Xu L, Zhang F, Wang Y, Gao L (2020) Research on bearing fault diagnosis of wind turbine gearbox based on 1DCNN-PSO-SVM. IEEE Access 8:192248\u2013192258","journal-title":"IEEE Access"},{"issue":"4","key":"247_CR8","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1007\/s00521-023-09168-7","volume":"36","author":"A Kara","year":"2024","unstructured":"Kara A, Pekel E, Ozcetin E, Y\u0131ld\u0131z GB (2024) Genetic algorithm optimized a deep learning method with attention mechanism for soil moisture prediction. Neural Comput Appl 36(4):1761\u20131772","journal-title":"Neural Comput Appl"},{"issue":"6","key":"247_CR9","first-page":"77","volume":"41","author":"C Miao","year":"2021","unstructured":"Miao C, Yan-Xia S (2021) Fault diagnosis strategy ofwind turbine bearings based on bayesian optimized CNN# Br. Noise Vib Control 41(6):77","journal-title":"Noise Vib Control"},{"key":"247_CR10","doi-asserted-by":"crossref","unstructured":"Amin A, Bibo A, Panyam M, Tallapragada P (2023) A bayesian deep learning framework for reliable fault diagnosis in wind turbine gearboxes under various operating conditions. Wind Eng, p. 0309524X231206723","DOI":"10.1177\/0309524X231206723"},{"key":"247_CR11","doi-asserted-by":"publisher","first-page":"114022","DOI":"10.1016\/j.eswa.2020.114022","volume":"167","author":"TW Rauber","year":"2021","unstructured":"Rauber TW, da Silva Loca AL, de Assis Boldt F, Rodrigues AL, Varej\u00e3o FM (2021) An experimental methodology to evaluate machine learning methods for fault diagnosis based on vibration signals. Expert Syst Appl 167:114022","journal-title":"Expert Syst Appl"},{"key":"247_CR12","doi-asserted-by":"crossref","unstructured":"Salata G, Cenkeramaddi LR, Robbersmyr KG, Jha A (2023) Time-frequency analysis and fault prediction of motor bearings using millimeter wave radar. IEEE Sens J","DOI":"10.1109\/JSEN.2023.3292899"},{"key":"247_CR13","doi-asserted-by":"crossref","unstructured":"Bai Y, Cheng W, Wen W, Liu Y (2023) Application of time-frequency analysis in rotating machinery fault diagnosis, Shock Vib., vol. 2023","DOI":"10.1155\/2023\/9878228"},{"key":"247_CR14","doi-asserted-by":"crossref","unstructured":"Gbashi SM, Madushele N, Olatunji OO, Adedeji PA, Jen T (2022) Wind turbine main bearing: a mini review of its failure modes and condition monitoring techniques, in ICMIMT","DOI":"10.1109\/ICMIMT55556.2022.9845317"},{"key":"247_CR15","doi-asserted-by":"publisher","unstructured":"Gbashi SM, Olatunji OO, Adedeji PA, Madushele N (2023) A hybrid empirical mode decomposition (EMD)-support vector machine (SVM) for multi-fault recognition in a wind turbine gearbox, in Int Conf Electr Comp Energy Technol (ICECET), pp. 1\u20137. https:\/\/doi.org\/10.1109\/ICECET58911.2023.10389608","DOI":"10.1109\/ICECET58911.2023.10389608"},{"key":"247_CR16","doi-asserted-by":"publisher","first-page":"103791","DOI":"10.1016\/j.rineng.2024.103791","volume":"25","author":"SM Gbashi","year":"2025","unstructured":"Gbashi SM, Adedeji PA, Olatunji OO, Madushele N (2025) Optimal feature selection for a weighted k-nearest neighbors for compound fault classification in wind turbine gearbox. Results Eng 25:103791","journal-title":"Results Eng"},{"issue":"6","key":"247_CR17","first-page":"99","volume":"31","author":"GU Yingkui","year":"2021","unstructured":"Yingkui GU, Ping LIU, Zhonghai LIN, Guangqi QIU (2021) Fault diagnosis method of rolling bearing based on kurtogram and DSCN. China Saf Sci J 31(6):99","journal-title":"China Saf Sci J"},{"key":"247_CR18","doi-asserted-by":"crossref","unstructured":"Prosvirin A, Kim J, Kim J-M (2018) Bearing fault diagnosis based on convolutional neural networks with kurtogram representation of acoustic emission signals, in advances in Comput Sci Ubiquitous Comput: CSA-CUTE 17, pp. 21\u201326","DOI":"10.1007\/978-981-10-7605-3_4"},{"key":"247_CR19","first-page":"1","volume":"4","author":"V Kehri","year":"2020","unstructured":"Kehri V, Awale RN (2020) A facial EMG data analysis for emotion classification based on spectral kurtogram and CNN. Int J Digit Signals Smart Syst 4:1\u20133","journal-title":"Int J Digit Signals Smart Syst"},{"key":"247_CR20","doi-asserted-by":"crossref","unstructured":"Link H et al (2011) Gearbox reliability collaborative project report: findings from phase 1 and phase 2 testing. Natl Renew Energy Lab (NREL), Golden, CO (United States)","DOI":"10.2172\/1018489"},{"key":"247_CR21","doi-asserted-by":"publisher","first-page":"113192","DOI":"10.1016\/j.combustflame.2023.113192","volume":"259","author":"D Nayak","year":"2024","unstructured":"Nayak D, Jonnalagadda A, Balakrishnan U, Kolla H, Aditya K (2024) A co-kurtosis PCA based dimensionality reduction with nonlinear reconstruction using neural networks. Combust Flame 259:113192","journal-title":"Combust Flame"},{"issue":"2","key":"247_CR22","doi-asserted-by":"publisher","first-page":"376","DOI":"10.3390\/electronics13020376","volume":"13","author":"J-H Kim","year":"2024","unstructured":"Kim J-H, Kwon S-Y, Kim H-N (2024) Spectral-Kurtosis and Image-Embedding approach for target classification in Micro-Doppler signatures. Electronics 13(2):376","journal-title":"Electronics"},{"issue":"2","key":"247_CR23","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.ymssp.2004.09.001","volume":"20","author":"J Antoni","year":"2006","unstructured":"Antoni J (2006) The spectral kurtosis: a useful tool for characterising non-stationary signals. Mech Syst Signal Process 20(2):282\u2013307","journal-title":"Mech Syst Signal Process"},{"key":"247_CR24","doi-asserted-by":"crossref","unstructured":"Liu Z (2024) A nonlinear AutoRegressive-based noise cancellation method for Real-time fault diagnosis of rolling bearings. IEEE Trans Instrum Meas","DOI":"10.1109\/TIM.2024.3353832"},{"key":"247_CR25","doi-asserted-by":"publisher","first-page":"109537","DOI":"10.1016\/j.apacoust.2023.109537","volume":"211","author":"P Shi","year":"2023","unstructured":"Shi P, He J, Xu X, Han D (2023) A novel feature enhancement framework for rotating machinery fault identification under limited datasets. Appl Acoust 211:109537","journal-title":"Appl Acoust"},{"key":"247_CR26","doi-asserted-by":"publisher","unstructured":"Tao H, Jia P, Wang X, Wang L (2024) Real-Time fault diagnosis for hydraulic system based on Multi-Sensor convolutional neural network. Sensors 24(2). https:\/\/doi.org\/10.3390\/s24020353","DOI":"10.3390\/s24020353"},{"key":"247_CR27","doi-asserted-by":"crossref","unstructured":"Wang X, Jin Y, Schmitt S, Olhofer M (2023) Recent advances in Bayesian optimization, ACM Comput. Surv., vol. 55, no. 13s, pp. 1\u201336","DOI":"10.1145\/3582078"},{"key":"247_CR28","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1016\/j.eswa.2018.08.023","volume":"115","author":"T Theckel Joy","year":"2019","unstructured":"Theckel Joy T, Rana S, Gupta S, Venkatesh S (2019) A flexible transfer learning framework for bayesian optimization with convergence guarantee. Expert Syst Appl 115:656\u2013672. https:\/\/doi.org\/10.1016\/j.eswa.2018.08.023","journal-title":"Expert Syst Appl"},{"key":"247_CR29","unstructured":"Rempling R, Gustavsson E, Jirstrand M (2020) Multi-objective constrained bayesian optimization for structural design"},{"key":"247_CR30","doi-asserted-by":"crossref","unstructured":"Dai B, Peng Y, Lin N, Wang P (2023) Bearing Fault Diagnosis Based on Prime Mean Spectral Segmentation Kurtogram, in Journal of Physics: Conference Series, vol. 2419, no. 1, p. 12080","DOI":"10.1088\/1742-6596\/2419\/1\/012080"}],"container-title":["Journal of Reliable Intelligent Environments"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40860-025-00247-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40860-025-00247-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40860-025-00247-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T05:01:59Z","timestamp":1750741319000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40860-025-00247-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["247"],"URL":"https:\/\/doi.org\/10.1007\/s40860-025-00247-1","relation":{},"ISSN":["2199-4668","2199-4676"],"issn-type":[{"value":"2199-4668","type":"print"},{"value":"2199-4676","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"19 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"7"}}