{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T14:59:05Z","timestamp":1780844345039,"version":"3.54.1"},"reference-count":26,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T00:00:00Z","timestamp":1610409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Nowadays, despite a negative impact on the natural environment, coal combustion is still a significant energy source. One way to minimize the adverse side effects is sophisticated combustion technologies, such as, e.g., staged combustion, co-combustion with biomass, and oxy-combustion. Maintaining the combustion process at its optimal state, considering the emission of harmful substances, safe operation, and costs requires immediate information about the process. Flame image is a primary source of data which proper processing make keeping the combustion at desired conditions, possible. The paper presents a method combining flame image processing with a deep convolutional neural network (DCNN) that ensures high accuracy of identifying undesired combustion states. The method is based on the adaptive selection of the gamma correction coefficient (G) in the flame segmentation process. It uses the empirically determined relationship between the G coefficient and the average intensity of the R image component. The pre-trained VGG16 model for classification was used. It provided accuracy in detecting particular combustion states on the ranging from 82 to 98%. High accuracy and fast processing time make the proposed method possible to apply in the real systems.<\/jats:p>","DOI":"10.3390\/s21020500","type":"journal-article","created":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T20:11:31Z","timestamp":1610482291000},"page":"500","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Flame Image Processing and Classification Using a Pre-Trained VGG16 Model in Combustion Diagnosis"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6614-7799","authenticated-orcid":false,"given":"Zbigniew","family":"Omiotek","sequence":"first","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, 20-618 Lublin, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9442-6090","authenticated-orcid":false,"given":"Andrzej","family":"Kotyra","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, 20-618 Lublin, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.combustflame.2008.06.010","article-title":"Flame imaging as a diagnostic tool for industrial combustion","volume":"155","author":"Ballester","year":"2008","journal-title":"Combust. Flame"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"513","DOI":"10.3103\/S875669901805014X","article-title":"Combustion Regime Monitoring by Flame Imaging and Machine Learning","volume":"54","author":"Abdurakipov","year":"2018","journal-title":"Optoelectron. Instrum. Data Process."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gangopadhyay, T., Locurto, A., Boor, P., Michael, J.B., and Sarkar, S. (October, January 30). Characterizing Combustion Instability Using Deep Convolutional Neural Network. Proceedings of the ASME 2018 Dynamic Systems and Control Conference, Atlanta, GA, USA.","DOI":"10.1115\/DSCC2018-9208"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.neucom.2017.04.083","article-title":"Early fire detection using convolutional neural networks during surveillance for effective disaster management","volume":"288","author":"Muhammad","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"18174","DOI":"10.1109\/ACCESS.2018.2812835","article-title":"Convolutional Neural Networks Based Fire Detection in Surveillance Videos","volume":"6","author":"Muhammad","year":"2018","journal-title":"IEEE Access"},{"key":"ref_6","first-page":"257","article-title":"Automation of combustion monitoring in boilers using discriminant radial basis network","volume":"3","author":"Sujatha","year":"2013","journal-title":"Int. J. Artif. Intell. Soft Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"8776","DOI":"10.1021\/acs.energyfuels.7b00576","article-title":"Flame Images for Oxygen Content Prediction of Combustion Systems Using DBN","volume":"31","author":"Liu","year":"2017","journal-title":"Energy Fuels"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.ifacol.2018.09.285","article-title":"Image-Based Process Monitoring Using Deep Belief Networks","volume":"51","author":"Lyu","year":"2018","journal-title":"IFAC PapersOnLine"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1080\/00102202.2015.1102905","article-title":"Prediction of NOx Emissions from a Biomass Fired Combustion Process Based on Flame Radical Imaging and Deep Learning Techniques","volume":"188","author":"Li","year":"2016","journal-title":"Combust. Sci. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Qiu, T., Liu, M., Zhou, G., Wang, L., and Gao, K. (2019). An Unsupervised Classification Method for Flame Image of Pulverized Coal Combustion Based on Convolutional Auto-Encoder and Hidden Markov Model. Energies, 12.","DOI":"10.3390\/en12132585"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1016\/j.fuel.2017.03.091","article-title":"Multi-mode combustion process monitoring on a pulverised fuel combustion test facility based on flame imaging and random weight network techniques","volume":"202","author":"Bai","year":"2017","journal-title":"Fuel"},{"key":"ref_12","first-page":"1","article-title":"Prognostics of combustion instabilities from hi-speed flame video using a deep convolutional selective autoencoder","volume":"7","author":"Akintayo","year":"2016","journal-title":"Int. J. Progn. Health Manag."},{"key":"ref_13","unstructured":"Sarkar, S., Lore, K.G., and Sarkar, S. (2015, January 11\u201312). Early detection of combustion instability by neural-symbolic analysis on hi-speed video. Proceedings of the 2015th International Conference on Cognitive Computation: Integrating Neural and Symbolic Approaches, Montreal, QC, Canada."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sarkar, S., Lore, K.G., Sarkar, S., Ramanan, V., Chakravarthy, S.R., Phoha, S., and Ray, A. (2015, January 18\u201324). Early Detection of Combustion Instability from Hi-speed Flame Images via Deep Learning and Symbolic Time Series Analysis. Proceedings of the Annual Conference of the Prognostics and Health Management Society (PHM 2015), Coronado, CA, USA.","DOI":"10.36001\/phmconf.2015.v7i1.2723"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, Y., and He, Z. (2017). Video Object Segmentation through Deep Convolutional Networks. Int. J. Artif. Intell. Tools, 26.","DOI":"10.1142\/S0218213017500166"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ba\u015ftan, M., and Y\u0131lmaz, \u00d6. (2018). Multi-View Product Image Search with Deep ConvNets Representations. Int. J. Artif. Intell. Tools, 27.","DOI":"10.1142\/S021821301850032X"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.apenergy.2017.05.080","article-title":"Image-based deep neural network prediction of the heat output of a step-grate biomass boiler","volume":"200","author":"Garami","year":"2017","journal-title":"Appl. Energy"},{"key":"ref_18","unstructured":"Kotyra, A. (2010). Diagnostyka Procesu Spalania Py\u0142u W\u0119glowego z Wykorzystaniem Metod Przetwarzania Obrazu, Lublin University of Technology."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","article-title":"A threshold selection method from gray-level histograms","volume":"9","author":"Otsu","year":"1979","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1080\/2151237X.2007.10129236","article-title":"Adaptive Thresholding using the Integral Image","volume":"12","author":"Bradley","year":"2007","journal-title":"J. Graph. Tools"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.F. (2009, January 20\u201325). Imagenet: A Large-Scale Hierarchical Image Database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_23","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_24","unstructured":"TensorFlow (2020, August 27). An End-To-End Open Source Machine Learning Platform. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_25","unstructured":"Keras (2020, August 27). The Python Deep Learning API. Available online: https:\/\/keras.io\/."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.energy.2017.05.012","article-title":"Deep learning based monitoring of furnace combustion state and measurement of heat release rate","volume":"131","author":"Wang","year":"2017","journal-title":"Energy"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/2\/500\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:10:09Z","timestamp":1760159409000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/2\/500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,12]]},"references-count":26,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["s21020500"],"URL":"https:\/\/doi.org\/10.3390\/s21020500","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,12]]}}}