基于轻量化网络的陶瓷辊道窑火焰图像识别方法Flame Image Recognition Method of Ceramic Roller Kiln Based on Lightweight Convolutional Neural Network
朱永红,杨荣杰,段明明
摘要(Abstract)：
针对热电偶在陶瓷辊道窑高温环境下容易腐蚀老化，导致其温度检测精度下降的问题，提出采用计算机视觉火焰检测代替热电偶的陶瓷辊道窑温度智能检测方法。该方法是一种基于新型轻量化卷积神经网络，通过减少网络深度，以及采用大卷积核的设计，避免模型的过拟合现象，减少了模型的复杂度和推算时间，使模型实现了检测准确性的提升。实验结果表明：该新型轻量化卷积神经网络相比原始MobelinetV2模型，识别特征平均准确率提升了4.58%、平均相对误差减少了0.0918%、运算时间减少了41.89%。显然，该新型网络模型使运算速度和分类性能大大提高。
关键词(KeyWords)： 陶瓷辊道窑;轻量化卷积神经网络;火焰图像识别;温度检测
基金项目(Foundation): 国家自然科学基金(62063010,62062044);; 江西省自然科学基金(20202BABL202010)
作者(Author): 朱永红,杨荣杰,段明明
DOI: 10.13958/j.cnki.ztcg.2023.03.001
参考文献(References)：
- [1]陈华,章兢,张小刚,等.一种基于Parzen窗估计的鲁棒ELM烧结温度检测方法[J].自动化学报, 2012, 38(5):841-849.
- [2] LI W T, WANG D H, CHAI T Y. Burning state recognition of rotary kiln using ELMs with heterogeneous features[J].Neurocomputing, 2013, 102:144-153.
- [3] LI W T, WANG D H, CHAI T Y. Flame image-based burning state recognition for sintering process of rotary kiln using heterogeneous features and fuzzy integral[J]. IEEE Transactions on Industrial Informatics, 2012, 8(4):780-790.
- [4] GUO S Y, SHENG Y X, CHAI L. SVD-based burning state recognition in rotary kiln using machine learning[C]//The12th IEEE Conference on Industrial Electronics and Applications, Siem Reab, Cambodia,2017:154-158.
- [5]周晓杰,蔡元强,夏克江,等.基于火焰图像显著区域特征学习与分类器融合的回转窑烧结工况识别[J].控制与决策, 2017, 32(1):187-192.
- [6] WANG Z Y, SONG C F, CHEN T. Deep learning based monitoring of furnace combustion state and measurement of heat release rate[J]. Energy, 2017, 131:106-112.
- [7] HU Y C, ZHENG W H, WANG X, et al. Working condition recognition based on transfer learning and attention mechanism for a rotary kiln[J]. Entropy, 2022, 24(9):1186.
- [8] LI G, ZHANG H X, E L N, et al. Recognition of honeycomb lung in CT images based on improved MobileNet model[J].Medical Physics, 2021, 48(8):4304-4315.
- [9]李丽圆,李潇雁,胡琸悦,等.基于回归模型与注意力的轻量化SAR舰船检测模型[J].红外与毫米波学报, 2022,41(3):618-625.
- [10] SANDLER M, HOWARD A, ZHU M L, et al. Mobilenetv2:Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, 2018:4510-4520.
- [11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90.
- [12] RUSSAKOVSKY O, DENG J, SU H, et al. Image Net large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252.
- [13] HOWARD A G, ZHU M L, CHEN B, et al. Mobilenets:Efficient convolutional neural networks for mobile vision applications[EB/OL].[2017-04-17]. https://arxiv.org/abs/1704.04861
- [14] DING X H, ZHANG X Y, HAN J G, et al. Scaling up your kernels to 31×31:revisiting large kernel design in CNNs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, Louisiana, 2022:11963-11975.
- [15] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas, Nevada, 2016:770-778.
- [16] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, 2017:4700-4708.
- [17] ZHOU B L, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, 2016:2921-2929.