TSMS-InceptionNeXt: A Framework for Image-Based Combustion State Recognition in Counterflow Burners via Feature Extraction Optimization
Source abstract
Abstract
The counterflow burner is a combustion device used for research on combustion. By utilizing deep convolutional models to identify the combustion state of a counterflow burner through visible flame images, it facilitates the o... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Combustion and flame dynamics · Advanced Combustion Engine Technologies · Fire dynamics and safety research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (33)
Show source-provided references
1. Local combustion regime identification using machine learning10.1080/13647830.2021.1991595 ↗
2. Machine learning-based classification of combustion events in an RCCI engine using heat release rate shapes
3. Thresholdless Classification of chaotic dynamics and combustion instability via probabilistic finite state automata10.1016/j.ymssp.2021.108213 ↗
4. Detection of slight variations in combustion conditions with machine learning and computer vision10.1016/j.engappai.2023.106772 ↗
5. Evaluating the feasibility of machine learning algorithms for combustion regime classification in biodiesel-fueled homogeneous charge compression ignition engines10.1016/j.fuel.2024.132406 ↗
6. Combustion instability monitoring through deep-learning-based classification of sequential high-speed flame images10.3390/electronics9050848 ↗
7. Data-driven analysis of turbulent flame images
8. Flame image processing and classification using a pre-trained VGG16 model in combustion diagnosis10.3390/s21020500 ↗
9. Convolutional neural networks for identification of moving combustion chambers entering a brazing process10.1016/j.procs.2022.12.309 ↗
10. Pattern analysis of the combustions of various copper concentrate tablets using high-speed microscopy and video-based deep learning10.1016/j.ces.2023.118822 ↗
11. Combustion state identification of MSWI processes using ViT-IDFC10.1016/j.engappai.2023.106893 ↗
12. Artificial neural network aided unstable combustion state prediction and dominant chemical kinetic analysis10.1016/j.ces.2024.120567 ↗
13. Combustion optimization study of pulverized coal boiler based on proximal policy optimization algorithm10.1016/j.applthermaleng.2024.123857 ↗
14. Unsupervised quantitative judgment of furnace combustion state with CBAM-SCAE-based flame feature extraction10.1016/j.joei.2024.101733 ↗
15. Yu F. Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122. 2015.
16. Spatial transformer networks
17. Squeeze-and-excitation networks
18. Shufflenet: an extremely efficient convolutional neural network for mobile devices
19. ECA-Net: efficient channel attention for deep convolutional neural networks
20. Simam: a simple, parameter-free attention module for convolutional neural networks
21. Rotate to attend: convolutional triplet attention module
22. Repvgg: making vgg-style convnets great again
23. Seaformer: squeeze-enhanced axial transformer for mobile semantic segmentation
24. Simplifying and empowering transformers for large-graph representations
25. Vanillanet: the power of minimalism in deep learning
26. Inceptionnext: when inception meets convnext
27. Rethinking the inception architecture for computer vision
28. A convnet for the 2020s
29. Dosovitskiy A. An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv:2010.11929. 2020.
30. Arbitrary shape text detection fusing InceptionNeXt and multi-scale attention mechanism10.1007/s11227-024-06418-w ↗
31. AudioRepInceptionNeXt: a lightweight single-stream architecture for efficient audio recognition10.1016/j.neucom.2024.127432 ↗
32. Lin T. Focal loss for dense object detection. arXiv:1708.02002. 2017.10.1109/ICCV.2017.324 ↗
33. Kang R, Liatsis P, Kyritsis DC. Flame-state monitoring based on very low number of visible or infrared images via few-shot learning. arXiv:2210.07845. 2022.