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 optimization of the combustion process and enhances combustion efficiency. Among existing deep convolutional models, InceptionNeXt is a deep learning architecture that integrates the ideas of the Inception series and ConvNeXt. It has garnered significant attention for its computational efficiency, remarkable model accuracy, and exceptional feature extraction capabilities. However, since this model still has limitations in the combustion state recognition task, we propose a Triple-Scale Multi-Stage InceptionNeXt (TSMS-InceptionNeXt) combustion state recognition method based on feature extraction optimization. First, to address the InceptionNeXt model’s limited ability to capture dynamic features in flame images, we introduce Triplet Attention, which applies attention to the width, height, and Red Green Blue (RGB) dimensions of the flame images to enhance its ability to model dynamic features. Secondly, to address the issue of key information loss in the Inception deep convolution layers, we propose a Similarity-based Feature Concentration (SimC) mechanism to enhance the model’s capability to concentrate on critical features. Next, to address the insufficient receptive field of the model, we propose a Multi-Scale Dilated Channel Parallel Integration (MDCPI) mechanism to enhance the model’s ability to extract multi-scale contextual information. Finally, to address the issue of the model’s Multi-Layer Perceptron Head (MlpHead)neglecting channel interactions, we propose a Channel Shuffle-Guided Channel-Spatial Attention (ShuffleCS) mechanism, which integrates information from different channels to further enhance the representational power of the input features. To validate the effectiveness of the method, experiments are conducted on the counterflow burner flame visible light image dataset. The experimental results show that the TSMS-InceptionNeXt model achieved an accuracy of 85.71% on the dataset, improving by 2.38% over the baseline model and outperforming the baseline model’s performance. It achieved accuracy improvements of 10.47%, 4.76%, 11.19%, and 9.28% compared to the Reparameterized Visual Geometry Group (RepVGG), Squeeze-erunhanced Axial Transoformer (SeaFormer), Simplified Graph Transformers (SGFormer), and VanillaNet models, respectively, effectively enhancing the recognition performance for combustion states in counterflow burners.

Electrolysis tanks are used to smelt metals based on electrochemical principles, and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures, thus affecting normal production. Aiming at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks, an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5 (YOLOv5) is proposed. Firstly, we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network (Real-ESRGAN) by changing the U-shaped network (U-Net) to Attention U-Net, to preprocess the images; secondly, we propose a new Focus module that introduces the Marr operator, which can provide more boundary information for the network; again, because Complete Intersection over Union (CIOU) cannot accommodate target borders that are increasing and decreasing, replace CIOU with Extended Intersection over Union (EIOU), while the loss function is changed to Focal and Efficient IOU (Focal-EIOU) due to the different difficulty of sample detection. On the homemade dataset, the precision of our method is 94%, the recall is 70.8%, and the map@.5 is 83.6%, which is an improvement of 1.3% in precision, 9.7% in recall, and 7% in map@.5 over the original network. The algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection, which can lay a technical foundation for improving production efficiency and reducing production waste.