In this paper, an improved MobileNetV3-Small algorithm model is proposed for the problem of poor real-time wildfire identification based on convolutional neural networks (CNNs). Firstly, a wildfire dataset is constructed and subsequently expanded through image enhancement techniques. Secondly, an efficient channel attention mechanism (ECA) is utilised instead of the Squeeze-and-Excitation (SE) module within the MobileNetV3-Small model to enhance the model’s identification speed. Lastly, a support vector machine (SVM) is employed to replace the classification layer of the MobileNetV3-Small model, with principal component analysis (PCA) applied before the SVM to reduce the dimensionality of the features, thereby enhancing the SVM’s identification efficiency. The experimental results demonstrate that the improved model achieves an accuracy of 98.75% and an average frame rate of 93. Compared to the initial model, the mean frame rate has been elevated by 7.23. The wildfire identification model designed in this paper improves the speed of identification while maintaining accuracy, thereby advancing the development and application of CNNs in the field of wildfire monitoring.

To ensure the economy and safety of the pipelines, the study of the residual strength of corrosion pipelines is key to determining whether the pipelines can continue to operate. There is often a conflict between accuracy and convenience. Artificial intelligence algorithms offer the advantages of high accuracy and ease of use. Therefore, research on the prediction of the residual strength of corroded pipelines using artificial intelligence algorithms is of great significance. CNN and LSTM algorithms are often used to predict the remaining strength of pipelines. However, single CNN models perform poorly in handling time-series data, while LSTM and BiLSTM models also have limitations in processing high-dimensional spatial features. In this article, a pipeline residual strength prediction model based on the CNN-BiLSTM-Adaboost algorithm is proposed. Correlation analysis was used to evaluate the influencing factors of the pipeline’s residual strength, and the CNN algorithm parameters were optimized using BiLSTM and AdaBoost algorithms. The proposed CNN–BiLSTM–AdaBoost evaluation method achieves a significantly improved prediction accuracy for pipeline residual strength, with an average relative error of 4.694%. Our method reduces the predictive error by 28.901%, 43.391%, and 40.753% relative to ASME B31G, DNV RP F101, and PCORRC. This model can predict the residual strength of pipelines conveniently and accurately, minimizing losses caused by corrosion.