Task allocation plays an important role in multi-robot systems regarding team efficiency. Conventional heuristic or meta-heuristic methods face difficulties in generating satisfactory solutions in a reasonable computational time, particularly for large-scale multi-robot task allocation problems. This paper proposes a novel graph deep-reinforcement-learning-based approach, which solves the problem through learning. The framework leverages the graph sample and aggregate concept as the encoder to extract the node features in the context of the graph, followed by a cross-attention decoder to output the probability that each task is allocated to each robot. A graph normalization technique is also proposed prior to the input, enabling an easy adaption to real-world applications, and a deterministic solution can be guaranteed. The most important advantage of this architecture is the scalability and quick feed-forward character; regardless of whether cases have a varying number of robots or tasks, single depots, multiple depots, or even mixed single and multiple depots, solutions can be output with little computational effort. The high efficiency and robustness of the proposed method are confirmed by extensive experiments in this paper, and various multi-robot task allocation scenarios demonstrate its advantage.

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.

In the Pu’er tea market, the ubiquity of blending different varieties and the fraudulent representation of vintage years present a persistent challenge. Traditional sensory evaluation and experience are often inadequate for discerning the true variety and vintage of tea, highlighting the need for more sophisticated analytical methods to ensure authenticity and quality. Fourier transform near infrared diffuse reflectance spectroscopy combined with radial basis function neural network (RBFNN) was applied for determination of the varieties and vintages of Pu’er tea. For vintage identification, the accuracy, precision, recall, and F1-score of the RBFNN model for the prediction set were 99.2%, 98.2%, 98.0%, and 98.0%, respectively. For identification of varieties adulteration, the corresponding parameters were 98.9%, 97.2%, 96.7%, and 96.6%, respectively. These results illustrated the feasibility to identify the adulteration of varieties and misrepresentation of vintages of Pu’er tea with near infrared spectra and RBFNN model, proving an efficient alternative for Pu’er tea quality inspection, and offering a robust method for combating the pervasive issues within the market.

Due to fast analysis speed, analyzing composition content of cement raw meal utilizing near infrared (NIR) spectroscopy, combined with partial least squares regression (PLS), is a reliable alternative method for the cement industry to obtain qualified cement products. However, it has hardly been studied. The raw materials employed in different cement plants differ, and the spectral absorption intensity in the NIR range of the raw meal component is weaker than organic substances, although there are obvious absorption peaks, which place high demands on the generality of modeling and accuracy of the analytical model. An effective modeling procedure is proposed, which optimizes the quantitative analytical model from several modeling stages, and two groups of samples with different raw material types and origins are collected to validate it. For the samples in the prediction set from Qufu, the root mean square error of prediction (RMSEP) of CaO, SiO₂, Al₂O₃, and Fe₂O₃ were 0.1910, 0.2307, 0.0921, and 0.0429, respectively; the average prediction errors for CaO, SiO₂, Al₂O₃, and Fe₂O₃ were 0.171%, 0.193%, 0.069%, and 0.032%, respectively; for the samples in the prediction set from Linyi, the RMSEP of CaO, SiO₂, Al₂O₃, and Fe₂O₃ were 0.1995, 0.1267, 0.0336 and 0.0242, respectively, the average prediction errors for CaO, SiO₂, Al₂O₃, and Fe₂O₃ were 0.154%, 0.100%, 0.022%, and 0.018%, respectively. The standard methods for chemical analysis of cement require that the mean measurement error for CaO, SiO₂, Al₂O₃, and Fe₂O₃ should be within 0.40%, 0.30%, 0.20%, and 0.15%, respectively. It is obvious that the results of both groups of samples fully satisfied the requirements of raw material proportioning control of the production line, demonstrating that the modeling procedure has excellent generality, the models established have high prediction accuracy, and the NIR spectroscopy combined with the proposed modeling procedure is a rapid and accurate alternative approach for the analysis of cement raw meal composition content.

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.

Optimization of injection molding process parameters is essential for improving product quality and production efficiency. Traditional methods, which rely heavily on operator experience, often result in inconsistencies, high time consumption, high defect rates, and suboptimal energy consumption. In this study, an improved particle swarm optimization (IPSO) algorithm was proposed, integrating dynamic inertia weight adjustment, adaptive acceleration coefficients, and position constraints to address the issue of premature convergence and enhance global search capabilities. A dual-model architecture was implemented: a constraint validation mechanism based on support vector machine (SVM) was enforced per iteration cycle to ensure stepwise quality compliance, while a fitness function derived by extreme gradient boosting (XGBoost) was formulated to minimize cycle time as the optimization objective. The results demonstrated that the average injection cycle time was reduced by 9.41% while ensuring that the product was qualified. The SVM and XGBoost models achieved high performance metrics (accuracy: 0.92; R²: 0.93; RMSE: 1.05), confirming their robustness in quality classification and cycle time prediction. This method provides a systematic and data-driven solution for multi-objective optimization in injection molding, significantly improving production efficiency and energy utilization.