dataset of aerodynamic force coefficients and flow fields is generated using Computational Fluid Dynamics (CFD). Three deep learning architectures (U-net, Encoder-Decoder, and Decoder models) are employed and trained to predict the aerodynamic characteristics of Flettner rotors. Three deep learning models are established through a training stage with a hyperparameter study and by altering the number of layers. The aerodynamic force coefficients and flow fields are predicted by established deep learning models and show small absolute errors compared to those from the CFD analysis. Moreover, predicted flow fields reflect the flow characteristics according to the difference of spin ratio and arrangement of Flettner rotors. In conclusion, the established deep learning models demonstrate rapid and robust predictions of aerodynamic force coefficients and flow fields for Flettner rotors under varying arrangements and spin ratios. Furthermore, a significant reduction in computational time is measured when comparing the analysis time of CFD simulations to the training and testing time of the deep learning models.

trustworthy arrival of products on a global scale. Conventional methods of estimating delivery timelines, which are founded upon historical data, possess certain limitations in their ability to handle the intricacies inherent in contemporary textile manufacturing environments. The paper introduces an innovative deep learning model designed for predicting lead time delivery, with the anticipation that this predictive capability will produce a host of advantages. These benefits encompass heightened operational efficiency and elevated levels of customer satisfaction. Methods: To deal with these difficulties, this paper suggests employing deep learning approaches to predict the lead time in the textile industry. The utilization of historical production data obtained from manufacturing execution systems is leveraged for the purpose of training the models. This paper appraises the most advanced approaches in lead-time prediction, delineates a methodology for anticipating textile manufacturing outcomes, and examines the practicality of these methods through experimentation using real-world data. Results: The conducted research compares three advanced models of deep learning with a classical deep learning model. The three models under consideration are Eagle Strategy Slime Mould Algorithm - General Regression Neural Network (ESSMA-GRNN), Eagle Strategy Slime Mould Algorithm - Convolutional Neural Networks (ESSMA-CNN), and Eagle Strategy Slime Mould Algorithm - Generative Adversarial Networks (ESSMA-GAN), in the specific context of predicting lead-time in textile supply chain. The results demonstrate that the ESSMA-GRNN model exhibits high performance in terms of key evaluation measures, such as Mean Squared Error (MSE), Mean Absolute Error (MAE), R-squared, and Explained Variance, when compared to ESSMA-CNN and ESSMA-GAN. Improving the lead time prediction afforded decision-makers the opportunity to overcome delays and establish effective strategies for minimizing lead time. Conclusions: The study highlights the limitations of conventional lead-time estimation approaches and supports the implementation of sophisticated deep learning methods in the textile supply chain. This paper provides practical perspectives for production planners, underscoring the significance of utilizing advanced techniques to surmount the intricacies of the supply chain. The study concludes by proposing future research directions for lead-time prediction and optimization in the textile sector.

strategies. Methods: This research represents an innovative methodology for predicting the risk of late deliveries in supply chains. The presented framework combines clustering and multiclassification techniques, where the clustering phase is executed through hyperparameter optimization and a novel metaheuristic called RIME. In the multiclassification phase, five distinct deep learning models are employed, namely, Generative Adversarial Network (GAN), Convolutional Neural Network Long Short-Term Memory (CNN-LSTM), within Ensemble learning via bagging, Ensemble learning stacking, and Ensemble learning within boosting. The three ensemble learning models are based in GAN and CNN-LSTM. Result: This paper presents a systematic evaluation of diverse models in a risk of late delivery prediction framework. This evaluation demonstrates that Ensemble learning stacking provides the higher accuracy by 0.926, showcasing its prowess in precise predictions. Notably, Ensemble learning bagging and Ensemble learning boosting exhibit strong precision. Regression metrics reveal Ensemble learning stacking and Ensemble learning bagging's superior error minimization (MSE 0.11, MAE 0.09). This metric demonstrates that the proposed model can predict the risk level of late delivery in a supply chain with high precision. Conclusion: This paper introduces an innovative clustering and multiclassification-based framework for predicting the risk of late deliveries. The ability of prediction late deliveries risk helps organizations to enhance supply chain resilience by adopting a proactive management risks strategy, optimizing operational processes, and elevating customer satisfaction.

lumped-parameter model coupled with one-dimensional model (0-1D), whilst a deep learning model for predicting pressure drop (DLM-PD) caused by stenosis and a cerebral autoregulation model (CAM) were introduced into the model. Based on this model, 9 CoW structural models before and after bypass were constructed, to investigate the effects of different CoW structures on cerebral hyperperfusion after bypass. The model and the results were further validated by clinical data. The MSE of mean flow rates from 0-1D model calculation and from clinical measurement was 1.4%. The patients exhibited hyperperfusion in three CoW structures after bypass: missing right anterior segment of the anterior cerebral artery (mRACA1) (13.96% hyperperfusion); mRACA1 and foetal-type right anterior segment of posterior cerebral artery (12.81%), and missing anterior communicating artery and missing left posterior communicating artery (112.41%). The error between the average flow ratio from the model calculations and from clinical measurements was less than 5%. This study demonstrated that the CoW structure had a significant impact on hyperperfusion after bypass. The general 0-1D model coupled with DLM-PD and CAM proposed in this study, could accurately simulate the hemodynamic environment of different CoW structures before and after bypass, which might help physicians identify high-risk patients with hyperperfusion before surgery, and promote the development of non-invasive diagnosis and treatment of cerebrovascular diseases.