Additive manufacturing (AM) technology is extensively utilized in aerospace and industrial manufacturing. However, parts built using AM are susceptible to spheroidization, porosity, cracks, and poor surface quality, making it difficult to establish an actionable product quality degree. Hence, developing a reasonable method to equate product quality with a new degree and further analyzing the product quality based on these standards has proven effective for enhancing part quality in AM. To achieve this goal, this paper proposes a surface roughness classification method that utilizes surface roughness analysis and sample enhancement. This method leverages edge cloud cooperation to efficiently analyze and integrate data from different sensors, enabling real-time monitoring and adjustment of the manufacturing process. Subsequently, the quality degree analysis system was developed utilizing matter-element extension cloud model. Furthermore, a bidirectional-gated recurrent unit (Bi-GRU) based model for quality classification and recognition has been established, with Wasserstein generative adversarial network (WGAN) employed for sample enhancement to address the issue of imbalanced column classification and to enhance the accuracy of both classification and recognition. Finally, the results obtained from this case study demonstrate through comparative experiments that the proposed method for classifying surface roughness can accurately identify 98% of prepared samples.

As significant sources of energy consumption and carbon emissions, data centers have become a focal point for improving energy efficiency worldwide. To address the challenges of high computational resource demands and limited adaptability of traditional prediction models to complex conditions, this paper proposes an artificial intelligence-enabled predictive energy saving planning based on the Transformer-GRU model for predicting coolant temperature in the liquid cooling system of data centers. By integrating the self-attention mechanism of the Transformer and the time-series prediction strengths of GRU, the model performs correlation analysis and feature extraction of key parameters to achieve high-precision predictions of coolant return temperature. Experimental results demonstrate the model’s superior accuracy compared to traditional prediction models, achieving an MSE of 1.349, RMSE of 1.157, MAPE of 0.0244, and R 2 of 81.07 %, significantly outperforming baseline models such as Transformer-LSTM (MSE = 1.355), Informer (MSE = 1.356), Reformer (MSE = 1.353), DeepAR (MSE = 1.385), LSTM (MSE = 1.351), GRU (MSE = 1.366), and CNN-GRU (MSE = 1.363). The model maintains high predictive accuracy under fluctuating environments and complex cooling conditions, effectively reducing the operational energy consumption of the liquid cooling system. This advancement not only enhances cooling efficiency but also drives data centers toward greater intelligence and sustainability. By leveraging real-time monitoring data and predictive control, the model dynamically optimizes cooling strategies, reducing coolant and energy usage while promoting sustainable resource utilization. Additionally, this study offers implementation insights for high-performance computing environments, laying the groundwork for future research on extending model capabilities and integrating multimodal data.