Simple trigger logic is commonly used in actual wind farms to monitor unit conditions, which face problems such as a high false-alarm rate and overlapping alarms. In addition, the characteristics of SCADA data, such as large quantity, complexity, and variable correlation, lead to insufficient accuracy of fault diagnosis. To address this problem, an improved fault diagnosis method based on a Multi-Channel Attention Mechanism Convolutional Neural Network (MCAMCNN) is proposed. Firstly, feature analysis is performed after preprocessing SCADA data to fully explore the coupling characteristics between data, and a dataset is established. Then, the proposed fault diagnosis model is used for feature screening. Innovatively, a structure combining double-layer multi-scale convolution and multi-channel attention is adopted to extract multi-domain features and dynamically calibrate the weights of feature channels. Fault classification is realized after adaptive fusion of features by Efficient Channel Attention (ECA). Finally, experiments are designed based on real data from an onshore wind farm in China, which verify that the method is timely and accurate in fault diagnosis, with significantly improved accuracy and F1-score, and has obvious advantages over comparative methods.

The rapid development of high-end equipment has created stringent requirements for multifunctional integration in materials. However, traditional porous materials have faced a fundamental trade-off between lightweight characteristics and mechanical and acoustic performance. To address this challenge, a design and fabrication method for interpenetrating phase composites (IPCs) based on triply periodic minimal surface (TPMS) structures was proposed. The effects of porosity, unit cell size, and structural type on the performance of porous structures were systematically investigated. TPMS frameworks were fabricated from AlSi7Mg alloy using laser powder bed fusion (LPBF). These frameworks were then combined with thermoplastic polyurethane (TPU) via a foaming infiltration process to create the AlSi7Mg/TPU IPCs. Acoustic and compression tests were performed using an impedance tube and a universal testing machine. The results indicated that, compared to unfilled TPMS structures, the IPCs exhibited a shift in the first peak acoustic absorption coefficient to lower frequencies, an increase (1.59 = fold) in the average acoustic absorption coefficient within the 500–6300 Hz range, and a significant enhancement (35.58 fold) in the average normal incidence transmission loss (TL). Under quasi-static compression, the plateau stage was sustained over 60% strain, and the energy absorption capacity increased by a factor of 3.56. This research provides a technical reference for developing multifunctional materials for aerospace and other acoustic applications.

In response to the problem of large time-delays in cement kilns, a dynamic time-delay calculation algorithm based on MI and adaptive sliding windows is proposed. For cement rotary kiln temperatures that are difficult to measure and that are influenced by historical time series data, a modelling algorithm for residual network and bidirectional novel gated recurrent unit is proposed. To address the problem of cement rotary kilns that produce a wide range of operating conditions, a Gaussian-weighted multi-model fusion method is proposed. To verify the advantages and feasibility of the proposed method, experimental validation is carried out using original production data from a large cement manufacturing enterprise in South China. The results demonstrate that the presented approach can predict cement kiln temperatures quickly and accurately. This will provide an effective solution for online decision-making during actual cement production.