Accurate power load forecasting can provide crucial insights for power system scheduling and energy planning. In this paper, to address the problem of low accuracy of power load prediction, we propose a method that combines secondary data cleaning and adaptive variational mode decomposition (VMD), convolutional neural networks (CNN), bi-directional long short-term memory (BILSTM), and adding attention mechanism (AM). The Inner Mongolia electricity load data were first cleaned use the K-means algorithm, and then further refined with the density-based spatial clustering of applications with the noise (DBSCAN) algorithm. Subsequently, the parameters of the VMD algorithm were optimized using a multi-strategy Cubic-T dung beetle optimization algorithm (CTDBO), after which the VMD algorithm was employed to decompose the twice-cleaned load sequences into a number of intrinsic mode functions (IMFs) with different frequencies. These IMFs were then used as inputs to the CNN-BILSTM-Attention model. In this model, a CNN is used for feature extraction, BILSTM for extracting information from the load sequence, and AM for assigning different weights to different features to optimize the prediction results. It is proved experimentally that the model proposed in this paper achieves the highest prediction accuracy and robustness compared to other models and exhibits high stability across different time periods.

A novel series of biocomposites was prepared through the utilisation of hot-pressing and blending methods, utilising bamboo particles of varying sizes and a zein solution. The influence of particle size and the parameters of hot pressing on the mechanical properties of the composites was investigated through the application of an alkali solution to pre-treat the bamboo particles and the employment of ultra-high pressure to pre-handle the zein solution. Four response surface models were established to optimise the processing parameters based on mechanical testing experiments and quadratic regression analysis. The influencing factors were moisture content, press temperature, and press time, and the responses were modulus of rupture (MOR), modulus of elasticity (MOE), tensile strength (TS) and 2 h thickness swelling rate (2h-TSR). The findings indicated that the TS of composites reached a maximum value of 17.5 MPa with a bamboo particle size of 40 mesh; the MOR and MOE of composites reached a maximum value of 28.72 MPa and 2669.75 MPa when the bamboo particle size was 60 mesh; regarding the 2h-TSR of composites the lowest value of 5.8% was obtained for 80-mesh bamboo particle size. The optimum moulding process parameters were obtained with moisture content ranging from 14% to 16%, press temperature ranging from 170 °C to 175 °C, and press time ranging from 12 min to 15 min, respectively.

Fault diagnosis methods based on deep learning have made certain progress in recent years. However, in actual industrial scenarios, there are severe strong background noise and limited computing resources, which poses challenges to the practical application of fault diagnosis models. In response to the above issues, this paper proposes a novel noise-resistant and lightweight fault diagnosis framework with nonlinear timestep degenerative greedy strategy (NTDGS) and dual residual horizontal feature pyramid (DRHFPN) for fault diagnosis in strong noise scenarios. This method takes advantage of the strong fitting ability of deep learning methods to model the agent in reinforcement learning by the ways of parameterization, fully leveraging the advantages of both deep learning and reinforcement learning methods. NTDGS is further developed to adaptively adjust the action sampling strategy of the agent at different training stages, improving the convergence speed of the network. To enhance the noise resistance of the network, DRHFPN is constructed, which can filter out interference noise at the feature map level by fusing local feature details and global semantic information. Furthermore, the feature map weighting attention mechanism (FMWAM) is designed to enhance the weak feature extraction ability of the network through adaptive weighting of the feature maps. Finally, the performance of the proposed method is evaluated in different datasets and strong noise environments. Experiments show that in various fault diagnosis scenarios, the proposed method has better noise resistance, higher fault diagnosis accuracy, and fewer parameters compared to other methods.