Search

Forecasting energy demand is critical to ensure the steady operation of the power system. However, present approaches to estimating power load are still unsatisfactory in terms of accuracy, precision, and efficiency. In this paper, we propose a novel method, named ELFNet, for estimating short-term electricity consumption, based on the deep convolutional neural network model with a double-attention mechanism. The Gramian Angular Field method is utilized to convert electrical load time series into 2D image data for input into the proposed model. The prediction accuracy is greatly improved through the use of a convolutional neural network to extract the intrinsic characteristics from the input data, along with channel attention and spatial attention modules, to enhance the crucial features and suppress the irrelevant ones. The present ELFNet method is compared to several classic deep learning networks across different prediction horizons using publicly available data on real power demands from the Belgian grid firm Elia. The results show that the suggested approach is competitive and effective for short-term power load forecasting. [ABSTRACT FROM AUTHOR]

A combined dam structure using different concrete materials offers many practical benefits. There are several real-world cases where large-volume heterogeneous concrete materials have been used together. From the engineering design standpoint, it is crucial to understand the deformation coordination characteristics and mechanical properties of large-volume heterogeneous concrete, which affect dam safety and stability. In this study, a large dam facility was selected for a case study, and various design schemes of the combined dam structure were developed by changing the configurations of material zoning and material types for a given dam shape. Elastoplastic analysis of the dam-foundation-reservoir system for six schemes was carried out under dynamic conditions, in which the concrete damaged plasticity (CDP) model, the Lagrangian finite element formulation, and a surface-to-surface contact model were utilized. To evaluate the mechanical properties of zoning interfaces and coordination characteristics, the vertical distribution of the first principal stress at the longitudinal joint was used as the critical index of deformation coordination control, and the overall deformation and damage characteristics of the dam were also investigated. Through a comparative study of the design schemes, an optimal scheme of the combined dam structure was identified: large-volume roller-compacted concrete (RCC) is recommended for the dam body upstream of the longitudinal joint, and high-volume fly ash conventional concrete (CC) for the dam body downstream of the longitudinal joint. This study provides engineers with a reference basis for combined dam structure design.

The purpose of aspect-based sentiment analysis (ABSA) is to determine the sentiment polarity of aspects in a given sentence. Most historical works on sentiment analysis used complex and inefficient methods to integrate external knowledge. Furthermore, they fell short of completely utilizing BERT's potential because when trying to generate word embeddings, they merely averaged the BERT subword vectors. To overcome these limitations, we propose a knowledge-guided heterogeneous graph convolutional network for aspect-based sentiment analysis (KHGCN). Specifically, we consider merging subword vectors utilizing a dynamic weight mechanism in the BERT embedding layer. Additionally, heterogeneous graphs are constructed to fuse different feature associations between words, and graph convolutional networks are utilized to identify context-specific syntactic features. Furthermore, by embedding a knowledge graph, the model can learn additional features from sources other than the corpus. Based on this knowledge, it is consequently possible to obtain more knowledge representation for a particular aspect by utilizing the attention mechanism. Last but not least, semantic features, syntactic features, and knowledge are dynamically combined using feature fusion. Experiments on three public datasets demonstrate that our model achieves accuracy rates of 80.87%, 85.42%, and 91.07%, which is an improvement of more than 2% compared to other benchmark models based on HGCNs and BERT. [ABSTRACT FROM AUTHOR]

This paper investigates the bipartite formation tracking (BFT) problem of networked Lagrangian systems (NLSs) with signed directed graphs. Each system suffers from actuator fault with bounded input. Firstly, the unknown input of the leader is estimated for all the followers based on an observer in the prescribed time, which is constructed by employing a time base generator (TBG). Then, a hierarchical fully distributed controller is proposed to achieve BFT without using the global information with respect to the communication graphs. Then, the related sufficient condition for the system stability is derived by means of the Lyapunov theory. Finally, a simulation example is proposed to demonstrate the performance of the hierarchical fully distributed controller for achieving BFT. [ABSTRACT FROM AUTHOR]

The aim of this study was to investigate the association of mean platelet volume (MPV) with 1-year major cardiac outcomes in ST-elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI) and explore its relation with prognosis. Patients (n=301) with a diagnosis of STEMI were divided into 2 groups (G) according to their mean platelet volume (G1≤ 9.9 fl, n=101; G2 > 9.9 fl, n=200) which was measured within 12 hours after PCI. They were followed up for MCO during 1-year. MCO rate was higher in G2 than G1 (25% vs. 13.9%; P=0.026). This difference resulted from differences in recurrent-angina (17.5% vs. 7.9%; P=0.024) and re-hospitalization rates (19.5% vs. 9.9%; P=0.033). In binary logistic regression analysis, high MPV was an independent predictor of MCO (OR 1.30, 95%CL 1.01-1.69, p=0.045). In conclusion, elevated MPV was independently associated with MCO in patients with STEMI after PCI. Moreover, MPV greater than 9.9fl was predictive of 1-year MCO.