Search

Residential Short-term load forecasting is an important basis for power department to make dispatching plan reasonably. A short-term load forecasting framework was proposed that is based on Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) clustering algorithm, Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU). In this framework, based on historical load data collected by smart meters, BIRCH clustering algorithm is adopted to cluster users into multiple user groups according to different users’ electricity consumption habits. A multivariate time series dataset composed of load data, time data, and climate data are into the CNN network, which is composed of a one-dimensional convolutional layer and a pooling layer. The CNN network is responsible for extracting the potential relationship and high dimensional characteristics of different variables. After that, the data are input into the GRU network, and the sequence characteristics of the time sequence data are studied. Finally, the short-term load prediction results are output from the full-connected layer. Taking the open dataset provided by the Commission for Energy Regulation (CER) of Ireland as an example, the Mean Absolute Percentage Error (MAPE) of the proposed method reached 2.932 1%. Compared with the prediction efficiency and accuracy of ANN network, CNN network, and CNN-GRU network under the same conditions, the experimental results showed that the proposed method has higher prediction accuracy and higher training efficiency.

Stroke has a high disability rate and fatality rate. It is of great clinical significance to study the automatic recognition and segmentation of stroke lesions. Convolutional neural network can not make use of time sequence correlation of medical image data, and has the problem of low feature utilization. Therefore, a bidirectional recurrent U-Net (BIRU-Net) model was proposed for segmentation of lesions. First, a recurrent neural network is introduced to replace part of the convolutional layer in U-Net with an improved attention convolutional gate recursive unit (ACGRU), so that the segmentation model is not only suitable for small-scale annotated medical image data sets, but also has the characteristics of long-term memory. Second, a dual-channel fusion training mechanism is adopted to input the forward and reverse slice data of a single view into BIRU-Net at the same time, and realize bidirectional feature fusion in the process of model forward propagation, effectively utilizing the bidirectional dependence of slice sequence. Finally, the segmentation results of each single view are refused to effectively utilize the spatial context information of data. The experimental results of ATLAS data set show that the DSC value of the proposed method reaches 62.58%. Compared with other methods at the present stage, the proposed method can segment the lesion region more accurately.

To solve the problem that Dempster-Shafer (D-S) evidence theory gives combines results contrary to with facts when dealing with conflict evidence, a novel method of conflict evidence combination was proposed. First, the Spearman correlation coefficient is improved and the support between evidences is calculated, and original evidence is amended for the first time. Then, combined with the advantages of the interval distance based on fixed integrals, the uncertainty of evidence is analyzed, a new discount coefficient is determined, and original evidence body is secondarily revised. Finally, the fusion results are obtained by using the Dempster combination rule. The calculation and example analysis demonstrates that the proposed method can effectively fuse the evidence of conflict, and has a higher basic probability distribution than the classical improved algorithm. The proposed method was used for carbon/carbon composite sedimentation data, and a carbon/carbon composite sedimentation mass prediction model based on improved D-S evidence theory was established. Compared with several classical classifiers and the existing prediction model based on D-S evidence theory, this model is increased in accuraey by 5%~13%, which proves its validity.

Aiming at the problem that traditional anomaly detection model has poor recognition effect on a small number of abnormal samples under the condition of data imbalance, in this paper we proposed a support vector data description algorithm combined with improved diffusion maps (DM-SVDD), constructed a new model and applied it to industry abnormal detection. The diffusion mapping algorithm was improved by introducing Euclidean distance and Mahalanobis distance to construct a new neighbor graph. Combined with support vector data description algorithm for modeling, the new model improved the recognition performance of normal samples, and the detection performance of abnormal samples was better than that from traditional models. Experimental data were selected of polysilicon ingot data sets. The results show that for an unbalanced data set formed by fewer abnormal samples, compared with traditional anomaly detection model, the model proposed in this paper can increase G-Mean optimally by 15.73% and F-Score optimally by 19.37%, which meet the requirements of industrial anomaly detection. The model can be used to guide the actual production process and reduce production costs.

In the quality analysis of polysilicon ingot batching, a two-stage genetic algorithm (NRS-SVM-GA) combining the NRS-SVM model with genetic algorithm (GA) was proposed to solve the problem of neighborhood radius and SVM parameter values in the processing of continuous data of polysilicon ingot batting with rough set-support vector machine (NRS-SVM) model. The first stage of the algorithm, by searching for a new neighborhood radius, a better reduction set is obtained. In the second stage the attribute reduction results from the first stage are adopted to, by searching the new parameters of SVM, train the classification model with higher accuracy. According to the purpose of each stage, the corresponding fitness function and termination conditions are put forward. The distinctive features of this method is to implement the NRS-SVM automatic feature extraction and classification prediction, and run the two stages independently to avoid the time consumption for the evaluation of reduction by classifiec. The experimental results of polysilicon ingot batching data set show that this method has shorter running time, stable output, less features, and higher classification accuracy than the standard genetic algorithm.