Search Results (2)

In order to meet the requirements of high accuracy and fast algorithm for numerical heat transfer simulation, an iterative scheme of Proper Orthogonal Decomposition (for short, POD) dimension reduction based on the classical central difference Galerkin spectral method is proposed for solving two-dimensional transient heat conduction problems. The POD dimension reduction spectral method model is constructed by taking the calculation results of classical central difference Galerkin spectral method as sample data. The numerical algorithm characteristics of flow and heat transfer are studied by using a partial differential equation as a mathematical model, and the error estimation is given. Finally, different time intervals are used as parameters to simulate experiments. The results show that the POD method is applicable to transient nonlinear heat conduction problems, and the maximum average relative error of the reconstructed temperature field is 0.89675%. Moreover, the POD method not only has a high calculation accuracy, but also has an average calculation speed as high as 310.25 times that of the central difference Galerkin algorithm. It can be seen that under the condition that the error between the solution of POD dimension reduction extrapolation algorithm and the solution of classical central difference Galerkin spectrum method is small enough, the POD method can greatly reduce the calculation amount, shorten the running time, and ensure a high accuracy of the calculation results, thus verifying the effectiveness and feasibility of the algorithm. Full article

In order to forecast some high intensity and rapidly changing phenomena, such as thunderstorms, heavy rain, and hail within 2 h, and reduce the influence brought by destructive weathers, this paper proposes a weather radar echo extrapolation method based on deep learning. The proposed method includes the design and combination of the data preprocessing, convolutional long short-term memory (Conv-LSTM) neuron and encoder–decoder model. We collect eleven thousand weather radar echo data in high spatiotemporal resolution, these data are then preprocessed before they enter the neural network for training to improve the data’s quality and make the training better. Next, the neuron integrates the structure and the advantages of convolutional neural network (CNN) and long short-term memory (LSTM), called Conv-LSTM, is applied to solve the problem that the full-connection LSTM (FC-LSTM) cannot extract the spatial information of input data. This operation replaced the full-connection structure in the input-to-state and state-to-state parts so that the Conv-LSTM can extract the information from other dimensions. Meanwhile, the encoder–decoder model is adopted due to the size difference of the input and output data to combine with the Conv-LSTM neuron. In the neural network training, mean square error (MSE) loss function weighted according to the rate of rainfall is added. Finally, the matrix “point-to-point” test method, including the probability of detection (POD), critical success index (CSI), false alarm ratio (FAR) and spatial test method contiguous rain areas (CRA), is used to examine the radar echo extrapolation’s results. Under the threshold of 30 dBZ, at the time of 1 h, we achieved 0.60 (POD), 0.42 (CSI) and 0.51 (FAR), compared with 0.42, 0.28 and 0.58 for the CTREC algorithm, and 0.30, 0.24 and 0.71 for the TITAN algorithm. Meanwhile, at the time of 1 h, we achieved 1.35 (total MSE ) compared with 3.26 for the CTREC algorithm and 3.05 for the TITAN algorithm. The results demonstrate that the radar echo extrapolation method based on deep learning is obviously more accurate and stable than traditional radar echo extrapolation methods in near weather forecasting. Full article