Urban water demand forecasting is beneficial for reducing the waste of water resources and enhancing environmental protection in sustainable water management. However, it is a challenging task to accurately predict water demand affected by a range of factors with nonlinear and uncertainty temporal patterns. This paper proposes a new hybrid framework for urban daily water demand with multiple variables, called the attention-based CNN-LSTM model, which combines convolutional neural network (CNN), long short-term memory (LSTM), attention mechanism (AM), and encoder-decoder network. CNN layers are used to learn the representation and correlation between multivariate variables. LSTM layers are utilized as the building blocks of the encoder-decoder network to capture temporal characteristics from the input sequence, while AM is introduced to the encoder-decoder network to assign corresponding attention according to the importance of water demand multivariable time series at different times. The new hybrid framework considers correlation between multiple variables and neglects irrelevant data points, which helps to improve the prediction accuracy of multivariable time series. The proposed model is contrasted with the LSTM model, the CNN-LSTM model, and the attention-based LSTM to predict the daily water demand time series in Suzhou, China. The results show that the hybrid model achieves higher prediction performance with the smallest mean absolute error (MAE), root mean squared error (RMSE), and mean absolute percentage error (MAPE), and largest correlation coefficient (R²).

Assembly and disassembly are important activities in the manufacturing/remanufacturing process. Although the line balancing problems of them have been extensively discussed in the existing literature, they are rarely integrated into one system. In this paper, a hybrid production line balancing problem is adopted while considering the similarity between the assembly and disassembly tasks. First, to better reflect the uncertainty existing in the actual production environment, a mathematical model of the multi-objective stochastic hybrid production line balancing problem is presented, in which task disassembly times are assumed to be random variables with known normal probability distributions. Then, a hybrid VNS-NSGA II algorithm combining variable neighbourhood search (VNS) and non-dominated sorting genetic algorithm II (NSGA II) is proposed to solve the problem. VNS is embedded into NSGA II as a local search to improve the quality of the solutions found by the NSGA II at each generation. Finally, the effectiveness of the proposed method is verified by a case study, and the superiority of hybrid production line is reflected by comparing the solutions of the independent production line with the hybrid production line. Computational comparisons demonstrate the potential benefits of the hybrid production line and the proposed method.