Accurate prediction of mill load parameters is crucial to improving grinding efficiency and saving energy. Traditional prediction models have challenges such as poor interpretability, low prediction efficiency and differences in data distribution. This study innovatively proposed a multi-task prediction model that integrates physical information and domain adaptation. By constructing a physical-data-driven hybrid model, the physical relationship between mill load parameters is embedded into the model as prior knowledge to improve the prediction accuracy of the model. At the same time, multi-task learning is used to predict the material-to-ball volume ratio and the pulp density at the same time, which improves efficiency and reduces repetitive work. The domain adaptation method is introduced to ensure that the model maintains stable prediction performance when the data distribution changes. Laboratory ball mill data verification shows that the proposed model not only improves the prediction accuracy, but also adapts well to variable working conditions, showing significant superiority.

The industrially collected process data usually exhibit non-Gaussian and multi-mode characteristics. Due to sensor failures, irregular disturbances, and transmission problems, there are unavoidable outliers that make the data exhibit heavy-tailed characteristics. To this end, a variational auto-encoder regression method based on the mixture Laplacian distribution (MLVAER) is proposed, by introducing a type-II multivariate Laplacian distribution in the latent variable space for robust modeling, and further extending it to the mixture form to accommodate multi-mode processes, the corresponding reparameterization trick is finally proposed for the mixture form of this distribution for neural network gradient descent training. The model based on this distribution assumption has higher degrees of freedom than the model based on the traditional multivariate Laplace distribution assumption when the network structure is the same. Numerical simulation and experiments on two industrial examples demonstrate that the proposed algorithm reduces the root mean square error by over 15% compared to other algorithms.

Accurately predicting runoff is crucial for managing water resources, preventing and mitigating floods, scheduling hydropower plant operations, and protecting the environment. The hydrological dynamic composite system that forms runoff is complex and random, and seemingly random behavior may be caused by nonlinear variables in a simple deterministic system, which poses a challenge to runoff prediction. In this paper, we construct parallel and multi-timescale reservoirs from a chaotic theory perspective to simulate the stochasticity of chaotic systems. We propose a multi-task-based "Decomposition-Integration-Prediction" (Multi-SDIPC) model for runoff prediction. To validate our research results, we use the Catchment Attributes and Meteorology for Large-Sample Studies (CAMELS) dataset and compare our proposed model with 10 baseline models. The results show that our model has an average NSE metric of 0.83 and exhibits higher accuracy, better generalization, and greater stability than the other models in multi-step forecasting. Based on our findings, we recommend wider application of the Multi-SDIPC model in different regions of the world for medium or long-term runoff prediction.