Meta-learning prediction of physical and chemical properties of magnetized water and fertilizer based on LSTM

Background Due to the high cost of data collection for magnetization detection of media, the sample size is limited, it is not suitable to use deep learning method to predict its change trend. The prediction of physical and chemical properties of magnetized water and fertilizer (PCPMWF) by meta-learning can help to explore the effects of magnetized water and fertilizer irrigation on crops. Method In this article, we propose a meta-learning optimization model based on the meta-learner LSTM in the field of regression prediction of PCPMWF. In meta-learning, LSTM is used to replace MAML’s gradient descent optimizer for regression tasks, enables the meta-learner to learn the update rules of the LSTM, and apply it to update the parameters of the model. The proposed method is compared with the experimental results of MAML and LSTM to verify the feasibility and correctness. Results The average absolute percentage error of the meta-learning optimization model of meta-learner LSTM is reduced by 0.37% compared with the MAML model, and by 4.16% compared with the LSTM model. The loss value of the meta-learning optimization model in the iterative process drops the fastest and steadily compared to the MAML model and the LSTM model. In cross-domain experiments, the average accuracy of the meta-learning optimized model can still reach 0.833. Conclusions In the case of few sample, the proposed model is superior to the traditional LSTM model and the basic MAML model. And in the training of cross-domain datasets, this model performs best.

Investigation of Mechanical and Durability Properties of Concrete Mixed with Water Exposed to a Magnetic Field

Water is a crucial element in the concrete mix and is alone responsible for concrete work ability and cement hydration. The massive quantity of potable water consumed during the production of concrete is a concern. In general, fresh and hard concrete qualities are most influenced by the quantity and water quality. The use of magnetic water in concrete gives many benefits when it comes to increasing its properties. A substantial quantity of water can be saved by substituting potable water with magnetized water in concrete. In this study, the effects of magnetized water on the concrete's mechanical and durability properties were tested. Four different combinations were made using potable water and magnetic water. Mechanical properties including compression, flexural, tensile strength, and SEM analysis were evaluated. Water absorption, acid resistance, and corrosion resistance were all tested as part of the durability tests. According to the results of the experiments, employing magnetic water for concrete preparation and curing enhanced the mechanical properties and durability. Concrete mix MMMC prepared and subjected to curing using magnetized water has a 14.86% greater compressive strength than ordinary concrete. Similarly, tensile and flexural strength of mix MMMC amplified to 14.32% and 14.02%, respectively. Besides, the consumption of chemical admixtures also considerably reduced in magnetized water imbibed concrete.

Meta-learning Prediction of Physical and Chemical Properties of Magnetized Water and Fertilizer Based on LSTM

BackgroundDue to the high cost of data collection and labeling for magnetization detection of medium, the sample size is limited, it is not suitable to use deep learning method to predict its change trend. The prediction of physical and chemical properties of magnetized water and fertilizer(PCPMWF) by meta-learning can help to explore the effects of magnetized water and fertilizer irrigation on crops. MethodIn this article, we propose a meta-learning optimization model based on the meta-learner LSTM in the field of regression prediction of PCPMWF. In meta-learning, LSTM is used to replace MAML's gradient descent optimizer for regression tasks, enables the meta-learner to learn the update rules of the LSTM, and apply it to update the parameters of the model. The proposed method is compared with the experimental results of MAML and LSTM to verify the feasibility and correctness.ResultsThe average absolute percentage error of the meta-learning optimization model of meta-learner LSTM is reduced by 0.37% compared with the MAML model, and by 4.16% compared with the LSTM model.ConclusionsIn the case of few sample, the proposed model is superior to the traditional LSTM model and the basic MAML model.

Study on the Dust Removal and Temperature Reduction Coupling Performances of Magnetized Water Spray

Dust pollution and heat damage hazards are important problems affecting underground safety production. This paper is aimed at exploring the optimal magnetization conditions of magnetized water for dust removal and temperature reduction, and improve the utilization rate of water. First, the surface tension, viscosity and specific heat capacity of water under different magnetization conditions were measured experimentally. Then, the magnetization conditions with the best coupling performances were obtained through ANSYS Fluent simulation. Finally, a spray system was designed to control the magnetization conditions strictly. The results demonstrate that the dust removal performance is better when the magnetic field intensity is 150 mT and the magnetization time is 80 s. Under this condition, the specific heat capacity also reaches the maximum. These research results can provide a theoretical basis for the selection of dust pollution and heat damage control measures in mines.