Method for predicting glass phase content in fly ash by using machine learning

Abstract

The invention discloses a method for predicting the content of a glass phase in fly ash by utilizing machine learning, which is characterized in that a machine learning model is established by utilizing the relationship between the content of the glass phase in the fly ash and the chemical composition of the fly ash so as to predict the content of the glass phase in the fly ash. The method comprises the following specific steps: 1, determining chemical composition factors influencing the glass phase content of the fly ash, and carrying out feature selection; 2, starting to collect related data based on the determined features to form a sample data set; 3, dividing the data into a training set and a test set; 4, selecting and establishing a machine learning algorithm model; and 5, determining hyper-parameters by the training set through an optimization algorithm to obtain a prediction model, and verifying the effect of the model by using the test set. According to the determined characteristic parameters influencing the glass phase content in the fly ash, prediction of the glass phase content in the fly ash is realized based on machine learning, and the method has great significance in activity prediction of the fly ash.

Description

technical field [0001] The invention relates to the field of solid waste treatment, in particular to a method for predicting the glass phase content in fly ash based on machine learning. Background technique [0002] Rapid economic development and industrial production drive the growing demand for energy. Fossil fuels such as coal have always been the main source of global energy supply due to their high calorific value and low cost. Coal has a high output and a large consumption, and is mainly used for power production and industrial production. At present, coal-fired power generation is still the main way of power generation, accounting for about 40% of the total power generation. Fly ash is a by-product of coal combustion in thermal power plants, with an annual output of about 800 million tons. The massive discharge of fly ash not only occupies land resources, but also increases harmful elements in water, destroys soil structure and function, causes serious damage to t...

AI Technical Summary

Problems solved by technology

[0003] The activity of fly ash is the key to its ability to be used as an auxiliary cementitious material. At present, the existing methods for testing the activity of fly ash mainly rely on X-ray diffraction (XRD) tests, which are complex in operation, time-consuming and costly, and require Expertise, so the test has not been promoted on a large scale, which seriously hinders the resource utilization of fly ash

Images