A method and system for accurately predicting the grinding efficiency of a ball mill

By using a neural network model to predict mill power in ball mills and combining it with real-time data analysis, the lag and inaccuracy in judging grinding efficiency were solved, and accurate prediction of grinding efficiency was achieved, improving the accuracy and timeliness of grinding efficiency judgment.

CN118122444BActive Publication Date: 2026-07-03HUNAN CHANGTIAN AUTOMATION ENG CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUNAN CHANGTIAN AUTOMATION ENG CO LTD
Filing Date
2022-12-02
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

The current method of judging the grinding efficiency of ball mills relies on human experience, which leads to untimely detection, waste of manpower, vague judgment results or delayed analysis, and cannot reflect the condition of the mill in a timely and accurate manner.

Method used

By acquiring real-time input data and feeding it into a pre-trained neural network model, the model is used to predict mill power. By combining the deviation analysis between the preliminary predicted value and the measured value of mill power, accurate prediction of grinding efficiency is achieved.

Benefits of technology

It enables timely and accurate prediction of grinding efficiency under changing operating conditions, solving the problems of untimely and labor-intensive methods in the past, and improving the accuracy of grinding efficiency judgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118122444B_ABST
    Figure CN118122444B_ABST
Patent Text Reader

Abstract

The application provides a grinding efficiency precise prediction method and system for a ball mill, through acquiring twelve real-time input data, inputting the real-time input data into a pre-trained neural network model, accepting a mill power preliminary prediction value output by the neural network model, determining a deviation value of the mill power preliminary prediction value and a mill power measured value, and judging whether the deviation value is within a preset range, when the deviation value is within the preset range, outputting the mill power preliminary prediction value as a mill power final prediction value for reflecting the grinding efficiency, so as to realize precise prediction of the grinding efficiency. The application adopts a deep learning mode, and proposes a method of predicting the grinding efficiency by predicting the mill power, so that the grinding efficiency can be timely and accurately predicted under the change of working conditions, and the problems of existing methods, such as untimely discovery, consumption of manpower, fuzzy judgment result or analysis lag, are solved.
Need to check novelty before this filing date? Find Prior Art