Zinc flotation process concentrate grade prediction method based on feedback compensation mechanism optimization

Abstract

The invention provides a zinc flotation process concentrate grade prediction method based on feedback compensation mechanism optimization, and the method comprises the following steps: firstly collecting zinc flotation process image feature data and corresponding concentrate grade data as sample data, and carrying out the preprocessing of the collected data; dividing the preprocessed sample data into five independent sub-sample spaces according to the concentrate grade, and performing time difference on the five independent sub-sample spaces respectively; extracting high-contribution-rate features as key features by adopting KPCA; training an LSSVM (Least Square Support Vector Machine) based on the key feature sample, and establishing a relationship between the image features and the concentrate grade; optimizing two parameters of a penalty factor xi and a kernel width sigma of the LSSVM by using an improved flora algorithm; establishing a model error feedback compensation mechanism, and starting the feedback compensation mechanism to compensate the model when the model error is not controlled. The method can be directly implemented by programming on a computer, is low in cost, high in precision and good in timeliness, and has important significance for guiding field production.

Description

technical field [0001] The invention belongs to the technical field of froth flotation, and in particular relates to a zinc flotation process concentrate grade prediction method based on model error estimation and feedback compensation mechanism optimization [0002] technical background [0003] Froth flotation is one of the most important beneficiation methods in current lead-zinc smelting. Flotation method is a method of sorting minerals by using the different physical and chemical properties of the surface of mineral particles to lead to different hydrophilicity. practical value. However, because the flotation process is long, the internal mechanism is not clear, there are many influencing factors, many variables are involved and the nonlinearity is serious, many process indicators cannot be detected online. Predicting the obtained concentrate grade and using it to complete the on-site operation is highly subjective and relies too much on experience and knowledge. It is ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the difficulty of on-line detection of concentrate grade in the flotation process and the deficiency of the prior art in zinc flotation concentrate grade prediction, the present invention utilizes various characteristics related to zinc concentrate grade to propose a method based on an improved flora algorithm Data-driven concentrate grade prediction method for zinc flotation process

Images