Cement mill system power consumption index prediction method based on extreme learning machine

Abstract

The invention discloses a cement grinding mill system power consumption index prediction method based on an extreme learning machine, and the method comprises the steps: firstly collecting related variables, carrying out the operation analysis of a cement grinding mill system, selecting eight variables related to the power consumption of a cement grinding mill as input variables, selecting the ton power consumption as an output variable, and constructing an input and output layer of an ELM model; optimizing the number L of neurons of the ELM, the weight w of an input layer and the bias b of a hidden layer by using an IPSO algorithm; the IPSO algorithm taking a mean square error of the model as a fitness function in a parameter optimization process; ELM related parameters obtained through IPSO optimization being combined with sample data to complete training of an IPSO-ELM prediction model, and industrial field actual data being substituted into the trained model to complete online prediction of the power consumption of the cement grinding mill system. According to the method, the IPSO-ELM model is trained by using the sample data to obtain the power consumption prediction model, and variable data of an actual cement production site is input into the trained model, so that online prediction of the power consumption index of the cement grinding mill is realized.

Description

technical field [0001] The invention belongs to the field of prediction of power consumption index of cement mill system, and in particular relates to a prediction method of power consumption index of cement mill system based on extreme learning machine. Background technique [0002] The cement industry is a traditional industry in my country. With the development of the country, large-scale buildings continue to appear, and the consumption of cement has increased greatly. The cement industry is a major high-energy-consuming and high-emission industry in my country. Realizing the online prediction of cement mill power consumption index is beneficial to guide the scheduling optimization of various production indicators in the cement mill grinding process, and is conducive to reducing the power consumption of cement mill production process, so as to achieve the purpose of energy saving and emission reduction. However, due to the hysteresis and high coupling between the various...

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention provides a method for predicting the power consumption index of cement mill system based on extreme learning machine, which effectively solves the problem of hysteresis between various power consumption indexes of cement mill system and the problem of strong coupling between multiple power consumption indexes. problem, and compared with other neural network models, the extreme learning machine (Extreme Learning Machine, ELM) has a fast training speed and calculation speed, and can achieve real-time training-prediction; the extreme learning machine randomly generates weight w and bias b before training, just need to determine The number of neurons in the hidden layer and the infinitely differentiable activation function of neurons in the hidden layer, so the training process of the extreme learning machine is to solve However, setting the number of neurons in the hidden layer of the extreme learning machine and randomly generating weight w and bias b according to experience will make the prediction accuracy unstable, and the improved particle swarm optimization algorithm (ImproveParticleSwarmOptimization, IPSO) is added to the prediction model Optimize the above parameters to improve the accuracy and stability of predictions and enhance the generalization ability

Images