Soft measurement method for coal power fineness in powdering producer

Abstract

A pulverized coal fineness soft-sensing method in a powder-making process based on a least squares support vector machine depends on a hardware platform, measuring instruments and a computer system used for performing a software calculation, wherein said software performs a soft-sensing through real-time process data obtained by a controlling computer of a data collector. Said method comprises the steps of selecting assistant variables, determining the structure of sample data, determining sample components, building a soft-sensing model based on the least squares support vector machine and performing the model training, parameter selection as well as the model validation and the model parameter emendation. The present invention is applied simply and easily, has a lower cost, has more accurate soft-sensing results, and helps to achieve an optimal control and an optimal operation of a pulverizing process.

Description

technical field [0001] The invention belongs to the technical field of automatic measurement, and particularly relates to the final product of the mid-storage steel ball mill coal pulverization system composed of a steel ball coal mill, a coarse powder separator and a cloth bag collector for pulverized coal grinding in the pulverization process—coal The method of soft measurement of powder fineness index. Background technique [0002] In pulverization production, the medium-storage steel ball coal mill consisting of steel ball coal mill, coarse powder separator and cloth bag collector is widely used to grind coal powder to the fineness range required by the process. The fineness of pulverized coal is an important process index for evaluating the pulverization process, an important factor to improve product quality and economic benefits, and plays a very important role in the process control of coal-fired power generation and sintering. At present, in the industrial applica...

AI Technical Summary

Problems solved by technology

At present, in the industrial application of on-line detection of coal fineness, due to the limitation of actual conditions, there is no industrial test, no practical operability, and no mature detection device. In the actual production process, it mainly relies on sampling and testing. get offline

The disadvantages of this method are: 1. The influence of human factors is large during manual operation, and the objectivity of the measurement results is poor; 2. The time interval of measurement is long, and the time for feedback of measurement results is also long, so the obtained information lacks guiding significance for operators; 3. .Coal powder leakage is inevitable when sampling coal powder, causing environmental pollution

Due to the limited number of sample data and the influence of large interference errors on training, the convergence speed of the model is slow and prone to overfitting using common neural network methods.

Images