Industrial process soft measurement modeling method based on cooperative training partial least squares model

Abstract

The invention discloses a soft measurement research method for the industrial production process under the condition that the number of available training samples is small, which is applied to carrying out soft measurement modeling under the condition that modeling data is small in amount and realizing prediction for product information. According to the invention, an effective linear prediction model is established by using a cooperative training based partial least squares learning method, a problem of low model precision under the condition that sampling data of the industrial production process is small in amount, and the predication accuracy and the performance of the model established in allusion to the process are improved, thereby enabling the industrial production process to be more reliable, and enabling the product quality to be more stable.

Description

technical field [0001] The invention belongs to the field of industrial process prediction and control, and in particular relates to a soft sensor modeling method of a cooperative training algorithm and a partial least squares algorithm. Background technique [0002] In the traditional industrial process, there are many variables that cannot or are difficult to be directly measured by sensors, such as product reaction rate, product component content, etc., and these parameters play an important role in improving product quality and ensuring safe production, and are necessary in the industrial production process. Parameters that are strictly monitored and controlled. Although these variables can be detected by online analytical instruments, on the one hand, it requires a large amount of investment, and on the other hand, the adjustment may not be timely due to the large measurement lag, making it difficult to guarantee product quality. These variables that play an important ...

AI Technical Summary

Problems solved by technology

However, when the number of training samples in the traditional multivariate statistical method is small, the prediction accuracy of the established model often cannot achieve effective accuracy; in addition, the data used in the modeling of the traditional multivariate statistical learning method are often those The auxiliary variable has data corresponding to the information of the leading variable, and the data without the corresponding leading variable and only the information of the auxiliary variable is often directly ignored

In the industrial process, based on the above-mentioned reasons that the leading variable is difficult to detect, there are a large number of data in the industrial process that do not contain the leading variable and only auxiliary variable information. These data contain a lot of useful information and are discarded directly. no waste

Images