A method and system based on selective double-layer ensemble learning suitable for missing data completion of complex industrial process product quality indicators

Abstract

The invention elates to the technical field of industrial process control, and discloses a method and system applicable to complementing missing data of product quality indicators in the complex industrial process based on selective double-layer ensemble learning. The method comprises the steps of firstly extracting different dimensions of variables of the sampled data to generate multiple sampling sets which serve as training sets of sub-models; then modeling each sub-model by respectively adopting a vector machine method, a BP neural network method and a partial least squares method; and finally putting forward a complementing effect evaluation indicator to perform evaluation on the complementing effect of each sub-model, and selecting a plurality of sub-models with the best complementing effect to perform selective ensemble. The method makes full use of all variables of the training samples, has a good data complementing effect, and facilitates enterprises to obtain the actual operation condition of the production process according to the analysis so as to perform targeted production operation optimization.

Description

Technical field [0001] The invention relates to the technical field of industrial process control, in particular to a method and system based on selective double-layer integrated learning, which is suitable for the completion of missing data of product quality indicators in complex industrial processes. Background technique [0002] In complex industrial processes, because some quality indicators cannot be directly measured by sensors, offline testing needs to be manually collected. The testing cycle is long and quality indicator data cannot be obtained in real time. This makes the completion of missing data on quality indicators a focus. At present, most of the complex industrial processes have introduced computer control systems. The mass production process data obtained from this measurement facilitates the completion of missing data for difficult-to-measure quality indicators. [0003] However, the data in complex industrial processes often have the following characteristics, w...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to address the difficulties of numerous process variables, strong coupling between variables, and large data fluctuations in complex industrial processes. Complementary method and system:

Images