Online quality prediction method of complex industrial process based on JY-KPLS

• Main Authors: MA XIAOPING, CHU FEI, SHEN JIAN, CHENG XIANG
• Format: Patent
• Language: Chinese; English
• Published: 13.06.2017
• Subjects: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION ORPROCESSING OF GOODS; CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS; TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINSTCLIMATE CHANGE

The invention discloses an online quality prediction method of complex industrial process based on JY-KPLS. The method is capable of building an offline quality prediction model of operating state and an online quality prediction of batch industrial process with the kernel partial least squares technology of joint variable Y, specifically including the following steps. First, the offline quality prediction model is built by using the kernel partial least squares technology of joint variable Y. All data of a decision point are acquired online. The data are completed by mean value filling, and the product quality is predicted by the prediction model. The method is capable of effectively overcoming a problem that the prediction model is unable to be built for few new production process data, so that the modeling speed is raised, the model prediction accuracy is improved, model adaption is achieved, prediction results are acquired on the basis of real time, site operators can promptly adjust production strategy,