Abnormal interval prediction model construction method and abnormal interval prediction method

• Main Authors: PU ZHIYONG, LI XUTAO, ZHENG HAO, ZHU TIANLUN, XU JIANGNAN, WANG YUN
• Format: Patent
• Language: Chinese; English
• Published: 11.10.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention provides an abnormal interval prediction model construction method and an abnormal interval prediction method, and relates to the technical field of wind turbine generator state monitoring. The construction method comprises the steps of obtaining wind turbine power generation power data, labeling the wind turbine power generation power data through a self-adaptive abnormal point labeling algorithm to obtain labeled data, and constructing abnormal interval data according to the labeled data, and according to the abnormal interval data, constructing an abnormal interval prediction model based on a multi-scale time sequence Transform. According to the method, the generation power data of the wind generator are labeled through the adaptive abnormal point labeling algorithm to label the abnormal points with trend changes, the labeling cost is effectively reduced, the labeling efficiency and precision are improved, the abnormal interval prediction model based on the multi-scale time sequence Transform