一种电力施工作业节奏预测方法及系统
By combining GBDT and SVM models and using autoencoders and gradient boosting decision trees for data preprocessing and feature selection, the problem of lack of intelligent monitoring in power construction operations was solved, and intelligent prediction and reliable monitoring of high-speed operations were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGZHOU BAILING DATA CO LTD
- Filing Date
- 2022-12-26
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack intelligent monitoring solutions to effectively manage the excessively fast-paced work of power construction workers. Furthermore, support vector machine models are sensitive to missing data and lack general solutions for nonlinear problems, leading to complex feature engineering processing.
By combining the GBDT and SVM models of machine learning, the system uses an autoencoder to complete missing and outlier values in the data, utilizes gradient boosting decision trees for feature selection and discretization to construct a suitable discrete feature set, and uses a support vector machine for hyperplane separation to achieve intelligent prediction of whether workers are working at an excessive pace.
It improves the reliability and accuracy of data prediction, shortens the characteristic experiment cycle, realizes intelligent monitoring of the fast-paced work of power construction workers, and reduces the reliance on human experience.
Smart Images
Figure CN115936241B_ABST