Hydraulic cylinder modeling and fault diagnosis method based on real-time data driving
By constructing physical and neural network models of hydraulic cylinders and combining them with real-time sensor data for hydraulic cylinder fault diagnosis, the problems of high hardware cost, limited installation, and high model complexity in existing technologies have been solved. This has enabled low-cost, transferable, and adaptive fault diagnosis with early warning capabilities.
CN122407643APending Publication Date: 2026-07-17THE 715TH RES INST OF CHINA SHIPBUILDING IND CORP
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- THE 715TH RES INST OF CHINA SHIPBUILDING IND CORP
- Filing Date
- 2026-05-22
- Publication Date
- 2026-07-17
Smart Images
Figure CN122407643A_ABST
Abstract
本发明涉及一种基于实时数据驱动的液压油缸建模及故障诊断方法，包括以下步骤，S1采集液压系统实时运行数据，根据连杆部件旋转角度推算油缸实际位置，计算实测速度和油液粘度，并根据控制指令拆分数据集；S2构建液压油缸理论物理模型，通过最小二乘法辨识泄露系数；S3若未测得流量则构建神经网络模型测算油缸流量；S4定期迭代更新模型参数；S5通过泄露系数下降速率诊断密封老化，通过理论位置与实际位置比对诊断卡滞故障。本发明通过物理模型与神经网络混合建模，实现低成本、可迁移、自适应的液压油缸故障诊断，具有物理可解释性强、早期预警能力好的优点。
Need to check novelty before this filing date? Find Prior Art