基于GAF与并行CNN的混流式气液混输泵故障诊断方法
By constructing a fault diagnosis method based on GAF and parallel CNN, the problems of high sampling frequency and high implementation difficulty in the fault diagnosis of mixed-flow gas-liquid pumps are solved. This method enables the identification and early warning of multiple fault modes, improving the accuracy and robustness of fault diagnosis.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAN UNIV OF TECH
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for fault diagnosis of mixed-flow gas-liquid pumps require high sampling frequencies, are difficult to implement, and are difficult to adapt to complex working conditions, thus failing to achieve accurate identification and early warning of early faults.
A fault diagnosis method based on GAF and parallel CNN is adopted. By fusing vibration signals and pressure pulsation signals, a virtual feature parameter sequence is constructed and converted into Gram angle and field images. A dual-channel parallel CNN model is then used for fault identification.
It reduces the requirements for sampling frequency, improves the accuracy of fault identification and early warning capabilities, and enhances adaptability to complex operating conditions and noise resistance.
Smart Images
Figure CN122113001B_ABST