用于电气化铁路供电安全检测监测系统5C的缺陷分析方法
By using multi-scale feature adaptive fusion and physical mechanism-driven defect decoupling discrimination, the problems of high false alarm rate and poor scale adaptability in pantograph sliding plate detection are solved, achieving high-precision defect detection and risk quantification assessment, and improving the intelligence and engineering level of pantograph condition monitoring in high-speed railways.
CN122134722BActive Publication Date: 2026-07-17CHENGDU NUOBIKAN TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENGDU NUOBIKAN TECH CO LTD
- Filing Date
- 2026-05-06
- Publication Date
- 2026-07-17
Smart Images
Figure CN122134722B_ABST
Abstract
本发明公开了用于电气化铁路供电安全检测监测系统5C的缺陷分析方法，属于计算机视觉检测技术领域。首先获得滑板区域掩码及高风险区域；再进行多尺度特征提取，并利用尺度自适应融合权重构建融合模型，得到缺陷融合特征图；依据异物附着、滑板折弯、滑板断裂三类缺陷的物理机理进行解耦判别；最后结合缺陷类型、空间位置与高风险区域，开展多因子耦合的风险综合评估，输出风险告警等级与运维决策。该方法借助注意力机制与互信息自适应增强缺陷敏感尺度特征，解决尺度跨度大带来的漏检问题，并通过结构先验约束与物理机理解耦，有效剔除误检、区分真实缺陷，显著提升检测精度与可解释性。
Need to check novelty before this filing date? Find Prior Art