A method and system for monitoring the quality of water supply network welding

By collecting welding process data and images, and combining dynamic confidence intervals and adaptive clipping and limiting processing, the welding quality index is calculated, which solves the problem of multi-parameter collaborative analysis in water supply network welding quality monitoring and realizes real-time and reliable quality assessment.

CN122407989APending Publication Date: 2026-07-17CHINA RAILWAY GUIZHOU ENG CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA RAILWAY GUIZHOU ENG CORP LTD
Filing Date
2026-04-28
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

The existing monitoring of welding quality in water supply networks relies on visual inspection and non-destructive testing, which suffers from problems such as strong subjectivity, low efficiency, high cost, long cycle, and lack of multi-parameter collaborative analysis, making it difficult to achieve real-time and reliable quality assessment.

Method used

By synchronously acquiring time-series data of current, voltage, and speed during the welding process, and combining them with weld appearance images, the system calculates welding process stability, edge regularity, forming uniformity, and surface defect index through dynamic confidence intervals and adaptive clipping and limiting processing. The system integrates and evaluates the overall quality of the weld, and classifies it based on historical statistical distribution.

Benefits of technology

It enables multi-dimensional quantitative assessment of welding quality, improves the real-time nature and reliability of quality control, provides a scientific basis for resource allocation, and enhances management efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122407989A_ABST
    Figure CN122407989A_ABST
Patent Text Reader

Abstract

本发明公开了一种供水管网焊接质量监测方法和系统,涉及焊接技术领域,所述方法包括如下步骤:同步采集焊接过程的电流、电压、速度时序数据,进行自适应异常值检测与修正;采集焊后焊缝外观图像,进行对比度增强预处理;基于处理后的时序数据,计算焊接过程稳定性指数;基于处理后的图像,量化计算边缘规整度指数、成形均匀性指数和表面缺陷量化指数;将上述指数通过预设权重融合,得到焊缝综合质量评分;根据历史统计分布确定的质量等级阈值,将焊缝划分为四个等级,并输出监测报告。本发明实现了焊接过程参数与外观图像的多源信息融合,通过预处理算法和融合模型,显著提升了质量监测的准确性和效率。
Need to check novelty before this filing date? Find Prior Art