An automatic drilling and riveting equipment riveting interference amount prediction method based on an improved analytic hierarchy process

CN122241418APending Publication Date: 2026-06-19ZHEJIANG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ZHEJIANG UNIV
Filing Date
2026-02-05
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

In existing methods for predicting the riveting quality of automated drilling and riveting equipment, the input parameter weights rely on human experience, resulting in insufficient model interpretability and poor prediction stability. This makes it difficult to achieve high-precision and stable quality prediction in complex and variable processing environments.

Method used

An improved analytic hierarchy process (AHP) is used to calculate the impact weights of real-time production data. Combined with a deep learning model, a riveting quality prediction model is constructed. Through multi-scale feature extraction and a weight perception mechanism, high-precision prediction of riveting quality is achieved.

Benefits of technology

It improves the accuracy and stability of riveting quality prediction, has real-time prediction capabilities, outputs riveting quality and input parameter weight information, and supports process optimization and equipment status analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122241418A_ABST
    Figure CN122241418A_ABST
Patent Text Reader

Abstract

This invention discloses a method for predicting riveting interference in automated riveting equipment based on an improved analytic hierarchy process (AHP). The method includes acquiring real-time production data and calculating the influence weights of the real-time production data on riveting interference using the improved AHP; combining the real-time production data, the corresponding riveting interference, and the influence weights into a dataset; constructing an initial model and training it using the dataset to obtain a prediction model for predicting riveting interference. The method provided by this invention solves the problems of existing methods for predicting riveting quality in automated riveting equipment, such as the reliance on human experience for input parameter weights, insufficient model interpretability, and poor prediction stability.
Need to check novelty before this filing date? Find Prior Art