High-precision thread machining process optimization method and system applied to hot runner system

By optimizing the thread processing technology through neural networks, the thermal eccentricity problem of threaded connectors in hot runner systems under high-temperature service conditions was solved, achieving high-precision coaxial connection and improving system stability and production efficiency.

CN121187253BActive Publication Date: 2026-07-21ZHEJIANG HENGDAO TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG HENGDAO TECH
Filing Date
2025-11-07
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

In existing hot runner systems, threaded connections suffer from insufficient reliability due to thermal eccentricity and failure to adapt to traditional machining standards under high-temperature service conditions. This can easily lead to "tooth-biting" failures, affecting system stability and production efficiency.

Method used

A high-precision thread machining optimization method based on neural networks is adopted. By obtaining the machining and working condition parameters of the threaded connection, the ideal machining compensation angle or compensation amount is calculated using a pre-trained neural network model. The tool path of the CNC machine tool is adjusted to achieve pre-compensation eccentricity in the cold state and tend to be coaxial or have uniform contact stress at the working temperature.

Benefits of technology

It significantly reduces the risk of thread breakage, improves the long-term reliability of threaded connectors, reduces maintenance costs, adapts to high-temperature operating conditions, requires no additional hardware modifications, and balances precision and practicality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121187253B_ABST
    Figure CN121187253B_ABST
Patent Text Reader

Abstract

The application relates to the field of machine learning-based machining process optimization, and particularly discloses a high-precision thread machining process optimization method and system applied to a hot runner system, which comprises the following steps: acquiring machining parameters (thread nominal diameter, pitch, etc.) and working condition parameters (material linear expansion coefficient, working temperature range, etc.); inputting the parameters into a pre-trained neural network model to output ideal machining compensation angle or quantity, wherein the model is trained by historical, simulation or experimental data; calculating the radial offset amount of a numerical control machine tool cutter path according to the compensation angle or quantity; and controlling the machine tool to machine according to the offset amount, so that the thread cold state contains a pre-compensation eccentricity, and the thread hot state tends to be coaxial or the contact stress is uniform. The application improves the high-temperature service reliability of the thread, reduces the risk of biting, is suitable for existing machine tools, and has high practicability.
Need to check novelty before this filing date? Find Prior Art