Hot-Dip Galvanized Steel Defect Prediction for Non-Plating Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for manufacturing hot-dip galvanized steel sheets with high-tensile steel containing Si face challenges in predicting and reducing non-plating defects, which often occur unevenly between the front and back surfaces, and their causes are not clearly understood, leading to yield inconsistencies.
Innovation Solution
A method utilizing machine learning to predict non-plating defects by analyzing data from annealing and plating equipment parameters, including dew points, temperatures, and steel attributes, followed by adjusting operational parameters to maintain a preset allowable defect rate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Strength
If high-tensile steel sheet containing Si is used as base material, then hole expandability and ductility are improved, but non-plating defects occur during hot-dip galvanizing
Solution Approach 1:
The invention performs preliminary oxidation of Si during the annealing process before hot-dip galvanizing. By controlling the annealing atmosphere (maintaining dew point between -30°C to 0°C) and temperature (600-900°C), Si is oxidized to SiO2 and removed from the steel sheet surface in advance, preventing subsequent non-plating defects during galvanizing while preserving the beneficial mechanical properties of Si-containing steel
2Object-affected harmful factors
If dew point is raised by injection of humidified gas to internally oxidize Si, then non-plating defects are reduced, but manufacturing process complexity increases
Solution Approach 1:
The invention controls the dew point parameter within a specific range (-30°C to 0°C) during annealing to achieve optimal Si oxidation. This parameter control approach simplifies the process compared to aggressive humidified gas injection, as it only requires maintaining dew point within the specified range rather than actively injecting gases, thereby reducing equipment complexity while still effectively preventing non-plating defects
3Productivity
If machine learning prediction is implemented, then non-plating defects are accurately predicted and yield is improved, but measurement and data processing complexity increases
Solution Approach 1:
The invention implements a feedback mechanism where a non-plating defect prediction model (trained using machine learning on historical data including steel sheet attributes, annealing conditions, and defect occurrences) continuously predicts the likelihood of non-plating defects. The prediction results are fed back to adjust annealing parameters (dew point, temperature, time) in real-time, creating a closed-loop control system that improves yield while managing measurement complexity through automated data processing
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately predicts non-plating defects and reduces their frequency, thereby improving the manufacturing yield of hot-dip galvanized steel sheets.
Implementation Method 1
heat annealing of the steel sheet of the base material is performed at a temperature of about 600 to 900° C. in a reducing atmosphere or a non-oxidizing atmosphere
Implementation Method 2
Si in steel is an easily oxidized element, and is selectively oxidized even in a generally used reducing atmosphere or non-oxidizing atmosphere, and is concentrated on the steel sheet surface and forms an oxide
Implementation Method 3
This oxide reduces wettability of the steel sheet and the hot-dip galvanizing during the hot-dip galvanizing treatment
Implementation Method 4
a hot-dip galvanizing treatment is performed on a steel sheet surface, whereby a hot-dip galvanized steel sheet is manufactured
Data Source
AI summary
A steel-sheet non-plating defect prediction method in manufacturing equipment of a hot-dip galvanized steel sheet which equipment includes an annealing furnace, and a plating device arranged on a downstream side of the annealing furnace, the method includes: predicting steel-sheet non-plating defect information on an exit side of the manufacturing equipment by using a non-plating defect prediction model which is learned by machine learning, the non-plating defect prediction model for which an input data is data including one or two or more parameters selected from attribute information of a steel sheet charged into the manufacturing equipment, one or two or more operational parameters selected from operational parameters of the annealing furnace, and one or two or more operational parameters selected from operational parameters of the plating device, and an output data is non-plating defect information of the steel sheet on the exit side of the manufacturing equipment.