Casting Mold Temperature Control With ML-Guided Thermocouple Layout

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional mold temperature control in low-pressure casting processes lacks accuracy and timely adjustment, relying heavily on human experience, which is inadequate for modern production needs and complex casting structures.

Innovation Solution

An intelligent temperature control method using thermocouples arranged based on mold feature regions, combined with a random forest model and gradient boosting decision tree model, to optimize thermocouple placement and dynamically adjust cooling processes for precise mold temperature control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If open-loop control mode is used for mold temperature control, then the control system is simple and easy to operate, but the temperature control accuracy is poor and adjustment is not timely

Engineering Contradiction:
Improveease of operationVSAvoidtemperature control accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent implements a closed-loop feedback control system by installing thermocouples at multiple positions in the mold to detect temperature in real-time. The detected temperature data is fed back to the control system, which automatically adjusts cooling parameters to maintain optimal temperature, thereby improving temperature control accuracy and timeliness while maintaining operational simplicity through automation.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces manual mechanical adjustment of cooling parameters with an automated electronic control system. The control system uses algorithms to process temperature data and automatically adjusts cooling parameters, substituting human judgment and manual operation with automated electronic control, thus improving both accuracy and timeliness of temperature adjustment.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If multiple thermocouples are arranged in the mold, then temperature measurement coverage is improved, but the complexity of thermocouple arrangement and data processing increases

Engineering Contradiction:
Improvetemperature measurement coverageVSAvoidthermocouple arrangement complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by strategically placing thermocouples at specific critical positions in the mold where temperature control is most important, rather than uniformly distributing them throughout. This targeted approach improves temperature measurement coverage at key locations while minimizing the total number of thermocouples needed, thereby reducing arrangement and data processing complexity.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent segments the mold into different regions and places thermocouples at representative positions in each region. This segmentation approach allows comprehensive temperature monitoring across the entire mold while using a manageable number of thermocouples, as each thermocouple represents the temperature characteristics of its specific region.

Inventive Principle:
Principle #1Segmentation

3Device complexity

If manual adjustment of cooling parameters based on technician experience is used, then the control system is simple, but the process stability is poor and automation cannot be achieved

Engineering Contradiction:
Improvecontrol system complexityVSAvoidprocess stability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent implements self-service control where the system automatically monitors temperature, analyzes data, and adjusts cooling parameters without human intervention. The control system uses embedded algorithms to process temperature data from thermocouples and automatically modifies cooling parameters to maintain optimal temperature, achieving both automation and process stability while keeping the control system relatively simple.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent establishes a closed-loop feedback control mechanism where temperature data is continuously monitored and fed back to the control system, which automatically adjusts cooling parameters in response to temperature variations. This feedback-driven automation improves process stability and eliminates reliance on technician experience, achieving reliable automated control with moderate system complexity.

Inventive Principle:
Principle #23Feedback

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

Improves temperature control accuracy and timeliness, reducing defects and ensuring high-quality manufacturing of aluminum alloy castings by automating the process.

Implementation Method 1

obtaining feature regions of a casting mold and arranging thermocouples in the feature regions of the mold based on structural characteristics of castings

Methodology Applied
Scientific EffectSeebeck effect: Seebeck Effect

Implementation Method 2

During filling and solidification, an alloy melt, which is in direct contact with a mold, cools and solidifies through heat exchange

Methodology Applied
Scientific EffectHeat conduction: Conduction (thermal)

Implementation Method 3

Mold temperature is controlled within a reasonable range through an appropriate cooling process

Methodology Applied
Scientific EffectConvection: Convection

Data Source

PatentUS20260086512A1Intelligent temperature control method for casting system
Publication Date: 2026.03.26 CITIC DICASTAL CO LTD
  • US20260086512A1 patent drawing
  • US20260086512A1 patent drawing
  • US20260086512A1 patent drawing

AI summary

The present disclosure provides an intelligent temperature control method for a casting system, including: obtaining feature regions of a casting mold and arranging thermocouples in the feature regions of the mold based on structural characteristics of castings; building a random forest model and performing recursive feature elimination based on temperature measurement results of the thermocouples and casting quality inspection results, to determine a correlation between temperature measurement data of each thermocouple and casting quality, thereby optimizing a quantity of the thermocouples and screening the thermocouples; and analyzing temperature data of screened thermocouple temperature measurement points, cooling process parameters, and corresponding casting quality, constructing a relation among the cooling process parameters, an initial temperature of each thermocouple in the mold, and the casting quality through a gradient boosting decision tree model, and controlling the temperature of the casting system based on the relation.