Coupling Taguchi experimental designs with deep adaptive learning enhanced AI process models for experimental cost...

Area of Science:

• Materials Science and Engineering
• Manufacturing Processes
• Artificial Intelligence in Engineering

Background:

• Machining optimization for aluminum alloys like AA7075 is crucial for cost-effective manufacturing.
• Traditional experimental designs can be resource-intensive, necessitating more efficient methods.

Purpose of the Study:

• To investigate the potential of deep adaptive learning-enhanced artificial intelligence (AI) process models for optimizing dry finishing turning operations.
• To evaluate AI models' ability to understand low-resolution experimental designs and identify causal relationships.
• To achieve significant cost savings in machining process optimization.

Main Methods:

• Utilized L18 (6^13^3) Taguchi orthogonal array experiments with six tool inserts and three operational parameters (depth of cut, feed rate, cutting speed).
• Trained AI models, including Multi-layer Perceptron Artificial Neural Networks (MLP-ANNs), Support Vector Machines (SVMs), and Decision Trees, using experimental data.
• Compared AI models for their efficacy in understanding low-resolution experimental designs and identifying causal relationships between input and output variables.

Main Results:

• AI models successfully identified optimal operational input ranges for workpiece surface roughness and tool life.
• AI-response surfaces revealed distinct tool life behaviors for alloy-based versus non-alloy-based coated tool inserts.
• The AI-Taguchi hybrid modeling achieved 26% experimental savings compared to conventional Taguchi design with full factorial experimentation.

Conclusions:

• Deep adaptive learning-enhanced AI models offer a promising approach for optimizing machining processes with reduced experimental effort.
• AI models can effectively extract causal relationships from low-resolution experimental data, leading to significant cost savings.
• The AI-Taguchi hybrid technique provides a powerful tool for efficient machining process optimization in industries utilizing aluminum alloys.