Supervised artificial intelligence classification of clinker processing conditions by optical microscopy

Area of Science:

• Materials Science
• Computer Science
• Industrial Chemistry

Background:

• Optical microscopy is crucial for characterizing industrial clinkers, providing insights into production processes.
• Current limitations include time-consuming sample preparation, image interpretation, and operator subjectivity.
• Automating clinker analysis is of significant interest to enhance efficiency and objectivity.

Purpose of the Study:

• To investigate the application of supervised artificial intelligence (AI) methodologies to clinker micrographs.
• To assess AI's capability to support human operators in interpreting experimental results.
• To evaluate AI's potential for autonomously determining experimental parameters in clinker analysis.

Main Methods:

• Utilized supervised artificial intelligence (AI) models.
• Applied AI to a dataset of clinker micrographs.
• Focused on AI's ability to interpret images and determine experimental parameters.

Main Results:

• AI models demonstrated a promising capability in analyzing clinker micrographs.
• The study confirmed AI's potential to support human operators in result interpretation.
• AI showed effectiveness in autonomously determining experimental parameters.

Conclusions:

• Supervised AI methodologies show significant potential for automating industrial clinker analysis.
• AI can enhance the objectivity and efficiency of optical microscopy in clinker characterization.
• Further development of AI in this field could revolutionize industrial process monitoring.