Data Science Methods and Tools for Industry 4.0: A Systematic Literature Review and Taxonomy.

Area of Science:

• Computer Science
• Industrial Engineering
• Data Science

Background:

• Industry 4.0 involves automated manufacturing and massive sensor data generation.
• Data science methods and tools are crucial for interpreting this industrial data.
• Effective data interpretation supports managerial and technical decision-making.

Purpose of the Study:

• To systematically review data science methods and tools in Industry 4.0.
• To investigate their application across different industrial segments, time series levels, and data quality.
• To synthesize the state-of-the-art for future research.

Main Methods:

• Systematic literature review of 10,456 articles from five academic databases.
• Filtering and selection of 103 articles for the study corpus.
• Answering seven research questions (three general, two focused, two statistical).

Main Results:

• Identified 16 distinct industrial segments utilizing Industry 4.0 technologies.
• Cataloged 168 data science methods and 95 software tools employed in the literature.
• Highlighted the use of various neural network subvariations and noted missing data composition details.

Conclusions:

• The research synthesizes a state-of-the-art representation of data science in Industry 4.0.
• A taxonomic approach visualizes findings to guide future research.
• Understanding data science applications is key to advancing Industry 4.0.