Analyzing industrial robot selection based on a fuzzy neural network under triangular fuzzy numbers

Area of Science:

• Engineering
• Artificial Intelligence
• Decision Science

Background:

• Selecting the appropriate industrial robot is complex due to numerous available models.
• Production companies require robust methods for optimal robot selection tailored to specific needs.
• Existing decision-making processes may lack the precision needed for complex industrial environments.

Purpose of the Study:

• To develop and apply a novel Triangular Fuzzy Neural Network (TFNN) decision model for industrial robot selection.
• To address the specific challenge faced by a Pakistani production company in choosing the most suitable robot.
• To integrate expert knowledge and fuzzy logic for a more accurate selection process.

Main Methods:

• A novel Triangular Fuzzy Neural Network (TFNN) with a Yager aggregation operator was introduced.
• Expert information was collected using Triangular Fuzzy Numbers (TFNs).
• Distance measure techniques and Yager aggregation were employed for weight calculation and information aggregation across network layers.

Main Results:

• The TFNN model successfully processed expert information and calculated criteria weights.
• The model aggregated information through hidden and output layers, generating score values.
• The final ranking of robots was achieved using activation functions, identifying the most suitable option.

Conclusions:

• The proposed TFNN decision model provides an effective framework for industrial robot selection.
• The integration of fuzzy logic and neural networks enhances the precision of complex decision-making tasks.
• This approach offers a valuable tool for production companies seeking to optimize their robotic investments.