This volume constitutes the refereed proceedings of the 7th International Workshop on AI System Engineering: Math, Modelling and Software, AISys 2025 and the First International Workshop on Optimisation of Industrial Production with AI Algorithms, AI4IP, co-located with the 36th International Conference on Database and Expert Systems Applications, DEXA 2025, which took place in Bangkok, Thailand, during August 25-27, 2025.
The 11 full papers were thoroughly reviewed and selected from a total of 23 submissions. They are organized in topical sections as follows: AI System Engineering: Math, Modelling and Software; and Optimization of Industrial Production with AI Algorithms.

Klappentext

.- AI System Engineering: Math, Modelling and Software. .- Exploring the benefits of iterative retrieval-augmented generation for risk mitiga tion in LLM response. .- TrustAI: Designing and Implementing a Trustworthy and User-Centered AI Plat form. .- Collaborative Trustworthy Foundation Model Framework: An Environmental Sustainability Use-Case to Detect Contamination Objects in Organic Waste Streams. .- Optimisation of Industrial Production with AI Algorithms. .- Efficient Federated Learning Integration into Existing MLOps Pipelines via Centralized Model Management. .- Deep Photometric Stereo for Tool Wear Inspection. .- Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control. .- Deep learning-based defect detection in laser powder bed fusion. .- Prediction of CNC Manufacturing Time Under Real-World Conditions Using Graph Convolutional Networks. .- A Vision-Guided Approach to Pick-and-Place Robotics: From Assembly Drawings to Industrial Assembly Automation. .- Towards Real-time Tool Wear Detection on Edge Devices: A Lightweight Di mensionality Reduction Approach for Spindle Integrated Cutting Force Sensor Data. .- Energy Optimized Piecewise Polynomial Approximation Utilizing Modern Ma chine Learning Optimizers.

Inhalt

.- AI System Engineering: Math, Modelling and Software.

.- Exploring the benefits of iterative retrieval-augmented generation for risk mitiga tion in LLM response.

.- TrustAI: Designing and Implementing a Trustworthy and User-Centered AI Plat form.

.- Collaborative Trustworthy Foundation Model Framework: An Environmental Sustainability Use-Case to Detect Contamination Objects in Organic Waste Streams.

.- Optimisation of Industrial Production with AI Algorithms.

.- Efficient Federated Learning Integration into Existing MLOps Pipelines via Centralized Model Management.

.- Deep Photometric Stereo for Tool Wear Inspection.

.- Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control.

.- Deep learning-based defect detection in laser powder bed fusion.

.- Prediction of CNC Manufacturing Time Under Real-World Conditions Using Graph Convolutional Networks.

.- A Vision-Guided Approach to Pick-and-Place Robotics: From Assembly Drawings to Industrial Assembly Automation.

.- Towards Real-time Tool Wear Detection on Edge Devices: A Lightweight Di mensionality Reduction Approach for Spindle Integrated Cutting Force Sensor
Data.

.- Energy Optimized Piecewise Polynomial Approximation Utilizing Modern Ma chine Learning Optimizers.