PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

OpenSSA: Small Specialist Agents based on Domain-Aware Neurosymbolic Agent (DANA) architecture for industrial problem-solving

roadmap to applied ai

AI SDK Tutorials helps you to get familiar with AI Software Development Kit (AI SDK) through a set of end-to-end tutorials, how-to jupyter notebooks, and how-to guides.

Build an enterprise-level AI agent operating system enabling cross-departmental and cross-system intelligent collaboration.

[CVPRW'25] Official Code For "SK-RD4AD: Skip-Connected Reverse Distillation for One-Class Anomaly Detection"

This article presents a reference architecture to enhance the compatibility of Siemens Industrial Artificial Intelligence (Industrial AI) products with Microsoft Azure.

This repository provides code for the paper "Vipul Bansal, Yong Chen, Shiyu Zhou, Component-Wise Markov Decision Process for Solving Condition Based Maintenance of Large Multi-Component Systems with Economic Dependence"

Build an enterprise-level AI agent operating system enabling cross-departmental and cross-system intelligent collaboration.

Automatically identify whether the sounds produced by industrial machines are normal or anomalous (faulty machines). This is crucial for ensuring efficient and safe operations in the context of AI-based factory automation.

Industrial AI Agents using LLMs

[CVPR 2025 Workshop] SK-RD4AD: Skip-Connected Reverse Distillation for One-Class Anomaly Detection

A GitOps-driven pipeline for automated prediction of industrial equipment efficiency. Includes Dockerized ML models, CI/CD integration with Jenkins, and infrastructure-as-code practices for scalable deployment.

Zero and few-shot industrial image anomaly detection framework comparing AnomalyDINO & MuSc models across MVTec AD, BTAD, and ViSA datasets with MLflow tracking and flexible configuration.

Industrial LLM Engine is an innovative and scalable solution engineered to empower large language models to understand and analyze industrial telemetry data, transforming raw measurements into actionable insights.

Predicting product quality in hot forming processes using interpretable machine learning models. Includes preprocessing, feature engineering, model selection and evaluation in a reproducible Docker setup. Based on a master’s thesis in Industrial Data Science / Engineering.

Image classification project to detect defective products in manufacturing processes using deep learning. Helps automate quality control by classifying items as 'Defective' or 'Non-Defective'.

SDK to Implement custom Industrial camera connectors for usage in Siemens Vision Connector

AI-powered production line optimization using reinforcement learning (PPO).