ADINO – Adaptive Intelligence For State-aware Industrial Optimization

The project develops artifical intelligence (AI) based solutions into the processes of the manufacturing industry.

ADINO – Adaptive Intelligence for State‑aware Industrial Optimization

The ADINO project develops human‑centric, state‑aware AI solutions that help industrial companies optimize production, resource flows, and decision‑making in real time. The project is jointly implemented by Centria University of Applied Sciences and Turku University of Applied Sciences, in close collaboration with industrial partners.

Modern factories generate vast amounts of data from machines, sensors, systems, and people, yet this data is often fragmented. ADINO addresses this challenge by integrating AI, IoT, digital twins, vision systems, and human input into a unified framework that improves efficiency, safety, sustainability, and competitiveness—while keeping humans in control.

At its core, ADINO focuses on augmenting workers, optimizing material and energy flows, and monitoring machines proactively. AI continuously analyzes the operational state, highlights risks and anomalies, and provides clear, explainable recommendations to support faster and better decisions on the shop floor.

Project Goals

• Optimize industrial resource flows involving workers, materials, machines, and energy
• Enable real‑time situational awareness through AI, IoT, and digital twins
• Improve energy efficiency, quality, and workplace safety
• Support human‑centric AI, where AI assists rather than replaces operators
• Strengthen collaboration between research institutions and industry and develop scalable AI business models

Example Pilots

ADINO pilots demonstrate practical impact in real industrial environments:

• AI‑assisted work reporting: capture spoken explanations and photos, auto‑generate ERP/MES reports
• Ergonomics and safety monitoring: detect physically risky movements using video‑based pose tracking
• Material flow tracking: combine logs and cameras to prevent picking errors and expose bottlenecks
• Predictive maintenance: detect early breakdown risks from sensor, log, and operator data
• AI‑based quality inspection: flag visual anomalies with scores and highlighted areas for fast human verification

Human‑Centric AI Vision

Centria University of Applied Sciences and Turku University of Applied Sciences are implementing the project in cooperation. The aim of the higher education institutions is to increase competence and share knowledge in close cooperation with companies with the aim of raising the level of competence in AI, Deep learning, Data Analytics techniques and advanced production technologies.

International Research Partners

1. University of Birmingham United Kingdom

Research partner contributing to advanced intelligence and industrial AI methods

2. Fraunhover Institute for Machine Tools and Forming Technology (Fraunhover IWU) Germany

Research partner specializing in smart manufacturing, digital production systems, and industrial optimization

3. Hamburg University of Applied Sciences (HAW Hamburg) Germany

Research partner supporting applied research in industrial automation and human-centric manufacturing systems

Professor Himat Shah was awarded a PhD degree in Computer Science from the University of Eastern Finland, specializing in machine learning and data science. In addition, he holds two master’s degrees: Masters in Business Administration (MBA) degree from the United Kingdom (UK) and one in Computer Sciences from Pakistan. He has also several years of experience in teaching and research at different universities.

At Centria, he works as a senior researcher and lecturer in the Centria Robotics and Artificial Intelligence top research group.