COALA | COgnitive Assisted agile manufacturing for a LAbor force supported by trustworthy Artificial Intelligence
01-10-2020
-30-09-2023
The COALA solution will support the workers when performing process and product quality inspections with quality predictions and prescriptions for mitigation measures. The Augmented Manufacturing Analytics feature is A set of DIA functions interfacing the prescriptive quality analytics service connected to shop floor data sources. It will enable non-data-scientist workers to utilize and customize data analytics during product quality tests.
COALA will contribute in the ongoing discussion about AI ethics and potential standards, monitor the standardization potential for worker education under consideration of AI competencies, and will use and contribute to IT standards. We will take into account available IT-related standards and use them when applicable. This includes normative standards as set by ISO and its national bodies, which are of high importance to industrial companies. We will assess standards proposed by major influential de-facto standardization bodies like W3C, OASIS, and OMG. Standardization topics concern:
- The technical system architecture level. Standardize communication protocols, data exchange formats, data exchange interfaces.
- The content level. Ontologies for the semantic data integration and the WHY engine.
- The process level. This includes innovation management system, terminology, terms and definitions, and tools and methods.
COALA solution for on-the-job-training using digital assistant allows the workers to meet the requirements of their work environtment: to be skilled and flexible. To keep up with continuously changing demands and to cope with altering product and process information, production workers need to adopt an approach that welcomes change. They need to be empowered by making customization transparent, enabling rapid adaptations, providing operational flexibility, and augmentation of their skills.
COALA aims to develop a cognitive advisor with dedicated human-assisted AI methods for enabling transfer of tacit knowledge of experts to novice workers. The transfer of tacit knowledge of production workers that grows with their experiences enabling them to cope with challenges of agile manufacturing.
For the change over time we expect a reduction of 15% to 30% by shortening the worker training time.
COALA is expected to impact on the productivity of employees involved in the quality detection
and repair as well as on reduction of the not detected defects delivered.
- COALA solution aims to meet manufacturing requirements regarding, e.g. time criticality, reliability (e.g. deal with factory noise, number of defects), safety when giving advice to workers, and security in business environments.
- The COALA didactic concept will provide media materials, exercises, and competencies tests to teach factory workers and evaluate their learning progress regarding the opportunities, challenges (e.g. reliability, accuracy, and accountability of AI decisions), and risks (e.g. data security, ethical issues, and information quality) when working with AI-powered digital assistants.
- A Market Analysis (Value Chain analysis, competition evaluation, market segmentation and sizing, business expectations) will be performed to define a successful strategic positioning of COALA.
- A Business Model and Plan will be developed in order to define a go-to-market strategy and demonstrate the financial interest.
COALA's three use cases (textile, white goods, liquid production) will evaluate the COALA solution in their manufacturing processes with significant economic value.