|
Project name |
aiWOODassist - AI module for optimizing the machining of advanced eco-way materials |
| Project number | CZ.01.01.01/01/24_063/0006771 |
| Beneficary | HOUFEK a.s. |
| Total budget | 26 509 606 CZK |
| Total budget of FLD | 3 664 311 CZK |
| Implementation period | 1.7.2025 – 30.6.2028 |
| Grantor | Ministry of Industry and Trade of the Czech Republic |
| Name of programme | Operational Programme Technologies and Application for Competitiveness |
| Call name | Applications – Call III. – DEEP TECH |
Project annotation:
The aiWOODassist project focuses on developing an advanced AI module to optimize technical preparation in the production of CNC machines designed for milling progressive eco-way materials. The system will combine advanced sensor technology, camera imaging, and machine learning algorithms for automated monitoring and offering options for optimizing cutting parameters. This will reduce errors and enable more efficient use of materials.
What problem does the project deal with?
Current CNC milling processes are not sufficiently optimized for machining progressive eco-way materials. This results in higher scrap rates, inefficient use of raw materials, and increased energy consumption. The process of preparing machining technology for new materials is time-consuming, material-intensive, and costly, requiring extensive testing and experienced specialists. This factor slows down the wider implementation of eco-friendly composite materials in the manufacturing sector.
Causes of the problem:
The main reason for this problem is that the technical preparation of machines for machining new materials is carried out by trial and error, which leads to excessive tool wear and higher material consumption. In this way, even an experienced technician is unable to achieve optimal cutting parameters; his goal is only to achieve the minimum error rate specified by the standard/customer. At present, the modern possibilities of using intelligent adaptive control systems that would automatically optimize machining parameters based on sensor data are still not sufficiently exploited. Current CNC milling of eco-way materials requires manual parameter setting, causes errors, and is very time-consuming.
Project goal:
The main objective of the project is to develop and implement the aiWOODassist intelligent module, which will enable automated and adaptive setting of milling parameters using artificial intelligence based on data from sensors and a camera system, fully in line with the field of deep tech artificial intelligence and machine learning, including big data. The aim of the project is to develop the deep tech field of artificial intelligence, primarily within machine learning (specifically supervised learning) as a subfield of artificial intelligence, in the form of learning and applying a model for the automated optimization of machining parameters for the machining of innovative eco-materials. This will make it possible to achieve optimized settings for all cutting parameters, which cannot be achieved by conventional trial and error methods. The development of the device will lead to faster and more accurate machine settings for the customer, thereby increasing milling efficiency, reducing error rates, optimizing energy consumption, and expanding the use of environmentally friendly composite materials in industrial production. The project will result in a functional prototype of the device, a digital AI model solution, and a verified AI-based adjustment technology. The three outputs in the project indicator will be supplemented by a published scientific article for further future development of science and research based on the findings.
Expected changes as a result of project implementation:
The introduction of the aiWOODassist system will bring about a fundamental transformation in the CNC machining of advanced materials. The implementation of machine learning will enable immediate analysis and optimization of milling parameters, reducing the need for manual adjustment and shortening the time required for technological preparation of production. The result will be a reduction in energy and material consumption, increased productivity, and improved surface machining quality of eco-way materials, thus promoting the wider use of environmentally friendly materials in practice. This will also lead to greater sustainability in industrial production.
