6.08 WASTELESS: Enhancing Additive Manufacturing for Waste Reduction through Big Data mining, in-situ monitoring and control and net-shape design and production

SPOKE DI RIFERIMENTO
SPOKE CORRELATI
PROJECT LEADER
Bianca Maria Colosimo
DATA INIZIO
Gennaio 2023
DATA FINE
Dicembre 2025
PROPOSER
Politecnico di Milano
PARTNER COINVOLTI

Politecnico di Bari, Università degli studi di Napoli Federico II, Università degli Studi di Padova, Brembo S.p.A, Camozzi Group S.p.A., Prima Additive S.R.L., Leonardo S.p.A., Thales Alenia Space Italia S.p.A. 

6.08 WASTELESS: Enhancing Additive Manufacturing for Waste Reduction through Big Data mining, in-situ monitoring and control and net-shape design and production

The primary objective of this project is to create an advanced autonomous and intelligent Additive Manufacturing (AM) platform that utilizes innovative sensing solutions, big data mining, self-learning, and adaptive control to produce defect-free 3D printed parts. This will involve the implementation of new defect prevention, detection, correction, and postprocessing solutions, as well as the design of complex shapes and defect-tolerant geometries.
The project will be based on five main research pillars: design for zero-waste, inspection and measurement, modeling, control, and improvement. The project will specifically focus on addressing complex challenges in AM, such as lattice structures and support-free parts, to achieve first-time-right AM capabilities and improve geometrical conformity and roughness. The system will possess autonomous learning, prediction, self-adaptation, and self-correction capabilities, making it a novel and advanced type of AM system.

Task 6.4.1 New solutions for AM sensing (POLIMI, POLIBA, CAMOZZI, PRIMA, UNINA) New solutions for measuring process signature in-situ and in-line

Task 6.4.2 In-situ and ex-situ correlation of defect for inline qualification (POLIMI, UNIPD)
Approaches to link the in-situ signature with the defects observed on the printed products

Task 6.4.3 Big data mining (POLIMI, POLIBA, UNINA) – Use of machine learning, data fusion, artificial intelligence (AI) and digital twin per zero-waste production in AM

Task 6.4.4 Feedforward e feedback control in metal AM (POLIMI, POLIBA, UNINA) – new solutions for predicting and healing defects insitu and inline

Task 6.4.5 Process chains for improved surface finish and structural integrity of highperformance mechanical parts (Brembo, UNIPD). To improve the structural durability of highperformance mechanical parts made of Al and Ti alloys, the entire AM-based process chain needs to be optimised, including thermal treatments, and finishing operations. State-of-the-art fatigue modelling and testing will be included. Sustainable finishing operations based on cryogenic cooling have the potential to increase fatigue and corrosion resistance and will be investigated.

Task 6.4.6 Design and manufacturing of defect-tolerant lattice structure
(POLIMI Leonardo) – new solutions for lightweight lattice structures via defect-tolerant design and in-situ data mining

Task 6.4.7 Hybrid extrusion-based AM (POLIBA) smart sensing as a support to combine
additive and subtractive solutions for net-shape zero-defect products

Task 6.4.8 New solutions of space AM (POLIMI, THALES) smart sensing for first-time Am in unknown, unexpected conditions.

RISULTATI ATTESI

We expect to design a new generation of Additive Manufacturing (AM) solutions that minimize resource waste by reducing defects, supports, and enabling first-time-right production, even for non-expert users in small and medium-sized enterprises (SMEs).
The expected results include:

  • Developing new design solutions for defect-tolerant, high-performance, green products that are lightweight and long-lasting with fewer components.
  • Designing a new platform that incorporates AI and big data mining for in-situ
    qualification of AM printed products.
  • Developing novel solutions for closed-loop control of AM processes, which are not currently available in the literature.
  • Developing a new generation of sustainable AM processes that produce green products supported by AI and big data mining.
  • Establishing a relationship between in-situ process signatures and ex-situ defect
    qualification to define new processes and process strategies.
  • Improving the reliability of high-performance parts made using AM technologies.
  • Enhancing the understanding of the effects of multiple process chain steps, including thermal treatments and finishing operations.
  • Improving fatigue modelling and testing procedures.

Overall, the project is expected to result in significant advancements in AM technology, enabling the production of green and sustainable products with improved reliability and reduced waste.

WASTELESS project KPI’s:

  • Defect reduction: The project aims to minimize defects in 3D printed parts: 30%
    reduction in the number of defects in parts produced using the new AM platform compared to traditional AM systems.
  • First-time-right production rate: The project aims to achieve first-time-right production capabilities: 80% of parts that are produced without defects on the first attempt.
  • Resource efficiency: The project aims to minimize resource waste in AM: 40% of
    reduction in the amount of material and energy used to produce a given part compared to traditional AM systems.
  • Reliability: The project aims to improve the reliability of high-performance parts
    produced using AM technologies: 20% increase in the mean time between failures (MTBF) of parts produced using the new AM platform compared to traditional AM systems.
  • Productivity: the first-time-right production rate, which measures the percentage of parts that are produced without defects on the first attempt, can impact productivity by reducing the need for rework or reprinting of defective parts. This can help increase the overall throughput and speed of the AM process, leading to a higher number of parts produced per unit time (+30%).