Periodic Reporting for period 1 - AMA - AM meets AI (Accelerating the transition to innovative and sustainable manufacturing by an AI-based software simulation that achieves first-time right printing of lightweight and complex of aluminium alloy parts.)
Période du rapport: 2022-06-01 au 2023-05-31
Additive Manufacturing (AM), commonly known as 3D printing, heralds a new era in manufacturing, characterized by the creation of complex and customized components through a layer-by-layer construction process, guided by digital models. This technique stands in stark contrast to traditional subtractive manufacturing methods, where material is removed from a larger piece to shape the desired object. AM has carved a niche in several industries, such as aerospace, healthcare, automotive, and construction, facilitating the development of intricate geometries, minimizing material wastage, and democratizing manufacturing entry barriers.
Besides its promises, it has still some shortcomings, that need to be overcome for a fully industrialized additive manufacturing.
This includes:
Process Stability: The AM process is often prone to fluctuations and inconsistencies due to various factors such as material properties, machine parameters, and environmental conditions. These variations can lead to a lack of process stability, which is particularly challenging when scaling up the production.
High Scrap Rate: The intricacies of the AM process sometimes result in a high scrap rate, as the produced parts do not always meet the requisite quality standards. This not only leads to material wastage but also drives up the manufacturing costs, making scaling an economically challenging proposition.
Post-Processing Requirements: AM usually necessitates substantial post-processing steps, including support removal and surface finishing. These processes can add to both the time and cost of manufacturing, thereby curtailing the economic feasibility of large-scale production.
Quality Consistency: Ensuring a uniform quality across production batches is a significant challenge in AM. The process might introduce defects and variations, which are unacceptable, especially in industries where component quality is of paramount importance, such as aerospace and healthcare.
Technical Expertise: Implementing AM at a larger scale requires a nuanced understanding of both design and production nuances. Cultivating this expertise is both time and resource-intensive, which can potentially hinder the scalability of the technology.
In this project, we have worked on a software solution and the business plan for the company to sell a software solution that can tackle the mentioned issues leveraging artificial intelligence and cloud computing.
Besides its promises, it has still some shortcomings, that need to be overcome for a fully industrialized additive manufacturing.
This includes:
Process Stability: The AM process is often prone to fluctuations and inconsistencies due to various factors such as material properties, machine parameters, and environmental conditions. These variations can lead to a lack of process stability, which is particularly challenging when scaling up the production.
High Scrap Rate: The intricacies of the AM process sometimes result in a high scrap rate, as the produced parts do not always meet the requisite quality standards. This not only leads to material wastage but also drives up the manufacturing costs, making scaling an economically challenging proposition.
Post-Processing Requirements: AM usually necessitates substantial post-processing steps, including support removal and surface finishing. These processes can add to both the time and cost of manufacturing, thereby curtailing the economic feasibility of large-scale production.
Quality Consistency: Ensuring a uniform quality across production batches is a significant challenge in AM. The process might introduce defects and variations, which are unacceptable, especially in industries where component quality is of paramount importance, such as aerospace and healthcare.
Technical Expertise: Implementing AM at a larger scale requires a nuanced understanding of both design and production nuances. Cultivating this expertise is both time and resource-intensive, which can potentially hinder the scalability of the technology.
In this project, we have worked on a software solution and the business plan for the company to sell a software solution that can tackle the mentioned issues leveraging artificial intelligence and cloud computing.
The following main activites have been performed:
Activity 1: Detailed definition of the use case based on realistic customer challenge
Activity 2: Building the AI process simulation and correction to this material
Activity 3: Additive manufacturing build preparation
Activity 4: Optimization workflow
Activity 5: Print with our partner
Activity 6: Preparations of technical reports
The main achievement include a material model for an Al-based alloy and an optimized print process for our partner.
Activity 1: Detailed definition of the use case based on realistic customer challenge
Activity 2: Building the AI process simulation and correction to this material
Activity 3: Additive manufacturing build preparation
Activity 4: Optimization workflow
Activity 5: Print with our partner
Activity 6: Preparations of technical reports
The main achievement include a material model for an Al-based alloy and an optimized print process for our partner.
The results we've achieved represent a significant advancement, both from technical and business perspectives. We have innovated a novel approach to training material models, specifically designed to predict thermal issues in laser powder bed fusion. This breakthrough will soon be integrated into our software product, further enhancing its capabilities. Moreover, our inclusion of an aluminum-based material model not only opens doors to new market opportunities but also presents us with unique technical challenges that we are eager and well-prepared to address with our software solution.