Machine learning: the importance of artificial intelligence for additive manufacturing

For many companies, digitization and automation are the keys to the further development of additive manufacturing. Thus, more and more manufacturers are relying on cloud-based solutions and integrating various algorithms into their 3D printing solutions in order to exploit the full potential of the technology. As a digital process in itself, 3D printing is part of Industry 4.0 and therefore an important component of an era where artificial intelligence, such as machine learning, is increasingly used to optimize the value chain. Artificial intelligence (AI) is able to process a large amount of complex data in a very short period of time, which is why it is becoming increasingly important as a decision maker. We explain what machine learning is and why this form of AI is helping to shape the future of additive manufacturing.

Machine learning is a subcategory of AI and is defined as a system or software that uses algorithms to examine data and then recognize patterns or determine solutions. Contrary to a widespread belief that machine learning is a new kind of phenomenon, it can be said that its beginnings date back to the 1940s, when the first researchers began to recreate the neurons in the brain with electrical circuits. In 1957, the Mark I Perceptron was the first big success in this area: the machine was able to classify input data independently. In doing so, the device learned from mistakes made in previous attempts, which improved the classification over time. Since then, the foundations have been laid and researchers have become fascinated by the possibilities and potential of the technology. In the meantime, we encounter artificial intelligence in all areas of life every day. From speech recognition to smart chatbots to personalized treatment plans, machine learning is used in a variety of applications.

The Mark I Perceptron laid the foundation for machine learning.

Supervised or unsupervised machine learning

In the machine learning spectrum, it is important to distinguish between different methods and models. Not all automatic learnings are the same. For example, a distinction should be made between supervised and unsupervised machine learning. Supervised machine learning requires that the categorized data (input data) and the target variable (output data) are available. From these, the model is derived, which then examines the (new) uncategorized data and itself determines the target variable for it. This form of machine learning is used, for example, for predictions, for example: to predict maintenance intervals.

In unsupervised machine learning, the opposite is true as a starting point. The software does not have a target variable (output data), but must recognize patterns or suggest solutions based on the input data. This type of machine learning is used, among other things, in marketing to identify customer segments, which is called “clustering”. But there are other differences. For example, there is still semi-supervised learning, which uses only a small amount of predefined data in a large amount of raw data to train the model, and reinforcement learning, in which the system learns itself. even according to predefined rules. Therefore, users should choose the appropriate method based on the raw data and the target variable.

How is machine learning used in additive manufacturing?

As a digital production process, additive manufacturing benefits from the capabilities of machine learning. As countless data is collected and processed (in real time) along the additive value chain, it can be used to analyze the REAL state and subsequently redefine the TARGET state. In doing so, it is first important for companies to define what data is relevant. This decision depends in each case on the method used. The next step is to find and integrate the right measurement tool to capture the values ​​before defining an appropriate model or algorithm for data collection and processing. In this context, it is also important to understand that all stages of the additive value chain influence each other, which is why an isolated view is not appropriate in most cases. For example, the design already influences the quality of subsequent components and the desired component quality influences the design. For this reason, more and more companies are trying to offer a complete software solution with which the advantages of artificial intelligence can be exploited in the best possible way for the additive manufacturing process.

Smart design

At the start of every 3D printed component is a file, in most cases a CAD file. This is already where businesses can benefit from artificial intelligence. For example, most of the software solutions on the market today already use AI to suggest smart design variations to users based on predefined variables. This process is known as generative design, among others. Machine learning is also used for topology optimization. Many software solutions also make suggestions on production methods, materials and the optimal use of installation space. This helps to reduce costs and produce parts not only more efficiently, but also in a more sustainable manner.

The simulation tool of the nTop software offers several variants of a lattice structure and classifies them according to weight and mechanical performance (photo credits: nTopology)

Quality assurance

If the 3D printable file is already optimized, the focus can instead be on the 3D printing process used, the quality of the material and the quality of the components. Today, many manufacturers have already built cameras and sensors into their machines, which can track printing and trigger an alarm or stop printing if necessary. In this step, it is important to know how the quality of the part is defined during printing so that you can define the required measurement values. It is also important to define which action should be taken by the machine at which threshold value. Today, some algorithms are already able to define these parameters independently and to deepen the model on the basis of the data already collected. What it might look like is best explained with a practical example.

EOS has partnered with NNAISENSE, a Swiss software provider, to develop a digital twin for the DMLS process. During the printing process, thermal images are captured from each printed layer using optical tomography (OT) and compared to the image predicted by AI. This allows anomalies to be detected immediately and the printing process to be stopped if necessary, resulting in material and cost savings. The model developed by NNAISENSE is a self-supervised deep learning strategy. Siemens points out that quality assurance in additive manufacturing (AM) using artificial intelligence and machine learning can reduce the time between prototype and finished part and accelerate the efficiency of high volume production. The company appreciates the integrated camera by EOS to monitor individual print layers, as it can identify in real time missing powder on parts to be printed (left) or powder drops during overlay (right).

Left: Anomaly due to a lack of powder; Right: error during coating (photo credits: Siemens)

The quality of each coating is recorded as a numerical value and evaluated automatically. When this so-called severity score reaches a certain threshold, it may indicate a serious problem with the coating (as in the example above). The company says this simplifies optical inspections, as only critical layers need to be assessed by an expert.

Other applications

AUTOMAT3D, PostProcess’ post-processing software, monitors key process factors in real time and responds autonomously to achieve the best possible finish on 3D printed parts. To do this, the company uses data from hundreds of thousands of reference parts. In addition, AI is increasingly used to automate and optimize workflows. Intelligent sensors are found in critical components, which are the measure of intelligent and preventive maintenance, or “predictive maintenance”. It is predictable that the use of machine learning for manufacturers’ production processes will continue to increase in the years to come. The global artificial intelligence and advanced machine learning market is expected to reach $ 471.39 billion by 2028 at a growth rate (CAGR) of 35.2%.

What potential do you think machine learning has for use in additive manufacturing? Let us know in a comment below or on our Linkedin, Facebook and Twitter pages! Don’t forget to sign up for our free weekly newsletter here, the latest 3D printing news straight to your inbox! You can also find all our videos on our YouTube channel.

* Cover photo credits: Siemens