According to market observations from 3D Science Valley, 3D printing-additive manufacturing processes are surpassing traditional production techniques as additive manufacturing processes are not only more flexible, but also more economical and practical in certain applications. However, in many cases, the processing efficiency of additive manufacturing still lags behind traditional processes.
Fraunhofer is solving this problem with artificial intelligence (AI): Thanks to new software for process control, especially laser material deposition will be automatically optimized and made more efficient.
© Apollo
Artificial intelligence shines into the reality of 3D printing
According to 3D Science Valley, the advanced design and intelligent manufacturing based on additive thinking are deeply integrated with the new generation of artificial intelligence technology to form a new generation of intelligent manufacturing technology with high throughput, high product quality control capability and high product complexity, and thus become the first generation of intelligent manufacturing technology. The core technology engine of the four industrial revolutions. Wear parts like this stone crusher tooth with an outer diameter of approximately 140 mm are repaired by the LMD process. Thanks to artificial intelligence, the process of repairing irregular surfaces will be optimized.
As part of the 3+2 funding program between Germany and Canada, the AI-SLAM project is funded by the German Federal Ministry of Education and Research and the Canadian side by the NRC. The focus is on using artificial intelligence to develop new technologies for industrial production. Each project comes from real needs from all walks of life. Covering a wide range of applications; including needs from the mining and energy sectors, to the automotive industry and telecommunications, to construction and infrastructure management, the grant will run until March 2024.
© Apollo Machine and Welding Ltd, Canada.
/ artificial intelligence optimizes process parameters/ data capture + algorithm
Apollo, a machine manufacturer from Canada, supplies extraction equipment to the mining and oil industries, where the teeth of rock breakers used in the mining industry require regular maintenance. By using a Laser Material Deposition (LMD)-metal 3D printing process, metal layers can be deposited on worn parts until the original geometry is recreated.
The problem with this repair process is uneven wear of the parts, which means that layers of different thicknesses have to be applied. The operator must measure it after each coating step or at least after every ten coats and readjust the process.
In the project "AI-SLAM for Artificial Intelligence-Enhanced Adaptive Laser Additive Manufacturing", German and Canadian partners are working together to develop software for mining equipment manufacturers that can be used to automate the LMD process. For this purpose, the system automatically records the geometry during the coating process, detects deviations from the specified contour and readjusts process parameters, such as the feed rate.
Optimized control parameters are calculated with the help of artificial intelligence, which analyzes larger data sets and independently learns how to iteratively improve the process. The latest milestone in this three-year project is the commissioning of software functions for scanning components and automatic path planning at the Fraunhofer Institute for Laser Research - Fraunhofer ILT.
On the German side, the Fraunhofer Institute for Laser Technology ILT in Aachen, Germany, and software developer BCT are involved in the AI SLAM project. In Canada, the project is coordinated by the National Research Council of Canada (NRC). The focus of the project was very complex: Basically, as much process data as possible had to be collected and processed systematically. Then, from this data, artificial intelligence automatically learns how to optimize process control so that you can ultimately produce more with less effort.
Thanks to regular video conferences and jointly prepared online documents, work on the German-Canadian cooperation project runs smoothly. During the virtual lab tour, partners have become familiar with each other's software and hardware environment. For exchanging process data and implementing machine learning models, the mlOS machine learning operating system is open to all project partners.
There are several ways to use AI in manufacturing, usually starting with analyzing images or other data. AI can even recognize structures in complex data with the algorithms given by the human "teacher". As a result, it can detect deviations from a predefined optimum at an early stage, allowing adjustments to the process. The highest level is reached when the recording and processing of data is combined with process control to form an autonomous process: the intelligent adjustment of machining strategies.
There are several ways to use AI in manufacturing, usually starting with analyzing images or other data. AI can even recognize structures in complex data with the algorithms given by the human "teacher". As a result, it can detect deviations from a predefined optimum at an early stage, allowing adjustments to the process. The highest level is reached when the recording and processing of data is combined with process control to form an autonomous process: the intelligent adjustment of machining strategies.
In terms of 3D printing, according to the 3D Science Valley, the Fraunhofer ILT is currently able to significantly improve the results of metal 3D printing through AI. In a laser powder bed selective metal melting (LPBF) process system, the component surface in each layer is photographed using a high-resolution HDR camera. The image data can capture two effects: on the one hand, the possible warping of the component during the process can be measured; on the other hand, the roughness of the surface can be scrutinized. Thus, defects can be classified during production.
Of course, Fraunhofer's research will not stop at the adaptation of a single device. According to 3D Science Valley, in early 2020, Fraunhofer IPT Fraunhofer Institute for Production Technology IPT and Swedish mobile network provider Ericsson jointly developed 5G sensors monitoring and controlling highly complex manufacturing processes, mobile robots, logistics and multi-site production chains, distributed manufacturing control, blockchain, artificial intelligence and edge cloud computing, etc. The way the future has come is presented to us.
"Dark Knowledge" said that it can be perceived, and in the near future, the next step of artificial intelligence will span a single 3D printing device to achieve coordination and process optimization between devices. If the algorithm is the design of the engine, then the computing power is the horsepower of the engine, and the data is the fuel of the engine. © 3D Science Valley White Paper
With the help of artificial intelligence, laser parameters can also be specifically changed during the process in order to dynamically react to changes in the process state. This improves the quality of the part and prevents defects before they occur. AI not only enables users to optimize production processes and achieve zero-defect production. In processes with large amounts of complex data, such as the development of modern optics, artificial intelligence also reduces complexity. The development process becomes clearer, more certain and less dependent on the intuition of individual experts.
In terms of commercialization, process monitoring systems with integrated AI will support this transition and enable a straightforward approach to evolve from full-detail testing to intelligent testing, according to 3D Science Valley's market understanding. According to the market observation of 3D Science Valley, the international commercial software companies that use AI to control the quality of additive manufacturing processing currently include printsyst in Israel, addiguru in the United States, nebumind in Germany, and Nnaisense in Switzerland.
Looking back at additive manufacturing, the development trend of additive manufacturing is like TV. From the original black and white, even the human figure can be seen silently in a small "box", then to color TV, to the current ultra-thin and large-screen digital TV, The feeling of being reborn in its development makes it impossible to freeze this technology in what TV once looked like.
Here, software plays an important role... The young 3D printing industry is looking forward to a fully automated factory that produces not just one product, but hundreds, or even thousands, of digital serial manufacturing patterns.
Software Makes 3D Printing Faster, Smarter, More Efficient…
Algorithm-based software is empowering the whole world. 3D Science Valley believes that soon the 3D printing industry will find that some people in the best team of a 3D printing company are proficient in algorithms, or can write code or be good at using software, otherwise such a company will become impossible.
Knowing as deep as you can, you can go far. 3D Science Valley provides the industry with an in-depth observation of additive and intelligent manufacturing from a global perspective. For more cutting-edge sharing of 3D printing in the field of additive manufacturing, please continue to pay attention to the Valley Frontier series of 3D Science Valley .
About Manly
More than 12 years of experience in producing lithium battery cells and battery packs for various
applications. Welcome to send your requiry to info@manlybattery.com
