Reducing Waste in 3D Printing Using a Neural Network Based on an Own Elbow Exoskeleton

Abstract

Traditional rehabilitation systems are evolving into advanced systems that enhance and improve rehabilitation techniques and physical exercise. The reliable assessment and robotic support of the upper limb joints provided by the presented elbow exoskeleton are important clinical goals in early rehabilitation after stroke and other neurological disorders. This allows for not only the support of activities of daily living, but also prevention of the progression neuromuscular pathology through proactive physiotherapy toward functional recovery. The prices of plastics are rising very quickly, as is their consumption, so it makes sense to optimize three dimensional (3D) printing procedures through, for example, improved artificial intelligence-based (AI-based) design or injection simulation, which reduces the use of filament, saves material, reduces waste, and reduces environmental impact. The time and cost savings will not reduce the high quality of the products and can provide a competitive advantage, especially in the case of thinly designed mass products. AI-based optimization allows for one free print after every 6.67 prints (i.e., from materials that were previously wasted).

Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons

“…The MDR directive regulates the manufacture and distribution of medical devices in Europe. Compliance with the MDR is mandatory for medical device companies wishing to sell their products on the European market and ensures that the medical device is safe, of good quality, meets the essential requirements for EU medical devices, and is CE-marked [28]. ISO 13485:2016 specifies the quality management system requirements for organizations providing medical devices and related services.…”

“…AI-based optimization improved the speed of calculations and print quality and allowed researchers to identify a set of print parameters not previously considered [26,27]. It is possible to reduce filament consumption by up to 13.04% by reducing the amount of waste and thus reducing the environmental impact [28].…”

Artificial intelligence in the design and production of personalized 3D printed products – conclusions from the project “Things are for People”

“…Oszczędność czasu i kosztów nie powoduje utraty wysokiej jakości produktów i może stanowić przewagę konkurencyjną, zwłaszcza w przypadku cienko zaprojektowanych produktów masowych. Optymalizacja oparta na AI pozwala na uzyskanie jednego darmowego wydruku po każdych 6,67 wydrukach (czyli z materiałów, które wcześniej były marnowane) [7].…”

AI-Based Support System for Monitoring the Quality of a Product within Industry 4.0 Paradigm

“…In a broader context, this allows not only material optimization [ 6 ], but also cost, time efficiency, and product quality optimization [ 7 ]. In times characterized by an energy crisis, increases in raw material prices, and the simultaneous need for sustainable development, intelligent training optimization, including data-driven approaches (such as machine learning—ML), becomes of particular importance, both economically and socially [ 8 ].…”