Garbowski Tomasz, Knitter-Piątkowska Anna, Grabski Jakub Krzysztof
Department of Biosystems Engineering, Poznan University of Life Sciences, Wojska Polskiego 50, 60-627 Poznań, Poland.
Institute of Structural Analysis, Poznan University of Technology, Piotrowo 5, 60-965 Poznań, Poland.
Materials (Basel). 2023 Feb 15;16(4):1631. doi: 10.3390/ma16041631.
Recently, AI has been used in industry for very precise quality control of various products or in the automation of production processes through the use of trained artificial neural networks (ANNs) which allow us to completely replace a human in often tedious work or in hard-to-reach locations. Although the search for analytical formulas is often desirable and leads to accurate descriptions of various phenomena, when the problem is very complex or when it is impossible to obtain a complete set of data, methods based on artificial intelligence perfectly complement the engineering and scientific workshop. In this article, different AI algorithms were used to build a relationship between the mechanical parameters of papers used for the production of corrugated board, its geometry and the resistance of a cardboard sample to edge crushing. There are many analytical, empirical or advanced numerical models in the literature that are used to estimate the compression resistance of cardboard across the flute. The approach presented here is not only much less demanding in terms of implementation from other models, but is as accurate and precise. In addition, the methodology and example presented in this article show the great potential of using machine learning algorithms in such practical applications.
最近，人工智能已应用于工业领域，通过使用经过训练的人工神经网络（ANN）对各种产品进行非常精确的质量控制，或实现生产过程的自动化，这使我们能够在通常枯燥乏味的工作或难以到达的地点完全取代人工。尽管寻找解析公式通常是可取的，并且能对各种现象进行准确描述，但当问题非常复杂或无法获得完整数据集时，基于人工智能的方法能完美补充工程和科学领域的工作方法。在本文中，使用了不同的人工智能算法来建立用于生产瓦楞纸板的纸张机械参数、其几何形状与纸板样品耐边压性之间的关系。文献中有许多分析、经验或先进的数值模型用于估计瓦楞纸板的抗压强度。这里提出的方法不仅在实施方面比其他模型要求低得多，而且同样准确和精确。此外，本文介绍的方法和示例展示了在这类实际应用中使用机器学习算法的巨大潜力。
