Название: Smart Agents for the Industry 4.0: Enabling Machine Learning in Industrial Production Автор: Max Hoffmann
Издательство: Springer Vieweg
Год: 2019
Страниц: 345
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB
Max Hoffmann describes the realization of a framework that enables autonomous decision-making in industrial manufacturing processes by means of multi-agent systems and the OPC UA meta-modeling standard. The integration of communication patterns and SOA with grown manufacturing systems enables an upgrade of legacy environments in terms of Industry 4.0 related technologies. The added value of the derived solutions are validated through an industrial use case and verified by the development of a demonstrator that includes elements of self-optimization through Machine Learning (ML) and communication with high-level planning systems such as ERP.
Although the main focus of this work is on the information modeling of decentralized automation systems, an extension of single agents in terms of Machine Learning will be carried out. Additionally, an evaluation use-case for an emerging multi-agent system will be given in terms of a machine learning scenario.
The terms Machine Learning (ML) and Artificial Intelligence (AI) are often used synonymously. As a matter of fact, both fields of research share common ground as they are both located in the research area of computer science and are mostly used in combination. However, the area of ML should rather be characterized as a subset of AI just like the paradigms of intelligent agents are also summarized under AI methods.
The research field of ML is further distinguished into three main categories according to the literature, which are summarized under the terms unsupervised learning, reinforcement learning and supervised learning. Each of these learning techniques is fulfilled by making use of concrete algorithms or toolboxes, of whom the most important or best-known are artificial neural networks, Support Vector Machine (SVM) or clustering approaches.
An examination of machine learning techniques in the context of manufacturing shows that supervised learning methods are mostly applied in the manufacturing industry, especially “due to the data-rich but knowledge-sparse nature of the problems. Supervised ML is applied in different domains of manufacturing, monitoring, and control being a very prominent one among them”.
Скачать Smart Agents for the Industry 4.0: Enabling Machine Learning in Industrial Production