This thesis provides an especially designed overview for the needs of decision makers in the production industry on the field of machine learning. By concerning economic and technological factors, as well as the individual challenges for companies, the goal of this thesis is to serve as a guideline for the usage of machine learning in production systems.
After the revolutionary change caused by the introduction of the steam engine, the production line, electronics and IT, into the manufacturing industry, a new disrupting change is expected. Nowadays the rapidly increasing digitalization of the economy leads to the fourth industrial revolution. This global phenomenon is called ‘Industrie 4.0’ (GER) or ‘Smart Factory’ (US), and it combines production technology with information and communication technology. Especially, data based optimization in production is one of the predominant goals of Industrie 4.0. For the automatized analysis of large amounts of data, machine learning is an effective instrument and therefore a central element in Industrie 4.0.
Recent progress in machine learning has been driven by the development of new learning algorithms and by the increasing availability of data and low-cost computation power. For many applications - from computer vision to adaptive robots – it was very difficult to devise deterministic rules. However, for these applications, it is possible to collect data, and now the idea is to use algorithms that learn from data, instead of being manually programmed. Thus, machine learning has the potential to transform data into valuable knowledge for decision making, while making improvements possible to the production system, with approaches such as predictive maintenance. The transfer of machine learning from the lab to the ‘real world’ leads to an increased interest in learning techniques, demanding further effort in explaining, on how machine learning works, and what it can be used for in other disciplines.
However, the entry barrier to the diverse field of machine learning is high. With many different algorithms, theories and methods, it is hard to oversee, and therefore its influence remains limited. In addition, a recent study states that about 47% of jobs in the US are at high risk of computerization within the next decades. Therefore, employees feel insecure, and demand answers on what effect machine learning will have on their future role in the factory.
Inhaltsverzeichnis (Table of Contents)
- Introduction
- Objective
- Structure of Thesis
- Research Method and Study Design
- Impact of Machine Learning in Industrie 4.0
- Market Pull is Changing the World of Manufacturing
- Key Challenges for Production Systems in an Evolving Business World
- Industrie 4.0
- Ubiquitous Computing and Visualization
- Impact on Human Employment
- Computerisation in Non-Routine Manual Tasks
- Computerisation in Non-Routine Cognitive Tasks
- Implications for Employment
- Paradigm Shift from Abstract Models to Real World Data
- What Machine Learning is and Why it is a Promising Approach
- Machine Learning Techniques
- Regression
- Classification and Clustering
- Dimensionality reduction
- Association rule mining
- Learning Types
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- Algorithm Selection: Implicit vs. Explicit Knowledge Representation
- Applications of Machine Learning in Production
- Descriptive Analytics
- Diagnostic Analytics
- Predictive Analytics
- Prescriptive Analytics
- Guidelines for the Usage of Machine Learning in Production
- Domain Maturity: Machine Learning
- Domain Maturity: Production
- Infrastructure: Connection Task
- Data: Capturing Task
- Security: Cyber Security and Accountability Task
- People: Knowledge and Acceptance Task
- Strategy: Cooperate Design Task
Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)
This thesis aims to provide a comprehensive overview of machine learning for decision-makers in the production industry. It focuses on economic and technological factors, as well as the individual challenges faced by companies, in order to guide the implementation of machine learning into production systems.
- The impact of machine learning on production systems in Industrie 4.0
- The different techniques and types of machine learning
- The applications of machine learning in production analytics
- The challenges and guidelines for implementing machine learning in production
- The implications of machine learning for human employment in manufacturing
Zusammenfassung der Kapitel (Chapter Summaries)
Introduction: This chapter introduces the concept of Industrie 4.0 and the role of machine learning in data-driven optimization within production systems. It highlights the potential of machine learning to transform data into valuable knowledge for decision-making and improve production systems through applications like predictive maintenance. The chapter also discusses the increasing interest in machine learning and the need for further research to clarify its applicability and address concerns related to job security.
Impact of Machine Learning in Industrie 4.0: This chapter explores the impact of machine learning on the manufacturing industry. It examines the market pull towards digitization and the key challenges faced by production systems in an evolving business world. The chapter discusses the concept of Industrie 4.0 and its focus on data-based optimization, emphasizing the importance of machine learning in this context. It also analyzes the impact of ubiquitous computing and visualization, as well as the potential effects of machine learning on human employment, particularly in non-routine tasks.
Paradigm Shift from Abstract Models to Real World Data: This chapter delves into the fundamentals of machine learning. It defines machine learning and explains its potential as a promising approach to analyzing real-world data. The chapter discusses various machine learning techniques, including regression, classification, clustering, dimensionality reduction, and association rule mining. It then explores different learning types, such as supervised, unsupervised, and reinforcement learning, and the importance of algorithm selection based on explicit and implicit knowledge representation.
Applications of Machine Learning in Production: This chapter examines the various applications of machine learning in production systems. It outlines different types of analytics, including descriptive, diagnostic, predictive, and prescriptive analytics, and discusses how machine learning can be used to enhance decision-making in each of these areas.
Guidelines for the Usage of Machine Learning in Production: This chapter presents a framework for the successful implementation of machine learning in production systems. It discusses various factors that need to be considered, such as domain maturity, infrastructure, data, security, people, and strategy. The chapter provides specific guidelines for addressing these factors and navigating the challenges associated with integrating machine learning into production processes.
Schlüsselwörter (Keywords)
The key concepts and themes explored in this thesis include machine learning, Industrie 4.0, production systems, data analytics, predictive maintenance, human employment, job security, data science, manufacturing, and the challenges and opportunities associated with integrating machine learning into real-world production environments.
- Citation du texte
- Alexander Volz (Auteur), 2017, Machine Learning. A Guideline for its Usability in Production Systems, Munich, GRIN Verlag, https://www.grin.com/document/489418
