AI in paint process - Manfred Schwartz - E-Book

AI in paint process E-Book

Manfred Schwartz

0,0

Beschreibung

This work is intended to arouse interest in the use of artificial intelligence (AI) when coating components. The first chapter is introducing the concept of the book, while chapter two deals with the current state of the art in the field of painting. The third chapter discusses what is AI in all possible variations and applications as well as research. The fourth chapter then lists examples of the use of AI in the painting process. It will turn out that our paintwork will be significantly improved, more cost-effective and more ecological using AI. Finally, Chapter 5 of this work addresses the consequences and effects of using artificial intelligence in the painting process.

Sie lesen das E-Book in den Legimi-Apps auf:

Android
iOS
von Legimi
zertifizierten E-Readern
Kindle™-E-Readern
(für ausgewählte Pakete)

Seitenzahl: 98

Das E-Book (TTS) können Sie hören im Abo „Legimi Premium” in Legimi-Apps auf:

Android
iOS
Bewertungen
0,0
0
0
0
0
0
Mehr Informationen
Mehr Informationen
Legimi prüft nicht, ob Rezensionen von Nutzern stammen, die den betreffenden Titel tatsächlich gekauft oder gelesen/gehört haben. Wir entfernen aber gefälschte Rezensionen.



Table of Contents

Chapter 1 Introduction

Chapter 2 Painting process

2.1 Storage

2.2 Pre-treatment

2.3 Layer one

2.4 Layer two

2.5 Layer three

2.6 Removal of the painted parts

Chapter 3 AI

3.1 General information

3.1.1 Origin of the term and attempts at definition

3.1.2. Strong and weak AI

3.1. 3 Fields of research

3.2 Sub-areas

3.2.1 Knowledge-based systems

3.2.2 Pattern analysis and pattern recognition

3.2.3 Pattern prediction

3.2.4 Robotics

3.2.5 Artificial life

3.2.6 AI-Alignment

3.3 Methods

3.4 Applications

3.4.1. AI in the jurisprudence

3.4.2. AI in killing machines and weapons of war

3.4.3. AI in Marketing

3.4.4. AI in computer and board games

3.4.5. AI to generate images and works of art

3.4.6. AI for producing product design

3.4.7. AI in higher education

3.4.8. AI in climate protection

3.4.9. AI in the world of work

3.4.10 AI in logistics and transport

3.4.11 AI in tax advice

3.5. Turing-Test

3.6. Technological singularity

3.7. Consciousness in artificial intelligence

3.8. Related sciences

3.8.1. Linguistics

3.8.2. Psychology

3.8.3. Psychotherapy

3.8.4. Philosophy

3.8.5. Human rights

3.8.6. Computer Science

3.9 Criticism of AI research

3.9.1. Suggestions for dealing with AI

3.9.2. Spread of AI in Germany

3.9.3. The AI Observatory

3.10.1. European Union

3.10.2. United States

3.11. Representation in film, video games and literature

3.12. Social Impact

3.13. Summary

3.14. References

3.15. Weblinks

Chapiter 4 AI in the paint process

4.1. Raw parts

4.2. Pre-treatment

4.2.1. Cleaning

4.2.2. Activation

4.2.3. Layer one

4.2.4. Layer two

4.2.5 Layer three

4.2.6 Removal of painted parts

4.7 Literature

Chapter 5 Consequences and effects

5.1 Literature

Chapter 1 Introduction

This book aims to provide suggestions on how the painting process of components can be made more efficient, cost-effective and ecological using artificial intelligence (AI).

To this end, a typical industrial painting process is first broken down into its individual steps (Chapter 2). The different variants at the level of the process steps are not yet considered. The more detailed discussion including AI will be found in Chapter 4.

Once the basis for the structure of the painting process has been created, Chapter 3 discusses what artificial intelligence is. A wide range of approaches for various possible applications are shown, as well as certain negative aspects of the use of artificial intelligence.

Chapter 4 then shows where and how the use of artificial intelligence brings benefits at the level of each process step in the paint shop.

Last but not the least, Chapter 5 deals with the consequences and effects of using artificial intelligence in the painting process.

Chapter 2 Painting process

The typical painting process is generally divided into various sub-steps. These are now described in terms of their sequence. At this level, only the principles of the painting process are listed in this chapter so that a basis can be created and all readers have the same starting point.

The painting process presented here is carried out in a more or less automated industrial plant.

2.1 Storage

The raw parts should be stored correctly and cleanly and supplied promptly to the painting process. If the raw parts are stored for too long, the surface can be adversely affected by contamination or the sweating out of moving molecules.

2.2 Pre-treatment

Be that as it may, the raw parts must undergo pre-treatment.

As a rule, the first pre-treatment step involves cleaning the component surface.

Cleaning media are generally used for this whether wet-chemical or dry.

After cleaning, depending on the surface polarity of the component, a further pre-treatment, activation, must be carried out. This involves a balancing act between sufficient activation and avoiding too much activation.

2.3 Layer one

After cleaning and, if necessary, activation, the first layer is applied on the component. Depending on the application and objective, this first layer is referred to as a filler, primer or undercoat. The task of this first layer is to create a good bond to the component surface, to conceal any defects in the unfinished part and to enable the bonding of further coatings.

2.4 Layer two

After the first coat has passed a flash off zone and is dried by introducing energy, a second coat is usually applied to the first coat in a timely manner. The task of this second layer is to create a good bond with the first layer, to introduce a design function and to enable the bonding of further coatings.

2.5 Layer three

After the second coat has passed a flash off zone and is dried by introducing energy, a third coat is usually applied to the second coat in a timely manner. The task of this third layer is to create a good bond with the second layer, to introduce a protective function and to finalise the coating.

The third layer passes a flash off zone and is dried by introducing energy.

2.6 Removal of the painted parts

After the last layer has been dried, the painted component can be removed (from the skids) and quality assurance can be carried out, for example with layer thickness and colour measurement.

In this chapter, only the process of painting components will be outlined more or less schematically so that the various stages are clearly delineated. This subdivision supports the further discussion of how AI can be utilised in the painting process. Now that the process in an industrial paint shop has been outlined, we need to go into more detail: what is AI?

Chapter 3 AI

The process in a typical paint shop was roughly defined in Chapter 2. The question now is: what is artificial intelligence (AI) and how can we use it in a paint shop? Since AI is already in use, even though it is actually a novelty, the following discussion should not be limited to painting. The most important findings of this chapter are brought together in Chapter 4 in the connection between the painting process and AI. So now to the question: What is artificial intelligence?

Artificial intelligence Artificial intelligence (AI) is a branch of computer science that deals with the automation of intelligent behaviour and machine learning. The term is difficult to define, as there is already a lack of a precise definition of "intelligence". Nevertheless, it is used in research and development.

One attempt to define "intelligence" is that it is the quality that enables a being to act appropriately and with foresight in its environment; this includes the ability to perceive environmental data, i.e. to have sensory impressions and respond to them. This includes the ability to perceive and react to sensory impressions, to absorb and process information and store it as knowledge, to understand and produce language, to solve problems and achieve goals.

Practical AI successes are quickly integrated into the areas of application and then no longer count as AI. Because of this so-called "AI effect" [1], AI research only seems to struggle with hard nuts that it cannot crack, which is also expressed by Tesler's "theorem": "Intelligence is what machines have not yet done".

3.1 General information

The understanding of the term artificial intelligence (AI) reflects the materialistic concept of "man as a machine" from the Enlightenment. L'Homme-Machine is the title of the relevant "blasphemous work" by the Radical Enlightenment philosopher La Mettrie from 1748. This is precisely the goal of so-called strong AI. It wants to create an intelligence that mechanically imitates human thinking [2]. It wants to construct a machine that reacts intelligently and behaves like a human being.

After decades of research, the goals of strong AI are still visionary.

3.1.1 Origin of the term and attempts at definition

The term artificial intelligence was coined in 1955 by the US computer scientist John McCarthy as part of a funding application for a research project [3, 4].

There are numerous definitions of the term AI. Depending on the point of view, artificial intelligence is defined in industry, research and politics either by the applications to be achieved or by looking at the scientific foundations:

"Artificial intelligence is the property of an IT system to exhibit "human-like", intelligent behaviour." - Bitkom e. v. and German research centre for artificial intelligence [5].

"Artificial intelligence [...] is a branch of computer science that deals with research into the mechanisms of intelligent human behaviour [...]." - Spektrum der Wissenschaft, Lexikon der Neurowissenschaften [4]. "By artificial intelligence (AI), we mean technologies that complement and strengthen human abilities in seeing, hearing, analysing, deciding and acting." - Microsoft Corp. [6].

"Artificial intelligence is the ability of a machine to mimic human abilities such as reasoning, learning, planning and creativity." - European parliament (website) [7].

3.1.2. Strong and weak AI

Strong AI would be cognitive systems that can take on the work of completing difficult tasks on an equal footing with humans. In contrast, weak AI is about mastering specific application problems. The aim here is to support human thinking and technical applications in individual areas [2]. The ability to learn is a key requirement for AI systems and must be an integral component that is not added as an afterthought. A second main criterion is the ability of an AI system to deal with uncertainties and probabilities (as well as probabilistic information) [8]. In particular, those applications are of interest for whose solution a form of "intelligence" seems to be necessary according to general understanding. Ultimately, weak AI is therefore concerned with simulating intelligent behaviour using mathematics and computer science; it is not concerned with creating awareness or a deeper understanding of intelligence. While the creation of strong AI has failed to date due to the philosophical issues involved, significant progress has been made on the weak AI side in recent years.

A strong AI system need not have much in common with humans. It will probably have a different cognitive architecture and its developmental stages will not be comparable to the evolutionary cognitive stages of human thought (evolution of thought). Above all, it cannot be assumed that an artificial intelligence possesses feelings such as love, hate, fear or joy [9].

3.1. 3 Fields of research

In addition to the research results of core informatics itself, research into AI has also incorporated results from psychology, neurology and neuroscience, mathematics and logic, communication science, philosophy and linguistics. Conversely, AI research has also influenced other fields, especially neuroscience. This can be seen in the development of the field of neuroinformatics, which is assigned to biology-orientated computer science, and computational neuroscience.

Artificial neural networks are techniques that have been developed since the middle of the 20th century and are based on neurophysiology.

AI is therefore not a closed field of research. Rather, techniques from different disciplines are used without necessarily being connected to each other.

One important conference is the International Joint Conference on Artificial Intelligence (IJCAI), which has been held since 1969.

Since the term was coined in 1955, several relatively independent sub-disciplines have emerged:

Pattern recognition, which includes speech recognition and handwriting recognition.

Knowledge modelling, including logic programming and inference

engines.

Expert systems, question-answer systems and chatbots.

Machine learning.

Artificial neural networks and deep learning.

Computer vision.

Robotics; and

Universal game programmes.

There are close links to the research field of artificial life. The long-term goal of AI is the ability of an intelligent agent, known as strong AI or artificial general intelligence, to understand or learn any intellectual task that a human or other living being can perform.

3.2 Sub-areas

3.2.1 Knowledge-based systems