![]() |
Educational guide | |||||||||||||||||||||||||||||||||||||||
IDENTIFYING DATA | 2024_25 | |||||||||||||||||||||||||||||||||||||||
Subject | INTELLIGENT SYSTEMS IN INDUSTRY | Code | 01744004 | |||||||||||||||||||||||||||||||||||||
Study programme |
|
|||||||||||||||||||||||||||||||||||||||
Descriptors | Credit. | Type | Year | Period | ||||||||||||||||||||||||||||||||||||
3 | Compulsory | First | First |
|||||||||||||||||||||||||||||||||||||
Language |
|
|||||||||||||||||||||||||||||||||||||||
Prerequisites | ||||||||||||||||||||||||||||||||||||||||
Department | ING.ELECTR.DE SIST. Y AUTOMATI |
|||||||||||||||||||||||||||||||||||||||
Coordinador |
|
vgonc@unileon.es arods@unileon.es |
||||||||||||||||||||||||||||||||||||||
Lecturers |
|
|||||||||||||||||||||||||||||||||||||||
Web | http:// | |||||||||||||||||||||||||||||||||||||||
General description | The course introduces the student to the current use being made of artificial intelligence in the industry to create intelligent systems that contribute to the development of Industry 4.0. Initially, some of the fundamental concepts and methods of artificial intelligence are introduced and revised, focusing on those techniques that have a greater application in the industry. Later, some of the main techniques used in the creation of intelligent systems are presented, such as rule systems, probabilistic methods and deep learning. Finally, the main use cases in different types of industry are explained, presenting examples of successful applications and providing criteria for using artificial intelligence in real applications. The theoretical part is complemented by various practices carried out using the Python language, where the student will be able to see the application of some of the methods explained in theory to solve industrial problems. | |||||||||||||||||||||||||||||||||||||||
Tribunales de Revisión |
|
|||||||||||||||||||||||||||||||||||||||
Competencies |
Type A | Code | Competences Specific |
A18640 | ||
A18641 | ||
Type B | Code | Competences Transversal |
B5708 | ||
B5711 | ||
B5712 | ||
B5715 | ||
B5716 | ||
Type C | Code | Competences Nuclear |
C1 | ||
C3 |
Learning aims |
Competences | |||
The student will acquire theoretical knowledge about methods based on machine learning, will be able to explain their foundations and will know how to apply them in an industrial process. The student will also be able to develop simple intelligent systems using a high-level programming language and will understand the different stages involved in developing an intelligent system that is applied to an industrial problem. | A18640 A18641 |
B5708 B5711 B5712 B5715 B5716 |
C1 C3 |
Contents |
Topic | Sub-topic |
Block I: INTRODUCTION TO INTELLIGENT SYSTEMS | Lesson 1: INTRODUCTION TO ARTIFICIAL INTELLIGENCE Fundamentals of AI, smart agents, basic methods, state and search spaces, knowledge representation and reasoning. Lesson 2: UNCERTAINTY AND ARTIFICIAL INTELLIGENCE Representation of uncertainty, probability, fuzzy sets, belief functions, Markov models, Kalman filters. Lesson 3: MACHINE LEARNING Introduction to machine learning. Supervised learning. Models for learning: decision trees, linear models, neural networks, support vector machines. Unsupervised learning. Lesson 4: ARTIFICIAL VISION AND NATURAL LANGUAGE PROCESSING Introduction and basic concepts of Machine Vision. Example of a task in VA: Image Classification. Definition, main stages and algorithms used. Natural language processing, concept Example of a task in NLP: Text Classification. Definition, main stages and algorithms used. |
Block II: INTELLIGENT SYSTEMS AND THEIR APPLICATIONS IN INDUSTRIAL PROCESSES | Lesson 1: RULES-BASED AND INTELLIGENT CONTROL SYSTEMS Classic rule systems, forward and backward search, fuzzy rule systems and intelligent control Lesson 2: PROBABILISTIC METHODS Statistical learning, Probabilistic graphical methods Topic 3: NEURAL NETWORKS AND DEEP LEARNING Basic models of neural networks, deep learning in neural networks, CNNs, autoencoders. |
Block III: USE CASES IN DIFFERENT TYPES OF INDUSTRY AND THEIR RELATION TO METHODS BASED ON ARTIFICIAL INTELLIGENCE | Lesson 1: INTELLIGENT SYSTEMS IN INDUSTRY Criteria and main areas of application of intelligent systems in the industry Lesson 2: APPLICATIONS Examples of successful applications of intelligent systems in the industry. |
Block IV: DEVELOPMENT OF APPLICATIONS BASED ON MACHINE LEARNING FOR THE SMART INDUSTRY | Lab 1: INTRODUCTION TO PYTHON Installation and configuration of a programming environment with Python language. Top python libraries for machine learning Labs 2, 3, 4: TROUBLESHOOTING IN INDUSTRIAL APPLICATIONS Guided implementation of technical applications of NLP, CV and Machine Learning to solve real problems in the industry. |
Planning |
Methodologies :: Tests | |||||||||
Class hours | Hours outside the classroom | Total hours | |||||||
Practicals using information and communication technologies (ICTs) in computer rooms | 8 | 20 | 28 | ||||||
Lecture | 15 | 21 | 36 | ||||||
Mixed tests | 1 | 10 | 11 | ||||||
(*)The information in the planning table is for guidance only and does not take into account the heterogeneity of the students. |
Methodologies |
Description | |
Practicals using information and communication technologies (ICTs) in computer rooms | Use of free software, Python, to carry out guided practices that will allow the student to make small applications that help solving problems in the industry, applying artificial intelligence techniques. |
Lecture | Theoretical presentations in the classroom, containing examples with use cases, applications and exercises. |
Personalized attention |
|
|
Assessment |
Description | Qualification | ||
Lecture | Written exams to assess the assimilation of the concepts taught. | 35% | |
Practicals using information and communication technologies (ICTs) in computer rooms | They will be evaluated through deliveries made by students | 30% | |
Others | Other activities that will allow continuous assessment of the content taught. | 35% | |
Other comments and second call | |||
In the second call, the criteria applied will be the same followed in the first one. |
Sources of information |
Access to Recommended Bibliography in the Catalog ULE |
Basic | |
Christopher M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer; Edición: 1st ed. 2006. Corr. 2nd printing 2011. Richard Duda & Peter Hart. Pattern Classidication. A. Wiley-Interscience. 2000. Richard Szeliski. Computer Vision: Algorithms and Applications. Springer. 2010. G. Cheng, L. Liu, X. Qiang and Y. Liu, "Industry 4.0 Development and Application of Intelligent Manufacturing," 2016 International Conference on Information System and Artificial Intelligence (ISAI), Hong Kong, 2016, pp. 407-410, doi: 10.1109/ISAI.2016.0092. Dufek, D., Ignas, T. & Strandberg, F. (2019). Sistemas Inteligentes en la Industria 4.0. Revista Antioqueña de las Ciencias Computacionales y la Ingeniería de Software (RACCIS), 9(2), 43-48. Ray Y. Zhong, Xun Xu, Eberhard Klotz, Stephen T. Newman, Intelligent Manufacturing in the Context of Industry 4.0: A Review, Engineering, Volume 3, Issue 5, 2017, Pages 616-630.
Jay Lee, Hossein Davari, Jaskaran Singh, Vibhor Pandhare. Industrial Artificial Intelligence for industry 4.0-based manufacturing systems, Manufacturing Letters. Volume 18. 2018. Pages 20-23.
Alex Castrounis. AI for People and Business: A Framework for Better Human Experiences and Business Success. O'Reilly Media. 2019 Andrew Park. Machine Learning: This Book Includes: Python Machine Learning and Data Science. A Comprehensive Guide for Beginners to Master Deep Learning, Artificial Intelligence and Data Science with Python. Independently published. 2020. |
|
Complementary | |
Recommendations |