Lesson 1: Advanced manufacturing: Artificial Intelligence & Machine Learning

Welcome to Lesson 1. Here you will learn some of the key technologies of the 4th industrial revolution: Artificial Intelligence & Machine Learning.

Before we start, you virtual assistant has something to say about the course structure and page layout. Therefore, scan the QR code here and… have fun!

Artificial Intelligence (AI) is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals.

AI is a branch of computer science that aims to create intelligent machines, and nowadays it has become an essential part of the technology industry.

The core problems of artificial intelligence include programming computers for certain traits such as:

Everyone has certainly experienced AI at least once in his or her life, few examples are:

  • Siri

    Siri is the virtual assistant part of Apple Inc.'s iOS, watchOS, macOS, HomePod, and tvOS operating systems. The assistant uses voice queries and a natural-language user interface to answer questions, make recommendations, and perform actions by delegating requests to a set of Internet services.

  • Cortana

    Cortana is a virtual assistant created by Microsoft for Windows 10, Windows 10 Mobile, Windows Phone 8.1. Invoke smart speaker, Microsoft Band, Surface Headphones, Xbox One, iOS, Android, Windows Mixed Reality, and Amazon Alexa. Cortana can set reminders, recognize natural voice without the requirement for keyboard input, and answer questions using information from the Bing search engine.

  • Computer chess

    Computer chess is a game of computer architecture encompassing hardware and software capable of playing chess autonomously without human guidance. Computer chess acts as solo entertainment (allowing players to practice and to better themselves when no sufficiently strong human opponents are available), as aids to chess analysis, for computer chess competitions, and as research to provide insights into human cognition. Current chess engines are able to defeat even the strongest human players under normal conditions. Nevertheless it is considered unlikely that computers could ever solve chess due to its high level of complexity. (1)

  • Google Translate

    Google Translate uses Google Neural Machine Translation (GNMT), a neural machine translation (NMT) system developed by Google and introduced in November 2016, that uses an artificial neural network to increase fluency and accuracy in Google Translate

In Figure 1 you can see the exponential growth in computing power. It predicts that in 2045 AI power will be equivalent to that of all human brains combined:

The accelerating pace of change and exponential growth in computing power
Figure 1: The accelerating pace of change and exponential growth in computing power. Source: Grossman L, 2045: The year man becomes immortal, Time Magazine, February 10, 2011

In his book “The Goal is Industry 4.0: Technologies and Trends of the Fourth Industrial Revolution” (02), Fran Yáñez emphasizes that to have Artificial Intelligence, Big Data from the Internet of Things (IoT) are required, and algorithms that allow the machines to identify patterns of behavior, decision making, even anticipate our needs and learn autonomously are required.

The Machine Learning concept has been the latest impulse to Artificial Intelligence. Using the right tools and processes, a machine can now learn better, faster and more reliably than a person starting from the same data.

Currently, the most commonly used learning method is image recognition. Other uses include digital assistants (like Siri and Cortana), face recognition (e.g. digital security), speech recognition and speech processing (e.g. Whatsapp and Navigation Systems), automated translation and transcription (like Google Translate), and autonomous driving.

In a Smart Factory context, autonomous driving can be translated into utilization of Automated Guided Vehicles (AGVs). Production processes and machines communicate each others by Cyber Physical Systems (CPS). Big Data supports process optimization by using image analysis and image recognition, for example.

In production facilities, intelligent systems identify objects on conveyor belts and are able to automatically sort them. These types of systems are also used in quality control: they recognize product flaws, such as whether it is the wrong color.

In continuous improvement, the huge amount of data can be used to be continuously analyzed to indentify root causes in real time providing instant reaction time to eventually adapt the process. In principle, statistical analysis currently performed manually by using Six Sigma technologies can be fully automated.

Companies today use machine learning in maintenance and support services. By means of sensors, artificial intelligence helps capture the energy consumption of individual machines, analyze maintenance cycles, and then optimize them in the following stage. Operating data indicates when a part must be replaced or where there is likely to be a defect. As the amount of data increases, the system becomes better at optimizing itself and making more accurate predictions.

To conclude, AI is the basis of robots. In the future, human physical activities may be fully substituted by antropomorphic robots. Just to understand the current level achieved, have a look at the following video from BostonDynamics:


02. Yáñez F, The Goal is Industry 4.0: Technologies and Trends of the Fourth Industrial Revolution, Amazon Digital Services, 2017

Notify of
Inline Feedbacks
View all comments
Would love your thoughts, please comment.x