Topics & Schedule

The schedule is a guide and subject to change. Optional courses and hand-on tutorials especially may be adapted to meet more closely the needs of participants.

The course is expected to require a total time investment of 5-10h / week, roughly split into

1h lecture - video material
1h reading (optional)
2h workshop tutorials
1h Q&A sessions (optional)
1-2h individual project work

The course features

Synchronous and asynchronous video lectures.
Reading materials in the form of text book chapters and (easy to understand) scientific papers, associated with topics and lectures.
Questions about topics will be discussed in general Q&A sessions, once a week.
2h live workshop tutorials are provided for
- design and critiquing exercises, as well as
- for a selection of free, open source and commercial data analytics tools, to demonstrate the range of features available, skills required and user support, for deriving insight into data through exploration and analysis. While not compulsory, participants are encouraged to take full advantage of these sessions to engage in discussions with peers and invited subject matter and domain experts, and to obtain direct feedback on assignments.
Drop-in support to help with briefs, create a design to meet the requirements identified, and, within the constraints of the course, build a data-driven solution.
Complementary teaching material in the form of videos and websites will be provided to participants throughout the course.
At least once every 2 to 3 weeks we will host a 1h live seminar by a guest speaker from academia or industry illustrating application of data science in a variety of fields and the benefits this brings to creating value and gaining a competitive edge and other manufacturing related insights.
A dedicated Slack/Teams channel will support networking and discussions.

Course Structure

The course will deliver all topics via a common platform established by introducing students to the fundamentals of using the Python programming language within Jupyter Notebooks and concepts of software version control with Git and Github. Each topics will be taught via Python libraries whose functionality will enable students to explore their application using high-level commands and a number of curated datasets.

The course is developed to facilitate hybrid teaching and is comprised of a series of lectures, tutorials/workshop sessions that will encourage student-centred learning. The lectures will introduce and demonstrate concepts and tools that will provide a starting point for workshop exercises that will provide hands-on experience of both the challenges and capabilities of modern digital technologies.

The course will employ case study materials, video resources, and industrial guest speakers to emphasis the industrial relevance of the techniques. Although the focus is on manufacturing, the course will also touch on the philosophies of Product Lifecycle Management and Product Data Management and examines the interactions between information technologies, organisation and product data. It aims to equip participants with the skills to use data science to uncover insight, support informed decision-making and the creation of value from data.

Week 1: Introduction and Foundations

Introduction and Foundations: In the first lecture will explain how the course will work, give a brief overview of Data Science and its application to manufacturing. In the workshop, you will be introduced to: Key data science concepts, Python programming with Jupyter Notebooks, Version control with GIT

Week 2: Data carpentry

Data carpentry: In this lecture you will be introduced to the concepts and tools of data carpentry. In the workshop we will discuss and practice with data cleansing and data carpentry.

Week 3: Product Lifecycle / Material flow

Product Lifecycle / Material flow: This lecture will discuss data associated with product lifecycle and material flows in manufacturing plants. The need for manufacturing engineers to develop coding skills will be demonstrated using industrial case studies. In the workshop we will discuss and practice with Python on Jupyter notebooks and Github.

Week 4: Data visualisation and Exploratory Data Analysis

Data visualisation and Exploratory Data Analysis: This lecture overviews and introduces data visualisation formats and techniques and how to perform exploratory data analysis. In the workshop we will discuss and practice with data visualisation exploratory data analysis.

Week 5: Current Manufacturing Software / PLM / ERP /MES

Current Manufacturing Software / PLM / ERP /MES: This lecture overviews and introduces current manufacturing software / PLM / ERP /MES. In the workshop we will discuss and practice with data representation and relational databases.

Week 6: Guest lecture: Data Ethics

This week is featuring no taught content but gives you time to work on your project. We will take a breather from taught lecture material and focus on project 1-on-1s, where we will go through projects with participants. These sessions will allow participants to discuss their ideas and work to this point with one of the organisers, and to receive interim feedback.

Week 7: Machine Learning and Artificial Intelligence (ML/AI)

Machine Learning and Artificial Intelligence (ML/AI): This lecture overviews and introduces machine learning and artificial intelligence in the context of manufacturing. In the workshop we will discuss and practice with Jupyter Notebooks and supervised machine learning approaches.

Week 8: Asset Management / internet of things (IoT)

Asset Management / internet of things (IoT): This lecture overviews and introduces asset management and internet of things. In the workshop you will practice and unsupervised machine learning approaches.

Week 9: EBoM / MBoM / Geometry / Time Series

EBoM / MBoM / Geometry / Time Series: This lecture overviews and introduces data representation / EBoM / MBoM / Geometry / Time Series The workshop we will discuss and practice with data representation and relational databases with us and the peers.

Week 10: Guest lecture: Data for Industry 4 / New Business Models/Digital Twin / Thread

This week is featuring no taught content but gives you time to work on your project. We will also host a guest lecture on one of the themes of Data for Industry 4 / New Business Models / Digital Twin. In the workshop we will discuss and practice with presenting information with us and the peers. This session will allow participants to discuss their ideas and work with one of the organisers, and to receive interim feedback.

Week 11: Assessment

Assessment: Submitting your final project. [link to course catalogue entry on DPRS]

Guest Talks

We will host a variety of guest talks across diverse areas including: