Content

1. Definition of / introduction to digital twins

• 1.1 Introduction: History of digital twins (DT) – what are DT
• 1.2 Definition of the architectural components of a digital twin:
  • 1.2.1 The virtual system
  • 1.2.2 The physical system
  • 1.2.3 Data streams and sensors
  • 1.2.4 The data management part: keeping consistency between real and virtual twin
  • 1.2.5 The interface with the human
  • 1.2.6 How to build up a DT – how to select the appropriate building blocks
• 1.3 What is the added value of a DT for a given application and use case
  • 1.3.1 Automatic interaction with the real asset in e.g. direct control
  • 1.3.2 Interaction via a Human operator/design getting information from the DT
• 1.4 Industrially relevant Use Cases presentation – ideally covering machine, factory and operations

2. Building blocks of a digital twin

• 2.1 The virtual system
  • 2.1.1 Overview of modelling techniques, i.e., white/grey/black box modelling, multi-body, CAD, multi-physics, surrogate models (e.g. stochastic approaches (PCE, Kriging, ...), kinematics/dynamics, ...
  • 2.1.2 How to integrate/couple selected (sub)-models in a simulation environment? Definition of proper inputs, outputs & internal data-streams for the different sub-models that constitute the DM. – incl. model nesting
  • 2.1.3 Notions of MOR
• 2.2 The physical system – capturing data from the real asset
  • 2.2.1 Sensor selection and positioning
  • 2.2.2 Signal processing
  • 2.2.3 Communication and IT architecture
  • 2.2.4 Data quality, data quality propagation
  • 2.2.5 Limitations and difficulties in an industrial practice
  • 2.2.6 Basic notions on Cybersecurity – relation to edge/cloud
• 2.3 Coupling real and virtual assets together – creating the Digital Twin
  • 2.3.1 How to couple the digital model to real time sensor data – estimation, filtering, real-time/online/offline, time-stepping
  • 2.3.2 Where to allocate which computing power (edge, cloud) – including basic notions on execution platforms, co-simulation, etc.
  • 2.3.3 Concepts of observability and sensor location optimization
  • 2.3.4 Parameter identification/updating
  • 2.3.5 Data analytics
• 2.4 How to validate and use a digital twin
  • 2.4.1 Validation of twins for correct operation
  • 2.4.2 Validation of twins in fault conditions link to failure mode lectures in Monitoring & Prognostics
  • 2.4.3 Robustness of DT:
    • - How to deal with missing data? Impact on reliability?
    • - Forward UQ (sampling, reliability methods)
    • - Inverse UQ (PI, ML) - getting the required information
  • 2.4.4 Illustrative (academic) Use Cases

3. Creating added value with the digital twin – selected use case presentations

A well identified selection of illustrative use cases with clear links to Module 2 building blocks making sure different technologies are highlighted.

Possible scenarios to be considered: Digital Twins for

• sensing
• control
• monitoring
• decision making
• maintenance support
• business
• operator/designer/human support
• for those application cases where the DT interacts via a Human with the real asset: DT interfacing (dashboarding, AR, …): how to visualize/interact with the operator/designer/human?
• …

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Content

What are “operations management strategies”?

Operations Management Strategies are defined, and their components and drivers, … in a contemporary business context, are described.

• Operations management strategies: Link with business strategy. Operations Management decision making: strategic, tactical & operational level
• Business context: impact of external (products, processes, customers, …) and internal (level of “smart” maturity, change management & organizational culture, … ) content. Organization structure: centralized, decentralized, hybrid, outsourcing?
• Link between maintenance and production strategies, asset management: ISO 55000, product service systems (PSS)
• Special attention is given to existing new and emergent technologies and their potential value for strategy support.

Maintenance

In order to fully understand the opportunities and challenges of smart maintenance strategies, first, a discussion of different types of maintenance intervention is made, followed by an introduction to maintenance strategy development concepts.

• Types of maintenance interventions: reactive, preventive, predictive, prognostic, prescriptive, opportunistic, design-out (proactive), ... : definitions, supporting technology, examples, critical reflection
• Strategies: life cycle costing/total cost of ownership considerations (LCC/TCO), total productive maintenance (TPM), FMEA/FMECA, reliability-centered maintenance (RCM, RCM 2, RCM 4.0, …), other concepts (e.g., value-driven maintenance (VDM))
• Special attention again to the impact/role of (smart) technology, which either brings a new dimension to old concepts or opens new opportunities (e.g. analysis through data mining, use of artificial intelligence for prescriptive maintenance)

Production

In order to fully understand opportunities and challenges of smart production strategies a walk through different production management strategies is made.

• Job Planning and Scheduling (Transportation Model, Assignment Model, Sequencing Models, etc.).
• The strategic role of forecasting in estimating production demand.
• Lean, Lean 4.0, Link between total quality management (TQM) and production, Process Quality Control, Six Sigma.
• Manufacturing System Dynamics and Queuing.
• Special attention again to the impact/role of (smart) technology, which either brings a new dimension to old concepts (e.g., lean, use of artificial intelligence for production optimization) or opens new opportunities.

Course material

The basic course material consists of the powerpoints used during the lectures. This material is complemented with compulsory reading material (for the interactive discussions) and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Language of instruction: more information

The course aims at an international student audience

Format: more information

Asynchronous online learning - Group assignment - Individual assignment - Paper - Presentation

The main format for this course consists of traditional, interactive lectures, complemented with guest lectures.

For this course a blended learning approach is offered. Besides traditional lectures and guest lectures from practitioners (either live, on-line synchronous or on-line asynchronous with class recordings), interactive paper discussions (e.g. academic papers, white papers from renowned organizations, professional journal contributions), assignments and team case discussions will be included.

Explanation

30 % for the compulsory(!)  assignments

70 % for the final exam

Information about retaking exams

In case the student has to retake the exam,

In case of failure in the assignment (if the total score including all assignments < 50%):

• If failed for the assignments: alternative assignments will be given
• If passed for the assignments, the points remain

The evaluation will be 70 % based on the final exam and 30% on an assignment. 

Content

• "Smart Factory" Introduction
  • Smart Factory Paradigm
  • Smart Factory Design
  • Driving forces towards “Smart”
  • Enabling technologies for “Smart”
  • Smart FactoryDesign Principles
• Factory Planning & Design
  • Facility layout basics
  • Systematic layout planning
  • Layout design algorithms
  • ​Exercises
• Digital Tools for Factory Planning & Design
  • Digital Twin driven Factory Design
  • Virtual Commissioning
  • ​Towards a Digital Twin
• Enabling Technologies
  • AMR/AGV
  • Robotics
  • Simulation/emulation exercises
• Control Architectures
  • Computer Integrated Manufacturing
  • MOM software landscape
  • How to select an adequate solution?
  • Industrial standards & software integration
  • MES 4.0
• Human-Centered
• Digital Twin for Production and Logistics

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Laboratory session - Project work

Explanation

Final score (/20) = C1 x P1 + C2 x P2

Cx are the weight factors and Px the scores (/20)

P1: written exam on theory 
P2: workshop participation and assignment report/presentation
C1 = 60%, C2 = 40%

Information about retaking exams

Written exam to redetermine the P1 score (analogue to first examination period).  Half of the P2 score is transferred to the second examination period. The other half will be determined by a practical exercise related to the project.

Content

The OLA “industrial testimonials” is taught entirely by guest lecturers from companies, who offer their in-house insights to the students of this programme. There are cross-references with the (core) OLA “managing innovation & transformation”.

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Guest lecture

Content

This OLA consists of 2 big parts (each divided in a more theoretical part and an application/critical reflection part)

1) Innovation management & transformation from a process perspective:

• Key drivers for successfully managing (technological) innovation
• Perspectives on managing innovation/transformation (traditional perspective and design thinking perspective, incl. workshop)

2) Innovation management & transformation from a human perspective:

• Leadership, strategy/(cultural) change, learning
• Integration of these aspects into a holistic view

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Discussion - Group assignment

Content

The master’s thesis is the final and completing work of the master's program and focuses on the concrete realisation of innovation concerning a technological solution. In the context of the master’s thesis, the term innovation should be understood as the establishment of a new (or innovative) product, process or service or the application of an optimisation process to an existing product, process or service. “New” or “innovative” is to be interpreted here as “new” or “innovative” for the student. The required knowledge should clearly exceed the knowledge considered as already being acquired during the curriculum.

In principle, each student is assigned a different topic for the master’s thesis. Every Master thesis is supervised by a promoter belonging to FIIW or FirW (KU Leuven) or FEA (Ghent University). An additional promoter or co-promoter of an external organisation, or a thesis related research group may be included.

Possible thesis topics are proposed by the industry (preferably), by internal research groups linked to the Engineering Faculties, by external research, by lecturers/professors or by the student. There are also possibilities to conduct the master’s thesis abroad. Each topic presented must be approved by the campus-related research unit. For the student, the selection process of the subject and/or promoter is initiated during the academic year preceding the master’s thesis.

After having successfully completed the assignment, the student must scientifically describe the result of the thesis and orally defend it before a jury of at least three persons: the promotor(s), the daily guide and one or more assessors.

Course material

N.A.

Explanation

The master’s thesis is evaluated by a jury of at least three persons: the promotor(s), the daily guide and one or more assessors, on the basis of three aspects: the process (40%), the final text (30%) and the presentation and oral discussion (30%).

• Process

Process (work ethic): approach, planning, commitment, initiative, communication, professional attitude, etc.

Process (methodology & results): quality of the end result, personal contribution, methodology, etc.

• The final text:

Paper and scientific summary (form): structure, language, style, etc.

Paper and scientific summary (content & product): quality of delivered work, scientific accuracy, personal input, critical analysis.

• Presentation and oral examination

Presentation and defense (form): slide configuration, language, attitude, time management, etc.

Presentation and defense (content & product): completeness, quality of the work proposed, of the defense, and of the proficiency in answering questions, etc.

A result of less than 8/20 in any of the three aspects (process, thesis & scientific summary, and presentation & defense) always results in an insufficient grade for the entire master’s thesis. The final grade for the master’s thesis shall, in this case, not exceed 9/20.

The final grade of the master’s thesis is to be written in the form of one decimal place, except for results between 9.0/20 and 10.0/20. If the calculated final mark for the dissertation falls between these two values, the final grade is set at 9.0 and justified in writing unless the jury, based upon its deliberations, decides the student can pass the Master thesis. In such a situation the final grade is set to 10.0/20.

Failure to submit the thesis or failing to show up for its presentation and defense results in the result NA for the master’s thesis.

Component marks of at least 10/20 published in the academic progress file are transferred to the next examination period within the same academic year and to the following academic years, except for temporary marks and marks for intermittent tests.

Information about retaking exams

The evaluation process is similar to that of the first examination opportunity. If a student does not pass the initial exam, additional work that the student must complete will be specified.

Additionally, the revised thesis will be reevaluated, and the student will participate in the final defense in EP3. During the retake, the score from the initial evaluation will be reviewed on a student-by-student basis.

Content

We could define a project timeline throughout the semester with a few intermediate milestones, which they have to present to the student group, each preceded by some ‘more applied’ courses:

1. Milestone 1 (week 3): Definition of use case, definition of required behaviors of the DT, selection or modelling techniques, definition of DT architecture and sensor selection...

a. Short repetition of the first module of the main DT course – more applied manner – to refresh the minds.
b. Overview of the available INFRA systems/data sets/company use cases which the students can choose from.
c. Result: students report on their findings to each other and to the coaches

2. Milestone 2 (week 6): Development of the virtual replica

a. Common feedback collected from phase 1 can be given to the whole group
b. Typical model workflows (data, physical lumped, discrete event simulation, physical 3D, …) - how to do this in practice.
c. One-on-one for each group/system -> introduction to models relevant for the selected use case (setup with some models are made available; students to select the right model)
d. Result: students report on their findings/demonstrate to each other and to the coaches

3. Milestone 3 (week 9): Development of the digital twin

a. Common feedback collected from phase 2 can be given to the whole group
b. Typical workflows on how to create the link between the virtual replica and the real asset - how to do this in practice.
c. One-on-one for each group/system -> introduction of available sensors, datasets, computing platforms, …
d. Result: students report on their findings/demonstrate to each other and to the coaches

4. Milestone 4 (week 12): V&V (use) of the digital twin

a. Common feedback collected from phase 3 can be given to the whole group
b. Result: Students present the added-value of their digital twin to each other and to the coaches

Course material

The basic course material consists of the presentations used during the lectures and available INFRA systems/data sets/company use cases. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Traditional lecture

Explanation

Project/Product (50%), Progress (15%), Presentation (20%), Report (15%)

Information about retaking exams

Project/Product (50%), Progress (15%), Presentation (20%), Report (15%)

Content

Course topics:

• What delta is required towards upgraded machine (this course of other course (broader towards factory?) --> link to M&P course
  • Cost-benefit analysis
• What sequence of actions typically to follow to limit effort/cost/downtime to reach delta
  • Brownfield installations, system installation in a non-invasive way?  limit downtime and remanufacturing costs/effort
  • Including also DevOps for software when new, extended capabilities come available, execution without disruption. Upgrading the IOT features automatically/ redundancy (not too deep in software aspects)
  • Continuous updating/future updating --> PLM of Digital Twin
• How to get started – how to deal with limited/missing information – given CAD/CAE information is often lacking - system identification
  • Data-driven modelling/system identification for DT construction (applied, basics in main course) --> link to DT course
• From design:
  • Adaptive systems design (flexible instead of rigid, machine level)
  • Modular design – upgradable design
• Drive focus: optimal component selection & dimensioning for drivetrain retrofitting, e.g., from old DC machine to optimal high-end servo, from old single drive with mechanical conversion system to individually actuated multi-drive system with electronic gearing/CAM,
• Open standards (how to collect data, ...) - open system architecture – easier to upgrade afterwards
  • Industrial Interface protocols and middleware (profibus, modbus, CAN, IO-link)
• Use cases:
  • Given an old machine, which components would you replace, where would you add which sensors, to upgrade this asset into a smart machine with limited cost/impact but maximum smartness?
  • Guest speakers (VINTIV, VersaSense, Flanders Make)

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Explanation

For this course, the students will need to make a case study where several topics in the course are used to come to a full solution.  Students will present this solution in a report and in a presentation which will be judged according to:

• Content
• Form
• Presentation

The points will be given on the report (80%) and the presentation (20%).

Information about retaking exams

The student is able to work further on the case study.  He will be able to improve his report and presentation.  A moment for a presentation will be made. 

Content

0. Introduction

•  Definition of smart sensing

1. Innovative sensor-technology (full field sensors, sensor networks, ...)

Do we look into the design of the physical sensor at such: yes, but only regarding what can we   expect as output and what are features needed to operate the sensor in a Smart environment

• Sensor networks (wired/wireless, 5G, …)
• Full field techniques (DIC, camera)
• Linking with existing system sensing platforms (e.g. Kistler in injection moulding systems) focus on specific sensor for manufacturing
• Sensor technology (e.g. MEMS)
• Microcontroller architectures/embedded controllers – notions on available technologies
• Power supply functions (energy harvesting, EMI) - innovative powering of sensors

2. Augmenting/improving/enriching sensor data/information // smart exploitation of sensor data

• Self-adapting sensor/smart sensors
• (Model selection for) deployment in state-estimation/sensor fusion
• Extension from state- to input-/state- and parameter-estimation
• Sensor fusion (multi-source sensors)
• Virtual sensing & case studies (electrical machine as a sensor, drive as a sensor, vehicle state estimation, …)
• Handling of large data streams
• Machine learning in view of smart sensing

3. Optimal use of smart sensors: how to select, deploy, …  both smart, innovative sensors and traditional sensors

• Automatic data pre-processing (filtering, feature extraction - without interpretation (e.g. images), removing conflicting data, redundancy, …)
• (Automatic) calibration
• Sensor selection and placement
• (Manual) (virtual) sensor tuning
• Edge versus cloud
• Validation of the smart sensing system

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Content

Basic Concepts and Taxonomy of Dependable and Secure Computing  
o        See "famous" paper of A. Avizienis & J.C. Laprie 
o        Main definitions relating to dependability, a generic concept including as special case such attributes as reliability, availability, safety, integrity, maintainability, etc.  
o        What do the following terms mean? Dependability, security, trust, faults, errors, failures, vulnerabilities, attacks, fault tolerance, fault removal, fault forecasting.  

EU CE Marking 

Safety by Design
o        Introduction to System Safety 
o        Safety concepts and lifecycle 
o        Hazard and Risk Identification and Analysis (incl. Systems Thinking and Systems View based methods) 
o        Risk Reduction 
o        Safety Integrity 
o        Safety Cases 
o        Safety-Critical Software 
o        Safety Standards 
o        Safety I vs Safety II : Resilience 

Security by Design
o        Cyber attacks and mitigation strategies 
     §     Prevention 
     §     Detection + action plans 
o        Security technologies for ICS environments 
     §     Network/communication oriented technology
          - ICS network security (o.a. firewalls, zoning, intrusion prevention / detection…) 
          - Secure communication technologies (oa. intro in crypto, security in ICS communication protocols…) 
     §     System oriented security technology 
          - Security monitoring: system hardening, virus scanners, access policies, BYOD mgmt … 
          - IoT/gateway/cloud security 
o        Basics in system administration (operational challenges) 

Resilience by Design
o        Resilient Software 
     §     Recover from bitflips 
     §     Hot-standby 
     §     .. 
o        Resilient hardware 
     §     Voting 
     §     Spatial/temporal/.. diversity 
     §     … 

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Computer session - Practice session - Project work

Explanation

Assignment: 25%

Theoretical exam: 75%

Information about retaking exams

A second examination opportunity is available for the theoretical exam. The points from the assignments will be retained.

Content

- cobots versus robots: differences and complementarities, standards, typical use cases

- tooling and fixture: gripper principles and overview, gripper selection

- navigation (mobile robots): tracking, localisation and map building

- manipulation (arms): velocity and force control, grasp planning and execution; coordination arm-gripper motions

- coordination: fleet control of AMR’s, dual-arm tasks, mobile manipulators

- manufacturing execution systems: reconfigurability concept and architectures, leveraging on flexible automation capabilities  

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Laboratory session - Practice session

Explanation

Final score (/20) = C1 x P1 + C2 x P2

Cx are the weight factors and Px the scores (/20)

P1: oral exam on theory 
P2: participation in hands-on experience sessions
C1 = 60%, C2 = 40%

Information about retaking exams

Oral exam to redetermine the P1 score (analogue to first examination period).  Half of the P2 score is transferred to the second examination period. The other half will be determined by a practical exercise related to the hands-on experience sessions.

Content

1) Introduction to Human-Centered Manufacturing

• The human role in smart operations & maintenance
  • Operator 4.0 | Industry 5.0 | ..  
• Human-centered design principles
• Human-machine interaction
• Human augmentation
• Re- and upskilling challenges

2) Human factors: evaluation measures and methods

• Ergonomics | Cognitive load | Technology acceptance | Worker satisfaction | ..
• The dynamics of learning and forgetting
• Evaluation: expert-based vs. data-driven
• Time and method studies

3) Enabling technologies

• Off-the-job and on-the-job training and guidance
  • Digital work instruction platforms
  • Remote maintenance applications
  • VR training
  • Industrial social network and knowledge sharing concepts
  • Context-aware functionality: e.g. filtering instructions, proactive smart assistant
• Capability monitoring and management
  • Learning management systems
  • Skills & competency matrix tools
• Human-robot collaboration
  • Cobots
  • Exoskeletons
  • Mobile robots
• The adaptive workplace
  • Load balancing
  • Personal reconfiguration (e.g. table height, work content, etc.)
  • Workplace lay-out
• Decision support by intelligent systems (not only for operators, also production/operations managers, schedulers, etc.)

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Guest lecture - Practice session - Project work

Explanation

Final score (/20) = C1 x P1 + C2 x P2

Cx are the weight factors and Px the scores (/20)

P1: written exam on theory 
P2: assignment participation and project report/presentation
C1 = 40%, C2 = 60%

Information about retaking exams

Written exam to redetermine the P1 score (analogue to first examination period).  Half of the P2 score is transferred to the second examination period. The other half will be determined by a practical exercise related to the project.

Content

This course discusses some advanced methods and approaches for decision-making support on maintenance activities and their related processes such as staffing and spare parts management. Focus is on the tactical level.

- Reliability and maintenance modeling
- Fitting probability distributions to data, use of data mining
- Maintenance decision models and optimization
- Human resources capacity planning
- Spare parts management
- Operational aspects: remote maintenance, scheduling, ...

Various models will be presented in the course. The main goal is to understand the applicability and shortcomings of the models and being able to apply them.

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).

Format: more information

Computer session - Guest lecture - Practice session

Explanation

30 % for the compulsory (!) assignments; no submission of the assignments = 0 for the exam as well

70% for the final exam

Information about retaking exams

in case of failure (total score < 50%):

• If failed for the assignments: alternative assignments will be given
• If passed for the assignments: the points remain

Content

1) Introduction (present challenges, history of CM, possible monitoring techniques)

- The role of condition monitoring and prognostics in a maintenance & operations framework: for machines, processes and production + maintenance strategies, RUL, terminology

- Motivating case studies: could be used throughout the course (machine/process/production) Real cases - degradation tests, possible use of test rigs

•           Importance of Condition monitoring (Measurements, Aims, Life concepts in monitoring, Failure rates)

•           Failure modes & criticality (Machine failures fault tree analysis)

•           Phases of Condition Monitoring (Fault detection/Fault diagnosis/fault prognosis)

•           Maintenance Strategies: no decision making here, focus on CM & Progn.

•           Permanent vs intermittent monitoring

•           Condition Monitoring Methods (Vibration Analysis, Oil/lubricant Analysis, Performance Analysis, Thermography, Electric Current Analysis, Ultrasonics, Acoustic Emissions, Instantaneous speed analysis)

•           Physical Quantities (vibration, current, voltage, speed)

•           Types and Benefits of Vibration Analysis (Benefits compared with other methods, International Standards and Guidelines)

•           Types and Benefits of Motor Current Signature Analysis, International Standards and Guidelines

2) Physical signatures of faults in mechatronic systems (typical faults, possible standards)

Machine faults / dynamic models for motors, gearboxes, pumps, … how does the fault occurs / generation of physical signatures

Bearings /Gears / transmissions / Motor / loads / pumps/airfans / Belts, couplings, misalignment/unbalance

3) Sensors & data acquisition (sensors, data, communication)

Sensors (Vibration Transducers, Torsional Transducers, Current Transducers, Voltage Transducers ), Characteristics of each sensor (bandwidth, ranges,..)

data types, DAQ, communication (networks) from an architectural point of view

sensor specs wrt application needs

4) Data processing (signals)

Signal class, toolchain,…

5) Diagnostics, with feature extraction and reduction

            Output is/are the features

• Vibration analysis
• Electric signal analysis
• Image based, object recognition, motion

6) Prognostics

Course material

The basic course material consists of the presentations used during the lectures. This material is complemented with compulsory reading material and optional reading materials for those students who want to deepen their insights in specific topics. Where possible, materials will be made available electronically (Toledo).