AI400: Predictive Maintenance in Industry with Machine Learning

Training: Artificial Intelligence

Developers and IT professionals receive a practical introduction to predictive maintenance with machine learning. The course covers fundamentals of statistics, data-driven approaches, and predictive models, as well as the processing of sensor data. It addresses industrial use cases in which techniques of data analysis and machine learning are practically applied and compared using Python.

Unfortunately there are currently no available appointments.
Would you like to request an appointment? Then click on 'No matching appointment?'

Request prefered appointment period:

* All fields marked with an asterisk are mandatory fields.

Agenda:

  • Introduction to predictive maintenance fundamentals
    • Forecasting
    • Statistics etc.

 

  • Comparison and examples of various techniques such as
    • Data analytics/ML
    • IoT
    • Condition monitoring etc.

 

  • Examine various application scenarios and use cases, including analysis of time series from sensor data

 

  • Introduction to Python libraries and tools for implementation of predictive maintenance solutions, such as
    • Scikit-learn
    • TensorFlow
    • Keras etc.

 

  • Hands-on exercises for application of learned techniques in Python (including implementation of simple use cases)

 

  • Discussion on best practices and future developments in predictive maintenance, such as
    • AI-based techniques
    • Integration of data from various sources etc.

Objectives:

Understand fundamentals of Predictive Maintenance, learn various techniques, examine application scenarios, be able to develop Python applications for Predictive Maintenance.

Target audience:

  • Developers
  • IT Professionals

Prerequisites:

To be able to follow the learning pace and content of the training AI400 Predictive Maintenance in Industry with Machine Learning effectively, we recommend prior participation in the following courses:


Alternatively, prior knowledge in the following areas is required:

  • Python programming fundamentals
  • Data extraction and data preprocessing
  • Machine Learning

Description:

Knowing when it happens before it happens. This is the basic concept of 'Predictive Maintenance'. To achieve this objective, relevant status data and environmental parameters of the systems to be monitored are collected and evaluated using statistical methods and Machine Learning. If the collected data makes a malfunction appear probable, the system triggers an alarm and timely maintenance can be scheduled.

The workshop AI400 Predictive Maintenance in Industry with Machine Learning aims to provide participants with the knowledge and skills to deploy such a system. For this purpose, the fundamentals of Predictive Maintenance, including statistics, data-driven approaches and prediction models, are presented. The course will focus on sensor data processing and introduce and compare various data analysis and machine learning techniques based on use cases. Participants will also learn how to apply these techniques in Python to implement use cases themselves.

check-icon

Guaranteed implementation:

from 2 Attendees

Booking information

Price:

450,00 € plus VAT.

(including lunch & drinks)

We are happy to conduct this training as an inhouse session at your location as well, please contact us.

Authorized training partner

NetApp Partner Authorized Learning
Commvault Training Partner
CQI | IRCA Approved Training Partner
Veeam Authorized Education Center
Acronis Authorized Training Center
AWS Partner Select Tier Training
ISACA Accredited Partner
iSAQB
CompTIA Authorized Partner
EC-Council Accredited Training Center

Memberships

Allianz für Cyber-Sicherheit
TeleTrust Pioneers in IT security
Bundesverband der IT-Sachverständigen und Gutachter e.V.
Bundesverband mittelständische Wirtschaft (BVMW)
Allianz für Sicherheit in der Wirtschaft
NIK - Netzwerk der Digitalwirtschaft
BVSW
Bayern Innovativ
KH-iT
CAST
IHK Nürnberg für Mittelfranken
eato e.V.
Sicherheitsnetzwerk München e.V.