Training: Industrial Data Analytics

The increasing connectivity in the industrial sector offers companies enormous opportunities to generate insights from their data and thereby strengthen their competitive position. Industrial data analytics enables improvements in areas such as quality control, fault detection, and predictive maintenance. However, the successful application of data analytics requires expertise in mathematical methods of statistics, machine learning, and artificial intelligence (AI). Technical staff and engineers have extensive knowledge of manufacturing, but they often lack practical experience in applying data analytics. In our training, you will have the opportunity to apply data analytics methods and learn all the steps from data selection and preparation to data analysis and interpretation. You will work with real training data in the Python programming environment and create your own machine learning models during the training. Our training takes into account the numerous specific challenges involved in handling production data and provides you with valuable insights for the successful implementation of industrial data analytics projects. 

The hands-on training course “Industrial Data Analytics” is designed for technical staff who wish to learn how to handle large volumes of data and develop intelligent solutions for specific use cases based on real-world tasks.

• You will learn the essential fundamentals and procedures for working with data in production.
• You will gain a solid overview of proven industrial data analytics methods and technologies.
• You will apply this knowledge to a real-world case study using actual production data throughout the data processing chain (data pipeline).
• You will learn to systematically generate insights from data to provide a foundation for strategic decisions.
• You will develop your skills in one of today’s most in-demand fields and strengthen your personal skill set.
• Upon completion of the training, you will gain access to high-quality self-study content on Industrial Data Analytics in the IEM Learning World.

• What methods and tools are suitable for analyzing and evaluating operational and machine data?
• What role do statistical methods, machine learning, and artificial intelligence (AI) play in optimizing production processes?
• What steps are required to create and interpret machine learning models?
• How can production data be effectively selected and prepared for use in data analytics projects?
• How can I implement my own machine learning projects in the Python programming environment?
• What best practices can help us when implementing industrial data analytics projects?

Following an introduction to the topics of Industrial AI, Industrial Data Analytics, and key basic concepts, methods and tools will be taught using a practical example from the field of mechanical and plant engineering. The overarching topics of data sources, data infrastructure, data analytics, and use cases will be covered in the following modules:

Day 1 | Use Cases, Data Storage and Data Structures

• Industrial Data Analytics Use Cases – Artificial Intelligence in Practice
• Data Storage and Access via Databases
• Programming Environment (Python)
• Data Structures
• Visualization and Exploration

Day 2 | Modeling and Machine Learning

• Data cleaning and filtering
• Signal processing methods
• Manual and automated feature extraction
• Supervised, unsupervised, and semi-supervised modeling methods
• Fundamentals of machine learning for classification and anomaly detection
• Fundamentals of machine learning for regression and prediction models

• Technical staff and engineers, e.g. from IT, software engineering, production, and maintenance
• Staff in Operational Excellence and Technology Management
• Requirements: 
  • Basic knowledge of statistics and data analysis, as well as some programming experience, is a plus.
  • Knowledge of databases and data structures is a plus.