Automated machine learning (Industrial AutoML)

Faster creation and use of end-to-end solutions for machine learning models

With Weidmuller Industrial AutoML you can optimize operational processes, increase product quality and create new business models by taking advantage of advanced analytics. As a machine or process expert, you can easily build, deploy and operate machine learning models with no prior knowledge of data science. The AutoML tool enables you to transform your data and domain knowledge into ML models that add value to your business. Models can be deployed in existing manufacturing environments to make real-time analytics and insights available to production workers and stakeholders across your operation.

Realize the full potential of the technology in cooperation with us. We use our expertise to support you from correct data selection to the final integration in your production environment. Find out more about the Weidmüller data-based AutoML solution and optimize your processes for long-term business success.

Download free white paper “Machine Learning automation for industrial applications” here

Your AutoML benefits at a glance

BOGE Kompressoren

In today’s data-driven world, not everyone has the knowledge or the ability to make use of data. AutoML closes this gap. It uses ML algorithms and models to allow everyone to gain valuable insights from existing data. At Weidmüller, we also offer you a number of promising benefits:

Accelerate innovation

Benefit from advanced analytics while using your existing machine data and domain knowledge. No extra training required. Build your own machine learning models in just an hour.

End-to-end solution

Create machine learning models, operate and optimize them “on premise” or in the cloud. You can continuously improve model performance simply by retraining models as you gain more insights and collect more data from machines and processes.

Build customer relationships and new business models

Increase customer satisfaction with improved products and services, and achieve a better understanding of your customer’s needs. Use the data-driven insights made possible by AutoML to develop an individual product.

Benefit from AutoML without a prior knowledge of data science

Watch our 2-minute animation for a compact overview of the Weidmüller Industrial AutoML solution including its key benefits and an explanation on how it works. See the intuitive user interface and seamless integration of automated machine learning for yourself. Find out how AutoML can revolutionise your data-driven journey from anomaly detection through to predictive maintenance.

Our AutoML software product modules and features

GEA

APPLICATION AREA

Automatic detection of anomalies in the behavior of separators in the dairy industry

Scope: 500 integrated machines

BENEFITS

Increase in efficiency and productivity

Transfer of application knowledge into an algorithm

Extension and development of offered services

GEA

Discover and utilise the full potential of the smart product modules in our AutoML solution. Create, validate and export customised models without expertise in data science with ModelBuilder’s easy-to-use user interface. The ModelRuntime module supports the seamless operation, configuration and analysis of the AutoML models – on premise as well as in the cloud. Benefit from the advanced functions that make data-based services as well as greater productivity possible through anomaly detection and predictive maintenance.

edgeML – Machine learning tool for automation Product innovation

Deploy ML models independently of hardware and operating systems

edgeML makes it possible to integrate ML models into automation in a particularly easy and flexible way – regardless of the hardware. And this is done completely independent of the hardware. The tool uses machine learning to continuously and efficiently monitor systems or processes directly at the machine. Users import and manage ML models via the web interface using drag & drop. REST APIs and PROCON-Connect form interfaces to the system. The Docker-based solution is hardware-independent and enables simple, flexible integration of ONNX-based ML models into automation.

edgeML – Machine learning tool for automation

Simple integration in controllers
Intuitive operation of ML models
Supports ML models in ONNX format

Learn more about Weidmuller Industrial AutoML from our experts

Delve deeper into the fascinating world of AutoML and receive valuable information from our experts. Find out how automated machine learning helps domain experts create and optimize models and understand the basics of the complex world of data science and the possibilities it entails.

Industrial AutoML enables domain experts to create and optimize machine learning models

Our responsible product manager, Dr. Carlos Paiz Gatica, explains why machine learning is transforming the industry, how Industrial AutoML is accelerating this process and how you can benefit from it.

Industrial AutoML opens up the complex world of Data Science to you

Find out more about the data science background of our Weidmuller Industrial AutoML tool from our Data Scientist Dr. Daniel Kress.

Weidmuller Industrial AutoML in use

Discover the wide range of potential applications of Weidmuller Industrial AutoML by finding out more about the major companies that are already successfully using the solution. From predicting wear behavior to monitoring, data collection and automatic anomaly detection – we have been able to help a variety of companies optimize their processes and improve their quality with AutoML.

Create, validate and export your own AutoML models with ModelBuilder

ModelBuilder is based on the following step by step approach:

Import and examine your machine and process data.
Assess your data based on automatically generated quality indicators (e.g. missing values).
Enrich your data by creating custom features.
Contextualize your data e.g. by defining what is normal behavior and what is not.
Choose the kind of AutoML model to create (e.g. anomaly detection or classification).
The tool then automates the model creation process, including feature engineering, required preprocessing and post processing operations.
Select the most appropriate model from the models created, based on criteria such as model performance and plausibility.

ModelRuntime – operate, configure and analyze machine learning models

ModelRuntime can be used as follows:

Deploy your AutoML models where you need them: on-premise or in the cloud.
Connect your machine to ModelRuntime by configuring data sources e.g. a database.
Import the created models and assign them to the specific machine. Multiple models can be used for the same machine.
Schedule model execution according to your requirements.
Visualize results using the embedded GUI.
Use and configure ModelRuntime using a program by applying the interfaces provided.
Apply the AutoML model results in practice by importing model outcomes into the existing machine or manufacturing systems.

Weidmüller Industrial AutoML: Find out more from our experts

Boge compressors
GEA Dairy Industry
MULTIVAC packaging
Weidmuller Galvanic

AutoML – Boge compressors

APPLICATION AREA

Predicting the wear behavior of critical compressor modules

Monitoring compressed air availability

BENEFITS

Delivering the relevant sensor data

Optimized production processes and test procedures

The automated machine learning tool helped me to create my own analytics models in a short time without having any data science know-how. I was positively surprised at how good the results the tool produced were based on my application knowledge about the compressor. The model creation process and model selection was intuitive and easy for me to follow.

Dr. rer. nat. Christian Heesing, BOGE

AutoML – GEA

APPLICATION AREA

Automatic detection of anomalies in the behavior of separators in the dairy industry

Scope: 500 integrated machines

BENEFITS

Increase in efficiency and productivity

Transfer of application knowledge into an algorithm

Extension and development of offered services

More information

We were fascinated by the solution, as we have a lot of process engineers who are very familiar with the machines and who are, to a certain extent, able to interpret the data. With Weidmuller’s help, we can now transfer this knowledge to an algorithm.

Matthias Heinrich, Manager Digital Solutions, GEA

With the help of Weidmulller’s AutoML software, we were able to generate an initial model for detecting anomalies with fairly little effort. This has already identified 97 percent of the anomalies in the actual process. We especially like how easy the software is to use. The ability to mark normal and abnormal time ranges for model building is very well implemented.

Dr. Martin Roth, Data Scientist, MULTIVAC

AutoML ModelBuilder enables the simple and fast creation and validation of procedures for anomaly detection based on historical data of motor currents in a milling process. It is intuitive to operate and effectively supports both beginners as well as experienced data science users.

Andre Schmidt, Automation/Software Development, G.Kraft Maschinenbau GmbH

AutoML – Weidmuller Galvanic

APPLICATION AREA

Monitoring of pumps in a galvanic plant

Sensors collect data from pumps e.g. vibrations, current strength, temperature or flow rate
The goal is to detect unusual pump behavior, e.g. bearing damage, to avoid unplanned downtimes and ensure process quality

BENEFITS

Easy and quick testing of predictive monitoring of pumps

Speed: a model is generated in less than 1 hour with ModelBuilder
Intuitive usage: you are taken step by step through the model generation process
Flexible on-premise deployment with ModelRuntime

Trust in an award-winning AutoML solution

When you use Weidmuller Industrial AutoML, you are using an award-winning solution that sets itself apart with its outstanding performance and new products. It has received numerous awards recognizing its advanced development and successful use. Trust in award-winning AutoML technology that has already contributed to the success of countless companies.