The digital transformation is in full swing and current developments are characterized by advances in digital business models, IIoT platforms and technological impetus from machine learning and artificial intelligence in the use of data. Many companies see data-based value-added services as crucial for their future business. They are working on analysis solutions that can be used to optimize production processes or create completely new data-based business models. Weidmüller wants to enable machine builders and operators to create machine learning models (ML models) quickly and easily and thus translate the collected data into concrete recommendations for action. Close local collaboration, ecosystems and global marketplaces - such as this one between Microsoft and Weidmüller - are emerging in order to meet the high demands of the industry and expand agilely in the digital feedback loop.

With guided analytics for machine learning applications

Today, data scientists analyze the data and create ML models. This process is largely manual and exploratory. The process of modeling and creating the ML pipeline is very complex. In total, there are up to 10 to the power of 40 possible combinations to build an ML solution. The actual design of the ML pipeline is also specific to each use case. Weidmüller wants to simplify the application of machine learning so much that domain experts can use their knowledge of the machine or the production process to implement ML solutions independently - without the need for data science expertise. Sebastian Seutter, Sr. Industry Executive at Microsoft, summarizes: "In industrial companies, Weidmüller's approaches towards intelligent, self-optimizing systems are increasingly becoming a key competitive advantage."

The Industrial AutoML software guides the user through the process of model development, which is why Weidmüller also refers to this as "guided analytics". The software helps to translate and archive the valuable application knowledge of the domain experts into a reliable machine learning application by querying the existing knowledge and combining it with the ML process working in the background. Compared to an automated modeling process, the most important factor - model quality - improves substantially when domain knowledge is integrated.

The Industrial AutoML solution essentially consists of two modules: The "Model Builder" and the Runtime cover the complete cycle of development, execution and optimization of the ML models over their life cycle.

With the Model Builder, the user can generate ML solutions for anomaly detection, classification and error prediction. This combines supervised and unsupervised machine learning and thus integrates domain knowledge into the model building process. The task of the user is to mark the normal or possible misbehavior of the machines in the training data and, if necessary, to generate their own features that are particularly relevant for the use case. This creates a data set enriched with domain knowledge, on which the training, optimization and validation of alternative ML models are performed automatically. The topic of "Explainable AI" is particularly important in this AutoML approach: The Industrial AutoML software enables domain experts to easily understand the influence of their application knowledge on the model quality and ultimately understand why an ML model results in a certain analysis result. Seutter also appreciates the advantages of the Weidmüller solution: "It is precisely the interplay of comprehensibility and automated execution that leads to trust and significant efficiency gains for users."

The second module of the Industrial AutoML solution is the execution environment, which is used to operate the ML models in the cloud or even directly on the machine in an on-premise application. The execution environment presents the model results in an understandable way so that the user can implement specific actions, for example to avoid errors.

The Industrial AutoML solution has been available worldwide via the Microsoft Azure Marketplace for several weeks now. As part of this collaboration, both companies are combining their respective strengths: Weidmüller is contributing its industrial and machine learning expertise for use cases in mechanical and plant engineering, which is crystallized in the Industrial AutoML solution and tailored to the requirements of industry. The trusted cloud infrastructure and modern Azure services from Microsoft enable the Industrial AutoML software to be easily deployed by users. This includes fast access via the Marketplace as well as simple deployment and scaling during operation. "Our partnership combines industrial knowledge and technological core competencies. This helps customers to focus, implement quickly and differentiate themselves from the competition," emphasizes Seutter.

Comprehensive cooperation between Weidmüller and Microsoft

The cooperation between the two companies goes beyond a technological exchange. Weidmüller is part of Microsoft's partner network and has achieved "co-sell" status. This means that Microsoft and Weidmüller also operate together on the market and offer a service package that enables all partners in the ecosystem to increase their speed of transformation, innovation and scaling - almost worldwide.

"Together, we are accelerating machine builders and operators to transform their domain knowledge into data-driven innovation and digital value-added services by enabling quick and easy adoption of ML and IIoT technologies," explains Tobias Gaukstern, Vice President Business Unit Industrial Analytics.