Maintenance with AI New AI assistant keeps Lenze high-bay warehouse fit and planable

Source: Press release of Fraunhofer IEM | Translated by AI 3 min Reading Time

Related Vendors

Automated storage systems are specialties of Lenze. Together with Fraunhofer IEM, they have now developed an AI-based maintenance assistant that helps prevent damage and downtimes.

Lenze high-bay warehouses are now maintained by an AI assistant to identify upcoming problems before they become critical. Left: Dr. Heiko Stichweh, Head of Innovation at Lenze, who developed the system with Maximilian Bause (right) from Fraunhofer IEM.(Image: Dock One)
Lenze high-bay warehouses are now maintained by an AI assistant to identify upcoming problems before they become critical. Left: Dr. Heiko Stichweh, Head of Innovation at Lenze, who developed the system with Maximilian Bause (right) from Fraunhofer IEM.
(Image: Dock One)

With powerful drives and specialized control technology, Lenze enables automated stocking and removal in its high-bay warehouses, reportedly ensuring smooth operations with up to 25,000 goods movements per day. However, maintaining these complex systems is important and unfortunately labor-intensive. If a system fails, the entire process comes to a halt. Depending on how quickly the error is identified and resolved, a warehouse shutdown can last several days and become costly. Therefore, secure precautionary measures were sought, which were found within the framework of artificial intelligence (AI).

The smart way to schedule repair cycles

To avoid downtime, Lenze is now using an AI-based maintenance assistant with the Fraunhofer Institute for Mechatronic Systems Design (IEM). This involves a "machine learning" algorithm that can detect critical conditions in the warehouse that require intervention. The tool also identifies and locates emerging defects or increasing wear on components before it reaches a critical point. For example, if the guide or drive wheels of the storage and retrieval machines are heavily worn, the maintenance assistant detects the impending failure in time. It can also pinpoint the affected location. Employees can then specifically plan the replacement of the wheels, which can occur depending on factors such as work schedules, delivery deadlines, or spare parts supply.

AI maintenance assistant is easy to retrofit

The special aspect of AI-based maintenance is that the assistant derives its information from the existing sensor monitoring of the drive motors. The motors serve as interfaces between the machines and the maintenance assistant. If something runs "unevenly" in the overall system, a deviation from the normal state is detected in the motor data. The algorithms are designed and trained to recognize and locate any changes in condition. Lenze users who wish to use the "intelligent" maintenance assistant can rely on existing sensors. This allows for a relatively uncomplicated and cost-saving integration of the smart assistant.

No cloud! With embedded and edge devices

In developing the AI maintenance assistant, the project team benefited from the high data quality of Lenze machines, as emphasized. The drive data possess very high quality, achieved through low noise at high-frequency and high-resolution sampling. This facilitates targeted analyses for monitoring various process-critical components, including those not connected to the motor, as a Lenze specialist notes. However, the challenge lies in processing large data volumes, which is resource-intensive and relatively energy-demanding. Therefore, the project team deliberately found an alternative to the cloud with embedded and edge devices. This allows data to be processed in close proximity to the machine when needed, reducing latency times and increasing data security.

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta)

Unfold for details of your consent