Reference

Predictive Maintenance for Industrial Belts

Automated Forecasting for Assembly Lines Using Data Science

We developed a predictive maintenance system for a German logistics company in the area of assembly line maintenance—including hardware components—that is in use worldwide at logistics centers and airports.

Our Work

Using sensors specifically designed for this purpose, audio data and the positions of the individual cells in the sorting system are recorded and then analyzed in high resolution using statistical methods to identify maintenance-related anomalies. This helps prevent unplanned downtime and increases efficiency. Above all, however, the use of automated maintenance forecasting significantly reduces the need for personnel, since only the few components of the sorting system specified by the forecasting algorithm need to be inspected, rather than all of them.

How Predictive Maintenance Solutions That Help Our Customers

Devices with Predictive Maintenance

0 k+

Airports and Logistics Centers

0 Locations

in use at maintenance stations

0 Sensor boxes

Key Areas of Cooperation

Project Objectives

The goal of the project was to develop a predictive maintenance system based on the analysis of audio data using data science methods. The software was designed to detect the degree of wear on the cells on the conveyor belt based on the recorded vibrations and to generate a maintenance request. Both dealing with background noise and the sometimes very different mechanical designs of the sorters posed particular challenges.

Key Factors

CI/CD
Cloud
Data Science (various statistical methods)
Hardware Concept and Design
DevOps
Frequency Analysis (Fast Fourier Transform)
IoT
Web Front End

Fleet Management Software: What Sets Good Solutions Apart

Software Architecture Design
Hardware Design of the Sensor
Cooperation in the Construction of Infrastructure
Full integration into the existing software architecture
Data Collection and Data Reduction in Compliance with Data Protection Regulations
Secure communication between internal corporate networks and the cloud (IoT)
Scalable Data Analysis/Forecasting in the Cloud
Support for Surface Design
Multi-client capability

Current Topics

White Paper

Digital Readiness Check for Fleet Operators: “How Data- and AI-Ready Is Your Fleet?”

We classify digital maturity along three dimensions – system compatibility, cost efficiency, and the proportion of standard and custom solutions….

Success Story

AI-Based Maintenance System for Energy Storage Systems

A neural network, trained on real-world data from more than 75,000 energy storage systems, identifies devices in the field that require maintenance before they fail. The project also included the handover of infrastructure to SENEC.

Blog Post

ZAP – The Security Tool Put to the Test by Experts

At IT Sonix, we regularly explore new testing methods to meet our standards for high-quality software…

Success Story

MAN Cloud Platform for Fleet Management

We developed MAN's cloud-based RIO platform and MAN DigitalServices, an open ecosystem that digitally connects fleet management, dispatching, and driver training…

White Paper

Energy Systems: Off-the-Shelf Software vs. Custom Solutions

We'll show you where SAP's standard solutions are sufficient, and where customized solutions are the better fit for the energy transition….

Results of the Collaboration

Using proven data science methods, a predictive maintenance system (hardware and software) was developed for assembly line logistics. This system detects maintenance-related anomalies in the carts and generates an automated notification in the administrative interface. The system significantly reduces the need for manual inspections, ensures that the maintenance process can be planned effectively through tiered early warnings, and prevents avoidable breakdowns.

Additional Industry References

Learn more about our expertise and services in predictive maintenance.