AI-Powered Vibration Testing: Enhancing Electric Motor Quality Control

Introduction

Quality control in electric motor production is a critical aspect of ensuring reliability and performance. Traditional methods of testing and classifying motors based on vibration analysis can be labor-intensive and prone to human error. To address these challenges, our project aims to revolutionize the quality assurance process for prototyping motors through the integration of AI-driven automation.
 

Background

Our team, composed of Naveen Chand Dugar (B.Tech in Electronic and Communication Engineering), Matthias Gumbert (PhD in Neuroscience), and Danijel Matesic (BSc in Information Technology), has leveraged its diverse expertise to tackle the complexities of motor quality control.
 

Aim and Objectives

The primary aim of our project is to enhance the efficiency and accuracy of quality assurance processes for prototyping electric motors. We intend to achieve this by automating the classification of vibration tests, employing AI for precise anomaly detection, and conducting root cause analysis to identify potential quality issues.
 

Key Objectives

• Automate Classification: Use AI to automate the classification of vibration tests, distinguishing between acceptable and faulty motors.
• Anomaly Detection: Implement AI models to detect anomalies in vibration data, providing insights into potential issues.
• Root Cause Analysis: Utilize data analytics to perform root cause analysis, improving the overall quality assurance process.

Current vs. Desired Workflow

Current Workflow:

• Motor test run
• Record vibrations
• Manually classify as acceptable or faulty

Desired Workflow with AI Integration:

• Motor test run
• Record vibrations
• Automate classification using AI
• Perform anomaly detection
• Conduct root cause analysis
• Utilize AI and data analytics for continuous improvement
• Data Processing and Analytics

To ensure the accuracy and reliability of our AI models, we follow a comprehensive workflow:

• Data Cleaning: Ensuring that the vibration data is free from noise and errors.
• Data Engineering: Preparing the data for analysis by structuring and formatting it appropriately.
• Descriptive and Predictive Analytics: Using advanced data analytics and AI models to predict motor quality and identify potential issues.

AI and Dashboard Integration

Our AI model, built using transfer learning with Convolutional Neural Networks (CNN), predicts motor quality by analyzing vibration data. The model is integrated into a user-friendly dashboard, allowing for easy interaction with testing data. This dashboard facilitates real-time analysis and visualization of motor test results, anomaly detection, and root cause analysis.
 

Conclusion

By leveraging AI to predict motor quality and conducting data analytics for root cause analysis, we have significantly improved the efficiency and accuracy of the quality assurance process. Our dashboard provides a streamlined interface for interacting with testing data, enabling engineers to make informed decisions more easily.
 

Future Considerations

To further enhance our system, we plan to:

• Integrate the AI model into the test workflow for real-time analysis.
• Continuously evaluate and optimize the model based on new data and feedback.
• Leverage large language models (LLM) for enhanced Q&A interaction, providing better support and insights to users.

 

Acknowledgments

We extend our gratitude to our collaborators at BMW Group and Constructor Academy, who have contributed to the success of this project.