[MA] - Mechanical Impedance Classification using Convolutional Neural Networks for Power Tools

Klassifizierung der mechanischen Impedanz mit Hilfe von neuronalen Faltungsnetzen für Elektrowerkzeuge

Mechanical Impedance Classification using Convolutional Neural Networks for Power Tools

Task Description / Aufgabenstellung

Mechanical impedance refers to the relationship between force and motion in a vibrating system. It is a crucial concept for understanding how different materials and structures respond to vibrations. By assessing mechanical impedance, we can gain insights into the dynamic behavior of mechanical systems, which is essential for various applications, including tool design and performance evaluation.

Extensively utilized across various industries, power tools significantly enhance efficiency and precision in tasks such as cutting, drilling, and grinding. However, proper usage and handling of these tools are vital for ensuring safety and achieving optimal performance. A secure grip is essential for maintaining control and accuracy while using power tools. An improper grip can lead to accidents, reduced performance, and increased fatigue for the user. Therefore, ergonomic designs that promote a comfortable grip are important, as they can help reduce the risk of injury and improve overall user experience.

Measuring mechanical impedance plays a significant role in understanding the effectiveness of a grip on a power tool. By evaluating how vibrations are transmitted through the hand, we can assess user comfort and control. Insights gained from impedance measurements can inform better tool designs that enhance user experience and safety.

In this context, Inertial Measurement Units (IMUs) can track motion and orientation, providing valuable data on grip dynamics. When combined with vibration motors, which can simulate and measure the hand's response to different frequencies, this technology allows for a comprehensive analysis of grip states. By assessing how well a user is gripping a power tool, we can identify potential issues and improve tool design and usability.

Overall, understanding mechanical impedance and its implications for tool grip is essential for enhancing the safety, comfort, and effectiveness of power tools in various applications. The integration of advanced technologies, such as IMUs, vibration motors, and neural networks, will pave the way for innovative solutions that optimize user interaction with power tools.

Objectives

• Measure accelerations with frequencies higher than 1 kHz

• Apply signal processing techniques to extract more information from the accelerations

• Organize the data for training

• Train a convolutional neural network to classify the data

• Optimize the Computational cost of the neural network

• Implement the neural network on a microcontroller

• Validate using an experiment with 10 subjects

Zeitplanung:

Checklist

• Introduction / tour in M4

• Urheberrechtsvereinbarung signed: https://www.tuhh.de/t3resources/sls/pdf/ZPA/Formulare_oeffentlich/Rechte_an_Abschlussarbeiten.pdf

• if applicable: signed confidential agreement

• official registration

Helpful links:

• Thesis Work / Studentische Arbeiten 

• Criteria for the evaluation of Bachelor's and Master's theses, handout version

• Laborordnung

• Spotlights / Kurzvorträge

• Templates (Latex, ppt etc.)

Document Upload Final Thesis / Dokumentenabgabe Abschlussdokument

File of final presentation / Dokumentenabgabe Abschlusspräsentation

Link for further files / Link für weitere Dokumente