Related Experiment Video
Updated: Jan 16, 2026
07:30
A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact
Published on: September 21, 2017
9.3K
Evaluation of Helmet Wearing Compliance: A Bionic Spidersense System-Based Method for Helmet Chinstrap Detection
1College of Electromechanical Engineering, Harbin Engineering University, Harbin 150009, China.
Biomimetics (Basel, Switzerland)
|September 26, 2025
Summary
This study introduces a novel, non-intrusive method using MEMS inertial sensors to detect safety helmet chinstrap status. The approach achieves 96% accuracy, enhancing occupational safety in industrial settings.
Area of Science:
- Engineering
- Biomimetics
- Wearable Technology
Background:
- Occupational safety is paramount in industrial intelligence, with safety helmets being crucial personal protective equipment (PPE).
- Real-time detection of helmet chinstrap status is needed, but current methods face challenges like user discomfort and privacy concerns.
- Existing vibration-based detection methods have limitations in capturing spatial characteristics and managing signal complexity.
Purpose of the Study:
- To propose a non-intrusive and privacy-preserving method for detecting safety helmet chinstrap wearing status.
- To emulate spider leg mechanosensory hair functionality using MEMS inertial sensors for helmet monitoring.
- To develop an advanced deep learning model for accurate classification of chinstrap tightness levels.
Main Methods:
- Utilized multiple MEMS inertial sensors to capture posture signals, mimicking spider leg mechanosensory hairs.
- Developed an improved adaptive convolutional neural network (ICNN) integrated with a long short-term memory (LSTM) network.
- Trained and validated the ICNN-LSTM model using data from 20 participants during wall-climbing robot operation tasks.
Main Results:
- The proposed non-intrusive method achieved a high recognition accuracy of 96% for helmet chinstrap wearing status.
- The ICNN-LSTM model effectively classified chinstrap tightness levels using both single-sensor and multi-sensor data.
- Demonstrated the efficacy of the biomimetic approach in addressing limitations of conventional detection techniques.
Conclusions:
- The developed method offers a practical, privacy-preserving, and highly effective solution for monitoring safety helmet usage.
- This research provides a significant advancement in ensuring occupational safety through intelligent PPE monitoring.
- The biomimetic sensor emulation and deep learning integration represent a novel approach to wearable safety technology.
