Improved ICNN-LSTM Model Classification Based on Attitude Sensor Data for Hazardous State Assessment of Magnetic Adhesion Climbing Wall Robots

2024-12-30

AI Summary

To address the critical safety risks of overturning and magnetic detachment in high-altitude operations of magnetically adhered tracked wall-climbing robots, this paper proposes a real-time hazardous-state identification method based on micro-vibration signals acquired from MEMS attitude sensors. To overcome the low sensitivity and poor generalizability of conventional threshold-based criteria, we design a high signal-to-noise ratio (SNR) micro-vibration acquisition strategy and develop an end-to-end temporal classification model that integrates an improved convolutional neural network (ICNN) with LSTM for multi-scale feature extraction and dynamic temporal modeling. Evaluated in realistic climbing scenarios, the proposed method achieves a hazardous-state recognition accuracy of 98.2%, significantly outperforming baseline models including CNN, LSTM, and SVM. This work delivers a deployable intelligent perception solution to enhance the safety and autonomy of magnetically adhered climbing robots.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Natural Language Processing: Safety and Robustness

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Magnetic adhesion tracked climbing robots are widely utilized in high-altitude inspection, welding, and cleaning tasks due to their ability to perform various operations against gravity on vertical or inclined walls. However, during operation, the robot may experience overturning torque caused by its own weight and load, which can lead to the detachment of magnetic plates and subsequently pose safety risks. This paper proposes an improved ICNN-LSTM network classification method based on Micro-Electro-Mechanical Systems (MEMS) attitude sensor data for real-time monitoring and assessment of hazardous states in magnetic adhesion tracked climbing robots. Firstly, a data acquisition strategy for attitude sensors capable of capturing minute vibrations is designed. Secondly, a feature extraction and classification model combining an Improved Convolutional Neural Network (ICNN) with a Long Short-Term Memory (LSTM) network is proposed. Experimental validation demonstrates that the proposed minute vibration sensing method achieves significant results, and the proposed classification model consistently exhibits high accuracy compared to other models. The research findings provide effective technical support for the safe operation of climbing robots

Problem

• Magnetic Adsorption
• Climbing Robot
• Safety Assurance

Innovation

• ICNN-LSTM model
• real-time monitoring
• posture sensors