A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine learning-based real-time tracking for concrete vibration
Abstract Proper concrete vibration is vital to the final quality and durability of concrete structures. There is a lack of objective methods to assess conformance to the requirements of vibration behavior in real time. Based on data fusion and machine learning, we propose a real-time tracking method for concrete vibration effort. The system combines the advantages of an ultra-wideband sensor and inclinometer—a simple structure, reliability, expandability, and low cost. A data processing algorithm and hybrid neural network recognition model are developed to process the data stream, enabling automatic derivation of the indexes related to the vibration effort and achieving active concrete vibration quality control. An evaluation method for the performance of the different vibration tracking systems is established using the error transfer formula. The feasibility and accuracy of the tracking method are experimentally verified. This proposed method provides a quality control tool that helps prevent potential quality problems during vibration.
Highlights A systematic framework is proposed for real-time concrete vibration tracking. The accuracy of the tracking system is verified by the general evaluation method. Two types of sensors are integrated to make the hardware simple and reliable. Four stages of the vibration are characterized to demonstrate the key to tracking. The proposed hybrid neural network achieves 95.5% accuracy on stage recognition.
Machine learning-based real-time tracking for concrete vibration
Abstract Proper concrete vibration is vital to the final quality and durability of concrete structures. There is a lack of objective methods to assess conformance to the requirements of vibration behavior in real time. Based on data fusion and machine learning, we propose a real-time tracking method for concrete vibration effort. The system combines the advantages of an ultra-wideband sensor and inclinometer—a simple structure, reliability, expandability, and low cost. A data processing algorithm and hybrid neural network recognition model are developed to process the data stream, enabling automatic derivation of the indexes related to the vibration effort and achieving active concrete vibration quality control. An evaluation method for the performance of the different vibration tracking systems is established using the error transfer formula. The feasibility and accuracy of the tracking method are experimentally verified. This proposed method provides a quality control tool that helps prevent potential quality problems during vibration.
Highlights A systematic framework is proposed for real-time concrete vibration tracking. The accuracy of the tracking system is verified by the general evaluation method. Two types of sensors are integrated to make the hardware simple and reliable. Four stages of the vibration are characterized to demonstrate the key to tracking. The proposed hybrid neural network achieves 95.5% accuracy on stage recognition.
Machine learning-based real-time tracking for concrete vibration
Quan, Yuhu (author) / Wang, Fenglai (author)
2022-05-08
Article (Journal)
Electronic Resource
English
Real-time tracking of concrete vibration effort for intelligent concrete consolidation
| Online Contents | 2015
Real-time tracking of concrete vibration effort for intelligent concrete consolidation
| British Library Online Contents | 2015