Compressive-Sensing-Based Reflectometer for Sparse-Fault Detection in Elevator Belts

Oya, José R. García; Fort, Eduardo Hidalgo; Chavero, Fernando Muñoz; Carvajal, R.G.

doi:10.1109/tim.2020.2970832

“…With the rapid growth of elevator ownership, traditional security warning methods that rely on manual detection, key indicators and statistical analysis no longer meet the practical needs. It's necessary to improve the efficiency and accuracy of elevator security warning through data mining technology [2][3][4]. On the other hand, market or government regulators effectively monitor the operating status of elevators through multiple data sources.…”

Section: Introductionmentioning

confidence: 99%

Tensorial Multi-view Subspace Clustering with Side Constraints for Elevator Security Warning

Xu¹,

Ruan²,

Ni

³

et al. 2023

Preprint

0

View full text Add to dashboard Cite

In recent years, using clustering technology to realize equipment security warning is a research hotspot in the field of data mining applications. However, due to the lack of data fusion mechanism and prior knowledge guidance, the performance of most existing methods is limited when applied to complex equipment such as elevator. In this paper, a novel Tensorial Multi-view Subspace Clustering with Side constraints (TMSCS) is proposed for elevator security warning, which first introduces tensorial multi-view subspace learning to achieve data fusion based on high-order correlation. Secondly, the prior knowledge is formalized as side constraints between samples through adaptive graph learning, where certain elevators is forced to have similar or dissimilar operation status. Thirdly, a unified model combining tensorial multi-view subspace learning and adaptive graph learning is constructed to eliminate the instability caused by phased learning. Furthermore, an efficient optimization algorithm is designed to solve this model. Extensive experiments on several benchmark datasets demonstrate the superiority of our method, and the experimental results on real elevator status datasets demonstrate that our method accurately identifies the operating status of each elevator equipment.

show abstract

“…These benefits lead to groundbreaking achievements in many computer vision applications, e.g., image super-resolution [1], image de-noising [2], image registration [3], etc. Sub-Nyquist sampling and data compression lead to significant time-saving results in fault-detection applications like belts [4], bearing [5], composite materials [6], etc. It can also reduces the hardware requirements for monitoring applications like pipelines [7,8].…”

Section: Introductionmentioning

confidence: 99%

A Real-Time and Robust Neural Network Model for Low-Measurement-Rate Compressed-Sensing Image Reconstruction

Chen,

Song,

Zeng

et al. 2023

Entropy

0

View full text Add to dashboard Cite

Compressed sensing (CS) is a popular data compression theory for many computer vision tasks, but the high reconstruction complexity for images prevents it from being used in many real-world applications. Existing end-to-end learning methods achieved real time sensing but lack theory guarantee for robust reconstruction results. This paper proposes a neural network called RootsNet, which integrates the CS mechanism into the network to prevent error propagation. So, RootsNet knows what will happen if some modules in the network go wrong. It also implements real-time and successfully reconstructed extremely low measurement rates that are impossible for traditional optimization-theory-based methods. For qualitative validation, RootsNet is implemented in two real-world measurement applications, i.e., a near-field microwave imaging system and a pipeline inspection system, where RootsNet easily saves 60% more measurement time and 95% more data compared with the state-of-the-art optimization-theory-based reconstruction methods. Without losing generality, comprehensive experiments are performed on general datasets, including evaluating the key components in RootsNet, the reconstruction uncertainty, quality, and efficiency. RootsNet has the best uncertainty performance and efficiency, and achieves the best reconstruction quality under super low-measurement rates.

show abstract

Tensorial multi-view subspace clustering with side constraints for elevator security warning

Xu,

Ruan,

Ni

et al. 2024

Multimedia Systems

0

View full text Add to dashboard Cite

In recent years, using clustering technology to realize equipment security warning is a research hotspot in the field of data mining applications. However, due to the lack of data fusion mechanism and prior knowledge guidance, the performance of most existing methods is limited when applied to complex equipment such as elevator. In this paper, a novel Tensorial Multi-view Subspace Clustering with Side constraints (TMSCS) is proposed for elevator security warning, which first introduces tensorial multi-view subspace learning to achieve data fusion based on high-order correlation. Secondly, the prior knowledge is formalized as side constraints between samples through adaptive graph learning, where certain elevators is forced to have similar or dissimilar operation status. Thirdly, a unified model combining tensorial multi-view subspace learning and adaptive graph learning is constructed to eliminate the instability caused by phased learning. Furthermore, an efficient optimization algorithm is designed to solve this model. Extensive experiments on several benchmark datasets demonstrate the superiority of our method, and the experimental results on real elevator status datasets demonstrate that our method accurately identifies the operating status of each elevator equipment.

show abstract

Compressive-Sensing-Based Reflectometer for Sparse-Fault Detection in Elevator Belts

Cited by 7 publications

References 10 publications

Tensorial Multi-view Subspace Clustering with Side Constraints for Elevator Security Warning

Tensorial Multi-view Subspace Clustering with Side Constraints for Elevator Security Warning

A Real-Time and Robust Neural Network Model for Low-Measurement-Rate Compressed-Sensing Image Reconstruction

Tensorial multi-view subspace clustering with side constraints for elevator security warning

Contact Info

Product

Resources

About