Subspace Energy Monitoring for Anomaly Detection @Sensor or @Edge

Marchioni, Alex; Mangia, Mauro; Pareschi, Fabio; Rovatti, Riccardo; Setti, Gianluca

doi:10.1109/jiot.2020.2985912

Cited by 16 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eigenvalue strategies compress data by projecting them onto the signal subspace spanned by the directions related to the most energetic components. For example, authors in [18] stressed the potential of PCA for feature compression and reconstruction in the context of predictive maintenance and anomaly detection. These methods show good recovery performances even under significant compression ratios.…”

Section: A Related Workmentioning

confidence: 99%

Model-Assisted Compressed Sensing for Vibration-Based Structural Health Monitoring

Zonzini

Zauli

Mangia

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

The main challenge in the implementation of longlasting vibration monitoring systems is to tackle the constantly evolving complexity of modern 'mesoscale' structures. Thus, the design of energy aware solutions is promoted for the joint optimization of data sampling rates, on-board storage requirements, and communication data payloads.In this context, the present work explores the feasibility of the rakeness-based compressed sensing (Rak-CS) approach to tune the sensing mechanism on the second-order statistics of measured data. In particular, a novel model-assisted variant (MRak-CS) is proposed, which is built on a synthetic derivation of the spectral profile of the structure by pivoting on numerical priors. Moreover, a signal-adapted sparsity basis relying on the Wavelet Packet Transform operator is conceived, which aims at maximizing the signal sparsity while allowing for a precise timefrequency localization.The adopted solutions were tested with experiments performed on a sensorized pinned-pinned steel beam. Results prove that the rakeness-based compression strategies are superior to conventional eigenvalue approaches and to standard CS methods. The achieved compression ratio is equal to 7 and the quality of the reconstructed structural parameters is preserved even in presence of defective configurations.

show abstract

Section: A Related Workmentioning

confidence: 99%

Model-Assisted Compressed Sensing for Vibration-Based Structural Health Monitoring

Zonzini

Zauli

Mangia

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

show abstract

“…VI-A), while it minimizes the network traffic. In addition, it could also be used as a standalone anomaly detection algorithm, as shown in [26], [27]. In particular, we used HPCA for compression in an SHM system composed of many sensors measuring three-axial acceleration and a few gateways (one gateway usually manages 40 to 50 sensors) employed to collect the sensor readings and send them to the cloud platform used for storage and processing.…”

Section: Introductionmentioning

confidence: 99%

Embedded Streaming Principal Components Analysis for Network Load Reduction in Structural Health Monitoring

Burrello

Marchioni

Brunelli

et al. 2021

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

Principal Component Analysis (PCA) is a wellestablished approach commonly used for dimensionality reduction. However, its computational cost and memory requirements hamper the adoption of PCA in heavily resource-constrained embedded platforms. Streaming approaches have been proposed that may enable embedded implementations of the PCA. Among them, the History PCA (HPCA) algorithm stands out for its robustness to the variability in parameters and accuracy. This paper presents a parallel and memory-efficient implementation of HPCA in a structural health monitoring (SHM) application based on a heterogeneous network with sensor nodes measuring three-axial accelerations and gateways collecting measurements from several nodes and sending them to the cloud storage and analytic facility. In the targeted application, standard PCA reaches 15× compression factor with an average reconstruction signal to noise ratio of 16 dB and a negligible impact on the accuracy in the tracking of structural modal frequencies. By embedding HPCA on our SHM network gateways, we achieve the same compression factor as standard PCA, with more than 1000× reduction in data memory footprint for running the algorithm. Furthermore, we parallelize HPCA on the gateway, and we achieve a speedup of 7.1× (on 8 cores). Finally, we explore a fixed-point HPCA implementation on sensors (network end-nodes), that maximally distributes compression workload, minimizes required communication bandwidth, and maintains the same quality of reconstruction as HPCA in floating-point, with a compression factor of 10×.

show abstract

“…Particularly when multiple measurements are available, datadependent transforms exploiting the eigenvalue decomposition (EVD) of the covariance matrix of the data can generally attain an optimum compaction of energy into a lower-dimensional subspace in the sense of the Karhunen-Loeve transform [5]; therefore subspace-based methods have emerged that exploit particular partitioning of the space spanned by eigenvectors of the EVD [6]- [10]. While this work has peaked two decades earlier, developments of energy-based subspace detectors are still afoot [11].…”

Section: Introductionmentioning

confidence: 99%

“…The above methods [2]- [4], [6]- [11] operate on narrowband data and calculate an instantaneous covariance matrix that will only capture phase shifts between elements of the data vector. To address the detection of broadband transient signals, it is possible to operate with tapped delay lines or in frequency bins created by a discrete Fourier transform (DFT), where problems can be treated as narrowband ones.…”

Section: Introductionmentioning

confidence: 99%

Detection of Weak Transient Signals Using a Broadband Subspace Approach

Weiss

Delaosa

Matthews

et al. 2021

2021 Sensor Signal Processing for Defence Conference (SSPD)

View full text Add to dashboard Cite

We investigate the detection of broadband weak transient signals by monitoring a projection of the measurement data onto the noise-only subspace derived from the stationary sources. This projection utilises a broadband subspace decomposition of the data's space-time covariance matrix. The energy in this projected 'syndrome' vector is more discriminative towards the presence or absence of a transient signal than the original data, and can be enhanced by temporal averaging. We investigate the statistics, and indicate in simulations how discrimination can be traded off with the time to reach a decision, as well as with the sample size over which the space-time covariance is estimated.

show abstract

Subspace Energy Monitoring for Anomaly Detection @Sensor or @Edge

Cited by 16 publications

References 44 publications

Model-Assisted Compressed Sensing for Vibration-Based Structural Health Monitoring

Model-Assisted Compressed Sensing for Vibration-Based Structural Health Monitoring

Embedded Streaming Principal Components Analysis for Network Load Reduction in Structural Health Monitoring

Detection of Weak Transient Signals Using a Broadband Subspace Approach

Contact Info

Product

Resources

About