Package Leak Detection Based on Aperiodic Anomaly Extraction

Muramatsu, Hisayoshi; Kakimi, Yuta; Takeuchi, Issei; Katsura, Seiichiro

doi:10.1109/jestie.2021.3056692

Cited by 4 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anomaly detection has been extensively used in a wide variety of applications such as cyber-intrusion detection [31], fraud detection [32], medical anomaly detection [33,34], industrial damage detection [35], hyperspectral image analysis [36], sensor networks [37], image processing [38], to cite just a few. Outlier detection is very popular in industrial applications [39][40][41][42][43] since it is critical to the efficient and secure operation of industrial equipment, integrated sensors, and the overall production process. Many industrial real problems focus on finding outliers from time series, i.e., data depending on time [29,[44][45][46][47][48].…”

Section: Related Workmentioning

confidence: 99%

Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

et al. 2021

View full text Add to dashboard Cite

The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging to the reservoir computing (RC) category and, as we believe, it also extends the extreme learning machines (ELM) domain. Furthermore, BBS-ESN performs binary block-based online training using fixed and minimal computational complexity to achieve low power consumption and deployability on an off-the-shelf micro-controller (MCU). This has been achieved through binarization of the images and 1-bit quantization of the network weights and activations. 3D rendering has been used to generate a novel publicly available dataset of photo-realistic images similar to those potentially acquired by image sensors on the field while monitoring the junction, without and with oil leaks. Extensive experimentation has been conducted using a STM32H743ZI2 MCU running at 480 MHz and the results achieved show an accurate identification of anomalies, with a reduced computational cost per image and memory occupancy. Based on the obtained results, we conclude that BBS-ESN is feasible on off-the-shelf 32 bit MCUs. Moreover, the solution is also scalable in the number of image cameras to be deployed and to achieve accurate and fast oil leak detections from different viewpoints.

show abstract

Section: Related Workmentioning

confidence: 99%

Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Hence, the aperiodic-pass filter is also capable of eliminating the harmonics instead of the comb filters. Previously, it was used to improve the robustness of the anomaly detection performance against disturbances for food package leak detection [10].…”

Section: Introductionmentioning

confidence: 99%

Harmonics Elimination by Periodic/Aperiodic Separation Filter for Chatter Detection

Muramatsu

Yamato

2023

Transactions of ISCIE

Self Cite

View full text Add to dashboard Cite

Process harmonics often need to be eliminated for accurate regenerative chatter diagnosis. To eliminate the harmonics with many band-stop characteristics, this paper uses a periodic/aperiodic separation filter (PASF) and proposes a chatter detection algorithm based on the PASF. The PASF can design the cutoff frequency and time constant, directly, and the high-order PASF improves the harmonics elimination performance without deteriorating chatter signal extraction performance. The experiments validated the proposed algorithm under several conditions of spindle speeds, cutting types, thresholds, and cutoff frequencies. Their results showed the robustness of the proposed chatter detection algorithm against the threshold selection and change of cutting conditions.

show abstract

“…The proposed high-order IIR and FIR realization improves the separation performance of the PASF, and the proposed KF-PASF realizes the prediction and estimation of the states under noise. Furthermore, the proposed realization and KF-PASF are expected to improve the precision of the periodic/aperiodic separation control for robots (Muramatsu and Katsura (2020)); improve the accuracy of the aperiodic anomaly detection (Muramatsu et al (2021)); and eliminate harmonics noise similar to and better than the comb filters.…”

Section: Introductionmentioning

confidence: 99%

Separation and Estimation of Periodic/Aperiodic State

Muramatsu

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Periodicity and aperiodicity can exist in a state simultaneously and typically become quasi-periodicity and quasi-aperiodicity in a dynamically changing state. The quasi-periodic and quasi-aperiodic states existing in the periodic/aperiodic state mostly correspond to different phenomena and require different controls. For separation control of these states, this paper defines the periodic/aperiodic, quasi-periodic, and quasi-aperiodic states to construct a periodic/aperiodic separation filter that separates the periodic/aperiodic state into the quasi-periodic and quasi-aperiodic states. Based on these definitions, the linearity of periodic-pass and aperiodic-pass functions and the orthogonality of quasi-periodic and quasi-aperiodic state functions are proved. Subsequently, the periodic/aperiodic separation filter composed of periodic-pass and aperiodic-pass filters that realize the periodic-pass and aperiodic-pass functions is designed and integrated with a Kalman filter for estimation of the quasiperiodic and quasi-aperiodic states.

show abstract

Package Leak Detection Based on Aperiodic Anomaly Extraction

Cited by 4 publications

References 26 publications

Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

Online Learning of Oil Leak Anomalies in Wind Turbines with Block-Based Binary Reservoir

Harmonics Elimination by Periodic/Aperiodic Separation Filter for Chatter Detection

Separation and Estimation of Periodic/Aperiodic State

Contact Info

Product

Resources

About