Sensor fault detection by sparsity optimization

Li, Bingxuan; Yu, Hao; Dauwels, Justin; Low, Kay Soon

doi:10.1109/icassp.2014.6855081

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study we focus our attention on the permanent faults characterized by continuity of the fault signature occurrence leading to an observable pattern that we can learn over time [38]. A quiet general model for the multiple faults case [62], [57] is given by:…”

Section: Assumptionsmentioning

confidence: 99%

“…, xt I +L ] the sensors measurements and their predictions over the SFI integration time, respectively. It is however not clear how to properly select the regularization parameter η to mitigate the risk of incurring in miss-classification of the faulty sensors [57]. The authors in [57], introduced an algorithm to determine the regularization parameter automatically from the data based on a bootstrap approach, also known as BINCO method [47].…”

Section: A Greedy Approach To the Sfi Problemmentioning

confidence: 99%

See 1 more Smart Citation

A Scalable Algorithm for Identifying Multiple-Sensor Faults Using Disentangled RNNs

Haldimann¹,

Guerriero

Maret

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

The problem of detecting and identifying sensor faults is critical for efficient, safe, regulatory-compliant and sustainable operations of modern systems. Their increasing complexity brings new challenges for the Sensor Fault Detection and Isolation (SFD-SFI) tasks. One of the key enablers for any SFD-SFI methods employed in modern complex sensor systems, is the so-called analytical redundancy, which is nothing but building an analytical model of the sensors observations (either derived from first principles or identified from historical data in a data-driven fashion). In a nutshell, SFD amounts to generate and to monitor residuals by comparing the sensor measurements with the model predictions with the idea that the faulty sensors will result in large residuals (i.e. the defective sensors generate measurement that are inconsistent with their expected behavior represented by the model). In this paper we introduce a disentangled Recurrent Neural Network (RNN) with the objective to cope with the smearing-out effect, i.e. the propagation of a sensor fault to the non-faulty sensors resulting in large misleading residuals. Moreover, the introduction of a probabilistic model for the residual generation allows us to develop a novel procedure for the identification of the faulty sensors. The computational complexity of the proposed algorithm is linear in the number of sensors as opposed to the combinatorial nature of the SFI problem. Finally, we empirically verify the performances of the proposed SFD-SFI architecture using a real data set collected at a petrochemical plant.

show abstract

Section: Assumptionsmentioning

confidence: 99%

Section: A Greedy Approach To the Sfi Problemmentioning

confidence: 99%

A Scalable Algorithm for Identifying Multiple-Sensor Faults Using Disentangled RNNs

Haldimann¹,

Guerriero

Maret

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Some attempts have been made by the author starting from the basic DC circuit using the L1 norm optimization method in [105] and the result shows that the method is efficient and could be analysed with the standard tools in statistics. Due to time constrain this research remains in the initial phase.…”

mentioning

confidence: 99%

Parameter monitoring for degradation and fault detection of DC-DC converter in a satellite power supply system

Li¹

View full text Add to dashboard Cite

Once injected into the orbit, the satellites operate in space all the time and they are exposed under very harsh space environment such as extreme temperature variation in vacuum condition, radiation etc. As a satellite requires significant amount of investment, it is desired to understand its lifespan and performance degradation before a replacement satellite is launched. The degradation process of an electronic component is strongly related to the thermal, radiation and pressure conditions in the low earth orbit. This research focuses on the degradation and fault monitoring of the electronics components in the DC-DC converters of satellite power system. The main contributions of this research are listed below. Main Contributions

show abstract