Remaining Useful Lifetime Estimation for Power MOSFETs Under Thermal Stress With RANSAC Outlier Removal

Düşmez, Serkan; Heydarzadeh, Mehrdad; Nourani, Mehrdad; Akin, Bilal

doi:10.1109/tii.2017.2665668

Cited by 57 publications

(20 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…be a favorable method for accurate F-matrix calculation [3]. Pragmatically, the method of finding point correspondences results in frequent mistakes in terms of image matching and introduces outliers in the CPPs for the F-matrix estimation [4].…”

Section: Random Sample Consensus (Ransac) Has Been Proved Tomentioning

confidence: 99%

A Deep Learning-Based Semantic Filter for RANSAC-Based Fundamental Matrix Calculation and the ORB-SLAM System

Shao¹,

Zhang²,

Fang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The estimation of a fundamental matrix (F-matrix) from two-view images is a crucial problem in epipolar geometry, and a key point in visual simultaneous localization and mapping (VSLAM). Conventional robust methods proposed by the data calculation space, such as Random Sample Consensus (RANSAC), encounter computational inefficiency and low accuracy when the outliers exceed 50%. In this paper, a semantic filter-based on faster region-based convolutional neural network (faster R-CNN) is proposed to solve the outlier problem in RANSAC based F-matrix calculations. The semantic filter is trained using semantic patches tailored by inliers, providing different semantic labels in various image regions. First, the patches classified into the top three bad labels are filtered out during the pre-processing phase. Second, precise and robust correspondences are determined by the remaining high-level semantic contexts. Finally, the inliers are assessed using RANSAC to produce an accurate F-matrix. The proposed algorithm can improve the accuracy of F-matrix calculations, as low-quality feature correspondences are effectively decreased. Experiments on KITTI and ETH sequences illustrate that the 3D position error can be reduced by applying the semantic filter to the ORB-SLAM system. Further, indoor and real environment experiments demonstrate that an effective lower trajectory error is yielded with the proposed approach.

show abstract

Section: Random Sample Consensus (Ransac) Has Been Proved Tomentioning

confidence: 99%

A Deep Learning-Based Semantic Filter for RANSAC-Based Fundamental Matrix Calculation and the ORB-SLAM System

Shao¹,

Zhang²,

Fang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the papers in this Special Section, the work by Fang et al [1] uses High Frequency (HF) resistance, and Expectation Maximization Particle Filter for the model parameter estimation, in this case for Permanent Magnet Synchronous (PMSM) machines. Dusmez et al [2] use also a model based on measuring or estimating on-state resistance, in this case for MOSFETs. Occasionally detection is based on the forced imposition of operating conditions, so that additional features become evident; a case in point is in [3] where current harmonics are injected to vary the speed, and use the effects to determine the permanent magnet condition.…”

mentioning

confidence: 99%

“…This model can be model based, statistical, [8], through approximation [2], or a linear [1] or nonlinear equation, relating it to the health state of interest. An alternative is that the model can be based on AI, mostly Neural Networks, e.g.…”

mentioning

confidence: 99%

“…In this Special Section there are two papers that indicative of the expanding body of literature in this field. The applications discussed there are the ones that have received the greatest interest so far: power electronics, [2] and bearings, [5]. These two applications have attracted attention because in bearings faults progress relatively slowly and prognosis allows for timely maintenance, while for power electronics, an impending fault, recognized before a failure can allow reconfiguration of the control system.…”

mentioning

confidence: 99%

“…These two applications have attracted attention because in bearings faults progress relatively slowly and prognosis allows for timely maintenance, while for power electronics, an impending fault, recognized before a failure can allow reconfiguration of the control system. The work by Dusmez et al [2] focuses on the estimation of the remaining useful lifetime (RUL) of degraded power MOSFETs, which are stressed by thermal cycling. The authors identify the relative change in on-state resistance as the fault signature.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Guest Editorial Special Section on Advanced Signal and Image Processing Techniques for Electric Machines and Drives Fault Diagnosis and Prognosis

Antonino-Daviu

Lee

Strangas

2017

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Contribution to Health Monitoring of Silicon Carbide MOSFET

Razik

Hologne-Carpentier

Allard

et al. 2021

Applied Condition Monitoring

View full text Add to dashboard Cite

Power converters' usage is expanding ever in industrial ap-plications as they provide flexibility, high level of performances and new functionalities. However, with increased complexity come new constraints with respect to reliability. This chapter covers a study on reliability of a lab-scale power electronic module taken here as a vehicle. The downsizing of converters and new application-related operating constraints are accompanied by an increase in current density. The use of Silicon Car-bide wide-gap technology in power modules is therefore attracting but remains a challenge because this technology is not yet mature and does not benefit from the deep knowledge established about Silicon counter-part. Therefore, health monitoring has naturally emerged as an effective way to implement a reliability assessment. After a brief description of the expected failure modes, an experimental failure monitoring bench will be presented. The choice and implementation of failure indicators through a classification using a neural network will be discussed and presented.

show abstract

Remaining Useful Lifetime Estimation for Power MOSFETs Under Thermal Stress With RANSAC Outlier Removal

Cited by 57 publications

References 32 publications

A Deep Learning-Based Semantic Filter for RANSAC-Based Fundamental Matrix Calculation and the ORB-SLAM System

A Deep Learning-Based Semantic Filter for RANSAC-Based Fundamental Matrix Calculation and the ORB-SLAM System

Guest Editorial Special Section on Advanced Signal and Image Processing Techniques for Electric Machines and Drives Fault Diagnosis and Prognosis

Contribution to Health Monitoring of Silicon Carbide MOSFET

Contact Info

Product

Resources

About