- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE International Conference on Intelligent Transportation Systems (ITSC) - Maui, HI, USA (2018.11.4-2018.11.7)] 2018 21st International Conference on Intelligent Transportation Systems (ITSC) - Real-time Stereo Reconstruction Failure Detection and Correction using Deep Learning
摘要： This paper introduces a stereo reconstruction method that besides producing accurate results in real-time, is capable to detect and conceal possible failures caused by one of the cameras. A classification of stereo camera sensor faults is initially introduced, the most common types of defects being highlighted. We next present a stereo camera failure detection method in which various additional checks are being introduced, with respect to the aforementioned error classification. Furthermore, we propose a novel error correction method based on CNNs (convolutional neural networks) that is capable of generating reliable disparity maps by using prior information provided by semantic segmentation in conjunction with the last available disparity. We highlight the efficiency of our approach by evaluating its performance in various driving scenarios and show that it produces accurate disparities on images from Kitti stereo and raw datasets while running in real-time on a regular GPU.
关键词： error correction,convolutional neural networks,stereo reconstruction,failure detection,semantic segmentation
更新于2025-09-04 15:30:14
-
[IEEE 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) - Atlanta, GA, USA (2018.10.31-2018.11.2)] 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) - New Short Circuit Failure Mechanism for 1.2kV 4H-SiC MOSFETs and JBSFETs
摘要： The short circuit (SC-SOA) capability of power devices is crucial for power systems. In this paper, 1.2 kV SiC MOSFETs and JBSFETs are characterized, and their SC-SOA behavior was tested and analyzed. Due to the lower saturated drain current, the JBSFETs were found to have superior SC-SOA compared with MOSFETs despite the integrated Schottky contact. A new short circuit failure mechanism related to melting of the top Al metallization is proposed based up on non-isothermal TCAD numerical simulations supported with SEM measurements of failed die using Energy Dispersive X-ray Spectroscopy (EDS) analysis.
关键词： JBSFET,Robustness,MOSFET,Reliability,Silicon Carbide,4H-SiC,Failure Mechanism,Short Circuit,Ruggedness
更新于2025-09-04 15:30:14
-
[IEEE 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) - Atlanta, GA, USA (2018.10.31-2018.11.2)] 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) - Short Circuit Ruggedness of New Generation 1.2 kV SiC MOSFETs
摘要： New generations of silicon carbide (SiC) based MOSFETs are commercially available from manufacturers featuring smaller chip size with higher power density demonstrating performance improvement compared to their previous generation counterparts. As the size of the chip is small, the volume available to dissipate energy during short-circuit (SC) like conditions is reduced, leading to increased self-heating of the device. Therefore, the short circuit withstand time (SCWT) is reduced. As a reliability aspect, ruggedness to extreme operating conditions like SC needs to be analyzed for these devices, to improve the design or to design better detection and protection circuits for these MOSFETs when used in specific SC vulnerable applications. In this work, the new third generation 1.2 kV SiC MOSFET from Wolfspeed in a TO-247-4 pin package having a smaller chip size is measured for SC ruggedness. The causes for device failure under different DC-link voltages, gate bias voltages, SC pulse durations and self-heating behavior are analyzed based on the destructive SC tests performed. The device is measured to have an SCWT of 2 μs at a DC-link voltage of 800 V compared to SCWT of 4.5 μs for the second generation 1.2 kV devices with larger chip size and TO-247-3 pin package. The presence of the Kelvin source contact demonstrates higher peak SC currents compared to the same devices without Kelvin source.
关键词： short-circuit ruggedness,SiC MOSFETs,Kelvin source contact,self-heating,failure analysis
更新于2025-09-04 15:30:14
-
[IEEE 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) - Atlanta, GA, USA (2018.10.31-2018.11.2)] 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) - Power Cycling of Commercial SiC MOSFETs
摘要： The robustness under power cycling of three comparable silicon carbide MOSFETs in TO-247 packages from three different manufacturers is investigated, with silicon IGBTs serving as reference. The power cycling method, especially the junction temperature measurement and best practices to ensure its accuracy, is described. The results give insight into reliability and variability as well as aging behavior and failure modes. We ?nd a large variability between samples, both in initial characteristics and measured cycling lifetime, as well as signs of semiconductor device degradation. There is a signi?cant spread in the extent of the variability, in the average and minimum observed lifetime, as well as in the failure mode. Some samples fail quickly due to bond wire defects, some due to semiconductor degradation, while others show very long lifetimes.
关键词： power cycling,SiC MOSFETs,variability,reliability,aging behavior,failure modes
更新于2025-09-04 15:30:14
-
Multivariate Spatio-temporal Solar Generation Forecasting: A Unified Approach to Deal With Communication Failure and Invisible Sites
摘要： Short-term prediction of multivariate dynamical processes evolving over time when data are partially observable is a challenging task. The power from solar resources has reached grid parity and must be predicted based on real-time observations available up to the current time step to ensure efficient power systems operation. However, solar data in the form of a time series generated by a network of sensors are not always available. Invisible solar sites and communication failure are two causes that leave the energy management data acquisition system with an incomplete solar time series, thus leading to inaccurate forecasts. This paper addresses the impact of partially observable measurements on short-term solar power prediction. We present a low-rank tensor learning scheme to predict six-hour-ahead solar power generation. We use actual multivariate spatio-temporal National Renewable Energy Laboratory solar data in the state of Kansas presented in the form of tensors along with a photovoltaic power conversion model. A design of experiments experimental framework has been proposed to evaluate single and joint effects of spatio-temporal partially observable sites and the regulating parameters on forecasting accuracy. Numerical results show the capability of the framework to uncover detailed insight into the forecasting model behavior.
关键词： tensor,design of experiments (DOE),invisible sites,missing data,spatio-temporal prediction,Communication failure
更新于2025-09-04 15:30:14