2019
DOI: 10.1109/access.2019.2909741
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: The IGBT health evaluation of power semiconductor devices is usually based on the threshold evaluation method, which is usually a single characteristic parameter evaluation system. This kind of evaluation method cannot reflect the internal correlation of the change of multiple characteristic parameters in the deep level. Multi-label classification plays an important role in machine learning and can truly reflect the internal correlation principle of multi-feature parameters. Many studies have proved that multi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 19 publications
0
4
0
Order By: Relevance
“…In the process of robust rope skipping, the data are then preprocessed to acquire the limb key point coordinate data. Because the coordinates of the key locations of body motions are a time series with particular connections, this approach is eventually applied to the analysis of body movements using the algorithm transformation method in the multilabel classification algorithm [24]. According to the aforementioned analysis, the posture analysis issue in the…”
Section: Implementation Of Human Action Multilabel Classification In ...mentioning
confidence: 99%
“…In the process of robust rope skipping, the data are then preprocessed to acquire the limb key point coordinate data. Because the coordinates of the key locations of body motions are a time series with particular connections, this approach is eventually applied to the analysis of body movements using the algorithm transformation method in the multilabel classification algorithm [24]. According to the aforementioned analysis, the posture analysis issue in the…”
Section: Implementation Of Human Action Multilabel Classification In ...mentioning
confidence: 99%
“…Basically, the Naive Bayes algorithm works by calculating the probability that input data belongs to a certain class based on the frequency of occurrence of certain features in the data. (Zhang, H., & Liu, Y. 2021).…”
Section: Naïve Bayes (Nb)mentioning
confidence: 99%
“…Where ∆ i,j k (u+1) are updated parameters, ∆ i,j k (u) are parameters before updated, a j (k) is the learning rate, superscript k is the layer, subscript j is the order number of neurons in this layer, subscript m is the number of groups of input data. The partial derivative of the loss function is obtained by equation (12). ∂…”
Section: Figure 11 Time-series Nonparametric Model Framework For Igbtmentioning
confidence: 99%
“…However, the actual working environment of IGBT can be much more complex. Quan et al [12] proposed a multi-label classification learning model based on ISODATA for the multi-feature parameters of power semiconductor device IGBT, the method is proven that it is better at adapting to the IGBT health classification evaluation than general clustering algorithm. Ma et al [13] proposed a health monitoring method by harnessing the inverter operational characteristics and degradation-sensitive electrical parameters to address the IGBT wire bonding faults.…”
Section: Introductionmentioning
confidence: 99%