Fault Diagnosis for Power Converters Based on Optimized Temporal Convolutional Network

Gao, Yating; Wu, Wei; Lin, Qiongbin; Cai, Fenghuang; Chai, Qinqin

doi:10.1109/tim.2020.3021110

Cited by 49 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, researchers are dramatically improving deep learning methods or looking for new ones. In 2021, for the first time in [74], another deep learning technique called Temporal Convolutional Network has been introduced and employed to identify and classify OC faults and six unknown faults in a 3-phase voltage inverter.…”

Section: B Literature Review Of Fault Detection In Pessmentioning

confidence: 99%

“…Time-series mode modeling of input data is also not possible using this method. [59] Switch OC and SC [68] Switch OC Back-to-back converter in permanent magnet synchronous generator-based wind generation system [69] Switch SC 5-level neutral-point-clamped voltage source inverter connected to PV integrated microgrid system [70] Switch OC Hybrid active NPC inverter [74] Power There are different types of sensors related to measuring voltage and current, which are classified based on their performance and method of measurement, which the continuation of this section introduces each of them.…”

Section: Routine Of Fault Diagnosis In Pessmentioning

confidence: 99%

See 1 more Smart Citation

Data Mining Applications to Fault Diagnosis in Power Electronic Systems: A Systematic Review

Moradzadeh

Mohammadi‐Ivatloo

Pourhossein

et al. 2022

IEEE Trans. Power Electron.

View full text Add to dashboard Cite

Section: B Literature Review Of Fault Detection In Pessmentioning

confidence: 99%

Section: Routine Of Fault Diagnosis In Pessmentioning

confidence: 99%

Data Mining Applications to Fault Diagnosis in Power Electronic Systems: A Systematic Review

Moradzadeh

Mohammadi‐Ivatloo

Pourhossein

et al. 2022

IEEE Trans. Power Electron.

View full text Add to dashboard Cite

“…Causal convolution can be visually represented in Figure 6. The output at time t is only related to the elements at time t and before in the previous layer [36]. Different from the traditional convolutional neural network, causal convolution cannot see the future data, and it is a one-way structure, not a two-way one.…”

Section: Causal Convolutionsmentioning

confidence: 99%

Attention-TCN-BiGRU: An Air Target Combat Intention Recognition Model

2021

View full text Add to dashboard Cite

The prerequisite for victory in war is the rapid and accurate identification of the tactical intention of the target on the battlefield. The efficiency of manual recognition of the combat intention of air targets is becoming less and less effective with the advent of information warfare. Moreover, if the traditional method of combat intention of air targets is based only on data from a single moment in time, the characteristic information on the time-series data is difficult to capture effectively. In this context, we design a new deep learning method attention mechanism with temporal convolutional network and bidirectional gated recurrent unit (Attention-TCN-BiGRU) to improve the recognition of the combat intent of air targets. Specifically, suitable characteristics are selected based on the combat mission and air posture to construct a characteristic set of air target intentions and encode them into temporal characteristics. Each characteristic in the characteristic set is given an appropriate weight through the attention mechanism. In addition, temporal convolutional network (TCN) is used to mine the data for latent characteristics and bidirectional gated recurrent unit (BiGRU) is used to capture long-term dependencies in the data. Experiments comparing with other methods and ablation demonstrate that Attention-TCN-BiGRU outperforms state-of-the-art methods in terms of accuracy in recognizing target intent in the air.

show abstract

“…The characteristic prediction module is based on the BiGRU network. The historical aerial target operational intention recognition characteristic set V m is used as input, a linear default activation function of the fully connected layer is used to obtain the prediction characteristic set W m , and these two sets are formed into the temporal characteristic data and input to the intention recognition module constructed by the BiGRU-Attention [ 25 ] network. The probability of each intention type is calculated using the softmax function, and the maximum probability intention type label is output as the aerial target combat intention recognition result.…”

Section: Model Frameworkmentioning

confidence: 99%

“…In summary, we use an aerial target combat intention characteristic consisting of a 16-dimensional characteristic vector of {enemy aircraft flight altitude, our aircraft altitude, enemy aircraft flight speed, our aircraft flight speed, enemy aircraft acceleration, our aircraft acceleration, enemy aircraft air combat capability factor, our aircraft air combat capability factor, heading angle, the distance between the two sides, azimuth angle, air-to-air radar status, marine radar status, maneuver type, jamming status, jammed status}, which can be divided into numeric and nonnumeric characteristics, as shown in Figure 4. data and input to the intention recognition module constructed by the BiGRU-Attention [25] network. e probability of each intention type is calculated using the softmax function, and the maximum probability intention type label is output as the aerial target combat intention recognition result.…”

Section: Selection Of Aerial Target Combat Intention Characteristicmentioning

confidence: 99%

A GRU‐Based Method for Predicting Intention of Aerial Targets

Teng

Song

Gang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Since a target’s operational intention in air combat is realized by a series of tactical maneuvers, its state presents the characteristics of temporal and dynamic changes. Depending only on a single moment to take inference, the traditional combat intention recognition method is neither scientific nor effective enough. Based on a gated recurrent unit (GRU), a bidirectional propagation mechanism and attention mechanism are introduced in a proposed aerial target combat intention recognition method. The proposed method constructs an air combat intention characteristic set through a hierarchical approach, encodes into numeric time-series characteristics, and encapsulates domain expert knowledge and experience in labels. It uses a bidirectional gated recurrent units (BiGRU) network for deep learning of air combat characteristics and adaptively assigns characteristic weights using an attention mechanism to improve the accuracy of aerial target combat intention recognition. In order to further shorten the time for intention recognition and with a certain predictive effect, an air combat characteristic prediction module is introduced before intention recognition to establish the mapping relationship between predicted characteristics and combat intention types. Simulation experiments show that the proposed model can predict enemy aerial target combat intention one sampling point ahead of time based on 89.7% intent recognition accuracy, which has reference value and theoretical significance for assisting decision-making in real-time intention recognition.

show abstract

Fault Diagnosis for Power Converters Based on Optimized Temporal Convolutional Network

Cited by 49 publications

References 25 publications

Data Mining Applications to Fault Diagnosis in Power Electronic Systems: A Systematic Review

Data Mining Applications to Fault Diagnosis in Power Electronic Systems: A Systematic Review

Attention-TCN-BiGRU: An Air Target Combat Intention Recognition Model

A GRU‐Based Method for Predicting Intention of Aerial Targets

Contact Info

Product

Resources

About