Comparison of CNN and CNN-LSTM Architectures for Tool Wear Estimation

Zegarra, Fabio C.; Vargas-Machuca, Juan; Coronado, Alberto M.

doi:10.1109/eircon52903.2021.9613659

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pooled layer is followed by the fully connected layer. The fully connected layer converts all the feature matrices of the pooled layer into one-dimensional feature vectors, which are generally placed at the end of the CNN structure, and are used to classify the feature matrices after multi-layer convolution pooling [ 28 ]. The process data from the pooling layer to the fully connected layer will be mapped from more to less to reduce the dimension.…”

Section: Voiceprint Signal Preprocessing and Classifiermentioning

confidence: 99%

Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement

Wan

Dong

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

A voiceprint signal as a non-contact test medium has a broad application prospect in power-transformer operation condition monitoring. Due to the high imbalance in the number of fault samples, when training the classification model, the classifier is prone to bias to the fault category with a large number of samples, resulting in poor prediction performance of other fault samples, and affecting the generalization performance of the classification system. To solve this problem, a method of power-transformer fault voiceprint signal diagnosis based on Mixup data enhancement and a convolution neural network (CNN) is proposed. First, the parallel Mel filter is used to reduce the dimension of the fault voiceprint signal to obtain the Mel time spectrum. Then, the Mixup data enhancement algorithm is used to reorganize the generated small number of samples, effectively expanding the number of samples. Finally, CNN is used to classify and identify the transformer fault types. The diagnosis accuracy of this method for a typical unbalanced fault of a power transformer can reach 99%, which is superior to other similar algorithms. The results show that this method can effectively improve the generalization ability of the model and has good classification performance.

show abstract

Section: Voiceprint Signal Preprocessing and Classifiermentioning

confidence: 99%

Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement

Wan

Dong

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In several articles involving time series forecasting, the use of Optuna has been used as an automatic hyper-parameter optimization framework. In [Ekundayo 2020b] Optuna is used to optimize a CNN-LSTM model for predicting residential energy consumption, in [Nishitsuji and Nasseri 2022] it is used to optimize forgetting gates for lithofacies prediction, [Zegarra et al 2021] uses Optuna to optimize LSTM architectures for tool wear estimation, and in [dos Santos Antoniassi 2022] it is used to optimize GRU models for river level prediction in the hydrographic region.…”

Section: Related Workmentioning

confidence: 99%

On the benefits of automated tuning of hyper-parameters: an experiment related to temperature prediction on UAV computers

Maximiano¹,

Júnior²,

Shiguemori³

2022

Anais Do XIX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2022)

View full text Add to dashboard Cite

Finding the best configuration of a neural network to solve a problem has been challenging given the numerous possibilities of values of the hyper-parameters. Thus, tuning of hyper-parameters is one important approach and researchers suggest doing this automatically. However, it is important to verify when it is suitable to perform automated tuning which is usually very costly financially and also in terms of hardware infrastructure. In this study, we analyze the advantages of using a hyper-parameter optimization framework as a way of optimizing the automated search for hyper-parameters of a neural network. To achieve this goal, we used data from an experiment related to temperature prediction of computers embedded in unmanned aerial vehicles (UAVs), and the models Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) to perform these predictions. In addition, we compare the hyper-parameter optimization framework to the hyper-parameter exhaustive search technique varying the size of the training dataset. Results of our experiment shows that designing a model using a hyper-parameter optimizer can be up to 36.02% better than using exhaustive search, in addition to achieving satisfactory results with a reduced dataset.

show abstract

“…Since the convolutional neural network(CNN) was proposed in 2012, the field of trajectory prediction based on deep learning has also ushered in an explosion.In LeCun [11] designed and trained convolutional neural networks based on error gradients and showed a leading performance in some pattern recognition tasks compared with other methods at that time. Hochreiter & Schimidhuber proposed Long Short-Term Memory(LSTM) [12], which effectively solved the problem of gradient explosion and gradien disappearance.In literature [13], a comparison is made between a CNN network and a CNN-LSTM network. Recurrent neural networks are more promising when dealing with large amounts of data.…”

Section: Introductionmentioning

confidence: 99%

Accurate TDOA Localization Based On Trajectory Prediction to Deal With Positioning Nodes Failure

Liu

2022

Preprint

View full text Add to dashboard Cite

The multi-point cooperative TDOA positioning can achieve good positioning accuracy. But when some positioning nodes are blocked or fail, the positioning equation will be unsolved and lead to the failure location algorithm. A TDOA localization algorithm based on trajectory prediction is proposed to deal with the positioning nodes failure. Firstly, based on the target trajectory before the failure of the location node, the trajectory of the target in the next stage is predicted by machine learning. Then the predicted trajectory information is used to estimate the information of the failed node, so as to realize the solution of the TDOA positioning equation. The proposed algorithm is verified through the positioning error analysis comapared with other positioning strategies.

show abstract

Comparison of CNN and CNN-LSTM Architectures for Tool Wear Estimation

Cited by 8 publications

References 10 publications

Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement

Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement

On the benefits of automated tuning of hyper-parameters: an experiment related to temperature prediction on UAV computers

Accurate TDOA Localization Based On Trajectory Prediction to Deal With Positioning Nodes Failure

Contact Info

Product

Resources

About