This paper presents a new method for specific emitter identification(SEI)using the reparameterization visual geometry group(RepVGG)neural network model and Gramian angular summation field(GASF).It converts in-phase an...This paper presents a new method for specific emitter identification(SEI)using the reparameterization visual geometry group(RepVGG)neural network model and Gramian angular summation field(GASF).It converts in-phase and quadrature(IQ)signals into 2D feature maps,retaining both time and frequency domain features.Compared to residual network 18-layer(ResNet18)and Hilbert transform methods,this approach offers higher accuracy,faster training,and a smaller model size,making it ideal for hardware deployment.展开更多
Marine power-generation diesel engines operate in harsh environments.Their vibration signals are highly complex and the feature information exhibits a non-linear distribution.It is difficult to extract effective featu...Marine power-generation diesel engines operate in harsh environments.Their vibration signals are highly complex and the feature information exhibits a non-linear distribution.It is difficult to extract effective feature information from the network model,resulting in low fault-diagnosis accuracy.To address this problem,we propose a fault-diagnosis method that combines the Gramian angular field(GAF)with a convolutional neural network(CNN).Firstly,the vibration signals are transformed into 2D images by taking advantage of the GAF,which preserves the temporal correlation.The raw signals can be mapped to 2D image features such as texture and color.To integrate the feature information,the images of the Gramian angular summation field(GASF)and Gramian angular difference field(GADF)are fused by the weighted average fusion method.Secondly,the channel attention mechanism and temporal attention mechanism are introduced in the CNN model to optimize the CNN learning mechanism.Introducing the concept of residuals in the attention mechanism improves the feasibility of optimization.Finally,the weighted average fused images are fed into the CNN for feature extraction and fault diagnosis.The validity of the proposed method is verified by experiments with abnormal valve clearance.The average diagnostic accuracy is 98.40%.When−20 dB≤signal-to-noise ratio(SNR)≤20 dB,the diagnostic accuracy of the proposed method is higher than 94.00%.The proposed method has superior diagnostic performance.Moreover,it has a certain anti-noise capability and variable-load adaptive capability.展开更多
To apply the advantages of deep learning in recognizing two-dimensional(2D)images to three-phase inverter fault diagnosis,a threephase inverter fault diagnosis model based on gramian angular field(GAF)combined with co...To apply the advantages of deep learning in recognizing two-dimensional(2D)images to three-phase inverter fault diagnosis,a threephase inverter fault diagnosis model based on gramian angular field(GAF)combined with convolutional neural network(CNN)was proposed.Since the current signals of the inverter in different working states are different,the images formed by the time series encoding are also different,which enables the image recognition technology to be used for time series classification to identify the fault current signal of the inverter.Firstly,the one-dimensional(1D)inverter fault current signal was converted into a 2D image through the GAF.Next,the CNN model suitable for inverter fault diagnosis was input to realize the detection,classification and location of inverter fault.The simulation results show that the recognition accuracy of this method is 99.36%under different noisy data.Compared with other traditional methods,it has higher accuracy and reliability,and stronger anti-noise interference capability and robustness in dealing with noisy data.Therefore,it is an effective fault diagnosis method for inverters.展开更多
In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GA...In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GADF)of multi-channel signal fusion and multi-scale attention residual network(MA-ResNet)was proposed.Firstly,the multi-channel vibration signals were subdivided into various frequency bands using wavelet packet decomposition,and the sensitive channels were selected for signal fusion by doing correlation analysis between the signals of various frequency bands and the surface roughness.Then the fused signals were converted into pictures using GADF image encoding.Finally,the pictures were inputted into the residual network model combining the parallel dilation convolution and attention module for training and verifying the effectiveness of the model performance.The proposed method has a root mean square error of 0.0187,a mean absolute error of 0.0143,and a coefficient of determination of 0.8694 in predicting the surface roughness,which is close to the actual value.Therefore,the proposed method had good engineering significance for high-precision prediction and was conducive to on-line monitoring of surface quality during workpiece processing.展开更多
Candlestick charts display the high,low,opening,and closing prices in a specific period.Candlestick patterns emerge because human actions and reactions are patterned and continuously replicate.These patterns capture i...Candlestick charts display the high,low,opening,and closing prices in a specific period.Candlestick patterns emerge because human actions and reactions are patterned and continuously replicate.These patterns capture information on the candles.According to Thomas Bulkowski’s Encyclopedia of Candlestick Charts,there are 103 candlestick patterns.Traders use these patterns to determine when to enter and exit.Candlestick pattern classification approaches take the hard work out of visually identifying these patterns.To highlight its capabilities,we propose a two-steps approach to recognize candlestick patterns automatically.The first step uses the Gramian Angular Field(GAF)to encode the time series as different types of images.The second step uses the Convolutional Neural Network(CNN)with the GAF images to learn eight critical kinds of candlestick patterns.In this paper,we call the approach GAF-CNN.In the experiments,our approach can identify the eight types of candlestick patterns with 90.7%average accuracy automatically in real-world data,outperforming the LSTM model.展开更多
Electrochemical impedance spectroscopy plays a crucial role in monitoring the state of health of lithium-ion batteries.However,effective feature extraction often relies on limited information and prior knowledge.To ad...Electrochemical impedance spectroscopy plays a crucial role in monitoring the state of health of lithium-ion batteries.However,effective feature extraction often relies on limited information and prior knowledge.To add-ress this issue,this paper presents an innovative approach that utilizes the gramian angular field method to transform raw electrochemical impedance spectroscopy data into image data that is easily recognizable by convolutional neural networks.Subsequently,the convolutional block attention module is integrated with bidirectional gated recurrent unit for state of health prediction.First,convolu-tional block attention module is applied to the electro-chemical impedance spectroscopy image data to enhance key features while suppressing redundant information,thereby effectively extracting representative battery state features.Subsequently,the extracted features are fed into a bidirectional gated recurrent unit network for time series modeling to capture the dynamic changes in battery state of health.Experimental results show a significant im-provement in the accuracy of state of health predictions,highlighting the effectiveness of convolutional block atten-tion module in feature extraction and the advantages of bidirectional gated recurrent unit in time series forecasting.This research provides an attention mechanism-based feature extraction solution for lithium-ion battery health management,demonstrating the extensive application potential of deep learning in battery state monitoring.展开更多
基金supported by the National Natural Science Foundation of China(No.62027801).
文摘This paper presents a new method for specific emitter identification(SEI)using the reparameterization visual geometry group(RepVGG)neural network model and Gramian angular summation field(GASF).It converts in-phase and quadrature(IQ)signals into 2D feature maps,retaining both time and frequency domain features.Compared to residual network 18-layer(ResNet18)and Hilbert transform methods,this approach offers higher accuracy,faster training,and a smaller model size,making it ideal for hardware deployment.
基金supported by the Project of Shanghai Engineering Research Center for Intelligent Operation and Maintenance and Energy Efficiency Monitoring of Ships(No.20DZ2252300),China.
文摘Marine power-generation diesel engines operate in harsh environments.Their vibration signals are highly complex and the feature information exhibits a non-linear distribution.It is difficult to extract effective feature information from the network model,resulting in low fault-diagnosis accuracy.To address this problem,we propose a fault-diagnosis method that combines the Gramian angular field(GAF)with a convolutional neural network(CNN).Firstly,the vibration signals are transformed into 2D images by taking advantage of the GAF,which preserves the temporal correlation.The raw signals can be mapped to 2D image features such as texture and color.To integrate the feature information,the images of the Gramian angular summation field(GASF)and Gramian angular difference field(GADF)are fused by the weighted average fusion method.Secondly,the channel attention mechanism and temporal attention mechanism are introduced in the CNN model to optimize the CNN learning mechanism.Introducing the concept of residuals in the attention mechanism improves the feasibility of optimization.Finally,the weighted average fused images are fed into the CNN for feature extraction and fault diagnosis.The validity of the proposed method is verified by experiments with abnormal valve clearance.The average diagnostic accuracy is 98.40%.When−20 dB≤signal-to-noise ratio(SNR)≤20 dB,the diagnostic accuracy of the proposed method is higher than 94.00%.The proposed method has superior diagnostic performance.Moreover,it has a certain anti-noise capability and variable-load adaptive capability.
文摘To apply the advantages of deep learning in recognizing two-dimensional(2D)images to three-phase inverter fault diagnosis,a threephase inverter fault diagnosis model based on gramian angular field(GAF)combined with convolutional neural network(CNN)was proposed.Since the current signals of the inverter in different working states are different,the images formed by the time series encoding are also different,which enables the image recognition technology to be used for time series classification to identify the fault current signal of the inverter.Firstly,the one-dimensional(1D)inverter fault current signal was converted into a 2D image through the GAF.Next,the CNN model suitable for inverter fault diagnosis was input to realize the detection,classification and location of inverter fault.The simulation results show that the recognition accuracy of this method is 99.36%under different noisy data.Compared with other traditional methods,it has higher accuracy and reliability,and stronger anti-noise interference capability and robustness in dealing with noisy data.Therefore,it is an effective fault diagnosis method for inverters.
基金supported by Shaanxi Province Key Research and Development Plan(No.2023-YBGY-386)Shaanxi Province Key Research and Development Plan(No.2022-JBGS-07).
文摘In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GADF)of multi-channel signal fusion and multi-scale attention residual network(MA-ResNet)was proposed.Firstly,the multi-channel vibration signals were subdivided into various frequency bands using wavelet packet decomposition,and the sensitive channels were selected for signal fusion by doing correlation analysis between the signals of various frequency bands and the surface roughness.Then the fused signals were converted into pictures using GADF image encoding.Finally,the pictures were inputted into the residual network model combining the parallel dilation convolution and attention module for training and verifying the effectiveness of the model performance.The proposed method has a root mean square error of 0.0187,a mean absolute error of 0.0143,and a coefficient of determination of 0.8694 in predicting the surface roughness,which is close to the actual value.Therefore,the proposed method had good engineering significance for high-precision prediction and was conducive to on-line monitoring of surface quality during workpiece processing.
基金Jun-Hao Chen and Yun-Cheng Tsai are supported in part by the Ministry of Science and Technology of Taiwan under grant 108-2218-E-002-050-.
文摘Candlestick charts display the high,low,opening,and closing prices in a specific period.Candlestick patterns emerge because human actions and reactions are patterned and continuously replicate.These patterns capture information on the candles.According to Thomas Bulkowski’s Encyclopedia of Candlestick Charts,there are 103 candlestick patterns.Traders use these patterns to determine when to enter and exit.Candlestick pattern classification approaches take the hard work out of visually identifying these patterns.To highlight its capabilities,we propose a two-steps approach to recognize candlestick patterns automatically.The first step uses the Gramian Angular Field(GAF)to encode the time series as different types of images.The second step uses the Convolutional Neural Network(CNN)with the GAF images to learn eight critical kinds of candlestick patterns.In this paper,we call the approach GAF-CNN.In the experiments,our approach can identify the eight types of candlestick patterns with 90.7%average accuracy automatically in real-world data,outperforming the LSTM model.
文摘Electrochemical impedance spectroscopy plays a crucial role in monitoring the state of health of lithium-ion batteries.However,effective feature extraction often relies on limited information and prior knowledge.To add-ress this issue,this paper presents an innovative approach that utilizes the gramian angular field method to transform raw electrochemical impedance spectroscopy data into image data that is easily recognizable by convolutional neural networks.Subsequently,the convolutional block attention module is integrated with bidirectional gated recurrent unit for state of health prediction.First,convolu-tional block attention module is applied to the electro-chemical impedance spectroscopy image data to enhance key features while suppressing redundant information,thereby effectively extracting representative battery state features.Subsequently,the extracted features are fed into a bidirectional gated recurrent unit network for time series modeling to capture the dynamic changes in battery state of health.Experimental results show a significant im-provement in the accuracy of state of health predictions,highlighting the effectiveness of convolutional block atten-tion module in feature extraction and the advantages of bidirectional gated recurrent unit in time series forecasting.This research provides an attention mechanism-based feature extraction solution for lithium-ion battery health management,demonstrating the extensive application potential of deep learning in battery state monitoring.
