Shiue‐Der Lu, Yi‐Hsuan Jiang, Chia‐Chun Wu, Hong-Wei Sian
Faulty gears are a common cause of wind turbine failures. For this sake, this work was developed as a reliable diagnostic tool for wind turbines to improve wind power stability accordingly. A convolutional extension neural network (CENN) was proposed to identify vibration and audio signals captured from a gearbox. According to the status of the contained faulty gears, a gearbox was categorised as one of the three types: (i) broken, (ii) rusty and (iii) a combination of (i) and (ii). It was further assigned one of the three severity levels: mild, moderate and severe. Therefore, there were a total of nine combinations for identification. Captured raw vibration and audio signals were applied to a chaotic synchronisation detector by which 3D chaotic error scatter feature images were generated to train and test the CENN. The recognition rate provided by CENN and the majority rule reached 99.6%, and then slightly fell to 97.4% in a noise robustness test, and consequently CENN outperformed counterparts in terms of the recognition rate and the robustness against noise. Accordingly, multiple gearbox faults can be well diagnosed for the first time in the literature. Finally, this paper concludes with a simplified version of the original proposal.
{"title":"A high‐accuracy and robust diagnostic tool for gearbox faults in wind turbines","authors":"Shiue‐Der Lu, Yi‐Hsuan Jiang, Chia‐Chun Wu, Hong-Wei Sian","doi":"10.1049/tje2.12411","DOIUrl":"https://doi.org/10.1049/tje2.12411","url":null,"abstract":"Faulty gears are a common cause of wind turbine failures. For this sake, this work was developed as a reliable diagnostic tool for wind turbines to improve wind power stability accordingly. A convolutional extension neural network (CENN) was proposed to identify vibration and audio signals captured from a gearbox. According to the status of the contained faulty gears, a gearbox was categorised as one of the three types: (i) broken, (ii) rusty and (iii) a combination of (i) and (ii). It was further assigned one of the three severity levels: mild, moderate and severe. Therefore, there were a total of nine combinations for identification. Captured raw vibration and audio signals were applied to a chaotic synchronisation detector by which 3D chaotic error scatter feature images were generated to train and test the CENN. The recognition rate provided by CENN and the majority rule reached 99.6%, and then slightly fell to 97.4% in a noise robustness test, and consequently CENN outperformed counterparts in terms of the recognition rate and the robustness against noise. Accordingly, multiple gearbox faults can be well diagnosed for the first time in the literature. Finally, this paper concludes with a simplified version of the original proposal.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"48 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141693393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xin He, Wenlu Zhao, Licheng Zhang, Qiushi Zhang, Xinyu Li
Short‐term load forecasting is critical for power system planning and operations, and ensemble forecasting methods for electricity loads have been shown to be effective in obtaining accurate forecasts. However, the weights in ensemble prediction models are usually preset based on the overall performance after training, which prevents the model from adapting in the face of different scenarios, limiting the improvement of prediction performance. In order to improve the accurateness and validity of the ensemble prediction method further, this paper proposes an ensemble deep reinforcement learning approach using Q‐learning dynamic weight assignment to consider local behaviours caused by changes in the external environment. Firstly, the variational mode decomposition is used to reduce the non‐stationarity of the original data by decomposing the load sequence. Then, the recurrent neural network (RNN), long short‐term memory (LSTM), and gated recurrent unit (GRU) are selected as the basic power load predictors. Finally, the optimal weights are ensembled for the three sub‐predictors by the optimal weights generated using the Q‐learning algorithm, and the final results are obtained by combining their respective predictions. The results show that the forecasting capability of the proposed method outperforms all sub‐models and several baseline ensemble forecasting methods.
{"title":"A novel ensemble deep reinforcement learning model for short‐term load forecasting based on Q‐learning dynamic model selection","authors":"Xin He, Wenlu Zhao, Licheng Zhang, Qiushi Zhang, Xinyu Li","doi":"10.1049/tje2.12409","DOIUrl":"https://doi.org/10.1049/tje2.12409","url":null,"abstract":"Short‐term load forecasting is critical for power system planning and operations, and ensemble forecasting methods for electricity loads have been shown to be effective in obtaining accurate forecasts. However, the weights in ensemble prediction models are usually preset based on the overall performance after training, which prevents the model from adapting in the face of different scenarios, limiting the improvement of prediction performance. In order to improve the accurateness and validity of the ensemble prediction method further, this paper proposes an ensemble deep reinforcement learning approach using Q‐learning dynamic weight assignment to consider local behaviours caused by changes in the external environment. Firstly, the variational mode decomposition is used to reduce the non‐stationarity of the original data by decomposing the load sequence. Then, the recurrent neural network (RNN), long short‐term memory (LSTM), and gated recurrent unit (GRU) are selected as the basic power load predictors. Finally, the optimal weights are ensembled for the three sub‐predictors by the optimal weights generated using the Q‐learning algorithm, and the final results are obtained by combining their respective predictions. The results show that the forecasting capability of the proposed method outperforms all sub‐models and several baseline ensemble forecasting methods.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"10 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141703502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to prevent wastage of generated power of renewable resources, the energy storage systems can be utilized in the stand‐alone micro grids to store the excess produced power of the renewable generation units. When the generated power of the renewable resources is less than the required load, the energy storage systems can help to compensate all or part of the power shortage. In the current study, a stand‐alone micro grid including wind and tidal turbines, PV systems, batteries and fuel‐based generation units is considered to supply the required load of the micro grid. The generated power of each dispatch‐able generation units is determined in such a way as to minimize the operating cost. In the operating cost of the micro grid, the operating cost of the fuel‐based generation units and the reliability cost associated to the penalty of the curtailed loads are considered. To calculate the reliability cost of the micro grid, a comprehensive reliability evaluation of the micro grid considering the resource‐dependent failure rates for all composed components is performed. To study the effectiveness of the proposed reliability‐based scheduling approach, the numerical results associated to a stand‐alone micro grid containing wind, tidal, PV and fuel‐based generation units connected to the batteries are given.
{"title":"Optimal scheduling of the stand‐alone micro grids considering the reliability cost","authors":"Ayoub Nargeszar, A. Ghaedi, M. Nafar, M. Simab","doi":"10.1049/tje2.12387","DOIUrl":"https://doi.org/10.1049/tje2.12387","url":null,"abstract":"In order to prevent wastage of generated power of renewable resources, the energy storage systems can be utilized in the stand‐alone micro grids to store the excess produced power of the renewable generation units. When the generated power of the renewable resources is less than the required load, the energy storage systems can help to compensate all or part of the power shortage. In the current study, a stand‐alone micro grid including wind and tidal turbines, PV systems, batteries and fuel‐based generation units is considered to supply the required load of the micro grid. The generated power of each dispatch‐able generation units is determined in such a way as to minimize the operating cost. In the operating cost of the micro grid, the operating cost of the fuel‐based generation units and the reliability cost associated to the penalty of the curtailed loads are considered. To calculate the reliability cost of the micro grid, a comprehensive reliability evaluation of the micro grid considering the resource‐dependent failure rates for all composed components is performed. To study the effectiveness of the proposed reliability‐based scheduling approach, the numerical results associated to a stand‐alone micro grid containing wind, tidal, PV and fuel‐based generation units connected to the batteries are given.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"21 82","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141696446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This research addresses the challenge faced by most existing prediction methods in handling nonlinear data of cables. Furthermore, it proposes a novel power cable monitoring method utilizing UHF‐RFID and deep learning within an edge computing environment, specifically targeting the currently suboptimal wireless monitoring of cables. First, based on edge computing, a power cable monitoring system is designed to migrate the analysis of massive data to the edge of the network to improve the monitoring efficiency. Then, the temperature sensing chip and RFID chip were integrated to design a UHF‐RFID temperature tag, which was fixed at the cable temperature measurement point to achieve passive wireless monitoring of the cable. Finally, the parameters of the GRNN model are optimized using the beetle antennae search algorithm, and the EEMD decomposed data is input into the BAS‐GRNN model for learning to output temperature prediction results. Based on the establishment of an experimental platform, the method was demonstrated, and results showed that the maximum error between the UHF‐RFID temperature tag temperature measurement results and the thermocouple was within 0.3°C, and the average relative error of the proposed method was only 0.01, which can meet the accuracy requirements of actual monitoring of power cables.
{"title":"Power cable monitoring method based on UHF‐RFID and deep learning in edge computing environment","authors":"Xiongfei Gu, Jian Shang, Changlu Shen","doi":"10.1049/tje2.12407","DOIUrl":"https://doi.org/10.1049/tje2.12407","url":null,"abstract":"This research addresses the challenge faced by most existing prediction methods in handling nonlinear data of cables. Furthermore, it proposes a novel power cable monitoring method utilizing UHF‐RFID and deep learning within an edge computing environment, specifically targeting the currently suboptimal wireless monitoring of cables. First, based on edge computing, a power cable monitoring system is designed to migrate the analysis of massive data to the edge of the network to improve the monitoring efficiency. Then, the temperature sensing chip and RFID chip were integrated to design a UHF‐RFID temperature tag, which was fixed at the cable temperature measurement point to achieve passive wireless monitoring of the cable. Finally, the parameters of the GRNN model are optimized using the beetle antennae search algorithm, and the EEMD decomposed data is input into the BAS‐GRNN model for learning to output temperature prediction results. Based on the establishment of an experimental platform, the method was demonstrated, and results showed that the maximum error between the UHF‐RFID temperature tag temperature measurement results and the thermocouple was within 0.3°C, and the average relative error of the proposed method was only 0.01, which can meet the accuracy requirements of actual monitoring of power cables.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141705887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmad Darabi, Fazel Pourmirzaei Deylami, Morteza Sheikhian, Mohammad Ali Taheripour
This article intends to propose a new concept of electric machines that works based on a category of magnetic fluids called “ferrofluids”. For this purpose, a disc‐shaped rotor filled with ferrofluid material is employed instead of a common rotor of an axial‐flux machine, and the conceptual design of the new machine named here “axial‐flux ferrofluid electric machine (FFEM)” is presented. The operation principle of the FFEM is described and a dynamic‐transient model built on the d–q axes equivalent circuits is presented. Simulations are carried out by applying the given model in MATLAB and the results are investigated in different operating conditions. In order to identify the basic parameters and validate the simulation results, a prototype of the FFEM has been designed and manufactured, and some preliminary functional tests have been performed on the prototype. All simulation and experimental results indicate some distinguished excellent performances of the new machine. In the end, it can be stated briefly with some confidence that ferrofluid electric machines can have a high potential for future research and applications in various industries due to the simplicity of the structure, self‐starting capability, ability to work at a wide range of speeds and a flat torque profile.
{"title":"Ferrofluid‐based electrical machines: Conceptualization and experimental evaluation","authors":"Ahmad Darabi, Fazel Pourmirzaei Deylami, Morteza Sheikhian, Mohammad Ali Taheripour","doi":"10.1049/tje2.12408","DOIUrl":"https://doi.org/10.1049/tje2.12408","url":null,"abstract":"This article intends to propose a new concept of electric machines that works based on a category of magnetic fluids called “ferrofluids”. For this purpose, a disc‐shaped rotor filled with ferrofluid material is employed instead of a common rotor of an axial‐flux machine, and the conceptual design of the new machine named here “axial‐flux ferrofluid electric machine (FFEM)” is presented. The operation principle of the FFEM is described and a dynamic‐transient model built on the d–q axes equivalent circuits is presented. Simulations are carried out by applying the given model in MATLAB and the results are investigated in different operating conditions. In order to identify the basic parameters and validate the simulation results, a prototype of the FFEM has been designed and manufactured, and some preliminary functional tests have been performed on the prototype. All simulation and experimental results indicate some distinguished excellent performances of the new machine. In the end, it can be stated briefly with some confidence that ferrofluid electric machines can have a high potential for future research and applications in various industries due to the simplicity of the structure, self‐starting capability, ability to work at a wide range of speeds and a flat torque profile.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"262 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141692694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, deep learning (DL) based dynamic security assessment (DSA) methods have been very successful. However, although a DSA model can be trained well for a specific topology, it often does not perform well for other topologies. Since the topology in real‐world power systems is frequently changing, the performance reduction of DL‐based DSA methods is very serious, which is a challenging and urgent problem. This paper proposes a novel DSA method based on a convolutional neural network (CNN) to solve this problem. In the proposed method, a strong yet simple domain adaptation approach named adaptive batch normalization (AdaBN) is used, which significantly enhances the extensibility and generalizability of the DSA model when the topology changes and eliminates the need to train a large number of models. This approach achieves a deep adaptation effect by modulating the statistics from the source domain to the target domain in all batch normalization layers across the model. Unlike other domain adaptation methods, this method is parameter‐free, requires no additional components, and has advanced performance despite its simplicity. In addition, this paper introduces TGAN‐based data augmentation to deal with the difficulty of costly data collection and labelling. This data augmentation makes the proposed model applicable to small databases. The test results of the proposed method on IEEE 39‐bus and IEEE 118‐bus systems show that this method can evaluate system dynamic security during topology changes and in the face of data noise with high accuracy.
{"title":"A domain adaptation‐based convolutional neural network incorporating data augmentation for power system dynamic security assessment","authors":"Sasan Azad, M. Ameli","doi":"10.1049/tje2.12400","DOIUrl":"https://doi.org/10.1049/tje2.12400","url":null,"abstract":"Recently, deep learning (DL) based dynamic security assessment (DSA) methods have been very successful. However, although a DSA model can be trained well for a specific topology, it often does not perform well for other topologies. Since the topology in real‐world power systems is frequently changing, the performance reduction of DL‐based DSA methods is very serious, which is a challenging and urgent problem. This paper proposes a novel DSA method based on a convolutional neural network (CNN) to solve this problem. In the proposed method, a strong yet simple domain adaptation approach named adaptive batch normalization (AdaBN) is used, which significantly enhances the extensibility and generalizability of the DSA model when the topology changes and eliminates the need to train a large number of models. This approach achieves a deep adaptation effect by modulating the statistics from the source domain to the target domain in all batch normalization layers across the model. Unlike other domain adaptation methods, this method is parameter‐free, requires no additional components, and has advanced performance despite its simplicity. In addition, this paper introduces TGAN‐based data augmentation to deal with the difficulty of costly data collection and labelling. This data augmentation makes the proposed model applicable to small databases. The test results of the proposed method on IEEE 39‐bus and IEEE 118‐bus systems show that this method can evaluate system dynamic security during topology changes and in the face of data noise with high accuracy.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"45 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141697975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yangchun Cheng, Xiangdong Liu, Yufei Sha, Wenzhi Chang, Jiangang Bi
Frequency response analysis is widely used for the offline diagnosis of winding deformations in power transformers. To apply this approach to a working transformer, the magnitude of the response current needs to be measured by using Rogowski coil sensors across a load current. The saturation of the power frequency magnetic field in these current sensors must be prevented to ensure accurate measurement of such small response currents. Here, a method is presented to suppress the power frequency magnetic field using a sensing system including a special connection of three‐phase current sensors based on the sum of the three‐phase power frequency load currents of the transformer being close to zero. Each sensor comprises two secondary coils: a measuring coil and an anti‐saturation coil. The anti‐saturation coils are connected in parallel with one another through small inductors to eliminate the power frequency magnetic field in the cores of the sensors. Theoretical analysis is used to derive a solution for this system. The experimental results verify the proposed method as enabling the sensors to function with a transformer carrying a load current of 2333 A.
频率响应分析被广泛用于电力变压器绕组变形的离线诊断。要将这种方法应用于工作中的变压器，需要使用罗戈夫斯基线圈传感器跨负载电流测量响应电流的大小。必须防止这些电流传感器中的工频磁场饱和，以确保准确测量如此小的响应电流。本文介绍了一种抑制工频磁场的方法，该方法使用的传感系统包括一个特殊连接的三相电流传感器，其基础是变压器的三相工频负载电流之和接近于零。每个传感器包括两个次级线圈：一个测量线圈和一个抗饱和线圈。抗饱和线圈通过小型电感器相互并联，以消除传感器铁芯中的工频磁场。理论分析用于推导该系统的解决方案。实验结果验证了所提出的方法能够使传感器在负载电流为 2333 A 的变压器上正常工作。
{"title":"Power frequency magnetic field interference suppression method for online frequency response analysis of power transformers","authors":"Yangchun Cheng, Xiangdong Liu, Yufei Sha, Wenzhi Chang, Jiangang Bi","doi":"10.1049/tje2.12417","DOIUrl":"https://doi.org/10.1049/tje2.12417","url":null,"abstract":"Frequency response analysis is widely used for the offline diagnosis of winding deformations in power transformers. To apply this approach to a working transformer, the magnitude of the response current needs to be measured by using Rogowski coil sensors across a load current. The saturation of the power frequency magnetic field in these current sensors must be prevented to ensure accurate measurement of such small response currents. Here, a method is presented to suppress the power frequency magnetic field using a sensing system including a special connection of three‐phase current sensors based on the sum of the three‐phase power frequency load currents of the transformer being close to zero. Each sensor comprises two secondary coils: a measuring coil and an anti‐saturation coil. The anti‐saturation coils are connected in parallel with one another through small inductors to eliminate the power frequency magnetic field in the cores of the sensors. Theoretical analysis is used to derive a solution for this system. The experimental results verify the proposed method as enabling the sensors to function with a transformer carrying a load current of 2333 A.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141850516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yutao Yang, Shaolei Zhai, Hansong Tang, Genyue Duan, Liwu Deng
A temporary frequency response test and measurement error prediction method of direct current voltage transformer (DCTV) based on artificial intelligence (AI) is proposed. Firstly, the frequency characteristic of direct current (DC) side voltage of DCTV is analyzed. On this basis, a DCTV transient Frequency Response testing method based on transient alternating current (AC) & DC superposition was developed. Then, the method of voltage sudden change and phase correction is used to achieve transient process DCTV response time testing. Finally, the ant colony optimization (ACO) algorithm was improved by combining an adaptive inertia weight improvement strategy, achieving accurate prediction of the Measurement Error of DCTV. The proposed AI based DCTV transient Frequency Response testing and Measurement Error prediction method were compared and analyzed with the other three methods through simulation experiments. Compared to the other three comparison methods, the maximum transformation error in the evaluation indicators of mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) decreased by 0.006, 0.0119, and 0.0085, respectively, while the maximum phase error decreased by 0.2794, 0.3004, and 0.2823, respectively.
{"title":"Transient frequency response test and measurement error prediction of DCTV based on adaptive inertial weight improved ACO","authors":"Yutao Yang, Shaolei Zhai, Hansong Tang, Genyue Duan, Liwu Deng","doi":"10.1049/tje2.12399","DOIUrl":"https://doi.org/10.1049/tje2.12399","url":null,"abstract":"A temporary frequency response test and measurement error prediction method of direct current voltage transformer (DCTV) based on artificial intelligence (AI) is proposed. Firstly, the frequency characteristic of direct current (DC) side voltage of DCTV is analyzed. On this basis, a DCTV transient Frequency Response testing method based on transient alternating current (AC) & DC superposition was developed. Then, the method of voltage sudden change and phase correction is used to achieve transient process DCTV response time testing. Finally, the ant colony optimization (ACO) algorithm was improved by combining an adaptive inertia weight improvement strategy, achieving accurate prediction of the Measurement Error of DCTV. The proposed AI based DCTV transient Frequency Response testing and Measurement Error prediction method were compared and analyzed with the other three methods through simulation experiments. Compared to the other three comparison methods, the maximum transformation error in the evaluation indicators of mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) decreased by 0.006, 0.0119, and 0.0085, respectively, while the maximum phase error decreased by 0.2794, 0.3004, and 0.2823, respectively.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141705444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ali Al-Naji, G. Khalid, Mustafa F. Mahmood, J. Chahl
Early diagnosis of eye diseases is very important to prevent visual impairment and guide appropriate treatment methods. This paper presents a unique approach that can detect numerous eye diseases automatically. Initially, this approach used the pre‐trained ImageNet models that provides various pre‐trained models for training the acquired data. The existing data sets are composed of 645 data images acquired clinically, represented by two groups of subjects as healthy and others holding the proposed eye defect like cataracts, foreign bodies, glaucoma, subconjunctival haemorrhage, and viral conjunctivitis. Followed by comparisons of the pre‐trained model's coefficients and prediction performance. Later, the first‐class execution model is integrated within the Raspberry Pi staging and the real‐time digital camera detection. The evaluation process used the confusion matrix, model accuracy, precision factor, recall coefficient, F1 score, and the Matthews Correlation Coefficient (MCC). Resulting in the performance of these pre‐trained ImageNet models used in this study represented by 93% (InceptionResNetV2), 90% (MobileNet), 86% (Residual Network ResNet50), 85% (InceptionV3), 78% (Visual Geometry Group VGG19), and 72% (Neural Architecture Search Network NASNetMobile). The results show that the InceptionResNetV2 achieved the highest performance. This proposed approach shows its efficiency and strength by early detection of the subject's unhealthy eyes through real‐time monitoring in the field of ophthalmology.
{"title":"Computer vision for eye diseases detection using pre‐trained deep learning techniques and raspberry Pi","authors":"Ali Al-Naji, G. Khalid, Mustafa F. Mahmood, J. Chahl","doi":"10.1049/tje2.12410","DOIUrl":"https://doi.org/10.1049/tje2.12410","url":null,"abstract":"Early diagnosis of eye diseases is very important to prevent visual impairment and guide appropriate treatment methods. This paper presents a unique approach that can detect numerous eye diseases automatically. Initially, this approach used the pre‐trained ImageNet models that provides various pre‐trained models for training the acquired data. The existing data sets are composed of 645 data images acquired clinically, represented by two groups of subjects as healthy and others holding the proposed eye defect like cataracts, foreign bodies, glaucoma, subconjunctival haemorrhage, and viral conjunctivitis. Followed by comparisons of the pre‐trained model's coefficients and prediction performance. Later, the first‐class execution model is integrated within the Raspberry Pi staging and the real‐time digital camera detection. The evaluation process used the confusion matrix, model accuracy, precision factor, recall coefficient, F1 score, and the Matthews Correlation Coefficient (MCC). Resulting in the performance of these pre‐trained ImageNet models used in this study represented by 93% (InceptionResNetV2), 90% (MobileNet), 86% (Residual Network ResNet50), 85% (InceptionV3), 78% (Visual Geometry Group VGG19), and 72% (Neural Architecture Search Network NASNetMobile). The results show that the InceptionResNetV2 achieved the highest performance. This proposed approach shows its efficiency and strength by early detection of the subject's unhealthy eyes through real‐time monitoring in the field of ophthalmology.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"27 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141709416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hongwen Guo, Xin Liu, Zhuoni Zheng, Zhihao Liu, Xinyu Mei
A method of transmission of highly confidential information in power communication network based on digital watermarking technology is proposed in order to reduce the leakage risk of power information and achieve the purpose of safe transmission of private information. This method establishes the data topology model of power communication network and connects the data receiving and sending terminals. Digital watermarking technology is used to embed digital watermarking in the information to be transmitted, encrypt the private information, and optimize the DES encryption algorithm to encrypt the information twice, so as to realize the safe transmission of information. The experimental results show that the digital watermark embedding rate, DES encryption rate, DES decryption rate and watermark extraction rate of the proposed method are all above 90 Mbps, and the file transfer time of 3965Byte is less than 5s, leakage risk rate and packet loss rate are 0.0001% and 0.006%, respectively, which effectively protects the security of high privacy information in the power communication network and prevents information leakage.
{"title":"Anti‐leakage transmission method of high privacy information in electric power communication network based on digital watermarking technology","authors":"Hongwen Guo, Xin Liu, Zhuoni Zheng, Zhihao Liu, Xinyu Mei","doi":"10.1049/tje2.12403","DOIUrl":"https://doi.org/10.1049/tje2.12403","url":null,"abstract":"A method of transmission of highly confidential information in power communication network based on digital watermarking technology is proposed in order to reduce the leakage risk of power information and achieve the purpose of safe transmission of private information. This method establishes the data topology model of power communication network and connects the data receiving and sending terminals. Digital watermarking technology is used to embed digital watermarking in the information to be transmitted, encrypt the private information, and optimize the DES encryption algorithm to encrypt the information twice, so as to realize the safe transmission of information. The experimental results show that the digital watermark embedding rate, DES encryption rate, DES decryption rate and watermark extraction rate of the proposed method are all above 90 Mbps, and the file transfer time of 3965Byte is less than 5s, leakage risk rate and packet loss rate are 0.0001% and 0.006%, respectively, which effectively protects the security of high privacy information in the power communication network and prevents information leakage.","PeriodicalId":510109,"journal":{"name":"The Journal of Engineering","volume":"95 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141693080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：