Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2632/1/012013
Yiming Chen
Abstract Insulators are important components for achieving electrical insulation and mechanical support, but they are prone to various defects in harsh operating environments, which can damage their mechanical strength and insulation performance. This article proposes the Shuffle YOLOv7 model based on the YOLOv7 algorithm for insulator defect detection, aiming to solve the weakness of low precision in traditional object detection algorithms when facing complex backgrounds and small-sized defects. To address the issue of low attention to flashover faults in traditional algorithms, the ShuffleAttention fusion attention mechanism is supplied to concentrate on both intra-channel and inter-channel deep features, and the original PANet structure is replaced with a pyramid which has a bidirectional feature fusion structure to enhance the network’s feature extraction ability. The Focal-EIOU LOSS optimization method focuses on high-quality prior boxes to improve model accuracy, and the effectiveness of the optimization method is verified through ablation experiments. These results of the experiment show that the proposed algorithm achieves varying degrees of performance improvement in terms of precision, recall, average precision, and overall loss compared to mainstream object detection algorithms in detecting insulator damage and flashover.
{"title":"Insulator Defect Detection Method upon Fused Attention Mechanism and Bidirectional Feature Fusion","authors":"Yiming Chen","doi":"10.1088/1742-6596/2632/1/012013","DOIUrl":"https://doi.org/10.1088/1742-6596/2632/1/012013","url":null,"abstract":"Abstract Insulators are important components for achieving electrical insulation and mechanical support, but they are prone to various defects in harsh operating environments, which can damage their mechanical strength and insulation performance. This article proposes the Shuffle YOLOv7 model based on the YOLOv7 algorithm for insulator defect detection, aiming to solve the weakness of low precision in traditional object detection algorithms when facing complex backgrounds and small-sized defects. To address the issue of low attention to flashover faults in traditional algorithms, the ShuffleAttention fusion attention mechanism is supplied to concentrate on both intra-channel and inter-channel deep features, and the original PANet structure is replaced with a pyramid which has a bidirectional feature fusion structure to enhance the network’s feature extraction ability. The Focal-EIOU LOSS optimization method focuses on high-quality prior boxes to improve model accuracy, and the effectiveness of the optimization method is verified through ablation experiments. These results of the experiment show that the proposed algorithm achieves varying degrees of performance improvement in terms of precision, recall, average precision, and overall loss compared to mainstream object detection algorithms in detecting insulator damage and flashover.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"95 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135716771","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2632/1/012005
Jiuxin Hu, Zhihao Pan, Zhiyong Li, Jin Tang
Abstract Registration is a critical task in the field of point clouds, aiming to align data acquired at different times or from different viewpoints for accurate matching. Deep learning methods have made important progress in point cloud registration tasks. However, most existing approaches do not handle the non-overlapping parts of point clouds, resulting in poor performance in low-overlap and noisy scenarios. We propose a registration model called OPSNet, which achieves optimal alignment transformation estimation and overlapping region prediction through an iterative process. OPSNet consists of modules including global feature extraction, overlapping region prediction segmentation, and alignment registration. By utilizing a segmentation algorithm to deal with the non-overlapping parts of data, OPSNet reduces the adverse effects caused by non-overlapping regions in point cloud registration. The model learns feature representations and performs iterative optimization to achieve precise point cloud alignment. We conduct comprehensive experiments on common point cloud registration datasets and compare OPSNet with several classical point cloud registration methods. The experimental results display that OPSNet achieves outstanding performance in terms of rotation and translation errors, outperforming other methods. Additionally, we evaluate the registration performance under different overlap ratios and find that OPSNet can achieve better registration results even in low-overlap scenarios.
{"title":"OPSNet: Point Cloud Registration Based on Overlapping Predictive Segmentation","authors":"Jiuxin Hu, Zhihao Pan, Zhiyong Li, Jin Tang","doi":"10.1088/1742-6596/2632/1/012005","DOIUrl":"https://doi.org/10.1088/1742-6596/2632/1/012005","url":null,"abstract":"Abstract Registration is a critical task in the field of point clouds, aiming to align data acquired at different times or from different viewpoints for accurate matching. Deep learning methods have made important progress in point cloud registration tasks. However, most existing approaches do not handle the non-overlapping parts of point clouds, resulting in poor performance in low-overlap and noisy scenarios. We propose a registration model called OPSNet, which achieves optimal alignment transformation estimation and overlapping region prediction through an iterative process. OPSNet consists of modules including global feature extraction, overlapping region prediction segmentation, and alignment registration. By utilizing a segmentation algorithm to deal with the non-overlapping parts of data, OPSNet reduces the adverse effects caused by non-overlapping regions in point cloud registration. The model learns feature representations and performs iterative optimization to achieve precise point cloud alignment. We conduct comprehensive experiments on common point cloud registration datasets and compare OPSNet with several classical point cloud registration methods. The experimental results display that OPSNet achieves outstanding performance in terms of rotation and translation errors, outperforming other methods. Additionally, we evaluate the registration performance under different overlap ratios and find that OPSNet can achieve better registration results even in low-overlap scenarios.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"93 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135716778","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}
Abstract A dual-axis tracking parabolic trough solar collector, using a certain straight-trough tube, was set up to experimentally investigate the heat collecting performance. An artificial neural network(ANN) model was developed. Experimental data were used to train and predict the mean temperature of Heat transfer fluid in the solar trough collector based on the developed model. The Levenberg-Marquardt (LM) method was also applied to optimize the weights and thresholds for the classic BP Newton algorithm, providing an ANN model with 9 hidden nodes and 30,000 training times. The predicted values are all in good agreement with the experimental data, with a mean relative error of 0.21% and a maximum error of 1.2%. In comparison, the mean relative error of the one-dimensional steady-state model reaches 1.07%. It indicates that the ANN exhibits excellent performance in predicting the export temperature of the solar collector with a specific flow rate of Heat transfer fluid. This ANN model is promising to predict the performance of solar trough collectors under different operating and environmental conditions.
{"title":"Performance Prediction of a Dual-axis Tracking Solar Trough Collector Based on Artificial Neural Network","authors":"Jue Li, Ting Xia, Ruofan Wang, Haijun Chen, Xiran Xu","doi":"10.1088/1742-6596/2636/1/012040","DOIUrl":"https://doi.org/10.1088/1742-6596/2636/1/012040","url":null,"abstract":"Abstract A dual-axis tracking parabolic trough solar collector, using a certain straight-trough tube, was set up to experimentally investigate the heat collecting performance. An artificial neural network(ANN) model was developed. Experimental data were used to train and predict the mean temperature of Heat transfer fluid in the solar trough collector based on the developed model. The Levenberg-Marquardt (LM) method was also applied to optimize the weights and thresholds for the classic BP Newton algorithm, providing an ANN model with 9 hidden nodes and 30,000 training times. The predicted values are all in good agreement with the experimental data, with a mean relative error of 0.21% and a maximum error of 1.2%. In comparison, the mean relative error of the one-dimensional steady-state model reaches 1.07%. It indicates that the ANN exhibits excellent performance in predicting the export temperature of the solar collector with a specific flow rate of Heat transfer fluid. This ANN model is promising to predict the performance of solar trough collectors under different operating and environmental conditions.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"30 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135764055","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2623/1/012021
M Habibbulloh, M Anggaryani, M Satriawan, O Saputra, A Zakaria, F Septiawan
Abstract This study aims to empirically prove the Torricelli equation formula in the case of leaky reservoirs with the help of video tracker analysis. The method used in this research is quantitative descriptive. The experiment was carried out with a simple tool: a 19-liter gallon of water filled with water and dyed, and then three holes were made vertically with different heights. The gallon is filled with water with a constant water level. Next, take a video of each leaking hole. Video is analyzed with Tracker software. Variables observed were the velocity of water exiting from the leak point ( v ), the time it took for water to gush from the leak point to the bottom ( t ), and the horizontal distance from the leak point position to the bottom ( x ). The results obtained based on video analysis with the tracker are that the farther the distance from the surface of the water to the leak point, the farther the horizontal distance of the resulting jet of water will be. This study concludes that theoretical data and experimental data have significant value, so the video analysis tracker software is feasible to use in dynamic and static fluid learning.
{"title":"Suitability of Torricelli’s Theorem Formulation in Cases of Leaking Reservoirs with Video Analysis Tracker","authors":"M Habibbulloh, M Anggaryani, M Satriawan, O Saputra, A Zakaria, F Septiawan","doi":"10.1088/1742-6596/2623/1/012021","DOIUrl":"https://doi.org/10.1088/1742-6596/2623/1/012021","url":null,"abstract":"Abstract This study aims to empirically prove the Torricelli equation formula in the case of leaky reservoirs with the help of video tracker analysis. The method used in this research is quantitative descriptive. The experiment was carried out with a simple tool: a 19-liter gallon of water filled with water and dyed, and then three holes were made vertically with different heights. The gallon is filled with water with a constant water level. Next, take a video of each leaking hole. Video is analyzed with Tracker software. Variables observed were the velocity of water exiting from the leak point ( v ), the time it took for water to gush from the leak point to the bottom ( t ), and the horizontal distance from the leak point position to the bottom ( x ). The results obtained based on video analysis with the tracker are that the farther the distance from the surface of the water to the leak point, the farther the horizontal distance of the resulting jet of water will be. This study concludes that theoretical data and experimental data have significant value, so the video analysis tracker software is feasible to use in dynamic and static fluid learning.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"20 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135763536","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2623/1/012023
F K A Anggraeni, L Nuraini, A Harijanto, S H B Prastowo, S Subiki, B Supriadi, M Maryani
Abstract Currently, the utilization of technology is needed in education as a learning media. This integration demands digital literacy skills. Hence, this research examines the digital literacy skills of Physics Education students at Jember University. This research is descriptive research with data collection methods using questionnaires. Analyzing the questionnaire results follows descriptive analysis techniques. The research findings indicate that students display good digital literacy skills in terms of operational abilities, excellent critical understanding skills, and satisfactory communication skills through media. Therefore, Physics Education students at Jember University possess good digital literacy when utilizing digital-based learning media.
{"title":"Student Digital Literacy Analysis in Physics Learning Through Implementation Digital-Based Learning Media","authors":"F K A Anggraeni, L Nuraini, A Harijanto, S H B Prastowo, S Subiki, B Supriadi, M Maryani","doi":"10.1088/1742-6596/2623/1/012023","DOIUrl":"https://doi.org/10.1088/1742-6596/2623/1/012023","url":null,"abstract":"Abstract Currently, the utilization of technology is needed in education as a learning media. This integration demands digital literacy skills. Hence, this research examines the digital literacy skills of Physics Education students at Jember University. This research is descriptive research with data collection methods using questionnaires. Analyzing the questionnaire results follows descriptive analysis techniques. The research findings indicate that students display good digital literacy skills in terms of operational abilities, excellent critical understanding skills, and satisfactory communication skills through media. Therefore, Physics Education students at Jember University possess good digital literacy when utilizing digital-based learning media.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"25 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135763652","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2636/1/012041
Zile Jia, Dan Liu, Hao Sun, Meng Zhao, Xingbo Lan
Abstract The finned tube heat exchanger is the core component of the flue gas waste heat utilization system. In order to optimize and control the heat transfer efficiency of the heat exchanger in real time under smart heating conditions, we use the entransy dissipation thermal resistance as a kernel index to assess its heat exchange performance, and Trnsys simulation software is employed to figure out the influence of heat exchanger operating parameters (flue gas inlet velocity) and fin structure parameters (fin height, fin pitch) on heat exchanger heat transfer characteristics. The results show that in a reasonable range, increasing the flue gas inlet velocity can decrease the irreversible loss of heat transfer, obviously improving the heat transfer effect. The pitch and height of the fin also have a large impact on the performance of heat transfer. To significantly promote the performance of the heat exchanger, it is useful to reduce the pitch of the fin and increase the fin height within a reasonable range.
{"title":"Study on hydro-thermal coupling heat transfer performance of flue gas-water heat exchanger","authors":"Zile Jia, Dan Liu, Hao Sun, Meng Zhao, Xingbo Lan","doi":"10.1088/1742-6596/2636/1/012041","DOIUrl":"https://doi.org/10.1088/1742-6596/2636/1/012041","url":null,"abstract":"Abstract The finned tube heat exchanger is the core component of the flue gas waste heat utilization system. In order to optimize and control the heat transfer efficiency of the heat exchanger in real time under smart heating conditions, we use the entransy dissipation thermal resistance as a kernel index to assess its heat exchange performance, and Trnsys simulation software is employed to figure out the influence of heat exchanger operating parameters (flue gas inlet velocity) and fin structure parameters (fin height, fin pitch) on heat exchanger heat transfer characteristics. The results show that in a reasonable range, increasing the flue gas inlet velocity can decrease the irreversible loss of heat transfer, obviously improving the heat transfer effect. The pitch and height of the fin also have a large impact on the performance of heat transfer. To significantly promote the performance of the heat exchanger, it is useful to reduce the pitch of the fin and increase the fin height within a reasonable range.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135763659","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2636/1/012011
Huitong Ru, Jisheng Zhao, Yi Sui, Zhe Huang, Zhouyang Chen, Bo Fan, Bo Wang
Abstract For the current problems that economic benefit and energy saving can not be considered in the existing optimal scheduling schemes of wind-solar-diesel-storage system, this paper proposes an optimal scheduling scheme of this system based on multi-objective particle swarm optimization. The mathematical models of active power output of wind turbines, solar turbines and energy storage units of wind-solar-diesel-storage system are established respectively. According to the historical data of wind power generation and photovoltaic power generation, the power prediction data of corresponding prediction models are adopted respectively On this basis, the objective function is constructed by minimizing the operating cost of the system and maximizing the wind-solar consumption ratio, and the system active power, energy storage battery capacity and diesel generator power are taken as constraints Using multi-objective particle swarm optimization algorithm to solve the output of each unit in the system. Simulation results illustrate the optimization scheme can well achieve the target of taking into account both economic benefits and energy saving in the optimal scheduling of wind-solar-diesel-storage system.
{"title":"Research on wind-solar-storage system optimal scheduling based on multi-objective particle swarm algorithm","authors":"Huitong Ru, Jisheng Zhao, Yi Sui, Zhe Huang, Zhouyang Chen, Bo Fan, Bo Wang","doi":"10.1088/1742-6596/2636/1/012011","DOIUrl":"https://doi.org/10.1088/1742-6596/2636/1/012011","url":null,"abstract":"Abstract For the current problems that economic benefit and energy saving can not be considered in the existing optimal scheduling schemes of wind-solar-diesel-storage system, this paper proposes an optimal scheduling scheme of this system based on multi-objective particle swarm optimization. The mathematical models of active power output of wind turbines, solar turbines and energy storage units of wind-solar-diesel-storage system are established respectively. According to the historical data of wind power generation and photovoltaic power generation, the power prediction data of corresponding prediction models are adopted respectively On this basis, the objective function is constructed by minimizing the operating cost of the system and maximizing the wind-solar consumption ratio, and the system active power, energy storage battery capacity and diesel generator power are taken as constraints Using multi-objective particle swarm optimization algorithm to solve the output of each unit in the system. Simulation results illustrate the optimization scheme can well achieve the target of taking into account both economic benefits and energy saving in the optimal scheduling of wind-solar-diesel-storage system.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"31 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135764043","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2623/1/012012
S B A Neswary, B K Prahani, None Marianus, F C Wibowo, R F R Uulaa
Abstract In the 21 st century, students are required to have skills, one of which is Critical Thinking Skill (CTS) in physics learning. Physics aims to master concepts and principles to solve problems by applying critical thinking skills in physics learning. This study aims to analyze the CTS profile of Senior High School (SHS) in physics learning. This current research is pre-research with 107 of 10 th grade students as participants. This research was conducted in a high school in Indonesia. CTS has four indicators: interpretation, analysis, evaluation, and inference. In this study, the CTS profile of high school students in physics learning is still low. The implications of this study can be used as a bridge as clear evidence that the CTS of SHS students in physics learning is still low and needs to be leveled up.
{"title":"A Profile of senior high school student’s critical thinking skills in physics learning","authors":"S B A Neswary, B K Prahani, None Marianus, F C Wibowo, R F R Uulaa","doi":"10.1088/1742-6596/2623/1/012012","DOIUrl":"https://doi.org/10.1088/1742-6596/2623/1/012012","url":null,"abstract":"Abstract In the 21 st century, students are required to have skills, one of which is Critical Thinking Skill (CTS) in physics learning. Physics aims to master concepts and principles to solve problems by applying critical thinking skills in physics learning. This study aims to analyze the CTS profile of Senior High School (SHS) in physics learning. This current research is pre-research with 107 of 10 th grade students as participants. This research was conducted in a high school in Indonesia. CTS has four indicators: interpretation, analysis, evaluation, and inference. In this study, the CTS profile of high school students in physics learning is still low. The implications of this study can be used as a bridge as clear evidence that the CTS of SHS students in physics learning is still low and needs to be leveled up.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"31 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135764045","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2632/1/012014
Ming Ding, Runping Ma
Abstract In view of the long training time for the optimization of the network model parameters of the SELM and the uncertainty of the model generalization ability, this paper proposes an analog circuit fault diagnosis model based on the sailfish algorithm to optimize the stacked kernel extreme learning machine(SKELM). This model introduces a kernel function to build a multi-layer KELM, which can improve the generalization ability and learning speed of the feedforward neural network. The weights of each layer of SKELM are obtained through the automatic encoder training based on the KELM. Since KELM-AE does not need to set initial parameters, the training speed is improved. However, the kernel parameters and regularization coefficients of KELM-AE are set manually, so the sailfish optimizer (SFO) is used to optimize these two parameters, and then the optimal SKELM model is built through layer by layer training. Finally, the Leap frog filter circuit is used as the simulation experiment circuit, and further compared with the optimized SELM. The results show that KELM-AE has strong generalization ability, and it can map fault features to high-dimensional feature space through nonlinear mapping without extracting fault features separately, thus improving the classification accuracy.
{"title":"Fault Diagnosis of Analog Circuits Based on The Sailfish Algorithm Optimized SKELM","authors":"Ming Ding, Runping Ma","doi":"10.1088/1742-6596/2632/1/012014","DOIUrl":"https://doi.org/10.1088/1742-6596/2632/1/012014","url":null,"abstract":"Abstract In view of the long training time for the optimization of the network model parameters of the SELM and the uncertainty of the model generalization ability, this paper proposes an analog circuit fault diagnosis model based on the sailfish algorithm to optimize the stacked kernel extreme learning machine(SKELM). This model introduces a kernel function to build a multi-layer KELM, which can improve the generalization ability and learning speed of the feedforward neural network. The weights of each layer of SKELM are obtained through the automatic encoder training based on the KELM. Since KELM-AE does not need to set initial parameters, the training speed is improved. However, the kernel parameters and regularization coefficients of KELM-AE are set manually, so the sailfish optimizer (SFO) is used to optimize these two parameters, and then the optimal SKELM model is built through layer by layer training. Finally, the Leap frog filter circuit is used as the simulation experiment circuit, and further compared with the optimized SELM. The results show that KELM-AE has strong generalization ability, and it can map fault features to high-dimensional feature space through nonlinear mapping without extracting fault features separately, thus improving the classification accuracy.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135715695","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}
Pub Date : 2023-11-01DOI: 10.1088/1742-6596/2632/1/012001
Xiaoshu Wang, Wei Bai, Kaibei Peng
Abstract It is a significant concern that there is a risk of passenger intrusions at station platform ends. Current detection uses video triggered by single-line radar, but it is ineffective for accurate identification. In this paper, we address this issue by first analyzing the characteristics of intruders at the ends of train platforms. We propose a two-stage filtering-recognition method to achieve intruder detection based on single-line radar point cloud data. In the first stage, we smooth initial point cloud data using a double-chain exponential weighted moving average filter by grouping points. In the second stage, we extract features using the background subtraction method and a critical threshold of point numbers to detect intruder targets. Experimental results demonstrate that this method is effectively capable of detecting intruders at different distances.
{"title":"The algorithm for Detecting Intruders at Station Platform Ends Based on Single-line Radar Point Clouds","authors":"Xiaoshu Wang, Wei Bai, Kaibei Peng","doi":"10.1088/1742-6596/2632/1/012001","DOIUrl":"https://doi.org/10.1088/1742-6596/2632/1/012001","url":null,"abstract":"Abstract It is a significant concern that there is a risk of passenger intrusions at station platform ends. Current detection uses video triggered by single-line radar, but it is ineffective for accurate identification. In this paper, we address this issue by first analyzing the characteristics of intruders at the ends of train platforms. We propose a two-stage filtering-recognition method to achieve intruder detection based on single-line radar point cloud data. In the first stage, we smooth initial point cloud data using a double-chain exponential weighted moving average filter by grouping points. In the second stage, we extract features using the background subtraction method and a critical threshold of point numbers to detect intruder targets. Experimental results demonstrate that this method is effectively capable of detecting intruders at different distances.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":"87 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135716615","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：