Pub Date : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9941765
P. Jiang, Xiaodong Wang, Dian Zhang, Jianjun Qi
Reliability acceptance tests are used to qualify product’s reliability, which decides whether the product could be accepted. For highly reliable systems, conventional reliability acceptance tests in standards are not preferred, as the test plans either require long test durations or induce high risks for both producer and consumer, which results from the facts that the methods only use the system test data. Meanwhile, some related reliability data, such as data from subsystem test, are often neglected. To make use of the subsystem data, this paper proposes a reliability acceptance test plan derivation method, to derive system test plans with short test durations while keeping producer and consumer risks low, compared with the conventional RAT plans. A case study is provided to illustrate that when using subsystem test data in deriving system test plans, our proposed method has the potential to reduce the risks and shorten the test duration as well.
{"title":"A Subsystem Data Based Reliability Acceptance Test Plan Derivation Method","authors":"P. Jiang, Xiaodong Wang, Dian Zhang, Jianjun Qi","doi":"10.1109/PHM-Yantai55411.2022.9941765","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9941765","url":null,"abstract":"Reliability acceptance tests are used to qualify product’s reliability, which decides whether the product could be accepted. For highly reliable systems, conventional reliability acceptance tests in standards are not preferred, as the test plans either require long test durations or induce high risks for both producer and consumer, which results from the facts that the methods only use the system test data. Meanwhile, some related reliability data, such as data from subsystem test, are often neglected. To make use of the subsystem data, this paper proposes a reliability acceptance test plan derivation method, to derive system test plans with short test durations while keeping producer and consumer risks low, compared with the conventional RAT plans. A case study is provided to illustrate that when using subsystem test data in deriving system test plans, our proposed method has the potential to reduce the risks and shorten the test duration as well.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"405 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124803948","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942025
Huiqi Ruan, Xingjian Ma, Qingchuan He, Jun Pan
Electro-Hydrostatic Actuators (EHA) are used extensively to produce displacements and high forces in various industrial applications, such as aircraft and ships. The internal leakage of EHA can lead to economic loss and personal injury. Convolutional neural network (CNN) is a basic method of deep learning, which has strong autonomous learning capability. In this paper, a two-dimensional convolutional neural network (2D-CNN) based fault diagnosis method for EHA internal leakage is proposed. Firstly, the one-dimensional pressure signals collected by sensors are converted into two-dimensional signals, and then these two-dimensional signals are directly fed into a 2D-CNN model, features are extracted through convolution and pooling operations, and the model is optimized using the reset learning rate to improve the fault diagnosis accuracy of the model, and then the diagnostic results are output using a classifier. The results of the study show that the accuracy of this method in diagnosing the internal leakage of EHA reaches 95.75% Compared with the traditional 1D-CNN, the accuracy of this method in fault diagnosis has been improved to a large extent.
{"title":"2D-CNN-Based Fault Diagnosis of Internal Leakage in Electro-Hydrostatic Actuators","authors":"Huiqi Ruan, Xingjian Ma, Qingchuan He, Jun Pan","doi":"10.1109/PHM-Yantai55411.2022.9942025","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942025","url":null,"abstract":"Electro-Hydrostatic Actuators (EHA) are used extensively to produce displacements and high forces in various industrial applications, such as aircraft and ships. The internal leakage of EHA can lead to economic loss and personal injury. Convolutional neural network (CNN) is a basic method of deep learning, which has strong autonomous learning capability. In this paper, a two-dimensional convolutional neural network (2D-CNN) based fault diagnosis method for EHA internal leakage is proposed. Firstly, the one-dimensional pressure signals collected by sensors are converted into two-dimensional signals, and then these two-dimensional signals are directly fed into a 2D-CNN model, features are extracted through convolution and pooling operations, and the model is optimized using the reset learning rate to improve the fault diagnosis accuracy of the model, and then the diagnostic results are output using a classifier. The results of the study show that the accuracy of this method in diagnosing the internal leakage of EHA reaches 95.75% Compared with the traditional 1D-CNN, the accuracy of this method in fault diagnosis has been improved to a large extent.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124891604","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942090
Lijuan Zhang
Aiming at the difficulty of users obtaining preschool education network resources, a precise recommendation algorithm of preschool education network resources based on improved decision tree is proposed. The categories of effective information of preschool education network resources are adjusted by improved decision tree, combined with the reconstruction of preschool education network resources, Extract the effective information of preschool education network resources, set the weight threshold of preschool education network resources similarity through the analysis of the similarity of different preschool education network resources in the data set, calculate the weight value, obtain the similarity between preschool education network resources in the data set, obtain the distribution of the similarity between preschool education network resources, and complete the calculation of the similarity value between preschool education network resources, Through user interest modeling, an accurate recommendation algorithm for preschool education network resources is designed. The experimental results show that the accurate recommendation algorithm of preschool education network resources based on improved decision tree has good effect and performance on preschool education network resources recommendation.
{"title":"Accurate Recommendation Algorithm of Preschool Education Network Resources Based on Improved Decision Tree","authors":"Lijuan Zhang","doi":"10.1109/PHM-Yantai55411.2022.9942090","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942090","url":null,"abstract":"Aiming at the difficulty of users obtaining preschool education network resources, a precise recommendation algorithm of preschool education network resources based on improved decision tree is proposed. The categories of effective information of preschool education network resources are adjusted by improved decision tree, combined with the reconstruction of preschool education network resources, Extract the effective information of preschool education network resources, set the weight threshold of preschool education network resources similarity through the analysis of the similarity of different preschool education network resources in the data set, calculate the weight value, obtain the similarity between preschool education network resources in the data set, obtain the distribution of the similarity between preschool education network resources, and complete the calculation of the similarity value between preschool education network resources, Through user interest modeling, an accurate recommendation algorithm for preschool education network resources is designed. The experimental results show that the accurate recommendation algorithm of preschool education network resources based on improved decision tree has good effect and performance on preschool education network resources recommendation.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125075135","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942107
Bingyi Li, X. Jia, Bowen Li
The high-fidelity data (HF) referring to the test data from real experiments can more accurately reflect the real performance indicators of the workpieces for reliability analysis in engineering. Due to the limited cost, enough HF data is difficult to be collected to meet the requirement of reliability analysis. Alternatively, a large amount of low-fidelity (LF) experimental data from simulation experiments can be integrated with HF data to achieve reliability estimates with high precision. Existing literatures have studied this problem and made some progress, but the model is rather complicated and the solving efficiency is limited. Therefore, a new data fusion prediction model on reliability evaluation is introduced by Gaussian process (GP) and Bayesian theory. The key idea is to describe the LF and HF response models, respectively, with the same regression parameter and GP correlation parameter. Furthermore, the joint parameters sampling is adopted to estimate the unknown parameters and predict the reliability based on the hybrid Markov chain Monte Carlo algorithm. It is demonstrated through an illustrative example on the Nonlinear oscillation workpiece that the proposed model and sampling methods are flexible and efficient.
{"title":"A new data fusion prediction model for low-fidelity and high-fidelity data on reliability evaluation based on joint parameters sampling","authors":"Bingyi Li, X. Jia, Bowen Li","doi":"10.1109/PHM-Yantai55411.2022.9942107","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942107","url":null,"abstract":"The high-fidelity data (HF) referring to the test data from real experiments can more accurately reflect the real performance indicators of the workpieces for reliability analysis in engineering. Due to the limited cost, enough HF data is difficult to be collected to meet the requirement of reliability analysis. Alternatively, a large amount of low-fidelity (LF) experimental data from simulation experiments can be integrated with HF data to achieve reliability estimates with high precision. Existing literatures have studied this problem and made some progress, but the model is rather complicated and the solving efficiency is limited. Therefore, a new data fusion prediction model on reliability evaluation is introduced by Gaussian process (GP) and Bayesian theory. The key idea is to describe the LF and HF response models, respectively, with the same regression parameter and GP correlation parameter. Furthermore, the joint parameters sampling is adopted to estimate the unknown parameters and predict the reliability based on the hybrid Markov chain Monte Carlo algorithm. It is demonstrated through an illustrative example on the Nonlinear oscillation workpiece that the proposed model and sampling methods are flexible and efficient.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134319740","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942042
Anqi Shan, Zengqiang Jiang, M. E, Qi Li
Refined maintenance decisions and health management of products is an important research direction in reliability. This study proposes a differentiation maintenance method considering individual random effects in the degradation process under periodic inspection. First, the slowly degradation products are divided into several groups according to the individual degradation differences, and the degradation models are established respectively. On this basis, a reasonable state space and maintenance decision space are constructed, the state transfer probability of the degradation process is solved. The optimal differential maintenance strategy is solved by strategy iteration under the framework of semi-Markov decision process model to minimize the unit expected cost. The GaAs taser degradation case is used as a validation and compared with the repair strategy with a fixed replacement threshold, and it is demonstrated that the proposed grouped repair strategy can reduce the cost. In addition, the effectiveness of the proposed method for newly put-in-use individuals is also verified by simulating new individual extrapolation.
{"title":"A Grouped Semi-Markov Maintenance Strategy Considering Random Effects","authors":"Anqi Shan, Zengqiang Jiang, M. E, Qi Li","doi":"10.1109/PHM-Yantai55411.2022.9942042","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942042","url":null,"abstract":"Refined maintenance decisions and health management of products is an important research direction in reliability. This study proposes a differentiation maintenance method considering individual random effects in the degradation process under periodic inspection. First, the slowly degradation products are divided into several groups according to the individual degradation differences, and the degradation models are established respectively. On this basis, a reasonable state space and maintenance decision space are constructed, the state transfer probability of the degradation process is solved. The optimal differential maintenance strategy is solved by strategy iteration under the framework of semi-Markov decision process model to minimize the unit expected cost. The GaAs taser degradation case is used as a validation and compared with the repair strategy with a fixed replacement threshold, and it is demonstrated that the proposed grouped repair strategy can reduce the cost. In addition, the effectiveness of the proposed method for newly put-in-use individuals is also verified by simulating new individual extrapolation.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129074688","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 : 2022-10-13DOI: 10.1109/phm-yantai55411.2022.9942212
Jing Tang, Bochen Chen, Yuechuan Zhang, Shuhan Lu, Yuping Sun
Rotor broken bar fault is one of the frequent faults in induction motor. The (1-2s)f1 component in motor current is recognized as an useful fault characteristics for the fault. However, due to the slip frequency s is very small the fault component is usually covered by the fundamental. As a result, it is difficult to identify the fault by extracting the (1-2s)f1 characteristic. Therefore, this paper proposes a rotor fault diagnosis method by using the sidebands induced by the space MMF harmonic, which has advantages of being easily implemented. Firstly, the rotor broken bar fault mechanism is analyzed, which shows that manufacturing defect and environmental stress are the main causes for the fault. Then, the space harmonic MMF of the non-sinusoidal distributed stator winding is introduced, which produces a series of fault components in motor current, including (5-6s)f1, (5-4s)f1, (7-6s)f1 and (7-8s)f1 components. Finally, the experiment is performed, and motor currents under different load condition are acquired with sensors, where rotor broken bar fault is injected by drilling a hole in one rotor bar. The experimental results indicate that the analyzed sidebands in motor current are obvious and easily extracted, which can be used to detect the rotor broken bar fault.
{"title":"Rotor broken bar fault diagnosis based on the current harmonic characteristics analysis","authors":"Jing Tang, Bochen Chen, Yuechuan Zhang, Shuhan Lu, Yuping Sun","doi":"10.1109/phm-yantai55411.2022.9942212","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9942212","url":null,"abstract":"Rotor broken bar fault is one of the frequent faults in induction motor. The (1-2s)f1 component in motor current is recognized as an useful fault characteristics for the fault. However, due to the slip frequency s is very small the fault component is usually covered by the fundamental. As a result, it is difficult to identify the fault by extracting the (1-2s)f1 characteristic. Therefore, this paper proposes a rotor fault diagnosis method by using the sidebands induced by the space MMF harmonic, which has advantages of being easily implemented. Firstly, the rotor broken bar fault mechanism is analyzed, which shows that manufacturing defect and environmental stress are the main causes for the fault. Then, the space harmonic MMF of the non-sinusoidal distributed stator winding is introduced, which produces a series of fault components in motor current, including (5-6s)f1, (5-4s)f1, (7-6s)f1 and (7-8s)f1 components. Finally, the experiment is performed, and motor currents under different load condition are acquired with sensors, where rotor broken bar fault is injected by drilling a hole in one rotor bar. The experimental results indicate that the analyzed sidebands in motor current are obvious and easily extracted, which can be used to detect the rotor broken bar fault.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134192250","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 : 2022-10-13DOI: 10.1109/phm-yantai55411.2022.9942015
Sun Xiaohan, Huo Weiwei, Li Ming, Zhu Xulan
There is a general disconnect between reliability analysis and performance analysis in existing studies of servo mechanism performance simulation. This paper integrates reliability principles with performance analysis and carries out joint performance and reliability simulations of servo mechanisms. The article first builds up the motor drive module, motor-screw module, and control algorithm module based on Simulink and forms the servo mechanism performance model. Then, the reliability modeling is carried out for the functional circuit part of the servo mechanism, and the life distribution parameters of the functional circuit are obtained based on Monte Carlo sampling. Finally, the paper injects the functional circuit life distribution into the performance simulation model based on the logical relationship between the structure of the servo mechanism, establishes a joint performance and reliability simulation model of the servo mechanism, and obtains the reliability evaluation results based on the reliability principle.
{"title":"Simulink-based Joint Simulation Method for Servo Mechanism Performance and Reliability","authors":"Sun Xiaohan, Huo Weiwei, Li Ming, Zhu Xulan","doi":"10.1109/phm-yantai55411.2022.9942015","DOIUrl":"https://doi.org/10.1109/phm-yantai55411.2022.9942015","url":null,"abstract":"There is a general disconnect between reliability analysis and performance analysis in existing studies of servo mechanism performance simulation. This paper integrates reliability principles with performance analysis and carries out joint performance and reliability simulations of servo mechanisms. The article first builds up the motor drive module, motor-screw module, and control algorithm module based on Simulink and forms the servo mechanism performance model. Then, the reliability modeling is carried out for the functional circuit part of the servo mechanism, and the life distribution parameters of the functional circuit are obtained based on Monte Carlo sampling. Finally, the paper injects the functional circuit life distribution into the performance simulation model based on the logical relationship between the structure of the servo mechanism, establishes a joint performance and reliability simulation model of the servo mechanism, and obtains the reliability evaluation results based on the reliability principle.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133936134","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942041
Qingkang Wen, Z. Li
Reliability growth is to improve the reliability performance of the system by simulating the reliability evolution of the system during the testing process, which relies on the establishment of reliability models. This paper proposes a reliability growth modeling method based on Bayesian parameter inference. As data continues to be acquired, the distribution can be updated to obtain more accurate reliability parameters. Since the parameter distribution of the model will gradually become more complex during the update process, the parameter distribution is simplified to make its prior and posterior distribution have a conjugate relationship, and the feasibility of the method is verified by simulation experiments.
{"title":"Reliability Growth Model Based on Bayesian Parameter Inference","authors":"Qingkang Wen, Z. Li","doi":"10.1109/PHM-Yantai55411.2022.9942041","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942041","url":null,"abstract":"Reliability growth is to improve the reliability performance of the system by simulating the reliability evolution of the system during the testing process, which relies on the establishment of reliability models. This paper proposes a reliability growth modeling method based on Bayesian parameter inference. As data continues to be acquired, the distribution can be updated to obtain more accurate reliability parameters. Since the parameter distribution of the model will gradually become more complex during the update process, the parameter distribution is simplified to make its prior and posterior distribution have a conjugate relationship, and the feasibility of the method is verified by simulation experiments.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"358 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133228397","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942144
Fanhao Zhou, Kun Yang, Dayang Li, Huimin Gao, Xinfa Shi
Turbine oil is very easy to generate a large number of air bubbles in the process of operation. Air bubbles not only have a great impact on the quality of oil and the operation of machinery, but also have a great impact on the reliability of oil online monitoring, resulting in monitoring data errors. Therefore, it is necessary to analyze the influence of air bubbles in the oil on the monitoring parameters. In this study, the dielectric constant sensor, particle contamination sensor, particle number sensor and viscosity sensor were used to study the changing law of the influence of bubbles on various characteristic parameters of oil, and make a qualitative analysis. And under the experimental conditions, the influence of temperature on the physical and chemical indicators was excluded by the temperature control method. The experimental results show that the number of air bubbles will affect the oil, and the more air bubbles, the worse the performance of the oil.
{"title":"Research on Influence of Turbine Oil Bubbles on Oil Condition Monitoring","authors":"Fanhao Zhou, Kun Yang, Dayang Li, Huimin Gao, Xinfa Shi","doi":"10.1109/PHM-Yantai55411.2022.9942144","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942144","url":null,"abstract":"Turbine oil is very easy to generate a large number of air bubbles in the process of operation. Air bubbles not only have a great impact on the quality of oil and the operation of machinery, but also have a great impact on the reliability of oil online monitoring, resulting in monitoring data errors. Therefore, it is necessary to analyze the influence of air bubbles in the oil on the monitoring parameters. In this study, the dielectric constant sensor, particle contamination sensor, particle number sensor and viscosity sensor were used to study the changing law of the influence of bubbles on various characteristic parameters of oil, and make a qualitative analysis. And under the experimental conditions, the influence of temperature on the physical and chemical indicators was excluded by the temperature control method. The experimental results show that the number of air bubbles will affect the oil, and the more air bubbles, the worse the performance of the oil.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121268605","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 : 2022-10-13DOI: 10.1109/PHM-Yantai55411.2022.9942118
Yanzhi Dong, Lekang Liu, Jiaxin Xu, Guangqi Wan
With the frequent occurrence of smog weather, traffic accidents occur frequently. It poses new challenges to the transportation system. Aiming at the serious fog weather, the paper proposes a YOLO-Demist algorithm based on the homomorphic filter function model which adopted the linear improvements factor em. By using the improved homomorphic filter for image enhancement and the maximum inhibition processing on photographs or videos, the results show that the average detection rate is increased from 66.01% to 83.16%, the detection rate is more stable, and the leakage and error detection rate are significantly improved compared with YOLO-V3. The algorithms run with OpenCV for target detection, and the main objects detected are cars and birds. Compared with HLE (Histogram Equalization), SSR(Single Scale Retinex), and other traditional algorithms, the results show that the algorithm can effectively detect the visual disability of road traffic objects under haze weather and reduce the frequency of traffic accidents under severe weather.
{"title":"Target detection algorithm based on improved homomorphic filter in haze days","authors":"Yanzhi Dong, Lekang Liu, Jiaxin Xu, Guangqi Wan","doi":"10.1109/PHM-Yantai55411.2022.9942118","DOIUrl":"https://doi.org/10.1109/PHM-Yantai55411.2022.9942118","url":null,"abstract":"With the frequent occurrence of smog weather, traffic accidents occur frequently. It poses new challenges to the transportation system. Aiming at the serious fog weather, the paper proposes a YOLO-Demist algorithm based on the homomorphic filter function model which adopted the linear improvements factor em. By using the improved homomorphic filter for image enhancement and the maximum inhibition processing on photographs or videos, the results show that the average detection rate is increased from 66.01% to 83.16%, the detection rate is more stable, and the leakage and error detection rate are significantly improved compared with YOLO-V3. The algorithms run with OpenCV for target detection, and the main objects detected are cars and birds. Compared with HLE (Histogram Equalization), SSR(Single Scale Retinex), and other traditional algorithms, the results show that the algorithm can effectively detect the visual disability of road traffic objects under haze weather and reduce the frequency of traffic accidents under severe weather.","PeriodicalId":315994,"journal":{"name":"2022 Global Reliability and Prognostics and Health Management (PHM-Yantai)","volume":"233 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117002786","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：