Pedestrian Re-identification faces many difficulties in training of supervised model because of limited number of labeled data of surveillance videos. Besides, applications of pedestrian re-identification in pedestrian retrieving and criminal tracking are limited because of the lack of semantic representation. In this paper, a data-driven pedestrian re-identification model based on hierarchical semantic representation is proposed, this model extracting essential features with unsupervised deep learning model and enhancing the semantic representation of features with hierarchical mid-level attributes. Firstly, CNNs, well-trained with the training process of CAEs, is used to extract features of horizontal blocks segmented from unlabeled pedestrian images. Then, these features are input into corresponding attribute classifiers to judge whether the pedestrian has the attributes. Lastly, with a table of ‘attributes-classes mapping relations’, final result can be calculated. Our method is proved to significantly outperform the state of the art on the VIPeR and i-LIDS data set in the aspects of accuracy and semanteme.
{"title":"Data-driven and semantic-based pedestrian re-identification","authors":"Fangjie Xu, Keyang Cheng, Kaifa Hui, Jianming Zhang","doi":"10.1109/FSKD.2017.8393408","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393408","url":null,"abstract":"Pedestrian Re-identification faces many difficulties in training of supervised model because of limited number of labeled data of surveillance videos. Besides, applications of pedestrian re-identification in pedestrian retrieving and criminal tracking are limited because of the lack of semantic representation. In this paper, a data-driven pedestrian re-identification model based on hierarchical semantic representation is proposed, this model extracting essential features with unsupervised deep learning model and enhancing the semantic representation of features with hierarchical mid-level attributes. Firstly, CNNs, well-trained with the training process of CAEs, is used to extract features of horizontal blocks segmented from unlabeled pedestrian images. Then, these features are input into corresponding attribute classifiers to judge whether the pedestrian has the attributes. Lastly, with a table of ‘attributes-classes mapping relations’, final result can be calculated. Our method is proved to significantly outperform the state of the art on the VIPeR and i-LIDS data set in the aspects of accuracy and semanteme.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123000243","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393136
Zhaoyu Shou, Simin Li
As one of the most important research problems of data analytics and data mining, outlier detection from large datasets has drawn many research attentions in recent years. In this paper, we investigate the interesting research problem of summarizing large datasets for supporting efficient local outlier detection. To summarize large datasets, efficient summarization algorithms are proposed which produce a highly compact summary of the original dataset which can be applied to detect local outliers from future similar datasets. A novel automatic parameter optimization method is proposed to produce the optimal setup of the key parameters used in the summarization algorithm. Parallel processing methods are also proposed to accelerate significantly the summarization process. The experimental evaluation results demonstrate that our proposed algorithms are highly scalable for large datasets and effective in producing dataset summary for local outlier detection.
{"title":"Large dataset summarization with automatic parameter optimization and parallel processing for outlier detection","authors":"Zhaoyu Shou, Simin Li","doi":"10.1109/FSKD.2017.8393136","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393136","url":null,"abstract":"As one of the most important research problems of data analytics and data mining, outlier detection from large datasets has drawn many research attentions in recent years. In this paper, we investigate the interesting research problem of summarizing large datasets for supporting efficient local outlier detection. To summarize large datasets, efficient summarization algorithms are proposed which produce a highly compact summary of the original dataset which can be applied to detect local outliers from future similar datasets. A novel automatic parameter optimization method is proposed to produce the optimal setup of the key parameters used in the summarization algorithm. Parallel processing methods are also proposed to accelerate significantly the summarization process. The experimental evaluation results demonstrate that our proposed algorithms are highly scalable for large datasets and effective in producing dataset summary for local outlier detection.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122701455","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8392928
Natanael Nunes de Moura Junior, J. Seixas
In naval warfare operations, several techniques have been developed for passive sonar signal detection and classification. Sonar systems operate over very noisy conditions and, in modern warfare scenario, it might be necessary to classify ships that were not available for the classifier training process. Kernel-based algorithms efficiently access high-order statistics and, because of this, they can be used as preprocessing and classification techniques. Support vector machines (SVMs) are one of most common supervised kernel-based learning models and one of its applications is one-class SVM, which detects events that were generated from the same generating function estimated along the training process. Kernel PCA (kPCA) is kernel-based extension of principal component analysis (PCA). This paper proposes the application of experimental sonar data to one-class SVM model combined with kPCA to detect ships events that were not available in the training process, i.e. novelty class events.
{"title":"Novelty detection in passive sonar systems using a kernel approach","authors":"Natanael Nunes de Moura Junior, J. Seixas","doi":"10.1109/FSKD.2017.8392928","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8392928","url":null,"abstract":"In naval warfare operations, several techniques have been developed for passive sonar signal detection and classification. Sonar systems operate over very noisy conditions and, in modern warfare scenario, it might be necessary to classify ships that were not available for the classifier training process. Kernel-based algorithms efficiently access high-order statistics and, because of this, they can be used as preprocessing and classification techniques. Support vector machines (SVMs) are one of most common supervised kernel-based learning models and one of its applications is one-class SVM, which detects events that were generated from the same generating function estimated along the training process. Kernel PCA (kPCA) is kernel-based extension of principal component analysis (PCA). This paper proposes the application of experimental sonar data to one-class SVM model combined with kPCA to detect ships events that were not available in the training process, i.e. novelty class events.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122811162","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393295
Qiang Wei, Qihong Yang, Zhong Liu
In the environment of non-Gaussian background clutter without target signal distribution parameters, it is difficult to derive the likelihood ratio merit function of traditional multiple frame target detection algorithms. To solve this problem, a dynamic programming MFTD algorithm based on the accumulation model of conditional probability ration is proposed together with the analysis of its performance. In this thesis, problems in the traditional MFTD method have been analyzed. With the maximum of the target's state conditional PDF ratio as the optimal criteria, a recursive accumulation model is established according to this algorithm, which is then locally linearized by Taylor series expansion. And a linearized approximate function is adopted, instead of the likelihood ratio, during the recursive accumulation, so the clutter outliers can be restrained by making use of clutter's feature of distribution, the recursive accumulation equations of MFTD algorithm based on local linearization are derived, under different non-Gaussian distribution. Through simulation experiments, comparisons between the algorithm and the traditional ones are made, which proves that such an algorithm enjoys better detection and tracking performances in the non-Gaussian clutter background.
{"title":"DP-MFTD algorithm based on the conditional probability ratio accumulation model","authors":"Qiang Wei, Qihong Yang, Zhong Liu","doi":"10.1109/FSKD.2017.8393295","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393295","url":null,"abstract":"In the environment of non-Gaussian background clutter without target signal distribution parameters, it is difficult to derive the likelihood ratio merit function of traditional multiple frame target detection algorithms. To solve this problem, a dynamic programming MFTD algorithm based on the accumulation model of conditional probability ration is proposed together with the analysis of its performance. In this thesis, problems in the traditional MFTD method have been analyzed. With the maximum of the target's state conditional PDF ratio as the optimal criteria, a recursive accumulation model is established according to this algorithm, which is then locally linearized by Taylor series expansion. And a linearized approximate function is adopted, instead of the likelihood ratio, during the recursive accumulation, so the clutter outliers can be restrained by making use of clutter's feature of distribution, the recursive accumulation equations of MFTD algorithm based on local linearization are derived, under different non-Gaussian distribution. Through simulation experiments, comparisons between the algorithm and the traditional ones are made, which proves that such an algorithm enjoys better detection and tracking performances in the non-Gaussian clutter background.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122852152","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393046
Ziqi Chen, Bing Li, Bo Han
KNN (K nearest neighbor) algorithm is a widely used regression method, with a very simple principle about neighborhood. Though it achieves success in many application areas, the method has a shortcoming of weighting equal contributions to each attribute when computing distance between instances. In this paper, we applied a weighted KNN approach by using weights obtained from optimization and feature selection methods and compared the performance and efficiency of these two types of algorithms in regression problems. Experiments on two UCI datasets show that optimization algorithms like particle swarm optimization can obtain more valuable weights than feature selection algorithms, such as information gain and RelefF, with the tradeoff of running time cost. Both of them canimprove the performance of traditional KNN with equal feature weights.
{"title":"Improve regression accuracy by using an attribute weighted KNN approach","authors":"Ziqi Chen, Bing Li, Bo Han","doi":"10.1109/FSKD.2017.8393046","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393046","url":null,"abstract":"KNN (K nearest neighbor) algorithm is a widely used regression method, with a very simple principle about neighborhood. Though it achieves success in many application areas, the method has a shortcoming of weighting equal contributions to each attribute when computing distance between instances. In this paper, we applied a weighted KNN approach by using weights obtained from optimization and feature selection methods and compared the performance and efficiency of these two types of algorithms in regression problems. Experiments on two UCI datasets show that optimization algorithms like particle swarm optimization can obtain more valuable weights than feature selection algorithms, such as information gain and RelefF, with the tradeoff of running time cost. Both of them canimprove the performance of traditional KNN with equal feature weights.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131618764","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393378
Y. Xia, Baitong Chen, Wenjin Lu, Frans Coenen, Bailing Zhang
This paper seek answer to question how to search clothing when consumer pays attention to a part of clothing. A novel framework is proposed to solve above problem by attributes. First of all, Fast-RCNN detects person from complex background. Then a Convolutional Neural Network (CNN) is combined with Multi-Task Learning (MTL) to extract features related to attributes. Next Principal Component Analysis (PCA) reduce dimensionality of feature from CNN. Finally, Locality Sensitive Hashing (LSH) searches similar samples in the gallery. Extensive experiments were done on the clothing attribute dataset, experimental results proves this framework is effective.
{"title":"Attributes-oriented clothing description and retrieval with multi-task convolutional neural network","authors":"Y. Xia, Baitong Chen, Wenjin Lu, Frans Coenen, Bailing Zhang","doi":"10.1109/FSKD.2017.8393378","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393378","url":null,"abstract":"This paper seek answer to question how to search clothing when consumer pays attention to a part of clothing. A novel framework is proposed to solve above problem by attributes. First of all, Fast-RCNN detects person from complex background. Then a Convolutional Neural Network (CNN) is combined with Multi-Task Learning (MTL) to extract features related to attributes. Next Principal Component Analysis (PCA) reduce dimensionality of feature from CNN. Finally, Locality Sensitive Hashing (LSH) searches similar samples in the gallery. Extensive experiments were done on the clothing attribute dataset, experimental results proves this framework is effective.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130188336","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393155
Shupeng Gao, Jiaqi Zhong, Yali Cui, Chao Gao, Xianghua Li
Travelling salesman problem (TSP), as a famous combinational optimization problem, has promoted the generation of a large number of algorithms. However, the existing algorithms, such as ant colony optimization (ACO) algorithms, still need to be enhanced further in terms of their robustness and the quality of the solution. In this paper, a novel pheromone initialization (NPI) strategy of ACO algorithms has been proposed for solving TSP, which shows a better efficiency in both robustness and the quality of the solution. Combining NPI strategy with a typical ACO algorithm like ant colony system (ACS) algorithm, a novel algorithm, called NPI-ACS algorithm, is put forward to strengthen the efficiency of ACS. Meanwhile, seven different scale datasets related to TSP are used to estimate the performance of NPI strategy. Afterwards, the experimental results show that there is a remarkable improvement in terms of robustness and the quality of the solution. Moreover, the proposed NPI strategy is flexible enough to be combined with multifarious ACO algorithms for solving TSP because of its independence in operation details.
{"title":"A novel pheromone initialization strategy of ACO algorithms for solving TSP","authors":"Shupeng Gao, Jiaqi Zhong, Yali Cui, Chao Gao, Xianghua Li","doi":"10.1109/FSKD.2017.8393155","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393155","url":null,"abstract":"Travelling salesman problem (TSP), as a famous combinational optimization problem, has promoted the generation of a large number of algorithms. However, the existing algorithms, such as ant colony optimization (ACO) algorithms, still need to be enhanced further in terms of their robustness and the quality of the solution. In this paper, a novel pheromone initialization (NPI) strategy of ACO algorithms has been proposed for solving TSP, which shows a better efficiency in both robustness and the quality of the solution. Combining NPI strategy with a typical ACO algorithm like ant colony system (ACS) algorithm, a novel algorithm, called NPI-ACS algorithm, is put forward to strengthen the efficiency of ACS. Meanwhile, seven different scale datasets related to TSP are used to estimate the performance of NPI strategy. Afterwards, the experimental results show that there is a remarkable improvement in terms of robustness and the quality of the solution. Moreover, the proposed NPI strategy is flexible enough to be combined with multifarious ACO algorithms for solving TSP because of its independence in operation details.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134193623","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393129
Guanghui Lu, Bo Liu, Yanshan Xiao
The effect of behavior recognition has been very good in a fixed angle. However they do not work well in a new angle, in order to solve the limitation of single angle, the paper adopts an effective idea to solve the cross-angle behavior recognition. We propose supervised dictionary learning for cross-angle behavior recognition, which learns a common dictionary to represent the common behavior of the same behavior under different perspectives. This makes the same behavior with similar sparse representation in different perspectives. At the same time we learn a set of characteristic dictionaries to represent the same behavior under different perspectives, so that the sparse representation of the same behavior from different perspectives is distinguished. Finally, obtain the common dictionary and the characteristic dictionary of the same behavior combined with different angles, in order that the behavior can be represented and classified. Experiments show that our proposed method can more effectively solve the cross-angle behavior recognition.
{"title":"Cross-angle behavior recognition via supervised dictionary learning","authors":"Guanghui Lu, Bo Liu, Yanshan Xiao","doi":"10.1109/FSKD.2017.8393129","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393129","url":null,"abstract":"The effect of behavior recognition has been very good in a fixed angle. However they do not work well in a new angle, in order to solve the limitation of single angle, the paper adopts an effective idea to solve the cross-angle behavior recognition. We propose supervised dictionary learning for cross-angle behavior recognition, which learns a common dictionary to represent the common behavior of the same behavior under different perspectives. This makes the same behavior with similar sparse representation in different perspectives. At the same time we learn a set of characteristic dictionaries to represent the same behavior under different perspectives, so that the sparse representation of the same behavior from different perspectives is distinguished. Finally, obtain the common dictionary and the characteristic dictionary of the same behavior combined with different angles, in order that the behavior can be represented and classified. Experiments show that our proposed method can more effectively solve the cross-angle behavior recognition.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115352014","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393059
Shuang Wang, G. Wen, Hua Cai
A complete face recognition system includes four parts: face detection, image preprocessing, feature extraction and face recognition. Feature extraction is a key step in face recognition system. It is a very important problem how to extract features effectively. In the feature extraction phase, the PCA feature extraction method and 2DPCA feature extraction method are studied, and the two methods are compared by experiments. Since the 2DPCA method is used to account for a large memory space, and the embedded system resources are limited, this paper adopts the method of PCA feature extraction. In the face recognition stage, the Euclidean distance is used to calculate the projection points of each face image in the face space to judge which face to be recognized.
{"title":"Feature extraction and face recognition algorithm","authors":"Shuang Wang, G. Wen, Hua Cai","doi":"10.1109/FSKD.2017.8393059","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393059","url":null,"abstract":"A complete face recognition system includes four parts: face detection, image preprocessing, feature extraction and face recognition. Feature extraction is a key step in face recognition system. It is a very important problem how to extract features effectively. In the feature extraction phase, the PCA feature extraction method and 2DPCA feature extraction method are studied, and the two methods are compared by experiments. Since the 2DPCA method is used to account for a large memory space, and the embedded system resources are limited, this paper adopts the method of PCA feature extraction. In the face recognition stage, the Euclidean distance is used to calculate the projection points of each face image in the face space to judge which face to be recognized.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115684708","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 : 2017-07-29DOI: 10.1109/FSKD.2017.8393140
J. Bian, Su Yang, Xiaoyun Sun
The maintenance strategy has an impact on the life cycle cost of power transformers. There are many problems in existing maintenance models, such as neglecting the influence of the overhaul on the reliability or ignoring the relationship between the failure rate and the equivalent age and so on. In the paper, the concept of a variable weight and a retirement age were introduced based on the life cycle cost, and a graphic method based on the variable weight was proposed. The method considered the weight, the cost, the failure rate and other factors. And from the perspective of the life cycle cost and the failure rate, the method was used to select the optimal maintenance scheme. In the end, the comprehensiveness and the feasibility of the method were proved by cases.
{"title":"The optimal maintenance strategy of power transformers based on the life cycle cost","authors":"J. Bian, Su Yang, Xiaoyun Sun","doi":"10.1109/FSKD.2017.8393140","DOIUrl":"https://doi.org/10.1109/FSKD.2017.8393140","url":null,"abstract":"The maintenance strategy has an impact on the life cycle cost of power transformers. There are many problems in existing maintenance models, such as neglecting the influence of the overhaul on the reliability or ignoring the relationship between the failure rate and the equivalent age and so on. In the paper, the concept of a variable weight and a retirement age were introduced based on the life cycle cost, and a graphic method based on the variable weight was proposed. The method considered the weight, the cost, the failure rate and other factors. And from the perspective of the life cycle cost and the failure rate, the method was used to select the optimal maintenance scheme. In the end, the comprehensiveness and the feasibility of the method were proved by cases.","PeriodicalId":236093,"journal":{"name":"2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116105264","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：