際際滷shows by User: kince / http://www.slideshare.net/images/logo.gif 際際滷shows by User: kince / Fri, 06 Sep 2024 17:22:56 GMT 際際滷Share feed for 際際滷shows by User: kince Joint Autoencoder-Classifier Model for Malfunction Identification and Classification on Marine Diesel Engine Diagnostics Data /slideshow/joint-autoencoder-classifier-model-for-malfunction-identification-and-classification-on-marine-diesel-engine-diagnostics-data/271615955 2022-phme-export-240906172256-cf052eba
Abstract: There has been an increasing demand on marine transportation and traveling, since the voyage of the ships are more economical and efficient than air or land-based alternatives. The propulsion of a ship is provided by a main engine system which includes the shaft, the propellers, and other auxiliary equipment. Marine diesel engine is a complex structure that the faults within these machines can cause malfunction of the whole system, which in turn inhibits the ships mission. It is crucial to monitor the engine and other auxiliary systems during the operation and infer their condition from their diagnostic data. In this study, we analyze monitoring data of a crude oil tanker for different ship loads and conditions. Our primary analysis includes main engine fault detection and classification for which we propose an end-to-end joint autoencoder-classifier model that contains a convolutional autoencoder, and a long-short term memory regressor connected to the latent space. Genetic algorithms optimized models gave us 93.61% accuracy for fault classification task. Further investigation on features contributions to the model, we increased the accuracy up to 96%. One concern about marine transportation is the pollution of the air with greenhouse effect gases. In this study, we have developed NOx and SOx emission estimators for different faults and working conditions. Leveraging ship load, working conditions and engine faults in the models helped us to achieve 50% better estimation performance. Although there are other studies regarding gases emissions in the literature, this is the first study that took engine faults into account. We believe that the joint autoencoder-classifier model will be useful for other time series estimation task on other domains, especially where the operating condition plays a role in the process. https://doi.org/10.36001/phme.2022.v7i1.3335]]>
Abstract: There has been an increasing demand on marine transportation and traveling, since the voyage of the ships are more economical and efficient than air or land-based alternatives. The propulsion of a ship is provided by a main engine system which includes the shaft, the propellers, and other auxiliary equipment. Marine diesel engine is a complex structure that the faults within these machines can cause malfunction of the whole system, which in turn inhibits the ships mission. It is crucial to monitor the engine and other auxiliary systems during the operation and infer their condition from their diagnostic data. In this study, we analyze monitoring data of a crude oil tanker for different ship loads and conditions. Our primary analysis includes main engine fault detection and classification for which we propose an end-to-end joint autoencoder-classifier model that contains a convolutional autoencoder, and a long-short term memory regressor connected to the latent space. Genetic algorithms optimized models gave us 93.61% accuracy for fault classification task. Further investigation on features contributions to the model, we increased the accuracy up to 96%. One concern about marine transportation is the pollution of the air with greenhouse effect gases. In this study, we have developed NOx and SOx emission estimators for different faults and working conditions. Leveraging ship load, working conditions and engine faults in the models helped us to achieve 50% better estimation performance. Although there are other studies regarding gases emissions in the literature, this is the first study that took engine faults into account. We believe that the joint autoencoder-classifier model will be useful for other time series estimation task on other domains, especially where the operating condition plays a role in the process. https://doi.org/10.36001/phme.2022.v7i1.3335]]> Fri, 06 Sep 2024 17:22:56 GMT /slideshow/joint-autoencoder-classifier-model-for-malfunction-identification-and-classification-on-marine-diesel-engine-diagnostics-data/271615955 kince@slideshare.net(kince) Joint Autoencoder-Classifier Model for Malfunction Identification and Classification on Marine Diesel Engine Diagnostics Data kince Abstract: There has been an increasing demand on marine transportation and traveling, since the voyage of the ships are more economical and efficient than air or land-based alternatives. The propulsion of a ship is provided by a main engine system which includes the shaft, the propellers, and other auxiliary equipment. Marine diesel engine is a complex structure that the faults within these machines can cause malfunction of the whole system, which in turn inhibits the ships mission. It is crucial to monitor the engine and other auxiliary systems during the operation and infer their condition from their diagnostic data. In this study, we analyze monitoring data of a crude oil tanker for different ship loads and conditions. Our primary analysis includes main engine fault detection and classification for which we propose an end-to-end joint autoencoder-classifier model that contains a convolutional autoencoder, and a long-short term memory regressor connected to the latent space. Genetic algorithms optimized models gave us 93.61% accuracy for fault classification task. Further investigation on features contributions to the model, we increased the accuracy up to 96%. One concern about marine transportation is the pollution of the air with greenhouse effect gases. In this study, we have developed NOx and SOx emission estimators for different faults and working conditions. Leveraging ship load, working conditions and engine faults in the models helped us to achieve 50% better estimation performance. Although there are other studies regarding gases emissions in the literature, this is the first study that took engine faults into account. We believe that the joint autoencoder-classifier model will be useful for other time series estimation task on other domains, especially where the operating condition plays a role in the process. https://doi.org/10.36001/phme.2022.v7i1.3335 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2022-phme-export-240906172256-cf052eba-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Abstract: There has been an increasing demand on marine transportation and traveling, since the voyage of the ships are more economical and efficient than air or land-based alternatives. The propulsion of a ship is provided by a main engine system which includes the shaft, the propellers, and other auxiliary equipment. Marine diesel engine is a complex structure that the faults within these machines can cause malfunction of the whole system, which in turn inhibits the ships mission. It is crucial to monitor the engine and other auxiliary systems during the operation and infer their condition from their diagnostic data. In this study, we analyze monitoring data of a crude oil tanker for different ship loads and conditions. Our primary analysis includes main engine fault detection and classification for which we propose an end-to-end joint autoencoder-classifier model that contains a convolutional autoencoder, and a long-short term memory regressor connected to the latent space. Genetic algorithms optimized models gave us 93.61% accuracy for fault classification task. Further investigation on features contributions to the model, we increased the accuracy up to 96%. One concern about marine transportation is the pollution of the air with greenhouse effect gases. In this study, we have developed NOx and SOx emission estimators for different faults and working conditions. Leveraging ship load, working conditions and engine faults in the models helped us to achieve 50% better estimation performance. Although there are other studies regarding gases emissions in the literature, this is the first study that took engine faults into account. We believe that the joint autoencoder-classifier model will be useful for other time series estimation task on other domains, especially where the operating condition plays a role in the process. https://doi.org/10.36001/phme.2022.v7i1.3335
Joint Autoencoder-Classifier Model for Malfunction Identification and Classification on Marine Diesel Engine Diagnostics Data from Kr罩t NCE
]]> 16 0 https://cdn.slidesharecdn.com/ss_thumbnails/2022-phme-export-240906172256-cf052eba-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Birleik Otokodlay脹c脹-Regresyon Mimarisi ile C-MAPSS Veri K端mesi zerinde Kalan Faydal脹 m端r Kestirimi /slideshow/birlesik-otokodlayici-regresyon-mimarisi-ile-c-mapss-veri-kumesi-uzerinde-kalan-faydali-omur-kestirimi/271592507 2022-siu-export-240905174530-80bfba73
zet: End端striyel sistemlerin bak脹m maliyetleri 巽ou zaman ilk yat脹r脹m maliyetinin 端zerine 巽脹kmaktad脹r. Toplam bak脹m maliyetini d端端rmede en etkili y旦ntemlerden biri olan kestirimci bak脹m, yeni end端stri devrimi ile artan otomasyon, izleme kabiliyeti ve gelien teknikler ile veri odakl脹 arat脹rma yapanlar脹n ilgi alan脹na girmitir. Bu 巽al脹mada, 旦zg端n birleik otokodlay脹c脹-regresyon mimarisi kullan脹larak NASA Turbofan Motoru Bozulma Veri K端mesi 端zerinde yap脹lan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Derin 旦renme tekniklerinin uyguland脹脹 bu mimaride otokodlay脹c脹 i巽in InceptionTime a脹, kalan faydal脹 旦m端r kestirimi i巽in uzun-k脹sa s端reli bellek kullan脹lm脹t脹r. 聴lk aamada genetik algoritmalar kullan脹larak modeller eitilmi ve eniyiletirilmi, ard脹ndan g端r端lt端 ekleme ve a budama teknikleri ile modellere ince ayar yap脹lm脹t脹r. Elde edilen sonu巽lar InceptionTime temelli birleik otokodlay脹c脹-regresyon mimarisinin rekabet巽i olduunu ortaya koymaktad脹r. G端r端lt端 ekleme ile iyiletirilen modeller tekniin bilinen durumuna yak脹n baar脹m g旦stermektedir. http://doi.org/10.1109/SIU55565.2022.9864796 ]]>
zet: End端striyel sistemlerin bak脹m maliyetleri 巽ou zaman ilk yat脹r脹m maliyetinin 端zerine 巽脹kmaktad脹r. Toplam bak脹m maliyetini d端端rmede en etkili y旦ntemlerden biri olan kestirimci bak脹m, yeni end端stri devrimi ile artan otomasyon, izleme kabiliyeti ve gelien teknikler ile veri odakl脹 arat脹rma yapanlar脹n ilgi alan脹na girmitir. Bu 巽al脹mada, 旦zg端n birleik otokodlay脹c脹-regresyon mimarisi kullan脹larak NASA Turbofan Motoru Bozulma Veri K端mesi 端zerinde yap脹lan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Derin 旦renme tekniklerinin uyguland脹脹 bu mimaride otokodlay脹c脹 i巽in InceptionTime a脹, kalan faydal脹 旦m端r kestirimi i巽in uzun-k脹sa s端reli bellek kullan脹lm脹t脹r. 聴lk aamada genetik algoritmalar kullan脹larak modeller eitilmi ve eniyiletirilmi, ard脹ndan g端r端lt端 ekleme ve a budama teknikleri ile modellere ince ayar yap脹lm脹t脹r. Elde edilen sonu巽lar InceptionTime temelli birleik otokodlay脹c脹-regresyon mimarisinin rekabet巽i olduunu ortaya koymaktad脹r. G端r端lt端 ekleme ile iyiletirilen modeller tekniin bilinen durumuna yak脹n baar脹m g旦stermektedir. http://doi.org/10.1109/SIU55565.2022.9864796 ]]> Thu, 05 Sep 2024 17:45:29 GMT /slideshow/birlesik-otokodlayici-regresyon-mimarisi-ile-c-mapss-veri-kumesi-uzerinde-kalan-faydali-omur-kestirimi/271592507 kince@slideshare.net(kince) Birleik Otokodlay脹c脹-Regresyon Mimarisi ile C-MAPSS Veri K端mesi zerinde Kalan Faydal脹 m端r Kestirimi kince zet: End端striyel sistemlerin bak脹m maliyetleri 巽ou zaman ilk yat脹r脹m maliyetinin 端zerine 巽脹kmaktad脹r. Toplam bak脹m maliyetini d端端rmede en etkili y旦ntemlerden biri olan kestirimci bak脹m, yeni end端stri devrimi ile artan otomasyon, izleme kabiliyeti ve gelien teknikler ile veri odakl脹 arat脹rma yapanlar脹n ilgi alan脹na girmitir. Bu 巽al脹mada, 旦zg端n birleik otokodlay脹c脹-regresyon mimarisi kullan脹larak NASA Turbofan Motoru Bozulma Veri K端mesi 端zerinde yap脹lan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Derin 旦renme tekniklerinin uyguland脹脹 bu mimaride otokodlay脹c脹 i巽in InceptionTime a脹, kalan faydal脹 旦m端r kestirimi i巽in uzun-k脹sa s端reli bellek kullan脹lm脹t脹r. 聴lk aamada genetik algoritmalar kullan脹larak modeller eitilmi ve eniyiletirilmi, ard脹ndan g端r端lt端 ekleme ve a budama teknikleri ile modellere ince ayar yap脹lm脹t脹r. Elde edilen sonu巽lar InceptionTime temelli birleik otokodlay脹c脹-regresyon mimarisinin rekabet巽i olduunu ortaya koymaktad脹r. G端r端lt端 ekleme ile iyiletirilen modeller tekniin bilinen durumuna yak脹n baar脹m g旦stermektedir. http://doi.org/10.1109/SIU55565.2022.9864796 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2022-siu-export-240905174530-80bfba73-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> zet: End端striyel sistemlerin bak脹m maliyetleri 巽ou zaman ilk yat脹r脹m maliyetinin 端zerine 巽脹kmaktad脹r. Toplam bak脹m maliyetini d端端rmede en etkili y旦ntemlerden biri olan kestirimci bak脹m, yeni end端stri devrimi ile artan otomasyon, izleme kabiliyeti ve gelien teknikler ile veri odakl脹 arat脹rma yapanlar脹n ilgi alan脹na girmitir. Bu 巽al脹mada, 旦zg端n birleik otokodlay脹c脹-regresyon mimarisi kullan脹larak NASA Turbofan Motoru Bozulma Veri K端mesi 端zerinde yap脹lan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Derin 旦renme tekniklerinin uyguland脹脹 bu mimaride otokodlay脹c脹 i巽in InceptionTime a脹, kalan faydal脹 旦m端r kestirimi i巽in uzun-k脹sa s端reli bellek kullan脹lm脹t脹r. 聴lk aamada genetik algoritmalar kullan脹larak modeller eitilmi ve eniyiletirilmi, ard脹ndan g端r端lt端 ekleme ve a budama teknikleri ile modellere ince ayar yap脹lm脹t脹r. Elde edilen sonu巽lar InceptionTime temelli birleik otokodlay脹c脹-regresyon mimarisinin rekabet巽i olduunu ortaya koymaktad脹r. G端r端lt端 ekleme ile iyiletirilen modeller tekniin bilinen durumuna yak脹n baar脹m g旦stermektedir. http://doi.org/10.1109/SIU55565.2022.9864796
Birle罧k Otokodlayc-Regresyon Mimarisi ile C-MAPSS Veri Kmesi 綽erinde Kalan Faydal r Kestirimi from Kr罩t NCE
]]> 16 0 https://cdn.slidesharecdn.com/ss_thumbnails/2022-siu-export-240905174530-80bfba73-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Fault Detection and Classification for Robotic Test-bench /slideshow/fault-detection-and-classification-for-robotic-test-bench/271562686 2021-phm-export-240904154514-e4ec3c60
Abstract: Maintenance of industrial systems often cost as much as their initial investment. Implementing predictive maintenance via system health analysis is one of the strategies to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Sixth European Conference of the Prognostics and Health Management Society 2021 Data Challenge, which introduces a fuse test bench for quality control system, and asks fault detection and classification for the test bench. We proposed classification workflows, which deploy gradient boosting, linear discriminant analysis, and Gaussian process classifiers, and report their performance for different window sizes. Our gradient boosting based solution has been ranked 4th in the data challenge. https://doi.org/10.36001/phme.2021.v6i1.3040 ]]>
Abstract: Maintenance of industrial systems often cost as much as their initial investment. Implementing predictive maintenance via system health analysis is one of the strategies to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Sixth European Conference of the Prognostics and Health Management Society 2021 Data Challenge, which introduces a fuse test bench for quality control system, and asks fault detection and classification for the test bench. We proposed classification workflows, which deploy gradient boosting, linear discriminant analysis, and Gaussian process classifiers, and report their performance for different window sizes. Our gradient boosting based solution has been ranked 4th in the data challenge. https://doi.org/10.36001/phme.2021.v6i1.3040 ]]> Wed, 04 Sep 2024 15:45:14 GMT /slideshow/fault-detection-and-classification-for-robotic-test-bench/271562686 kince@slideshare.net(kince) Fault Detection and Classification for Robotic Test-bench kince Abstract: Maintenance of industrial systems often cost as much as their initial investment. Implementing predictive maintenance via system health analysis is one of the strategies to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Sixth European Conference of the Prognostics and Health Management Society 2021 Data Challenge, which introduces a fuse test bench for quality control system, and asks fault detection and classification for the test bench. We proposed classification workflows, which deploy gradient boosting, linear discriminant analysis, and Gaussian process classifiers, and report their performance for different window sizes. Our gradient boosting based solution has been ranked 4th in the data challenge. https://doi.org/10.36001/phme.2021.v6i1.3040 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2021-phm-export-240904154514-e4ec3c60-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Abstract: Maintenance of industrial systems often cost as much as their initial investment. Implementing predictive maintenance via system health analysis is one of the strategies to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Sixth European Conference of the Prognostics and Health Management Society 2021 Data Challenge, which introduces a fuse test bench for quality control system, and asks fault detection and classification for the test bench. We proposed classification workflows, which deploy gradient boosting, linear discriminant analysis, and Gaussian process classifiers, and report their performance for different window sizes. Our gradient boosting based solution has been ranked 4th in the data challenge. https://doi.org/10.36001/phme.2021.v6i1.3040
Fault Detection and Classification for Robotic Test-bench from Kr罩t NCE
]]> 158 0 https://cdn.slidesharecdn.com/ss_thumbnails/2021-phm-export-240904154514-e4ec3c60-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Birleik Otokodlay脹c脹-Regresyon ile Turbofan Motorlar脹 zerinde Kalan Faydal脹 m端r Kestirimi /slideshow/birlesik-otokodlayici-regresyon-ile-turbofan-motorlari-uzerinde-kalan-faydali-omur-kestirimi/271536861 2020-siu-export-240903183324-7795eb06
zet: End端striyel makinelerin faydal脹 旦mr端, kestirimci bak脹m kapsam脹nda en 巽ok arat脹r脹lan konulardan biridir. Bu bildiride CMAPSS veri k端mesi 端zerinde otokodlay脹c脹-regresyon y旦ntemi ile yap脹lan kalan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Abstract: Useful life of industrial machinery is one of the most researched area of predictive maintenance. In this paper, we used CMAPSS dataset to predict remaining useful life using autoencoder-regression models.]]>
zet: End端striyel makinelerin faydal脹 旦mr端, kestirimci bak脹m kapsam脹nda en 巽ok arat脹r脹lan konulardan biridir. Bu bildiride CMAPSS veri k端mesi 端zerinde otokodlay脹c脹-regresyon y旦ntemi ile yap脹lan kalan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Abstract: Useful life of industrial machinery is one of the most researched area of predictive maintenance. In this paper, we used CMAPSS dataset to predict remaining useful life using autoencoder-regression models.]]> Tue, 03 Sep 2024 18:33:24 GMT /slideshow/birlesik-otokodlayici-regresyon-ile-turbofan-motorlari-uzerinde-kalan-faydali-omur-kestirimi/271536861 kince@slideshare.net(kince) Birleik Otokodlay脹c脹-Regresyon ile Turbofan Motorlar脹 zerinde Kalan Faydal脹 m端r Kestirimi kince zet: End端striyel makinelerin faydal脹 旦mr端, kestirimci bak脹m kapsam脹nda en 巽ok arat脹r脹lan konulardan biridir. Bu bildiride CMAPSS veri k端mesi 端zerinde otokodlay脹c脹-regresyon y旦ntemi ile yap脹lan kalan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Abstract: Useful life of industrial machinery is one of the most researched area of predictive maintenance. In this paper, we used CMAPSS dataset to predict remaining useful life using autoencoder-regression models. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2020-siu-export-240903183324-7795eb06-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> zet: End端striyel makinelerin faydal脹 旦mr端, kestirimci bak脹m kapsam脹nda en 巽ok arat脹r脹lan konulardan biridir. Bu bildiride CMAPSS veri k端mesi 端zerinde otokodlay脹c脹-regresyon y旦ntemi ile yap脹lan kalan faydal脹 旦m端r kestirimi anlat脹lmaktad脹r. Abstract: Useful life of industrial machinery is one of the most researched area of predictive maintenance. In this paper, we used CMAPSS dataset to predict remaining useful life using autoencoder-regression models.
Birle罧k Otokodlayc-Regresyon ile Turbofan Motorlar 綽erinde Kalan Faydal r Kestirimi from Kr罩t NCE
]]> 19 0 https://cdn.slidesharecdn.com/ss_thumbnails/2020-siu-export-240903183324-7795eb06-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Remaining Useful Life Prediction for Experimental Filtration System: A Data Challenge /slideshow/remaining-useful-life-prediction-for-experimental-filtration-system-a-data-challenge/271506536 2020-phme-export-240902192309-2ffd5459
Abstract: Maintenance costs of industrial systems often exceed the initial investment cost. Predictive maintenance, which analyzes the health of the system and suggests maintenance planning, is one of the strategies implemented to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Fifth European Conference of the Prognostics and Health Management Society 2020 Data Challenge, which introduces an experimental filtration system for different experiment setups, and asks for remaining useful life predictions. We compared random forest, gradient boosting, and Gaussian process regression algorithms to predict the useful life of the experimental system. With the help of a new fault-based piecewise linear RUL assignment strategy, our gradient boosting based solution has been ranked 3rd in the data challenge. https://doi.org/10.36001/phme.2020.v5i1.1317 ]]>
Abstract: Maintenance costs of industrial systems often exceed the initial investment cost. Predictive maintenance, which analyzes the health of the system and suggests maintenance planning, is one of the strategies implemented to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Fifth European Conference of the Prognostics and Health Management Society 2020 Data Challenge, which introduces an experimental filtration system for different experiment setups, and asks for remaining useful life predictions. We compared random forest, gradient boosting, and Gaussian process regression algorithms to predict the useful life of the experimental system. With the help of a new fault-based piecewise linear RUL assignment strategy, our gradient boosting based solution has been ranked 3rd in the data challenge. https://doi.org/10.36001/phme.2020.v5i1.1317 ]]> Mon, 02 Sep 2024 19:23:09 GMT /slideshow/remaining-useful-life-prediction-for-experimental-filtration-system-a-data-challenge/271506536 kince@slideshare.net(kince) Remaining Useful Life Prediction for Experimental Filtration System: A Data Challenge kince Abstract: Maintenance costs of industrial systems often exceed the initial investment cost. Predictive maintenance, which analyzes the health of the system and suggests maintenance planning, is one of the strategies implemented to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Fifth European Conference of the Prognostics and Health Management Society 2020 Data Challenge, which introduces an experimental filtration system for different experiment setups, and asks for remaining useful life predictions. We compared random forest, gradient boosting, and Gaussian process regression algorithms to predict the useful life of the experimental system. With the help of a new fault-based piecewise linear RUL assignment strategy, our gradient boosting based solution has been ranked 3rd in the data challenge. https://doi.org/10.36001/phme.2020.v5i1.1317 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2020-phme-export-240902192309-2ffd5459-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Abstract: Maintenance costs of industrial systems often exceed the initial investment cost. Predictive maintenance, which analyzes the health of the system and suggests maintenance planning, is one of the strategies implemented to reduce maintenance costs. Health status and life estimation of the machinery are the most researched topics in this context. In this paper, we present our analysis for Fifth European Conference of the Prognostics and Health Management Society 2020 Data Challenge, which introduces an experimental filtration system for different experiment setups, and asks for remaining useful life predictions. We compared random forest, gradient boosting, and Gaussian process regression algorithms to predict the useful life of the experimental system. With the help of a new fault-based piecewise linear RUL assignment strategy, our gradient boosting based solution has been ranked 3rd in the data challenge. https://doi.org/10.36001/phme.2020.v5i1.1317
Remaining Useful Life Prediction for Experimental Filtration System: A Data Challenge from Kr罩t NCE
]]> 196 0 https://cdn.slidesharecdn.com/ss_thumbnails/2020-phme-export-240902192309-2ffd5459-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Data Analysis for Automobile Brake Fluid Fill Process Leakage Detection using Machine Learning Methods /slideshow/data-analysis-for-automobile-brake-fluid-fill-process-leakage-detection-using-machine-learning-methods/271476325 2019-asyu-export-240901203435-d908396e
Abstract: During the production of an automobile, various fluids such as steering fluid, brake fluid, radiator coolant, etc. that are required for the operation of an automobile, are filled to the vehicle via a specific process. Any problems such as leakage in the fluids systems should be identified during the filling process and necessary corrections must be made to the automobile before it goes forward in the production line. The fluid filling process consists of vacuuming step followed by filling step. This paper provides results of our research on the brake fluid system quality based on the sensor data, which is recorded during filling process. The filling dataset contains two time series data corresponding to the vacuuming and filling steps. First, we use this raw data to construct a dataset with 1-faulty/0-Not-faulty labels. Later we use this dataset to construct machine learning models, with classical methods, and convolutional neural network models. Results show that gradient boosting methods are better with the current settings, and we have improvement opportunities related to convolutional neural network architectures. https://doi.org/10.1109/ASYU48272.2019.8946399]]>
Abstract: During the production of an automobile, various fluids such as steering fluid, brake fluid, radiator coolant, etc. that are required for the operation of an automobile, are filled to the vehicle via a specific process. Any problems such as leakage in the fluids systems should be identified during the filling process and necessary corrections must be made to the automobile before it goes forward in the production line. The fluid filling process consists of vacuuming step followed by filling step. This paper provides results of our research on the brake fluid system quality based on the sensor data, which is recorded during filling process. The filling dataset contains two time series data corresponding to the vacuuming and filling steps. First, we use this raw data to construct a dataset with 1-faulty/0-Not-faulty labels. Later we use this dataset to construct machine learning models, with classical methods, and convolutional neural network models. Results show that gradient boosting methods are better with the current settings, and we have improvement opportunities related to convolutional neural network architectures. https://doi.org/10.1109/ASYU48272.2019.8946399]]> Sun, 01 Sep 2024 20:34:35 GMT /slideshow/data-analysis-for-automobile-brake-fluid-fill-process-leakage-detection-using-machine-learning-methods/271476325 kince@slideshare.net(kince) Data Analysis for Automobile Brake Fluid Fill Process Leakage Detection using Machine Learning Methods kince Abstract: During the production of an automobile, various fluids such as steering fluid, brake fluid, radiator coolant, etc. that are required for the operation of an automobile, are filled to the vehicle via a specific process. Any problems such as leakage in the fluids systems should be identified during the filling process and necessary corrections must be made to the automobile before it goes forward in the production line. The fluid filling process consists of vacuuming step followed by filling step. This paper provides results of our research on the brake fluid system quality based on the sensor data, which is recorded during filling process. The filling dataset contains two time series data corresponding to the vacuuming and filling steps. First, we use this raw data to construct a dataset with 1-faulty/0-Not-faulty labels. Later we use this dataset to construct machine learning models, with classical methods, and convolutional neural network models. Results show that gradient boosting methods are better with the current settings, and we have improvement opportunities related to convolutional neural network architectures. https://doi.org/10.1109/ASYU48272.2019.8946399 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/2019-asyu-export-240901203435-d908396e-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Abstract: During the production of an automobile, various fluids such as steering fluid, brake fluid, radiator coolant, etc. that are required for the operation of an automobile, are filled to the vehicle via a specific process. Any problems such as leakage in the fluids systems should be identified during the filling process and necessary corrections must be made to the automobile before it goes forward in the production line. The fluid filling process consists of vacuuming step followed by filling step. This paper provides results of our research on the brake fluid system quality based on the sensor data, which is recorded during filling process. The filling dataset contains two time series data corresponding to the vacuuming and filling steps. First, we use this raw data to construct a dataset with 1-faulty/0-Not-faulty labels. Later we use this dataset to construct machine learning models, with classical methods, and convolutional neural network models. Results show that gradient boosting methods are better with the current settings, and we have improvement opportunities related to convolutional neural network architectures. https://doi.org/10.1109/ASYU48272.2019.8946399
Data Analysis for Automobile Brake Fluid Fill Process Leakage Detection using Machine Learning Methods from Kr罩t NCE
]]> 177 0 https://cdn.slidesharecdn.com/ss_thumbnails/2019-asyu-export-240901203435-d908396e-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 GTU GeekDay 2019 Limitations of Artificial Intelligence /kince/gtu-geekday-2019-limitations-of-artificial-intelligence geekday2019-limitationsofai-190302195941
"Limitations of Artificial Intelligence" presented at GTU GeekDay 2019.]]>
"Limitations of Artificial Intelligence" presented at GTU GeekDay 2019.]]> Sat, 02 Mar 2019 19:59:41 GMT /kince/gtu-geekday-2019-limitations-of-artificial-intelligence kince@slideshare.net(kince) GTU GeekDay 2019 Limitations of Artificial Intelligence kince "Limitations of Artificial Intelligence" presented at GTU GeekDay 2019. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/geekday2019-limitationsofai-190302195941-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> &quot;Limitations of Artificial Intelligence&quot; presented at GTU GeekDay 2019.
GTU GeekDay 2019 Limitations of Artificial Intelligence from Kr罩t NCE
]]> 919 2 https://cdn.slidesharecdn.com/ss_thumbnails/geekday2019-limitationsofai-190302195941-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 GTU GeekDay Data Science and Applications /slideshow/gtu-geekday-data-science-and-applications/72594267 gtugeekday-datascienceandapplicationsbykince-170226174227
Data Science presentation at Gebze Technical University GeekDay on 25 Feb. 2017 http://geekday.gtubt.com/ ]]>
Data Science presentation at Gebze Technical University GeekDay on 25 Feb. 2017 http://geekday.gtubt.com/ ]]> Sun, 26 Feb 2017 17:42:26 GMT /slideshow/gtu-geekday-data-science-and-applications/72594267 kince@slideshare.net(kince) GTU GeekDay Data Science and Applications kince Data Science presentation at Gebze Technical University GeekDay on 25 Feb. 2017 http://geekday.gtubt.com/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gtugeekday-datascienceandapplicationsbykince-170226174227-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Data Science presentation at Gebze Technical University GeekDay on 25 Feb. 2017 http://geekday.gtubt.com/
GTU GeekDay Data Science and Applications from Kr罩t NCE
]]> 427 4 https://cdn.slidesharecdn.com/ss_thumbnails/gtugeekday-datascienceandapplicationsbykince-170226174227-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-kince-48x48.jpg?cb=1725643350 https://cdn.slidesharecdn.com/ss_thumbnails/2022-phme-export-240906172256-cf052eba-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/joint-autoencoder-classifier-model-for-malfunction-identification-and-classification-on-marine-diesel-engine-diagnostics-data/271615955 Joint Autoencoder-Clas... https://cdn.slidesharecdn.com/ss_thumbnails/2022-siu-export-240905174530-80bfba73-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/birlesik-otokodlayici-regresyon-mimarisi-ile-c-mapss-veri-kumesi-uzerinde-kalan-faydali-omur-kestirimi/271592507 Birleik Otokodlay脹c脹-... https://cdn.slidesharecdn.com/ss_thumbnails/2021-phm-export-240904154514-e4ec3c60-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/fault-detection-and-classification-for-robotic-test-bench/271562686 Fault Detection and Cl...