Reliability has been widely used as a potential indicator of the performance assessment for several real-life networks. Focus on a multistate transportation network in tourism (MTN), this study evaluates the reliability of the MTN as a basis for investigating the influence of transit time. Reliability is the probability to fulfill transportation demand under the given time threshold and budget limitation and evaluated at various levels of transit times. An algorithm, which employs the boundary points and recursive sum of disjoint products technique, is proposed to evaluate the MTN reliability. According to the obtained results, this paper analyzes the influence of transit times on MTN reliability. Particularly, this paper discusses and provides some suggestions about the appropriate transit time to maintain reliability. Decision-makers in the tourism industry also can predetermine the significant drops of reliability to improve the relevant transit times. Besides, the proposed investigation is indicated and proved through an illustrative example and a practical case.
{"title":"Investigation of the influence of transit time on a multistate transportation network in tourism","authors":"Thi-Phuong Nguyen, Yi-Kuei Lin","doi":"10.17531/ein.2021.4.9","DOIUrl":"https://doi.org/10.17531/ein.2021.4.9","url":null,"abstract":"Reliability has been widely used as a potential indicator of the performance assessment for several real-life networks. Focus on a multistate transportation network in tourism (MTN), this study evaluates the reliability of the MTN as a basis for investigating the influence of transit time. Reliability is the probability to fulfill transportation demand under the given time threshold and budget limitation and evaluated at various levels of transit times. An algorithm, which employs the boundary points and recursive sum of disjoint products technique, is proposed to evaluate the MTN reliability. According to the obtained results, this paper analyzes the influence of transit times on MTN reliability. Particularly, this paper discusses and provides some suggestions about the appropriate transit time to maintain reliability. Decision-makers in the tourism industry also can predetermine the significant drops of reliability to improve the relevant transit times. Besides, the proposed investigation is indicated and proved through an illustrative example and a practical case.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"38 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78520913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The purpose of this paper is to evaluate the efficiency of airport processes using simulation tools. A critical review of selected scientific studies relating to the performance of airport processes with respect to reliability, particularly within the apron, has been undertaken. The developed decision-making model evaluates the efficiency of airport processes in terms of minimizing penalties associated with aircraft landing before or after the scheduled landing time. The model takes into account, among other things, aircraft take-offs and landings and separation times between successive aircraft. In order to be able to verify the correctness of the decision-making model, a simulation tool was developed to support decision making in the implementation of airport operations based on a genetic algorithm. A novel development of the structure of a genetic algorithm as well as crossover and mutation operators adapted to the determination of aircraft movement routes on the apron is presented. The developed simulation tool was verified on real input data.
{"title":"Evaluation of efficiency and reliability of airport processes using simulation tools","authors":"P. Gołda, T. Zawisza, M. Izdebski","doi":"10.17531/ein.2021.4.8","DOIUrl":"https://doi.org/10.17531/ein.2021.4.8","url":null,"abstract":"The purpose of this paper is to evaluate the efficiency of airport processes using simulation tools. A critical review of selected scientific studies relating to the performance of airport processes with respect to reliability, particularly within the apron, has been undertaken. The developed decision-making model evaluates the efficiency of airport processes in terms of minimizing penalties associated with aircraft landing before or after the scheduled landing time. The model takes into account, among other things, aircraft take-offs and landings and separation times between successive aircraft. In order to be able to verify the correctness of the decision-making model, a simulation tool was developed to support decision making in the implementation of airport operations based on a genetic algorithm. A novel development of the structure of a genetic algorithm as well as crossover and mutation operators adapted to the determination of aircraft movement routes on the apron is presented. The developed simulation tool was verified on real input data.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"16 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73667719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Haiyang Che, S. Zeng, Qidong You, Yueheng Song, Jianbin Guo
Many lives and aircrafts have been lost due to human errors associated with mental workload overload (MWLOL). Human errors are successfully considered in existing Fault Tree Analysis (FTA) methods. However, MWLOL is considered through Performance Shaping Factors indirectly and its information is hidden in FT construction, which is not conducive to analyze the root causes of human errors and risks. To overcome this difficulty, we develop a risk analysis method where Multiple Resources Model (MRM) is incorporated into FTA methods. MRM analyzes mental workload by estimating the resources used during performing concurrent tasks, probably including abnormal situation handling tasks introduced by basic events in FT. Such basic events may cause MWLOL and then trigger corresponding human error events. A MWLOL gate is proposed to describe MWLOL explicitly and add these new relationships to traditional FT. This new method extends previous FTA methods and provides a more in-depth risk analysis. An accident, a helicopter crash in Maryland, is analyzed by the proposed method.
{"title":"A fault tree-based approach for aviation risk analysis considering mental workload overload","authors":"Haiyang Che, S. Zeng, Qidong You, Yueheng Song, Jianbin Guo","doi":"10.17531/ein.2021.4.7","DOIUrl":"https://doi.org/10.17531/ein.2021.4.7","url":null,"abstract":"Many lives and aircrafts have been lost due to human errors associated with mental workload overload (MWLOL). Human errors are successfully considered in existing Fault Tree Analysis (FTA) methods. However, MWLOL is considered through Performance Shaping Factors indirectly and its information is hidden in FT construction, which is not conducive to analyze the root causes of human errors and risks. To overcome this difficulty, we develop a risk analysis method where Multiple Resources Model (MRM) is incorporated into FTA methods. MRM analyzes mental workload by estimating the resources used during performing concurrent tasks, probably including abnormal situation handling tasks introduced by basic events in FT. Such basic events may cause MWLOL and then trigger corresponding human error events. A MWLOL gate is proposed to describe MWLOL explicitly and add these new relationships to traditional FT. This new method extends previous FTA methods and provides a more in-depth risk analysis. An accident, a helicopter crash in Maryland, is analyzed by the proposed method.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"1 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83175450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Mamala, M. Graba, A. Bieniek, K. Prażnowski, A. Augustynowicz, M. Śmieja
The paper presents an analysis of energy consumption in a Plug-in Hybrid Electric Vehicle (PHEV) used in actual road conditions. Therefore, the paper features a comparison of the consumption of energy obtained from fuel and from energy taken from the vehicle’s batteries for each travel with a total distance of 5000 km. The instantaneous energy consumption per travelling kilometre in actual operating conditions for a combustion engine mode are within the range of 233 to 1170 Wh/km and for an electric motor mode are within the range of 135 to 420 Wh/km. The average values amount to 894 Wh/km for the combustion engine and 208 Wh/km for the electric motor. The experimental data was used to develop curves for the total energy consumption per 100km of road section travelled divided into particular engine types (combustion/electric), demonstrating a close correlation to actual operating conditions. These values were referred to the tested passenger vehicle’s approval data in a WLTP test, with the average values of 303 Wh/km and CO2 emission of 23 g/km.
{"title":"Study of energy consumption of a hybrid vehicle in real-world conditions","authors":"J. Mamala, M. Graba, A. Bieniek, K. Prażnowski, A. Augustynowicz, M. Śmieja","doi":"10.17531/ein.2021.4.6","DOIUrl":"https://doi.org/10.17531/ein.2021.4.6","url":null,"abstract":"The paper presents an analysis of energy consumption in a Plug-in Hybrid Electric Vehicle\u0000(PHEV) used in actual road conditions. Therefore, the paper features a comparison of the\u0000consumption of energy obtained from fuel and from energy taken from the vehicle’s batteries for each travel with a total distance of 5000 km. The instantaneous energy consumption per travelling kilometre in actual operating conditions for a combustion engine mode are within the range of 233 to 1170 Wh/km and for an electric motor mode are within the range of 135 to 420 Wh/km. The average values amount to 894 Wh/km for the combustion engine and 208 Wh/km for the electric motor. The experimental data was used to develop curves for the total energy consumption per 100km of road section travelled divided into particular engine types (combustion/electric), demonstrating a close correlation to actual operating conditions. These values were referred to the tested passenger vehicle’s approval data in a WLTP test, with the average values of 303 Wh/km and CO2 emission of 23 g/km.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"1 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87340205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H-Y. Lyu, Shuai Wang, Xiaowen Zhang, Zaiyou Yang, Michael G. Pecht
In this paper, a system reliability model subject to Dependent Competing Failure Processes (DCFP) with phase-type (PH) distribution considering changing degradation rate is proposed. When the sum of continuous degradation and sudden degradation exceeds the soft failure threshold, soft failure occurs. The interarrival time between two successive shocks and total number of shocks before hard failure occurring follow the continuous PH distribution and discrete PH distribution, respectively. The hard failure reliability is calculated using the PH distribution survival function. Due to the shock on soft failure process, the degradation rate of soft failure will increase. When the number of shocks reaches a specific value, degradation rate changes. The hard failure is calculated by the extreme shock model, cumulative shock model, and run shock model, respectively. The closed-form reliability function is derived combining with the hard and soft failure reliability model. Finally, a Micro-Electro-Mechanical System (MEMS) demonstrates the effectiveness of the proposed model.
{"title":"Reliability modeling for dependent competing failure processes with phase-type distribution considering changing degradation rate","authors":"H-Y. Lyu, Shuai Wang, Xiaowen Zhang, Zaiyou Yang, Michael G. Pecht","doi":"10.17531/ein.2021.4.5","DOIUrl":"https://doi.org/10.17531/ein.2021.4.5","url":null,"abstract":"In this paper, a system reliability model subject to Dependent Competing Failure Processes (DCFP) with phase-type (PH) distribution considering changing degradation rate is proposed. When the sum of continuous degradation and sudden degradation exceeds the soft failure threshold, soft failure occurs. The interarrival time between two successive shocks and total number of shocks before hard failure occurring follow the continuous PH distribution and discrete PH distribution, respectively. The hard failure reliability is calculated using the PH distribution survival function. Due to the shock on soft failure process, the degradation rate of soft failure will increase. When the number of shocks reaches a specific value, degradation rate changes. The hard failure is calculated by the extreme shock model, cumulative shock model, and run shock model, respectively. The closed-form reliability function is derived combining with the hard and soft failure reliability model. Finally, a Micro-Electro-Mechanical System (MEMS) demonstrates the effectiveness of the proposed model.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"33 1 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90450512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Łukasz Rymaniak, J. Merkisz, Natalia Szymlet, Michalina Kamińska, S. Weymann
The paper presents the proposed proprietary M exhaust emission indicator, which is based on the assumption that CO2 emissions are a measure of the correctness of the combustion process. The measurements were performed using a farm tractor meeting the Tier 3 emission norm, operated in real conditions during plowing work. The tests were carried out for a given land section at three speeds In the analysis of test results, the net engine work was used, as it is carried out in the type approval procedures. When measuring in real operating conditions, the torque read from the OBD system is overstated because it takes into account the engine’s internal resistance. In the analysis of test results, the fuel consumption, emission indicators of gaseous compounds and particulates were determined, and the best conditions for conducting agricultural works were indicated in terms of their impact on the natural environment. The aim of the work is to verify the possibility of determining the emission index for an off-road vehicle and a comparative analysis of its values for various operating parameters of a farm tractor. On this basis, it was found that the lowest values of the M identity were recorded for the test characterized by a vehicle speed of 15 km/h.
{"title":"Use of emission indicators related to CO2 emissions in the ecological assessment of an agricultural tractor","authors":"Łukasz Rymaniak, J. Merkisz, Natalia Szymlet, Michalina Kamińska, S. Weymann","doi":"10.17531/ein.2021.4.2","DOIUrl":"https://doi.org/10.17531/ein.2021.4.2","url":null,"abstract":"The paper presents the proposed proprietary M exhaust emission indicator, which is based on the assumption that CO2 emissions are a measure of the correctness of the combustion process. The measurements were performed using a farm tractor meeting the Tier 3 emission norm, operated in real conditions during plowing work. The tests were carried out for a given land section at three speeds In the analysis of test results, the net engine work was used, as it is carried out in the type approval procedures. When measuring in real operating conditions, the torque read from the OBD system is overstated because it takes into account the engine’s internal resistance. In the analysis of test results, the fuel consumption, emission indicators of gaseous compounds and particulates were determined, and the best conditions for conducting agricultural works were indicated in terms of their impact on the natural environment. The aim of the work is to verify the possibility of determining the emission index for an off-road vehicle and a comparative analysis of its values for various operating parameters of a farm tractor. On this basis, it was found that the lowest values of the M identity were recorded for the test characterized by a vehicle speed of 15 km/h.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"46 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75570668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Road accidents are one of the basic road safety determinants. Most research covers large territorial areas. The results of such research do not take into account the differences between individual regions, which often leads to incorrect results and their interpretation. What makes it difficult to conduct analyses in a narrow territorial area is the small number of observations. The narrowing of the research area means that the number of accidents in time units is often very low. There are many zero observations in the data sets, which may affect the reliability of the research results. Such data are usually aggregated, which leads to information loss. The authors have therefore applied a model that addresses such problems. They proposed a method that does not require data aggregation and allows for the analysis of sets with an excess of zero observations. The presented model can be implemented in different territorial areas.
{"title":"Influence of meteorological conditions on road accidents. A model for observations with excess zeros","authors":"A. Borucka, D. Pyza","doi":"10.17531/EIN.2021.3.20","DOIUrl":"https://doi.org/10.17531/EIN.2021.3.20","url":null,"abstract":"Road accidents are one of the basic road safety determinants. Most research covers large territorial areas. The results of such research do not take into account the differences between individual regions, which often leads to incorrect results and their interpretation. What makes it difficult to conduct analyses in a narrow territorial area is the small number of observations. The narrowing of the research area means that the number of accidents in time units is often very low. There are many zero observations in the data sets, which may affect the reliability of the research results. Such data are usually aggregated, which leads to information loss. The authors have therefore applied a model that addresses such problems. They proposed a method that does not require data aggregation and allows for the analysis of sets with an excess of zero observations. The presented model can be implemented in different territorial areas.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"5 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85167897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The purpose of this paper is to propose a general precision allocation method to improve machining performance of CNC machine tools based on certain design requirements. A comprehensive error model of machine tools is established by using the differential motion relation of coordinate frames. Based on the comprehensive error model, a reliability model is established by updating the primary reliability with an advanced importance sampling method, which is used to predict the machining accuracy reliability of machine tools. Besides, to identify and optimize geometric error parameters which have a great influence on machining accuracy reliability of machine tools, the sensitivity analysis of machining accuracy is carried out by improved first-order second-moment method. Taking a large CNC gantry guide rail grinder as an example, the optimization results show that the method is effective and can realize reliability optimization of machining accuracy.
{"title":"Enhancing machining accuracy reliability of multi-axis CNC machine tools using an advanced importance sampling method","authors":"Zhiming Wang, Hao Yuan","doi":"10.17531/EIN.2021.3.17","DOIUrl":"https://doi.org/10.17531/EIN.2021.3.17","url":null,"abstract":"The purpose of this paper is to propose a general precision allocation method to improve\u0000machining performance of CNC machine tools based on certain design requirements. A\u0000comprehensive error model of machine tools is established by using the differential motion\u0000relation of coordinate frames. Based on the comprehensive error model, a reliability model\u0000is established by updating the primary reliability with an advanced importance sampling\u0000method, which is used to predict the machining accuracy reliability of machine tools. Besides, to identify and optimize geometric error parameters which have a great influence on machining accuracy reliability of machine tools, the sensitivity analysis of machining accuracy is carried out by improved first-order second-moment method. Taking a large CNC gantry guide rail grinder as an example, the optimization results show that the method is effective and can realize reliability optimization of machining accuracy.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"133 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75702859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arkadiusz Czarnuch, Marek Stembalski, T. Szydłowski, Damain Batory
The aim of the article is to present and validate a methodology for collecting road load data on a vehicle, driving on roads and analysis of a drive data signal under the wheel in the time domain, using FRF (Frequency Response Function) and the MTS 320 eight-poster inertia reacted road simulator. The elaborated drive data, was used to control the actuators forcing the movements of the wheels and the coupling part of the semi-trailer during durability tests. The road tests were carried out by registering physical variables in the time domain, by a set of sensors mounted on a vehicle. The data was collected from roads categorized as motorways, national and local roads. Differences between the variability of the parameters, collected on the roads and the variability of the drive data under the wheel, were determined for the particular types of roads, for loaded and unloaded vehicle. The obtained accuracy of reconstruction of the road load data conditions was as high as 97%. Therefore, the proposed method is suitable for reliable durability tests with use of the road simulator.
{"title":"Method of reconstructing dynamic load characteristics for durability test of heavy\u0000semitrailer under different road conditions","authors":"Arkadiusz Czarnuch, Marek Stembalski, T. Szydłowski, Damain Batory","doi":"10.17531/EIN.2021.3.16","DOIUrl":"https://doi.org/10.17531/EIN.2021.3.16","url":null,"abstract":"The aim of the article is to present and validate a methodology for collecting road load data on a vehicle, driving on roads and analysis of a drive data signal under the wheel in the time domain, using FRF (Frequency Response Function) and the MTS 320 eight-poster inertia reacted road simulator. The elaborated drive data, was used to control the actuators forcing the movements of the wheels and the coupling part of the semi-trailer during durability tests. The road tests were carried out by registering physical variables in the time domain, by a set of sensors mounted on a vehicle. The data was collected from roads categorized as motorways, national and local roads. Differences between the variability of the parameters, collected on the roads and the variability of the drive data under the wheel, were determined for the particular types of roads, for loaded and unloaded vehicle. The obtained accuracy of reconstruction of the road load data conditions was as high as 97%. Therefore, the proposed method is suitable for reliable durability tests with use of the road simulator.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"16 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90744418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maciej Badora, Marzia Sepe, M. Bielecki, A. Graziano, T. Szolc
In this paper several statistical learning algorithms are used to predict the maximal length of fatigue cracks based on a sample composed of 31 observations. The small-data regime is still a problem for many professionals, especially in the areas where failures occur rarely. The analyzed object is a high-pressure Nozzle of a heavy-duty gas turbine. Operating parameters of the engines are used for the regression analysis. The following algorithms are used in this work: multiple linear and polynomial regression, random forest, kernel-based methods, AdaBoost and extreme gradient boosting and artificial neural networks. A substantial part of the paper provides advice on the effective selection of features. The paper explains how to process the dataset in order to reduce uncertainty; thus, simplifying the analysis of the results. The proposed loss and cost functions are custom and promote solutions accurately predicting the longest cracks. The obtained results confirm that some of the algorithms can accurately predict maximal lengths of the fatigue cracks, even if the sample is small.
{"title":"Predicting length of fatigue cracks by means of machine learning algorithms in the small-data regime","authors":"Maciej Badora, Marzia Sepe, M. Bielecki, A. Graziano, T. Szolc","doi":"10.17531/EIN.2021.3.19","DOIUrl":"https://doi.org/10.17531/EIN.2021.3.19","url":null,"abstract":"In this paper several statistical learning algorithms are used to predict the maximal length of fatigue cracks based on a sample composed of 31 observations. The small-data regime is still a problem for many professionals, especially in the areas where failures occur rarely. The analyzed object is a high-pressure Nozzle of a heavy-duty gas turbine. Operating parameters of the engines are used for the regression analysis. The following algorithms are used in this work: multiple linear and polynomial regression, random forest, kernel-based methods, AdaBoost and extreme gradient boosting and artificial neural networks. A substantial part of the paper provides advice on the effective selection of features. The paper explains how to process the dataset in order to reduce uncertainty; thus, simplifying the analysis of the results. The proposed loss and cost functions are custom and promote solutions accurately predicting the longest cracks. The obtained results confirm that some of the algorithms can accurately predict maximal lengths of the fatigue cracks, even if the sample is small.","PeriodicalId":50549,"journal":{"name":"Eksploatacja I Niezawodnosc-Maintenance and Reliability","volume":"43 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74979723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","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：