Pub Date : 2023-11-21DOI: 10.3390/machines11121037
J. Robinson, Abul Arafat, A. Vance, A. Arjunan, A. Baroutaji
In this study, silver (Ag) and silver–diamond (Ag-D) composites with varying diamond (D) content are fabricated using laser powder bed fusion (L-PBF) additive manufacturing (AM). The L-PBF process parameters and inert gas flow rate are optimised to control the build environment and the laser energy density at the powder bed to enable the manufacture of Ag-D composites with 0.1%, 0.2% and 0.3% D content. The Ag and D powder morphology are characterised using scanning electron microscopy (SEM). Ag, Ag-D0.1%, Ag-D0.2% and Ag-D0.3% tensile samples are manufactured to assess the resultant density and tensile strength. In-process EOSTATE melt pool monitoring technology is utilised as a comparative tool to assess the density variations. This technique uses in-process melt pool detection to identify variations in the melt pool characteristics and potential defects and/or density deviations. The resultant morphology and associated defect distribution for each of the samples are characterised and reported using X-ray computed tomography (xCT) and 3D visualisation techniques. Young’s modulus, the failure strain and the ultimate tensile strength of the L-PBF Ag and Ag-D are reported. The melt pool monitoring results revealed in-process variations in the build direction, which was confirmed through xCT 3D visualisations. Additionally, the xCT analysis displayed density variations for all the Ag-D composites manufactured. The tensile results revealed that increasing the diamond content reduced Young’s modulus and the ultimate tensile strength.
{"title":"Melt Pool Monitoring and X-ray Computed Tomography-Informed Characterisation of Laser Powder Bed Additively Manufactured Silver–Diamond Composites","authors":"J. Robinson, Abul Arafat, A. Vance, A. Arjunan, A. Baroutaji","doi":"10.3390/machines11121037","DOIUrl":"https://doi.org/10.3390/machines11121037","url":null,"abstract":"In this study, silver (Ag) and silver–diamond (Ag-D) composites with varying diamond (D) content are fabricated using laser powder bed fusion (L-PBF) additive manufacturing (AM). The L-PBF process parameters and inert gas flow rate are optimised to control the build environment and the laser energy density at the powder bed to enable the manufacture of Ag-D composites with 0.1%, 0.2% and 0.3% D content. The Ag and D powder morphology are characterised using scanning electron microscopy (SEM). Ag, Ag-D0.1%, Ag-D0.2% and Ag-D0.3% tensile samples are manufactured to assess the resultant density and tensile strength. In-process EOSTATE melt pool monitoring technology is utilised as a comparative tool to assess the density variations. This technique uses in-process melt pool detection to identify variations in the melt pool characteristics and potential defects and/or density deviations. The resultant morphology and associated defect distribution for each of the samples are characterised and reported using X-ray computed tomography (xCT) and 3D visualisation techniques. Young’s modulus, the failure strain and the ultimate tensile strength of the L-PBF Ag and Ag-D are reported. The melt pool monitoring results revealed in-process variations in the build direction, which was confirmed through xCT 3D visualisations. Additionally, the xCT analysis displayed density variations for all the Ag-D composites manufactured. The tensile results revealed that increasing the diamond content reduced Young’s modulus and the ultimate tensile strength.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"35 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139253413","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}
Pub Date : 2023-11-20DOI: 10.3390/machines11111035
Stefan Junk, Henning Einloth, Dirk Velten
In 4D printing, an additively manufactured component is given the ability to change its shape or function in an intended and useful manner over time. The technology of 4D printing is still in an early stage of development. Nevertheless, interesting research and initial applications exist in the literature. In this work, a novel methodical approach is presented that helps transfer existing 4D printing research results and knowledge into solving application tasks systematically. Moreover, two different smart materials are analyzed, used, and combined following the presented methodical approach to solving the given task in the form of recovering an object from a poorly accessible space. This is implemented by self-positioning, grabbing, and extracting the target object. The first smart material used to realize these tasks is a shape-memory polymer, while the second is a polymer-based magnetic composite. In addition to the presentation and detailed implementation of the methodical approach, the potentials and behavior of the two smart materials are further examined and narrowed down as a result of the investigation. The results show that the developed methodical approach contributes to moving 4D printing closer toward a viable alternative to existing technologies due to its problem-oriented nature.
{"title":"4D Printing: A Methodical Approach to Product Development Using Smart Materials","authors":"Stefan Junk, Henning Einloth, Dirk Velten","doi":"10.3390/machines11111035","DOIUrl":"https://doi.org/10.3390/machines11111035","url":null,"abstract":"In 4D printing, an additively manufactured component is given the ability to change its shape or function in an intended and useful manner over time. The technology of 4D printing is still in an early stage of development. Nevertheless, interesting research and initial applications exist in the literature. In this work, a novel methodical approach is presented that helps transfer existing 4D printing research results and knowledge into solving application tasks systematically. Moreover, two different smart materials are analyzed, used, and combined following the presented methodical approach to solving the given task in the form of recovering an object from a poorly accessible space. This is implemented by self-positioning, grabbing, and extracting the target object. The first smart material used to realize these tasks is a shape-memory polymer, while the second is a polymer-based magnetic composite. In addition to the presentation and detailed implementation of the methodical approach, the potentials and behavior of the two smart materials are further examined and narrowed down as a result of the investigation. The results show that the developed methodical approach contributes to moving 4D printing closer toward a viable alternative to existing technologies due to its problem-oriented nature.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"1 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139256051","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}
Pub Date : 2023-11-20DOI: 10.3390/machines11111036
Niels Divens, Théo Tuerlinckx, Bernhard Westerhof, Kurt Stockman, David van Os, Koen Laurijssen
This paper assesses the energy consumption, control performance, and application-specific functional requirements of a modular drivetrain in comparison to a benchmark drivetrain. A decentralised control architecture has been developed and validated using mechanical plant models. Simscape models have been validated with data from an experimental setup including an equivalent modular and benchmark drivetrain. In addition, the control strategy has been implemented and validated on the experimental setup. The results prove the ability of the control strategy to synchronize the motion of the different sliders, resulting in crank position tracking errors below 0.032 radians on the setup. The model and experimental data show an increased performance of the modular drivetrain compared to the benchmark drivetrain in terms of energy consumption, control performance, and functional requirements. The modular drivetrain is especially advantageous for machines running highly dynamic motion profiles due to the reduced inertia. For such motion profiles, an increased position tracking of up to 84% has been measured. In addition, it is shown that the modular drivetrain root mean square (RMS) torque is reduced with 32% compared to the benchmark drivetrain. However, these mechanical energy savings are partly counteracted by the higher motor losses seen in the modular drivetrain, resulting in potential electrical energy savings of around 29%.
{"title":"Increased Dynamic Drivetrain Performance by Implementing a Modular Design with Decentralized Control Architecture","authors":"Niels Divens, Théo Tuerlinckx, Bernhard Westerhof, Kurt Stockman, David van Os, Koen Laurijssen","doi":"10.3390/machines11111036","DOIUrl":"https://doi.org/10.3390/machines11111036","url":null,"abstract":"This paper assesses the energy consumption, control performance, and application-specific functional requirements of a modular drivetrain in comparison to a benchmark drivetrain. A decentralised control architecture has been developed and validated using mechanical plant models. Simscape models have been validated with data from an experimental setup including an equivalent modular and benchmark drivetrain. In addition, the control strategy has been implemented and validated on the experimental setup. The results prove the ability of the control strategy to synchronize the motion of the different sliders, resulting in crank position tracking errors below 0.032 radians on the setup. The model and experimental data show an increased performance of the modular drivetrain compared to the benchmark drivetrain in terms of energy consumption, control performance, and functional requirements. The modular drivetrain is especially advantageous for machines running highly dynamic motion profiles due to the reduced inertia. For such motion profiles, an increased position tracking of up to 84% has been measured. In addition, it is shown that the modular drivetrain root mean square (RMS) torque is reduced with 32% compared to the benchmark drivetrain. However, these mechanical energy savings are partly counteracted by the higher motor losses seen in the modular drivetrain, resulting in potential electrical energy savings of around 29%.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"57 3","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139258803","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}
Pub Date : 2023-11-20DOI: 10.3390/machines11111034
Eunkyeong Kim, Seunghwan Jung, Minseok Kim, Jinyong Kim, Baekcheon Kim, Jonggeun Kim, Sungshin Kim
Machine tools are used in a wide range of applications, and they can manufacture workpieces flexibly. Furthermore, they require maintenance; the overall costs include maintenance costs, which constitute a significant portion, and the costs involved in ensuring product quality. Therefore, anomaly detection in tool conditions is required, because these tools are essential industrial elements. However, the data related to tool conditions present some challenges: data imbalances and deficiencies. Data imbalances and deficiencies can affect the performance of anomaly detection models. A model trained using data with imbalances and deficiencies may miscalculate that abnormal data are normal data, leasing to errors. To overcome these problems, the proposed method has been designed using the wavelet transform, color space conversion, color extraction, puzzle-based data augmentation, and double transfer learning. The proposed method generated image data from time-series data, effectively extracted features, and generated new image data using puzzle-based data augmentation. The color information was processed to highlight features, and the proposed puzzle-based data augmentation was applied during processing to increase the amount of data to improve the performance of the anomaly detection model. The experimental results showed that the proposed method can classify normal and abnormal data with greater accuracy. In particular, the accuracy of abnormal data classification increased from 25.00% to 91.67%. This demonstrates that the proposed method is effective and can overcome data imbalances and deficiencies.
{"title":"Anomaly Detection Using Puzzle-Based Data Augmentation to Overcome Data Imbalances and Deficiencies","authors":"Eunkyeong Kim, Seunghwan Jung, Minseok Kim, Jinyong Kim, Baekcheon Kim, Jonggeun Kim, Sungshin Kim","doi":"10.3390/machines11111034","DOIUrl":"https://doi.org/10.3390/machines11111034","url":null,"abstract":"Machine tools are used in a wide range of applications, and they can manufacture workpieces flexibly. Furthermore, they require maintenance; the overall costs include maintenance costs, which constitute a significant portion, and the costs involved in ensuring product quality. Therefore, anomaly detection in tool conditions is required, because these tools are essential industrial elements. However, the data related to tool conditions present some challenges: data imbalances and deficiencies. Data imbalances and deficiencies can affect the performance of anomaly detection models. A model trained using data with imbalances and deficiencies may miscalculate that abnormal data are normal data, leasing to errors. To overcome these problems, the proposed method has been designed using the wavelet transform, color space conversion, color extraction, puzzle-based data augmentation, and double transfer learning. The proposed method generated image data from time-series data, effectively extracted features, and generated new image data using puzzle-based data augmentation. The color information was processed to highlight features, and the proposed puzzle-based data augmentation was applied during processing to increase the amount of data to improve the performance of the anomaly detection model. The experimental results showed that the proposed method can classify normal and abnormal data with greater accuracy. In particular, the accuracy of abnormal data classification increased from 25.00% to 91.67%. This demonstrates that the proposed method is effective and can overcome data imbalances and deficiencies.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"1 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139258223","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}
Pub Date : 2023-11-19DOI: 10.3390/machines11111032
Robin Ströbel, Alexander Bott, Andreas Wortmann, Jürgen Fleischer
In today’s manufacturing landscape, Digital Twins play a pivotal role in optimising processes and deriving actionable insights that extend beyond on-site calculations. These dynamic representations of systems demand real-time data on the actual state of machinery, rather than static images depicting idealized configurations. This paper presents a novel approach for monitoring tool and component wear in CNC milling machines by segmenting and classifying individual machining cycles. The method assumes recurring sequences, even with a batch size of 1, and considers a progressive increase in tool wear between cycles. The algorithms effectively segment and classify cycles based on path length, spindle speed and cycle duration. The tool condition index for each cycle is determined by considering all axis signals, with upper and lower thresholds established for quantifying tool conditions. The same approach is adapted to predict component wear progression in machine tools, ensuring robust condition determination. A percentage-based component state description is achieved by comparing it to the corresponding Tool Condition Codes (TCC) range. This method provides a four-class estimation of the component state. The approach has demonstrated robustness in various validation cases.
{"title":"Monitoring of Tool and Component Wear for Self-Adaptive Digital Twins: A Multi-Stage Approach through Anomaly Detection and Wear Cycle Analysis","authors":"Robin Ströbel, Alexander Bott, Andreas Wortmann, Jürgen Fleischer","doi":"10.3390/machines11111032","DOIUrl":"https://doi.org/10.3390/machines11111032","url":null,"abstract":"In today’s manufacturing landscape, Digital Twins play a pivotal role in optimising processes and deriving actionable insights that extend beyond on-site calculations. These dynamic representations of systems demand real-time data on the actual state of machinery, rather than static images depicting idealized configurations. This paper presents a novel approach for monitoring tool and component wear in CNC milling machines by segmenting and classifying individual machining cycles. The method assumes recurring sequences, even with a batch size of 1, and considers a progressive increase in tool wear between cycles. The algorithms effectively segment and classify cycles based on path length, spindle speed and cycle duration. The tool condition index for each cycle is determined by considering all axis signals, with upper and lower thresholds established for quantifying tool conditions. The same approach is adapted to predict component wear progression in machine tools, ensuring robust condition determination. A percentage-based component state description is achieved by comparing it to the corresponding Tool Condition Codes (TCC) range. This method provides a four-class estimation of the component state. The approach has demonstrated robustness in various validation cases.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"39 3","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139259927","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}
Pub Date : 2023-11-17DOI: 10.3390/machines11111029
Dimitrios A. Moysidis, Georgios D. Karatzinis, Y. Boutalis, Y. L. Karnavas
As the field of fault diagnosis in electrical machines has significantly attracted the interest of the research community in recent years, several methods have arisen in the literature. Also, raw data signals can be acquired easily nowadays, and, thus, machine learning (ML) and deep learning (DL) are candidate tools for effective diagnosis. At the same time, a challenging task is to identify the presence and type of a bearing fault under noisy conditions, especially when relevant faults are at their incipient stage. Since, in real-world applications and especially in industrial processes, electrical machines operate in constantly noisy environments, a key to an effective approach lies in the preprocessing stage adopted. In this work, an evaluation study is conducted to find the most suitable signal preprocessing techniques and the most effective model for fault diagnosis of 16 conditions/classes, from a low-workload (computational burden) perspective using a well-known dataset. More specifically, the reliability and resiliency of conventional ML and DL models is investigated here, towards rolling bearing fault detection, simulating data that correspond to noisy industrial environments. Diverse preprocessing methods are applied in order to study the performance of different training methods from the feature extraction perspective. These feature extraction methods include statistical features in time-domain analysis (TDA); wavelet packet decomposition (WPD); continuous wavelet transform (CWT); and signal-to-image conversion (SIC), utilizing raw vibration signals acquired under varying load conditions. The noise effect is examined and thoroughly commented on. Finally, the paper provides accumulated usual practices in the sense of preferred preprocessing methods and training models under different load and noise conditions.
近年来，电机故障诊断领域引起了研究界的极大兴趣，文献中也出现了多种方法。此外，如今原始数据信号可以轻松获取，因此机器学习（ML）和深度学习（DL）成为有效诊断的候选工具。同时，一项具有挑战性的任务是在噪声条件下识别轴承故障的存在和类型，尤其是当相关故障处于萌芽阶段时。由于在实际应用中，特别是在工业流程中，电机是在持续噪声环境下运行的，因此有效方法的关键在于所采用的预处理阶段。在这项工作中，我们利用一个著名的数据集，从低工作量（计算负担）的角度出发，进行了一项评估研究，以找到最合适的信号预处理技术和最有效的模型，用于 16 种条件/类别的故障诊断。更具体地说，本文研究了传统 ML 和 DL 模型在滚动轴承故障检测方面的可靠性和适应性，模拟了对应于噪声工业环境的数据。为了从特征提取的角度研究不同训练方法的性能，我们采用了多种预处理方法。这些特征提取方法包括时域分析（TDA）中的统计特征、小波包分解（WPD）、连续小波变换（CWT）和信号到图像转换（SIC），利用的是在不同负载条件下获取的原始振动信号。本文对噪声影响进行了研究和深入评述。最后，本文提供了在不同负载和噪声条件下的首选预处理方法和训练模型方面积累的通常做法。
{"title":"A Study of Noise Effect in Electrical Machines Bearing Fault Detection and Diagnosis Considering Different Representative Feature Models","authors":"Dimitrios A. Moysidis, Georgios D. Karatzinis, Y. Boutalis, Y. L. Karnavas","doi":"10.3390/machines11111029","DOIUrl":"https://doi.org/10.3390/machines11111029","url":null,"abstract":"As the field of fault diagnosis in electrical machines has significantly attracted the interest of the research community in recent years, several methods have arisen in the literature. Also, raw data signals can be acquired easily nowadays, and, thus, machine learning (ML) and deep learning (DL) are candidate tools for effective diagnosis. At the same time, a challenging task is to identify the presence and type of a bearing fault under noisy conditions, especially when relevant faults are at their incipient stage. Since, in real-world applications and especially in industrial processes, electrical machines operate in constantly noisy environments, a key to an effective approach lies in the preprocessing stage adopted. In this work, an evaluation study is conducted to find the most suitable signal preprocessing techniques and the most effective model for fault diagnosis of 16 conditions/classes, from a low-workload (computational burden) perspective using a well-known dataset. More specifically, the reliability and resiliency of conventional ML and DL models is investigated here, towards rolling bearing fault detection, simulating data that correspond to noisy industrial environments. Diverse preprocessing methods are applied in order to study the performance of different training methods from the feature extraction perspective. These feature extraction methods include statistical features in time-domain analysis (TDA); wavelet packet decomposition (WPD); continuous wavelet transform (CWT); and signal-to-image conversion (SIC), utilizing raw vibration signals acquired under varying load conditions. The noise effect is examined and thoroughly commented on. Finally, the paper provides accumulated usual practices in the sense of preferred preprocessing methods and training models under different load and noise conditions.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"31 12","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139266137","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}
Pub Date : 2023-11-17DOI: 10.3390/machines11111030
Demetrio Pérez-Vigueras, J. Colín-Ocampo, Andrés Blanco-Ortega, R. Campos-Amezcua, Cuauhtémoc Mazón-Valadez, Víctor I. Rodríguez-Reyes, Saulo Jesús Landa-Damas
This paper is a review of the literature about CFD modeling and analysis of journal, thrust, and aerostatic bearings; the advantages and disadvantages of each are specified, and the bearing problems that have been analyzed are discussed to improve their designs and performance. A CFD transient analysis of journal bearings was conducted using the dynamic mesh method together with movement algorithms while keeping a structured mesh of a good quality in the ANSYS Fluent software to determine the equilibrium position of the journal and calculate the dynamic coefficients. Finally, areas of opportunity for analyzing and designing fluid film bearings to improve their performance are proposed.
{"title":"Fluid Film Bearings and CFD Modeling: A Review","authors":"Demetrio Pérez-Vigueras, J. Colín-Ocampo, Andrés Blanco-Ortega, R. Campos-Amezcua, Cuauhtémoc Mazón-Valadez, Víctor I. Rodríguez-Reyes, Saulo Jesús Landa-Damas","doi":"10.3390/machines11111030","DOIUrl":"https://doi.org/10.3390/machines11111030","url":null,"abstract":"This paper is a review of the literature about CFD modeling and analysis of journal, thrust, and aerostatic bearings; the advantages and disadvantages of each are specified, and the bearing problems that have been analyzed are discussed to improve their designs and performance. A CFD transient analysis of journal bearings was conducted using the dynamic mesh method together with movement algorithms while keeping a structured mesh of a good quality in the ANSYS Fluent software to determine the equilibrium position of the journal and calculate the dynamic coefficients. Finally, areas of opportunity for analyzing and designing fluid film bearings to improve their performance are proposed.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"54 12","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139262567","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}
Pub Date : 2023-11-17DOI: 10.3390/machines11111027
Haixiang Lin, Nana Hu, Ran Lu, Tengfei Yuan, Zhengxiang Zhao, Wansheng Bai, Qi Lin
The fault diagnosis of a switch machine is vital for high-speed railway operations because switch machines play an important role in the safe operation of high-speed railways, which often have faults because of their complicated working conditions. To improve the accuracy of turnout fault diagnosis for high-speed railways and prevent accidents from occurring, a combination of bi-directional long short-term memory (BiLSTM) with the multiple learning classification based on associations (MLCBA) model using the operation and maintenance text data of switch machines is proposed in this research. Due to the small probability of faults for a switch machine, it is difficult to form a diagnosis with the small amount of sample data, and more fault text features can be extracted with feedforward in a BiLSTM model. Then, the high-quality rules of the text data can be acquired by replacing the SoftMax classification with MLCBA in the output of the BiLSTM model. In this way, the identification of switch machine faults in a high-speed railway can be realized, and the experimental results show that the Accuracy and Recall of the fault diagnosis can reach 95.66% and 96.29%, respectively, as shown in the analysis of the ZYJ7 turnout fault text data of a Chinese railway bureau from five recent years. Therefore, the combined BiLSTM and MLCBA model can not only realize the accurate diagnosis of small-probability turnout faults but can also prevent high-speed railway accidents from occurring and ensure the safe operation of high-speed railways.
{"title":"Fault Diagnosis of a Switch Machine to Prevent High-Speed Railway Accidents Combining Bi-Directional Long Short-Term Memory with the Multiple Learning Classification Based on Associations Model","authors":"Haixiang Lin, Nana Hu, Ran Lu, Tengfei Yuan, Zhengxiang Zhao, Wansheng Bai, Qi Lin","doi":"10.3390/machines11111027","DOIUrl":"https://doi.org/10.3390/machines11111027","url":null,"abstract":"The fault diagnosis of a switch machine is vital for high-speed railway operations because switch machines play an important role in the safe operation of high-speed railways, which often have faults because of their complicated working conditions. To improve the accuracy of turnout fault diagnosis for high-speed railways and prevent accidents from occurring, a combination of bi-directional long short-term memory (BiLSTM) with the multiple learning classification based on associations (MLCBA) model using the operation and maintenance text data of switch machines is proposed in this research. Due to the small probability of faults for a switch machine, it is difficult to form a diagnosis with the small amount of sample data, and more fault text features can be extracted with feedforward in a BiLSTM model. Then, the high-quality rules of the text data can be acquired by replacing the SoftMax classification with MLCBA in the output of the BiLSTM model. In this way, the identification of switch machine faults in a high-speed railway can be realized, and the experimental results show that the Accuracy and Recall of the fault diagnosis can reach 95.66% and 96.29%, respectively, as shown in the analysis of the ZYJ7 turnout fault text data of a Chinese railway bureau from five recent years. Therefore, the combined BiLSTM and MLCBA model can not only realize the accurate diagnosis of small-probability turnout faults but can also prevent high-speed railway accidents from occurring and ensure the safe operation of high-speed railways.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"24 3","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139263334","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}
Pub Date : 2023-11-15DOI: 10.3390/machines11111025
M. Michalec, Jan Foltýn, Tomáš Dryml, Lukáš Snopek, Dominik Javorský, Martin Čupr, Petr Svoboda
Hydrostatic bearings come with certain advantages over rolling bearings in moving large-scale structures. However, assembly errors are a serious matter on large scales. This study focuses on finding assembly error tolerances for the most common types in segmented errors of hydrostatic bearing sliders: tilt and offset. The experimental part was performed in the laboratory on a full diagnostic hydrostatic bearing testing rig. An investigation of the type of error on bearing performance was first conducted under static conditions. We identified the limiting error-to-film thickness ratio (e/h) for static offset error as 2.5 and the tilt angle as θ = 0.46° for the investigated case. Subsequently, two types of offset error were investigated under slow-speed conditions at 38 mm/s. The limiting error for the offset error considering the relative bi-directional movement of the slider and the pad was determined as e/h < 1. The results further indicate that the error tolerance would further decrease with increasing speed. The experimental results of error tolerances can be used to determine the required film thickness or vice versa.
{"title":"Assembly Error Tolerance Estimation for Large-Scale Hydrostatic Bearing Segmented Sliders under Static and Low-Speed Conditions","authors":"M. Michalec, Jan Foltýn, Tomáš Dryml, Lukáš Snopek, Dominik Javorský, Martin Čupr, Petr Svoboda","doi":"10.3390/machines11111025","DOIUrl":"https://doi.org/10.3390/machines11111025","url":null,"abstract":"Hydrostatic bearings come with certain advantages over rolling bearings in moving large-scale structures. However, assembly errors are a serious matter on large scales. This study focuses on finding assembly error tolerances for the most common types in segmented errors of hydrostatic bearing sliders: tilt and offset. The experimental part was performed in the laboratory on a full diagnostic hydrostatic bearing testing rig. An investigation of the type of error on bearing performance was first conducted under static conditions. We identified the limiting error-to-film thickness ratio (e/h) for static offset error as 2.5 and the tilt angle as θ = 0.46° for the investigated case. Subsequently, two types of offset error were investigated under slow-speed conditions at 38 mm/s. The limiting error for the offset error considering the relative bi-directional movement of the slider and the pad was determined as e/h < 1. The results further indicate that the error tolerance would further decrease with increasing speed. The experimental results of error tolerances can be used to determine the required film thickness or vice versa.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"2 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139274646","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：