Pub Date : 2024-05-03DOI: 10.3390/machines12050315
Gabriella Faina Garcia Garcia, R. S. Gonçalves, Giuseppe Carbone
Various conditions, including traffic accidents, sports injuries, and neurological disorders, can impair human wrist movements, underscoring the importance of effective rehabilitation methods. Robotic devices play a crucial role in this regard, particularly in wrist rehabilitation, given the complexity of the human wrist joint, which encompasses three degrees of freedom: flexion/extension, pronation/supination, and radial/ulnar deviation. This paper provides a comprehensive review of wrist rehabilitation devices, employing a methodological approach based on primary articles sourced from PubMed, ScienceDirect, Scopus, and IEEE, using the keywords “wrist rehabilitation robot” from 2007 onwards. The findings highlight a diverse array of wrist rehabilitation devices, systematically organized in a tabular format for enhanced comprehension. Serving as a valuable resource for researchers, this paper enables comparative analyses of robotic wrist rehabilitation devices across various attributes, offering insights into future advancements. Particularly noteworthy is the integration of serious games with simplified wrist rehabilitation devices, signaling a promising avenue for enhancing rehabilitation outcomes. These insights lay the groundwork for the development of new robotic wrist rehabilitation devices or to make improvements to existing prototypes incorporating a forward-looking approach to improve rehabilitation outcomes.
{"title":"A Review of Wrist Rehabilitation Robots and Highlights Needed for New Devices","authors":"Gabriella Faina Garcia Garcia, R. S. Gonçalves, Giuseppe Carbone","doi":"10.3390/machines12050315","DOIUrl":"https://doi.org/10.3390/machines12050315","url":null,"abstract":"Various conditions, including traffic accidents, sports injuries, and neurological disorders, can impair human wrist movements, underscoring the importance of effective rehabilitation methods. Robotic devices play a crucial role in this regard, particularly in wrist rehabilitation, given the complexity of the human wrist joint, which encompasses three degrees of freedom: flexion/extension, pronation/supination, and radial/ulnar deviation. This paper provides a comprehensive review of wrist rehabilitation devices, employing a methodological approach based on primary articles sourced from PubMed, ScienceDirect, Scopus, and IEEE, using the keywords “wrist rehabilitation robot” from 2007 onwards. The findings highlight a diverse array of wrist rehabilitation devices, systematically organized in a tabular format for enhanced comprehension. Serving as a valuable resource for researchers, this paper enables comparative analyses of robotic wrist rehabilitation devices across various attributes, offering insights into future advancements. Particularly noteworthy is the integration of serious games with simplified wrist rehabilitation devices, signaling a promising avenue for enhancing rehabilitation outcomes. These insights lay the groundwork for the development of new robotic wrist rehabilitation devices or to make improvements to existing prototypes incorporating a forward-looking approach to improve rehabilitation outcomes.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141016532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-03DOI: 10.3390/machines12050313
O. Onysko, V. Kopei, Cristian Barz, Yaroslav Kusyi, S. Baskutis, M. Bembenek, P. Dašić, V. Panchuk
High-precision tapered threads are widely used in hard-loaded mechanical joints, especially in the aggressive environment of the drilling of oil and gas wells. Therefore, they must be made of workable materials often difficult to machine. This requires the use of high-performance cutting tools, which means the application of non-zero geometric parameters: rake and edge inclination angles. This study is based on analytical geometry methodology and describes the theoretical function of the thread profile as convoluted surfaces dependent on the tool’s geometric angles. The experiments were conducted using a visual algorithm grounded on the obtained function and prove the practical use of the scientific result. They predict the required accuracy of thread made using a lathe tool with a rake angle of up to 12°.
{"title":"Analytical Model of Tapered Thread Made by Turning from Different Machinability Workpieces","authors":"O. Onysko, V. Kopei, Cristian Barz, Yaroslav Kusyi, S. Baskutis, M. Bembenek, P. Dašić, V. Panchuk","doi":"10.3390/machines12050313","DOIUrl":"https://doi.org/10.3390/machines12050313","url":null,"abstract":"High-precision tapered threads are widely used in hard-loaded mechanical joints, especially in the aggressive environment of the drilling of oil and gas wells. Therefore, they must be made of workable materials often difficult to machine. This requires the use of high-performance cutting tools, which means the application of non-zero geometric parameters: rake and edge inclination angles. This study is based on analytical geometry methodology and describes the theoretical function of the thread profile as convoluted surfaces dependent on the tool’s geometric angles. The experiments were conducted using a visual algorithm grounded on the obtained function and prove the practical use of the scientific result. They predict the required accuracy of thread made using a lathe tool with a rake angle of up to 12°.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141016605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-02DOI: 10.3390/machines12050312
J. Maximov, G. Duncheva
When placed under cryogenic temperatures (below −180 °C), metallic materials undergo structural changes that can improve their service life. This process, known as cryogenic treatment (CrT), has received extensive research attention over the past five decades. CrT can be applied as either an autonomous process (for steels and non-ferrous alloys, tool materials, and finished products) or as an assisting process for conventional metalworking. Cryogenic impacts and conventional machining or static surface cold working (SCW) can also be performed simultaneously in hybrid processes. The static SCW, known as burnishing, is a widely used environmentally friendly finishing process that achieves high-quality surfaces of metal components. The present review is dedicated to the portion of the hybrid processes in which burnishing under cryogenic conditions is carried out from the viewpoint of surface engineering, namely, finishing–surface integrity (SI)–operational behavior. Analyzes and summaries of the effects of cryogenic-assisted (CrA) burnishing on SI and the operational behavior of the investigated materials are made, and perspectives for future research are proposed.
当金属材料被置于低温（低于 -180 °C）环境中时，其结构会发生变化，从而延长其使用寿命。这一过程被称为低温处理（CrT），在过去的五十年里受到了广泛的研究关注。低温处理既可以作为一种独立的工艺（适用于钢和有色金属合金、工具材料和成品），也可以作为传统金属加工的辅助工艺。低温冲击和传统加工或静态表面冷加工（SCW）也可以在混合工艺中同时进行。静态表面冷加工（SCW）被称为 "抛光"，是一种广泛使用的环保型精加工工艺，可获得高质量的金属部件表面。本综述从表面工程的角度，即精加工-表面完整性（SI）-操作行为的角度，专门讨论了混合工艺中在低温条件下进行灼烧的部分。分析和总结了低温辅助（CrA）灼烧对 SI 和所研究材料操作行为的影响，并提出了未来研究的展望。
{"title":"Effects of Cryogenic- and Cool-Assisted Burnishing on the Surface Integrity and Operating Behavior of Metal Components: A Review and Perspectives","authors":"J. Maximov, G. Duncheva","doi":"10.3390/machines12050312","DOIUrl":"https://doi.org/10.3390/machines12050312","url":null,"abstract":"When placed under cryogenic temperatures (below −180 °C), metallic materials undergo structural changes that can improve their service life. This process, known as cryogenic treatment (CrT), has received extensive research attention over the past five decades. CrT can be applied as either an autonomous process (for steels and non-ferrous alloys, tool materials, and finished products) or as an assisting process for conventional metalworking. Cryogenic impacts and conventional machining or static surface cold working (SCW) can also be performed simultaneously in hybrid processes. The static SCW, known as burnishing, is a widely used environmentally friendly finishing process that achieves high-quality surfaces of metal components. The present review is dedicated to the portion of the hybrid processes in which burnishing under cryogenic conditions is carried out from the viewpoint of surface engineering, namely, finishing–surface integrity (SI)–operational behavior. Analyzes and summaries of the effects of cryogenic-assisted (CrA) burnishing on SI and the operational behavior of the investigated materials are made, and perspectives for future research are proposed.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141019209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-02DOI: 10.3390/machines12050310
Yin Liu, Cunxian Ma, Yun Huang
In digital product and ion scheduling centers, order–factory allocation, factory–mold allocation, and mold routing can be performed centrally and efficiently to maximize the utilization of manufacturing resources (molds). Therefore, in this paper, a manufacturing resource (molds)-sharing mechanism based on the Internet of Things (IoT) and a cyber-physical production system (CPPS) is designed to realize the coordinated allocation of molds and production scheduling. A mixed-integer mathematical model is developed to optimize the cost structure and obtain a reasonable profit solution. A heuristic algorithm based on evolutionary reversal is used to solve the problem. The numerical results show that based on the digital coordinated production scheduling method, distributed two-stage assembly manufacturing with shared molds can effectively reduce the order delay time and increase potential benefits for distributed production enterprises.
{"title":"An Internet of Things-Based Production Scheduling for Distributed Two-Stage Assembly Manufacturing with Mold Sharing","authors":"Yin Liu, Cunxian Ma, Yun Huang","doi":"10.3390/machines12050310","DOIUrl":"https://doi.org/10.3390/machines12050310","url":null,"abstract":"In digital product and ion scheduling centers, order–factory allocation, factory–mold allocation, and mold routing can be performed centrally and efficiently to maximize the utilization of manufacturing resources (molds). Therefore, in this paper, a manufacturing resource (molds)-sharing mechanism based on the Internet of Things (IoT) and a cyber-physical production system (CPPS) is designed to realize the coordinated allocation of molds and production scheduling. A mixed-integer mathematical model is developed to optimize the cost structure and obtain a reasonable profit solution. A heuristic algorithm based on evolutionary reversal is used to solve the problem. The numerical results show that based on the digital coordinated production scheduling method, distributed two-stage assembly manufacturing with shared molds can effectively reduce the order delay time and increase potential benefits for distributed production enterprises.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141020650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-02DOI: 10.3390/machines12050311
Jana Moravčíková, R. Moravčík, M. Sahul, M. Necpal
The article is aimed at identifying the influence of laser texturing and subsequent coating with a hard, wear-resistant coating AlCrSiN (nACRo®) on selected tribological properties of the analyzed tool steels for cold work, produced by conventional and powder metallurgy. The substrate from each steel was heat treated to achieve optimal properties regarding the chemical composition and the method of production of the material. Böhler K100 and K390 Microclean® steels were used. These are highly alloyed tool steels used for various types of tools intended for cold work. The obtained results show that the coefficient of friction is increased by coating, but the wear rate is lower compared to the samples which were only textured.
{"title":"Influence of Laser Texturing and Coating on the Tribological Properties of the Tool Steels Properties","authors":"Jana Moravčíková, R. Moravčík, M. Sahul, M. Necpal","doi":"10.3390/machines12050311","DOIUrl":"https://doi.org/10.3390/machines12050311","url":null,"abstract":"The article is aimed at identifying the influence of laser texturing and subsequent coating with a hard, wear-resistant coating AlCrSiN (nACRo®) on selected tribological properties of the analyzed tool steels for cold work, produced by conventional and powder metallurgy. The substrate from each steel was heat treated to achieve optimal properties regarding the chemical composition and the method of production of the material. Böhler K100 and K390 Microclean® steels were used. These are highly alloyed tool steels used for various types of tools intended for cold work. The obtained results show that the coefficient of friction is increased by coating, but the wear rate is lower compared to the samples which were only textured.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141022456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abnormal detection plays a pivotal role in the routine maintenance of industrial equipment. Malfunctions or breakdowns in the drafting components of spinning equipment can lead to yarn defects, thereby compromising the overall quality of the production line. Fault diagnosis of spinning equipment entails the examination of component defects through Wavelet Spectrogram Analysis (WSA). Conventional detection techniques heavily rely on manual experience and lack generality. To address this limitation, this current study leverages machine learning technology to formulate a semi-supervised anomaly detection approach employing a convolutional autoencoder. This method trains deep neural networks with normal data and employs the reconstruction mode of a convolutional autoencoder in conjunction with Kernel Density Estimation (KDE) to determine the optimal threshold for anomaly detection. This facilitates the differentiation between normal and abnormal operational modes without the necessity for extensive labeled fault data. Experimental results from two sets of industrial data validate the robustness of the proposed methodology. In comparison to conventional Autoencoder and prevalent machine learning techniques, the proposed approach demonstrates superior performance across evaluation metrics such as Accuracy, Recall, Area Under the Curve (AUC), and F1-score, thereby affirming the feasibility of the suggested model.
异常检测在工业设备的日常维护中起着举足轻重的作用。纺纱设备牵伸部件的故障或断裂会导致纱疵，从而影响生产线的整体质量。纺纱设备的故障诊断需要通过小波频谱分析 (WSA) 来检查部件缺陷。传统的检测技术严重依赖人工经验，缺乏通用性。为解决这一局限性，本研究利用机器学习技术制定了一种采用卷积自动编码器的半监督异常检测方法。该方法使用正常数据训练深度神经网络，并结合核密度估计（KDE）使用卷积自动编码器的重构模式来确定异常检测的最佳阈值。这有助于区分正常和异常运行模式，而无需大量标注故障数据。两组工业数据的实验结果验证了所提方法的稳健性。与传统的自动编码器和流行的机器学习技术相比，所提出的方法在准确率、召回率、曲线下面积（AUC）和 F1 分数等评价指标上都表现出卓越的性能，从而肯定了所建议模型的可行性。
{"title":"Enhancing Yarn Quality Wavelength Spectrogram Analysis: A Semi-Supervised Anomaly Detection Approach with Convolutional Autoencoder","authors":"Haoran Wang, Zhongze Han, Xiaoshuang Xiong, Xuewei Song, Chen Shen","doi":"10.3390/machines12050309","DOIUrl":"https://doi.org/10.3390/machines12050309","url":null,"abstract":"Abnormal detection plays a pivotal role in the routine maintenance of industrial equipment. Malfunctions or breakdowns in the drafting components of spinning equipment can lead to yarn defects, thereby compromising the overall quality of the production line. Fault diagnosis of spinning equipment entails the examination of component defects through Wavelet Spectrogram Analysis (WSA). Conventional detection techniques heavily rely on manual experience and lack generality. To address this limitation, this current study leverages machine learning technology to formulate a semi-supervised anomaly detection approach employing a convolutional autoencoder. This method trains deep neural networks with normal data and employs the reconstruction mode of a convolutional autoencoder in conjunction with Kernel Density Estimation (KDE) to determine the optimal threshold for anomaly detection. This facilitates the differentiation between normal and abnormal operational modes without the necessity for extensive labeled fault data. Experimental results from two sets of industrial data validate the robustness of the proposed methodology. In comparison to conventional Autoencoder and prevalent machine learning techniques, the proposed approach demonstrates superior performance across evaluation metrics such as Accuracy, Recall, Area Under the Curve (AUC), and F1-score, thereby affirming the feasibility of the suggested model.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141020548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.3390/machines12050308
Ľ. Dulina, Ján Zuzik, Beáta Furmannová, Sławomir Kukla
The primary objective of this research endeavor was to devise an improved workplace design tailored to the demands of a digital factory environment. With the overarching aim of enhancing efficiency and productivity, a comprehensive proposal was formulated to improve layout configurations within the designated enterprise. The key focus lies in minimizing material transit across individual workstations, thereby mitigating potential bottlenecks and streamlining operations. Employing a structured workplace research framework, this study delved into material flow analysis techniques, augmented by the utilization of visTABLE software. While visTABLE served solely to visualize the work environment effectively, it played a crucial role in validating proposed solutions. Notably, the investigation yielded a discernible reduction in beam production time, marking a significant improvement of 10 min. These findings underscored the efficacy of the proposed solutions in addressing specific operational challenges faced by the company. Furthermore, this study facilitated a deeper understanding and visualization of the processes intrinsic to the digital factory environment. Elucidating workflow procedures at the workplace enabled stakeholders to identify areas for further improvement and refinement. In doing so, the research contributed to the overall efficiency and effectiveness of operations within the digital factory, paving the way for continued improvement and innovation in the field.
{"title":"Improving Material Flows in an Industrial Enterprise: A Comprehensive Case Study Analysis","authors":"Ľ. Dulina, Ján Zuzik, Beáta Furmannová, Sławomir Kukla","doi":"10.3390/machines12050308","DOIUrl":"https://doi.org/10.3390/machines12050308","url":null,"abstract":"The primary objective of this research endeavor was to devise an improved workplace design tailored to the demands of a digital factory environment. With the overarching aim of enhancing efficiency and productivity, a comprehensive proposal was formulated to improve layout configurations within the designated enterprise. The key focus lies in minimizing material transit across individual workstations, thereby mitigating potential bottlenecks and streamlining operations. Employing a structured workplace research framework, this study delved into material flow analysis techniques, augmented by the utilization of visTABLE software. While visTABLE served solely to visualize the work environment effectively, it played a crucial role in validating proposed solutions. Notably, the investigation yielded a discernible reduction in beam production time, marking a significant improvement of 10 min. These findings underscored the efficacy of the proposed solutions in addressing specific operational challenges faced by the company. Furthermore, this study facilitated a deeper understanding and visualization of the processes intrinsic to the digital factory environment. Elucidating workflow procedures at the workplace enabled stakeholders to identify areas for further improvement and refinement. In doing so, the research contributed to the overall efficiency and effectiveness of operations within the digital factory, paving the way for continued improvement and innovation in the field.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141042568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.3390/machines12050305
Yiming Li, Yize Wang, Liuwei Lu, Lumeng Chen
To solve the problem of fault diagnosis for the key components of the CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and an ensemble learning model is proposed in this study. First, various monitoring signals including vibration signals, noise signals, and current signals are collected. Then, the monitoring signals are preprocessed and the time domain, frequency domain, and time–frequency domain feature indices are extracted to construct a multi-dimensional mixed-domain feature set. Finally, the feature set is entered into the constructed DoubleEnsemble–LightGBM model to realize the fault diagnosis of the key components of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the widely used dataset and the feed system test bench dataset, and the average overall accuracy is 91.07% and 98.06%, respectively. Compared with XGBoost and other advanced ensemble learning models, this method demonstrates better accuracy. Therefore, the proposed method provides technical support for the stable operation and intelligence of CNC machines.
{"title":"A Fault Diagnosis Method for Key Components of the CNC Machine Feed System Based on the DoubleEnsemble–LightGBM Model","authors":"Yiming Li, Yize Wang, Liuwei Lu, Lumeng Chen","doi":"10.3390/machines12050305","DOIUrl":"https://doi.org/10.3390/machines12050305","url":null,"abstract":"To solve the problem of fault diagnosis for the key components of the CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and an ensemble learning model is proposed in this study. First, various monitoring signals including vibration signals, noise signals, and current signals are collected. Then, the monitoring signals are preprocessed and the time domain, frequency domain, and time–frequency domain feature indices are extracted to construct a multi-dimensional mixed-domain feature set. Finally, the feature set is entered into the constructed DoubleEnsemble–LightGBM model to realize the fault diagnosis of the key components of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the widely used dataset and the feed system test bench dataset, and the average overall accuracy is 91.07% and 98.06%, respectively. Compared with XGBoost and other advanced ensemble learning models, this method demonstrates better accuracy. Therefore, the proposed method provides technical support for the stable operation and intelligence of CNC machines.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141038253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.3390/machines12050307
Xuejian Zhang, Xiaobing Hu, Hang Li, Zheyuan Zhang, Haijun Chen, Hong Sun
Welding stands as a critical focus for the intelligent and digital transformation of the machinery industry, with automated laser welding playing a pivotal role in the sector’s technological advancement. The management of welding deformation in such operations is fundamental, relying on advanced analysis and prediction methods. The endeavor to accurately analyze welding deformation in practical applications is compounded by the interplay of numerous variables, a pronounced coupling effect among these factors, and a reliance on expert intuition. Thus, effective deformation control in automated laser welding operations necessitates the gathering of pre-test laser welding data to develop a predictive approach that accurately reflects real-world conditions and is characterized by improved reliability and stability. To address the technological evolution in automated laser welding, a predictive model based on neural network technology is proposed to map the intricate relationship between process variables and the resulting deformation. At the heart of this approach is the formulation of a predictive model utilizing a back-propagation neural network (BP), with an emphasis on four essential welding parameters: speed, peak power, duty cycle, and defocusing amount. The model’s predictive accuracy is then honed through the application of the whale optimization algorithm (WOA) and the differential evolutionary (DE) algorithm. Finally, extensive testing in an automated laser welding experimental setup is conducted to validate the accuracy and reliability of the proposed prediction model. It is demonstrated through these experiments that the deformation prediction model, enhanced by the DEWOA-BP neural network, accurately forecasts the relationship between laser welding parameters and the induced deformation, maintaining a prediction error margin of ±0.1mm. The model is employed to fulfill the requirements for a pre-welding quality evaluation, thereby facilitating a more calculated and informed approach to welding operations. This method of intelligent prediction is not only crucial for the intelligent transformation of laser welding but also holds significant implications for traditional machining technologies such as milling, grinding, and spraying. It offers innovative ideas and methods that are pivotal for the industrial revolution and technological advancement of the traditional machining industry.
{"title":"Research on Predicting Welding Deformation in Automated Laser Welding Processes with an Enhanced DEWOA-BP Algorithm","authors":"Xuejian Zhang, Xiaobing Hu, Hang Li, Zheyuan Zhang, Haijun Chen, Hong Sun","doi":"10.3390/machines12050307","DOIUrl":"https://doi.org/10.3390/machines12050307","url":null,"abstract":"Welding stands as a critical focus for the intelligent and digital transformation of the machinery industry, with automated laser welding playing a pivotal role in the sector’s technological advancement. The management of welding deformation in such operations is fundamental, relying on advanced analysis and prediction methods. The endeavor to accurately analyze welding deformation in practical applications is compounded by the interplay of numerous variables, a pronounced coupling effect among these factors, and a reliance on expert intuition. Thus, effective deformation control in automated laser welding operations necessitates the gathering of pre-test laser welding data to develop a predictive approach that accurately reflects real-world conditions and is characterized by improved reliability and stability. To address the technological evolution in automated laser welding, a predictive model based on neural network technology is proposed to map the intricate relationship between process variables and the resulting deformation. At the heart of this approach is the formulation of a predictive model utilizing a back-propagation neural network (BP), with an emphasis on four essential welding parameters: speed, peak power, duty cycle, and defocusing amount. The model’s predictive accuracy is then honed through the application of the whale optimization algorithm (WOA) and the differential evolutionary (DE) algorithm. Finally, extensive testing in an automated laser welding experimental setup is conducted to validate the accuracy and reliability of the proposed prediction model. It is demonstrated through these experiments that the deformation prediction model, enhanced by the DEWOA-BP neural network, accurately forecasts the relationship between laser welding parameters and the induced deformation, maintaining a prediction error margin of ±0.1mm. The model is employed to fulfill the requirements for a pre-welding quality evaluation, thereby facilitating a more calculated and informed approach to welding operations. This method of intelligent prediction is not only crucial for the intelligent transformation of laser welding but also holds significant implications for traditional machining technologies such as milling, grinding, and spraying. It offers innovative ideas and methods that are pivotal for the industrial revolution and technological advancement of the traditional machining industry.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141047349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.3390/machines12050306
Ziteng Li, Xinnan Lei, Zhichao You, Tao Huang, Kai Guo, Duo Li, Huan Liu
Since tool wear accumulates in the cutting process, the condition of the cutting tool shows a degradation trend, which ultimately affects the surface quality. Tool wear monitoring and prediction are of significant importance in intelligent manufacturing. The cutting signal shows short-term randomness due to non-uniform materials in the workpiece, making it difficult to accurately monitor tool condition by relying on instantaneous signals. To reduce the impact of transient fluctuations, this paper proposes a novel network based on deep learning to monitor and predict tool wear. Firstly, a CNN model based on residual connection was designed to extract deep features from multi-sensor signals. After that, a temporal model based on an encoder and decoder was built for short-term monitoring and long-term prediction. It captured the instantaneous features and long-term trend features by mining the temporal dependence of the signals. In addition, an encoder and decoder-based temporal model is proposed for smoothing correction to improve the estimation accuracy of the temporal model. To validate the performance of the proposed model, the PHM dataset was used for wear monitoring and prediction and compared with other deep learning models. In addition, CFRP milling experiments were conducted to verify the stability and generalization of the model under different machining conditions. The experimental results show that the model outperformed other deep learning models in terms of MAE, MAPE, and RMSE.
{"title":"Tool Wear Prediction Based on Residual Connection and Temporal Networks","authors":"Ziteng Li, Xinnan Lei, Zhichao You, Tao Huang, Kai Guo, Duo Li, Huan Liu","doi":"10.3390/machines12050306","DOIUrl":"https://doi.org/10.3390/machines12050306","url":null,"abstract":"Since tool wear accumulates in the cutting process, the condition of the cutting tool shows a degradation trend, which ultimately affects the surface quality. Tool wear monitoring and prediction are of significant importance in intelligent manufacturing. The cutting signal shows short-term randomness due to non-uniform materials in the workpiece, making it difficult to accurately monitor tool condition by relying on instantaneous signals. To reduce the impact of transient fluctuations, this paper proposes a novel network based on deep learning to monitor and predict tool wear. Firstly, a CNN model based on residual connection was designed to extract deep features from multi-sensor signals. After that, a temporal model based on an encoder and decoder was built for short-term monitoring and long-term prediction. It captured the instantaneous features and long-term trend features by mining the temporal dependence of the signals. In addition, an encoder and decoder-based temporal model is proposed for smoothing correction to improve the estimation accuracy of the temporal model. To validate the performance of the proposed model, the PHM dataset was used for wear monitoring and prediction and compared with other deep learning models. In addition, CFRP milling experiments were conducted to verify the stability and generalization of the model under different machining conditions. The experimental results show that the model outperformed other deep learning models in terms of MAE, MAPE, and RMSE.","PeriodicalId":509264,"journal":{"name":"Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141031677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：