Pub Date : 2023-12-29DOI: 10.3390/machines12010023
A. Zaman, Jaho Seo
This study presents a drone-based excavation platform prototype with the key objectives of balancing stability during excavation, sensing, and digging the soil pile autonomously without human intervention. The whole platform was first designed in CAD software, and then each part of the excavator assembly was 3D printed by using PLA filament. The physical system was then combined with numerous electronic components and linked to various software applications for a drone to perform autonomous excavations. Pixhawk Orange Cube served as the main controller for the drone, while Nvidia Jetson Nano was used for processing data and controlling the tip of the bucket at a specified location for the autonomous excavator. Two scenarios were considered to validate the functionality of the developed platform. In the first scenario, the drone flies independently to a construction site, lands, senses the soil, excavates it, and then travels to another location specified by the mission to deposit the soil.
{"title":"Design and Control of Autonomous Flying Excavator","authors":"A. Zaman, Jaho Seo","doi":"10.3390/machines12010023","DOIUrl":"https://doi.org/10.3390/machines12010023","url":null,"abstract":"This study presents a drone-based excavation platform prototype with the key objectives of balancing stability during excavation, sensing, and digging the soil pile autonomously without human intervention. The whole platform was first designed in CAD software, and then each part of the excavator assembly was 3D printed by using PLA filament. The physical system was then combined with numerous electronic components and linked to various software applications for a drone to perform autonomous excavations. Pixhawk Orange Cube served as the main controller for the drone, while Nvidia Jetson Nano was used for processing data and controlling the tip of the bucket at a specified location for the autonomous excavator. Two scenarios were considered to validate the functionality of the developed platform. In the first scenario, the drone flies independently to a construction site, lands, senses the soil, excavates it, and then travels to another location specified by the mission to deposit the soil.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"79 4","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139147348","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 : 2023-12-29DOI: 10.3390/machines12010022
Feng Shi, Yi Yang, Nianjun Sun, Zhaocai Du, Chen Zhang, Dongjie Zhao
In order to enhance application scenarios and increase the proportion of industrial robots in the field of drilling composites, the damage caused by carbon-fiber-reinforced polymer robotic drilling is studied. The shortcomings of the existing damage evaluation factors are analyzed, and new damage evaluation factors for carbon-fiber-reinforced polymer laminates made of unidirectional prepreg are proposed. A robot and a brad-and-spur drill were used to drill carbon-fiber-reinforced polymer laminates to study the influence of the process parameters on robotic drilling damage. Digital image correlation equipment and industrial computed tomography were used to study the formation process and the damage forms of the hole on the exit side with different process parameters. The test results show that delamination and tearing are significantly affected by the feed rate and spindle speed, while burrs are less affected by the cutting parameters. Appropriately increasing the spindle speed and reducing the feed rate are beneficial to reducing the comprehensive damage factor and improving the hole quality. To avoid hole scrapping caused by a large amount of damage, it is suggested that the robotic drilling parameters should be controlled at a spindle speed higher than 8000 rpm and a feed rate lower than 360 mm/min.
{"title":"Research on Damage Caused by Carbon-Fiber-Reinforced Polymer Robotic Drilling Based on Digital Image Correlation and Industrial Computed Tomography","authors":"Feng Shi, Yi Yang, Nianjun Sun, Zhaocai Du, Chen Zhang, Dongjie Zhao","doi":"10.3390/machines12010022","DOIUrl":"https://doi.org/10.3390/machines12010022","url":null,"abstract":"In order to enhance application scenarios and increase the proportion of industrial robots in the field of drilling composites, the damage caused by carbon-fiber-reinforced polymer robotic drilling is studied. The shortcomings of the existing damage evaluation factors are analyzed, and new damage evaluation factors for carbon-fiber-reinforced polymer laminates made of unidirectional prepreg are proposed. A robot and a brad-and-spur drill were used to drill carbon-fiber-reinforced polymer laminates to study the influence of the process parameters on robotic drilling damage. Digital image correlation equipment and industrial computed tomography were used to study the formation process and the damage forms of the hole on the exit side with different process parameters. The test results show that delamination and tearing are significantly affected by the feed rate and spindle speed, while burrs are less affected by the cutting parameters. Appropriately increasing the spindle speed and reducing the feed rate are beneficial to reducing the comprehensive damage factor and improving the hole quality. To avoid hole scrapping caused by a large amount of damage, it is suggested that the robotic drilling parameters should be controlled at a spindle speed higher than 8000 rpm and a feed rate lower than 360 mm/min.","PeriodicalId":48519,"journal":{"name":"Machines","volume":" 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139142807","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}
Recently, bearing fault diagnosis methods based on deep learning have achieved significant success. However, in practical engineering applications, the limited labeled data and various working conditions severely constrain the widespread application of most deep-learning-based fault diagnosis methods. Additionally, many methods focus solely on the amplitude information of samples, neglecting the rich relational information between samples. To address these issues, this paper proposes a novel cross-condition few-shot fault diagnosis method based on an adaptive dynamic threshold graph neural network (ADTGNN). The aim of the proposed method is to rapidly identify fault types after they occur only a few times or even once. The adaptive threshold computation module (ATCM) in ADTGNN dynamically assigns thresholds to each edge based on edge confidence, optimizing the graph structure and effectively alleviating the over-smoothing issue. Furthermore, a dynamic threshold adjustment strategy (DTAS) is introduced to gradually increase the threshold with the training iterations, preventing the model from prematurely discarding crucial edges due to insufficient performance. The proposed model’s effectiveness is demonstrated using three bearing datasets. The experimental results indicate that the proposed approach significantly outperforms other comparison methods in cross-condition bearing fault diagnosis.
{"title":"Adaptive Dynamic Threshold Graph Neural Network: A Novel Deep Learning Framework for Cross-Condition Bearing Fault Diagnosis","authors":"Linjie Zheng, Yonghua Jiang, Hongkui Jiang, Chao Tang, Weidong Jiao, Zhuoqi Shi, A. Rehman","doi":"10.3390/machines12010018","DOIUrl":"https://doi.org/10.3390/machines12010018","url":null,"abstract":"Recently, bearing fault diagnosis methods based on deep learning have achieved significant success. However, in practical engineering applications, the limited labeled data and various working conditions severely constrain the widespread application of most deep-learning-based fault diagnosis methods. Additionally, many methods focus solely on the amplitude information of samples, neglecting the rich relational information between samples. To address these issues, this paper proposes a novel cross-condition few-shot fault diagnosis method based on an adaptive dynamic threshold graph neural network (ADTGNN). The aim of the proposed method is to rapidly identify fault types after they occur only a few times or even once. The adaptive threshold computation module (ATCM) in ADTGNN dynamically assigns thresholds to each edge based on edge confidence, optimizing the graph structure and effectively alleviating the over-smoothing issue. Furthermore, a dynamic threshold adjustment strategy (DTAS) is introduced to gradually increase the threshold with the training iterations, preventing the model from prematurely discarding crucial edges due to insufficient performance. The proposed model’s effectiveness is demonstrated using three bearing datasets. The experimental results indicate that the proposed approach significantly outperforms other comparison methods in cross-condition bearing fault diagnosis.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"15 4","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139150098","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 : 2023-12-26DOI: 10.3390/machines12010014
M. Hoić, M. Hrgetic, N. Kranjcevic, J. Deur, Andreas Tissot
The paper presents a redesign of the custom disc-on-disc-type tribometer intended for the experimental characterization of the friction and wear of automotive dry clutch friction lining. The redesign is aimed at expanding the operating range at which the machine is not sensitive to shudder vibrations. This is achieved through a set of hardware and software upgrade measures. First, the natural frequency of the normal load-generation linear axis of the machine is increased by enlarging its bending stiffness and reducing the suspended mass. The former is realized by replacing the single, two-axial force/torque piezoelectric sensor with a set of three three-axial piezoelectric force sensors, adding a set of stiff linear guides, and reducing the lengths of the cantilevers of lateral forces acting on the linear axis guide system. The latter is accomplished by reducing the overall dimensions of the cooling disc and redesigning the thermal insulation components. The shudder sensitivity resistance is further reduced through individual normal force-readings-based adjustment of parallelism between friction contact surfaces and the increase in the stiffness of eccentrically positioned water-cooling pipes. Finally, the stability of the coefficient of friction and, consequently, the wear process are boosted by adjusting the control routines to minimize the circumferential and/or radial temperature gradients. These adjustments include the introduction of a clutch lock-up interval at the end of the clutch closing cycle, a minimum cooling delay inserted between two closing cycles, and maximum normal force demand of the clutch torque controller. The performance gain of the upgraded tribometer is demonstrated through a study of the dry clutch friction plate static wear experimental characterization for a wide range of operating conditions.
{"title":"Redesign of a Disc-on-Disc Computer Numerical Control Tribometer for a Wide-Range and Shudder-Resistant Operation","authors":"M. Hoić, M. Hrgetic, N. Kranjcevic, J. Deur, Andreas Tissot","doi":"10.3390/machines12010014","DOIUrl":"https://doi.org/10.3390/machines12010014","url":null,"abstract":"The paper presents a redesign of the custom disc-on-disc-type tribometer intended for the experimental characterization of the friction and wear of automotive dry clutch friction lining. The redesign is aimed at expanding the operating range at which the machine is not sensitive to shudder vibrations. This is achieved through a set of hardware and software upgrade measures. First, the natural frequency of the normal load-generation linear axis of the machine is increased by enlarging its bending stiffness and reducing the suspended mass. The former is realized by replacing the single, two-axial force/torque piezoelectric sensor with a set of three three-axial piezoelectric force sensors, adding a set of stiff linear guides, and reducing the lengths of the cantilevers of lateral forces acting on the linear axis guide system. The latter is accomplished by reducing the overall dimensions of the cooling disc and redesigning the thermal insulation components. The shudder sensitivity resistance is further reduced through individual normal force-readings-based adjustment of parallelism between friction contact surfaces and the increase in the stiffness of eccentrically positioned water-cooling pipes. Finally, the stability of the coefficient of friction and, consequently, the wear process are boosted by adjusting the control routines to minimize the circumferential and/or radial temperature gradients. These adjustments include the introduction of a clutch lock-up interval at the end of the clutch closing cycle, a minimum cooling delay inserted between two closing cycles, and maximum normal force demand of the clutch torque controller. The performance gain of the upgraded tribometer is demonstrated through a study of the dry clutch friction plate static wear experimental characterization for a wide range of operating conditions.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"4 5","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139156839","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 : 2023-12-25DOI: 10.3390/machines12010013
Yao Wang, Fengtao Wang, Yue Feng, S. Cao
Reliability is an inherent attribute of a system through optimal system design. However, during the aircraft system development process, the reliability evaluation and system function design efforts are often disconnected, leading to a divide between reliability experts and system designers in their work schedule. This disconnect results in an inefficient aircraft system reliability optimization process, known as the “two-skin” phenomenon. To address this issue, a three-state space model is proposed. Firstly, an analysis was conducted on the relationship between the system function architecture developed by the system designers and the reliability evaluation performed by the reliability experts. Secondly, based on the principle of function flow, the state of failure was categorized into “physical failure” and “non-physical failure”. Additionally, a new state of “function loss” was introduced as the third state for the system, in addition to the traditional states of “normal” and “faulty”. Thirdly, through the state of “Function loss”, an effective integration of system fault modes and function modes was achieved, leading to an optimized system reliability model. A three-state space modeling method was then developed by transforming the system function architecture into a system reliability model. Finally, this new model was applied to an aircraft’s rudder and fly-by-wire control system. The results demonstrate that the function architecture at the design stage of the system can be accurately transformed into the new three-state space model. The structure aligns closely with the function architecture and can be effectively utilized in quantitative system reliability calculations. In this way, the process of ensuring system reliability can be seamlessly integrated into the system optimization design process. This integration alleviates the issue of disjointed work between reliability experts and system designers, leading to a more streamlined and efficient aircraft system optimization process.
{"title":"A Three-State Space Modeling Method for Aircraft System Reliability Design","authors":"Yao Wang, Fengtao Wang, Yue Feng, S. Cao","doi":"10.3390/machines12010013","DOIUrl":"https://doi.org/10.3390/machines12010013","url":null,"abstract":"Reliability is an inherent attribute of a system through optimal system design. However, during the aircraft system development process, the reliability evaluation and system function design efforts are often disconnected, leading to a divide between reliability experts and system designers in their work schedule. This disconnect results in an inefficient aircraft system reliability optimization process, known as the “two-skin” phenomenon. To address this issue, a three-state space model is proposed. Firstly, an analysis was conducted on the relationship between the system function architecture developed by the system designers and the reliability evaluation performed by the reliability experts. Secondly, based on the principle of function flow, the state of failure was categorized into “physical failure” and “non-physical failure”. Additionally, a new state of “function loss” was introduced as the third state for the system, in addition to the traditional states of “normal” and “faulty”. Thirdly, through the state of “Function loss”, an effective integration of system fault modes and function modes was achieved, leading to an optimized system reliability model. A three-state space modeling method was then developed by transforming the system function architecture into a system reliability model. Finally, this new model was applied to an aircraft’s rudder and fly-by-wire control system. The results demonstrate that the function architecture at the design stage of the system can be accurately transformed into the new three-state space model. The structure aligns closely with the function architecture and can be effectively utilized in quantitative system reliability calculations. In this way, the process of ensuring system reliability can be seamlessly integrated into the system optimization design process. This integration alleviates the issue of disjointed work between reliability experts and system designers, leading to a more streamlined and efficient aircraft system optimization process.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"37 1 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139159671","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 : 2023-12-23DOI: 10.3390/machines12010011
Hao Wang, Li Zhang, Youliang Sun, L. Zou
A vibration scale training model for converter transformers is proposed by combining attention modules with convolutional neural networks to solve the nonlinear problem of converter transformers in similar processes. Firstly, according to the structure and operating parameters of the converter transformer, a reliable three-dimensional multi-field coupled finite element model was established considering the influence of the winding and iron core component structure on the overall vibration characteristics. By changing different input parameters such as the size and voltage of the finite element model, corresponding output parameters are obtained, and a dataset is established through data expansion for training and verifying the attention convolution model. By analyzing the prediction processes and results of five prediction models on different operating conditions datasets, it is shown that attention convolution has higher accuracy, faster convergence speed, more stable training process, and better generalization performance in the prediction process of converter transformer recognition. Based on the predictive model, a prototype of the proportional vibration model for the converter transformer with scale factor of 0.2 was designed and manufactured. By analyzing the basic experimental items and vibration characteristics of the prototype, the stability of the prototype and the reliability of the prediction model were verified.
{"title":"A Convolutional Neural Network Based on Attention Mechanism for Designing Vibration Similarity Models of Converter Transformers","authors":"Hao Wang, Li Zhang, Youliang Sun, L. Zou","doi":"10.3390/machines12010011","DOIUrl":"https://doi.org/10.3390/machines12010011","url":null,"abstract":"A vibration scale training model for converter transformers is proposed by combining attention modules with convolutional neural networks to solve the nonlinear problem of converter transformers in similar processes. Firstly, according to the structure and operating parameters of the converter transformer, a reliable three-dimensional multi-field coupled finite element model was established considering the influence of the winding and iron core component structure on the overall vibration characteristics. By changing different input parameters such as the size and voltage of the finite element model, corresponding output parameters are obtained, and a dataset is established through data expansion for training and verifying the attention convolution model. By analyzing the prediction processes and results of five prediction models on different operating conditions datasets, it is shown that attention convolution has higher accuracy, faster convergence speed, more stable training process, and better generalization performance in the prediction process of converter transformer recognition. Based on the predictive model, a prototype of the proportional vibration model for the converter transformer with scale factor of 0.2 was designed and manufactured. By analyzing the basic experimental items and vibration characteristics of the prototype, the stability of the prototype and the reliability of the prediction model were verified.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"59 10","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139162138","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 : 2023-12-23DOI: 10.3390/machines12010012
Mooyoung Yoo
Conventional household refrigerators consist of a motor-driven compressor, evaporator, condenser, and expansion valve. To determine the optimal operation strategies of refrigerators, it is essential to investigate the overall system performance, using an appropriate simulator. This study proposed a data-driven simulator based on engineering features and machine learning algorithms for conventional household refrigerators. The most correlated variables for identifying the indoor temperature of refrigerators were identified using variable importance, and these were revealed to be the circulation fan speed, compressor operation status, and refrigerant flow direction. A data-driven simulator was constructed using Bayesian calibration, which considers the important variables, combined with a straightforward heat balance equation. The Markov Chain Monte Carlo approach was used to simultaneously calibrate three coefficients on the critical variables based on the heat balancing equation on each time step, which is consistent with the actual temperature of the container. The results revealed that the proposed approach (equation-based Bayesian calibration outperforms) standard machine learning algorithms, such as linear regression and random forest models, by 38.5%. Additionally, compared to the typical numerical analysis method, it can reduce the delivery time and effort required to develop a reliable simulator for household refrigerators.
{"title":"Development of a Simulator for Household Refrigerator Using Equation-Based Optimization Control with Bayesian Calibration","authors":"Mooyoung Yoo","doi":"10.3390/machines12010012","DOIUrl":"https://doi.org/10.3390/machines12010012","url":null,"abstract":"Conventional household refrigerators consist of a motor-driven compressor, evaporator, condenser, and expansion valve. To determine the optimal operation strategies of refrigerators, it is essential to investigate the overall system performance, using an appropriate simulator. This study proposed a data-driven simulator based on engineering features and machine learning algorithms for conventional household refrigerators. The most correlated variables for identifying the indoor temperature of refrigerators were identified using variable importance, and these were revealed to be the circulation fan speed, compressor operation status, and refrigerant flow direction. A data-driven simulator was constructed using Bayesian calibration, which considers the important variables, combined with a straightforward heat balance equation. The Markov Chain Monte Carlo approach was used to simultaneously calibrate three coefficients on the critical variables based on the heat balancing equation on each time step, which is consistent with the actual temperature of the container. The results revealed that the proposed approach (equation-based Bayesian calibration outperforms) standard machine learning algorithms, such as linear regression and random forest models, by 38.5%. Additionally, compared to the typical numerical analysis method, it can reduce the delivery time and effort required to develop a reliable simulator for household refrigerators.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"44 2","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139162067","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 : 2023-12-23DOI: 10.3390/machines12010010
Adrián Peidró, Edward J. Haug
Kinematic control of redundant serial manipulators has been carried out for the past half century based primarily on a generalized inverse velocity formulation that is known to have mathematical deficiencies. A recently developed inverse kinematic configuration mapping is employed in an operational configuration space differentiable manifold formulation for redundant-manipulator kinematic control with obstacle avoidance. This formulation is shown to resolve deficiencies in the generalized inverse velocity formulation, especially for high-degree-of-redundancy manipulators. Tracking a specified output trajectory while avoiding obstacles for four- and twenty-degree-of-redundancy manipulators is carried out to demonstrate the effectiveness of the differentiable manifold approach for applications with a high degree of redundancy and to show that it indeed resolves deficiencies of the conventional generalized inverse velocity formulation in challenging applications.
{"title":"Obstacle Avoidance in Operational Configuration Space Kinematic Control of Redundant Serial Manipulators","authors":"Adrián Peidró, Edward J. Haug","doi":"10.3390/machines12010010","DOIUrl":"https://doi.org/10.3390/machines12010010","url":null,"abstract":"Kinematic control of redundant serial manipulators has been carried out for the past half century based primarily on a generalized inverse velocity formulation that is known to have mathematical deficiencies. A recently developed inverse kinematic configuration mapping is employed in an operational configuration space differentiable manifold formulation for redundant-manipulator kinematic control with obstacle avoidance. This formulation is shown to resolve deficiencies in the generalized inverse velocity formulation, especially for high-degree-of-redundancy manipulators. Tracking a specified output trajectory while avoiding obstacles for four- and twenty-degree-of-redundancy manipulators is carried out to demonstrate the effectiveness of the differentiable manifold approach for applications with a high degree of redundancy and to show that it indeed resolves deficiencies of the conventional generalized inverse velocity formulation in challenging applications.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"32 3","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139161489","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 : 2023-12-22DOI: 10.3390/machines12010009
Won-Chul Jeong, Jaeoh Han, Taesu Kim, Jongseok Lee, Sehoon Oh
The trend in the global automotive industry is moving towards electric vehicles that do not emit exhaust gases and use eco-friendly fuel. Electric vehicles are more eco-friendly compared to internal combustion engine vehicles, as they emit less carbon dioxide and pollutants. Research and development are actively underway to produce new electric vehicle models in the rapidly growing electric car market. In this study, a 2-speed transmission for electric vehicles, applicable to 300 Nm-class electric cars, has been developed. The 2-speed transmission structure enables efficient energy use and utilizes a planetary gear set and wet multi-plate clutch, which are effective in the power transmission process. The 2-speed transmission developed through the research results of this paper has a compact structure optimized for electric vehicles. The design feasibility of the transmission was verified through performance tests of the prototype, contributing to fuel efficiency improvement and environmental enhancement.
{"title":"Two-Speed Transmission Structure and Optimization Design for Electric Vehicles","authors":"Won-Chul Jeong, Jaeoh Han, Taesu Kim, Jongseok Lee, Sehoon Oh","doi":"10.3390/machines12010009","DOIUrl":"https://doi.org/10.3390/machines12010009","url":null,"abstract":"The trend in the global automotive industry is moving towards electric vehicles that do not emit exhaust gases and use eco-friendly fuel. Electric vehicles are more eco-friendly compared to internal combustion engine vehicles, as they emit less carbon dioxide and pollutants. Research and development are actively underway to produce new electric vehicle models in the rapidly growing electric car market. In this study, a 2-speed transmission for electric vehicles, applicable to 300 Nm-class electric cars, has been developed. The 2-speed transmission structure enables efficient energy use and utilizes a planetary gear set and wet multi-plate clutch, which are effective in the power transmission process. The 2-speed transmission developed through the research results of this paper has a compact structure optimized for electric vehicles. The design feasibility of the transmission was verified through performance tests of the prototype, contributing to fuel efficiency improvement and environmental enhancement.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"10 10","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138947753","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 : 2023-12-22DOI: 10.3390/machines12010008
Shaoming Peng, Gang Xiong, Jing Yang, Zhen Shen, Tariku Sinshaw Tamir, Zhikun Tao, Yunjun Han, Fei-Yue Wang
An extended flexible job scheduling problem is presented with characteristics of technology and path flexibility (dual flexibility), varied transportation time, and an uncertain environment. The scheduling can greatly increase efficiency and security in complex scenarios, e.g., distributed vehicle manufacturing, and multiple aircraft maintenance. However, optimizing the scheduling puts forward higher requirements on accuracy, real time, and generalization, while subject to the curse of dimension and usually incomplete information. Various coupling relations among operations, stations, and resources aggravate the problem. To deal with the above challenges, we propose a multi-agent reinforcement learning algorithm where the scheduling environment is modeled as a decentralized partially observable Markov decision process. Each job is regarded as an agent that decides the next triplet, i.e., operation, station, and employed resource. This paper is novel in addressing the flexible job shop scheduling problem with dual flexibility and varied transportation time in consideration and proposing a double Q-value mixing (DQMIX) optimization algorithm under a multi-agent reinforcement learning framework. The experiments of our case study show that the DQMIX algorithm outperforms existing multi-agent reinforcement learning algorithms in terms of solution accuracy, stability, and generalization. In addition, it achieves better solution quality for larger-scale cases than traditional intelligent optimization algorithms.
{"title":"Multi-Agent Reinforcement Learning for Extended Flexible Job Shop Scheduling","authors":"Shaoming Peng, Gang Xiong, Jing Yang, Zhen Shen, Tariku Sinshaw Tamir, Zhikun Tao, Yunjun Han, Fei-Yue Wang","doi":"10.3390/machines12010008","DOIUrl":"https://doi.org/10.3390/machines12010008","url":null,"abstract":"An extended flexible job scheduling problem is presented with characteristics of technology and path flexibility (dual flexibility), varied transportation time, and an uncertain environment. The scheduling can greatly increase efficiency and security in complex scenarios, e.g., distributed vehicle manufacturing, and multiple aircraft maintenance. However, optimizing the scheduling puts forward higher requirements on accuracy, real time, and generalization, while subject to the curse of dimension and usually incomplete information. Various coupling relations among operations, stations, and resources aggravate the problem. To deal with the above challenges, we propose a multi-agent reinforcement learning algorithm where the scheduling environment is modeled as a decentralized partially observable Markov decision process. Each job is regarded as an agent that decides the next triplet, i.e., operation, station, and employed resource. This paper is novel in addressing the flexible job shop scheduling problem with dual flexibility and varied transportation time in consideration and proposing a double Q-value mixing (DQMIX) optimization algorithm under a multi-agent reinforcement learning framework. The experiments of our case study show that the DQMIX algorithm outperforms existing multi-agent reinforcement learning algorithms in terms of solution accuracy, stability, and generalization. In addition, it achieves better solution quality for larger-scale cases than traditional intelligent optimization algorithms.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"8 4","pages":""},"PeriodicalIF":2.6,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138946079","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：