2022 25th International Conference on Mechatronics Technology (ICMT)最新文献_第3页

CoilFORM: the impact of the winding on the flat spiral shape memory alloy coils CoilFORM:绕线对平面螺旋形记忆合金线圈的影响

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997740

Ahmed Amine Chafik, J. Gaber, S. Tayane, M. Ennaji

引用次数: 0

The CCD-Algebraic Algorithm to solve the inverse kinematic and control the rotation of 6-DOF redundant manipulator in three spatial dimensions 采用ccd -代数算法求解三维空间六自由度冗余机械臂的运动学逆解和旋转控制

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997795

D. Tran, Trong Luong Tran, Minh Tri Duong, Hoang Vu Dao, K. Ahn

{"title":"The CCD-Algebraic Algorithm to solve the inverse kinematic and control the rotation of 6-DOF redundant manipulator in three spatial dimensions","authors":"D. Tran, Trong Luong Tran, Minh Tri Duong, Hoang Vu Dao, K. Ahn","doi":"10.1109/ICMT56556.2022.9997795","DOIUrl":"https://doi.org/10.1109/ICMT56556.2022.9997795","url":null,"abstract":"This paper presents a new method to solve the inverse kinematics problem of a hyper-redundant manipulator. Redundant resolution is a critical problem in the control of robotic manipulators. Forward kinematics of the 6 DOF redundant manipulator has been performed through Denevit and Hartenberg method. This article identifies a limitation of the existing CCD solution for solving inverse kinematics, i.e., the uncontrollable direction of the end effector. A new algorithm based on the cyclic coordinate descent (CCD) and named CCD-Algebraic is proposed to handle this drawback and solve inverse kinematic. The end-effector’s position is wholly managed with the cyclic coordinate descent (CCD), but it is adapted to uncontrollable rotation trajectories. With CCD-Algebraic, a rotation matrix of end-effector is attached to the position matrix of a lower hierarchical joint. Precisely, the position of the joint will determine both of position and rotation of the higher hierarchical joint. The proposed approach is applied in a three-dimensional (3D) space and can deal with many degrees of freedom. In addition, it has been used to perform continuous trajectories in MATLAB SIMULINK. Simulation results verify the strength of the proposal algorithm – simple, precise, and computationally efficient.","PeriodicalId":217521,"journal":{"name":"2022 25th International Conference on Mechatronics Technology (ICMT)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125115910","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}

引用次数: 1

Deep Convolutional Neural Network based Fabric Color Difference Detection 基于深度卷积神经网络的织物色差检测

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997628

Chao-Ching Ho, Chao-Wei Yu

{"title":"Deep Convolutional Neural Network based Fabric Color Difference Detection","authors":"Chao-Ching Ho, Chao-Wei Yu","doi":"10.1109/ICMT56556.2022.9997628","DOIUrl":"https://doi.org/10.1109/ICMT56556.2022.9997628","url":null,"abstract":"Image processing and statistical methods can quickly and accurately locate chromatic aberration defects. However, it becomes necessary to adjust the detection standard individually for different imaging equipment. Therefore, this study uses deep learning to solve the problem of a single applicable scene and achieves a continuous learning effect. This research innovatively develops an image transfer deep learning algorithm for the changing imaging environment. Two fabrics of the color green and blue, three scanners (Two HP scanners and One Epson scanner) with different configurations are used as different imaging environments to demonstrate the solution. The fabrics are scanned using these three scanners and the resultant image is labelled and then used to train three different neural networks. To eliminate the dependency of these neural networks on the imaging environment, a commercially available color calibration card is used on the three different scanners. Multiple neural networks are trained using these images to transfer the color blocks between different scanners. This enables fabric images gathered from a scanner to get converted to another scanner, such that it can be used for prediction by models trained on different scanners. Interactive experiments confirm the general application of this method. The experimental results show that within the same scanner model, the average predicted Intersection over Union (IoU) of the transfer result can be increased from 62.79% to 86.36%. If the scanner model is different, the image standard deviation is transferred from a scanner with a small image standard deviation to a large image standard deviation. The transfer results, the average predicted IoU increase from 38.65% to 86.64%. If the image standard deviation was transferred from a scanner with a large image standard deviation to a small image standard deviation, the predicted average IoU of the transfer result increases from 38.30% to 75.83%.","PeriodicalId":217521,"journal":{"name":"2022 25th International Conference on Mechatronics Technology (ICMT)","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121584297","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}

引用次数: 0

Nozzle Pressure and Clamping Force Based Injection Molding Process Parameter Optimization and Adaptive Process Quality Control 基于喷嘴压力和合模力的注塑工艺参数优化及自适应工艺质量控制

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997782

Guan-Yan Liou, Feng-Jung Cheng, Wei-Jie Su, Sheng-Jye Hwang, H. Peng, Hsiao-Yeh Chu

{"title":"Nozzle Pressure and Clamping Force Based Injection Molding Process Parameter Optimization and Adaptive Process Quality Control","authors":"Guan-Yan Liou, Feng-Jung Cheng, Wei-Jie Su, Sheng-Jye Hwang, H. Peng, Hsiao-Yeh Chu","doi":"10.1109/ICMT56556.2022.9997782","DOIUrl":"https://doi.org/10.1109/ICMT56556.2022.9997782","url":null,"abstract":"The parameter setting will decide the quality of the injection molded product. The quality of injection molded parts may be altered by environment changes, different material batches and improper processing parameter settings etc., resulting in unstable product quality in the long-term production process. This research aims at machine tooling and established a science based standard process parameter setting process for injection molding machine based on the least sensors, so that the production process is stable even without the use of the adaptive process control system. This study define the appropriate velocity to pressure (V/P) switchover point, injection speed and packing pressure according to the characteristics of the nozzle pressure, and define the appropriate clamping force by the peak value of the clamping force. The next step is to combine the sensors with an adaptive process control system to minimize product weight variation and stabilize product quality. Finally, experiments were carried out with different materials to verify the effectiveness of the system and to be suitable for different machines, and to prove the feasibility of industrialization.","PeriodicalId":217521,"journal":{"name":"2022 25th International Conference on Mechatronics Technology (ICMT)","volume":"1813 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129705736","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}

引用次数: 0

Time series prediction for thermal management in server applied with deep learning 基于深度学习的服务器热管理时间序列预测

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997645

Hsin-Cheng Chu, Chien-Ming Lee, K. Tung, Rongshun Chen

{"title":"Time series prediction for thermal management in server applied with deep learning","authors":"Hsin-Cheng Chu, Chien-Ming Lee, K. Tung, Rongshun Chen","doi":"10.1109/ICMT56556.2022.9997645","DOIUrl":"https://doi.org/10.1109/ICMT56556.2022.9997645","url":null,"abstract":"The portion of cooling power reaches up to one third of total power budget in the operation of data centers. Recently researchers pay more attention on thermal management for improving energy efficiency in the data centers as well as the servers. To the best of existing literatures, the complex interactions of cooling and heating resources is the main problem encountered in the design of server fan control. Moreover, to achieve better control performance, the thermal information of time series should be taken into account as well. Therefore, this work proposes time series prediction of server temperatures by utilizing two multivariate time series prediction models, named MTSMFF and MsA. An automatic data acquisition system has been designed for collecting massive scale dataset. To ensure the robustness of trained results, the dataset is divided into training data and validation data. These two models are trained with the training data, and MsA provides the best performance in accuracy with the validation data. The experimental results show that the time series prediction of MsA performs splendidly for the trend of the server temperatures.","PeriodicalId":217521,"journal":{"name":"2022 25th International Conference on Mechatronics Technology (ICMT)","volume":"89 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131230461","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}

引用次数: 0

Feasibility Assessment of Differential Voltage Analysis to Detect Lithium Plating in Battery Modules for Electric Vehicles 差分电压分析检测电动汽车电池模块镀锂的可行性评估

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997689

Nithin Somasundaran, Nessa Fereshteh Saniee, Truong Dinh Quang, J. Marco

引用次数: 2

Thermal Error Prediction of Ball Screws Based on Partial Least Square Method with Consideration of Friction Works 考虑摩擦功的滚珠丝杠热误差偏最小二乘法预测

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997681

Chien-Hsiang Hung, Meng-Shiun Tsai, Mao-Qi Hong, Yu-Hung Wang, Wen-Fang Chen

引用次数: 2

Rack Inlet Temperature Prediction Based on Deep Learning 基于深度学习的机架入口温度预测

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997747

Yudan Peng, Chien-Ming Lee, K. Tung, Rongshun Chen

{"title":"Rack Inlet Temperature Prediction Based on Deep Learning","authors":"Yudan Peng, Chien-Ming Lee, K. Tung, Rongshun Chen","doi":"10.1109/ICMT56556.2022.9997747","DOIUrl":"https://doi.org/10.1109/ICMT56556.2022.9997747","url":null,"abstract":"Improving the cooling efficiency of a data center becomes important due to the cooling power reaches one-half of total power budget in operating the data center. The major cause of inefficient cooling is the poor airflow management resulting in cold air bypass and hot air recirculation. Basically the architecture of airflow management includes the separation of cold aisle and hot aisle and raised floor with perforated tile. The cold air is generated by the Computer Room Air Conditioning (CRAC) unit and is delivered to the server rack through the perforated floor. To avoid hot air recirculation, an active tile is used to enhance the airflow in a specific location where the flow resistance is larger than the others. The priority of the airflow control is to eliminate hot spot owing to the hot air recirculation such that the control strategy is conservative. Recently many studies pay attention to real-time temperature prediction by utilizing airflow model to improve the control performance of the airflow. However the derivation of airflow model suffers the difficulty from the airflow measurement. Therefore this research aims at the development of deep learning model for predicting the inlet temperature distributions in real time for use in control strategies in order to improve energy usage dynamically. A rack tested system was established for the validation of the temperature prediction by using deep learning. In this paper we define the workload schedule of the rack to collect the training data and the GRU recurrent neural network model is used to develop the temperature prediction model. The experimental results show that the prediction model can predict the inlet temperature at a root mean square error of 0.29°C.","PeriodicalId":217521,"journal":{"name":"2022 25th International Conference on Mechatronics Technology (ICMT)","volume":"479 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133713340","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}

引用次数: 0

Development of a Senior-Friendly Foldable Wheelchair Using Design Thinking 用设计思维开发老年人友好型可折叠轮椅

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997592

I. Sung, I-Chen Wang, Ting Hsien Lu, Ming-Yen Hsieh

引用次数: 0

Research on detection of surface defects of lamps with multi-color light sources 多色光源灯具表面缺陷检测研究

2022 25th International Conference on Mechatronics Technology (ICMT) Pub Date : 2022-11-18 DOI: 10.1109/ICMT56556.2022.9997677

Tsung-Liang Wu, Yu-Ying Zhan

{"title":"Research on detection of surface defects of lamps with multi-color light sources","authors":"Tsung-Liang Wu, Yu-Ying Zhan","doi":"10.1109/ICMT56556.2022.9997677","DOIUrl":"https://doi.org/10.1109/ICMT56556.2022.9997677","url":null,"abstract":"Automated optical inspection (AOI) is one of the most intuitive technology for defect inspection, which is amply utilized in various industrial products. Nevertheless, each inspected target has a different characteristic, for instance, transparency. The transparency object possesses a high ratio of light-transmitting and the ratio will vary depending on the angle of an emitting light source. With this property, the emitting light source may reflect and transmit in accordance with some complex parameters and the capability of the inspection will be highly affected. One of a crucial parameter is the lighting design in the inspection environment. In this study, we propose several sets of wavelengths of the lighting source for evaluation. The multiple colors and natural light are used as the lighting source to capture the defects on the lamps cover. Then the images are assembled into a data set, which is imported into the ResNet model based on the convolutional neural network (CNN) for deep learning training. This study shows the results and concludes that the blue light source can acquire the best result with the highest accuracy of defect detection.","PeriodicalId":217521,"journal":{"name":"2022 25th International Conference on Mechatronics Technology (ICMT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130589078","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}

引用次数: 0