Cagri Yalcin, M. Sam, Yifeng Bu, Moran Amit, A. Skalsky, Michael C. Yip, T. Ng, H. Garudadri
Spasticity is a pathological condition that can occur in people with neuromuscular disorders. Objective, repeatable metrics are needed for evaluation to provide appropriate treatment and to monitor patient condition. Herein, an instrumented bimodal glove with force and movement sensors for spasticity assessment is presented. To mitigate noise artifacts, machine learning techniques are used, specifically a multitask neural network, to calibrate the instrumented glove signals against the ground truth from sensors integrated in a robotic arm. The motorized robotic arm system offers adjustable resistance to simulate different levels of muscle stiffness in spasticity, and the sensors on the robot provide ground‐truth measurements of angular displacement and force applied during flexion and extension maneuvers. The robotic sensor measurements are used to train the instrumented glove data through multitask learning. After processing through the neural network, the Pearson correlation coefficients between the processed signals and the ground truth are above 0.92, demonstrating successful signal calibration and noise mitigation.
{"title":"Artifacts Mitigation in Sensors for Spasticity Assessment","authors":"Cagri Yalcin, M. Sam, Yifeng Bu, Moran Amit, A. Skalsky, Michael C. Yip, T. Ng, H. Garudadri","doi":"10.1002/aisy.202000106","DOIUrl":"https://doi.org/10.1002/aisy.202000106","url":null,"abstract":"Spasticity is a pathological condition that can occur in people with neuromuscular disorders. Objective, repeatable metrics are needed for evaluation to provide appropriate treatment and to monitor patient condition. Herein, an instrumented bimodal glove with force and movement sensors for spasticity assessment is presented. To mitigate noise artifacts, machine learning techniques are used, specifically a multitask neural network, to calibrate the instrumented glove signals against the ground truth from sensors integrated in a robotic arm. The motorized robotic arm system offers adjustable resistance to simulate different levels of muscle stiffness in spasticity, and the sensors on the robot provide ground‐truth measurements of angular displacement and force applied during flexion and extension maneuvers. The robotic sensor measurements are used to train the instrumented glove data through multitask learning. After processing through the neural network, the Pearson correlation coefficients between the processed signals and the ground truth are above 0.92, demonstrating successful signal calibration and noise mitigation.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"695 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81783013","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}
G. Moretti, S. Rosset, R. Vertechy, I. Anderson, M. Fontana
Dielectric elastomer generator systems (DEGSs) are a class of electrostatic soft‐transducers capable of converting oscillating mechanical power from different sources into usable electricity. Over the past years, a diversity of DEGSs has been conceived, integrated, and tested featuring diverse topologies and implementation characteristics tailored on different applications. Herein, the recent advances on DEGSs are reviewed and illustrated in terms of design of hardware architectures, power electronics, and control, with reference to the different application targets, including large‐scale systems such as ocean wave energy converters, and small‐scale systems such as human motion or ambient vibration energy harvesters. Finally, challenges and perspectives for the advancement of DEGSs are identified and discussed.
{"title":"A Review of Dielectric Elastomer Generator Systems","authors":"G. Moretti, S. Rosset, R. Vertechy, I. Anderson, M. Fontana","doi":"10.1002/aisy.202000125","DOIUrl":"https://doi.org/10.1002/aisy.202000125","url":null,"abstract":"Dielectric elastomer generator systems (DEGSs) are a class of electrostatic soft‐transducers capable of converting oscillating mechanical power from different sources into usable electricity. Over the past years, a diversity of DEGSs has been conceived, integrated, and tested featuring diverse topologies and implementation characteristics tailored on different applications. Herein, the recent advances on DEGSs are reviewed and illustrated in terms of design of hardware architectures, power electronics, and control, with reference to the different application targets, including large‐scale systems such as ocean wave energy converters, and small‐scale systems such as human motion or ambient vibration energy harvesters. Finally, challenges and perspectives for the advancement of DEGSs are identified and discussed.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89270853","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}
Nazek El‐atab, R. B. Mishra, Fhad Al-Modaf, Lana Joharji, Aljohara A. Alsharif, Haneen Alamoudi, Marlon Diaz, N. Qaiser, M. Hussain
Soft robotics technologies are paving the way toward robotic abilities which are vital for a wide range of applications, including manufacturing, manipulation, gripping, human–machine interaction, locomotion, and more. An essential component in a soft robot is the soft actuator which provides the system with a deformable body and allows it to interact with the environment to achieve a desired actuation pattern, such as locomotion. This Review article aims to provide researchers interested in the soft robotics field with a reference guide about the various state‐of‐the‐art soft actuation methodologies that are developed with a wide range of stimuli including light, heat, applied electric and magnetic fields with a focus on their various applications in soft robotics. The underlying principles of the soft actuators are discussed with a focus on the resulting motion complexities, deformations, and multi‐functionalities. Finally, various promising applications and examples of the different soft actuators are discussed in addition to their further development potential.
{"title":"Soft Actuators for Soft Robotic Applications: A Review","authors":"Nazek El‐atab, R. B. Mishra, Fhad Al-Modaf, Lana Joharji, Aljohara A. Alsharif, Haneen Alamoudi, Marlon Diaz, N. Qaiser, M. Hussain","doi":"10.1002/aisy.202000128","DOIUrl":"https://doi.org/10.1002/aisy.202000128","url":null,"abstract":"Soft robotics technologies are paving the way toward robotic abilities which are vital for a wide range of applications, including manufacturing, manipulation, gripping, human–machine interaction, locomotion, and more. An essential component in a soft robot is the soft actuator which provides the system with a deformable body and allows it to interact with the environment to achieve a desired actuation pattern, such as locomotion. This Review article aims to provide researchers interested in the soft robotics field with a reference guide about the various state‐of‐the‐art soft actuation methodologies that are developed with a wide range of stimuli including light, heat, applied electric and magnetic fields with a focus on their various applications in soft robotics. The underlying principles of the soft actuators are discussed with a focus on the resulting motion complexities, deformations, and multi‐functionalities. Finally, various promising applications and examples of the different soft actuators are discussed in addition to their further development potential.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81620586","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}
The explosive growth of data and information has motivated technological developments in computing systems that utilize them for efficiently discovering patterns and gaining relevant insights. Inspired by the structure and functions of biological synapses and neurons in the brain, neural network algorithms that can realize highly parallel computations have been implemented on conventional silicon transistor‐based hardware. However, synapses composed of multiple transistors allow only binary information to be stored, and processing such digital states through complicated silicon neuron circuits makes low‐power and low‐latency computing difficult. Therefore, the attractiveness of the emerging memories and switches for synaptic and neuronal elements, respectively, in implementing neuromorphic systems, which are suitable for performing energy‐efficient cognitive functions and recognition, is discussed herein. Based on a literature survey, recent progress concerning memories shows that novel strategies related to materials and device engineering to mitigate challenges are presented to primarily achieve nonvolatile analog synaptic characteristics. Attempts to emulate the role of the neuron in various ways using compact switches and volatile memories are also discussed. It is hoped that this review will help direct future interdisciplinary research on device, circuit, and architecture levels of neuromorphic systems.
{"title":"Recent Advancements in Emerging Neuromorphic Device Technologies","authors":"Jiyong Woo, Jeong Hun Kim, J. Im, Seung Eon Moon","doi":"10.1002/aisy.202000111","DOIUrl":"https://doi.org/10.1002/aisy.202000111","url":null,"abstract":"The explosive growth of data and information has motivated technological developments in computing systems that utilize them for efficiently discovering patterns and gaining relevant insights. Inspired by the structure and functions of biological synapses and neurons in the brain, neural network algorithms that can realize highly parallel computations have been implemented on conventional silicon transistor‐based hardware. However, synapses composed of multiple transistors allow only binary information to be stored, and processing such digital states through complicated silicon neuron circuits makes low‐power and low‐latency computing difficult. Therefore, the attractiveness of the emerging memories and switches for synaptic and neuronal elements, respectively, in implementing neuromorphic systems, which are suitable for performing energy‐efficient cognitive functions and recognition, is discussed herein. Based on a literature survey, recent progress concerning memories shows that novel strategies related to materials and device engineering to mitigate challenges are presented to primarily achieve nonvolatile analog synaptic characteristics. Attempts to emulate the role of the neuron in various ways using compact switches and volatile memories are also discussed. It is hoped that this review will help direct future interdisciplinary research on device, circuit, and architecture levels of neuromorphic systems.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89287292","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}
This work studies a computation in‐memory concept for binary multiply‐accumulate operations based on complementary resistive switches (CRS). By exploiting the in‐memory boolean exclusive OR (XOR) operation of single CRS devices, the Hamming Distance (HD) can be calculated if the center electrodes of multiple CRS cells are connected. This HD is linearly encoded in the voltage drop of the common electrode, and from it the result of a binary multiply‐accumulate operation can be calculated. A small‐scale demonstration is experimentally realized and the feasibility of the in‐memory computation concept is confirmed. A simulation study identifies the low resistance state (LRS) variability as the main reason for the variations in the output voltage. The application as a potential hardware accelerator for the inference step of binary neural networks is investigated. Therefore, a 1‐layer fully connected neural network is trained on a binarized version of the MNIST data set and the inference step of the test data set is simulated. The concept achieves a prediction accuracy of approximately 86%.
{"title":"In‐Memory Binary Vector–Matrix Multiplication Based on Complementary Resistive Switches","authors":"T. Ziegler, R. Waser, D. Wouters, S. Menzel","doi":"10.1002/aisy.202000134","DOIUrl":"https://doi.org/10.1002/aisy.202000134","url":null,"abstract":"This work studies a computation in‐memory concept for binary multiply‐accumulate operations based on complementary resistive switches (CRS). By exploiting the in‐memory boolean exclusive OR (XOR) operation of single CRS devices, the Hamming Distance (HD) can be calculated if the center electrodes of multiple CRS cells are connected. This HD is linearly encoded in the voltage drop of the common electrode, and from it the result of a binary multiply‐accumulate operation can be calculated. A small‐scale demonstration is experimentally realized and the feasibility of the in‐memory computation concept is confirmed. A simulation study identifies the low resistance state (LRS) variability as the main reason for the variations in the output voltage. The application as a potential hardware accelerator for the inference step of binary neural networks is investigated. Therefore, a 1‐layer fully connected neural network is trained on a binarized version of the MNIST data set and the inference step of the test data set is simulated. The concept achieves a prediction accuracy of approximately 86%.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"105 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91183459","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}
Qilai Chen, Ying Zhang, Shuzhi Liu, Tingting Han, Xinhui Chen, Yanqing Xu, Ziqi Meng, Guanglei Zhang, Xuejun Zheng, Jinjin Zhao, G. Cao, Gang Liu
Machine vision is an indispensable part of today's artificial intelligence. The artificial visual systems used in industrial production and domestic daily life rely significantly on cameras and image‐processing components for live monitoring and target identifying. They, however, often suffer from bulky volume, high energy consumption, and more critically, lack of adaptive responsiveness under extreme lighting conditions and thus possible mortal visual disability of flash blinding or nyctalopia for applications such as auto‐piloting. Herein, it is demonstrated that perovskite switchable photovoltaic devices are used to effectively construct all‐in‐one sensory neural network. Arising from the spontaneous and electric field‐induced ion‐migration effect, the photoresponsivity of the perovskite device can be reconfigured over the wide range of 540–1270%, which not only allows high‐fidelity adaptive image sensing of the visual information but also acts as updatable synaptic weight to enable the sensor array for performing machine‐learning tasks. With the bioinspired electronic pupil regulation function achieved through adjustable photoresponsivity of the perovskite sensor array, a proof‐of‐concept adaptive machine vision system with a maximum 263% enhancement of the object recognition accuracy for compact, mobile yet delay‐sensitive applications is demonstrated.
{"title":"Switchable Perovskite Photovoltaic Sensors for Bioinspired Adaptive Machine Vision","authors":"Qilai Chen, Ying Zhang, Shuzhi Liu, Tingting Han, Xinhui Chen, Yanqing Xu, Ziqi Meng, Guanglei Zhang, Xuejun Zheng, Jinjin Zhao, G. Cao, Gang Liu","doi":"10.1002/aisy.202000122","DOIUrl":"https://doi.org/10.1002/aisy.202000122","url":null,"abstract":"Machine vision is an indispensable part of today's artificial intelligence. The artificial visual systems used in industrial production and domestic daily life rely significantly on cameras and image‐processing components for live monitoring and target identifying. They, however, often suffer from bulky volume, high energy consumption, and more critically, lack of adaptive responsiveness under extreme lighting conditions and thus possible mortal visual disability of flash blinding or nyctalopia for applications such as auto‐piloting. Herein, it is demonstrated that perovskite switchable photovoltaic devices are used to effectively construct all‐in‐one sensory neural network. Arising from the spontaneous and electric field‐induced ion‐migration effect, the photoresponsivity of the perovskite device can be reconfigured over the wide range of 540–1270%, which not only allows high‐fidelity adaptive image sensing of the visual information but also acts as updatable synaptic weight to enable the sensor array for performing machine‐learning tasks. With the bioinspired electronic pupil regulation function achieved through adjustable photoresponsivity of the perovskite sensor array, a proof‐of‐concept adaptive machine vision system with a maximum 263% enhancement of the object recognition accuracy for compact, mobile yet delay‐sensitive applications is demonstrated.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83159674","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}
Photoresponsive materials have attracted growing interest because of their potential applications in materials science, such as photoswitches, photopatterning, information storage, and so on. However, there are some challenges for photoresponsive materials for certain applications: 1) Only a few photoresponsive surfaces are transformed into multiple states after photoreactions to adapt to changing environmental conditions; 2) Photoresponsive materials may not function properly in cold environments, especially for gels. To address these problems, we have recently developed photoresponsive materials based on ruthenium (Ru) complexes. Such Ru complexes showed a photoinduced ligand substitution under visible light irradiation. Reconfigurable surfaces that can adapt to environmental changes and photoresponsive organohydrogels that function effectively at sub‐zero temperatures have been fabricated using photoresponsive Ru complexes. Herein, it is demonstrated that based on photocontrolled Ru–ligand coordination, reconfigurable surfaces can be modified for user‐defined functions via visible light irradiation and that photoresponsive gels can function even at –20 °C. As a perspective, Ru‐containing photoresponsive complexes could open up pathways for a variety of applications.
{"title":"Reconfigurable Materials Based on Photocontrolled Metal–Ligand Coordination","authors":"Jianxiong Han, Yun-shuai Huang, Ni Yang, Si Wu","doi":"10.1002/aisy.202000112","DOIUrl":"https://doi.org/10.1002/aisy.202000112","url":null,"abstract":"Photoresponsive materials have attracted growing interest because of their potential applications in materials science, such as photoswitches, photopatterning, information storage, and so on. However, there are some challenges for photoresponsive materials for certain applications: 1) Only a few photoresponsive surfaces are transformed into multiple states after photoreactions to adapt to changing environmental conditions; 2) Photoresponsive materials may not function properly in cold environments, especially for gels. To address these problems, we have recently developed photoresponsive materials based on ruthenium (Ru) complexes. Such Ru complexes showed a photoinduced ligand substitution under visible light irradiation. Reconfigurable surfaces that can adapt to environmental changes and photoresponsive organohydrogels that function effectively at sub‐zero temperatures have been fabricated using photoresponsive Ru complexes. Herein, it is demonstrated that based on photocontrolled Ru–ligand coordination, reconfigurable surfaces can be modified for user‐defined functions via visible light irradiation and that photoresponsive gels can function even at –20 °C. As a perspective, Ru‐containing photoresponsive complexes could open up pathways for a variety of applications.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"24 11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82682905","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}
The economical, agile, customizable manufacturing, and integration of multifunctional device modules into networked systems with mechanical compliance and robustness enable unprecedented human‐integrated smart wearables and usher in exciting opportunities in emerging technologies. The additive manufacturing (AM) processes have emerged as potential candidates for rapid prototyping printed devices with diversified functionalities, e.g., energy harvesting/storage, sensing, actuation, and computation. However, there are few review reports about the ink‐based additive nanomanufacturing of functional materials for human‐integrated smart wearables. To fill this gap, herein, the recent progress in ink‐based additive nanomanufacturing technologies, focusing on their capability and potential for producing wearable human‐integrated devices, is reviewed. The manufacturing process integration, functional materials, device implementation, and application performance issues in designing and implementing the ink‐based additively nanomanufactured wearable systems are thoroughly discussed. The recent printed devices focusing on the processing conditions and performance metrics are comprehensively reviewed. Finally, the vision and outlook for the challenges and opportunities associated with related topics are provided. The rapid progress achieved in related disciplines enables more capable smart human‐integrated wearable systems that can be fully printed with rapid, agile, reconfigurable, and smart AM platforms.
{"title":"Ink‐Based Additive Nanomanufacturing of Functional Materials for Human‐Integrated Smart Wearables","authors":"Shujia Xu, Wenzhuo Wu","doi":"10.1002/aisy.202000117","DOIUrl":"https://doi.org/10.1002/aisy.202000117","url":null,"abstract":"The economical, agile, customizable manufacturing, and integration of multifunctional device modules into networked systems with mechanical compliance and robustness enable unprecedented human‐integrated smart wearables and usher in exciting opportunities in emerging technologies. The additive manufacturing (AM) processes have emerged as potential candidates for rapid prototyping printed devices with diversified functionalities, e.g., energy harvesting/storage, sensing, actuation, and computation. However, there are few review reports about the ink‐based additive nanomanufacturing of functional materials for human‐integrated smart wearables. To fill this gap, herein, the recent progress in ink‐based additive nanomanufacturing technologies, focusing on their capability and potential for producing wearable human‐integrated devices, is reviewed. The manufacturing process integration, functional materials, device implementation, and application performance issues in designing and implementing the ink‐based additively nanomanufactured wearable systems are thoroughly discussed. The recent printed devices focusing on the processing conditions and performance metrics are comprehensively reviewed. Finally, the vision and outlook for the challenges and opportunities associated with related topics are provided. The rapid progress achieved in related disciplines enables more capable smart human‐integrated wearable systems that can be fully printed with rapid, agile, reconfigurable, and smart AM platforms.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"91 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85659195","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}
Chihun Lee, Juwon Na, Kyongho Park, Hye-jeong Yu, Jongsun Kim, Kwon-Il Choi, D. Park, Seongjin Park, J. Rho, Seungchul Lee
This study combines an artificial neural network (ANN) and a random search to develop a system to recommend process conditions for injection molding. Both simulation and experimental results are collected using a mixed sampling method that combines Taguchi and random sampling. The dataset consists of 3600 simulations and 476 experiments from 36 different molds. Each datum has five process and 15 geometry features as input and one weight feature as output. Hyper‐parameter tuning is conducted to find the optimal ANN model. Then, transfer learning is introduced, which allows the use of simultaneous experimental and simulation data to reduce the error. The final prediction model has a root mean‐square error of 0.846. To develop a recommender system, random search is conducted using the trained ANN forward model. As a result, the weight‐prediction model based on simulated data has a relative error (RE) of 0.73%, and the weight prediction using the transfer model has an RE of 0.662%. A user interface system is also developed, which can be used directly with the injection‐molding machine. This method enables the setting of process conditions that yield parts having weights close to the target, by considering only the geometry and target weight.
{"title":"Development of Artificial Neural Network System to Recommend Process Conditions of Injection Molding for Various Geometries","authors":"Chihun Lee, Juwon Na, Kyongho Park, Hye-jeong Yu, Jongsun Kim, Kwon-Il Choi, D. Park, Seongjin Park, J. Rho, Seungchul Lee","doi":"10.1002/aisy.202000037","DOIUrl":"https://doi.org/10.1002/aisy.202000037","url":null,"abstract":"This study combines an artificial neural network (ANN) and a random search to develop a system to recommend process conditions for injection molding. Both simulation and experimental results are collected using a mixed sampling method that combines Taguchi and random sampling. The dataset consists of 3600 simulations and 476 experiments from 36 different molds. Each datum has five process and 15 geometry features as input and one weight feature as output. Hyper‐parameter tuning is conducted to find the optimal ANN model. Then, transfer learning is introduced, which allows the use of simultaneous experimental and simulation data to reduce the error. The final prediction model has a root mean‐square error of 0.846. To develop a recommender system, random search is conducted using the trained ANN forward model. As a result, the weight‐prediction model based on simulated data has a relative error (RE) of 0.73%, and the weight prediction using the transfer model has an RE of 0.662%. A user interface system is also developed, which can be used directly with the injection‐molding machine. This method enables the setting of process conditions that yield parts having weights close to the target, by considering only the geometry and target weight.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75161616","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}
Yegor Piskarev, J. Shintake, V. Ramachandran, Neil Baugh, M. Dickey, D. Floreano
The inherent compliance of soft robots often makes it difficult for them to exert forces on surrounding surfaces or withstand mechanical loading. Controlled stiffness is a solution to empower soft robots with the ability to apply large forces on their environments and sustain external loads without deformations. Herein, a compact, soft actuator composed of a shared electrode used for both electrostatic actuation and variable stiffness is described. The device operates as a dielectric elastomer actuator, while variable stiffness is provided by a shared electrode made of gallium. The fabricated actuator, namely variable stiffness dielectric elastomer actuator (VSDEA), has a compact and lightweight structure with a thickness of 930 μm and a mass of 0.7 g. It exhibits a stiffness change of 183×, a bending angle of 31°, and a blocked force of 0.65 mN. Thanks to the lightweight feature, the stiffness change per mass of the actuator (261× g−1) is 2.6 times higher than that of the other type of VSDEA that has no shared electrode.
{"title":"Lighter and Stronger: Cofabricated Electrodes and Variable Stiffness Elements in Dielectric Actuators","authors":"Yegor Piskarev, J. Shintake, V. Ramachandran, Neil Baugh, M. Dickey, D. Floreano","doi":"10.1002/aisy.202000069","DOIUrl":"https://doi.org/10.1002/aisy.202000069","url":null,"abstract":"The inherent compliance of soft robots often makes it difficult for them to exert forces on surrounding surfaces or withstand mechanical loading. Controlled stiffness is a solution to empower soft robots with the ability to apply large forces on their environments and sustain external loads without deformations. Herein, a compact, soft actuator composed of a shared electrode used for both electrostatic actuation and variable stiffness is described. The device operates as a dielectric elastomer actuator, while variable stiffness is provided by a shared electrode made of gallium. The fabricated actuator, namely variable stiffness dielectric elastomer actuator (VSDEA), has a compact and lightweight structure with a thickness of 930 μm and a mass of 0.7 g. It exhibits a stiffness change of 183×, a bending angle of 31°, and a blocked force of 0.65 mN. Thanks to the lightweight feature, the stiffness change per mass of the actuator (261× g−1) is 2.6 times higher than that of the other type of VSDEA that has no shared electrode.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82472943","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：