Local or national crises, such as natural disasters, major infrastructure failures, and pandemics, pose dire threats to manufacturing. The concept of a rideshare‐like distributed network of consumer‐type 3D printers is proposed to address the limited ability of the industrial base to quickly respond to abrupt changes in critical product demand or to disruptions in manufacturing and supply‐chain capacity. The technical challenges that prevent the implementation of such a network are discussed, including 1) remote qualification of 3D printers, 2) dynamic routing algorithms with reactive and predictive components, which take advantage of real‐time information about current events that may affect the network, and 3) performance evaluation of the network. Furthermore, a cyber‐infrastructure that enables autonomous operation and reconfiguration of the network to render it “crisis‐proof” by minimizing human involvement is introduced. The concept of a distributed network of consumer‐type 3D printers allows anyone with a 3D printer and access to the internet to manufacture critical supplies, triggered by actual and predicted customer demand. Beyond crisis relief, distributed networks of manufacturing assets have broad relevance, and they can establish a virtual marketplace to exchange manufacturing capacity. Thus, this future manufacturing platform has the potential to transform how to manufacture for the masses.
{"title":"Manufacturing for the Masses: A Novel Concept for Consumer 3D Printer Networks in the Context of Crisis Relief","authors":"B. Raeymaekers, K. Leang, M. Porfiri, Shenghan Xu","doi":"10.1002/aisy.202100121","DOIUrl":"https://doi.org/10.1002/aisy.202100121","url":null,"abstract":"Local or national crises, such as natural disasters, major infrastructure failures, and pandemics, pose dire threats to manufacturing. The concept of a rideshare‐like distributed network of consumer‐type 3D printers is proposed to address the limited ability of the industrial base to quickly respond to abrupt changes in critical product demand or to disruptions in manufacturing and supply‐chain capacity. The technical challenges that prevent the implementation of such a network are discussed, including 1) remote qualification of 3D printers, 2) dynamic routing algorithms with reactive and predictive components, which take advantage of real‐time information about current events that may affect the network, and 3) performance evaluation of the network. Furthermore, a cyber‐infrastructure that enables autonomous operation and reconfiguration of the network to render it “crisis‐proof” by minimizing human involvement is introduced. The concept of a distributed network of consumer‐type 3D printers allows anyone with a 3D printer and access to the internet to manufacture critical supplies, triggered by actual and predicted customer demand. Beyond crisis relief, distributed networks of manufacturing assets have broad relevance, and they can establish a virtual marketplace to exchange manufacturing capacity. Thus, this future manufacturing platform has the potential to transform how to manufacture for the masses.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74523941","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}
Multimaterial 3D printing in electronics is expanding due to the ability to realize geometrically complex systems with simplified processes compared with conventional printed circuit board. Herein, the feasibility of using a copper‐based filament to realize 3D circuits with planar and vertical interconnections is presented. The resistivity of the tracks (1–3 mm wide) is studied with reference to printing parameters and orientation. Using lateral infill for 1 mm tracks offers lower resistance compared with longitudinal infill (≈75%). For wider tracks, the effect of infill orientation on resistance diminishes. The evaluation of tracks embedded in polylactic acid shows a drop in maximum current (to ≈11 mA) compared with exposed tracks (≈16 mA). There is no observed correlation between electrical performance and number of embedding layers. However, a significant correlation is observed between the tracks’ resistance and the amount of time the filament remains in the heated nozzle. This in‐depth study leads to optimum resolution to realize conductive tracks of 0.67 mm thickness and the first integration of fused deposition modeling (FDM)‐printed conductive traces with small‐outline integrated circuits to open a pathway for higher‐density 3D printed circuits. Finally, the transmission of digital data by a 3D printed circuit is demonstrated.
{"title":"Fused Deposition Modeling‐Based 3D‐Printed Electrical Interconnects and Circuits","authors":"Habib Nassar, R. Dahiya","doi":"10.1002/aisy.202100102","DOIUrl":"https://doi.org/10.1002/aisy.202100102","url":null,"abstract":"Multimaterial 3D printing in electronics is expanding due to the ability to realize geometrically complex systems with simplified processes compared with conventional printed circuit board. Herein, the feasibility of using a copper‐based filament to realize 3D circuits with planar and vertical interconnections is presented. The resistivity of the tracks (1–3 mm wide) is studied with reference to printing parameters and orientation. Using lateral infill for 1 mm tracks offers lower resistance compared with longitudinal infill (≈75%). For wider tracks, the effect of infill orientation on resistance diminishes. The evaluation of tracks embedded in polylactic acid shows a drop in maximum current (to ≈11 mA) compared with exposed tracks (≈16 mA). There is no observed correlation between electrical performance and number of embedding layers. However, a significant correlation is observed between the tracks’ resistance and the amount of time the filament remains in the heated nozzle. This in‐depth study leads to optimum resolution to realize conductive tracks of 0.67 mm thickness and the first integration of fused deposition modeling (FDM)‐printed conductive traces with small‐outline integrated circuits to open a pathway for higher‐density 3D printed circuits. Finally, the transmission of digital data by a 3D printed circuit is demonstrated.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84565067","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}
Inspired by competitive rules of the nature, competitive learning contributes to the specialization of the human brain and the general creativity of mankind. However, the construction of hardware competitive learning neural network still faces great challenges due to the lack of an accurate distance computation method and a self‐adaptive in situ training scheme. Herein, a fully memristive Euclidean distance (ED) engine based on analog multiply‐accumulate operation in a 32 × 32 TiN/TaO x /HfO x /TiN 1T1R array is demonstrated. The dual‐layer devices perform multilevel modulation under the target‐aware programming method with excellent read linearity in a dynamic range of 10–100 μS. The ED calculation is verified experimentally on a test board with an O(1) temporal complexity. Furthermore, in situ training and offline inference schemes for competitive learning, based on the ED engine, are developed and the simulated results show comparable success rates with those obtained by the CPU‐based software. Compared with a state‐of‐the‐art RTX6000 GPU (0.5 TOPS W−1), the energy efficiency of competitive learning models on ED engines can yield 100× improvements by utilizing optimized memristive devices.
竞争性学习受自然界竞争规律的启发，有助于人类大脑的专业化和人类的普遍创造力。然而，由于缺乏精确的距离计算方法和自适应的原位训练方案，硬件竞争学习神经网络的构建仍然面临着很大的挑战。本文演示了一种基于32 × 32 TiN/TaO x /HfO x /TiN 1T1R阵列模拟乘法累加运算的全记忆性欧氏距离(ED)引擎。该双层器件在目标感知编程方法下进行多电平调制，在10-100 μS的动态范围内具有良好的读取线性度。在时间复杂度为0(1)的测试板上进行了实验验证。此外，基于ED引擎开发了用于竞争学习的现场训练和离线推理方案，仿真结果显示与基于CPU的软件获得的成功率相当。与最先进的RTX6000 GPU (0.5 TOPS W−1)相比，利用优化的记忆器件，ED发动机上的竞争学习模型的能源效率可以提高100倍。
{"title":"Energy‐Efficient Memristive Euclidean Distance Engine for Brain‐Inspired Competitive Learning","authors":"Houji Zhou, Jia Chen, Yinan Wang, Sen Liu, Yi Li, Qingjiang Li, Qi Liu, Zhongrui Wang, Yuhui He, Hui Xu, X. Miao","doi":"10.1002/aisy.202100114","DOIUrl":"https://doi.org/10.1002/aisy.202100114","url":null,"abstract":"Inspired by competitive rules of the nature, competitive learning contributes to the specialization of the human brain and the general creativity of mankind. However, the construction of hardware competitive learning neural network still faces great challenges due to the lack of an accurate distance computation method and a self‐adaptive in situ training scheme. Herein, a fully memristive Euclidean distance (ED) engine based on analog multiply‐accumulate operation in a 32 × 32 TiN/TaO x /HfO x /TiN 1T1R array is demonstrated. The dual‐layer devices perform multilevel modulation under the target‐aware programming method with excellent read linearity in a dynamic range of 10–100 μS. The ED calculation is verified experimentally on a test board with an O(1) temporal complexity. Furthermore, in situ training and offline inference schemes for competitive learning, based on the ED engine, are developed and the simulated results show comparable success rates with those obtained by the CPU‐based software. Compared with a state‐of‐the‐art RTX6000 GPU (0.5 TOPS W−1), the energy efficiency of competitive learning models on ED engines can yield 100× improvements by utilizing optimized memristive devices.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77154710","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}
Untethered, magnetically driven microrobots have great potential in practical applications such as minimally invasive surgery. Microrods, also known as “nanowires,” are the most commonly used type of structure for microrobots due to the easy fabrication and promising functions. Driven by a uniform rotating magnetic field, microrods can perform a 2D movement with the assistance of a boundary surface, which severely limits the application of microrods in 3D spaces. Herein, an asymmetric structural design is proposed to construct rod‐shaped micropropellers that can achieve a surface‐free 3D propulsion. A theoretical model is formulated based on resistive force theory to investigate the dynamics of micropropellers. It is theoretically demonstrated and experimentally verified that the magnetic micropropeller can realize not only a 3D propulsion, but also multimodal locomotion to adapt to the environment. The work provides guidance for the design and optimization of autonomous micropropellers.
{"title":"3D Propulsions of Rod‐Shaped Micropropellers","authors":"Yuan Zhang, Xiangkui Tan, Xiying Li, Pengyu Lv, Tian-Yun Huang, Jianying Yang, Huiling Duan","doi":"10.1002/aisy.202100083","DOIUrl":"https://doi.org/10.1002/aisy.202100083","url":null,"abstract":"Untethered, magnetically driven microrobots have great potential in practical applications such as minimally invasive surgery. Microrods, also known as “nanowires,” are the most commonly used type of structure for microrobots due to the easy fabrication and promising functions. Driven by a uniform rotating magnetic field, microrods can perform a 2D movement with the assistance of a boundary surface, which severely limits the application of microrods in 3D spaces. Herein, an asymmetric structural design is proposed to construct rod‐shaped micropropellers that can achieve a surface‐free 3D propulsion. A theoretical model is formulated based on resistive force theory to investigate the dynamics of micropropellers. It is theoretically demonstrated and experimentally verified that the magnetic micropropeller can realize not only a 3D propulsion, but also multimodal locomotion to adapt to the environment. The work provides guidance for the design and optimization of autonomous micropropellers.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"164 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80389027","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}
Jing Li, Tianyu Wu, Huan Jiang, Yanyu Chen, Qibiao Yang
Pressure sensitivity and wide range are two crucial features of flexible electromechanical sensors for applications in the next‐generation of intelligent electronics, such as wearable healthcare monitors and soft human–machine interfaces. Conventional pressure sensors have a narrow pressure range (<10 kPa) and complex fabrication processes, which significantly hinder their extensive applications. A facile laser‐engraving method is proposed to fabricate a flexible multiwalled‐carbon‐nanotube (MWCNTs)/poly(dimethylsiloxane) (PDMS) composite‐based piezoresistive sensor with hierarchical microstructures. Herein, the nonstandard‐circular feature and Gaussian distributed facula of a laser spot are utilized to produce the middle‐level porous microdome upon the bottom‐level cylinder microcolumn array, while the top‐level tentacle‐like conical micropillars are produced by vertically rotating the acrylic mold during the laser engraving process. This novel hierarchical microstructure endows the proposed piezoresistive sensor with orders‐of‐magnitude of higher sensitivity (≈35.51 kPa−1) than that of other reported electromechanical sensors and a more extensive pressure sensing range up to 23 kPa. Moreover, the detection limit of the sensor is down to 2 Pa, which makes it a desirable candidate for monitoring subtle pressure. The sensor is successfully applied to distinguish the syllables of each pronounced word, detect movements of the human wrist, and monitor radial arterial pulse, thus demonstrating its promising applications in wearable electronics.
{"title":"Ultrasensitive Hierarchical Piezoresistive Pressure Sensor for Wide‐Range Pressure Detection","authors":"Jing Li, Tianyu Wu, Huan Jiang, Yanyu Chen, Qibiao Yang","doi":"10.1002/aisy.202100070","DOIUrl":"https://doi.org/10.1002/aisy.202100070","url":null,"abstract":"Pressure sensitivity and wide range are two crucial features of flexible electromechanical sensors for applications in the next‐generation of intelligent electronics, such as wearable healthcare monitors and soft human–machine interfaces. Conventional pressure sensors have a narrow pressure range (<10 kPa) and complex fabrication processes, which significantly hinder their extensive applications. A facile laser‐engraving method is proposed to fabricate a flexible multiwalled‐carbon‐nanotube (MWCNTs)/poly(dimethylsiloxane) (PDMS) composite‐based piezoresistive sensor with hierarchical microstructures. Herein, the nonstandard‐circular feature and Gaussian distributed facula of a laser spot are utilized to produce the middle‐level porous microdome upon the bottom‐level cylinder microcolumn array, while the top‐level tentacle‐like conical micropillars are produced by vertically rotating the acrylic mold during the laser engraving process. This novel hierarchical microstructure endows the proposed piezoresistive sensor with orders‐of‐magnitude of higher sensitivity (≈35.51 kPa−1) than that of other reported electromechanical sensors and a more extensive pressure sensing range up to 23 kPa. Moreover, the detection limit of the sensor is down to 2 Pa, which makes it a desirable candidate for monitoring subtle pressure. The sensor is successfully applied to distinguish the syllables of each pronounced word, detect movements of the human wrist, and monitor radial arterial pulse, thus demonstrating its promising applications in wearable electronics.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82463973","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}
Marco Fronzi, O. Isayev, D. Winkler, J. Shapter, Amanda V. Ellis, P. Sherrell, N. A. Shepelin, Alexander Corletto, M. Ford
The bandgap is one of the most fundamental properties of condensed matter. However, an accurate calculation of its value, which could potentially allow experimentalists to identify materials suitable for device applications, is very computationally expensive. Here, active machine learning algorithms are used to leverage a limited number of accurate density functional theory calculations to robustly predict the bandgap of a very large number of novel 2D heterostructures. Using this approach, a database of ≈2.2 million bandgap values for various novel 2D van der Waals heterostructures is produced.
{"title":"Active Learning in Bayesian Neural Networks for Bandgap Predictions of Novel Van der Waals Heterostructures","authors":"Marco Fronzi, O. Isayev, D. Winkler, J. Shapter, Amanda V. Ellis, P. Sherrell, N. A. Shepelin, Alexander Corletto, M. Ford","doi":"10.1002/aisy.202100080","DOIUrl":"https://doi.org/10.1002/aisy.202100080","url":null,"abstract":"The bandgap is one of the most fundamental properties of condensed matter. However, an accurate calculation of its value, which could potentially allow experimentalists to identify materials suitable for device applications, is very computationally expensive. Here, active machine learning algorithms are used to leverage a limited number of accurate density functional theory calculations to robustly predict the bandgap of a very large number of novel 2D heterostructures. Using this approach, a database of ≈2.2 million bandgap values for various novel 2D van der Waals heterostructures is produced.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"77 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87302926","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}
Priyanka Sharan, Charlie Maslen, Berk Altunkeyik, I. Rehor, J. Simmchen, T. Montenegro-Johnson
Hydrogels have received increased attention due to their biocompatible material properties, adjustable porosity, ease of functionalization, tuneable shape, and Young's moduli. Initial work has recognized the potential that conferring out‐of‐equilibrium properties to these on the microscale holds and envisions a broad range of biomedical applications. Herein, a simple strategy to integrate multiple swimming modes into catalase‐propelled hydrogel bodies, produced via stop‐flow lithography (SFL), is presented and the different dynamics that result from bubble expulsion are studied. It is found that for “Saturn” filaments, with active poles and an inert midpiece, the fundamental swimming modes correspond to the first three fundamental shape modes that can be obtained by buckling elastic filaments, namely, I, U, and S‐shapes.
{"title":"Fundamental Modes of Swimming Correspond to Fundamental Modes of Shape: Engineering I‐, U‐, and S‐Shaped Swimmers","authors":"Priyanka Sharan, Charlie Maslen, Berk Altunkeyik, I. Rehor, J. Simmchen, T. Montenegro-Johnson","doi":"10.1002/aisy.202100068","DOIUrl":"https://doi.org/10.1002/aisy.202100068","url":null,"abstract":"Hydrogels have received increased attention due to their biocompatible material properties, adjustable porosity, ease of functionalization, tuneable shape, and Young's moduli. Initial work has recognized the potential that conferring out‐of‐equilibrium properties to these on the microscale holds and envisions a broad range of biomedical applications. Herein, a simple strategy to integrate multiple swimming modes into catalase‐propelled hydrogel bodies, produced via stop‐flow lithography (SFL), is presented and the different dynamics that result from bubble expulsion are studied. It is found that for “Saturn” filaments, with active poles and an inert midpiece, the fundamental swimming modes correspond to the first three fundamental shape modes that can be obtained by buckling elastic filaments, namely, I, U, and S‐shapes.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"78 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74121778","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}
Intelligent microrobot systems at the microscopic scale provide enormous opportunities for emerging biomedical and environmental applications. Herein, a multiagent stochastic feedback control framework to control colloidal microrobot swarms for capturing Brownian cargo particles in complex environments such as mazes is proposed. The decision‐making module in the control framework consists of the adaptive generation of target sites surrounding the cargo, optimal target assignment, and approximate motion planning. The stochastic trajectories of robot swarms are efficiently navigated toward their exclusively assigned target around the cargo particle and enable the cargo to be captured. The capture strategy realized by the control framework is robust, adaptive, and flexible in that it accommodates diverse local geometries in the vicinity of a cargo, swarm, and maze sizes and is able to spontaneously split the workforce to catch multiple Brownian cargo particles via multitasking. The present intelligent robot swarm enabled by the multiagent control offers a path to realize complex functions at the microscopic scale in a resilient and flexible manner.
{"title":"Brownian Cargo Capture in Mazes via Intelligent Colloidal Microrobot Swarms","authors":"Kun Xu, Yuguang Yang, Bo Li","doi":"10.1002/aisy.202100115","DOIUrl":"https://doi.org/10.1002/aisy.202100115","url":null,"abstract":"Intelligent microrobot systems at the microscopic scale provide enormous opportunities for emerging biomedical and environmental applications. Herein, a multiagent stochastic feedback control framework to control colloidal microrobot swarms for capturing Brownian cargo particles in complex environments such as mazes is proposed. The decision‐making module in the control framework consists of the adaptive generation of target sites surrounding the cargo, optimal target assignment, and approximate motion planning. The stochastic trajectories of robot swarms are efficiently navigated toward their exclusively assigned target around the cargo particle and enable the cargo to be captured. The capture strategy realized by the control framework is robust, adaptive, and flexible in that it accommodates diverse local geometries in the vicinity of a cargo, swarm, and maze sizes and is able to spontaneously split the workforce to catch multiple Brownian cargo particles via multitasking. The present intelligent robot swarm enabled by the multiagent control offers a path to realize complex functions at the microscopic scale in a resilient and flexible manner.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"21 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91447542","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}
Chenxi Tian, Tianjiao Li, Jenniffer Bustillos, Shonak Bhattacharya, Talia Turnham, J. Yeo, A. Moridi
The latest industrial revolution, Industry 4.0, is driven by the emergence of digital manufacturing and, most notably, additive manufacturing (AM) technologies. The simultaneous material and structure forming in AM broadens the material and structural design space. This expanded design space holds a great potential in creating improved engineering materials and products that attract growing interests from both academia and industry. A major aspect of this growing interest is reflected in the increased adaptation of data‐driven tools that accelerate the exploration of the vast design space in AM. Herein, the integration of data‐driven tools in various aspects of AM is reviewed, from materials design in AM (i.e., homogeneous and composite material design) to structure design for AM (i.e., topology optimization). The optimization of AM tool path using machine learning for producing best‐quality AM products with optimal material and structure is also discussed. Finally, the perspectives on the future development of holistically integrated frameworks of AM and data‐driven methods are provided.
{"title":"Data‐Driven Approaches Toward Smarter Additive Manufacturing","authors":"Chenxi Tian, Tianjiao Li, Jenniffer Bustillos, Shonak Bhattacharya, Talia Turnham, J. Yeo, A. Moridi","doi":"10.1002/aisy.202100014","DOIUrl":"https://doi.org/10.1002/aisy.202100014","url":null,"abstract":"The latest industrial revolution, Industry 4.0, is driven by the emergence of digital manufacturing and, most notably, additive manufacturing (AM) technologies. The simultaneous material and structure forming in AM broadens the material and structural design space. This expanded design space holds a great potential in creating improved engineering materials and products that attract growing interests from both academia and industry. A major aspect of this growing interest is reflected in the increased adaptation of data‐driven tools that accelerate the exploration of the vast design space in AM. Herein, the integration of data‐driven tools in various aspects of AM is reviewed, from materials design in AM (i.e., homogeneous and composite material design) to structure design for AM (i.e., topology optimization). The optimization of AM tool path using machine learning for producing best‐quality AM products with optimal material and structure is also discussed. Finally, the perspectives on the future development of holistically integrated frameworks of AM and data‐driven methods are provided.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85860764","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}
Y. Lim, Chee Koon Ng, U. S. Vaitesswar, K. Hippalgaonkar
Bayesian optimization (BO) has emerged as the algorithm of choice for guiding the selection of experimental parameters in automated active learning driven high throughput experiments in materials science and chemistry. Previous studies suggest that optimization performance of the typical surrogate model in the BO algorithm, Gaussian processes (GPs), may be limited due to its inability to handle complex datasets. Herein, various surrogate models for BO, including GPs and neural network ensembles (NNEs), are investigated. Two materials datasets of different complexity with different properties are used, to compare the performance of GP and NNE—the first is the compressive strength of concrete (8 inputs and 1 target), and the second is a simulated high‐dimensional dataset of thermoelectric properties of inorganic materials (22 inputs and 1 target). While NNEs can converge faster toward optimum values, GPs with optimized kernels are able to ultimately achieve the best evaluated values after 100 iterations, even for the most complex dataset. This surprising result is contrary to expectations. It is believed that these findings shed new light on the understanding of surrogate models for BO, and can help accelerate the inverse design of new materials with better structural and functional performance.
{"title":"Extrapolative Bayesian Optimization with Gaussian Process and Neural Network Ensemble Surrogate Models","authors":"Y. Lim, Chee Koon Ng, U. S. Vaitesswar, K. Hippalgaonkar","doi":"10.1002/aisy.202100101","DOIUrl":"https://doi.org/10.1002/aisy.202100101","url":null,"abstract":"Bayesian optimization (BO) has emerged as the algorithm of choice for guiding the selection of experimental parameters in automated active learning driven high throughput experiments in materials science and chemistry. Previous studies suggest that optimization performance of the typical surrogate model in the BO algorithm, Gaussian processes (GPs), may be limited due to its inability to handle complex datasets. Herein, various surrogate models for BO, including GPs and neural network ensembles (NNEs), are investigated. Two materials datasets of different complexity with different properties are used, to compare the performance of GP and NNE—the first is the compressive strength of concrete (8 inputs and 1 target), and the second is a simulated high‐dimensional dataset of thermoelectric properties of inorganic materials (22 inputs and 1 target). While NNEs can converge faster toward optimum values, GPs with optimized kernels are able to ultimately achieve the best evaluated values after 100 iterations, even for the most complex dataset. This surprising result is contrary to expectations. It is believed that these findings shed new light on the understanding of surrogate models for BO, and can help accelerate the inverse design of new materials with better structural and functional performance.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89938243","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：