Human–machine interactions using deep-learning methods are important in the research of virtual reality,augmented reality,and metaverse.Such research remains challenging as current interactive sensing interfaces for ...Human–machine interactions using deep-learning methods are important in the research of virtual reality,augmented reality,and metaverse.Such research remains challenging as current interactive sensing interfaces for single-point or multipoint touch input are trapped by massive crossover electrodes,signal crosstalk,propagation delay,and demanding configuration requirements.Here,an all-inone multipoint touch sensor(AIOM touch sensor)with only two electrodes is reported.The AIOM touch sensor is efficiently constructed by gradient resistance elements,which can highly adapt to diverse application-dependent configurations.Combined with deep learning method,the AIOM touch sensor can be utilized to recognize,learn,and memorize human–machine interactions.A biometric verification system is built based on the AIOM touch sensor,which achieves a high identification accuracy of over 98%and offers a promising hybrid cyber security against password leaking.Diversiform human–machine interactions,including freely playing piano music and programmatically controlling a drone,demonstrate the high stability,rapid response time,and excellent spatiotemporally dynamic resolution of the AIOM touch sensor,which will promote significant development of interactive sensing interfaces between fingertips and virtual objects.展开更多
This study addresses the challenge of real-time resistivity gradient measurement in the Czochralski(CZ)silicon production process.Due to the inability to directly measure this parameter,we propose a Long Short-Term Me...This study addresses the challenge of real-time resistivity gradient measurement in the Czochralski(CZ)silicon production process.Due to the inability to directly measure this parameter,we propose a Long Short-Term Memory soft-sensing model based on Convolutional Neural Network(CNN)and attention mechanism(CNN-ALSTM)that enhances traditional LSTM by integrating CNN and attention mechanism to overcome time lag variations during silicon pulling.The CNN module extracts spatial features from multi-source sensor data,while the attention-enhanced LSTM(ALSTM)dynamically adjusts historical parameter weights,enabling accurate resistivity gradient prediction.Experiments with real production data show that CNN-ALSTM outperforms SVR,FNN,RNN,XGBoost,and GRU,improving prediction accuracy by 11.76%,16.67%,21.05%,30.23%,and 9.09%,respectively.This soft-sensing approach enhances real-time monitoring and optimization of monocrystalline silicon growth.展开更多
Lithium metal batteries provide high theoretical energy density and storage capacity but suffer from performance degradation and safety issues due to lithium dendrite formation.This research designed a resistivity gra...Lithium metal batteries provide high theoretical energy density and storage capacity but suffer from performance degradation and safety issues due to lithium dendrite formation.This research designed a resistivity gradient structure based on a 3D porous current collector to inhibit dendrite growth.Through a UV(ultraviolet)inactivation process,catalyst formation at the upper layers was suppressed,limiting the upper copper plating and enhancing plating toward the lower part during the electroless plating stage.Subsequently,electroplating was performed to increase the copper thickness.Experimental results showed that this gradient-resistivity current collector minimized the surface lithium deposition,which blocks pores.The charge-discharge stability evaluation demonstrated that batteries using this gradient structure exhibited higher stability and improved performance in full-cell and symmetrical-cell tests.This study presents significant technological progress toward commercializing lithium metal batteries.展开更多
Human-machine interfaces(HMI)are of paramount importance as they serve as essential conduits between humans and the digital realm.However,contemporary designs suffer from the following issues:large number of electrode...Human-machine interfaces(HMI)are of paramount importance as they serve as essential conduits between humans and the digital realm.However,contemporary designs suffer from the following issues:large number of electrodes,complex wiring,redundant data,and high power consumption.This work proposes a body-coupled minimalist human-machine interface for multifunctional touch detection(BM-HMI).The configuration of gradient resistive elements in the S-shape,in conjunction with a detection strategy founded upon the ratio of relative signal amplitudes,facilitates the effective detection of signals across a range of touch and sliding operations utilizing a mere two sensing electrodes.The experimental results demonstrate that the BM-HMI requires no battery,has remarkable stability(over 400,000 cycles),structural simplicity,rapid response time(approximately 5 ms),ultra-low detection threshold(below 0.04 N),robustness,and high scalability.This work presents a novel concept,demonstrating considerable potential for application in smart wearable devices,mixed reality systems,and ubiquitous sensing terminals.展开更多
基金supported by National Natural Science Foundation of China under Grants (U1805261 and 22161142024)A~*STAR SERC AME Programmatic Fund (A18A7b0058)
文摘Human–machine interactions using deep-learning methods are important in the research of virtual reality,augmented reality,and metaverse.Such research remains challenging as current interactive sensing interfaces for single-point or multipoint touch input are trapped by massive crossover electrodes,signal crosstalk,propagation delay,and demanding configuration requirements.Here,an all-inone multipoint touch sensor(AIOM touch sensor)with only two electrodes is reported.The AIOM touch sensor is efficiently constructed by gradient resistance elements,which can highly adapt to diverse application-dependent configurations.Combined with deep learning method,the AIOM touch sensor can be utilized to recognize,learn,and memorize human–machine interactions.A biometric verification system is built based on the AIOM touch sensor,which achieves a high identification accuracy of over 98%and offers a promising hybrid cyber security against password leaking.Diversiform human–machine interactions,including freely playing piano music and programmatically controlling a drone,demonstrate the high stability,rapid response time,and excellent spatiotemporally dynamic resolution of the AIOM touch sensor,which will promote significant development of interactive sensing interfaces between fingertips and virtual objects.
文摘This study addresses the challenge of real-time resistivity gradient measurement in the Czochralski(CZ)silicon production process.Due to the inability to directly measure this parameter,we propose a Long Short-Term Memory soft-sensing model based on Convolutional Neural Network(CNN)and attention mechanism(CNN-ALSTM)that enhances traditional LSTM by integrating CNN and attention mechanism to overcome time lag variations during silicon pulling.The CNN module extracts spatial features from multi-source sensor data,while the attention-enhanced LSTM(ALSTM)dynamically adjusts historical parameter weights,enabling accurate resistivity gradient prediction.Experiments with real production data show that CNN-ALSTM outperforms SVR,FNN,RNN,XGBoost,and GRU,improving prediction accuracy by 11.76%,16.67%,21.05%,30.23%,and 9.09%,respectively.This soft-sensing approach enhances real-time monitoring and optimization of monocrystalline silicon growth.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2022M3J1A1085403)the Korea Institute of Industrial Technology as“Development of root technology for multi-product flexible production”(KITECH EO-24-0009).
文摘Lithium metal batteries provide high theoretical energy density and storage capacity but suffer from performance degradation and safety issues due to lithium dendrite formation.This research designed a resistivity gradient structure based on a 3D porous current collector to inhibit dendrite growth.Through a UV(ultraviolet)inactivation process,catalyst formation at the upper layers was suppressed,limiting the upper copper plating and enhancing plating toward the lower part during the electroless plating stage.Subsequently,electroplating was performed to increase the copper thickness.Experimental results showed that this gradient-resistivity current collector minimized the surface lithium deposition,which blocks pores.The charge-discharge stability evaluation demonstrated that batteries using this gradient structure exhibited higher stability and improved performance in full-cell and symmetrical-cell tests.This study presents significant technological progress toward commercializing lithium metal batteries.
基金supported by the National Natural Science Foundation of China(No.52505071,No.52475071,No.52475072,No.52305308)the Yanzhao’s Young Scientist Project(2023203258)+5 种基金the Hebei Natural Science Foundation(E2022203002,and E2024203067)the Funded by Science Research Project of Hebei Education Department(QN2025183)the Shijiazhuang Science and Technology Planning Project(241790727A)the Opening Project of the Key Laboratory of Bionic Engineering(Ministry of Education,Jilin UniversityGrant Number KF2023003)The Fundamental Innovative Research Development Project of Yanshan University(2024LGQN008).
文摘Human-machine interfaces(HMI)are of paramount importance as they serve as essential conduits between humans and the digital realm.However,contemporary designs suffer from the following issues:large number of electrodes,complex wiring,redundant data,and high power consumption.This work proposes a body-coupled minimalist human-machine interface for multifunctional touch detection(BM-HMI).The configuration of gradient resistive elements in the S-shape,in conjunction with a detection strategy founded upon the ratio of relative signal amplitudes,facilitates the effective detection of signals across a range of touch and sliding operations utilizing a mere two sensing electrodes.The experimental results demonstrate that the BM-HMI requires no battery,has remarkable stability(over 400,000 cycles),structural simplicity,rapid response time(approximately 5 ms),ultra-low detection threshold(below 0.04 N),robustness,and high scalability.This work presents a novel concept,demonstrating considerable potential for application in smart wearable devices,mixed reality systems,and ubiquitous sensing terminals.
