We propose a high-refractive-index(RI)sensor based on a no-core fiber(NCF)with a waist-enlarged fusion-taper(WEFT)structure,achieving high measurement accuracy with the assistance of the gated recurrent unit(GRU)neura...We propose a high-refractive-index(RI)sensor based on a no-core fiber(NCF)with a waist-enlarged fusion-taper(WEFT)structure,achieving high measurement accuracy with the assistance of the gated recurrent unit(GRU)neural network.This sensor integrates the NCF in series with single-mode fibers,forming the WEFT structure through arc discharge using a fiber fusion splicer to construct a modal interferometer.In the experiment,the proposed sensor has been used for high RI(ranging from 1.4330 to 1.4505)measurement.Due to the high RI being close to that of the optical fiber,traditional spectral interference dip demodulation produces nonlinear responses,increasing the measurement error in sensing.The GRU neural network algorithm is employed to train and test the recorded spectral samples,and the experimental results indicate that the coefficient of determination for this neural network model reaches 99.93%,with a mean squared error of 2.24×10-8(RIU).This deep learning model can be widely applied to similar fiber sensing applications and demonstrates significant potential for intelligent sensing within optical networks.展开更多
Reverse design of highly GeO2-doped silica optical fibers with broadband and flat dispersion profiles is proposed using a neural network(NN) combined with a particle swarm optimization(PSO) algorithm.Firstly,the NN mo...Reverse design of highly GeO2-doped silica optical fibers with broadband and flat dispersion profiles is proposed using a neural network(NN) combined with a particle swarm optimization(PSO) algorithm.Firstly,the NN model designed to predict optical fiber dispersion is trained with an appropriate choice of hyperparameters,achieving a root mean square error(RMSE) of 9.47×10-7on the test dataset,with a determination coefficient(R2) of 0.999.Secondly,the NN is combined with the PSO algorithm for the inverse design of dispersion-flattened optical fibers.To expand the search space and avoid particles becoming trapped in local optimal solutions,the PSO algorithm incorporates adaptive inertia weight updating and a simulated annealing algorithm.Finally,by using a suitable fitness function,the designed fibers exhibit flat group velocity dispersion(GVD) profiles at 1 400—2 400 nm,where the GVD fluctuations and minimum absolute GVD values are below 18 ps·nm-1·km-1and 7 ps·nm-1·km-1,respectively.展开更多
Optical phase transfer via fiber optics is the most effective method for optical frequency standard comparison on the scale below thousands of kilometers.However,the monotonic phase discrimination range of conventiona...Optical phase transfer via fiber optics is the most effective method for optical frequency standard comparison on the scale below thousands of kilometers.However,the monotonic phase discrimination range of conventional optical phase-locked loops is limited,and link delays restrict the control bandwidth,which makes it a challenge to achieve a continuously reliable optical link.This paper presents an event-timing-based phase detection method that overcomes the monotonic phase discrimination range limitation of conventional phase-locked loops through dual-edge timestamp recording,achieving an optical phase measurement resolution on the order of 10 attoseconds.With such a technique,we established a 7-segment-cascaded optical link over 1402km of commercial fiber while sharing dense wavelength division multiplexing(DWDM)channels with live telecom traffic.The system maintained continuous operation for 11.7 days without phase cycle slips despite encountering 15 km aerial fiber noise up to 21000 rad^(2)·Hz^(−1)·km^(−1)at 1 Hz.Relative instabilities of the link are 3.7×10^(−15)at 1 s and 3.9×10^(−20)at 100000 s.展开更多
The rapid evolution of the autonomous driving industry has led to a surge in electronic units and applications,resulting in increased in-vehicle data traffic and higher demands for communication efficiency and securit...The rapid evolution of the autonomous driving industry has led to a surge in electronic units and applications,resulting in increased in-vehicle data traffic and higher demands for communication efficiency and security.Meanwhile,safe driving necessitates further development of in-vehicle thermal management systems,as traditional point-type sensors face deployment challenges due to their limited monitoring range.All-glass multimode fibers(AG-MMFs)emerge as an ideal solution for sensing and transmission.An integrated sensing and communication(ISAC)system based on AG-MMFs has been proposed and experimentally validated for stable and efficient operation across a broad temperature range from-18°C to 122°C,while maintaining strong tolerance to typical vehicle vibrations and connector misalignments.Utilizing a single commercial OM4 fiber,we achieve error-free PAM-4 transmission up to 100 Gb∕s with the aid of forward error correction and precise real-time temperature monitoring over 100 m at the same time.Furthermore,by adopting a looped link structure and a neural network-based denoising algorithm,temperature measuring maintains an average uncertainty and a spatial resolution of 0.1°C and 0.5 m,respectively,even under extreme conditions.Exhibiting such outstanding performance in both transmission and sensing,the ISAC architecture successfully addresses the growing demands for high-capacity in-vehicle networks and distributed thermal monitoring of critical components,while paving the theoretical foundation for“fiber to vehicle.”展开更多
While various kinds of fibers are used to improve the hot mix asphalt(HMA) performance, a few works have been undertaken on the hybrid fiber-reinforced HMA. Therefore, the fatigue life of modified HMA samples using po...While various kinds of fibers are used to improve the hot mix asphalt(HMA) performance, a few works have been undertaken on the hybrid fiber-reinforced HMA. Therefore, the fatigue life of modified HMA samples using polypropylene and polyester fibers was evaluated and two models namely regression and artificial neural network(ANN) were used to predict the fatigue life based on the fibers parameters. As ANN contains many parameters such as the number of hidden layers which directly influence the prediction accuracy, genetic algorithm(GA) was used to solve optimization problem for ANN. Moreover, the trial and error method was used to optimize the GA parameters such as the population size. The comparison of the results obtained from regression and optimized ANN with GA shows that the two-hidden-layer ANN with two and five neurons in the first and second hidden layers, respectively, can predict the fatigue life of fiber-reinforced HMA with high accuracy(correlation coefficient of 0.96).展开更多
To investigate wavelength response of the no core fiber（NCF）interference spectrum to concentration,a three-layer back propagation（BP）neural network model was established to optimize the concentration sensing data....To investigate wavelength response of the no core fiber（NCF）interference spectrum to concentration,a three-layer back propagation（BP）neural network model was established to optimize the concentration sensing data.In this method,the measured wavelength and the corresponding concentration were trained by a BP neural network,so that the accuracy of the measurement system was optimized.The wavelength was used as the training set and got into the input layer of the three layer BP network model which is used as the input value of the network,and the corresponding actual concentration value was used as the output value of the network,and the optimal network structure was trained.This paper discovers a preferable correlation between the predicted value and the actual value,where the former is approximately equal to the latter.The correlation coefficients of the measured and predicted values for a sucrose concentration were 1.000 89 and 1.003 94;similarly,correlations of0.999 51 and 1.018 8 for a glucose concentration were observed.The results demonstrate that the BP neural network can improve the prediction accuracy of the nonlinear relationship between the interference spectral data and the concentration in NCF sensing systems.展开更多
Al-Si alloy,a high temperature phase change material,has great potential in thermal management due to its advantages of high heat storage density and thermal conductivity.Microencapsulation of Al-Si alloy is one of th...Al-Si alloy,a high temperature phase change material,has great potential in thermal management due to its advantages of high heat storage density and thermal conductivity.Microencapsulation of Al-Si alloy is one of the effective techniques to solve high temperature leakage and corrosion.In this paper,commercial Al-10Si alloy micro powders were encapsulated with flexible ceramic shells whose total thickness is below 1μm by hydrothermal treatment and heat treatment in N_(2) atmosphere.The compositions and microstructures were characterized by XRD,SEM and TEM.The shell was composed of AlN fibers network structure embedded withα-Al_(2)O_(3)/AlN which prevented the alloy from leaking and oxidizing,as well as had excellent thermal stability.The latent heat of microcapsules was 351.8 J g^(-1)for absorption and 372.7 J g^(-1)for exothermic.The microcapsules showed near zero thermal performance loss with latent heat storage(LHS)/release(LHR)was 353.2/403.7 J g^(-1)after 3000 cycles.Compared with the published Al-Si alloy microcapsules,both high heat storage density and super thermal cycle stability were achieved,showing promising development prospects in high temperature thermal management.展开更多
In this study,artificial neural networks trained with swarm based artificial bee colony optimization algorithm was implemented for prediction of the modulus of rapture values of the fabricated glass fiber reinforced c...In this study,artificial neural networks trained with swarm based artificial bee colony optimization algorithm was implemented for prediction of the modulus of rapture values of the fabricated glass fiber reinforced concrete panels.For the application of the ANN models,143 different four-point bending test results of glass fiber reinforced concrete mixes with the varied parameters of temperature,fiber content and slump values were introduced the artificial bee colony optimization and conventional back propagation algorithms.Training and the testing results of the corresponding models showed that artificial neural networks trained with the artificial bee colony optimization algorithm have remarkable potential for the prediction of modulus of rupture values and this method can be used as a preliminary decision criterion for quality check of the fabricated products.展开更多
In this study, an artificial neural network (ANN) model for studying the strength properties of steel fiber reinforced concrete (SFRC) containing fly ash was devised. The mixtures were prepared with 0 wt%, 15 wt%, and...In this study, an artificial neural network (ANN) model for studying the strength properties of steel fiber reinforced concrete (SFRC) containing fly ash was devised. The mixtures were prepared with 0 wt%, 15 wt%, and 30 wt% of fly ash, at 0 vol.%, 0.5 vol.%, 1.0 vol.% and 1.5 vol.% of fiber, respectively. After being cured under the standard conditions for 7, 28, 90 and 365 d, the specimens of each mixture were tested to determine the corresponding compressive and flexural strengths. The pa- rameters such as the amounts of cement, fly ash replacement, sand, gravel, steel fiber, and the age of samples were selected as input variables, while the compressive and flexural strengths of the concrete were chosen as the output variables. The back propagation learning algorithm with three different variants, namely the Levenberg-Marquardt (LM), scaled conjugate gradient (SCG) and Fletcher-Powell conjugate gradient (CGF) algorithms were used in the network so that the best approach can be found. The results obtained from the model and the experiments were compared, and it was found that the suitable algorithm is the LM algorithm. Furthermore, the analysis of variance (ANOVA) method was used to determine how importantly the experimental parameters affect the strength of these mixtures.展开更多
Carbon fiber(C_(f))reinforced pyrolytic carbon(PyC)composites simultaneously possessing robust mechanical strength,excellent friction performances and outstanding anti-ablation properties are demanded for advanced aer...Carbon fiber(C_(f))reinforced pyrolytic carbon(PyC)composites simultaneously possessing robust mechanical strength,excellent friction performances and outstanding anti-ablation properties are demanded for advanced aerospace applications.Efficient architecture design and optimization of composites are promi-nent yet remain high challenging for realizing the above requirements.Herein,binary reinforcements of networked silicon nitride nanowires(Si_(3)N_(4) nws)and interconnected graphene(GE)have been successfully constructed into C f/PyC by precursor impregnation-pyrolysis and chemical vapor deposition.Notably,net-worked Si_(3)N_(4) nws are uniformly distributed among the carbon fibers,while interconnected GE is firmly rooted on the surface of both networked Si_(3)N_(4) nws and carbon fibers.In the networked Si_(3)N_(4) nws and interconnected GE reinforced C_(f)/PyC,networked Si_(3)N_(4) nws significantly boost the cohesion strength of PyC,while GE markedly improves the interface bonding of both Si_(3)N_(4) nws/PyC and fiber/PyC.Benefiting from the synergistic reinforcement effect of networked Si_(3)N_(4) nws and interconnected GE,the C_(f)/PyC have a prominent enhancement in mechanical(shear and compressive strengths increased by 119.9% and 52.84%,respectively)and friction(friction coefficient and wear rate reduced by 25.40% and 60.10%,respectively)as well as anti-ablation(mass ablation rate and linear ablation rate decreased by 71.25% and 63.01%,respectively).This present strategy for networked Si_(3)N_(4) nws and interconnected GE reinforced C_(f)/PyC provides a dominant route to produce mechanically robust,frictionally resisting and ablatively resistant materials for use in advanced aerospace applications.展开更多
This paper investigates the Medium Access Control(MAC)protocol performance in the IEEE 802.11g-over-fiber network for different payloads and fiber lengths using Direct Sequence Spread Spectrum-Orthogonal Frequency Div...This paper investigates the Medium Access Control(MAC)protocol performance in the IEEE 802.11g-over-fiber network for different payloads and fiber lengths using Direct Sequence Spread Spectrum-Orthogonal Frequency Division Multiplexing(DSSSOFDM)and Extended Rate PhysicalsOrthogonal Frequency Division Multiplexing(ERP-OFDM)physical layers using basic access mode,Request to Send/Clear to Send(RTS/CTS)and CTS-to-self mechanisms.The results show that IEEE 802.11g-over-fiber network employing the ERP-OFDM physical layer is much more efficient than that employing the DSSS-OFDM physical layer,with regards to both throughput and delay.For a given maximum throughput/minimum delay,the tradeoff among the access mechanism,the fiber length,and the payload size must be considered.Our quantified results give a selection basis for the operators to quickly select suitable IEEE 802.11g physical layers and the different access mechanisms,and accurately predict the data throughput and delay given the specific parameters.展开更多
SnO_(2) has been extensively investigated as an anode material for sodium-ion batteries(SIBs)and potassium-ion batteries(PIBs)due to its high Na/K storage capacity,high abundance,and low toxicity.However,the sluggish ...SnO_(2) has been extensively investigated as an anode material for sodium-ion batteries(SIBs)and potassium-ion batteries(PIBs)due to its high Na/K storage capacity,high abundance,and low toxicity.However,the sluggish reaction kinetics,low electronic conductivity,and large volume changes during charge and discharge hinder the practical applications of SnO_(2)-based electrodes for SIBs and PIBs.Engineering rational structures with fast charge/ion transfer and robust stability is important to overcoming these challenges.Herein,S-doped SnO_(2)(S-SnO_(2))quantum dots(QDs)(≈3 nm)encapsulated in an N,S codoped carbon fiber networks(S-SnO_(2)-CFN)are rationally fabricated using a sequential freeze-drying,calcination,and S-doping strategy.Experimental analysis and density functional theory calculations reveal that the integration of S-SnO_(2) QDs with N,S codoped carbon fiber network remarkably decreases the adsorption energies of Na/K atoms in the interlayer of SnO_(2)-CFN,and the S doping can increase the conductivity of SnO_(2),thereby enhancing the ion transfer kinetics.The synergistic interaction between S-SnO_(2) QDs and N,S codoped carbon fiber network results in a composite with fast Na+/K+storage and extraordinary long-term cyclability.Specifically,the S-SnO_(2)-CFN delivers high rate capacities of 141.0 mAh g^(−1) at 20 A g^(−1) in SIBs and 102.8 mAh g^(−1) at 10 A g^(−1) in PIBs.Impressively,it delivers ultra-stable sodium storage up to 10,000 cycles at 5 A g^(−1) and potassium storage up to 5000 cycles at 2 A g^(−1).This study provides insights into constructing metal oxide-based carbon fiber network structures for high-performance electrochemical energy storage and conversion devices.展开更多
Intelligent assembly of large-scale,complex structures using an intelligent manufacturing platform represents the future development direction for industrial manufacturing.During large-scale structural assembly proces...Intelligent assembly of large-scale,complex structures using an intelligent manufacturing platform represents the future development direction for industrial manufacturing.During large-scale structural assembly processes,several bottleneck problems occur in the existing auxiliary assembly technology.First,the traditional LiDARbased assembly technology is often limited by the openness of the manufacturing environment,in which there are blind spots,and continuous online assembly adjustment thus cannot be realized.Second,for assembly of large structures,a single-station LiDAR system cannot achieve complete coverage,which means that a multi-station combination method must be used to acquire the complete three-dimensional data;many more data errors are caused by the transfer between stations than by the measurement accuracy of a single station,which means that the overall system's measurement and adjustment errors are increased greatly.Third,because of the large numbers of structural components contained in a large assembly,the accumulated errors may lead to assembly interference,but the LiDAR-assisted assembly process does not have a feedback perception capability,and thus assembly component loss can easily be caused when assembly interference occurs.Therefore,this paper proposes to combine an optical fiber sensor network with digital twin technology,which will allow the test data from the assembly entity state in the real world to be applied to the"twin"model in the virtual world and thus solve the problems with test openness and data transfer.The problem of station and perception feedback is also addressed and represents the main innovation of this work.The system uses an optical fiber sensor network as a flexible sensing medium to monitor the strain field distribution within a complex area in real time,and then completes real-time parameter adjustment of the virtual assembly based on the distributed data.Complex areas include areas that are laser-unreachable,areas with complex contact surfaces,and areas with large-scale bending deformations.An assembly condition monitoring system is designed based on the optical fiber sensor network,and an assembly condition monitoring algorithm based on multiple physical quantities is proposed.The feasibility of use of the optical fiber sensor network as the real-state parameter acquisition module for the digital twin intelligent assembly system is discussed.The offset of any position in the test area is calculated using the convolutional neural network of a residual module to provide the compensation parameters required for the virtual model of the assembly structure.In the model optimization parameter module,a correction data table is obtained through iterative learning of the algorithm to realize state prediction from the test data.The experiment simulates a largescale structure assembly process,and performs virtual and real mapping for a variety of situations with different assembly errors to enable correction of the digital twin data stream for the assembly process through the optical fiber sensor network.In the plane strain field calibration experiment,the maximum error among the test values for this system is 0.032 mm,and the average error is 0.014 mm.The results show that use of visual calibration can correct the test error to within a very small range.This result is equally applicable to gradient curvature surfaces and freeform surfaces.Statistics show that the average measurement accuracy error for regular surfaces is better than 11.2%,and the average measurement accuracy error for irregular surfaces is better than 14.8%.During simulation of large-scale structure assembly experiments,the average position deviation accuracy is 0.043 mm,which is in line with the designed accuracy.展开更多
The computation resources at a single node in Edge Computing(EC)are commonly limited,which cannot execute large scale computation tasks.To face the challenge,an Offloading scheme leveraging on NEighboring node Resourc...The computation resources at a single node in Edge Computing(EC)are commonly limited,which cannot execute large scale computation tasks.To face the challenge,an Offloading scheme leveraging on NEighboring node Resources(ONER)for EC over Fiber-Wireless(FiWi)access networks is proposed in this paper.In the ONER scheme,the FiWi network connects edge computing nodes with fiber and converges wireless and fiber connections seamlessly,so that it can support the offloading transmission with low delay and wide bandwidth.Based on the ONER scheme supported by FiWi networks,computation tasks can be offloaded to edge computing nodes in a wider range of area without increasing wireless hops(e.g.,just one wireless hop),which achieves low delay.Additionally,an efficient Computation Resource Scheduling(CRS)algorithm based on the ONER scheme is also proposed to make offloading decision.The results show that more offloading requests can be satisfied and the average completion time of computation tasks decreases significantly with the ONER scheme and the CRS algorithm.Therefore,the ONER scheme and the CRS algorithm can schedule computation resources at neighboring edge computing nodes for offloading to meet the challenge of large scale computation tasks.展开更多
A large mode area multi-core orbital angular momentum(OAM)transmission fiber is designed and optimized by neural network and optimization algorithms.The neural network model has been established first to predict the o...A large mode area multi-core orbital angular momentum(OAM)transmission fiber is designed and optimized by neural network and optimization algorithms.The neural network model has been established first to predict the optical properties of multi-core OAM transmission fibers with high accuracy and speed,including mode area,nonlinear coefficient,purity,dispersion,and effective index difference.Then the trained neural network model is combined with different particle swarm optimization(PSO)algorithms for automatic iterative optimization of multi-core structures respectively.Due to the structural advantages of multi-core fiber and the automatic optimization process,we designed a number of multi-core structures with high OAM mode purity(>95%)and ultra-large mode area(>3000µm^(2)),which is larger by more than an order of magnitude compared to the conventional ring-core OAM transmission fibers.展开更多
The fiber nonlinearity and phase noise(PN)are the focused impairments in the optical communication system,induced by high-capacity transmission and high laser input power.The channels include high-capacity transmissio...The fiber nonlinearity and phase noise(PN)are the focused impairments in the optical communication system,induced by high-capacity transmission and high laser input power.The channels include high-capacity transmissions that cannot be achieved at the end side without aliasing because of fiber nonlinearity and PN impairments.Thus,addressing of these distortions is the basic objective for the 5G mobile network.In this paper,the fiber nonlinearity and PN are investigated using the assembled methodology of millimeter-wave and radio over fiber(mmWave-RoF).The analytical model is designed in terms of outage probability for the proposed mmWave-RoF system.The performance of mmWave-RoF against fiber nonlinearity and PN is studied for input power,output power and length using peak to average power ratio(PAPR)and bit error rate(BER)measuring parameters.The simulation outcomes present that the impacts of fiber nonlinearity and PNcan be balanced for a huge capacity mmWave-RoF model applying input power carefully.展开更多
An Extrinsic Fabry-Perot Interferometric (EFPI) fiber optical sensor system is an online testing system for the gas density. The system achieves the measurement of gas density information mainly by demodulating the ca...An Extrinsic Fabry-Perot Interferometric (EFPI) fiber optical sensor system is an online testing system for the gas density. The system achieves the measurement of gas density information mainly by demodulating the cavity length of EF- PI fiber optical sensor. There are many ways to achieve the demodulation of the cavity length. For shortcomings of the big intensity demodulation error and complex structure of phase demodulation, this paper proposes that BP neural net-work is used to locate the special peak points in normalized interference spectrum and combining the advantages of the unimodal and bimodal measurement achieves the demodulation of the cavity length. Through online simulation and actual measurement, the results show that the peak positioning technology based on BP neural network can not only achieve high-precision demodulation of the cavity length, but also achieve an absolute measurement of cavity length in large dynamic range.展开更多
The buckling load of carbon fiber composite cylindrical shells(CF-CCSs)was predicted using a backpropagation neural network improved by the sparrow search algorithm(SSA-BPNN).Firstly,two CF-CCSs,each with an inner dia...The buckling load of carbon fiber composite cylindrical shells(CF-CCSs)was predicted using a backpropagation neural network improved by the sparrow search algorithm(SSA-BPNN).Firstly,two CF-CCSs,each with an inner diameter of 100 mm,were manufactured and tested.The buckling behavior of CF-CCSs was analyzed by finite element and experiment.Subsequently,the effects of ply angle and length–diameter ratio on buckling load of CF-CCSs were analyzed,and the dataset of the neural network was generated using the finite element method.On this basis,the SSA-BPNN model for predicting buckling load of CF-CCS was established.The results show that the maximum and average errors of the SSA-BPNN to the test data are 6.88%and 2.24%,respectively.The buckling load prediction for CF-CCSs based on SSA-BPNN has satisfactory generalizability and can be used to analyze buckling loads on cylindrical shells of carbon fiber composites.展开更多
Fiber loop ringdown (FLRD) has demonstrated to be capable of sensing various quantities, such as chemical species, pressure, refractive index, strain, temperature, etc.;and it has high potential for the development of...Fiber loop ringdown (FLRD) has demonstrated to be capable of sensing various quantities, such as chemical species, pressure, refractive index, strain, temperature, etc.;and it has high potential for the development of a sensor network. In the present work, we describe design and development of three different types of FLRD sensors for water, cracks, and temperature sensing in concrete structures. All of the three aforementioned sensors were indigenously developed very recently in our laboratory and their capabilities of detecting the respective quantities were demonstrated. Later, all of the sensors were installed in a test grout cube for real-time monitoring. This work presents the results obtained in the laboratory-based experiments as well as the results from the real-time monitoring process in the test cube.展开更多
Phase-sensitive Optical Time-Domain Reflectometer(φ-OTDR)technology facilitates the real-time detection of vibration events along fiber optic cables by analyzing changes in Rayleigh scattering signals.This technology...Phase-sensitive Optical Time-Domain Reflectometer(φ-OTDR)technology facilitates the real-time detection of vibration events along fiber optic cables by analyzing changes in Rayleigh scattering signals.This technology is widely used in applications such as intrusion monitoring and structural health assessments.Traditional signal processing methods,such as Support Vector Machines(SVM)and K-Nearest Neighbors(KNN),have limitations in feature extraction and classification in complex environments.Conversely,a single deep learning model often struggles with capturing long time-series dependencies and mitigating noise interference.In this study,we propose a deep learning model that integrates Convolutional Neural Network(CNN),Long Short-Term Memory Network(LSTM),and Transformer modules,leveraging φ-OTDR technology for distributed fiber vibration sensing event recognition.The hybrid model combines the CNN's capability to extract local features,the LSTM's ability to model temporal dynamics,and the Transformer's proficiency in capturing global dependencies.This integration significantly enhances the accuracy and robustness of event recognition.In experiments involving six types of vibration events,the model consistently achieved a validation accuracy of 0.92,and maintained a validation loss of approximately 0.2,surpassing other models,such as TAM+BiLSTM and CNN+CBAM.The results indicate that the CNN+LSTM+Transformer model is highly effective in handling vibration signal classification tasks in complex scenarios,offering a promising new direction for the application of fiber optic vibration sensing technology.展开更多
基金supported by the Aeronautical Science Foun-dation of China(Grant No.2023M026068001).
文摘We propose a high-refractive-index(RI)sensor based on a no-core fiber(NCF)with a waist-enlarged fusion-taper(WEFT)structure,achieving high measurement accuracy with the assistance of the gated recurrent unit(GRU)neural network.This sensor integrates the NCF in series with single-mode fibers,forming the WEFT structure through arc discharge using a fiber fusion splicer to construct a modal interferometer.In the experiment,the proposed sensor has been used for high RI(ranging from 1.4330 to 1.4505)measurement.Due to the high RI being close to that of the optical fiber,traditional spectral interference dip demodulation produces nonlinear responses,increasing the measurement error in sensing.The GRU neural network algorithm is employed to train and test the recorded spectral samples,and the experimental results indicate that the coefficient of determination for this neural network model reaches 99.93%,with a mean squared error of 2.24×10-8(RIU).This deep learning model can be widely applied to similar fiber sensing applications and demonstrates significant potential for intelligent sensing within optical networks.
基金supported by the Fundamental Research Funds for the Central Universities (No.2024JBZY021)the National Natural Science Foundation of China (No.61575018)。
文摘Reverse design of highly GeO2-doped silica optical fibers with broadband and flat dispersion profiles is proposed using a neural network(NN) combined with a particle swarm optimization(PSO) algorithm.Firstly,the NN model designed to predict optical fiber dispersion is trained with an appropriate choice of hyperparameters,achieving a root mean square error(RMSE) of 9.47×10-7on the test dataset,with a determination coefficient(R2) of 0.999.Secondly,the NN is combined with the PSO algorithm for the inverse design of dispersion-flattened optical fibers.To expand the search space and avoid particles becoming trapped in local optimal solutions,the PSO algorithm incorporates adaptive inertia weight updating and a simulated annealing algorithm.Finally,by using a suitable fitness function,the designed fibers exhibit flat group velocity dispersion(GVD) profiles at 1 400—2 400 nm,where the GVD fluctuations and minimum absolute GVD values are below 18 ps·nm-1·km-1and 7 ps·nm-1·km-1,respectively.
基金supported by the National Key Research and Development Program of China(Grant No.2020YFC2200103)the Shandong Provincial Natural Science Foundation(Grant Nos.ZR2022LLZ006 and ZR2022LLZ011)+1 种基金the Innovation Program for Quantum Science and Technology(Grant Nos.2021ZD0300904 and 2021ZD0300903)the Key R&D Plan of Shandong Province(Grant No.2023CXPT105)。
文摘Optical phase transfer via fiber optics is the most effective method for optical frequency standard comparison on the scale below thousands of kilometers.However,the monotonic phase discrimination range of conventional optical phase-locked loops is limited,and link delays restrict the control bandwidth,which makes it a challenge to achieve a continuously reliable optical link.This paper presents an event-timing-based phase detection method that overcomes the monotonic phase discrimination range limitation of conventional phase-locked loops through dual-edge timestamp recording,achieving an optical phase measurement resolution on the order of 10 attoseconds.With such a technique,we established a 7-segment-cascaded optical link over 1402km of commercial fiber while sharing dense wavelength division multiplexing(DWDM)channels with live telecom traffic.The system maintained continuous operation for 11.7 days without phase cycle slips despite encountering 15 km aerial fiber noise up to 21000 rad^(2)·Hz^(−1)·km^(−1)at 1 Hz.Relative instabilities of the link are 3.7×10^(−15)at 1 s and 3.9×10^(−20)at 100000 s.
基金supported by the National Key R&D Program of China(Grant No.2023YFB2906303)the National Natural Science Foundation of China(Grant No.62225110)+1 种基金the JD Project of Hubei Province(Grant No.2023BAA013)the Innovation Fund of WNLO。
文摘The rapid evolution of the autonomous driving industry has led to a surge in electronic units and applications,resulting in increased in-vehicle data traffic and higher demands for communication efficiency and security.Meanwhile,safe driving necessitates further development of in-vehicle thermal management systems,as traditional point-type sensors face deployment challenges due to their limited monitoring range.All-glass multimode fibers(AG-MMFs)emerge as an ideal solution for sensing and transmission.An integrated sensing and communication(ISAC)system based on AG-MMFs has been proposed and experimentally validated for stable and efficient operation across a broad temperature range from-18°C to 122°C,while maintaining strong tolerance to typical vehicle vibrations and connector misalignments.Utilizing a single commercial OM4 fiber,we achieve error-free PAM-4 transmission up to 100 Gb∕s with the aid of forward error correction and precise real-time temperature monitoring over 100 m at the same time.Furthermore,by adopting a looped link structure and a neural network-based denoising algorithm,temperature measuring maintains an average uncertainty and a spatial resolution of 0.1°C and 0.5 m,respectively,even under extreme conditions.Exhibiting such outstanding performance in both transmission and sensing,the ISAC architecture successfully addresses the growing demands for high-capacity in-vehicle networks and distributed thermal monitoring of critical components,while paving the theoretical foundation for“fiber to vehicle.”
文摘While various kinds of fibers are used to improve the hot mix asphalt(HMA) performance, a few works have been undertaken on the hybrid fiber-reinforced HMA. Therefore, the fatigue life of modified HMA samples using polypropylene and polyester fibers was evaluated and two models namely regression and artificial neural network(ANN) were used to predict the fatigue life based on the fibers parameters. As ANN contains many parameters such as the number of hidden layers which directly influence the prediction accuracy, genetic algorithm(GA) was used to solve optimization problem for ANN. Moreover, the trial and error method was used to optimize the GA parameters such as the population size. The comparison of the results obtained from regression and optimized ANN with GA shows that the two-hidden-layer ANN with two and five neurons in the first and second hidden layers, respectively, can predict the fatigue life of fiber-reinforced HMA with high accuracy(correlation coefficient of 0.96).
基金Supported by the National Natural Science Foundation of China(61307122)the University Science and Technology Innovation Team Support Project of Henan Province(13IRTTHN016)the Innovative and Training Project of Post Graduate Funding from the Henan Normal University(201310476046)
文摘To investigate wavelength response of the no core fiber（NCF）interference spectrum to concentration,a three-layer back propagation（BP）neural network model was established to optimize the concentration sensing data.In this method,the measured wavelength and the corresponding concentration were trained by a BP neural network,so that the accuracy of the measurement system was optimized.The wavelength was used as the training set and got into the input layer of the three layer BP network model which is used as the input value of the network,and the corresponding actual concentration value was used as the output value of the network,and the optimal network structure was trained.This paper discovers a preferable correlation between the predicted value and the actual value,where the former is approximately equal to the latter.The correlation coefficients of the measured and predicted values for a sucrose concentration were 1.000 89 and 1.003 94;similarly,correlations of0.999 51 and 1.018 8 for a glucose concentration were observed.The results demonstrate that the BP neural network can improve the prediction accuracy of the nonlinear relationship between the interference spectral data and the concentration in NCF sensing systems.
基金financial support from the National Natural Science Foundation of China(No.52072276)Hubei Important Project on Science and Technology(No.2022BECO20).
文摘Al-Si alloy,a high temperature phase change material,has great potential in thermal management due to its advantages of high heat storage density and thermal conductivity.Microencapsulation of Al-Si alloy is one of the effective techniques to solve high temperature leakage and corrosion.In this paper,commercial Al-10Si alloy micro powders were encapsulated with flexible ceramic shells whose total thickness is below 1μm by hydrothermal treatment and heat treatment in N_(2) atmosphere.The compositions and microstructures were characterized by XRD,SEM and TEM.The shell was composed of AlN fibers network structure embedded withα-Al_(2)O_(3)/AlN which prevented the alloy from leaking and oxidizing,as well as had excellent thermal stability.The latent heat of microcapsules was 351.8 J g^(-1)for absorption and 372.7 J g^(-1)for exothermic.The microcapsules showed near zero thermal performance loss with latent heat storage(LHS)/release(LHR)was 353.2/403.7 J g^(-1)after 3000 cycles.Compared with the published Al-Si alloy microcapsules,both high heat storage density and super thermal cycle stability were achieved,showing promising development prospects in high temperature thermal management.
文摘In this study,artificial neural networks trained with swarm based artificial bee colony optimization algorithm was implemented for prediction of the modulus of rapture values of the fabricated glass fiber reinforced concrete panels.For the application of the ANN models,143 different four-point bending test results of glass fiber reinforced concrete mixes with the varied parameters of temperature,fiber content and slump values were introduced the artificial bee colony optimization and conventional back propagation algorithms.Training and the testing results of the corresponding models showed that artificial neural networks trained with the artificial bee colony optimization algorithm have remarkable potential for the prediction of modulus of rupture values and this method can be used as a preliminary decision criterion for quality check of the fabricated products.
文摘In this study, an artificial neural network (ANN) model for studying the strength properties of steel fiber reinforced concrete (SFRC) containing fly ash was devised. The mixtures were prepared with 0 wt%, 15 wt%, and 30 wt% of fly ash, at 0 vol.%, 0.5 vol.%, 1.0 vol.% and 1.5 vol.% of fiber, respectively. After being cured under the standard conditions for 7, 28, 90 and 365 d, the specimens of each mixture were tested to determine the corresponding compressive and flexural strengths. The pa- rameters such as the amounts of cement, fly ash replacement, sand, gravel, steel fiber, and the age of samples were selected as input variables, while the compressive and flexural strengths of the concrete were chosen as the output variables. The back propagation learning algorithm with three different variants, namely the Levenberg-Marquardt (LM), scaled conjugate gradient (SCG) and Fletcher-Powell conjugate gradient (CGF) algorithms were used in the network so that the best approach can be found. The results obtained from the model and the experiments were compared, and it was found that the suitable algorithm is the LM algorithm. Furthermore, the analysis of variance (ANOVA) method was used to determine how importantly the experimental parameters affect the strength of these mixtures.
基金financially supported by the National Natural Science Foundation of China(No.51872232)the Research Fund of the State Key Laboratory of Solidification Processing(NWPU),China(No.136-QP-2015)+4 种基金the“111”project of China(No.B08040)the National Training Program of Innovation and Entrepreneurship for Undergraduates(No.S202010699336)the Joint Funds of the National Natural Science Foundation of China(No.U21B2067)the Key Scientific and Technological Innovation Research Team of Shaanxi Province(No.2022TD-31)the Key R&D Program of Shaanxi Province(No.2021ZDLGY14-04).
文摘Carbon fiber(C_(f))reinforced pyrolytic carbon(PyC)composites simultaneously possessing robust mechanical strength,excellent friction performances and outstanding anti-ablation properties are demanded for advanced aerospace applications.Efficient architecture design and optimization of composites are promi-nent yet remain high challenging for realizing the above requirements.Herein,binary reinforcements of networked silicon nitride nanowires(Si_(3)N_(4) nws)and interconnected graphene(GE)have been successfully constructed into C f/PyC by precursor impregnation-pyrolysis and chemical vapor deposition.Notably,net-worked Si_(3)N_(4) nws are uniformly distributed among the carbon fibers,while interconnected GE is firmly rooted on the surface of both networked Si_(3)N_(4) nws and carbon fibers.In the networked Si_(3)N_(4) nws and interconnected GE reinforced C_(f)/PyC,networked Si_(3)N_(4) nws significantly boost the cohesion strength of PyC,while GE markedly improves the interface bonding of both Si_(3)N_(4) nws/PyC and fiber/PyC.Benefiting from the synergistic reinforcement effect of networked Si_(3)N_(4) nws and interconnected GE,the C_(f)/PyC have a prominent enhancement in mechanical(shear and compressive strengths increased by 119.9% and 52.84%,respectively)and friction(friction coefficient and wear rate reduced by 25.40% and 60.10%,respectively)as well as anti-ablation(mass ablation rate and linear ablation rate decreased by 71.25% and 63.01%,respectively).This present strategy for networked Si_(3)N_(4) nws and interconnected GE reinforced C_(f)/PyC provides a dominant route to produce mechanically robust,frictionally resisting and ablatively resistant materials for use in advanced aerospace applications.
基金supported in part by the National Basic Research Program of China under Grant No. 2012CB315705 (973 program)National Natural Science Foundation of China under Grants No.61107058, No.61120106001, No.60932004, No.61001121, No.60837004+2 种基金National High-Tech Research and Development Program of China under Grant No.2011AA010306 (863 program)Beijing Excellent Doctoral Thesis Project under Grant No.YB20101001301Cooperation Project between Province and Ministries under Grant No.2011A090200025
文摘This paper investigates the Medium Access Control(MAC)protocol performance in the IEEE 802.11g-over-fiber network for different payloads and fiber lengths using Direct Sequence Spread Spectrum-Orthogonal Frequency Division Multiplexing(DSSSOFDM)and Extended Rate PhysicalsOrthogonal Frequency Division Multiplexing(ERP-OFDM)physical layers using basic access mode,Request to Send/Clear to Send(RTS/CTS)and CTS-to-self mechanisms.The results show that IEEE 802.11g-over-fiber network employing the ERP-OFDM physical layer is much more efficient than that employing the DSSS-OFDM physical layer,with regards to both throughput and delay.For a given maximum throughput/minimum delay,the tradeoff among the access mechanism,the fiber length,and the payload size must be considered.Our quantified results give a selection basis for the operators to quickly select suitable IEEE 802.11g physical layers and the different access mechanisms,and accurately predict the data throughput and delay given the specific parameters.
基金National Natural Science Foundation of China,Grant/Award Number:51971065Innovation Program of Shanghai Municipal Education Commission,Grant/Award Number:2019-01-07-00-07-E00028。
文摘SnO_(2) has been extensively investigated as an anode material for sodium-ion batteries(SIBs)and potassium-ion batteries(PIBs)due to its high Na/K storage capacity,high abundance,and low toxicity.However,the sluggish reaction kinetics,low electronic conductivity,and large volume changes during charge and discharge hinder the practical applications of SnO_(2)-based electrodes for SIBs and PIBs.Engineering rational structures with fast charge/ion transfer and robust stability is important to overcoming these challenges.Herein,S-doped SnO_(2)(S-SnO_(2))quantum dots(QDs)(≈3 nm)encapsulated in an N,S codoped carbon fiber networks(S-SnO_(2)-CFN)are rationally fabricated using a sequential freeze-drying,calcination,and S-doping strategy.Experimental analysis and density functional theory calculations reveal that the integration of S-SnO_(2) QDs with N,S codoped carbon fiber network remarkably decreases the adsorption energies of Na/K atoms in the interlayer of SnO_(2)-CFN,and the S doping can increase the conductivity of SnO_(2),thereby enhancing the ion transfer kinetics.The synergistic interaction between S-SnO_(2) QDs and N,S codoped carbon fiber network results in a composite with fast Na+/K+storage and extraordinary long-term cyclability.Specifically,the S-SnO_(2)-CFN delivers high rate capacities of 141.0 mAh g^(−1) at 20 A g^(−1) in SIBs and 102.8 mAh g^(−1) at 10 A g^(−1) in PIBs.Impressively,it delivers ultra-stable sodium storage up to 10,000 cycles at 5 A g^(−1) and potassium storage up to 5000 cycles at 2 A g^(−1).This study provides insights into constructing metal oxide-based carbon fiber network structures for high-performance electrochemical energy storage and conversion devices.
基金supported by the National Science Foundation of China(Theoretical Model and Experimental Research on the Novel FBG Sensing System based on the Fusion Algorithm,No.61703056)the Jilin Province Science and Technology Development Plan Project(No.20190103154JH)。
文摘Intelligent assembly of large-scale,complex structures using an intelligent manufacturing platform represents the future development direction for industrial manufacturing.During large-scale structural assembly processes,several bottleneck problems occur in the existing auxiliary assembly technology.First,the traditional LiDARbased assembly technology is often limited by the openness of the manufacturing environment,in which there are blind spots,and continuous online assembly adjustment thus cannot be realized.Second,for assembly of large structures,a single-station LiDAR system cannot achieve complete coverage,which means that a multi-station combination method must be used to acquire the complete three-dimensional data;many more data errors are caused by the transfer between stations than by the measurement accuracy of a single station,which means that the overall system's measurement and adjustment errors are increased greatly.Third,because of the large numbers of structural components contained in a large assembly,the accumulated errors may lead to assembly interference,but the LiDAR-assisted assembly process does not have a feedback perception capability,and thus assembly component loss can easily be caused when assembly interference occurs.Therefore,this paper proposes to combine an optical fiber sensor network with digital twin technology,which will allow the test data from the assembly entity state in the real world to be applied to the"twin"model in the virtual world and thus solve the problems with test openness and data transfer.The problem of station and perception feedback is also addressed and represents the main innovation of this work.The system uses an optical fiber sensor network as a flexible sensing medium to monitor the strain field distribution within a complex area in real time,and then completes real-time parameter adjustment of the virtual assembly based on the distributed data.Complex areas include areas that are laser-unreachable,areas with complex contact surfaces,and areas with large-scale bending deformations.An assembly condition monitoring system is designed based on the optical fiber sensor network,and an assembly condition monitoring algorithm based on multiple physical quantities is proposed.The feasibility of use of the optical fiber sensor network as the real-state parameter acquisition module for the digital twin intelligent assembly system is discussed.The offset of any position in the test area is calculated using the convolutional neural network of a residual module to provide the compensation parameters required for the virtual model of the assembly structure.In the model optimization parameter module,a correction data table is obtained through iterative learning of the algorithm to realize state prediction from the test data.The experiment simulates a largescale structure assembly process,and performs virtual and real mapping for a variety of situations with different assembly errors to enable correction of the digital twin data stream for the assembly process through the optical fiber sensor network.In the plane strain field calibration experiment,the maximum error among the test values for this system is 0.032 mm,and the average error is 0.014 mm.The results show that use of visual calibration can correct the test error to within a very small range.This result is equally applicable to gradient curvature surfaces and freeform surfaces.Statistics show that the average measurement accuracy error for regular surfaces is better than 11.2%,and the average measurement accuracy error for irregular surfaces is better than 14.8%.During simulation of large-scale structure assembly experiments,the average position deviation accuracy is 0.043 mm,which is in line with the designed accuracy.
基金supported by National Natural Science Foundation of China(Grant No.61471053,61901052)Fundamental Research Funds for the Central Universities(Grant 2018RC03)Beijing Laboratory of Advanced Information Networks
文摘The computation resources at a single node in Edge Computing(EC)are commonly limited,which cannot execute large scale computation tasks.To face the challenge,an Offloading scheme leveraging on NEighboring node Resources(ONER)for EC over Fiber-Wireless(FiWi)access networks is proposed in this paper.In the ONER scheme,the FiWi network connects edge computing nodes with fiber and converges wireless and fiber connections seamlessly,so that it can support the offloading transmission with low delay and wide bandwidth.Based on the ONER scheme supported by FiWi networks,computation tasks can be offloaded to edge computing nodes in a wider range of area without increasing wireless hops(e.g.,just one wireless hop),which achieves low delay.Additionally,an efficient Computation Resource Scheduling(CRS)algorithm based on the ONER scheme is also proposed to make offloading decision.The results show that more offloading requests can be satisfied and the average completion time of computation tasks decreases significantly with the ONER scheme and the CRS algorithm.Therefore,the ONER scheme and the CRS algorithm can schedule computation resources at neighboring edge computing nodes for offloading to meet the challenge of large scale computation tasks.
基金supported by the National Natural Science Foundation of China(Nos.92048301,62020106004 and 11704283)in part by the Tianjin Municipal Education Commission(No.2018KJ146)in part by the Opening Foundation of Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems(No.2019LODTS004).
文摘A large mode area multi-core orbital angular momentum(OAM)transmission fiber is designed and optimized by neural network and optimization algorithms.The neural network model has been established first to predict the optical properties of multi-core OAM transmission fibers with high accuracy and speed,including mode area,nonlinear coefficient,purity,dispersion,and effective index difference.Then the trained neural network model is combined with different particle swarm optimization(PSO)algorithms for automatic iterative optimization of multi-core structures respectively.Due to the structural advantages of multi-core fiber and the automatic optimization process,we designed a number of multi-core structures with high OAM mode purity(>95%)and ultra-large mode area(>3000µm^(2)),which is larger by more than an order of magnitude compared to the conventional ring-core OAM transmission fibers.
基金The authors acknowledge the support from the Deanship of Scientific Research,Najran University.Kingdom of Saudi Arabia,for funding this work under the research groups funding program grant code number(NU/RG/SERC/11/3).
文摘The fiber nonlinearity and phase noise(PN)are the focused impairments in the optical communication system,induced by high-capacity transmission and high laser input power.The channels include high-capacity transmissions that cannot be achieved at the end side without aliasing because of fiber nonlinearity and PN impairments.Thus,addressing of these distortions is the basic objective for the 5G mobile network.In this paper,the fiber nonlinearity and PN are investigated using the assembled methodology of millimeter-wave and radio over fiber(mmWave-RoF).The analytical model is designed in terms of outage probability for the proposed mmWave-RoF system.The performance of mmWave-RoF against fiber nonlinearity and PN is studied for input power,output power and length using peak to average power ratio(PAPR)and bit error rate(BER)measuring parameters.The simulation outcomes present that the impacts of fiber nonlinearity and PNcan be balanced for a huge capacity mmWave-RoF model applying input power carefully.
文摘An Extrinsic Fabry-Perot Interferometric (EFPI) fiber optical sensor system is an online testing system for the gas density. The system achieves the measurement of gas density information mainly by demodulating the cavity length of EF- PI fiber optical sensor. There are many ways to achieve the demodulation of the cavity length. For shortcomings of the big intensity demodulation error and complex structure of phase demodulation, this paper proposes that BP neural net-work is used to locate the special peak points in normalized interference spectrum and combining the advantages of the unimodal and bimodal measurement achieves the demodulation of the cavity length. Through online simulation and actual measurement, the results show that the peak positioning technology based on BP neural network can not only achieve high-precision demodulation of the cavity length, but also achieve an absolute measurement of cavity length in large dynamic range.
基金supported by the National Natural Science Foundation of China(Grant No.52271277)the Natural Science Foundation of Jiangsu Province(Grant.No.BK20211343)+1 种基金the State Key Laboratory of Ocean Engineering(Shanghai Jiao Tong University)(Grant.No.GKZD010081)Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant.No.SJCX22_1906).
文摘The buckling load of carbon fiber composite cylindrical shells(CF-CCSs)was predicted using a backpropagation neural network improved by the sparrow search algorithm(SSA-BPNN).Firstly,two CF-CCSs,each with an inner diameter of 100 mm,were manufactured and tested.The buckling behavior of CF-CCSs was analyzed by finite element and experiment.Subsequently,the effects of ply angle and length–diameter ratio on buckling load of CF-CCSs were analyzed,and the dataset of the neural network was generated using the finite element method.On this basis,the SSA-BPNN model for predicting buckling load of CF-CCS was established.The results show that the maximum and average errors of the SSA-BPNN to the test data are 6.88%and 2.24%,respectively.The buckling load prediction for CF-CCSs based on SSA-BPNN has satisfactory generalizability and can be used to analyze buckling loads on cylindrical shells of carbon fiber composites.
文摘Fiber loop ringdown (FLRD) has demonstrated to be capable of sensing various quantities, such as chemical species, pressure, refractive index, strain, temperature, etc.;and it has high potential for the development of a sensor network. In the present work, we describe design and development of three different types of FLRD sensors for water, cracks, and temperature sensing in concrete structures. All of the three aforementioned sensors were indigenously developed very recently in our laboratory and their capabilities of detecting the respective quantities were demonstrated. Later, all of the sensors were installed in a test grout cube for real-time monitoring. This work presents the results obtained in the laboratory-based experiments as well as the results from the real-time monitoring process in the test cube.
基金Supported by Key Laboratory of Space Active Optical-Electro Technology of Chinese Academy of Sciences(2021ZDKF4)。
文摘Phase-sensitive Optical Time-Domain Reflectometer(φ-OTDR)technology facilitates the real-time detection of vibration events along fiber optic cables by analyzing changes in Rayleigh scattering signals.This technology is widely used in applications such as intrusion monitoring and structural health assessments.Traditional signal processing methods,such as Support Vector Machines(SVM)and K-Nearest Neighbors(KNN),have limitations in feature extraction and classification in complex environments.Conversely,a single deep learning model often struggles with capturing long time-series dependencies and mitigating noise interference.In this study,we propose a deep learning model that integrates Convolutional Neural Network(CNN),Long Short-Term Memory Network(LSTM),and Transformer modules,leveraging φ-OTDR technology for distributed fiber vibration sensing event recognition.The hybrid model combines the CNN's capability to extract local features,the LSTM's ability to model temporal dynamics,and the Transformer's proficiency in capturing global dependencies.This integration significantly enhances the accuracy and robustness of event recognition.In experiments involving six types of vibration events,the model consistently achieved a validation accuracy of 0.92,and maintained a validation loss of approximately 0.2,surpassing other models,such as TAM+BiLSTM and CNN+CBAM.The results indicate that the CNN+LSTM+Transformer model is highly effective in handling vibration signal classification tasks in complex scenarios,offering a promising new direction for the application of fiber optic vibration sensing technology.
