The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelli...The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelligent fault diagnosis.On the other hand,the vectorization of multi-source sensor signals may not only generate high-dimensional vectors,leading to increasing computational complexity and overfitting problems,but also lose the structural information and the coupling information.This paper proposes a new method for class-imbalanced fault diagnosis of bearing using support tensor machine(STM)driven by heterogeneous data fusion.The collected sound and vibration signals of bearings are successively decomposed into multiple frequency band components to extract various time-domain and frequency-domain statistical parameters.A third-order hetero-geneous feature tensor is designed based on multisensors,frequency band components,and statistical parameters.STM-based intelligent model is constructed to preserve the structural information of the third-order heterogeneous feature tensor for bearing fault diagnosis.A series of comparative experiments verify the advantages of the proposed method.展开更多
Multi-material laser powder bed fusion(LPBF)additive manufacturing is a promising approach for integrating the functionality and mechanical performance of dissimilar materials into complex parts.This review offers a c...Multi-material laser powder bed fusion(LPBF)additive manufacturing is a promising approach for integrating the functionality and mechanical performance of dissimilar materials into complex parts.This review offers a comprehensive overview of the recent advancements in multi-material LPBF,with a particular focus on compositionally heterogeneous/gradient parts and their fabrication methods and equipment,control of interfacial defects,innovative designs,and potential applications.It commences with the introduction of LPBF-processed compositionally heterogeneous/gradient structures with dissimilar material distributions,including Z-direction compositionally heterogeneous structures,compositionally gradient structures in the Z-direction and XY planes,and three-dimensional(3D)compositionally heterogeneous structures.Subsequently,various LPBF methods and equipment for fabricating compositionally heterogeneous/gradient structures have been presented.Furthermore,the interfacial defects and process control during LPBF for these types of compositionally heterogeneous/gradient structures are discussed.Additionally,innovative designs and potential applications of parts made from compositionally heterogeneous/gradient structures are illustrated.Finally,perspectives on the LPBF fabrication methods for compositionally heterogeneous/gradient structures are highlighted to provide guidance for future research.展开更多
With the acceleration of intelligent transformation of energy system,the monitoring of equipment operation status and optimization of production process in thermal power plants face the challenge of multi-source heter...With the acceleration of intelligent transformation of energy system,the monitoring of equipment operation status and optimization of production process in thermal power plants face the challenge of multi-source heterogeneous data integration.In view of the heterogeneous characteristics of physical sensor data,including temperature,vibration and pressure that generated by boilers,steam turbines and other key equipment and real-time working condition data of SCADA system,this paper proposes a multi-source heterogeneous data fusion and analysis platform for thermal power plants based on edge computing and deep learning.By constructing a multi-level fusion architecture,the platform adopts dynamic weight allocation strategy and 5D digital twin model to realize the collaborative analysis of physical sensor data,simulation calculation results and expert knowledge.The data fusion module combines Kalman filter,wavelet transform and Bayesian estimation method to solve the problem of data time series alignment and dimension difference.Simulation results show that the data fusion accuracy can be improved to more than 98%,and the calculation delay can be controlled within 500 ms.The data analysis module integrates Dymola simulation model and AERMOD pollutant diffusion model,supports the cascade analysis of boiler combustion efficiency prediction and flue gas emission monitoring,system response time is less than 2 seconds,and data consistency verification accuracy reaches 99.5%.展开更多
Although 316L stainless steel(SS316L)exhibits favorable ductility and toughness,its limited strength restricts its applicability.This study addressed this limitation by preparing a series of SS316L-xTC4 alloys(where x...Although 316L stainless steel(SS316L)exhibits favorable ductility and toughness,its limited strength restricts its applicability.This study addressed this limitation by preparing a series of SS316L-xTC4 alloys(where x indicates Ti6Al4V(TC4)contents of 0.5 wt%,1 wt%,2 wt%,and 4 wt%)with equiaxed grains,ultrafine grains,and heterogeneous structures using in-situ alloying via laser powder bed fusion.The Ti,Al,and V in the TC4 alloy were shown to stabilize and promote the formation of theαphase,which is stronger than theγphase in typical SS316L.Furthermore,these solute elements readily formed nanoparticles with impurities,such as C and O,to increase the nucleation rate and thereby achieve grain refinement.This resulted in the formation of ultrafine grains predominantly within theαphase,where the solute elements were primarily distributed.The formation of theαphase also impeded the growth of theγphase;coupled with the effects of the nanoparticles,this also significantly reduced the grain size in theγphase.Notably,the SS316L-2TC4 alloy exhibited fully equiaxed grains,and the coexistence of theαandγphases as well as ultrafine and coarse grains formed heterogeneous grain and dual-phase structures within.The synergistic effects of equiaxed grains,ultrafine grains,and heterostructures produced an SS316L alloy that exhibited both excellent strength and elongation.展开更多
As a universal casting Mg-RE alloy,Mg-6Gd-3Y-Zr(GW63K,wt.%)alloy exhibits superior strength-ductility synergy and holds significant potential for engineering applications.In this study,the GW63K alloy is produced usin...As a universal casting Mg-RE alloy,Mg-6Gd-3Y-Zr(GW63K,wt.%)alloy exhibits superior strength-ductility synergy and holds significant potential for engineering applications.In this study,the GW63K alloy is produced using the laser powder bed fusion(LPBF)additive manufacturing(AM)process for the first time.The printability,microstructure characteristics,and post-heat treatment conditions of the GW63K alloy are systematically investigated.The as-built GW63K samples demonstrate high relative densities exceeding 99.6%and exhibit no macroscopic and microscopic cracking across a wide range of process parameters,indicating excellent printability.An exceptional heterogeneous microstructure is observed in the as-built GW63K alloy,comprising coarse columnar grains,fine equiaxed grains with an average grain size of 21.72μm,uniformly distributed nano-sized Mg_(24)(Gd,Y)_(5)secondary phase,and numerous dislocations.Consequently,the as-built GW63K alloy displays enhanced tensile strengths and ductility compared to the as-cast alloy,with yield strength(YS),ultimate tensile strength(UTS)and elongation(EL)values of 218±4 MPa,284±5 MPa and 11.9±1.6%respectively.Additionally,due to the absence of coarse micron-sized secondary phase,a specific direct aging(T5)heat treatment regime at 200℃for 128 h is optimized for the as-built GW63K alloy to introduce dense and dispersedβ’aging precipitates.This T5 treatment surpasses the conventional solution plus aging(T6)heat treatment in enhancing mechanical properties.The LPBF-T5 GW63K alloy exhibits YS,UTS and EL values of 293±6 MPa,359±4 MPa and 2.9±0.7%,respectively.Notably,the YS of the LPBF-T5 alloy represents the highest value for the GW63K alloy,even surpassing that of the extrusion-T5 alloy.This study indicates that the GW63K alloy is a highly promising material for manufacturing near-net-shape high-strength Mg alloy components with intricate geometries using LPBF.展开更多
Additively manufactured bimetallic structures combine the advantages of dissimilar materials and can achieve localized properties through a customized composition distribution.However,additively manufactured parts may...Additively manufactured bimetallic structures combine the advantages of dissimilar materials and can achieve localized properties through a customized composition distribution.However,additively manufactured parts may still lack the dimensional accuracy and surface integrity essential for precision mechanical assemblies that the post-machining process can address.Therefore,this study aims to systematically investigate the microstructure and machinability of 316L/CuSn10 bimetallic structures fabricated using laser powder bed fusion.The results show that the fusion zone of the bimetallic structure had refined grains of microscale size owing to the mixture of the primary elements of the bimetals,which resulted in the highest microhardness of 3.4 GPa.The difference in microstructure and microhardness between the single-material and fusion zones also causes significant differences in the cutting response during the ultraprecision process.The 316L stainless steel side exhibited the highest cutting force and more severe material accumulation in the chips.The cutting force drops when cutting through the fusion zone,with an observable fracture in the chips and separation of dissimilar materials on the machined grooves,indicating that the heterogeneous properties of additively manufactured 316L/CuSn10 bimetallic structures pose challenges to the improvement of surface quality.The simulation results also showed that stress accumulation occurred in the tool path through the fusion zone owing to the higher yield strength and hardness of stainless steel,indicating that lower cutting speeds and depths of cut are favorable for reducing cutting force and improving surface quality.This study provides deep insight into the microstructure evolution mechanism and a theoretical basis for improving the surface quality of additively manufactured bimetallic structures using an ultraprecision machining process.展开更多
Maritime radar and automatic identification systems (AIS), which are essential auxiliary equipment for navigation safety in the shipping industry, have played significant roles in maritime safety supervision. However,...Maritime radar and automatic identification systems (AIS), which are essential auxiliary equipment for navigation safety in the shipping industry, have played significant roles in maritime safety supervision. However, in practical applications, the information obtained by a single device is limited, and it is necessary to integrate the information of maritime radar and AIS messages to achieve better recognition effects. In this study, the D-S evidence theory is used to fusion the two kinds of heterogeneous information: maritime radar images and AIS messages. Firstly, the radar image and AIS message are processed to get the targets of interest in the same coordinate system. Then, the coordinate position and heading of targets are chosen as the indicators for judging target similarity. Finally, a piece of D-S evidence theory based on the information fusion method is proposed to match the radar target and the AIS target of the same ship. Particularly, the effectiveness of the proposed method has been validated and evaluated through several experiments, which proves that such a method is practical in maritime safety supervision.展开更多
Zinc(Zn)is considered a promising biodegradable metal for implant applications due to its appropriate degradability and favorable osteogenesis properties.In this work,laser powder bed fusion(LPBF)additive manufacturin...Zinc(Zn)is considered a promising biodegradable metal for implant applications due to its appropriate degradability and favorable osteogenesis properties.In this work,laser powder bed fusion(LPBF)additive manufacturing was employed to fabricate pure Zn with a heterogeneous microstructure and exceptional strength-ductility synergy.An optimized processing window of LPBF was established for printing Zn samples with relative densities greater than 99%using a laser power range of 80∼90 W and a scanning speed of 900 mm s−1.The Zn sample printed with a power of 80 W at a speed of 900 mm s−1 exhibited a hierarchical heterogeneous microstructure consisting of millimeter-scale molten pool boundaries,micrometer-scale bimodal grains,and nanometer-scale pre-existing dislocations,due to rapid cooling rates and significant thermal gradients formed in the molten pools.The printed sample exhibited the highest ductility of∼12.1%among all reported LPBF-printed pure Zn to date with appreciable ultimate tensile strength(∼128.7 MPa).Such superior strength-ductility synergy can be attributed to the presence of multiple deformation mechanisms that are primarily governed by heterogeneous deformation-induced hardening resulting from the alternative arrangement of bimodal Zn grains with pre-existing dislocations.Additionally,continuous strain hardening was facilitated through the interactions between deformation twins,grains and dislocations as strain accumulated,further contributing to the superior strength-ductility synergy.These findings provide valuable insights into the deformation behavior and mechanisms underlying exceptional mechanical properties of LPBF-printed Zn and its alloys for implant applications.展开更多
Urbanization changes have been widely examined and numerous urban growth models have been proposed. We introduce an alternative urban growth model specifically designed to incorporate spatial heterogeneity in urban gr...Urbanization changes have been widely examined and numerous urban growth models have been proposed. We introduce an alternative urban growth model specifically designed to incorporate spatial heterogeneity in urban growth models. Instead of applying a single method to the entire study area, we segment the study area into different regions and apply targeted algorithms in each subregion. The working hypothesis is that the integration of appropriately selected region-specific models will outperform a globally applied model as it will incorporate further spatial heterogeneity. We examine urban land use changes in Denver, Colorado. Two land use maps from different time snapshots (1977 and 1997) are used to detect the urban land use changes, and 23 explanatory factors are produced to model urbanization. The proposed Spatially Heterogeneous Expert Based (SHEB) model tested decision trees as the underlying modeling algorithm, applying them in different subregions. In this paper the segmentation tested is the division of the entire area into interior and exterior urban areas. Interior urban areas are those situated within dense urbanized structures, while exterior urban areas are outside of these structures. Obtained results on this model regionalization technique indicate that targeted local models produce improved results in terms of Kappa, accuracy percentage and multi-scale performance. The model superiority is also confirmed by model pairwise comparisons using t-tests. The segmentation criterion of interior/exterior selection may not only capture specific characteristics on spatial and morphological properties, but also socioeconomic factors which may implicitly be present in these spatial representations. The usage of interior and exterior subregions in the present study acts as a proof of concept. Other spatial heterogeneity indicators, for example landscape, socioeconomic and political boundaries could act as the basis for improved local segmentations.展开更多
Laser powder bed fusion(L-PBF)of Sc/Zr-modified Al-based alloys has recently become a promising method for developing a new generation of high-performance Al alloys.To clarify the modification roles of Sc/Zr elements,...Laser powder bed fusion(L-PBF)of Sc/Zr-modified Al-based alloys has recently become a promising method for developing a new generation of high-performance Al alloys.To clarify the modification roles of Sc/Zr elements,an Al–4.66Mg–0.48Mn–0.72Sc–0.33Zr(wt.%)alloy was processed using L-PBF.The effect of the local solidification condition of the molten pool on the precipitation behavior of primary Al_(3)(Sc,Zr)was analyzed based on time-dependent nucleation theory.It was found that primary Al_(3)(Sc,Zr)inevitably precipitated at the fusion boundary,while its precipitation could be effectively suppressed in the inner region of the molten pool.This subsequently induced the formation of a heterogeneousα-Al matrix.After direct aging,the heredity of solidification microstructure introduced heterogeneous secondary Al_(3)(Sc,Zr)precipitates withinα-Al matrix.Owing to the inverse relationship between grain boundary strengthening and precipitation strengthening,the direct-aged sample with dual heterogeneous structures exhibited reduced mechanical heterogeneity,resulting in lowered hetero-deformation-induced hardening.The low strain-hardening capability in the direct-aged sample promoted necking instability while inducing a large Lüders elongation,which effectively improved the tensile ductility.展开更多
The problem of distributed fusion and random observation loss for mobile sensor networks is investigated herein.In view of the fact that the measured values,sampling frequency and noise of various sensors are differen...The problem of distributed fusion and random observation loss for mobile sensor networks is investigated herein.In view of the fact that the measured values,sampling frequency and noise of various sensors are different,the observation model of a heterogeneous network is constructed.A binary random variable is introduced to describe the drop of observation component and the topology switching problem caused by complete observation loss is also considered.A cubature information filtering algorithm is adopted to design local filters for each observer to suppress the negative effects of measurement noise.To derive a consistent and accurate estimation result,a novel weighted average consensus-based filtering approach is put forward.For the sensor that suffers from observation loss,its local prediction information vector is fused with the information contribution vectors of the neighbors to obtain the local estimation.Then the consensus weight matrix is designed for consensus-based distributed collaborative information fusion.The boundness of the estimation errors is proved by employing the stochastic stability theory.In the end,two numerical examples are offered to assert the validity of the presented method.展开更多
With the high-tech industrialization of earth observation satellite remote sensing and the implementation of digital earth strategy,the energy and natural resources have been decided to be the key research fields in C...With the high-tech industrialization of earth observation satellite remote sensing and the implementation of digital earth strategy,the energy and natural resources have been decided to be the key research fields in China.In these fields,from the model based on topology data,through simple feature data model to rule-based data model,the basic spatial analysis algorithms have been developed展开更多
The rapid urbanization and structural imbalances in Chinese megacities have exacerbated the housing supplydemand mismatch,creating an urgent need for fine-scale diagnostic tools.This study addresses this critical gap ...The rapid urbanization and structural imbalances in Chinese megacities have exacerbated the housing supplydemand mismatch,creating an urgent need for fine-scale diagnostic tools.This study addresses this critical gap by developing the Housing Contradiction Evaluation Weighted Index(HCEWI)model,making three key contributions to high-resolution housing monitoring.First,we establish a tripartite theoretical framework integrating dynamic population pressure(PPI),housing supply potential(HSI),and functional diversity(HHI).The PPI innovatively combines mobile signaling data with principal component analysis to capture real-time commuting patterns,while the HSI introduces a novel dual-criteria system based on Local Climate Zones(LCZ),weighted by building density and residential function ratio.Second,we develop a spatiotemporal coupling architecture featuring an entropy-weighted dynamic integration mechanism with self-correcting modules,demonstrating robust performance against data noise.Third,our 25-month longitudinal analysis in Shenzhen reveals significant findings,including persistent bipolar clustering patterns,contrasting volatility between peripheral and core areas,and seasonal policy responsiveness.Methodologically,we advance urban diagnostics through 500-meter grid monthly monitoring and process-oriented temporal operators that reveal“tentacle-like”spatial restructuring along transit corridors.Our findings provide a replicable framework for precision housing governance and demonstrate the transformative potential of mobile signaling data in implementing China’s“city-specific policy”approach.We further propose targeted intervention strategies,including balance regulation for high-contradiction zones,Transit-Oriented Development(TOD)activation for low-contradiction clusters,and dynamic land conversion mechanisms for transitional areas.展开更多
Additive manufacturing of aluminum alloys has received significant attention in the aerospace industry;however,achieving sufficient high strength,especially at elevated temperatures,remains challenging.Here,a crack-fr...Additive manufacturing of aluminum alloys has received significant attention in the aerospace industry;however,achieving sufficient high strength,especially at elevated temperatures,remains challenging.Here,a crack-free and near-full dense Al-1Fe-0.6Cu-1.3Zr alloy was fabricated by the laser powder bed fusion(LPBF)technique.The Al-Fe-Cu-Zr alloy exhibits heterogeneous microstructures with two distinct zones.One is the so-called coarse-grain zones(CGZs)with an average grain size of 0.95μm,where(Al,Cu)Fe_(3) nanoparticles precipitate in the Al matrix and Fe and Cu cosegregate at the grain boundaries(GBs).The other is fine-grain zones(FGZs)with an average grain size of 0.45μm,where an Al 3 Zr nanoparti-cle precipitates in each of theα-Al grains(serves as the nuclei),and Fe-rich nanoprecipitates and Fe/Cu cosegregation appear at the GBs.As a result,the LPBF Al-Fe-Cu-Zr alloy,with these unique heteroge-neous structures,displays high strength at both room temperature and elevated temperatures,e.g.,with high yield strengths of 500 MPa at room temperature,and 163 MPa at 573 K,both are higher than those of additive manufactured Al-based alloys reported thus far.It is suggested that the high strength over a wide temperature range of the current LPBF Al alloy is mainly attributed to the combination of the precipitation strengthening mechanism and grain-boundary strengthening mechanism.展开更多
In this work,a high-strength crack-free TiN/Al-Mn-Mg-Sc-Zr composite was fabricated by laser powder bed fusion(L-PBF).A large amount of uniformly distributed L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles were formed during the...In this work,a high-strength crack-free TiN/Al-Mn-Mg-Sc-Zr composite was fabricated by laser powder bed fusion(L-PBF).A large amount of uniformly distributed L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles were formed during the L-PBF process due to the partial melting and decomposition of TiN nanoparticles under a high temperature.These L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles exhibited a highly coherent lattice relationship with the Al matrix.All the prepared TiN/Al-Mn-Mg-Sc-Zr composite samples exhibit ultrafine grain mi-crostructure.In addition,the as-built composite containing 1.5 wt%TiN shows an excellent tensile prop-erty with a yield strength of over 580 MPa and an elongation of over 8%,which were much higher than those of wrought 7xxx alloys.The effects of various strengthening mechanisms were quantitatively estimated and the high strength of the alloy was mainly attributed to the refined microstructure,solid solution strengthening,and precipitation strengthening contributed by L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles.展开更多
Isotropy in microstructure and mechanical properties remains a challenge for laser powder bed fusion(LPBF)processed materials due to the epitaxial growth and rapid cooling in LPBF.In this study,a high-strength TiB_(2)...Isotropy in microstructure and mechanical properties remains a challenge for laser powder bed fusion(LPBF)processed materials due to the epitaxial growth and rapid cooling in LPBF.In this study,a high-strength TiB_(2)/Al-Cu composite with random texture was successfully fabricated by laser powder bed fusion(LPBF)using pre-doped TiB_(2)/Al-Cu composite powder.A series of advanced characterisation techniques,including synchrotron X-ray tomography,correlative focussed ion beam-scanning electron microscopy(FIB-SEM),scanning transmission electron microscopy(STEM),and synchrotron in situ X-ray diffraction,were applied to investigate the defects and microstructure of the as-fabricated TiB_(2)/Al-Cu composite across multiple length scales.The study showed ultra-fine grains with an average grain size of about 0.86μm,and a random texture was formed in the as-fabricated condition due to rapid solidification and the TiB_(2)particles promoting heterogeneous nucleation.The yield strength and total elongation of the as-fabricated composite were 317 MPa and 10%,respectively.The contributions of fine grains,solid solutions,dislocations,particles,and Guinier-Preston(GP)zones were calculated.Failure was found to be initiated from the largest lack-of-fusion pore,as revealed by in situ synchrotron tomography during tensile loading.In situ synchrotron diffraction was used to characterise the lattice strain evolution during tensile loading,providing important data for the development of crystal-plasticity models.展开更多
Post-heat treatment is generally adopted in the additive manufacturing field due to its alleviation of high residual stress and modification of rapid-solidified multilevel heterogeneous microstructure,and the related ...Post-heat treatment is generally adopted in the additive manufacturing field due to its alleviation of high residual stress and modification of rapid-solidified multilevel heterogeneous microstructure,and the related performance of the heat-treated counterparts calls for a systemic investigation to build a criterion of the heat treatment procedure.In this work,we focus on the heat treatment effects on the recrystallization of the Hastelloy X alloy produced by the laser powder bed fusion(LPBF)method,and the related surface passivation of the heat-treated counterparts is meticulously assessed as well.Results show that the multilevel heterostructure for LPBF Hastelloy X alloy consists of sub-micro dislocation cell substructures with Cr/Mo elemental segregation,fine columnar grains,and periodically-distributed molten pools.After heat treatment,partially and fully recrystallized structures for LPBF Hastelloy X alloys were achieved at 1100 and 1200℃for 1 h,respectively.Furthermore,the as-built LPBF Hastelloy X alloy shows superior corrosion resistance while the heat-treated one(1100℃)exhibits the worst in the borate buffer solution.The growth of passive film exhibited a highly linear correlation with the nucleation process controlled by diffusion,and high dislocation density and low angle grain boundary decreased the diffusion coefficient of cation vacancies,augmenting the nucleation sites of the passive film and enhancing its growth rate.Moreover,the micro-galvanic effect resulting from the partially recrystallized microstructure actively facilitated the formation of inhomogeneous porous passive films,leading to the worst corrosion resistance.展开更多
In the realm of data privacy protection,federated learning aims to collaboratively train a global model.However,heterogeneous data between clients presents challenges,often resulting in slow convergence and inadequate...In the realm of data privacy protection,federated learning aims to collaboratively train a global model.However,heterogeneous data between clients presents challenges,often resulting in slow convergence and inadequate accuracy of the global model.Utilizing shared feature representations alongside customized classifiers for individual clients emerges as a promising personalized solution.Nonetheless,previous research has frequently neglected the integration of global knowledge into local representation learning and the synergy between global and local classifiers,thereby limiting model performance.To tackle these issues,this study proposes a hierarchical optimization method for federated learning with feature alignment and the fusion of classification decisions(FedFCD).FedFCD regularizes the relationship between global and local feature representations to achieve alignment and incorporates decision information from the global classifier,facilitating the late fusion of decision outputs from both global and local classifiers.Additionally,FedFCD employs a hierarchical optimization strategy to flexibly optimize model parameters.Through experiments on the Fashion-MNIST,CIFAR-10 and CIFAR-100 datasets,we demonstrate the effectiveness and superiority of FedFCD.For instance,on the CIFAR-100 dataset,FedFCD exhibited a significant improvement in average test accuracy by 6.83%compared to four outstanding personalized federated learning approaches.Furthermore,extended experiments confirm the robustness of FedFCD across various hyperparameter values.展开更多
基金supported by the National Natural Science Foundation of China(No.52275104)the Science and Technology Innovation Program of Hunan Province(No.2023RC3097).
文摘The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelligent fault diagnosis.On the other hand,the vectorization of multi-source sensor signals may not only generate high-dimensional vectors,leading to increasing computational complexity and overfitting problems,but also lose the structural information and the coupling information.This paper proposes a new method for class-imbalanced fault diagnosis of bearing using support tensor machine(STM)driven by heterogeneous data fusion.The collected sound and vibration signals of bearings are successively decomposed into multiple frequency band components to extract various time-domain and frequency-domain statistical parameters.A third-order hetero-geneous feature tensor is designed based on multisensors,frequency band components,and statistical parameters.STM-based intelligent model is constructed to preserve the structural information of the third-order heterogeneous feature tensor for bearing fault diagnosis.A series of comparative experiments verify the advantages of the proposed method.
基金supported by the following projects:the National Key Research and Development Program of China(Nos.2022YFB4600303,and 2024YFB4608200)Guangdong Basic and Applied Basic Research Foundation(Nos.2022B1515020064,and 2022B1515120025)+2 种基金National Natural Science Foundation of China(Nos.52073105,and 52305358)the Fundamental Research Funds for the Central Universities(2024ZYGXZR079)Young Elite Scientists Sponsorship Program by CAST(2023QNRC001)。
文摘Multi-material laser powder bed fusion(LPBF)additive manufacturing is a promising approach for integrating the functionality and mechanical performance of dissimilar materials into complex parts.This review offers a comprehensive overview of the recent advancements in multi-material LPBF,with a particular focus on compositionally heterogeneous/gradient parts and their fabrication methods and equipment,control of interfacial defects,innovative designs,and potential applications.It commences with the introduction of LPBF-processed compositionally heterogeneous/gradient structures with dissimilar material distributions,including Z-direction compositionally heterogeneous structures,compositionally gradient structures in the Z-direction and XY planes,and three-dimensional(3D)compositionally heterogeneous structures.Subsequently,various LPBF methods and equipment for fabricating compositionally heterogeneous/gradient structures have been presented.Furthermore,the interfacial defects and process control during LPBF for these types of compositionally heterogeneous/gradient structures are discussed.Additionally,innovative designs and potential applications of parts made from compositionally heterogeneous/gradient structures are illustrated.Finally,perspectives on the LPBF fabrication methods for compositionally heterogeneous/gradient structures are highlighted to provide guidance for future research.
文摘With the acceleration of intelligent transformation of energy system,the monitoring of equipment operation status and optimization of production process in thermal power plants face the challenge of multi-source heterogeneous data integration.In view of the heterogeneous characteristics of physical sensor data,including temperature,vibration and pressure that generated by boilers,steam turbines and other key equipment and real-time working condition data of SCADA system,this paper proposes a multi-source heterogeneous data fusion and analysis platform for thermal power plants based on edge computing and deep learning.By constructing a multi-level fusion architecture,the platform adopts dynamic weight allocation strategy and 5D digital twin model to realize the collaborative analysis of physical sensor data,simulation calculation results and expert knowledge.The data fusion module combines Kalman filter,wavelet transform and Bayesian estimation method to solve the problem of data time series alignment and dimension difference.Simulation results show that the data fusion accuracy can be improved to more than 98%,and the calculation delay can be controlled within 500 ms.The data analysis module integrates Dymola simulation model and AERMOD pollutant diffusion model,supports the cascade analysis of boiler combustion efficiency prediction and flue gas emission monitoring,system response time is less than 2 seconds,and data consistency verification accuracy reaches 99.5%.
基金supported by National Key Research and Development Program of China(Grant No.2022YFB4602301)the National Natural Science Foundation of China(Grant Nos.52405371,52275381,52174346)+1 种基金the Training Program of Innovation and Entrepreneurship for Undergraduates(Grant No.CXCY2024027)We thank Qian Wang(Northwestern Polytechnical University),Yida Feng(Liaocheng University),Jingdong Ma(Liaocheng University),and Keri Xiaoqiangshiyao(Liaocheng University)for their support of this research.
文摘Although 316L stainless steel(SS316L)exhibits favorable ductility and toughness,its limited strength restricts its applicability.This study addressed this limitation by preparing a series of SS316L-xTC4 alloys(where x indicates Ti6Al4V(TC4)contents of 0.5 wt%,1 wt%,2 wt%,and 4 wt%)with equiaxed grains,ultrafine grains,and heterogeneous structures using in-situ alloying via laser powder bed fusion.The Ti,Al,and V in the TC4 alloy were shown to stabilize and promote the formation of theαphase,which is stronger than theγphase in typical SS316L.Furthermore,these solute elements readily formed nanoparticles with impurities,such as C and O,to increase the nucleation rate and thereby achieve grain refinement.This resulted in the formation of ultrafine grains predominantly within theαphase,where the solute elements were primarily distributed.The formation of theαphase also impeded the growth of theγphase;coupled with the effects of the nanoparticles,this also significantly reduced the grain size in theγphase.Notably,the SS316L-2TC4 alloy exhibited fully equiaxed grains,and the coexistence of theαandγphases as well as ultrafine and coarse grains formed heterogeneous grain and dual-phase structures within.The synergistic effects of equiaxed grains,ultrafine grains,and heterostructures produced an SS316L alloy that exhibited both excellent strength and elongation.
基金supported by the National Key Research and Development Program of China (No.2021YFB3701000)the National Natural Science Foundation of China (Nos. U21A2047, 52201129, 51821001,U2037601)+1 种基金the support by the China Postdoctoral Science Foundation (No. 2023M742219)the Postdoctoral Fellowship Program (Grade B) of CPSF(No. GZB20240419)
文摘As a universal casting Mg-RE alloy,Mg-6Gd-3Y-Zr(GW63K,wt.%)alloy exhibits superior strength-ductility synergy and holds significant potential for engineering applications.In this study,the GW63K alloy is produced using the laser powder bed fusion(LPBF)additive manufacturing(AM)process for the first time.The printability,microstructure characteristics,and post-heat treatment conditions of the GW63K alloy are systematically investigated.The as-built GW63K samples demonstrate high relative densities exceeding 99.6%and exhibit no macroscopic and microscopic cracking across a wide range of process parameters,indicating excellent printability.An exceptional heterogeneous microstructure is observed in the as-built GW63K alloy,comprising coarse columnar grains,fine equiaxed grains with an average grain size of 21.72μm,uniformly distributed nano-sized Mg_(24)(Gd,Y)_(5)secondary phase,and numerous dislocations.Consequently,the as-built GW63K alloy displays enhanced tensile strengths and ductility compared to the as-cast alloy,with yield strength(YS),ultimate tensile strength(UTS)and elongation(EL)values of 218±4 MPa,284±5 MPa and 11.9±1.6%respectively.Additionally,due to the absence of coarse micron-sized secondary phase,a specific direct aging(T5)heat treatment regime at 200℃for 128 h is optimized for the as-built GW63K alloy to introduce dense and dispersedβ’aging precipitates.This T5 treatment surpasses the conventional solution plus aging(T6)heat treatment in enhancing mechanical properties.The LPBF-T5 GW63K alloy exhibits YS,UTS and EL values of 293±6 MPa,359±4 MPa and 2.9±0.7%,respectively.Notably,the YS of the LPBF-T5 alloy represents the highest value for the GW63K alloy,even surpassing that of the extrusion-T5 alloy.This study indicates that the GW63K alloy is a highly promising material for manufacturing near-net-shape high-strength Mg alloy components with intricate geometries using LPBF.
基金supported by Guangdong Basic and Applied Basic Research Foundation(Grant.Nos.2023A1515110594,2024A1515012049)GDA Project of Science and Technology De-velopment(Grant.Nos.2022GDASZH-2022010107,2022GDASZH-2022010108)the China Postdoctoral Science Foundation(Grant.No.2022M711807)。
文摘Additively manufactured bimetallic structures combine the advantages of dissimilar materials and can achieve localized properties through a customized composition distribution.However,additively manufactured parts may still lack the dimensional accuracy and surface integrity essential for precision mechanical assemblies that the post-machining process can address.Therefore,this study aims to systematically investigate the microstructure and machinability of 316L/CuSn10 bimetallic structures fabricated using laser powder bed fusion.The results show that the fusion zone of the bimetallic structure had refined grains of microscale size owing to the mixture of the primary elements of the bimetals,which resulted in the highest microhardness of 3.4 GPa.The difference in microstructure and microhardness between the single-material and fusion zones also causes significant differences in the cutting response during the ultraprecision process.The 316L stainless steel side exhibited the highest cutting force and more severe material accumulation in the chips.The cutting force drops when cutting through the fusion zone,with an observable fracture in the chips and separation of dissimilar materials on the machined grooves,indicating that the heterogeneous properties of additively manufactured 316L/CuSn10 bimetallic structures pose challenges to the improvement of surface quality.The simulation results also showed that stress accumulation occurred in the tool path through the fusion zone owing to the higher yield strength and hardness of stainless steel,indicating that lower cutting speeds and depths of cut are favorable for reducing cutting force and improving surface quality.This study provides deep insight into the microstructure evolution mechanism and a theoretical basis for improving the surface quality of additively manufactured bimetallic structures using an ultraprecision machining process.
文摘Maritime radar and automatic identification systems (AIS), which are essential auxiliary equipment for navigation safety in the shipping industry, have played significant roles in maritime safety supervision. However, in practical applications, the information obtained by a single device is limited, and it is necessary to integrate the information of maritime radar and AIS messages to achieve better recognition effects. In this study, the D-S evidence theory is used to fusion the two kinds of heterogeneous information: maritime radar images and AIS messages. Firstly, the radar image and AIS message are processed to get the targets of interest in the same coordinate system. Then, the coordinate position and heading of targets are chosen as the indicators for judging target similarity. Finally, a piece of D-S evidence theory based on the information fusion method is proposed to match the radar target and the AIS target of the same ship. Particularly, the effectiveness of the proposed method has been validated and evaluated through several experiments, which proves that such a method is practical in maritime safety supervision.
基金National Natural Science Foundation of China (52305358)the Fundamental Research Funds for the Central Universities (2023ZYGXZR061)+3 种基金Guangdong Basic and Applied Basic Research Foundation (2022A1515010304)Science and Technology Program of Guangzhou (202201010362)Young Elite Scientists Sponsorship Program by CAST . (2023QNRC001)Young Talent Support Project of Guangzhou (QT-2023-001)
文摘Zinc(Zn)is considered a promising biodegradable metal for implant applications due to its appropriate degradability and favorable osteogenesis properties.In this work,laser powder bed fusion(LPBF)additive manufacturing was employed to fabricate pure Zn with a heterogeneous microstructure and exceptional strength-ductility synergy.An optimized processing window of LPBF was established for printing Zn samples with relative densities greater than 99%using a laser power range of 80∼90 W and a scanning speed of 900 mm s−1.The Zn sample printed with a power of 80 W at a speed of 900 mm s−1 exhibited a hierarchical heterogeneous microstructure consisting of millimeter-scale molten pool boundaries,micrometer-scale bimodal grains,and nanometer-scale pre-existing dislocations,due to rapid cooling rates and significant thermal gradients formed in the molten pools.The printed sample exhibited the highest ductility of∼12.1%among all reported LPBF-printed pure Zn to date with appreciable ultimate tensile strength(∼128.7 MPa).Such superior strength-ductility synergy can be attributed to the presence of multiple deformation mechanisms that are primarily governed by heterogeneous deformation-induced hardening resulting from the alternative arrangement of bimodal Zn grains with pre-existing dislocations.Additionally,continuous strain hardening was facilitated through the interactions between deformation twins,grains and dislocations as strain accumulated,further contributing to the superior strength-ductility synergy.These findings provide valuable insights into the deformation behavior and mechanisms underlying exceptional mechanical properties of LPBF-printed Zn and its alloys for implant applications.
文摘Urbanization changes have been widely examined and numerous urban growth models have been proposed. We introduce an alternative urban growth model specifically designed to incorporate spatial heterogeneity in urban growth models. Instead of applying a single method to the entire study area, we segment the study area into different regions and apply targeted algorithms in each subregion. The working hypothesis is that the integration of appropriately selected region-specific models will outperform a globally applied model as it will incorporate further spatial heterogeneity. We examine urban land use changes in Denver, Colorado. Two land use maps from different time snapshots (1977 and 1997) are used to detect the urban land use changes, and 23 explanatory factors are produced to model urbanization. The proposed Spatially Heterogeneous Expert Based (SHEB) model tested decision trees as the underlying modeling algorithm, applying them in different subregions. In this paper the segmentation tested is the division of the entire area into interior and exterior urban areas. Interior urban areas are those situated within dense urbanized structures, while exterior urban areas are outside of these structures. Obtained results on this model regionalization technique indicate that targeted local models produce improved results in terms of Kappa, accuracy percentage and multi-scale performance. The model superiority is also confirmed by model pairwise comparisons using t-tests. The segmentation criterion of interior/exterior selection may not only capture specific characteristics on spatial and morphological properties, but also socioeconomic factors which may implicitly be present in these spatial representations. The usage of interior and exterior subregions in the present study acts as a proof of concept. Other spatial heterogeneity indicators, for example landscape, socioeconomic and political boundaries could act as the basis for improved local segmentations.
基金financially supported by the National Key Research and Development Program of China(Nos.2018YFB1106302 and 2016YFB1100104)the National Natural Science Foundation of China(No.52005411)。
文摘Laser powder bed fusion(L-PBF)of Sc/Zr-modified Al-based alloys has recently become a promising method for developing a new generation of high-performance Al alloys.To clarify the modification roles of Sc/Zr elements,an Al–4.66Mg–0.48Mn–0.72Sc–0.33Zr(wt.%)alloy was processed using L-PBF.The effect of the local solidification condition of the molten pool on the precipitation behavior of primary Al_(3)(Sc,Zr)was analyzed based on time-dependent nucleation theory.It was found that primary Al_(3)(Sc,Zr)inevitably precipitated at the fusion boundary,while its precipitation could be effectively suppressed in the inner region of the molten pool.This subsequently induced the formation of a heterogeneousα-Al matrix.After direct aging,the heredity of solidification microstructure introduced heterogeneous secondary Al_(3)(Sc,Zr)precipitates withinα-Al matrix.Owing to the inverse relationship between grain boundary strengthening and precipitation strengthening,the direct-aged sample with dual heterogeneous structures exhibited reduced mechanical heterogeneity,resulting in lowered hetero-deformation-induced hardening.The low strain-hardening capability in the direct-aged sample promoted necking instability while inducing a large Lüders elongation,which effectively improved the tensile ductility.
基金supported by the Science and Technology Innovation 2030-Key Project of“New Generation Artificial Intelligence”of China(No.2020AAA0108200)the National Natural Science Foundation of China(Nos.61873011,61922008,61973013,61803014)+2 种基金the Innovation Zone Project of China(No.18-163-00-TS-001-001-34)the Defense Industrial Technology Development Program of China(No.JCKY2019601C106)the Special Research Project of Chinese Civil Aircraft,China。
文摘The problem of distributed fusion and random observation loss for mobile sensor networks is investigated herein.In view of the fact that the measured values,sampling frequency and noise of various sensors are different,the observation model of a heterogeneous network is constructed.A binary random variable is introduced to describe the drop of observation component and the topology switching problem caused by complete observation loss is also considered.A cubature information filtering algorithm is adopted to design local filters for each observer to suppress the negative effects of measurement noise.To derive a consistent and accurate estimation result,a novel weighted average consensus-based filtering approach is put forward.For the sensor that suffers from observation loss,its local prediction information vector is fused with the information contribution vectors of the neighbors to obtain the local estimation.Then the consensus weight matrix is designed for consensus-based distributed collaborative information fusion.The boundness of the estimation errors is proved by employing the stochastic stability theory.In the end,two numerical examples are offered to assert the validity of the presented method.
文摘With the high-tech industrialization of earth observation satellite remote sensing and the implementation of digital earth strategy,the energy and natural resources have been decided to be the key research fields in China.In these fields,from the model based on topology data,through simple feature data model to rule-based data model,the basic spatial analysis algorithms have been developed
基金National Natural Science Foundation of China(No.42101346)Undergraduate Training Programs for Innovation and Entrepreneurship of Wuhan University(GeoAI Special Project)(No.202510486196).
文摘The rapid urbanization and structural imbalances in Chinese megacities have exacerbated the housing supplydemand mismatch,creating an urgent need for fine-scale diagnostic tools.This study addresses this critical gap by developing the Housing Contradiction Evaluation Weighted Index(HCEWI)model,making three key contributions to high-resolution housing monitoring.First,we establish a tripartite theoretical framework integrating dynamic population pressure(PPI),housing supply potential(HSI),and functional diversity(HHI).The PPI innovatively combines mobile signaling data with principal component analysis to capture real-time commuting patterns,while the HSI introduces a novel dual-criteria system based on Local Climate Zones(LCZ),weighted by building density and residential function ratio.Second,we develop a spatiotemporal coupling architecture featuring an entropy-weighted dynamic integration mechanism with self-correcting modules,demonstrating robust performance against data noise.Third,our 25-month longitudinal analysis in Shenzhen reveals significant findings,including persistent bipolar clustering patterns,contrasting volatility between peripheral and core areas,and seasonal policy responsiveness.Methodologically,we advance urban diagnostics through 500-meter grid monthly monitoring and process-oriented temporal operators that reveal“tentacle-like”spatial restructuring along transit corridors.Our findings provide a replicable framework for precision housing governance and demonstrate the transformative potential of mobile signaling data in implementing China’s“city-specific policy”approach.We further propose targeted intervention strategies,including balance regulation for high-contradiction zones,Transit-Oriented Development(TOD)activation for low-contradiction clusters,and dynamic land conversion mechanisms for transitional areas.
基金This work was financially supported by the National Natural Science Foundation of China(Nos.52061160483 and 92166130)the Hubei Science Fund for Distinguished Young Scholars(No.2020CFA086).The authors are also grateful to the Analytical and Testing Center,Huazhong University of Science and Technology for technical assistance.
文摘Additive manufacturing of aluminum alloys has received significant attention in the aerospace industry;however,achieving sufficient high strength,especially at elevated temperatures,remains challenging.Here,a crack-free and near-full dense Al-1Fe-0.6Cu-1.3Zr alloy was fabricated by the laser powder bed fusion(LPBF)technique.The Al-Fe-Cu-Zr alloy exhibits heterogeneous microstructures with two distinct zones.One is the so-called coarse-grain zones(CGZs)with an average grain size of 0.95μm,where(Al,Cu)Fe_(3) nanoparticles precipitate in the Al matrix and Fe and Cu cosegregate at the grain boundaries(GBs).The other is fine-grain zones(FGZs)with an average grain size of 0.45μm,where an Al 3 Zr nanoparti-cle precipitates in each of theα-Al grains(serves as the nuclei),and Fe-rich nanoprecipitates and Fe/Cu cosegregation appear at the GBs.As a result,the LPBF Al-Fe-Cu-Zr alloy,with these unique heteroge-neous structures,displays high strength at both room temperature and elevated temperatures,e.g.,with high yield strengths of 500 MPa at room temperature,and 163 MPa at 573 K,both are higher than those of additive manufactured Al-based alloys reported thus far.It is suggested that the high strength over a wide temperature range of the current LPBF Al alloy is mainly attributed to the combination of the precipitation strengthening mechanism and grain-boundary strengthening mechanism.
基金Zhiyu Xiao acknowledges the financial support from the National Natural Science Foundation of China(No.52274363)the Guangdong Basic Applied Basic Research Foundation,China(No.2022A1515010558)+2 种基金Chaofeng Gao acknowledges the financial support by the Guangdong Basic Applied Basic Research Founda-tion,China(No.2022A1515011597)J.T.Zhang acknowledges the financial support by the Guangdong Basic Applied Basic Research Foundation,China(No.2022A1515240065)the Natural Science Foundation Project of Guangzhou,China(No.202201010526).
文摘In this work,a high-strength crack-free TiN/Al-Mn-Mg-Sc-Zr composite was fabricated by laser powder bed fusion(L-PBF).A large amount of uniformly distributed L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles were formed during the L-PBF process due to the partial melting and decomposition of TiN nanoparticles under a high temperature.These L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles exhibited a highly coherent lattice relationship with the Al matrix.All the prepared TiN/Al-Mn-Mg-Sc-Zr composite samples exhibit ultrafine grain mi-crostructure.In addition,the as-built composite containing 1.5 wt%TiN shows an excellent tensile prop-erty with a yield strength of over 580 MPa and an elongation of over 8%,which were much higher than those of wrought 7xxx alloys.The effects of various strengthening mechanisms were quantitatively estimated and the high strength of the alloy was mainly attributed to the refined microstructure,solid solution strengthening,and precipitation strengthening contributed by L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles.
基金the support of the Diamond Light Source for providing the beamtime(MG22506)at the I12 beamlinethe support from the Royal Society International Exchange Grant(IECNSFC191319)and Research Grant(RGSR2202122)。
文摘Isotropy in microstructure and mechanical properties remains a challenge for laser powder bed fusion(LPBF)processed materials due to the epitaxial growth and rapid cooling in LPBF.In this study,a high-strength TiB_(2)/Al-Cu composite with random texture was successfully fabricated by laser powder bed fusion(LPBF)using pre-doped TiB_(2)/Al-Cu composite powder.A series of advanced characterisation techniques,including synchrotron X-ray tomography,correlative focussed ion beam-scanning electron microscopy(FIB-SEM),scanning transmission electron microscopy(STEM),and synchrotron in situ X-ray diffraction,were applied to investigate the defects and microstructure of the as-fabricated TiB_(2)/Al-Cu composite across multiple length scales.The study showed ultra-fine grains with an average grain size of about 0.86μm,and a random texture was formed in the as-fabricated condition due to rapid solidification and the TiB_(2)particles promoting heterogeneous nucleation.The yield strength and total elongation of the as-fabricated composite were 317 MPa and 10%,respectively.The contributions of fine grains,solid solutions,dislocations,particles,and Guinier-Preston(GP)zones were calculated.Failure was found to be initiated from the largest lack-of-fusion pore,as revealed by in situ synchrotron tomography during tensile loading.In situ synchrotron diffraction was used to characterise the lattice strain evolution during tensile loading,providing important data for the development of crystal-plasticity models.
基金the National Science Fund for Distinguished Young Scholars(No.52125102)the China Postdoctoral Science Foundation(Nos.2022TQ0203 and 2022M722047)+1 种基金Fundamental Research Funds for the Central Universities(No.FRF-TP-2021-02C2)Shanghai Technical Barriers to Trade(No.2021TBT004).
文摘Post-heat treatment is generally adopted in the additive manufacturing field due to its alleviation of high residual stress and modification of rapid-solidified multilevel heterogeneous microstructure,and the related performance of the heat-treated counterparts calls for a systemic investigation to build a criterion of the heat treatment procedure.In this work,we focus on the heat treatment effects on the recrystallization of the Hastelloy X alloy produced by the laser powder bed fusion(LPBF)method,and the related surface passivation of the heat-treated counterparts is meticulously assessed as well.Results show that the multilevel heterostructure for LPBF Hastelloy X alloy consists of sub-micro dislocation cell substructures with Cr/Mo elemental segregation,fine columnar grains,and periodically-distributed molten pools.After heat treatment,partially and fully recrystallized structures for LPBF Hastelloy X alloys were achieved at 1100 and 1200℃for 1 h,respectively.Furthermore,the as-built LPBF Hastelloy X alloy shows superior corrosion resistance while the heat-treated one(1100℃)exhibits the worst in the borate buffer solution.The growth of passive film exhibited a highly linear correlation with the nucleation process controlled by diffusion,and high dislocation density and low angle grain boundary decreased the diffusion coefficient of cation vacancies,augmenting the nucleation sites of the passive film and enhancing its growth rate.Moreover,the micro-galvanic effect resulting from the partially recrystallized microstructure actively facilitated the formation of inhomogeneous porous passive films,leading to the worst corrosion resistance.
基金the National Natural Science Foundation of China(Grant No.62062001)Ningxia Youth Top Talent Project(2021).
文摘In the realm of data privacy protection,federated learning aims to collaboratively train a global model.However,heterogeneous data between clients presents challenges,often resulting in slow convergence and inadequate accuracy of the global model.Utilizing shared feature representations alongside customized classifiers for individual clients emerges as a promising personalized solution.Nonetheless,previous research has frequently neglected the integration of global knowledge into local representation learning and the synergy between global and local classifiers,thereby limiting model performance.To tackle these issues,this study proposes a hierarchical optimization method for federated learning with feature alignment and the fusion of classification decisions(FedFCD).FedFCD regularizes the relationship between global and local feature representations to achieve alignment and incorporates decision information from the global classifier,facilitating the late fusion of decision outputs from both global and local classifiers.Additionally,FedFCD employs a hierarchical optimization strategy to flexibly optimize model parameters.Through experiments on the Fashion-MNIST,CIFAR-10 and CIFAR-100 datasets,we demonstrate the effectiveness and superiority of FedFCD.For instance,on the CIFAR-100 dataset,FedFCD exhibited a significant improvement in average test accuracy by 6.83%compared to four outstanding personalized federated learning approaches.Furthermore,extended experiments confirm the robustness of FedFCD across various hyperparameter values.
