The centroid coordinate serves as a critical control parameter in motion systems,including aircraft,missiles,rockets,and drones,directly influencing their motion dynamics and control performance.Traditional methods fo...The centroid coordinate serves as a critical control parameter in motion systems,including aircraft,missiles,rockets,and drones,directly influencing their motion dynamics and control performance.Traditional methods for centroid measurement often necessitate custom equipment and specialized positioning devices,leading to high costs and limited accuracy.Here,we present a centroid measurement method that integrates 3D scanning technology,enabling accurate measurement of centroid across various types of objects without the need for specialized positioning fixtures.A theoretical framework for centroid measurement was established,which combined the principle of the multi-point weighing method with 3D scanning technology.The measurement accuracy was evaluated using a designed standard component.Experimental results demonstrate that the discrepancies between the theoretical and the measured centroid of a standard component with various materials and complex shapes in the X,Y,and Z directions are 0.003 mm,0.009 mm,and 0.105 mm,respectively,yielding a spatial deviation of 0.106 mm.Qualitative verification was conducted through experimental validation of three distinct types.They confirmed the reliability of the proposed method,which allowed for accurate centroid measurements of various products without requiring positioning fixtures.This advancement significantly broadened the applicability and scope of centroid measurement devices,offering new theoretical insights and methodologies for the measurement of complex parts and systems.展开更多
Intelligent perception,as a cutting-edge field of modern science and technology,is profoundly changing our understanding and interaction with the world.With the rapid development of artificial intelligence,the Interne...Intelligent perception,as a cutting-edge field of modern science and technology,is profoundly changing our understanding and interaction with the world.With the rapid development of artificial intelligence,the Internet of things,big data,and other technologies,intelligent perception systems have shown great potential in non-destructive testing,safety monitoring,human-computer interaction,and precision measurement.Traditional sensing technologies face many challenges in complex scenarios or specific needs,while intelligent perception provides a new path for innovation and breakthroughs in instrumentation and sensing technologies through multidisciplinary integration.展开更多
The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack...The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack of semantic information,high decoder magnification,and insufficient detail retention ability.A hierarchical feature fusion network(HFFNet)was proposed.Firstly,a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions.The extracted features were processed independently.Subsequently,the features from the transformer and CNN were fused under the guidance of features from different sources.This fusion process assisted in restoring information more comprehensively during the decoding stage.Furthermore,a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features.The experimental results showed that HFFNet had superior performance on UAVid,LoveDA,Potsdam,and Vaihingen datasets,and its cross-linking index was better than DeepLabv3+and other competing methods,showing strong generalization ability.展开更多
Noninvasive detection of human physiology plays a key role for diagnosis or therapeutic assessment of various diseases.In the past,many functional modalities,such as electrocardiograph(ECG),electroencephalogram(EEG),f...Noninvasive detection of human physiology plays a key role for diagnosis or therapeutic assessment of various diseases.In the past,many functional modalities,such as electrocardiograph(ECG),electroencephalogram(EEG),fluorescence microscope,and positron emission computed tomography(PETS)have been applied to clinic for probing human heart,brain waves or tissue metabolism,owing to rapid development in fields of electromagnetism,optics or particle physics.Nowadays,a few smart sensing technologies are emerging for human physiology detection in more wide range.展开更多
High-sensitivity sensors represent a critical frontier in modern sensing technology,driving innovations across fields such as biomedical monitoring,precision instrumentation,environmental detection,and indus-trial aut...High-sensitivity sensors represent a critical frontier in modern sensing technology,driving innovations across fields such as biomedical monitoring,precision instrumentation,environmental detection,and indus-trial automation.As demands for accuracy,miniaturization,and reliability continue to grow,developing novel sensor architectures and functional materials has become essential to achieving enhanced performance under extreme or complex conditions.展开更多
Accurate and real-time fire detection is crucial for industrial production and daily life.However,the variable form of fire and the significant differences in visual characteristics across its different stages pose gr...Accurate and real-time fire detection is crucial for industrial production and daily life.However,the variable form of fire and the significant differences in visual characteristics across its different stages pose great challenges to precise fire prevention and control.To address this issue,a multi-scale fire target detection algorithm using YOLO-fire was proposed by improving the YOLOv8 model.This model introduced new layer structures and attention mechanism,replaced new feature fusion modules and loss functions.By introducing a small-target detection P2 layer,the model’s ability to detect early-stage fires is improved.The coordinate attention mechanism is integrated into the layer structures of multi-scale target detection,enhancing the capture of target location information and channel relationships,thereby focusing more on the target regions.The Neck network structure was optimized by adopting a BiFPN_F strategy for different feature layers,which strengthened the cross-scale representation of fire features and controlled the parameter count of the designed model.The WIoU loss function was employed to optimize the regression process,improving fire source localization accuracy in complex scenarios,enhancing model robustness,and increasing detection precision.Experimental results on fire datasets demonstrated that YOLO-fire could effectively detect multi-scale fire targets in various scenarios.Compared to the baseline model(YOLOv8n),YOLO-fire achieves improvements of 1.37%in accuracy,1.25%in mAP50-95,and 0.35%in F1-score,while reducing parameters by 3.79%.Furthermore,compared to current mainstream target detection algorithms,YOLO-Fire achieved optimal detection performance while reducing network parameters and computational complexity.This research provided effective technical support for fire safety prevention and control in related fields.展开更多
In response to the problems of low sampling efficiency,strong randomness of sampling points,and the tortuous shape of the planned path in the traditional rapidly-exploring random tree(RRT)algorithm and bidirectional R...In response to the problems of low sampling efficiency,strong randomness of sampling points,and the tortuous shape of the planned path in the traditional rapidly-exploring random tree(RRT)algorithm and bidirectional RRT algorithm used for unmanned aerial vehicle(UAV)path planning in complex environments,an improved bidirectional RRT algorithm was proposed.The algorithm firstly adopted a goal-oriented strategy to guide the sampling points towards the target point,and then the artificial potential field acted on the random tree nodes to avoid collision with obstacles and reduced the length of the search path,and the random tree node growth also combined the UAV’s own flight constraints,and by combining the triangulation method to remove the redundant node strategy and the third-order B-spline curve for the smoothing of the trajectory,the planned path was better.The planned paths were more optimized.Finally,the simulation experiments in complex and dynamic environments showed that the algorithm effectively improved the speed of trajectory planning and shortened the length of the trajectory,and could generate a safe,smooth and fast trajectory in complex environments,which could be applied to online trajectory planning.展开更多
The switch machine is a vital component in the railway system,playing a significant role in ensuring the safe operation of trains.To address the shortcomings of existing fault diagnosis methods for the switch machine ...The switch machine is a vital component in the railway system,playing a significant role in ensuring the safe operation of trains.To address the shortcomings of existing fault diagnosis methods for the switch machine and leveraging the strong anti-interference and high sensitivity characteristics of vibration signals,we proposed a VMD-SDP-CNN(Variational mode decomposition-Symmetric dot pattern-Convolutional neural network)fault diagnosis method based on switch machine vibration signals.Firstly,the vibration signal of the switch machine was decomposed by VMD to obtain several intrinsic mode function(IMF)components.Secondly,the SDP method was employed to transform the decomposed IMF components into two-dimensional images,and the issue of one-dimensional signal recognition was transformed into the issue of two-dimensional image recognition.Finally,a CNN was used to realize the fault diagnosis of the switch machine.The experimental results showed that the recognition accuracy of the five actual working conditions of the switch machine using this method was superior to that of typical deep learning and machine learning methods,verifying its practicability and effectiveness.展开更多
The traditional train positioning methods suffer from inadequate accuracy and high maintenance costs,rendering them unsuitable for the development requirements of lightweight and intelligent train positioning technolo...The traditional train positioning methods suffer from inadequate accuracy and high maintenance costs,rendering them unsuitable for the development requirements of lightweight and intelligent train positioning technology.To address these restraints,the BeiDou navigation satellite system/strapdown inertial navigation system(BDS/SINS)integrated train positioning system based on an adaptive unscented Kalman filter(AUKF)is proposed.Firstly,the combined denoising algorithm(CDA)and Lagrange interpolation algorithm are introduced to preprocess the original data,effectively eliminating the influence of noise signals and abnormal measurements on the train positioning system.Secondly,the innovation theory is incorporated into the unscented Kalman filter(UKF)to derive the AUKF,which accomplishes an adaptive update of the measurement noise covariance.Finally,the positioning performance of the proposed AUKF is contrasted with that of conventional algorithms in various operation scenes.Simulation results demonstrate that the average value of error calculated by AUKF is less than 1.5 m,and the success rate of positioning touches 95.0%.Compared to Kalman filter(KF)and UKF,AUKF exhibits superior accuracy and stability in train positioning.Consequently,the proposed AUKF is well-suited for providing precise positioning services in variable operating environments for trains.展开更多
To enable optimal navigation for unmanned surface vehicle(USV),we proposed an adaptive hybrid strategy-based sparrow search algorithm(SSA)for efficient and reliable path planning.The proposed method began by enhancing...To enable optimal navigation for unmanned surface vehicle(USV),we proposed an adaptive hybrid strategy-based sparrow search algorithm(SSA)for efficient and reliable path planning.The proposed method began by enhancing the fitness function to comprehensively account for critical path planning metrics,including path length,turning angle,and navigation safety.To improve search diversity and effectively avoid premature convergence to local optima,chaotic mapping was employed during the population initialization stage,allowing the algorithm to explore a wider solution space from the outset.A reverse inertia weight mechanism was introduced to dynamically balance exploration and exploitation across different iterations.The adaptive adjustment of the inertia weight further improved convergence efficiency and enhanced global optimization performance.In addition,a Cauchy-Gaussian hybrid update strategy was incorporated to inject randomness and variation into the search process,which helped the algorithm escape local minima and maintain a high level of solution diversity.This approach significantly enhanced the robustness and adaptability of the optimization process.Simulation experiments confirmed that the improved SSA consistently outperformed benchmark algorithms such as the original SSA,PSO,and WMR-SSA.Compared with the three algorithms,in the simulated sea area,the path lengths of the proposed algorithm are reduced by 21%,21%,and 16%,respectively,and under the actual sea simulation conditions,the path lengths are reduced by 13%,15%,and 11%,respectively.The results highlighted the effectiveness and practicality of the proposed method,providing an effective solution for intelligent and autonomous USV navigation in complex ocean environments.展开更多
With the rapid development of flexible electronics,the tactile systems for object recognition are becoming increasingly delicate.This paper presents the design of a tactile glove for object recognition,integrating 243...With the rapid development of flexible electronics,the tactile systems for object recognition are becoming increasingly delicate.This paper presents the design of a tactile glove for object recognition,integrating 243 palm pressure units and 126 finger joint strain units that are implemented by piezoresistive Velostat film.The palm pressure and joint bending strain data from the glove were collected using a two-dimensional resistance array scanning circuit and further converted into tactile images with a resolution of 32×32.To verify the effect of tactile data types on recognition precision,three datasets of tactile images were respectively built by palm pressure data,joint bending strain data,and a tactile data combing of both palm pressure and joint bending strain.An improved residual convolutional neural network(CNN)model,SP-ResNet,was developed by light-weighting ResNet-18 to classify these tactile images.Experimental results show that the data collection method combining palm pressure and joint bending strain demonstrates a 4.33%improvement in recognition precision compared to the best results obtained by using only palm pressure or joint bending strain.The recognition precision of 95.50%for 16 objects can be achieved by the presented tactile glove with SP-ResNet of less computation cost.The presented tactile system can serve as a sensing platform for intelligent prosthetics and robot grippers.展开更多
Fluxgate current sensors(FGCSs)are increasingly employed in power systems due to their high-precision characteristics,yet their measurement flexibility remains constrained by conventional closed-core designs.To addres...Fluxgate current sensors(FGCSs)are increasingly employed in power systems due to their high-precision characteristics,yet their measurement flexibility remains constrained by conventional closed-core designs.To address this limitation,we proposed a split-core sensor structure comprising four magnetic core strips,which achieved non-intrusive current measurement while maintaining detection accuracy.An analytical model of the induced electromotive force was established based on the probe’s geometric configuration,followed by finite element simulations to optimize key parameters including core radius,core width,excitation coil turns,and sensing coil configuration.A complete prototype integrating the measurement probe,excitation circuit,and signal processing circuitry was developed and experimentally validated.The experimental results show a sensitivity of 0.1099 V/A,a hysteresis error of 0.559%,and a repeatability error of 1.574%over a measurement range of±10 A.After polynomial fitting-based error compensation,the nonlinearity error was reduced to 0.208%,achieving performance comparable to closed-core sensors.This work provided a practical solution for applications demanding both high measurement accuracy and installation flexibility.展开更多
This paper presents a new type of ultra-material microwave pressure sensor designed for extreme environments,and conducts a systematic study on its structural design,manufacturing process,working mechanism,and experim...This paper presents a new type of ultra-material microwave pressure sensor designed for extreme environments,and conducts a systematic study on its structural design,manufacturing process,working mechanism,and experimental performance.The sensor is based on the cross-slot ultra-material resonant structure.Platinum-based conductive patterns are precisely fabricated on a high-purity alumina ceramic substrate through screen printing,and a strong bond between metal and ceramic is achieved through high-temperature sintering.Thanks to the high-temperature stability of the ceramic material and the high precision of the process,this sensor maintains excellent structural integrity and performance consistency in harsh environments.The working mechanism of the sensor is based on the microstructural deformation induced by pressure.When external pressure is applied to the ceramic cavity,the deformation of the cavity will change the equivalent electromagnetic boundary conditions inside,thereby causing perturbations in the resonant modes of the metamaterial,resulting in a continuous measurable shift in the resonant frequency.Based on this mechanism,the change in pressure can be precisely mapped to the frequency change,enabling wireless and passive pressure measurement.By utilizing the intrinsic resonant radiation of the metamaterial to achieve coupled readings,the complexity of sensor integration is significantly reduced and its working reliability in high-pressure,high-temperature,and strong electromagnetic interference environments is improved.During the design stage,the influence laws of the geometric parameters of the metamaterial and other factors on the resonant performance and pressure sensitivity were analyzed through finite element coupling simulation.Experimental verification shows that the sensor exhibits excellent linear pressure response within the range of 0−500 kPa,and maintains good repeatability and frequency stability in the high-pressure zone.The maximum sensitivity reaches 135 kHz/kPa,and the frequency drift is minimal during multiple loading-unloading cycles,fully demonstrating that the structural strength and reliability of the design meet the engineering requirements.The sensor proposed in this study could achieve longterm stable operation in aerospace engine compartments,high-temperature metallurgical furnaces,deep mine pressure monitoring,petrochemical high-corrosion pipelines,and extreme environment equipment.This research not only demonstrated the potential of integrating metamaterials with advanced ceramic processes to construct wireless passive sensors,but also provided new design ideas and process routes for the engineering application of microwave sensing technology in harsh environments.展开更多
Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding ...Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.展开更多
To enhance the quality factor and sensitivity of refractive index sensors,a feedback waveguide slot grating micro-ring resonator was proposed.An air-hole grating structure was introduced based on the slot micro-ring,u...To enhance the quality factor and sensitivity of refractive index sensors,a feedback waveguide slot grating micro-ring resonator was proposed.An air-hole grating structure was introduced based on the slot micro-ring,utilizing the reflection of the grating to achieve the electromagnetic-like induced transparency effect at different wavelengths.The high slope characteristics of the EIT-like effect enabled a higher quality factor and sensitivity.The transmission principle of the structure was analyzed using the transmission matrix method,and the transmission spectrum and mode field distribution were simulated using the finite-difference time-domain(FDTD)method,and the device structure parameters were adjusted for optimization.Simulation results show that the proposed structure achieves an EIT-like effect with a quality factor of 59267.5.In the analysis of refractive index sensing characteristics,the structure exhibits a sensitivity of 408.57 nm/RIU and a detection limit of 6.23×10^(-5) RIU.Therefore,the proposed structure achieved both a high quality factor and refractive index sensitivity,demonstrating excellent sensing performance for applications in environmental monitoring,biomedical fields,and other areas with broad market potential.展开更多
To improve the accuracy of indoor localization methods with channel state information(CSI)images,a localization method that used CSI images from selected multiple access points(APs)was proposed.The method had an off-l...To improve the accuracy of indoor localization methods with channel state information(CSI)images,a localization method that used CSI images from selected multiple access points(APs)was proposed.The method had an off-line phase and an on-line phase.In the off-line phase,three APs were selected from the four APs in the localization area based on the received signal strength indication(RSSI).Next,CSI data was collected from the three selected APs using a commercial Intel 5300 network interface card.A single-channel subimage was constructed for each selected AP by combining the amplitude information from different antennas and the phase difference information between neighboring antennas.These sub-images were then merged to form a three-channel RGB image,which was subsequently fed into the convolutional neural network(CNN)for training.The CNN model was saved upon completion of training.In the on-line phase,the CSI data from the target device was collected,converted into images using the same process as in the off-line phase,and fed into the well-trained CNN model.Finally,the real position of the target device was estimated using a weighted centroid algorithm based on the model’s output probabilities.The proposed method was validated in indoor environments using two datasets,achieving good localization accuracy.展开更多
In camera calibration,accurate estimation of homography matrix between the world coordinates of the calibration board and its image coordinates is a key step in high-precision calibration of intrinsic camera parameter...In camera calibration,accurate estimation of homography matrix between the world coordinates of the calibration board and its image coordinates is a key step in high-precision calibration of intrinsic camera parameters.The existing homography matrix estimation methods have problems such as dependence on thresholds,low computational efficiency,and initial model or sorting quality affecting results.In this paper,a homography matrix estimation method based on adaptive genetic algorithm was proposed.Firstly,a new circular grid calibration board was designed and the strategy of first sampling of data sets was optimized.Secondly,a mathematical model for the estimated homography matrix was established according to the adaptive genetic algorithm.Thereby the optimal homography matrix between the calibration board and its image was obtained.Finally,the intrinsic camera parameters were calculated based on Zhang’s calibration method.The experimental results show that compared with the results of three traditional estimation methods RANSAC,PROSAC,and LMEDS,the reprojection error of the images by our estimation method is reduced by about 4.11%-7.85%,11.94%-16.91%,and 10.19%-17.82%,respectively;and the average running time of the algorithm decreases by about 25.85%-37.47%,11.99%-22.71%,and 46.50%-53.35%,respectively.In addition,the homography matrix estimation method in this paper was applied to camera calibration.The results show that compared with the traditional estimation method,the average accuracy of the camera during the calibration process increases by about 5.48%,15.06%,and 11.47%,respectively;and the average calibration efficiency of the camera is improved by about 10.13%,5.71%,and 14.26%,respectively.The homography matrix estimation method proposed in this paper not only obtained reliable results,but also had certain value and significance in improving the estimation accuracy and calculation efficiency in camera calibration.展开更多
Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a co...Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical settings.These methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality combinations.Additionally,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training data.This work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing modalities.The proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”data.Co-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing modalities.The model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation task.EACNet was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance respectively.Notably,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing methods.The analysis suggests that the ensemble approach offers potential benefits,and the adversarial co-training contributes to the increased robustness and accuracy of EACNet for brain tumor segmentation of MRI scans with missing modalities.The experimental results show that EACNet has promising results for the task of brain tumor segmentation of MRI scans with missing modalities and is a better candidate for real-world clinical applications.展开更多
Data collected in fields such as cybersecurity and biomedicine often encounter high dimensionality and class imbalance.To address the problem of low classification accuracy for minority class samples arising from nume...Data collected in fields such as cybersecurity and biomedicine often encounter high dimensionality and class imbalance.To address the problem of low classification accuracy for minority class samples arising from numerous irrelevant and redundant features in high-dimensional imbalanced data,we proposed a novel feature selection method named AMF-SGSK based on adaptive multi-filter and subspace-based gaining sharing knowledge.Firstly,the balanced dataset was obtained by random under-sampling.Secondly,combining the feature importance score with the AUC score for each filter method,we proposed a concept called feature hardness to judge the importance of feature,which could adaptively select the essential features.Finally,the optimal feature subset was obtained by gaining sharing knowledge in multiple subspaces.This approach effectively achieved dimensionality reduction for high-dimensional imbalanced data.The experiment results on 30 benchmark imbalanced datasets showed that AMF-SGSK performed better than other eight commonly used algorithms including BGWO and IG-SSO in terms of F1-score,AUC,and G-mean.The mean values of F1-score,AUC,and Gmean for AMF-SGSK are 0.950,0.967,and 0.965,respectively,achieving the highest among all algorithms.And the mean value of Gmean is higher than those of IG-PSO,ReliefF-GWO,and BGOA by 3.72%,11.12%,and 20.06%,respectively.Furthermore,the selected feature ratio is below 0.01 across the selected ten datasets,further demonstrating the proposed method’s overall superiority over competing approaches.AMF-SGSK could adaptively remove irrelevant and redundant features and effectively improve the classification accuracy of high-dimensional imbalanced data,providing scientific and technological references for practical applications.展开更多
In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GA...In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GADF)of multi-channel signal fusion and multi-scale attention residual network(MA-ResNet)was proposed.Firstly,the multi-channel vibration signals were subdivided into various frequency bands using wavelet packet decomposition,and the sensitive channels were selected for signal fusion by doing correlation analysis between the signals of various frequency bands and the surface roughness.Then the fused signals were converted into pictures using GADF image encoding.Finally,the pictures were inputted into the residual network model combining the parallel dilation convolution and attention module for training and verifying the effectiveness of the model performance.The proposed method has a root mean square error of 0.0187,a mean absolute error of 0.0143,and a coefficient of determination of 0.8694 in predicting the surface roughness,which is close to the actual value.Therefore,the proposed method had good engineering significance for high-precision prediction and was conducive to on-line monitoring of surface quality during workpiece processing.展开更多
基金supported by National Natural Science Foundation of China(No.52176122).
文摘The centroid coordinate serves as a critical control parameter in motion systems,including aircraft,missiles,rockets,and drones,directly influencing their motion dynamics and control performance.Traditional methods for centroid measurement often necessitate custom equipment and specialized positioning devices,leading to high costs and limited accuracy.Here,we present a centroid measurement method that integrates 3D scanning technology,enabling accurate measurement of centroid across various types of objects without the need for specialized positioning fixtures.A theoretical framework for centroid measurement was established,which combined the principle of the multi-point weighing method with 3D scanning technology.The measurement accuracy was evaluated using a designed standard component.Experimental results demonstrate that the discrepancies between the theoretical and the measured centroid of a standard component with various materials and complex shapes in the X,Y,and Z directions are 0.003 mm,0.009 mm,and 0.105 mm,respectively,yielding a spatial deviation of 0.106 mm.Qualitative verification was conducted through experimental validation of three distinct types.They confirmed the reliability of the proposed method,which allowed for accurate centroid measurements of various products without requiring positioning fixtures.This advancement significantly broadened the applicability and scope of centroid measurement devices,offering new theoretical insights and methodologies for the measurement of complex parts and systems.
文摘Intelligent perception,as a cutting-edge field of modern science and technology,is profoundly changing our understanding and interaction with the world.With the rapid development of artificial intelligence,the Internet of things,big data,and other technologies,intelligent perception systems have shown great potential in non-destructive testing,safety monitoring,human-computer interaction,and precision measurement.Traditional sensing technologies face many challenges in complex scenarios or specific needs,while intelligent perception provides a new path for innovation and breakthroughs in instrumentation and sensing technologies through multidisciplinary integration.
基金supported by National Natural Science Foundation of China(No.52374155)Anhui Provincial Natural Science Foundation(No.2308085 MF218).
文摘The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack of semantic information,high decoder magnification,and insufficient detail retention ability.A hierarchical feature fusion network(HFFNet)was proposed.Firstly,a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions.The extracted features were processed independently.Subsequently,the features from the transformer and CNN were fused under the guidance of features from different sources.This fusion process assisted in restoring information more comprehensively during the decoding stage.Furthermore,a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features.The experimental results showed that HFFNet had superior performance on UAVid,LoveDA,Potsdam,and Vaihingen datasets,and its cross-linking index was better than DeepLabv3+and other competing methods,showing strong generalization ability.
文摘Noninvasive detection of human physiology plays a key role for diagnosis or therapeutic assessment of various diseases.In the past,many functional modalities,such as electrocardiograph(ECG),electroencephalogram(EEG),fluorescence microscope,and positron emission computed tomography(PETS)have been applied to clinic for probing human heart,brain waves or tissue metabolism,owing to rapid development in fields of electromagnetism,optics or particle physics.Nowadays,a few smart sensing technologies are emerging for human physiology detection in more wide range.
文摘High-sensitivity sensors represent a critical frontier in modern sensing technology,driving innovations across fields such as biomedical monitoring,precision instrumentation,environmental detection,and indus-trial automation.As demands for accuracy,miniaturization,and reliability continue to grow,developing novel sensor architectures and functional materials has become essential to achieving enhanced performance under extreme or complex conditions.
基金supported by Natural Science Foundation of Inner Mongolia Autonomous Region,China(No.2023QN05023)the Key R&D and Achievement Transformation Programs of Inner Mongolia Autonomous Region,China(Nos.2025KYPT0051,2025KYPT0050).
文摘Accurate and real-time fire detection is crucial for industrial production and daily life.However,the variable form of fire and the significant differences in visual characteristics across its different stages pose great challenges to precise fire prevention and control.To address this issue,a multi-scale fire target detection algorithm using YOLO-fire was proposed by improving the YOLOv8 model.This model introduced new layer structures and attention mechanism,replaced new feature fusion modules and loss functions.By introducing a small-target detection P2 layer,the model’s ability to detect early-stage fires is improved.The coordinate attention mechanism is integrated into the layer structures of multi-scale target detection,enhancing the capture of target location information and channel relationships,thereby focusing more on the target regions.The Neck network structure was optimized by adopting a BiFPN_F strategy for different feature layers,which strengthened the cross-scale representation of fire features and controlled the parameter count of the designed model.The WIoU loss function was employed to optimize the regression process,improving fire source localization accuracy in complex scenarios,enhancing model robustness,and increasing detection precision.Experimental results on fire datasets demonstrated that YOLO-fire could effectively detect multi-scale fire targets in various scenarios.Compared to the baseline model(YOLOv8n),YOLO-fire achieves improvements of 1.37%in accuracy,1.25%in mAP50-95,and 0.35%in F1-score,while reducing parameters by 3.79%.Furthermore,compared to current mainstream target detection algorithms,YOLO-Fire achieved optimal detection performance while reducing network parameters and computational complexity.This research provided effective technical support for fire safety prevention and control in related fields.
基金supported by Gansu Provincial Science and Technology Program Project(No.23JRRA868)Lanzhou Municipal Talent Innovation and Entrepreneurship Project(No.2019-RC-103)。
文摘In response to the problems of low sampling efficiency,strong randomness of sampling points,and the tortuous shape of the planned path in the traditional rapidly-exploring random tree(RRT)algorithm and bidirectional RRT algorithm used for unmanned aerial vehicle(UAV)path planning in complex environments,an improved bidirectional RRT algorithm was proposed.The algorithm firstly adopted a goal-oriented strategy to guide the sampling points towards the target point,and then the artificial potential field acted on the random tree nodes to avoid collision with obstacles and reduced the length of the search path,and the random tree node growth also combined the UAV’s own flight constraints,and by combining the triangulation method to remove the redundant node strategy and the third-order B-spline curve for the smoothing of the trajectory,the planned path was better.The planned paths were more optimized.Finally,the simulation experiments in complex and dynamic environments showed that the algorithm effectively improved the speed of trajectory planning and shortened the length of the trajectory,and could generate a safe,smooth and fast trajectory in complex environments,which could be applied to online trajectory planning.
基金supported by Scientific Research Project of the Education Department of Liaoning Province(No.JYTMS20230008)Scientific Research Project of Transportation Department of Liaoning Province(No.202320).
文摘The switch machine is a vital component in the railway system,playing a significant role in ensuring the safe operation of trains.To address the shortcomings of existing fault diagnosis methods for the switch machine and leveraging the strong anti-interference and high sensitivity characteristics of vibration signals,we proposed a VMD-SDP-CNN(Variational mode decomposition-Symmetric dot pattern-Convolutional neural network)fault diagnosis method based on switch machine vibration signals.Firstly,the vibration signal of the switch machine was decomposed by VMD to obtain several intrinsic mode function(IMF)components.Secondly,the SDP method was employed to transform the decomposed IMF components into two-dimensional images,and the issue of one-dimensional signal recognition was transformed into the issue of two-dimensional image recognition.Finally,a CNN was used to realize the fault diagnosis of the switch machine.The experimental results showed that the recognition accuracy of the five actual working conditions of the switch machine using this method was superior to that of typical deep learning and machine learning methods,verifying its practicability and effectiveness.
基金supported by Project Fund of China National Railway Group Co.,Ltd.(No.N2022G012)Natonal Natural Science Foundation of China(No.61661027)。
文摘The traditional train positioning methods suffer from inadequate accuracy and high maintenance costs,rendering them unsuitable for the development requirements of lightweight and intelligent train positioning technology.To address these restraints,the BeiDou navigation satellite system/strapdown inertial navigation system(BDS/SINS)integrated train positioning system based on an adaptive unscented Kalman filter(AUKF)is proposed.Firstly,the combined denoising algorithm(CDA)and Lagrange interpolation algorithm are introduced to preprocess the original data,effectively eliminating the influence of noise signals and abnormal measurements on the train positioning system.Secondly,the innovation theory is incorporated into the unscented Kalman filter(UKF)to derive the AUKF,which accomplishes an adaptive update of the measurement noise covariance.Finally,the positioning performance of the proposed AUKF is contrasted with that of conventional algorithms in various operation scenes.Simulation results demonstrate that the average value of error calculated by AUKF is less than 1.5 m,and the success rate of positioning touches 95.0%.Compared to Kalman filter(KF)and UKF,AUKF exhibits superior accuracy and stability in train positioning.Consequently,the proposed AUKF is well-suited for providing precise positioning services in variable operating environments for trains.
基金supported by Shandong Provincial Department of Science and Technology Project(No.2022C01246)National Undergraduate Innovation Training Project(Nos.202410390028,202310390026)+1 种基金Fujian Provincial Undergraduate Innovation Training Project(No.202410390093)Jimei University Innovation Training Project(Nos.2024xj224,2023xj179).
文摘To enable optimal navigation for unmanned surface vehicle(USV),we proposed an adaptive hybrid strategy-based sparrow search algorithm(SSA)for efficient and reliable path planning.The proposed method began by enhancing the fitness function to comprehensively account for critical path planning metrics,including path length,turning angle,and navigation safety.To improve search diversity and effectively avoid premature convergence to local optima,chaotic mapping was employed during the population initialization stage,allowing the algorithm to explore a wider solution space from the outset.A reverse inertia weight mechanism was introduced to dynamically balance exploration and exploitation across different iterations.The adaptive adjustment of the inertia weight further improved convergence efficiency and enhanced global optimization performance.In addition,a Cauchy-Gaussian hybrid update strategy was incorporated to inject randomness and variation into the search process,which helped the algorithm escape local minima and maintain a high level of solution diversity.This approach significantly enhanced the robustness and adaptability of the optimization process.Simulation experiments confirmed that the improved SSA consistently outperformed benchmark algorithms such as the original SSA,PSO,and WMR-SSA.Compared with the three algorithms,in the simulated sea area,the path lengths of the proposed algorithm are reduced by 21%,21%,and 16%,respectively,and under the actual sea simulation conditions,the path lengths are reduced by 13%,15%,and 11%,respectively.The results highlighted the effectiveness and practicality of the proposed method,providing an effective solution for intelligent and autonomous USV navigation in complex ocean environments.
基金supported by the Key Research and Development Program of Shaanxi Province(No.2024 GX-YBXM-178)the Shaanxi Province Qinchuangyuan“Scientists+Engineers”Team Development(No.2022KXJ032)。
文摘With the rapid development of flexible electronics,the tactile systems for object recognition are becoming increasingly delicate.This paper presents the design of a tactile glove for object recognition,integrating 243 palm pressure units and 126 finger joint strain units that are implemented by piezoresistive Velostat film.The palm pressure and joint bending strain data from the glove were collected using a two-dimensional resistance array scanning circuit and further converted into tactile images with a resolution of 32×32.To verify the effect of tactile data types on recognition precision,three datasets of tactile images were respectively built by palm pressure data,joint bending strain data,and a tactile data combing of both palm pressure and joint bending strain.An improved residual convolutional neural network(CNN)model,SP-ResNet,was developed by light-weighting ResNet-18 to classify these tactile images.Experimental results show that the data collection method combining palm pressure and joint bending strain demonstrates a 4.33%improvement in recognition precision compared to the best results obtained by using only palm pressure or joint bending strain.The recognition precision of 95.50%for 16 objects can be achieved by the presented tactile glove with SP-ResNet of less computation cost.The presented tactile system can serve as a sensing platform for intelligent prosthetics and robot grippers.
基金supported by Yunnan Fundamental Research Projects(No.202301AT070181)Yunnan Fundamental Research Projects(No.202401CF070126)+1 种基金Xingdian Talent Support Program of Yunnan Province(No.KKRD202203070)Yunnan High level Science and Technology Talents and Innovation Team Selection Special Project(No.202405AS350001).
文摘Fluxgate current sensors(FGCSs)are increasingly employed in power systems due to their high-precision characteristics,yet their measurement flexibility remains constrained by conventional closed-core designs.To address this limitation,we proposed a split-core sensor structure comprising four magnetic core strips,which achieved non-intrusive current measurement while maintaining detection accuracy.An analytical model of the induced electromotive force was established based on the probe’s geometric configuration,followed by finite element simulations to optimize key parameters including core radius,core width,excitation coil turns,and sensing coil configuration.A complete prototype integrating the measurement probe,excitation circuit,and signal processing circuitry was developed and experimentally validated.The experimental results show a sensitivity of 0.1099 V/A,a hysteresis error of 0.559%,and a repeatability error of 1.574%over a measurement range of±10 A.After polynomial fitting-based error compensation,the nonlinearity error was reduced to 0.208%,achieving performance comparable to closed-core sensors.This work provided a practical solution for applications demanding both high measurement accuracy and installation flexibility.
基金supported by Key Research and Development Plan of Shanxi Province(Nos.202102030201005,202203021222022)National Natural Science Foundation of China(No.62401522)+2 种基金Fundamental Research of Shanxi Province(No.202203021222070)China Postdoctoral Science Foundation(No.2023M743313)Research Project Supported by Shanxi Scholarship Council of China.
文摘This paper presents a new type of ultra-material microwave pressure sensor designed for extreme environments,and conducts a systematic study on its structural design,manufacturing process,working mechanism,and experimental performance.The sensor is based on the cross-slot ultra-material resonant structure.Platinum-based conductive patterns are precisely fabricated on a high-purity alumina ceramic substrate through screen printing,and a strong bond between metal and ceramic is achieved through high-temperature sintering.Thanks to the high-temperature stability of the ceramic material and the high precision of the process,this sensor maintains excellent structural integrity and performance consistency in harsh environments.The working mechanism of the sensor is based on the microstructural deformation induced by pressure.When external pressure is applied to the ceramic cavity,the deformation of the cavity will change the equivalent electromagnetic boundary conditions inside,thereby causing perturbations in the resonant modes of the metamaterial,resulting in a continuous measurable shift in the resonant frequency.Based on this mechanism,the change in pressure can be precisely mapped to the frequency change,enabling wireless and passive pressure measurement.By utilizing the intrinsic resonant radiation of the metamaterial to achieve coupled readings,the complexity of sensor integration is significantly reduced and its working reliability in high-pressure,high-temperature,and strong electromagnetic interference environments is improved.During the design stage,the influence laws of the geometric parameters of the metamaterial and other factors on the resonant performance and pressure sensitivity were analyzed through finite element coupling simulation.Experimental verification shows that the sensor exhibits excellent linear pressure response within the range of 0−500 kPa,and maintains good repeatability and frequency stability in the high-pressure zone.The maximum sensitivity reaches 135 kHz/kPa,and the frequency drift is minimal during multiple loading-unloading cycles,fully demonstrating that the structural strength and reliability of the design meet the engineering requirements.The sensor proposed in this study could achieve longterm stable operation in aerospace engine compartments,high-temperature metallurgical furnaces,deep mine pressure monitoring,petrochemical high-corrosion pipelines,and extreme environment equipment.This research not only demonstrated the potential of integrating metamaterials with advanced ceramic processes to construct wireless passive sensors,but also provided new design ideas and process routes for the engineering application of microwave sensing technology in harsh environments.
基金supported by Natural Science Foundation Programme of Gansu Province(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Science and Technology Plan Key Research and Development Program Project(No.24YFFA024).
文摘Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.
基金supported by Natural Science Foundation of Gansu Province(NO.21JR7RA289)。
文摘To enhance the quality factor and sensitivity of refractive index sensors,a feedback waveguide slot grating micro-ring resonator was proposed.An air-hole grating structure was introduced based on the slot micro-ring,utilizing the reflection of the grating to achieve the electromagnetic-like induced transparency effect at different wavelengths.The high slope characteristics of the EIT-like effect enabled a higher quality factor and sensitivity.The transmission principle of the structure was analyzed using the transmission matrix method,and the transmission spectrum and mode field distribution were simulated using the finite-difference time-domain(FDTD)method,and the device structure parameters were adjusted for optimization.Simulation results show that the proposed structure achieves an EIT-like effect with a quality factor of 59267.5.In the analysis of refractive index sensing characteristics,the structure exhibits a sensitivity of 408.57 nm/RIU and a detection limit of 6.23×10^(-5) RIU.Therefore,the proposed structure achieved both a high quality factor and refractive index sensitivity,demonstrating excellent sensing performance for applications in environmental monitoring,biomedical fields,and other areas with broad market potential.
基金supported by Lanzhou Science and Technology Plan Project(No.2023-3-104)Gansu Province Higher Education Industry Support Plan Project(No.2023CYZC-40)Gansu Province Excellent Graduate“Innovation Star”Program(No.2023CXZX-546)。
文摘To improve the accuracy of indoor localization methods with channel state information(CSI)images,a localization method that used CSI images from selected multiple access points(APs)was proposed.The method had an off-line phase and an on-line phase.In the off-line phase,three APs were selected from the four APs in the localization area based on the received signal strength indication(RSSI).Next,CSI data was collected from the three selected APs using a commercial Intel 5300 network interface card.A single-channel subimage was constructed for each selected AP by combining the amplitude information from different antennas and the phase difference information between neighboring antennas.These sub-images were then merged to form a three-channel RGB image,which was subsequently fed into the convolutional neural network(CNN)for training.The CNN model was saved upon completion of training.In the on-line phase,the CSI data from the target device was collected,converted into images using the same process as in the off-line phase,and fed into the well-trained CNN model.Finally,the real position of the target device was estimated using a weighted centroid algorithm based on the model’s output probabilities.The proposed method was validated in indoor environments using two datasets,achieving good localization accuracy.
基金supported by Anhui Province Key Research and Development Program(No.2022107020012).
文摘In camera calibration,accurate estimation of homography matrix between the world coordinates of the calibration board and its image coordinates is a key step in high-precision calibration of intrinsic camera parameters.The existing homography matrix estimation methods have problems such as dependence on thresholds,low computational efficiency,and initial model or sorting quality affecting results.In this paper,a homography matrix estimation method based on adaptive genetic algorithm was proposed.Firstly,a new circular grid calibration board was designed and the strategy of first sampling of data sets was optimized.Secondly,a mathematical model for the estimated homography matrix was established according to the adaptive genetic algorithm.Thereby the optimal homography matrix between the calibration board and its image was obtained.Finally,the intrinsic camera parameters were calculated based on Zhang’s calibration method.The experimental results show that compared with the results of three traditional estimation methods RANSAC,PROSAC,and LMEDS,the reprojection error of the images by our estimation method is reduced by about 4.11%-7.85%,11.94%-16.91%,and 10.19%-17.82%,respectively;and the average running time of the algorithm decreases by about 25.85%-37.47%,11.99%-22.71%,and 46.50%-53.35%,respectively.In addition,the homography matrix estimation method in this paper was applied to camera calibration.The results show that compared with the traditional estimation method,the average accuracy of the camera during the calibration process increases by about 5.48%,15.06%,and 11.47%,respectively;and the average calibration efficiency of the camera is improved by about 10.13%,5.71%,and 14.26%,respectively.The homography matrix estimation method proposed in this paper not only obtained reliable results,but also had certain value and significance in improving the estimation accuracy and calculation efficiency in camera calibration.
基金supported by Gansu Natural Science Foundation Programme(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Education,Science and Technology Innovation and Industry(No.2021CYZC-04)。
文摘Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical settings.These methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality combinations.Additionally,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training data.This work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing modalities.The proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”data.Co-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing modalities.The model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation task.EACNet was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance respectively.Notably,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing methods.The analysis suggests that the ensemble approach offers potential benefits,and the adversarial co-training contributes to the increased robustness and accuracy of EACNet for brain tumor segmentation of MRI scans with missing modalities.The experimental results show that EACNet has promising results for the task of brain tumor segmentation of MRI scans with missing modalities and is a better candidate for real-world clinical applications.
基金supported by Fundamental Research Program of Shanxi Province(Nos.202203021211088,202403021212254,202403021221109)Graduate Research Innovation Project in Shanxi Province(No.2024KY616).
文摘Data collected in fields such as cybersecurity and biomedicine often encounter high dimensionality and class imbalance.To address the problem of low classification accuracy for minority class samples arising from numerous irrelevant and redundant features in high-dimensional imbalanced data,we proposed a novel feature selection method named AMF-SGSK based on adaptive multi-filter and subspace-based gaining sharing knowledge.Firstly,the balanced dataset was obtained by random under-sampling.Secondly,combining the feature importance score with the AUC score for each filter method,we proposed a concept called feature hardness to judge the importance of feature,which could adaptively select the essential features.Finally,the optimal feature subset was obtained by gaining sharing knowledge in multiple subspaces.This approach effectively achieved dimensionality reduction for high-dimensional imbalanced data.The experiment results on 30 benchmark imbalanced datasets showed that AMF-SGSK performed better than other eight commonly used algorithms including BGWO and IG-SSO in terms of F1-score,AUC,and G-mean.The mean values of F1-score,AUC,and Gmean for AMF-SGSK are 0.950,0.967,and 0.965,respectively,achieving the highest among all algorithms.And the mean value of Gmean is higher than those of IG-PSO,ReliefF-GWO,and BGOA by 3.72%,11.12%,and 20.06%,respectively.Furthermore,the selected feature ratio is below 0.01 across the selected ten datasets,further demonstrating the proposed method’s overall superiority over competing approaches.AMF-SGSK could adaptively remove irrelevant and redundant features and effectively improve the classification accuracy of high-dimensional imbalanced data,providing scientific and technological references for practical applications.
基金supported by Shaanxi Province Key Research and Development Plan(No.2023-YBGY-386)Shaanxi Province Key Research and Development Plan(No.2022-JBGS-07).
文摘In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GADF)of multi-channel signal fusion and multi-scale attention residual network(MA-ResNet)was proposed.Firstly,the multi-channel vibration signals were subdivided into various frequency bands using wavelet packet decomposition,and the sensitive channels were selected for signal fusion by doing correlation analysis between the signals of various frequency bands and the surface roughness.Then the fused signals were converted into pictures using GADF image encoding.Finally,the pictures were inputted into the residual network model combining the parallel dilation convolution and attention module for training and verifying the effectiveness of the model performance.The proposed method has a root mean square error of 0.0187,a mean absolute error of 0.0143,and a coefficient of determination of 0.8694 in predicting the surface roughness,which is close to the actual value.Therefore,the proposed method had good engineering significance for high-precision prediction and was conducive to on-line monitoring of surface quality during workpiece processing.
