Simulation Experiments Research Articles

Positioning Improvement for Spaceborne Laser Footprint Based on Precisely Terrain Data

Abstract. Spaceborne laser altimetry represents a novel active remote sensing technology applicable to earth observation, which together with imaging spectroscopy and synthetic aperture radar as a core technology for data acquisition in the earth observation systems. However, the accuracy of horizontal positioning for laser footprints from spaceborne laser altimeters declines due to various factors such as the changes in the orbital environment and the deterioration of performance. Moreover, the limited frequency of in-orbit calibration of the spaceborne laser altimeters and the non-disclosure of calibration parameters mean that users are heavily reliant on positioning accuracy of the altimetry data provided. To address this issue, a new algorithm is proposed in this study for enhancing the accuracy of horizontal positioning for laser footprints in the absence of satellite altimeter pointing and ranging parameters. In this algorithm, high-resolution DSM is taken as the reference terrain data to take advantage of the higher precision in elevation over horizontal positioning of the laser footprints. By adjusting the horizontal position of the laser footprint within a small area, the algorithm achieves the optimal alignment of laser elevation data with the reference terrain. Then, the resulting shift in the horizontal position of the laser footprints is referenced to correct their horizontal positioning during that period. Based on the high-accuracy DSM data collected from the Xinjiang autonomous region in China and the data collected by the GF-7 satellite, simulation experiments are performed in this study to analyze and validate the proposed algorithm. According to the experimental results, the horizontal accuracy of the laser footprints improves significantly from 12.56 m to 3.11 m after optimization by the proposed method. With the elimination of 9.45 m horizontal error, accuracy is improved by 75.23%. This method is demonstrated as effective in further optimizing the horizontal position of laser altimetry data products in the absence of altimeter parameters and original data, which promotes the application of spaceborne laser data.

Traveling-wave-based Fault Location using Time Delays between Modal Components in Electrical Distribution Systems

Background: The distribution feeders usually include many laterals, too many sensors need to be installed to locate the fault positions in electrical distribution systems by using the traditional double-ended traveling-wave-based fault-location methods Objective: Fault location based on the time delays between the moments of the first wavefronts of zero-mode voltages and that of aerial-mode voltages arriving at one end of the distribution feeder. Methods: Large decomposition level in wavelet transformation is adopted in this paper to obtain the zero-mode velocity. Results: Both theoretical research and simulation experiments have proved that the proposed fault location method can greatly improve the accuracy of the fault location in the electrical distribution systems without many sensors. Conclusion: The proposed fault location method can provide one feasible way to locate the faults in the electrical distribution systems.

A simple method of shape transformation using the modified Gray–Scott model

In this paper, based on the original Gray–Scott model, we propose a modified Gray–Scott model by introducing a target term into the reaction–diffusion equations. We apply this modified model in the context of shape transformation problems. To expedite the process from the source shape to the target shape, we utilize the explicit Euler method to solve our proposed modified Gray–Scott model, making our approach simpler and more efficient. To validate the feasibility of our method, we conduct simulation experiments in both two-dimensional (2D) and three-dimensional (3D) spaces. By progressing through experiments of increasing complexity, we demonstrate the natural effectiveness of our simulation method as a viable approach for shape transformation. To demonstrate the efficiency of the method, we provide the runtime consumed by the simulated shape transformation experiment. Additionally, to assess the correspondence between the ground truth values of the target shape and the simulated results, we calculate the corresponding area change rate and volume change rate in 2D and 3D spaces to prove that our proposed method can effectively transform into the target shape.

Non-Destructive Assessment of Stone Heritage Weathering Types Based on Machine Learning Method Using Hyperspectral Data

Abstract. Stone cultural heritage is exposed to various environments, resulting in a diverse range of weathering types. The identification of these weathering types is vital for targeted conservation efforts. In this paper, a weathering type classification method based on hyperspectral imaging technology is proposed. Firstly, fresh sandstones are collected from Yungang Grottoes to carry out the simulated weathering experiments, including freeze-thaw cycles and wet-dry cycles with acid, alkali and salt solutions. Subsequently, the hyperspectral imaging system was used to collect the visible-near-infrared (VNIR) and short-wave infrared (SWIR) images of the sandstone samples with different weathering types and degrees. The surface spectral reflectance of sandstone samples with different weathering types were used as training data, with weathering types serving as the labels. Support vector machine (SVM), K-nearest neighbour (KNN), linear discriminant analysis (LDA) and random forest (RF) were used to establish weathering type classification models. The results show that the SVM model and LDA model based on both VNIR and SWIR spectra exhibit outstanding performance, with a best accuracy of 0.994. The framework proposed in this paper facilitates rapid and non-contact assessment of the weathering types of the superficial layers of stone cultural heritage, thereby supporting more targeted conservation work.

Crashworthiness Study of Functional Gradient Lattice-Reinforced Thin-Walled Tubes under Impact Loading.

Creating lightweight and impact-resistant box structures has been an enduring pursuit among researchers. A new energy-absorbing structure consisting of a bionic gradient lattice-enhanced thin-walled tube is presented in this article. The gradient lattice and thin-walled tube were prepared using selective laser melting (SLM) and wire-cutting techniques, respectively. To analyze the effects of gradient pattern, mass ratio, diameter range and impact speed on structural crashworthiness, low-speed impact at 4 m/s and finite element simulation experiments were conducted. The study demonstrates that the design of inward radial gradient lattice-reinforced thin-walled tubes can effectively enhance structure's energy-absorption efficiency and provide a more stable mode of deformation. It also shows a 17.44% specific energy-absorption advantage over the uniformly lattice-reinforced thin-walled tubes, with no significant overall gain in peak crushing force. A complex scale evaluation method was used to determine the optimum structure and the structure type with the best crashworthiness was found to be a gradient lattice-filled tube with a thickness of 0.9 mm and a slope index of 10. The gradient lattice-reinforced thin-walled tube suggested in this investigation offers guidance for designing a more efficient thin-walled energy-absorption structure.

Application of sulfidated nano zero-valent iron to enhance fluoranthene degradation by Fe(III) activated sodium percarbonate process in aqueous and soil media

Iron sludge generation poses a challenge to the application of Fenton/Fenton-like processes in wastewater treatment. In this study, sulfidated nano zero-valent iron (S-nZVI) was introduced to enhance the activation of sodium percarbonate (SPC) by Fe(III), mitigating the generation of iron sludge by promoting the Fe(III)/Fe(II) cycle. The proposed technique efficiently removed 94.3 % fluoranthene (FLT) in which HO• acted as the major reactive oxygen species responsible for FLT degradation. Toxicity analysis revealed phthalic acid and 1-phenylnaphthalene as FLT degradation intermediates which finally converted to CO2 and H2O. Similarly, the luminous bacteria experiment also showed that the FLT degradation process was environmentally benign. The support of S-nZVI to the Fe(III)/Fe(II) cycle was determined by analyzing the morphology and characterization of S-nZVI. The removal of FLT reached more than 80 % at pH ranging from 3.0 to 10.0, and the detrimental effects of low concentrations of Cl− were mitigated. SPC/S-nZVI/Fe(III) process showed good removal of FLT (90 %) in both real groundwater and river simulation experiments. Furthermore, SPC/S-nZVI/Fe(III) process was successfully applied in soil slurry media with around 90 % FLT degradation in 12 h. The influence of the soil/water ratio on FLT removal was found to be negligible. SPC/S-nZVI/Fe(III) process was superior for the removal of mixed FLT, naphthalene, and phenanthrene contamination. In conclusion, the SPC/S-nZVI/Fe(III) system exhibits enormous potential in the remediation of polycyclic aromatic hydrocarbons (PAHs) contaminated sites.

An Improved Golden Jackal Optimization Algorithm Based on Mixed Strategies

In an effort to overcome the problems with typical optimization algorithms’ slow convergence and tendency to settle on a local optimal solution, an improved golden jackal optimization technique is proposed. Initially, the development mechanism is enhanced to update the prey’s location, addressing the limitation of just relying on local search in the later stages of the algorithm. This ensures a more balanced approach to both algorithmic development and exploration. Furthermore, incorporating the instinct of evading natural predators enhances both the effectiveness and precision of the optimization process. Then, cross-mutation enhances population variety and facilitates escaping from local optima. Finally, the crossbar strategy is implemented to change both the individual and global optimal solutions of the population. This technique aims to decrease blind spots, enhance population variety, improve solution accuracy, and accelerate convergence speed. A total of 20 benchmark functions are employed for the purpose of comparing different techniques. The enhanced algorithm’s performance is evaluated using the CEC2017 test function, and the results are assessed using the rank-sum test. Ultimately, three conventional practical engineering simulation experiments are conducted to evaluate the suitability of IWKGJO for engineering issues. The results obtained demonstrate the beneficial effects of the altered methodology and illustrate that the expanded golden jackal optimization algorithm has superior convergence accuracy and a faster convergence rate.

Comparison of some Bayesian estimation methods for type-I generalized extreme value distribution with simulation

The Weibull distribution is considered one of the Type-I Generalized Extreme Value (GEV) distribution, and it plays a crucial role in modeling extreme events in various fields, such as hydrology, finance, and environmental sciences. Bayesian methods play a strong, decisive role in estimating the parameters of the GEV distribution due to their ability to incorporate prior knowledge and handle small sample sizes effectively. In this research, we compare several shrinkage Bayesian estimation methods based on the squared error and the linear exponential loss functions. They were adopted and compared by the Monte Carlo simulation method. The performance of these methods is assessed based on their accuracy and computational efficiency in estimating the scale parameter of the Weibull distribution. To evaluate their performance, we generate simulated datasets with different sample sizes and varying parameter values. A technique for pre-estimation shrinkage is suggested to enhance the precision of estimation. Simulation experiments proved that the Bayesian shrinkage estimator and shrinkage pre-estimation under the squared loss function method are better than the other methods because they give the least mean square error. Overall, our findings highlight the advantages of shrinkage Bayesian estimation methods for the proposed distribution. Researchers and practitioners in fields reliant on extreme value analysis can benefit from these findings when selecting appropriate Bayesian estimation techniques for modeling extreme events accurately and efficiently.

A resilience-driven two-stage operational chain optimization model for unmanned weapon system-of-systems under limited resource environments

Enhancing the battlefield resilience of unmanned weapon system-of-systems (UWSoS) through structural reconstruction requires scheduling additional physical resources. However, they are scarce in limited resource environments. To address the challenge of resource constraints, this paper focuses on improving the resilience of UWSoS by optimizing the operational chain of tasks after a disruption. First, a task-oriented resilience metric is proposed to characterize the impact of operational chain variations on UWSoS resilience. Based on this, a two-stage operational chain optimization model for UWSoS under limited resource environments is established, which considers the optimization actions of the edge node and rear command node in different resilience phases after the interruption for resilience enhancement. Finally, extensive simulation experiments validate the effectiveness and superiority of the proposed model. This work can support decision-makers in developing new task plans in disruption scenarios and serve as a transition approach to enhance UWSoS resilience.

Road dynamic landscape design and simulation based on fuzzy clustering algorithm

Against the backdrop of rapid economic growth and continuous expansion of road networks in China, the planning, design, greening, and beautification of roads at all levels have entered a systematic implementation phase. Particularly noteworthy is the emergence of dynamic road landscape design as a major focus in the research on urban road beautification in the new era. This paper proposes a road dynamic landscape optimization design scheme based on the fuzzy clustering algorithm. It analyzes the primary elements constituting dynamic road landscapes and summarizes the fundamental principles for designing such landscapes. The fuzzy clustering method is employed to classify different road landscapes, optimizing the design system. Through simulation experiments, the effectiveness of the proposed scheme is validated, with results indicating an 8.34% higher accuracy compared to traditional methods. The study suggests that such road design not only meets basic traffic needs but also achieves greening and beautification effects while catering to users visual and psychological needs, showcasing the unique cultural, historical, and lifestyle characteristics of the city. Furthermore, this design fosters harmonious integration between roads and their ancillary structures and surrounding buildings, significantly improving the citys landscape and living environment.

Calibration method for binocular vision system with large field of view based on small target image splicing

In vision measurement, camera calibration has a significant impact on measurement precision. The classical target-based calibration methods require the target to occupy more than one-third of the field of view. A small-size target that does not meet the requirements results in poor calibration accuracy, while an appropriate large-size target is difficult to manufacture and inconvenient to operate. In view of the above problem, we propose a flexible and accurate calibration method based on small target image splicing to calibrate the binocular vision system with a large field of view. The spliced images and virtual large targets are constructed to extend the target size, providing better flexibility for calibration. Moreover, an optimization objective function integrating two constraints in the imaging plane and measurement space is presented to improve the calibration accuracy during the parameter optimization process. The simulation experiments and actual experiments are carried out to test the performance of the proposed method. The results demonstrate that the calibration accuracy of the proposed method using a small target is equivalent to that of Zhang’s method using a large target. Additionally, when using a same-size target, the parameter error of the proposed method is less than that of Zhang’s method, and the proposed method reduces the distance measurement error from 1.169 mm to 0.208 mm compared to Zhang’s method.

Path tracking with personalized handling stability constraints matched to driving styles

In the path-tracking control process, drivers have different expectations of the lateral response of vehicles. To meet drivers’ expectations of handling stability, this paper proposes a model predictive control (MPC)-based path-tracking controller with personalized handling stability constraints matched to driving style. Firstly, the categories of driving styles are obtained by applying the K-Means algorithm to the collected driving data. Then the sideslip angle-longitudinal velocity map is constructed based on the nonlinear dynamics model of the vehicle to generate the front-wheel steering angle constraints that are matched with the maximum sideslip of the vehicle expected by drivers of different styles. After that, an MPC-based path-tracking controller has been built, and the front-wheel steering angle is incorporated into the MPC controller. Furthermore, compared to the strategy of directly using sideslip angle constraints for handling stability control, this approach avoids introducing additional constraint variables, leading to improved real-time performance. Simulation experiments are conducted to compare the dynamic vehicle responses between the handling stability control that takes into account the driving style and the control system that does not consider the driving style. In addition, the subjective evaluation is conducted to verify the proposed path-tracking control method that considers the stability constraints of driving style. The evaluation results show that the proposed method can obtain better subjective evaluation results than a path-tracking controller that does not consider the driving style. Finally, through the hardware-in-the-loop experiments, the real-time computational capability of the proposed controller is verified.

L-PCM: Localization and Point Cloud Registration-Based Method for Pose Calibration of Mobile Robots

The autonomous navigation of mobile robots contains three parts: map building, global localization, and path planning. Precise pose data directly affect the accuracy of global localization. However, the cumulative error problems of sensors and various estimation strategies cause the pose to have a large gap in data accuracy. To address these problems, this paper proposes a pose calibration method based on localization and point cloud registration, which is called L-PCM. Firstly, the method obtains the odometer and IMU (inertial measurement unit) data through the sensors mounted on the mobile robot and uses the UKF (unscented Kalman filter) algorithm to filter and fuse the odometer data and IMU data to obtain the estimated pose of the mobile robot. Secondly, the AMCL (adaptive Monte Carlo localization) is improved by combining the UKF fusion model of the IMU and odometer to obtain the modified global initial pose of the mobile robot. Finally, PL-ICP (point to line-iterative closest point) point cloud registration is used to calibrate the modified global initial pose to obtain the global pose of the mobile robot. Through simulation experiments, it is verified that the UKF fusion algorithm can reduce the influence of cumulative errors and the improved AMCL algorithm can optimize the pose trajectory. The average value of the position error is about 0.0447 m, and the average value of the angle error is stabilized at about 0.0049 degrees. Meanwhile, it has been verified that the L-PCM is significantly better than the existing AMCL algorithm, with a position error of about 0.01726 m and an average angle error of about 0.00302 degrees, effectively improving the accuracy of the pose.

Application of non parametric Bayesian methods in high dimensional data

With the development of technology and the widespread collection of data, high-dimensional data analysis has become a research hotspot in many fields. Traditional parameter methods often face problems such as dimensional disasters in high-dimensional data analysis. Non parametric methods have broad application prospects in high-dimensional data because they do not rely on specific parameter distribution assumptions. The Bayesian rule is more suitable for dealing with noise and outliers in high-dimensional data because it takes uncertainty into account. Therefore, it is of great significance to combine non parametric methods with Bayesian methods for application research in high-dimensional data analysis. In this paper, the nonparametric Bayesian method was applied to the analysis of high-dimensional data, and the Dirichlet process Mixture model was used to cluster high-dimensional data. The regression analysis of high-dimensional data was carried out through the prediction model of nonparametric Bayesian regression. In this paper, the nonparametric Bayesian method based on Bayesian sparse linear model was used for feature selection of high-dimensional data. In order to determine the superiority of nonparametric Bayesian methods in high-dimensional data analysis, this paper conducted experiments on nonparametric Bayesian methods and traditional parametric methods in high-dimensional data analysis from five aspects of cluster analysis, classification analysis, regression analysis, feature selection and anomaly detection, and evaluated them through multiple indicators. This article explored the application of non parametric Bayesian methods in high-dimensional data analysis from these aspects through simulation experiments. The experimental results show that the clustering accuracy of the non parametric Bayesian clustering algorithm was 0.93, and the accuracy of the non parametric Bayesian classification algorithm was between 0.93 and 0.99; the coefficient of determination of nonparametric Bayesian regression algorithm was 0.98; the F1 values of non parametric Bayesian methods in anomaly detection ranged from 0.86 to 0.91, which was superior to traditional methods. Non parametric Bayesian methods have broad application prospects in high-dimensional data analysis, and can be applied in multiple fields such as clustering, classification, regression, etc.

Mean squared error bound for learning-based multi-target localization and its application in learning network architecture design

The learning-based method has been widely applied in target localization. However, the performance of learning-based localization is mostly validated by simulation experiments and lacks theoretical analysis. In this paper, we investigate the performance of learning-based multi-target localization in a multiple-input multiple-output (MIMO) radar system with widely separated antennas. A mean squared error bound (MSEB) for learning-based multi-target localization is derived, which contains all the system parameters, including radar-related parameters and learning network-related parameters. Therefore, the MSEB can be employed as the metric to optimize any parameter of interest, such as those associated with the learning network architecture, which is usually determined with the trial-and-error method by minimizing the training loss. Leveraging the MSEB, we can design the optimal learning network architecture which maximizes the testing performance and this optimal architecture can be obtained before training. Numerical results are presented to verify the correctness of the MSEB and effectiveness of the MSEB-based learning network architecture design method.

Enhanced PET image reconstruction utilizing morphological filtering and MLEM algorithm

Positron Emission Tomography (PET) image reconstruction remains a pivotal area in PET technology, critically influencing clinical diagnostic outcomes. Addressing the need for enhanced image quality, this study introduces a novel algorithm for PET image reconstruction. This algorithm integrates a penalty mechanism, morphological filtering, and the Maximum Likelihood Expectation Maximization (MLEM) algorithm, aiming to improve reconstructed image quality significantly. The operational process of the algorithm within each iteration encompasses two primary phases. Initially, image reconstruction is accomplished via the MLEM algorithm, followed by the application of a morphological filter to attenuate noise in the reconstructed image. Simulation experiments demonstrate that this algorithm effectively mitigates noise while preserving crucial details, such as image edges. Notably, this method presents the dual benefits of straightforward parameter configuration and ease of implementation. The results indicate a substantial enhancement in noise suppression and fine structure preservation in the reconstructed images, marking a significant advancement in PET image reconstruction techniques.

Weighted three-way conflict analysis in multi-attribute decision-making perspective

In real life, multiple issues may have different weights in leading to conflicts. Some of the existing conflict analysis literature related to weight does not involve an explicit weight method, and some use common methods such as entropy weight method. This paper aims to design a reasonable weighting method for the inherent characteristics of conflict analysis. The main motivation is that the issues getting vast majority of support (or opposition) are assumed to be more likely to cause intense conflicts. Firstly, a novel weighting method using N-bounded symmetric concave reciprocal function is brought in. Some properties of the method such as duality, objectivity and symmetry are discussed. Then, by embedding the weights into the existing distance function a weighted three-way conflict analysis model is proposed. Next the thresholds of conflict, alliance and neutrality relations are given by decision-theoretic rough set theory. In addition, as a main characteristic of the model, the conflict distance between any two agents is determined by the overall conflict table rather than their own. Finally, the model of this paper is compared with the existing conflict analysis weight model. At the same time, a comparative simulation experiment was carried out on the weight change and the number of maximal coalitions. The new weighted conflict model proposed in this paper can effectively compensate for the limitations of existing weighted models, especially in three-valued information systems and multi-valued information systems. It can also theoretically expand the field of three-way conflict analysis.

DFUSNN: zero-shot dual-domain fusion unsupervised neural network for parallel MRI reconstruction

Objective. Recently, deep learning models have been used to reconstruct parallel magnetic resonance (MR) images from undersampled k-space data. However, most existing approaches depend on large databases of fully sampled MR data for training, which can be challenging or sometimes infeasible to acquire in certain scenarios. The goal is to develop an effective alternative for improved reconstruction quality that does not rely on external training datasets. Approach. We introduce a novel zero-shot dual-domain fusion unsupervised neural network (DFUSNN) for parallel MR imaging reconstruction without any external training datasets. We employ the Noise2Noise (N2N) network for the reconstruction in the k-space domain, integrate phase and coil sensitivity smoothness priors into the k-space N2N network, and use an early stopping criterion to prevent overfitting. Additionally, we propose a dual-domain fusion method based on Bayesian optimization to enhance reconstruction quality efficiently. Results. Simulation experiments conducted on three datasets with different undersampling patterns showed that the DFUSNN outperforms all other competing unsupervised methods and the one-shot Hankel-k-space generative model (HKGM). The DFUSNN also achieves comparable results to the supervised Deep-SLR method. Significance. The novel DFUSNN model offers a viable solution for reconstructing high-quality MR images without the need for external training datasets, thereby overcoming a major hurdle in scenarios where acquiring fully sampled MR data is difficult.

Potential probiotic characteristics and genomic analysis of a new folate-producing lactic acid bacteria Lactiplantibacillus plantarum ZFM55.

Folate is crucial for maintaining health, but humans are unable to synthesize folate and need to obtain it from food. Lactiplantibacillus plantarum can produce the necessary vitamin B for the human body, including folate. Whole genome sequencing technology can clarify the physiological characteristics of folate production in Lactiplantibacillus plantarum. In order to explore new Lactiplantibacillus plantarum that produce folate, the folate production and probiotic characteristics of Lactiplantibacillus plantarum ZFM55 isolated from infant feces were investigated, and whole genome sequencing was performed. The folate synthesis ability of Lactiplantibacillus plantarum ZFM55 were measured, and its total folate production was 299.72 ± 28.81 ng mL-1. Subsequently, its probiotic properties were explored. The antibacterial test showed that its inhibition zone diameter against Staphylococcus aureus and Salmonella typhimurium was 15.5 ± 0.82 mm and 13.88 ± 0.98 mm, respectively. The tolerance test results indicated that it maintained good activity in simulated gastrointestinal tract and bile salt environments. In vitro intestinal simulation experiments had confirmed that Lactiplantibacillus plantarum ZFM55 can increase the abundance of beneficial bacteria such as Bifidobacteria in the intestine and inhibit the growth of harmful bacteria such as Escherichia_Shigella. Genomic sequencing indicated that the genetic material of Lactiplantibacillus plantarum ZFM55 contains one chromosome and three plasmids, and it has 20 genes related to folate synthesis, which explains its ability to produce folate. This study reports a new potential probiotic that produces folate, and provides ideas for exploring probiotics with specific probiotic characteristics. © 2024 Society of Chemical Industry.

Fault diagnosis of drone motors driven by current signal data with few samples

Multi rotor unmanned aerial vehicles (UAVs) are extensively utilized across various domains, and the motor constitutes a pivotal element in the UAV power system. The majority of UAV failures and crashes stem from motor malfunctions, underscoring the imperative need for comprehensive research on fault diagnosis in UAV motors to ensure the stable and reliable execution of flight tasks. This study focuses on quadrotor UAVs as the research subject and devises targeted fault simulation experiments based on the structural features and operational characteristics of the DC brushless motor used in quadrotor UAVs, specifically examining the stator, rotor, and bearings. To address challenges related to the UAV’s own loads, limited space for redundant parts, and the high cost and difficulty associated with installing sensors for traditional fault diagnostic signals such as vibration and temperature, this study opts to use current signals as a substitute. This approach resolves the issue of challenging data collection for UAVs and investigates a current signal based fault diagnosis method for UAV motors. Lastly, in response to the limited training samples available for fault data due to the UAV’s highly sensitive characteristics regarding the health status of its components and flight stability, traditional machine learning and deep learning methods encounter difficulties in identifying representative features with a small number of training samples, leading to the risk of overfitting and reduced model accuracy in fault diagnosis. To overcome this challenge, we propose a hybrid neural network fault diagnosis model that incorporates a width learning system and a convolutional neural network (CNN). The width learning system eliminates temporal characteristics from the original current signal, capturing more comprehensive and representative sample features in the width feature space. Subsequently, the CNN is employed for feature extraction and classification tasks. In empirical small sample fault diagnosis experiments using current signal data for UAV motors, our proposed model outperforms other models used for comparison.