Abstract To address the challenges of weak feature representation, background interference, and missed small-target detections in identifying subtle surface damages on highly reflective refrigerator doors during production, this paper proposes a lightweight detection algorithm, YOLOv8-FD, based on the YOLOv8n architecture. First, a lightweight GhostConv module replaces standard convolution layers within the backbone network. This is integrated with a modified lightweight CBAM attention mechanism (L-CBAM) to form the C2f-GC module, significantly enhancing fine-grained feature extraction under complex backgrounds while minimising parametric overhead. Furthermore, the SPPELAN module is incorporated to expand the receptive field and aggregate multi-scale features without compromising the lightweight design. To adapt to the geometric heterogeneity of defects, a novel Static-Asymmetry IoU (SAIoU) loss function based on a subtraction penalty mechanism is proposed, which optimises bounding box regression for irregular and asymmetric targets. Experimental evaluations on a strictly partitioned, independent hold-out test set demonstrate that YOLOv8-FD operates with only 5.3 M parameters and 6.0 GFLOPs of computational complexity, achieving reductions of 15.9% and 26.8%, respectively, compared to the baseline YOLOv8n model. Concurrently, it improves the mean average precision (mAP50) by 1.33 percentage points and the F 1-score by 1.10 percentage points. These quantitative results empirically validate the efficacy of YOLOv8-FD in resolving fine-grained damage detection bottlenecks under resource-constrained edge-device scenarios.

The authors propose a novel fault diagnosis method to address the challenges of complex fault feature extraction and low diagnostic efficiency caused by the intricate and variable frequency components of vibration signals and the mismatch between the sampling frequency and the actual bearing vibration under variable-speed conditions in printing equipment bearings. This method is based on improved Least Squares Support Vector Machines (LSSVMs) with Kernel Principal Component Analysis (KPCA) for dimension reduction and Deep Belief Networks (DBNs) for variable-speed feature mining. Time-domain feature values of the vibration signal were first extracted to construct a feature set, and the KPCA algorithm was applied for dimensionality reduction. Dimensionality reduction features were used as the input of the DBN to extract higher-order features and enhance the discriminant ability. Finally, the optimized features were classified and diagnosed using the LSSVM model, enabling the extraction of nonlinear complex features under variable-speed conditions and improving diagnostic efficiency. In addition, the lightweight design that combines KPCA dimensionality reduction, DBN deep feature extraction, and improved LSSVM classification effectively addresses the issue of low efficiency in feature extraction and diagnosis caused by the complex and variable vibration signals under variable-speed conditions. Experiments were conducted using bearing vibration data collected from a simulated test bench, covering five fault types. The bearing acceleration vibration signals were collected within 0-5 sand 0-10 sin the speed range of 0-1800 r/min. The proposed model achieved diagnostic accuracies of 98.33% and 98.8889% under these two conditions, respectively, verifying its effectiveness and superiority under complex operating conditions.

Propelled by the "dual-carbon" strategy, green and intelligent ports are rapidly advancing toward low-carbon and intelligent development. However, the large-scale incorporation of renewable energy and the extensive electrification of transport equipment have substantially heightened system volatility and scheduling complexity. To address the challenges associated with multi-energy coupling and economic operation in medium and large ports, a hierarchical collaborative optimization scheduling strategy is proposed. The upper layer employs an improved Bio-enhanced Dung Beetle Optimization (BDBO) algorithm for parameter optimization and carbon-cost minimization. Meanwhile, the lower layer establishes a rolling time-series control mechanism grounded in Adaptive Dynamic Hierarchical Decoupling Planning (ADHDP), thereby constituting an integrated BDBO-ADHDP dual-agent system. Simulation results across four seasonal scenarios demonstrate that the proposed methodology outperforms DQN, PSO, GA, ACO, and DBO algorithms in reducing grid power purchases, enhancing renewable energy utilization, mitigating curtailment, and lowering operational costs. Moreover, it achieves faster convergence, superior robustness, and effective carbon-emission control. This study substantiates the efficacy of the proposed strategy within green port integrated energy systems and highlights its potential for broader application in other multi-energy coupled systems.

With the development of data science and artificial intelligence technology, multi-modal data fusion methods have demonstrated significant advantages in rice quality assessment and grading classification. Traditional grain grading methods rely on manual screening, which is inefficient and prone to human error, and typically depend on a single data source, such as images or sensor data, making it difficult to comprehensively reflect grain quality. To improve grading accuracy and automation, this study combines image data with gas data to explore the application of multi-modal data fusion methods in rice grading classification. By integrating image and gas data features, this study developed an efficient multimodal deep learning model, Vit-Resnet18-A, by connecting ViT and Resnet18. The results indicate that multimodal models based on the fusion of image and sensor signal data exhibit higher accuracy and robustness in rice quality grading, particularly when dealing with diverse rice varieties and complex quality standards. Through the improved Vit-Resnet18-A-DG model, the accuracy and efficiency of rice grading were further enhanced, achieving an accuracy rate of 97.98 %, precision of 96.03 %, recall rate of 95.97 %, and F1-score of 95.96 %. This study provides robust technical support for intelligent agricultural production and offers new insights into rice quality control.

To mitigate rotor vibrations in magnetic bearing systems arising from mass imbalance, this study proposes a novel suppression strategy that integrates the crested porcupine optimizer (CPO) with an enhanced linear active disturbance rejection control (ELADRC) framework. The approach introduces a disturbance estimation and compensation scheme based on a linear extended state observer (LESO), wherein both the LESO bandwidth ω0 and the LADRC controller parameter ωc are adaptively tuned using the CPO algorithm to enable decoupled control and real-time disturbance rejection in complex multi-degree-of-freedom (DOF) systems. Drawing inspiration from the crested porcupine’s layered defensive behavior, the CPO algorithm constructs a state-space model incorporating rotor displacement, rotational speed, and control current, while leveraging a reward function that balances vibration suppression performance against control energy consumption. The optimized parameters guide a real-time LESO-based compensation model, achieving accurate disturbance cancelation via amplitude-phase coordination between the generated electromagnetic force and the total disturbance. Concurrently, the LADRC feedback structure adjusts the system’s stiffness and damping matrices to improve closed-loop robustness under time-varying operating conditions. Simulation studies over a wide speed range (0~45,000 rpm) reveal that the proposed CPO-ELADRC scheme significantly outperforms conventional control methods: it shortens regulation time by 66.7% and reduces peak displacement by 86.8% under step disturbances, while achieving a 79.8% improvement in adjustment speed and an 86.4% reduction in peak control current under sinusoidal excitation. Overall, the strategy offers enhanced vibration attenuation, prevents current saturation, and improves dynamic stability across diverse operating scenarios.

With the rapid development of logistics automation and the digital transformation of the home appliance industry, damage to heavy appliance packaging cartons during storage and transportation has become increasingly frequent, adversely affecting product image and delivery quality. Common surface defects such as scratches, holes, and wet stains can easily lead to disputes and economic losses. Therefore, a highly efficient, automated, and terminaldeployable intelligent detection algorithm is urgently required to achieve accurate identification and recording of packaging damages. To address the limitations of YOLOv8n in carton surface damage detection-specifically, its constrained accuracy and the frequent occurrence of missed and false detections-the authors propose an age). The proposed model enhances detection performance while maintaining high efficiency through three key optimizations: introducing a large-kernel receptive field attention module (SPPF_LSKA) in the backbone to improve global context modeling; adopting the and incorporating a multi-path coordinate attention (MPCA) mechanism to strengthen key region perception. Experiments conducted on a self-constructed dataset containing three categories-scratches, holes, and wet stains-demonstrate that YOLOv8-PD achieves improvements of 1.4%, 0.9%, and 1.4% in mAP@0.5, Precision, and Recall, respectively, compared with the baseline YOLOv8n. These results validate the proposed method's superior accuracy and realtime performance in industrial application scenarios.

In Roll-to-Roll (R2R) precision coating systems, the unwinding section is a critical component that determines the stability of the entire tension control system, which primarily comprises unwinding and traction units. To address the limitations of conventional tension control methods, such as insufficient control accuracy and poor disturbance rejection during the unwinding process, this study proposes a cascaded dual-loop control strategy optimized by an improved artificial lemming algorithm (IALA). The outer loop employs a super-twisting sliding mode controller (STSMC), whereas the inner loop utilizes a proportional-integral controller with a nonlinear gain (NLPI). First, a nonlinear coupled dynamic model of the unwinding and traction units is established based on their tension transmission characteristics and operational mechanisms. Considering the nonlinearity and strong coupling of the system, a cascaded dual-unit control structure is developed. The outer tension loop generates the reference angular velocity via the STSMC, and the inner velocity loop performs angular-velocity tracking through the NLPI controller and generates the motor torque command, thereby achieving coordinated dual-loop control. The closed-loop stability and tracking convergence of the proposed cascaded control system are analyzed using Lyapunov theory. Because the STSMC contains multiple interdependent parameters that are difficult to tune using traditional empirical methods, this study introduces the IALA for controller-parameter optimization. The simulation results demonstrate that the proposed IALA exhibits superior optimization accuracy and convergence performance. Compared with conventional PID and ADRC controllers, the proposed IALA+STSMC-NLPI strategy exhibits superior dynamic response, disturbance rejection capability, and robustness. Under variable operating conditions, for the unwinding unit, the ITAE and IMSE are reduced by approximately 15.7

Driven by the knowledge economy and digitalization, the scale of book logistics continues to expand. However, the quality inspection process in this field currently uses generic target detection models and rarely considers defect characteristics. Therefore, this paper proposes the Merge-YOLO model to address the three prominent characteristics of book packaging defects: low contrast, small-sized defects, and irregular shapes. Three improvements are made to enhance detection performance: the WT-C3k2 module is designed to separate high- and low-frequency features using wavelet transforms, combined with multi-level convolutions and a bottleneck structure to enhance feature extraction capabilities for small objects and complex lighting conditions, while expanding the receptive field and reducing semantic detail loss; introducing the QA Transformer, which uses a learnable transformation matrix to generate adaptive quadrilateral windows, breaking through the limitations of traditional fixed windows and improving the ability to capture features of irregular defects; and adopting the DySample dynamic upscaler, which replaces nearest-neighbor interpolation by dynamically adjusting the scaling ratio through an adaptive scope factor, reducing computational overhead while preserving pixel-level details. Experiments show that the model achieves 95.8% precision, 93.6% recall, and 94.1%mAP@0.5 on the book packaging defect dataset, outperforming the baseline model YOLOv11 and traditional algorithms in all metrics. This provides an efficient and accurate detection model for quality control in book supply chain packaging.

With the rapid development of e-commerce and the logistics industry, the importance of logistics packaging defect detection as a key link in product quality control is becoming increasingly prominent. However, existing target detection models often face the problems of difficulty in improving detection accuracy and high model complexity when dealing with small-scale targets in logistics packaging. For this reason, an improved target detection model, DScanNet, is proposed in this paper. To address the problem that the model’s detailed feature extraction for small target defects is not sufficient and thus leads to low detection accuracy, the MEFE module, the local feature extraction module (LFEM Block), and the PCR module of the multi-scale convolution and feature enhancement strategy are proposed to enhance the model’s capability of capturing defective features and focusing on specific features, and to improve the detection accuracy. To address the problem of excessive model complexity, a Mamba module incorporating a channel attention mechanism is proposed to optimize the model via its linear complexity. Through experiments on its own dataset, BIGC-LP, DScanNet achieves a high accuracy of 96.8% on the defect detection task compared with the current mainstream detection algorithms, while the number of model parameters and the computational volume are effectively controlled.

The presence of factors such as tooth side clearance, bearing clearance, and time-varying meshing stiffness introduces strong nonlinearity into mechanical system, significantly impacting the reliability and safety of mechanical equipment. When analyzing the dynamic characteristics of gear systems, the clearance factor can not be ignored. Few studies have considered the coupling effect of bearing clearance and tooth side clearance on the nonlinear characteristics of gear system, and the influence mechanism remain unclear. In this paper, a nonlinear dynamic model of a single-stage gear system with six degrees of freedom (6-DOF) was established, incorporating the coupling effects of tooth side clearance and bearing clearance. Using the control variable method, the tooth side clearance and bearing clearance were regarded as constant or dynamic clearance, respectively. The dynamic characteristics of the gear system were analyzed through time history chart, phase diagram, Poincare section diagrams, and fast Fourier transform (FFT) spectrum. When studying dynamic clearance, the influence of surface micromorphology on the clearance was considered based on fractal theory. The results showed that when tooth side clearance and bearing clearance were regarded as constants, the periodicity of the gear system remained essentially unchanged despite variations in clearance values. When tooth side clearance was considering as a fractal clearance and bearing clearance as a constant, the system’s periodicity changed with variations in the fractal dimension D. When tooth side clearance and bearing clearance were treated as fractal clearances, the system transitioned from a chaotic state to a periodic state with increasing fractal dimension D. This paper provides a theoretical foundation for the design and manufacturing of gear and bearing surfaces in the future.

In this paper, a conformal acoustic black hole (CABH) based on the Zhukovski mapping is proposed. The design of the CABH incorporates the ABH technique and the conformal mapping method and is realized by varying the plate thickness. The uniqueness of the CABH is that it has the function of ABH flexural wave cloaking, meanwhile, its vibration reduction performance is consistent with the ordinary ABH. This work validated the ABH flexural wave broadband cloaking performance of the CABH by the scattering measure, then experimentally verified the significant vibration reduction performance of the CABH above the cut-on frequency by the linear average acceleration level. The conformal mapping method extends the function of the ordinary ABH, and the CABH can be used to replace the ordinary ABH for multi-functional applications of the ABH. This study has potential applications in vibration control of perforated wall panels in mechanical equipment.

In recent years, abnormal operation behaviors in logistics have imposed significant losses and poor experiences on both enterprises and customers. Identifying diverse abnormal behaviors remains a significant challenge in this field. Therefore, it is crucial to propose an objective and quantitative monitoring and evaluation method. This paper utilizes a high-precision, compact, and low-power barometric pressure sensor to detect the internal pressure of small packages for rapid identification of logistics abnormal operation behaviors. The authors introduce a recognition fusion algorithm based on variance analysis and support vector machines (SVMs). This algorithm can identify various logistics abnormal operation behaviors, including unilateral extrusion, bilateral extrusion, treading, dropping, and stepping. The SVM model is employed to deeply learn and recognize these abnormal behaviors, achieving an average recognition accuracy of 98%. The proposed method outperforms five other methods, including Naive Bayes, by 4.9%, 2.12%, 2.76%, 4.46%, and 3.22% in detection accuracy. The shortest training time in the experiment is 2.6862 s, and the fastest classification per second can reach 3700 times. The barometric pressure sensor emerges as a promising approach for identifying logistics abnormal operation behaviors, contributing significantly to improving the current logistics security environment.

In this study, we design reconfigurable multi-phased negative Poisson's ratio metamaterial (NPM) for low-frequency vibration reduction. The designed NPMs consist of a concave hexagonal skeleton and horizontal diamond-shaped counterweights, which incorporate a base material and replaceable metal cores. By replacing these metal cores, the bandgap can be reconfigured and adjusted as needed. Finite element simulations and excitation experiments are employed to investigate the vibration suppression effects of these NPMs. The results show that the three-phase NPM has more advantages in low-frequency vibration reduction, compared with the single-phase and two-phase NPMs. When the metal core of the three-phase NPM is made of a higher-density material (lead), the lower edge of the bandgap is as low as 471.4 Hz, and the bandgap coverage below 1000 Hz reaches 36.1%. These findings provide new ideas for low-frequency vibration reduction in engineering practice.

As the key intelligent equipment in the warehouse operation system, warehouse robots are indispensable in reducing logistics costs and improving logistics efficiency. Path planning is the core technology of warehouse robots, which directly affects the distance traveled by the robot during operation and is crucial for improving the efficiency of warehouse operation. Aiming at the problem of inefficient robot path planning in warehousing scenarios, this paper proposes a path planning model based on multi-robot paths and shortest as the objective function, with the number of robots and robot energy as the constraints. The model optimizes the robot path through an ant colony algorithm and subsequently uses the optimized path as the initial path for the genetic algorithm to improve the quality of the path. In this paper, the proposed algorithm is analyzed in comparison with a single ant colony algorithm and a single genetic algorithm in a warehousing scenario. Experimental results show that the proposed algorithm possesses better robustness and stability, and significantly improves the path planning efficiency of the warehouse robot.

This study develops a portable tea aroma detection stick system based on the Arduino Uno R3 microcontroller, equipped with six metal oxide gas sensors: MQ2, MQ3, MQ4, MQ5, MQ7, and MQ9. The system can quickly and conveniently collect aroma data from different quality grades of tea, and subsequently utilizes deep learning algorithms to classify the tea aromas, thus verifying the functionality of the system. Additionally, in response to the data characteristics of the gas sensor array, this paper proposes a Grouped Convolutional Hybrid Attention Mechanism (GCHAM) that combines channel information and spatial information. By focusing attention on the key information that affects classification performance, GCHAM suppresses noise and irrelevant information, enhancing the model’s feature representation capability. We introduce a high-performance tea gas classification network that combines GCHAM with depthwise separable convolution and elastic net regularization. By comparing with multiple attention mechanisms, machine learning, and deep learning models, the results show that the proposed method has superior recognition performance, with recognition accuracy, precision, recall, and F1 score of 95.33

Rice classification and quality testing are essential to ensure its safety and quality, and can effectively reduce food economic losses associated with rice, which is currently the subject of repeated reports of rice adulteration. For this reason, according to the experimental requirements, we selected the smallest and lightest version of YOLOv8n in the YOLOv8 series, and optimised and proposed the lightweight and efficient Faster-YOLO algorithm, which is more suitable for rice adulteration classification and recognition tasks, on the basis of the YOLOv8n algorithm. Firstly, this paper introduces the Group Convolutional Hybrid Attention Mechanism, which combines channel information and spatial information, and embeds it in the last layer of the Backbone network, which enhances the feature representation capability of the model by focusing on the key information to suppress the noise. Secondly, the C2F module in the Backbone part adopts the design of combining Faster and C2F to enhance the feature fusion capability and reduce the number of parameters and computational complexity of the model. Finally, the collected data are augmented with multiple aspects to simulate different environments and compared with multiple attention mechanisms and deep learning models. The experimental results show that the method proposed in this paper is superior in classification and recognition performance, with recognition accuracy of 93.4%, precision of 96.5%, recall of 96%, and F1 score of 96.2%. In this paper, the accuracy is improved by 1.1%, 2.4%, 6.9%, 7.5%, 13.1%, 7.9%, 7.1%, and 7.1% compared to yolov8n, yolo11, yolov5, EfficientNetV2, MobileNetV3, Restnet18, and VGG19 image classification methods, respectively. It is demonstrated that Faster-YOLO provides a strong basis for the rapid identification of rice adulteration by reducing the weight of the model while improving the detection and identification capabilities.

To address the challenges in identifying effective fault features and achieving sufficient diagnostic accuracy and robustness in variable-speed printing press bearings, where complex mixed-condition vibration signals exhibit non-stationarity, strong nonlinearity, ambiguous time-frequency characteristics, and overlapping fault features across multiple operating conditions, this paper proposes an adaptive optimization signal decomposition method combined with dual-modal time-series and image deep feature fusion for variable-speed multi-condition bearing fault diagnosis. First, to overcome the strong parameter dependency and significant noise interference of traditional adaptive decomposition algorithms, the Crested Porcupine Optimization Algorithm is introduced to adaptively search for the optimal noise amplitude and integration count of ICEEMDAN for effective signal decomposition. IMF components are then screened and reorganized based on correlation coefficients and variance contribution rates to enhance fault-sensitive information. Second, multidimensional time-domain features are extracted in parallel to construct time-frequency images, forming time-sequence-image bimodal inputs that enhance fault representation across different dimensions. Finally, a dual-branch deep learning model is developed: the time-sequence branch employs gated recurrent units to capture feature evolution trends, while the image branch utilizes SE-ResNet18 with embedded channel attention mechanisms to extract deep spatial features. Multimodal feature fusion enables classification recognition. Validation using a bearing self-diagnosis dataset from variable-speed hybrid operation and the publicly available Ottawa variable-speed bearing dataset demonstrates that this method achieves high-accuracy fault identification and strong generalization capabilities across diverse variable-speed hybrid operating conditions.

With the development of China's new economy, the express industry has also shifted from high-speed development to high-quality development. Joint distribution aims to reduce the repeated waste of resources caused by the separate transportation of various express delivery enterprises by means of joint transportation, and promote the transformation and upgrading of the express delivery industry to high-quality development. Therefore, the purpose of this paper is to effectively reduce the cost of and improve the efficiency of express delivery. In this paper, a dual-objective joint distribution network planning model with the highest efficiency and the lowest total cost of joint distribution network is established, which is solved by a three-stage algorithm. The feasibility of the model and algorithm has been applied for validation in the city of Beijing, and the reasonable planning of the express network provides an effective decision-making basis.

Reasonable cargo space allocation scheme can shorten the time of books in and out of the warehouse and achieve orderly storage of books, thus enhancing the overall operational efficiency of the uninhabited bookstore and providing customers with a convenient book-buying experience. In order to formulate a scientific cargo space allocation plan, this paper combines the status quo of domestic and international research on cargo space optimisation, analyses and collates relevant data such as book orders from uninhabited bookstores, and processes them using the K-means method; A mathematical model of space allocation is established with the optimisation objectives of operation equilibrium and book picking time minimisation. Subsequently, the crossover rate and mutation rate are dynamically adjusted on the basis of the traditional genetic algorithm, and a parameter dynamic adjustment strategy based on adaptive genetic strategy is proposed to improve the Non-dominated sorted genetic algorithm-II (NSGA-II). In order to improve the efficiency of solving the multi-objective uninhabited bookstore stock optimisation problem, and to avoid overly relying on the parameter selection to solve the result. Finally, taking B uninhabited bookstore as an example, 100 orders are randomly selected for experiments to verify the feasibility of the improved algorithm. The results show that the performance of the improved algorithm is enhanced, and the optimised book allocation scheme can effectively reduce the book access time and improve the efficiency of access and storage.

The bearing vibration fault monitoring of advanced printing systems is crucial for ensuring system reliability, improving print quality, and enhancing production efficiency. In consideration of the high noise and strong interference attributes of bearing vibration signals of printing equipment caused by complex environmental factors, the original data noise interference is suppressed by a diagnostic approach for rolling bearing vibration signal faults combined Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Dung Beetle Optimization-Support Vector Machine (DBO-SVM) proposed in this article. This method suppresses noise interference in the original data by decomposing and reconstructing vibration signals, and innovatively proposes the DBO-optimized SVM to address the problems of poor anti-interference ability and weak generalization ability of a single intelligent diagnostic method, effectively improving the fault diagnosis rate. First, the decomposition by CEEMDAN effectively overcomes the difficulties of modal aliasing and significant reconstruction errors found in traditional empirical mode decomposition (EMD). The optimal component reconstruction strategy considering the Correlation Coefficient and the Variance Contribution Rate is designed to obtain the vibration signal after noise reduction. Second, to effectively avoid the limitation of heavily relying on expert experience for hyperparameter adjustment, a DBO-SVM model is constructed utilizing a heuristic beetle optimization algorithm, dynamically optimizing the key kernel function parameters and penalty factors of SVM. Finally, the algorithm's performance was tested using public datasets and self-tested data from Case Western Reserve University. The results indicate that the proposed approach achieves greater diagnostic accuracy and exhibits robust generalization.