The aerospace field requires high structural integrity of critical components, and accurate and efficient fault detection is crucial for flight safety. In this paper proposed a fault detection algorithm based on ultrasonic C-scan imaging, called Ultrasonic-MYOLO. The method combines ultrasonic nondestructive testing techniques with the improved YOLO deep learning framework to realize high-precision recognition of defects. First, Ultrasonic-MYOLO constructs a detection model based on the state-space model, which can realize global information perception at a low computational cost. Second, a clustering self-attention mechanism is designed to further enhance the model’s ability to express non-local features. Finally, a hybrid expert mechanism is introduced to optimize the feature extraction unit based on the state-space model, which alleviates the problem of decreasing detection accuracy due to category imbalance. Compared with traditional image processing-based methods, Ultrasonic- MYOLO is able to extract defect features in ultrasound C-scan images more effectively and utilize deep learning models for automatic detection to improve detection accuracy and detection efficiency. Experimental results show that the algorithm exhibits excellent performance in several defect detection tasks for aerospace components, specifically, Ultrasonic-MYOLO can detect a single ultrasound image with a resolution of 224 × 224 within 1 millisecond, achieving an mAP50of 96.4%, demonstrating both high detection speed and accuracy, providing an efficient and intelligent solution for aerospace structural health monitoring.

In the wheat detection work, the wheat is located in a complex environment, weeds and dried leaves will hinder the detection of wheat, the wheat images of shadows, wheat obscuring each other and other phenomena will lead to a reduction in the accuracy of the detection. At the same time, for the small object detection problem, most of the detection algorithms use the detection speed as a cost to improve the detection accuracy, and cannot do a good job of balancing between the two. To address the above issues, this paper proposes an improved YOLO detection algorithm, which aims to improve the detection accuracy of small targets in complex environments while minimising the cost of detection speed. Firstly, two attention mechanisms for small target detection are added to the backbone of YOLOv8; secondly, the target detection header with unified attention is used in the head part, which improves the expressive power of the detection header without any computational expense; and finally, the Inner-MPDIoU function, which is a combination of MPDIoU and Inner ideas, is used as the localisation loss in loss functions.Extensive experiments on publicly available datasets show that the results of the network in this paper are improved in terms of both speed and accuracy compared to the original YOLOv8, enabling a better balance between detection accuracy and speed.

Firefighting UAV technology has become one of the core tools of modern firefighting operations, and its mission execution is constantly expanding in scale and complexity. In the face of this development, it has become even more critical to find an efficient way to ensure that drones can be assigned to perform their most suitable tasks. In this study, we used the Environment-Class, Agent, Role, Group, and Object (E-CARGO) model to systematically analyze the task assignment (FDTA) problem of firefighting drones, and introduced an enhanced whale optimization algorithm (EWOA) to optimize the path planning in the FDTA problem. Finally, simulation experiments are carried out under diverse terrain conditions to demonstrate the efficiency and fast response ability of the improved algorithm under different workloads and environmental conditions.

The popularization and application of 5G technology is about to open the era of global "data explosion". The traditional cloud computing model shows insufficient service support for resource-sensitive applications, especially in terms of latency, and edge computing can solve this problem by providing service support close to the user request side. This article formalizes the single application service deployment problem (SASDP) using the E-CARGO (Environment-Class, Agent, Role, Group, and Object) model. Through group role assignment (GRA), a high-satisfaction service deployment scheme for single application service deployment is designed, and satisfaction evaluation is established through delay to provide providers with satisfactory deployment solutions and achieve economic benefits. Finally, large-scale simulation experiments are carried out based on Python PuLP platform, and experiments show that our method is better than the baseline method in terms of overall satisfaction, user coverage and economy.

In order to solve the problem of the task collaboration of multi-agent, we propose a task collaboration planning based on mentorship mode (MM-TCP). In this paper, the Group Role Assignment (GRA) framework is used to formalize the multi-agent task collaboration problem. The Growth curve is adopted to describe the change trend of the qualification values of the prior and posterior agents in a mentorship mode. The IBM ILOG CPLEX optimization package (CPLEX) is used to find the solution of the model. Experiments show that the proposed method is feasible and effective. With the utilization of a mentorship mode, the performance of the whole team is improved. In addition, the effect of the Growth curve model on team performance is also discussed in this paper.

In this paper, we propose a Multi-Objective Optimization problem with Mentorship Mode (MM-MOOP) and formalize the real-world collaboration problem using group role assignment (GRA) framework. The GRA with budget constraints, which is a typical Multi-Objective Nonlinear Optimization problem, and it can be transformed into linear optimization problems and solved by IBM ILOG CPLEX optimization package (CPLEX). Through simulation experiment, the optimal proportion of novice and veteran in the group is obtained. The experiments also verifie that the group performance in Mentorship Mode can be improved under the same budget constraints.

In order to meet the growing demand for curtain wall cleaning UAVs in the market and improve the shortcomings of current manual cleaning and robot and UAV cleaning design. In this paper, a new type of curtain wall cleaning UAV is designed and developed. Firstly, the system structure of curtain wall cleaning UAV is designed, and the dynamic and kinematic models of curtain wall cleaning UAV are established. The cascade PID control algorithm is designed, and the outer position loop and inner attitude loop are used to control the curtain wall cleaning UAV. Finally, the control algorithm is verified by simulation experiment with MATLAB / Simulink. The simulation curve shows that the cascade PID control algorithm can meet the requirements of fast response speed and high stability of UAV, and has good anti-interference ability.

With the frequent occurrence of disasters, such as war, storms, hurricanes, and earthquakes, post-disaster rescue is particularly important. Based on the principle of life first life detection and rescue have become the primary task of post-disaster rescue. In this paper, the E-CARGO (Environments – Classes, Agents, Roles, Groups, and Objects) model is used to formalize the life detection and rescue problem. With the help of the idea of the convex hull algorithm, a Hierarchical Coverage Based on Square Algorithm (HCBS) is proposed to achieve the maximum coverage of the rescue area with the minimum number of detection areas, and then a rapid assignment of UAV life detection and rescue with minimized rescue cost is realized through group role assignment (GRA). Using the PuLP extension library of Python, we implement the proposed algorithm. The experiments show that the proposed method is fast and effective.

In this paper, view of the unstable output of a single online sequential learning machine, we propose a selective ensemble algorithm based on glowworm swarm optimization. On the basis of this algorithm, we design an adaptive learning framework of multiple learning machines, which can judge whether to use multiple learning machines for selective ensemble according to the preset threshold. The experimental results show that the proposed approach has higher classification accuracy and generalization performance compared with the basic online sequential extreme learning machine as well as the voting online sequential extreme learning machine.

Based on deep convolutional neural network, an optical remote sensing image classification method is proposed in this paper. Aiming at the particularity of remote sensing image and natural object classification, combined with the theory of deep learning convolutional neural network, a five-layer convolutional neural network was designed, which applied to classify the optical remote sensing image into two category. Testing and parameter optimization on the UC Merced Land Use data set. The convolutional neural network designed in this paper is trained and tested on the same test set. The result shows it has better effect of classifying on the current data set reach 98.15%. The experimental results indicate this network designed can apply to the scene of two-category image classification and improve the classification accuracy of aerial image.

The most prominent Business Process Model Abstraction (BPMA) use case is a construction of a process “quick view” for rapidly comprehending a complex process. Researchers propose various process abstraction methods to aggregate the activities most of which are based on [Formula: see text]-means hard clustering. This paper focuses on the limitation of hard clustering, i.e. it cannot identify the special activities (called “edge activities” in this paper) and each activity must be classified to some subprocess. A new method is proposed to classify activities based on fuzzy clustering which generates a fuzzy matrix by computing the possibilities of activities belonging to subprocesses. According to this matrix, the “edge activities” can be located. Considering the structure correlation feature of the activities in subprocesses, an approach is provided to generate the initial clusters based on the close connection characteristics of subprocesses. A hard partition algorithm is proposed to classify the edge activities and it evaluates the generated abstract models according to a new index designed by control flow order preserving requirement and the evaluation results guide the edge activities to be classified to the optimal hard partition. The proposed method is applied to a process model repository in use. The results verify the validity of the measurement based on the virtual document to generating fuzzy matrix. Also it mines the threshold parameter in the real world process model collection enriched with human designed subprocesses to compute the fuzzy matrix. Furthermore, a comparison is made between the proposed method and the [Formula: see text]-means clustering and the results show our approach more closely approximating the decisions of the involved modelers to cluster activities and it contributes to the development of modeling support for effective process model abstraction.

Online sequential extreme learning machine (OS-ELM) can learn the data one-by-one or chunk-by-chunk with the fixed or varying chunk size. It was proposed by Liang et al. is a faster and more accurate algorithm as compared to other online learning algorithms. However, besides the advantages of OS-ELM machine, the original OS-ELM algorithm also introced some issues; first, the improved OS-ELM algorithms need to be network structure adjustment to improve learning promance; second, OS-ELM algorithm learning with stability will affect its generalization ability. For such reasons, in this paper we propose a survey of OS-ELM algorithm with the development of history and the latest results of researching which can hopefully support researchers in the furture.