Unmanned aerial vehicles (UAVs) face critical challenges in path planning in dynamic environment, requiring optimized flight paths that account for constraints such as obstacle avoidance, energy efficiency, and altitude limits. Sand cat swarm optimization (SCSO) algorithm has demonstrated promise in addressing complex optimization challenges. However, SCSO is limited by slow convergence, susceptibility to local optima, and insufficient adaptability. To overcome these shortcomings, an enhanced SCSO with the spiral search, Lévy flight, tent chaotic mapping, and adaptive sparrow alert mechanism, namely TSLS-SCSO is developed to propose an autonomous path planning method for UAVs in Dynamic Environment. In TSLS-SCSO, a new population initialization strategy with tent chaotic mapping is designed to achieve a large dynamic range and coverage capability. For the expanding the search range, a new spiral search strategy is designed to broaden the search range in the search phase. For the increasing running efficiency and improving solution, a new Lévy flight strategy is employed to enrich the diversity of population in the attacking prey phase. A new sparrow alert mechanism with integrating the sand cat group with the sparrow alert is designed to obtain faster convergence speed and accuracy. The experiment results on CEC 2017 and CEC 2022 show that the TSLS-SCSO obtains higher accuracy and more stable solutions and exhibits better competitiveness. Furthermore, the proposed UAV path planning method successfully found effective paths with an obstacle avoidance effectiveness of 95.5%. The obtained results validate the effectiveness and competitiveness of TSLS-SCSO in UAV path planning in the dynamic environment.

Broad learning system (BLS) has shown remarkable results in various machine learning tasks, but the fragility of BLS based on the minimum mean square error criterion under the label noise environment in Internet of Things (IoT) limits its application. To solve these problems, a dual-model collaborative label adaptive correction BLS based on the collaboration of KRPBLS and SKBLS, namely SC-KSBLS is proposed to significantly improve the robustness of BLS under label noise environment. First, a new BLS based on the Kernel risk-sensitive mean p-power (KRP) criterion, namely KRPBLS is developed to overcome the sensitivity by optimizing the output weight matrix and replacing the minimum mean square error criterion. Then, the label feature space is constructed, and the popular regularization strategy is designed to construct the SKBLS model with the collaborative training of KRP criterion and regularization to improve the learning ability of BLS. Finally, the interaction mechanism between KRPBLS and SKBLS is designed to effectively identify and correct label noise. The robustness theory of the SC-KSBLS has been analyzed and proven. The experimental results on nine datasets in IoT show that the SC-KSBLS significantly improves the robustness and performance, which provide an innovative solution under label noise environment.

Capacitated Vehicle Routing Problem (CVRP) is a critical challenge in logistics optimization, which directly impact operational costs and service efficiency. While quantum differential evolution (QDE) algorithm offers potential advantages in solving combinatorial optimization problems, its application in CVRP is still limited due to the premature convergence, poor search capability and stagnation. To address these limitations, a novel multi-strategy QDE algorithm with cooperative co-evolution (CC) framework and hybrid local search strategy, namely MSCFLQDE is proposed to effectively solve the CVRP. Firstly, a new multi-population strategy with CC framework is designed to solve each sub-CVRP for enabling parallel optimization and preserving global constraints. Then an adaptive differential mutation mechanism is developed to balance the exploration and exploitation and accelerate the convergence. Thirdly, a new quantum rotation mode with the sorting coding rule is designed to adjust the search direction and reduce stagnation. In the later stage, a hybrid local search strategy is proposed to dynamically eliminate the redundant nodes and intersections. Finally, the experiment results on the five CVRPs (set A, set B, set P, set E, and set G) demonstrate that the MSCFLQDE has better search ability, higher convergence and stronger stability by comparing with the state-of-the-art algorithms(such as CCDE, CCDE-D, CCDE-R, CCDE-S, HGS, BILA, AGA-ES and TAMLS and so on), which achieves 5.53% shorter distances for P51_K10 by comparing with AGA-ES.

Aviation Internet of Things (AIoT) data sharing can create tremendous value for participants. With the development of AIoT and intelligent civil aviation, data security and privacy protection have become more prominent. To improve the data security and privacy of AIoT, and allow heterogeneous devices to participate in federated training, in this article, a blockchain-based federated knowledge distillation (BFKD) is proposed. First, federated knowledge distillation is used for knowledge transferring between clients to protect client data privacy. Second, a clustering algorithm is used to select aggregated soft labels to enhance Byzantine resistance. Finally, the consortium blockchain validates the data exchange process of federated knowledge distillation. In addition, a federated score grouping practical Byzantine fault-tolerant algorithm is proposed for improving consensus efficiency and to encourage participants to contribute more public data and honestly participate in federated training. Theoretical analysis and experimental results show that BFKD boasts high data mining performance and communication efficiency while safeguarding data privacy and security.

Intelligent fault diagnosis based on deep learning has gained widespread attention. However, existing transfer diagnosis methods under variable working conditions face challenges in aligning deep features and handling task-specific decision boundaries. To address these issues, a transfer diagnosis method based on maximum classifier discrepancy (MCD) and deep feature alignment, namely maximum classifier discrepancy with deep feature alignment (MCDDFA) is proposed in this article. First, MCD is employed for transfer diagnosis by considering task-specific decision boundaries comprehensively. Then, two mapping-based domain adaptation methods of the multikernel maximum mean discrepancy and correlation alignment are combined to align the deep features of the source and target domains, while preserving the unique characteristics of each domain. Finally, an innovative integration of conditional domain adversarial network with MCD is proposed by utilizing adversarial training to align the joint probability distributions between the source and target domains, which further enhance the transfer diagnosis capability of deep networks. The experimental results on different dataset show that the MCDDFA achieves the accuracy improvement of 2%–10% by comparing to existing methods under variable working conditions, which validate the effectiveness of the MCDDFA in complex transfer diagnosis tasks.

Rolling bearings are the core components of mechanical equipment, and their working state is closely related to the performance of mechanical equipment. When rolling bearings occur faults, the nonstationary signals will be generated. In order to effectively analyze the nonstationary signals with rapid instantaneous frequency changes, a new parametric time redistribution multisynchronous compression transform method, namely GTMSST is proposed. First, Fourier spectrum is employed to find the most suitable parametric coefficients for the kernel of General wavelet transform (GWT), and the signal is subjected to GWT to suppress the time-frequency energy diffusion. Second, a time-direction multiple iterative rearrangement strategy is developed to solve the problem that the time-reassigned synchrosqueezing is only applicable to the weak frequency signals and easily interfered with the noise, which can achieve higher time-frequency resolution and energy aggregation. Finally, the effectiveness of the GTMSST in analyzing nonstationary signals is proved through the experiments with numerical signals and actual fault signals. The results show that the GTMSST has high time-frequency energy concentration, and takes on better performance under different noise levels and operating working conditions. It can effectively diagnose the bearing faults.

Federated learning (FL) represents a distributed machine learning approach that leverages a centralized server to train models while keeping the data on edge devices isolated. FL has the benefits of preserving data privacy and improving model accuracy. However, the occurrence of unexpected device exits during model training can severely impact the performance of the models. To address the communication overhead issue and accelerate model convergence, a novel adaptive FL with a negative inner product aggregation approach, namely, NIPAFed is proposed in this article. The NIPAFed leverages a congestion control algorithm inspired by TCP, known as additive multiplication subtraction strategy, to adaptively predict the workload of devices based on historical workload. So NIPAFed effectively mitigates the impact of stragglers on the training process. Additionally, to reduce communication overhead and latency, a negative inner product aggregation strategy is employed to accelerate model convergence and minimize the number of communication rounds required. The convergence of the model is also analyzed theoretically. The validity of NIPAFed is tested on federated public data sets and the NIPAFed is compared with some algorithms. The experimental results clearly demonstrate the superiority of the NIPAFed in terms of performance. By reducing device dropouts and minimizing the communication rounds, the NIPAFed effectively controls the communication overhead while the convergence is ensured.

With the rapid growth of flight operation data, how to alleviate the contradiction between data sharing and privacy protection of civil aviation corporations has become a challenging problem. Therefore, a blockchain-based flight operation data sharing scheme, named BFOD is designed to achieve the privacy protection and secure sharing of flight operation data. In BFOD, physical entities of airlines, airports and air traffic control are divided into data owners, data requesters and authorization institutes according to the business logic. First, the authorization institute grants a hash anonymous identity and different levels of access right for each civil aviation corporation. When the data are accessed, a hash anonymous identity is designed to verify the access right of the data requester, which protects identity privacy. Then, zero-knowledge succinct noninteractive argument of knowledge (zk-SNARKs) is employed to verify whether the flight operation data meets the specific requirements raised by the data requester without disclosing data privacy. Finally, a proxy re-encryption is used to improve the sharing efficiency of flight operation data. In addition, a grouped practical Byzantine fault tolerant (PBFT) algorithm is proposed to reduce consensus latency. The theoretical analysis and experimental results show that the consensus latency of the grouped PBFT algorithm reduces 91.4% under the number of consensus node$\text{N}=$100, and the BFOD meets data confidentiality, availability and privacy protection, which is feasible and efficient.

Federated learning (FL) algorithm has been widely studied in recent years due to its ability for sharing data while protecting privacy. However, FL has risks such as model inversion attack, and is less effective when data is non-independent and identically distributed (non-IID). In response to these challenges, an intelligent optimization-based federated learning (IOFL) framework is developed to improve the privacy protection performance and global model performance in this paper. In the IOFL, the server searches model parameters by using intelligent optimization algorithm and distributes it to the clients. The clients use local data to validate the issued model by the server and return the validation results to the server. The server calculates the fitness function based on the weighted average of the received validation results, which guide the intelligent optimization algorithm to search for new model parameters. The experimental results on MNIST and Fashion-MNIST dataset show that the accuracy of the IOFL can reach over 0.8 and 0.68 under different non-IID settings with 200 round communications, whose performance is not affected by non-IID data distribution at clients.

Early detection of blade defects is crucial for turbines in Internet of Things (IoT) as it can prevent failures, minimize downtime, and enhance system reliability. Deep-learning-based methods have improved the accuracy of defect recognition and classification. However, there are challenges in balancing recognition efficiency, accuracy, and the ability to detect small targets. Therefore, a lightweight defect detection model of turbine blades using single-shot multibox detection based on ShuffleNetv2 and coordinate attention (SN-CA-SSD) in IoT is developed in this article. First, within the single-shot multibox detector framework, ShuffleNetv2 replaces the VGG-16 network as the fundamental feature extraction network. This substitution ensures detection accuracy while reducing model complexity. Second, the coordinate attention mechanism is introduced after the feature map, weighting important features to enhance the model’s ability to perceive key information. Finally, the loss function is redesigned using Efficient Intersection over Union (EIoU) loss to improve detected targets’ accuracy and localization precision. The proposed method is applied to defect detection images of turbine blades, and the results demonstrate that the algorithm significantly improves accuracy, detection efficiency, and the ability to detect small targets, striking a balance between precision and efficiency. By combining the model with an interpretable algorithm, the algorithm’s decision-making process is analyzed from the perspective of representation visualization, enhancing the algorithm’s interpretability.

In this paper, a large-scale multi-objective gate assignment model is constructed by considering the flight international and domestic attributes, task type, airline affiliation, and aircraft type. Then a multi-objective quantum-inspired evolutionary algorithm based on decomposition mechanism, namely MOQEA/D is developed to solve the constructed model effectively. Specifically, a new decomposition mechanism is designed to decompose the multi-objective GAP into several single-objective sub-GAPs. Each quantum bit string solves a single-objective sub-GAP independently. And a new optimal crossover strategy is proposed to limit the randomness of observation operations and maximize the preservation of excellent genes to further improve the optimization performance. Finally, the multi-objective knapsack problem and the multi-objective GAP are selected to verify the effectiveness of the MOQEA/D. The experiment results demonstrate that the MOQEA/D can effectively solve large-scale multi-objective knapsack problem and obtain ideal gate assignment results. It takes on very significance and application value in solving complex optimization problems.

With the rapid development of the air transportation industry, air traffic is facing a severe test. The accurate prediction of the estimated arrival time (EAT) plays an important role in rational and efficient scheduling of flights. Aircraft EAT predictions often rely on aircraft performance parameters or physical trajectories. This gives poor consideration to the flight environment and take-off and landing conditions. This paper applies a data-driven methodology for ETA prediction. A Cluster clustering-based modular integrated DNN (CC-MIDNN) is proposed. According to the information of flight mission and flight environment, it decomposes complex modeling tasks into multiple distinct subtasks using cluster-based clustering. Then Bayesian optimization is used to design corresponding parallel sub-networks to learn different sub-tasks in order to reduce the complexity of the subsequent sub-networks. Finally, a new integration scheme is proposed to solve the overfitting problem due to the reliance on the training accuracy of sub-modules. To verify the effectiveness of the method, CC-MIDNN performs EAT prediction on flight data of European Airlines LIS airport in 2017. The experimental results show that the CC-MIDNN improves the time prediction accuracy by 5.92 minutes and keeps the error within 13 minutes. Compared with other deep learning algorithms and integration algorithms, the CC-MIDNN has high accuracy and stability.

When the fine-grained recognition problems of image classification processed, broad learning system (BLS) is more efficient in classification, but has difficulty in distinguishing features with large similarities. Sparse representation classification (SRC) is more capable of handling similarity features, but is more computationally expensive. To better use the BLS model to tackle the fine-grained recognition problem and improve the ability to handle similarity features, this article combines the advantages of BLS and SRC, and proposes a broad sparse fine-grained image classification model based on dictionary selection strategy, dictionary broad sparse representation classification (DBSRC). First, to solve the parameter selection problem of the BLS model, leave one out cross validation (LOO) is introduced to quickly find the better regularization parameters and build a BLS-LOO coarse-grained classification model. Then propose reliability criteria based on a threshold selection strategy for the selection of fine-grained images. Next, an adaptive dictionary selection strategy is designed based on the output of the BLS-LOO to construct a sparse subdictionary for each fine-grained image that is not distinguished by the BLS-LOO. Finally, a sparse subdictionary based SRC model is used to classify fine-grained images. Experimental results show that DBSRC achieves good classification performance on three image datasets with different complex dimensions, ImageNet, USPS, and Pavia, and has strong processing capability for fine-grained features.

The sharing of flight operation data brings huge benefits to all participants, but for the privacy protection and data security, it is difficult to directly share flight operation data. Federated learning (FL) enables participants to jointly train machine learning models without exposing local data. However, due to the centralization of FL and the unreliability of FL participants, FL is vulnerable to malicious client and server attacks. In this paper, an anti-poisoning attack decentralized privacy enhanced federated learning (APDPFL) scheme is designed to mitigate the impact of server and malicious clients. Specifically, a local Rényi differential privacy is designed to protect client data privacy. Then, a verification method based on K-Means clustering is proposed to select models to participate in aggregation, which improves the anti-poisoning attack performance. Finally, a federated grouping practical Byzantine fault tolerance (FGPBFT) consensus algorithm based on consortium blockchain is proposed to dynamically change server and consensus clients, to decentralize server and improve the consensus efficiency. The theoretical analysis proves that the APDPFL achieves better convergence and provides data privacy protection and security protection. The experimental results on public datasets and flight operation datasets show that the APDPFL is robust and effective for sharing flight operation data.

Bearing fault diagnosis is of significance to ensure the safe and reliable operation of a motor. Deep learning provides a powerful ability to extract the features of raw data automatically. A convolutional deep belief network (CDBN) is an effective deep learning method. In this article, a novel vibration amplitude spectrum imaging feature extraction method using continuous wavelet transform and image conversion is proposed, which can extract the image features with two-dimensional and eliminate the effect of handcrafted features under low signal-to-noise ratio conditions, different operating conditions, and data segmentation. Then, a novel CDBN with Gaussian distribution is constructed to learn the representative features for bearing fault classification. The proposed method is tested on motor bearing dataset with four and ten classifications. The results have been compared with other methods. The experiment results show that the proposed method has achieved significant improvements and is more effective than the traditional methods.

With the continuous and rapid growth of air traffic demand, gate resource becomes a major bottleneck restricting airport development. Rational gate allocation is regarded as one of the most important means to solve this bottleneck. In this paper, in order to comprehensively considere different stakeholders, a three-objective gate allocation model is to consider a wider scope, in which the minimizing passenger walking distances, the most balanced idle time of each gate and the best full use of large gate are optimized simultaneously to improve the practical efficiency. To efficiently solve this model, an improved quantum evolutionary algorithm (QEA) based on the niche co-evolution strategy and enhanced particle swarm optimization (PSO), namely IPOQEA is designed. An IPOQEA-based gate allocation method is proposed to allocate the flights to suitable gates within different periods. Finally, the actual operation data of Baiyun Airport is used to validate the effectiveness of the proposed method. Comparison results show that the constructed model can address the passenger walking distances, robustness and costs in airport management. Moreover, the IPOQEA has better optimization ability in solving gate allocation problem. Therefore, the proposed gate allocation method has great potential for practical engineering since it can easily make decisions for airport managers.

Quantum-inspired differential evolution (QDE) is an evolutionary algorithm, which can effectively solve complex optimization problems. However, sometimes, it easily leads to premature convergence and low search ability and falls to local optima. To overcome these problems, based on the MSIQDE (improved QDE with multistrategies) algorithm, an enhanced MSIQDE algorithm based on mixing multiple strategies, namely, EMMSIQDE is proposed in this article. In the EMMSIQDE, a new differential mutation strategy of a difference vector is proposed to enhance the search ability and descent ability. Then, a new multipopulation mutation evolution mechanism is designed to ensure the relative independence of each subpopulation and the population diversity. The feasible solution space transformation strategy is used to achieve the optimal solution by mapping the quantum chromosome from a unit space to solution space. Finally, some multidimensional unimodal and multimodal functions are selected to demonstrate the optimization performance of EMMSIQDE. The results demonstrate that the EMMSIQDE is significantly better than the DE, QDE, QGA, and MSIQDE, and has better optimization ability, scalability, efficiency, and stability.