2026-08-01 2026, Volume 11 Issue 4

  • Select all
  • research-article
    Muhammad Zulkefal, Iftikhar Ahmad, Asad Habib, Asad Ayub, Hamza Sethi, Ihsanullah Ihsanullah, Hakan Caliskan, Hiki Hong
    2026, 11(4): 951-977. https://doi.org/10.1049/cit2.70103

    Machine learning (ML) integration is becoming increasingly popular in advancing the 4th industrial revolution, known as Industry 4.0. This review paper examines ML applications in CO2 management stages: emission, capture, and conversion. ML models, including multiple linear regression (MLR), multiple nonlinear regression (MNLR), and artificial neural networks (ANN), are used in the emission phase to predict the CO2 emissions for the countries and sectors, variables such as energy consumption, fuel usage, gross domestic product (GDP), population, and other miscellaneous socio-economic variables. In the capture stage, ML forecasts post-combustion and direct air CO2 capture efficiencies using models such as ANN, generalized regression neural networks (GRNN), backpropagation neural networks (BPNN), and group method of data handling (GMDH), considering input variables such as catalysts, process parameters, and rheological properties. In the conversion stage, ML models, primarily ANN, multi-layer perceptron (MLP), particle swarm optimization (PSO), and genetic algorithm (GA), forecast and optimize CO2 transformation into products such as methanol, C2 hydrocarbons, syngas, methane, lower olefins, and biofuels, considering factors such as catalyst compositions and process conditions. This study identifies several trends, with ANN emerging as the predominant ML technique. The discoveries will benefit academia and industry in the development of CO2 management models.

  • research-article
    Jinbin Wang, Aiping Yang, Guosong Jiang, Wenlong Yu, Dongwei Ren, Qinghua Hu
    2026, 11(4): 978-993. https://doi.org/10.1049/cit2.70162

    Adverse haze conditions introduce complex degradations that obscure scene details and distort structural cues critical for object detection, posing persistent challenges for vision-based sensing systems. Although existing haze removal methods have achieved notable improvements in visual clarity, their optimisation objectives are often misaligned with downstream detection requirements, leading to limited detection performance in real-world scenarios. To address this issue, this work proposes a task-aligned weakly supervised haze removal framework, termed Dehaze4Detection, which explicitly aligns low-level restoration with high-level detection objectives. The framework incorporates a Semantic-Aware Multi-Scale Fusion Module (SMFM) that embeds pixel-level semantic knowledge into the dehazing process, enabling selective enhancement of object regions while suppressing background over-enhancement to achieve detection-friendly restoration. To further improve feature quality, a Contrast Self-Correction Attention Module (CSAM) is introduced, which exploits contrast maps derived from pseudo-dehazed images to guide attention towards object contours and salient structures. The proposed SMFM and CSAM are integrated into a unified pipeline and jointly optimised using detection and dehazing losses. Extensive experiments on both synthetic and real-world benchmarks demonstrate that Dehaze4Detection achieves competitive perceptual quality while significantly improving detection accuracy.

  • research-article
    Haotian Li, Yifei Yang, Qiong Fu, Zhenyu Lei, Zhe Xu, Shangce Gao
    2026, 11(4): 994-1018. https://doi.org/10.1049/cit2.70150

    Exploring clean energy alternatives to fossil fuels has become a major research focus worldwide. Wind energy is regarded as one of the most promising renewable energy sources due to its clean and sustainable nature. However, wake interactions among turbines significantly reduce power conversion efficiency, making wind farm layout optimization (WFLO) crucial for maximising energy output. As the number of turbines increases, wake interactions become more pronounced, further deteriorating overall efficiency. Metaheuristic algorithms have been widely adopted to address the complex constraints and design objectives of WFLO. Nevertheless, traditional heuristic methods often suffer from poor solution quality and premature convergence when dealing with large-scale WFLO problems under complex wind conditions. To overcome these limitations, this study proposes a multi-strategy synergy-based differential evolution algorithm (LSDE) for large-scale WFLO under complex wind scenarios. The proposed method is evaluated against nine representative WFLO algorithms under four complex wind scenarios (4, 5, 6 and 7 wind directions) and three turbine scales (30, 50 and 100 turbines). Experimental results demonstrate that LSDE achieves superior performance, stability and robustness. Specifically, LSDE improves power conversion efficiency by 3.40%, 3.51%, 3.10% and 3.36% under the four wind scenarios, respectively, compared with other mainstream algorithms.

  • research-article
    Yongji Guan, Shunbao Zhang, Longbang Wang, Erchao Li
    2026, 11(4): 1019-1027. https://doi.org/10.1049/cit2.70111

    A central challenge in deep learning lies in achieving strong model generalisation, an area in which conventional optimisers such as stochastic gradient descent (SGD) often exhibit limitations, even though they ensure convergence. This paper introduces cascaded inertia SGD (CISGD), a novel optimisation algorithm specifically designed to address this challenge. The core mechanism of CISGD involves a hierarchical aggregation of historical gradients: it first accumulates past gradients and then compounds these accumulations to form multi-stage inertial terms. This deep integration of gradient history allows the optimiser produce more stable optimisation trajectories, thereby encouraging convergence towards flatter minima that are empirically associated with improved generalisation. To enhance practicality and robustness, we further eliminate manual hyperparameter tuning through a lightweight feed-forward neural network that automatically learns the optimal coefficients of the inertial terms, ensuring adaptability across diverse architectures and tasks. Extensive experiments on benchmark image classification and remote sensing change detection tasks demonstrate that CISGD consistently achieves superior generalisation performance compared with existing optimisers, demonstrating that CISGD achieves consistent, though moderate, improvements over standard optimisers while maintaining computational efficiency. This work offers a practical and theoretically grounded framework for automated and generalisable optimisation, promoting broader applications of adaptive deep learning in complex real-world tasks.

  • research-article
    Jingyi Huang, Guipeng Xi, Meixiu Lin, Haohui Zhang, Bo Li, Evgeny Neretin
    2026, 11(4): 1028-1046. https://doi.org/10.1049/cit2.70153

    In recent years, the widespread application of deep reinforcement learning (DRL) in autonomous systems has highlighted the importance of achieving high sample efficiency under sparse reward conditions. To improve sample efficiency in sparse reward environments, this paper proposes a reinforcement learning framework built upon the Soft Actor Critic architecture, which integrates multifaceted curiosity rewards (MCR) and adaptive experience replay utilisation (AERU) (MCR-AERU SAC). MCR combines multi-level intrinsic motivational signals, such as state prediction error and model uncertainty, to provide rich exploration incentives, encouraging the controlled entity to deviate from existing trajectories and discover new high-reward behaviours. AERU dynamically adjusts the experience replay priorities based on posterior temporal difference error (TD error), focusing on utilising ‘partially successful’ transitions that are easily overlooked. The synergy between MCR and AERU enables the proposed framework to achieve an optimal balance between exploration and exploitation, significantly accelerating policy convergence and improving sample utilisation. Extensive experiments in complex dynamic training environments demonstrate that the proposed MCR-AERU SAC algorithm achieves up to 1.41 times the early-stage gain rate and a 55.56% improvement in task success rate compared to the HER-SAC baseline, demonstrating superior sample efficiency and excellent robustness in large-scale sparse reward environments.

  • research-article
    Zhouwei Lin, Yudong Xia, Pingping Wu, Han Lin, Qingsong Xu, Zheng Fan, Juan Tu, Jun Wu
    2026, 11(4): 1047-1061. https://doi.org/10.1049/cit2.70168

    Accurate medical image segmentation with low model complexity remains difficult because lesions are often small in scale and boundary cues are easily corrupted by noise. Although recent segmentation methods have achieved strong performance, many of them rely on increasingly complex architectures with high computational costs, limiting their applicability in resource-constrained settings. To alleviate this issue, we propose PLNet, a lightweight hybrid segmentation framework for medical image analysis. The network improves representation learning by integrating fine-grained local-structure perception with long-range contextual modelling, thereby enhancing the representation of complex medical images. In addition, a feature selection mechanism is employed to emphasise informative feature responses and suppress redundant activations while preserving discriminative representations. Extensive experiments on multiple datasets demonstrate that PLNet achieves competitive IoU and Dice scores with relatively low model complexity. Overall, these results highlight the potential of PLNet as an effective lightweight framework that balances segmentation performance and computational complexity.

  • research-article
    Bora Çavdar, Erdinç Şahin, Fatih Mehmet Nuroğlu
    2026, 11(4): 1062-1087. https://doi.org/10.1049/cit2.70156

    Load-frequency control (LFC) comprises a primary process in interconnected electrical power systems, playing a critical role in maintaining the stability and reliability of the electrical grid. It is of paramount importance that the designed controller functions in an optimal manner, particularly with regard to the compression of area frequency and tie-line power deviations within the scheduled limits. In light of these considerations, this study puts forth the inaugural derivative-free and delay-based application of a predictive proportional-integral (PPI) and its fractional-order approach (FOPPI) controllers to address the LFC challenge in a PV-integrated two-area power system. To attain the most effective controller parameters of the PPI and FOPPI, the artificial rabbits optimisation (ARO) methodology is utilised by aiming to minimise the integral of the time-weighted absolute error (ITAE) performance measurement. The effectiveness of the proposed FOPPI controller is evaluated through a comparative analysis of existing controller structures in the literature and the classical PPI controller based on reported ITAE values in the literature. The proposed approach is validated through a series of detailed and systematic performance evaluations, such as time-domain analysis, uncertainty in system parameters, stochastic loading conditions, stability analysis and cyberattack performance of the proposed controllers. Furthermore, a cyberattack detection index for the controllers is considered together with a statistical analysis, and the dataset and simulation models supporting the study are made available as described in the Data Availability Statement. As evidenced by the outcomes of the performance assessments, the FOPPI controller, as conceptualised in this investigation, displays an augmented capacity for dynamic response and resilience in the face of specified scenarios when contrasted with alternative methodologies, including the PPI controller.

  • research-article
    Wenshuai Wang, Shiyu Liu, Peifeng Jiang, Hong Liu, Runwei Ding
    2026, 11(4): 1088-1103. https://doi.org/10.1049/cit2.70152

    Achieving high accuracy and synergy remains extremely difficult for multi-robot embodied visual localisation, which suffers from persistent real-world challenges such as viewpoint ambiguity, appearance variation and dynamic occlusion. Conventional optimisation-based methods often lead to incorrect feature matching without domain adaptation, whereas existing deep learning models are limited in both precision and generalisability for pose regression. Although semantic information can offer a cognitive-level scene representation, its potential has not been fully exploited due to inconsistent labelling and scaling. To address these issues, this paper proposes a novel semantic and synergic consensus framework (termed SSC-MR) that enhances image retrieval and pose estimation by leveraging multi-granular semantics and multi-robot consensus. Specifically, the spatial topology is attentively generated as a global scene graph for fast image retrieval across heterogeneous robots in a holistic workspace, whereas a local semantic-guided pose estimation strategy refines matched keypoints under semantic consistency constraints. To further improve the efficiency of multi-robot collaboration, an intra-robot minimum redundancy consensus module selects informative keyframes and compresses feature representations to reduce perceptual redundancy, and an inter-robot maximum correlation consensus module further establishes high-confidence state associations among interacting robots for knowledge sharing. Extensive experiments on five public datasets demonstrate that the proposed SSC-MR obtains superior effectiveness and robustness across diverse indoor and outdoor scenes, providing a reliable and scalable solution for embodied visual localisation in practical robotic applications. Notably, it achieves a 62.1% improvement in localisation accuracy with nearly 22× faster speed compared to a typical distributed architecture for 10 collaborative robots.

  • research-article
    Parham Imanzadeh Charandabi, Shivakumara Palaiahnakote, Apostolos Antonacopoulos, Christian Clausner
    2026, 11(4): 1104-1126. https://doi.org/10.1049/cit2.70169

    Flood detection is essential for real-time applications, including disaster management, emergency response, and alerting people in flood zones. For successful flood detection, accurate flood region segmentation is essential. However, the flood region segmentation is challenging due to the complex background and occlusions with debris and the effect of external adverse factors. In contrast to existing models that focus on satellite and remote sensing images, for real-time applications, this study proposes a new Transformer-based Multi-Scale-Attention U-Net (TMSA-Net) model for flood region segmentation in images with cluttered backgrounds. The proposed model extracts features hierarchically using a Convolutional Neural Network (CNN) encoder. The deepest features are fed to an adapted vision transformer for extracting global context. In the decoder, Multi-Scale Attention Gates are used in skip connections to selectively filter encoder features before fusion. The proposed model is compared with state-of-the-art methods, including Swin-UNet, DeepLabV3+, TransUNet, UNet++, and Attention U-Net. Experimental results show that TMSA-Net achieves a test IoU of 92.01%, with improvements of 2.82% and 5.95% IoU over DeepLabV3+ and TransUNet, respectively, demonstrating the effectiveness of the proposed approach. The newly created experimental dataset, with ground truth at the pixel level, will be publicly available (released upon acceptance).

  • research-article
    Jiaye Wei, Xin Xu, Yixing Lan, Tenglong Liu, Yueying Wang
    2026, 11(4): 1127-1143. https://doi.org/10.1049/cit2.70094

    Offline reinforcement learning (RL) is a paradigm that seeks to train policies directly based on fixed datasets derived from previous interactions with the environment. However, offline RL faces critical challenges in environments characterised by sparse rewards and datasets dominated by suboptimal trajectories. In this article, we propose a simple and efficient offline RL framework via advantage-guided transformer (AGT). Different from previous works, AGT promotes an advantage-guided policy constraint into the loss function during policy training that adaptively learns the features of trajectories with high advantage values. Furthermore, AGT samples actions with high advantage values during action generation, replacing manual designs with advantage values to update the return-to-go (RTG) as conditional inputs, to ensure action consistency with expected returns. Theoretical analysis shows that AGT's policy improvement guarantees convergence to near-optimal policies in environments with low stochasticity. Extensive experiments on D4RL benchmarks, including robotic locomotion control, dexterous manipulation and maze navigation tasks, show AGT outperforms state-of-the-art (SOTA) offline RL methods.

  • research-article
    Haixin Jia, Han Wang, Xiaoqiang Shi, Guoying Zhang, Hanqi Jiang, Jianbo Peng
    2026, 11(4): 1144-1160. https://doi.org/10.1049/cit2.70129

    To achieve high-precision real-time crack segmentation, we propose TriCrackNet, an efficient network based on a tri-branch collaborative architecture incorporating boundary constraints, semantic parsing, and spatial refinement. In the semantic branch, efficient atrous spatial pyramid pooling (EASPP) is integrated. The EASPP performs feature grouping and efficiently utilises each group's features through hierarchical residual connections. Simultaneously, it employs progressive dilated convolutions with incrementally expanding receptive fields to comprehensively capture multi-scale crack features. Meanwhile, an efficient feature enhancement module (EFEM) was inserted between the semantic branch and the other two branches. This module selectively utilises global features from the semantic branch to provide semantic guidance for the other branches, while enabling self-adaptive enhancement of local features in the target branches based on their own feature characteristics. Finally, the features of the last three branches are efficiently fused through an efficient feature fusion module that performs adaptive spatial weight weighting. Compared with other state-of-the-art methods, TriCrackNet achieves the best trade-off between inference speed and accuracy on CrackForest, Crack500, and DeepCrack datasets.

  • research-article
    Xianjing Cheng, Lintai Wu, Jie Wen, Tianhao Peng, Yong Xu, Zairong Wei
    2026, 11(4): 1161-1178. https://doi.org/10.1049/cit2.70124

    Semantic scene completion (SSC) aims to predict the semantic occupancy and geometry of 3D scenes. Recently, most studies focus on camera-based approaches due to the rich visual cues of images and the cost-effectiveness of cameras. However, these methods usually lack efficient fusion and fine-grained processing of cross-modal semantic information, resulting in sub-optimal performance. To address these issues, we propose a novel cross-modal semantic deep fusion framework. Unlike previous approaches, our method effectively integrates 2D textural, 2D spatial and 3D geometric knowledge from three different modalities to reconstruct complete 3D scenes. Specifically, we employ two encoders to extract 2D textural and 2D spatial features from RGB images and depth maps, which are then fused and lifted into 3D space via our tailored cross-modal semantic fusion module. In contrast to previous methods that encompass extensive redundant 3D voxel features, we design a lightweight voxel feature filter to efficiently eliminate these redundancies. Furthermore, 3D geometric features are extracted from the point cloud derived from the depth map. The 3D features from multiple modalities are deeply fused and further refined by a sparse-to-dense voxel completion module, which effectively enriches the semantic information. Besides, we propose a new evaluation metric more suitable for assessing the SSC task with class imbalance issues in the dataset. Extensive experiments show that our method achieves the state of the art in camera-based semantic scene completion. We will release the source code publicly.

  • research-article
    Guoyu Zuo, Minghui Zhang, Jingwei Ren, Qifei Wu, Jiaxin Li, Jianyu Chen, Chengyu Qiao, Shuangyue Yu
    2026, 11(4): 1179-1193. https://doi.org/10.1049/cit2.70165

    Knee joint moment estimation is a critical component in biomechanical analysis, with profound implications for rehabilitation assessment and the development of assistive devices like exoskeletons. However, existing data-driven approaches often rely on highly complex network architectures in pursuit of high accuracy, resulting in inherently inefficient training procedures. Furthermore, incorporating new subject-specific data typically requires retraining the entire model, which substantially increases computational cost. These limitations make it challenging for current data-driven methods to achieve personalised knee joint moment estimation. To address this challenge, this paper proposes a novel framework based on an Incremental Broad Learning System (IBLS) that can achieve efficient model training through a flattened network architecture and an analytical ridge regression solver. More importantly, it integrates an incremental learning algorithm that enables rapid model updates using only newly acquired subject-specific data, eliminating the need for costly full retraining. These capabilities collectively make efficient personalised knee joint moment estimation feasible. Extensive experiments on Dataset A and Dataset B demonstrate that our method achieves higher prediction accuracy compared to standard baselines (ANN and LSTM). Furthermore, our approach exhibits competitive performance when compared with advanced deep learning architectures (Transformer and TCN-LSTM). Notably, the training efficiency is significantly enhanced: the training time required by our method is approximately 30% of that for ANN, 7.5% for LSTM, and only 3.5% for both the Transformer and TCN-LSTM. Further experimental evidence indicates that incorporating incremental learning provides an additional 60% reduction in training time relative to full retraining, without sacrificing prediction accuracy. In addition, we systematically identify optimal Inertial Measurement Unit (IMU) configurations that balance accuracy with practical wearability, providing actionable guidelines for implementation. This work provides an efficient, accurate, and personalised solution for knee joint moment estimation, paving the way for the development of adaptive and efficient wearable robotic systems.

  • research-article
    Xiaojia Wang, Ziqing Luo, Chaoxu Mu
    2026, 11(4): 1194-1214. https://doi.org/10.1049/cit2.70154

    As an attestation engagement, auditing is required to provide reasonable assurance for its conclusions. Traditional auditing has limited capacity to handle unstructured data and is usually based on audit sampling techniques, which can lead to the neglect of important audit evidence during the auditing process and result in a higher audit risk, making the assurance level uncon trollably guaranteed. Meanwhile, the nature of attestation risk, which is characterised by multi-factor triggering chain trans mission and time evolution, brings difficulties to the acquisition of critical audit evidence. Therefore, this paper realizes the Full- chain Loop Tracking Audit through the business cycle audit process of ‘Obtaining Evidence of Internal Sequential Timing Audit-Obtaining Evidence of Horizontal Expansion of Audit Matters-Penetrating the Multi-Dimensional Evidence Associ ation Rules-Achieving the Anchor Point at The Reasonable Assurance Level’. This is called the Full-chain Loop Tracking Auditing framework (FcLTA framework). Firstly, ‘Obtaining Evidence of Internal Sequential Timing Audit’ is a process of identifying and obtaining abnormal trends in accounting book facts. This process obtains ‘Time Series Audit Evidence’ by embedding the time characteristics of audit evidence in the risk feature vector within the table. Secondly, ‘Obtaining Evidence of Horizontal Expansion of Audit Matters' is a ‘Triangular Verification’, system constructed by integrating financial, business and public opinion data. This process provides ‘Horizontal Expansion Audit Evidence’ by identifying isolated risk signals in financial information to address issues such as discrepancies between accounts and reality and performance whitewashing. Thirdly, ‘Penetrating the Multi-Dimensional Evidence Association Rules' is a process of integrating audit evidence and resolving con flicts. This process generates ‘Multi-Dimensional Penetration Audit Evidence Chain’ by constructing a high-order association across modalities and dimensions for verifying risks. Finally, ‘Achieving the Anchor Point at The Reasonable Assurance Level’ is a testing process for detecting risks with the goal of obtaining high-level assurance of audit evidence. It mainly includes two processes: predicting the level of audit assurance and determining whether to continue the audit. This paper has implemented the full-chain circular tracking audit through the FcLTA framework, and the generated audit evidence can meet the high-level assurance requirements of the attestation engagements, reducing the risk of audit failure.

  • research-article
    Jiajun Su, Yifan Shi, Pudu Liu, Jianqing Zhu, Huanqiang Zeng, Liu Liu, Zhen Lei
    2026, 11(4): 1215-1230. https://doi.org/10.1049/cit2.70163

    Fine-grained alignment is crucial for text-based person retrieval, which searches for relevant pedestrian images using a text query. However, background clutter and semantically vacuous words can cause interference and misalignment, hindering retrieval performance. Existing methods employ masked language modelling to randomly mask and predict words, or leverage multimodal large language models to generate diverse and pure samples. However, these methods rely on external tools and are not sufficiently stable or controllable. In this paper, we propose a pedestrian-relevant hierarchical parsing (PHP) module to extract well-aligned fine-grained visual and textual features for alignment. First, we design a coarse relevant feature mapping (CRFM) module, which uses learnable unified tokens to project both modalities into a shared low-dimensional space, enabling coarse-level semantic filtering. Next, we design an expert-driven feature parsing (EFP) module, which integrates the representational power of a mixture of experts with a modality-aware gating mechanism to uncover deep semantic associations between text and image features. Extensive experiments on three public large-scale datasets demonstrate that our approach outperforms existing state-of-the-art methods, achieving, in particular, a 5.68% improvement in mAP and a 4.81% boost in R1 accuracy on the CUHK-PEDES dataset.

  • research-article
    Yishen Liao, Naigong Yu, Hejie Yu, Shufei Fu
    2026, 11(4): 1231-1253. https://doi.org/10.1049/cit2.70167

    Efficient autonomous navigation in complex and unstructured environments without pre-existing maps remains a significant challenge for mobile robotics. Drawing inspiration from rodent neural architectures, this study proposes a brain-mimetic mapless navigation framework for mobile robots. It integrates three key components to achieve autonomous navigation: first, a visual stream-based localisation model utilising object-vector cells to compensate for cumulative path integration errors; second, a navigation-guiding model where the hippocampal-prefrontal circuitry outputs initial paths through exploration and learning, which are then dynamically optimised for obstacle avoidance through a self-organising strategy of hippocampal CA1 place cells incorporating boundary-vector cells' inputs; and finally, the consolidation of these optimised paths into stable navigation habits via spatial cells' theoretical firing rate and spike-timing-dependent plasticity learning rule. Extensive 2D and 3D simulation experiments demonstrate that the proposed framework not only outperforms various baseline algorithms in terms of convergence speed and path efficiency but also exhibits robust error correction under motion noise, rapid habit reshaping during task changes and strong invariance to the initial heading direction. Moreover, real-world experiments on a mobile robot in complex indoor environments further confirm its practical feasibility and effectiveness, which offers a biologically plausible and computationally efficient navigation solution.

  • research-article
    Xiali Li, Yang Xiao, Xiaojun Bi, Yanlong Luo
    2026, 11(4): 1254-1273. https://doi.org/10.1049/cit2.70161

    Handwritten Dongba Character Recognition (HDCR) contains a large number of visually similar characters with subtle and fragile edge cues, posing severe challenges to feature learning. To address this issue, an Edge Channel Aggregation Network (EdgeCANet) model is proposed. The core of EdgeCANet is the Edge Channel Attention Aggregation (ECAA) block, which integrates the Edge-Guided Enhancement Module (EGEM) for edge-aware spatial refinement and the Channel Texture Recalibration Module (CTRM) for channel-wise texture recalibration. Besides, the two-stage misclassified sample weight redistribution fine-tuning scheme based on Exponential Moving Average (EMA) algorithm is proposed to stabilise parameter updates, and to emphasise difficult and highly similar classes. The recognition accuracy of EdgeCANet significantly outperforms state-of-the-art models across the constructed high-similarity datasets HS-DB and HS-S20 K, as well as the public DB1404, OBC306, Sketch-20 K, and ImageNet-Sketch datasets. The results validate that EdgeCANet effectively enhances recognition accuracy for highly similar handwritten characters and ancient minority-script characters, offering more promising applicability for related recognition tasks.

  • research-article
    Ying Kong, Shaoyuan Sun, Yunliang Jiang, Lin Wei
    2026, 11(4): 1274-1283. https://doi.org/10.1049/cit2.70126

    Repetitive motion planning (RMP) for redundant manipulators with high convergent precision becomes an intense research topic due to its more degrees of freedom. In this paper, a specific zeroing neural dynamics (SZND) model for the RMP is first set up via zeroing neurodynamics. After that, a general linear three-step rule is presented and applied to discretise the SZND model. Then, we obtain a three-step discrete SZND (TS-DSZND) model for repetitive kinematics. It is necessary to point out that the stepsize in TS-DSZND algorithm is intimated to the stability of the proposed TS-DSZND. By utilizing linear transformation and the Jury stability criterion, the optimal stepsize interval of the TS-DSZND is obtained by a theorem. Furthermore, the truncation error constant, which tends to be neglected with most of the ZeaD-typed discretisation formulas for the RMP of redundant manipulators, is analysed and exhibits the impact for the convergent accuracy compared with the corresponding three-step rules. Besides, simulative illustrations on various redundant manipulators show the superiority and feasibility of the pro posed TS-DSZND as well as the effective stepsize domain. Finally, a physical experiment on a real UR5 robotic arm for fulfiling a flower-shaped path validates the satisfying performance of the TS-DSZND model.

  • research-article
    Qingguo Lü, Mingyu Guan, Chenglong He, Chen Chen, Xiangguang Dai, Man-Fai Leung, Wei Zhang
    2026, 11(4): 1284-1301. https://doi.org/10.1049/cit2.70122

    In this paper, we investigate a distributed constrained optimisation problem over directed networks. The agents in the networks conduct local computations and communications, endeavouring to collaboratively minimise the aggregation of all locally known convex cost functions subject to a global constraint set. However, since the agents are constantly transmitting information, most existing algorithms for this problem are prone to communication burdens, especially in large-scale networks under a limited communication bandwidth. Problems of this nature emerge in a number of applications, mostly evident in distributed classification tasks, distributed image restoration, distributed compressive sensing etc. To solve these kinds of problems, we propose an effective quantised push-sum distributed adaptive momentum (QPS-DADAM) algorithm. On the one hand, the QPS-DADAM algorithm employs the random quantiser to reduce the communication overhead and avoid the channel blockage. On the other hand, the QPS-DADAM algorithm incorporates the adaptive momentum method into the push-sum protocol to further accelerate the convergence over directed networks. Rigorous theoretical analyses are provided to illustrate that the QPS-DADAM algorithm converges sublinearly to the optimal solution. In addition, numerical simulations further demonstrate the efficacy of the QPS-DADAM algorithm and the correctness of the theoretical discoveries.

  • research-article
    Hongbin Xu, Yin Long, Junlin Wu
    2026, 11(4): 1302-1319. https://doi.org/10.1049/cit2.70149

    Accurate surface-pressure prediction over broad operating envelopes is critical for supersonic aerodynamic analysis and design. To overcome the bottlenecks of traditional computational fluid dynamics (CFD) in real-time performance and computational efficiency, data-driven deep learning methods have emerged. However, existing data-driven models face two fundamental physical challenges: first, the pressure response to Mach number, angle of attack and altitude is strongly spatially heterogeneous, which cannot be adequately captured by traditional global condition fusion methods; second, the inherent strong anisotropy of supersonic flows renders standard isotropic graph construction based on Euclidean distance prone to spurious cross-shock connections, resulting in nonphysical smoothing of predictions. To address these issues, we propose aircraft pressure transformer network (APTNet), a physics-informed deep learning framework that explicitly encodes flow–geometry interactions and streamwise physical priors. Specifically, we first propose a condition-sensitive local modulation (CSLM) module, which utilises a surface-normal–freestream alignment term to distinguish windward and leeward regions, and learns per-point sensitivity fields to implement physically interpretable local pressure modulation via a feature-wise linear modulation (FiLM) mechanism. Furthermore, we introduce a flow-aligned anisotropic graph construction strategy, which reshapes the local receptive fields of graph nodes into ellipsoids elongated along streamlines, enforcing information to propagate preferentially along streamlines and suppressing cross-shock feature mixing. Experiments on diverse complex aircraft configurations demonstrate that APTNet consistently outperforms existing baseline models in terms of both accuracy and efficiency. Beyond quantitative improvements, the model provides interpretable intermediate signals, such as attention maps and feature responses, which can be directly integrated into the aerodynamic design workflow.