In order to improve the flight efficiency of a flying–walking power transmission line inspection robot (FPTLIR) during flight missions, an accurate energy consumption model is constructed, and a multiobjective optimization approach using the improved NSGA-II is proposed to address the high energy consumption and long execution time. The energy consumption model is derived from the FPTLIR kinematics to the motor dynamics, with the key parameters validated using a test platform. A multiobjective optimization model is proposed that considers many constraints related to the FPTLIR during missions, offering a comprehensive analysis of the energy consumption and execution time. The NSGA-II algorithm is improved by integrating the Cauchy variation operator and the simulated annealing algorithm, which is used to construct the multiobjective optimization approach. Simulation and experimental results demonstrate that the proposed model accurately predicts the energy consumption of the FPTLIR across different paths and flight conditions with an average relative error ranging from 0.76% to 3.24%. After optimization, energy savings of 5.33% and 5.01% are achieved for on-line and off-line missions, respectively, while maintaining the shortest execution time at the given energy level. The energy consumption optimization approach significantly improves the flight efficiency of the system, providing a reference for analyzing and optimizing energy consumption of inspection robots.

To improve the mechanization levels of red cluster pepper harvesting in hilly and mountainous regions of southwest China, a crawler-type harvester is developed to suit the local planting and growth characteristics of red cluster pepper and to facilitate mechanized picking, conveying, and collecting processes. The design, supported by theoretical calculations and structural analysis, includes detailed studies of the picking, conveying, and collecting mechanisms, as well as the hydraulic system. Factors affecting picking efficiency were identified. ADAMS simulation was used to determine the optimum rotational speed range for the spring-tooth roller by analyzing its trajectory. A prototype was then built and field tested with forward speed and the spring-tooth roller’s rotational speed as variables to assess impurity, damage, loss, and hanging rates. Data from these tests were analyzed using Design Expert software, which created a mathematical model relating the test indices to the two variables. Optimum parameters were identified, resulting in a harvester configuration that achieved an average productivity of 0.21 ha·h⁻¹ at a forward speed of 1.75 m·s⁻¹ and a roller rotational speed of 181 r·min⁻¹. The impurity rate was 26.7%, the loss rate was 6.1%, the damage rate was 2.3%, and the hanging rate was 4.2%, conforming to the industry standard DG/T 114-2019. This research provides a viable solution for mechanized harvesting of red cluster pepper in hilly and mountainous regions with small planting plots.

To address power transmission lines (PTLs) traveling through complex environments leading to misdetections and omissions in fitting recognition using cameras, we propose a fitting recognition approach combining depth-attention YOLOv5 and prior synthetic dataset to improve the validity of fitting recognition. First, datasets with inspection features are automatically synthesized based on prior series data, achieving better results with a smaller data volume for the deep learning model and reducing the cost of obtaining fitting datasets. Next, a unique data collection mode is proposed using a developed flying-walking power transmission line inspection robot (FPTLIR) as the acquisition platform. The obtained image data in this collection mode has obvious time-space, stability, and depth difference, fusing the two data types in the deep learning model to improve the accuracy. Finally, a depth-attention mechanism is proposed to change the attention on the images with depth information, reducing the probability of model misdetection and omission. Test field experiments results show that compared with YOLOv5, the mAP5095 (mean average precision on step size 0.05 for thresholds from 0.5 to 0.95) of our depth-attention YOLOv5 model for fitting is 68.1%, the recall is 98.3%, and the precision is 98.3%. Among them, AP, recall, and precision increased by 5.2%, 4.8%, and 4.1%, respectively. Test field experiments verify the feasibility of the depth-attention YOLOv5. Line field experiments results show that the mAP5095 of our depth-attention YOLOv5 model for fittings is 64.6%, and the mAPs of each class are improved compared with other attention mechanisms. The inference speed of depth-attention YOLOv5 is 3 ms slower than the standard YOLOv5 model and 10 ms to 15 ms faster than other attention mechanisms, verifying the validity of the depth-attention YOLOv5. The proposed approach improves the accuracy of the fitting recognition on PTLs, providing a recognition and localization basis for the automation and intelligence of inspection robots.

To address the fuzzy reconstruction effect on distant objects in unbounded scenes and the difficulty in feature matching caused by the thin structure of power lines in images, this paper proposes a novel image-based method for the reconstruction of power transmission lines (PTLs). The dataset used in this paper comprises PTL progressive motion sequence datasets, constructed by a visual acquisition system carried by a developed Flying–walking Power Line Inspection Robot (FPLIR). This system captures close-distance and continuous images of power lines. The study introduces PL-NeRF, that is, an enhanced method based on the Neural Radiance Fields (NeRF) method for reconstructing PTLs. The highlights of PL-NeRF include (1) compressing the unbounded scene of PTLs by exploiting the spatial compression of normal $L^{\infty }$; (2) encoding the direction and position of the sample points through Integrated Position Encoding (IPE) and Hash Encoding (HE), respectively. Compared to existing methods, the proposed method demonstrates good performance in 3D reconstruction, with fidelity indicators of PSNR = 29, SSIM = 0.871, and LPIPS = 0.087. Experimental results highlight that the combination of PL-NeRF with progressive motion sequence images ensures the integrity and continuity of PTLs, improving the efficiency and accuracy of image-based reconstructions. In the future, this method could be widely applied for efficient and accurate 3D reconstruction and inspection of PTLs, providing a strong foundation for automated monitoring of transmission corridors and digital power engineering.

The operational complexities of the elastic tooth drum pepper harvester (ETDPH), characterized by variable drum loads that are challenging to recognize due to varying pepper densities, significantly impact pepper loss rates and mechanical damage. This study proposes a novel method integrating complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), kernel principal component analysis (KPCA), and a support vector machine (SVM) to enhance drum load recognition. The method consists of three principal steps: the initial experiments with ETDPHs to identify the critical factors affecting drum load and to formulate classification criteria; the development of a CEEMDAN-KPCA-SVM model for ETDPH drum load recognition, where drum spindle torque signals are processed by CEEMDAN for decomposition and reconstruction, followed by feature extraction and dimensionality reduction via KPCA to refine the model’s accuracy and training efficiency; and evaluation of the model’s performance on real datasets, highlighting the improvements brought by CEEMDAN and KPCA, as well as comparative analysis with other machine learning models. The results describe four load conditions—no load (mass of pepper intake (MOPI) = 0 kg/s), low load (0 < MOPI ≤ 0.658 kg/s), normal load (0.658 < MOPI ≤ 1.725 kg/s), and high load (MOPI > 1.725 kg/s)—with the CEEMDAN-KPCA-SVM model achieving 100% accuracy on both training and test sets, outperforming the standalone SVM by 6% and 12.5%, respectively. Additionally, it reduced the training time to 2.88 s, a 10.9% decrease, and reduced the prediction time to 0.0001 s, a 63.6% decrease. Comparative evaluations confirmed the superiority of the CEEMDAN-KPCA-SVM model over random forest (RF) and gradient boosting machine (GBM) in classification tasks. The synergistic application of CEEMDAN and KPCA significantly improved the accuracy and operational efficiency of the SVM model, providing valuable insights for load recognition and adaptive control of ETDPH drum parameters.

To enhance the safety of hybrid inspection robots (HIRs) landing on power transmission lines (PTLs) with inclination and flexibility, this research derives a coupled dynamic model for a developed flying–walking power transmission line inspection robot (FPTLIR) to analyze the dynamic behavior of the FPTLIR during the landing process. The model uses the absolute nodal coordinate formulation (ANCF) for the dynamics of the PTL and the Hunt–Crossley theory for the contact model, integrating these components with the Euler–Lagrange method. A modular simulation was conducted to evaluate the effects of different landing positions and robot masses. An experimental platform was designed to evaluate the landing performance and validate the model, which confirms the method’s accuracy, with a mean relative Z-displacement error of 0.004. Simulation results indicate that Z-displacement decreases with increased landing distance, with the farthest point showing only 34.4% of the Z-displacement observed at the closest point. Conversely, roll increases, with the closest point exhibiting 3.7% of the roll at the farthest point. Both Z-displacement and roll are directly correlated with the robot’s mass; the lightest robot’s Z-displacement and roll are 9.2% and 12.8% of those of the heaviest robot, highlighting the safety advantage of lighter robots. This research enables precise analysis and prediction of the system’s responses during the landing process, providing significant insights for safe landing and design.