For the nut connection problems of narrow and deep cavity, invisibility, no access to traditional operating tools of aero-engine rotor, a new automation assembly method is advocated based on the image recognition and laser assisted positioning technology. The automated blind assembly torque device is developed with the functions of automatic folding of wrench head, accurate positioning, rapid nut recognizing, and electric loading, which can enter the narrow and deep operation space that is invisible to naked eye, to solve the low-level errors caused by artificial missing and wrong nuts, avoiding collision and damage on the inner wall of the shaft cavity. The device can carry out the compound tightening strategy with torque and angle to achieve the accurate automatic connection of engine rotor nut all the time, and the %GageR&R and %P/T of system precision are %22.21, %3.78 respectively through the test of automatic blind nut assembly, which will increase the accuracy and consistency on the large degree, which will lay the important foundation of the working stability and reliability of aero-engine farther.

Lightweight design is an effective way to improve the economic and environmental protection of static pile driver, as the key component of the static pile driver, the combined fixture is important for its lightweight design. To realize the combined fixture structure safety and lightweight design goal, a three-dimensional model is established by using solid works, and ANSYS Workbench is used to analyze and evaluate the equivalent stress of the whole structure and main components under the condition of pile pressing. Based on the results of analysis and evaluation, the topology optimization method of superposition replacement is adopted to carry out the structural optimization design, while meeting the needs of safety and engineering practice, its total quality is reduced by about 30%, and the economic and environmental benefits are obvious.

Aiming at the problems of multi-dimensional small failure probability and implicit function in the reliability analysis for bridge crane structure, that is difficult to solve using traditional reliability analysis methods, the one based on dynamic Kriging surrogate model combined with important sampling method is proposed. Firstly, the dynamic Kriging surrogate model of the implicit function is constructed utilizing two learning functions, and then the most probable failure point (MPP) is obtained by using the improved first order second moment method combined with the Kriging surrogate model. Secondly, the importance sampling density function is constructed with the MPP as the central point. Finally, the reliability degree is calculated by the importance sampling method based on the established surrogate model. By introducing a new stop criterion combined with learning function, the number of finite element calls is reduced. Verified by an engineering case, the proposed method can well balance the model accuracy, result error and calculation cost.

A monitoring system for transportation of material ropeway of transmission line is designed for the difficulty in fully understanding the construction process and component stress state of material ropeway of transmission line. Based on wireless ad hoc network technology, tension sensors, high-precision positioning modules, and ad hoc network devices are integrated to achieve real-time collection and transmission of monitoring data for material ropeway transportation, such as tension of carrying rope, load of steering pulley, load of running car, position of running car, speed of material transportation. By combining the refined calculation method of material ropeway, the tension of the working rope during the transportation process of the material ropeway is calculated, which is compared with the monitoring data, and the visual display of the monitoring data and image data of the material ropeway transportation is achieved to realize the real-time monitoring of the material ropeway transportation status during the construction process. Through verification tests in transmission line engineering, the effectiveness and accuracy of the monitoring system for transportation of material ropeway of transmission line have been verified, which provides technical support for the transportation safety during the construction of the material ropeway.

The paper introduces mechanical character of boom for luffing jib crane, structural form and construction type of the inverted-Y boom are explained. A conversion section is arranged in the middle of the boom, the hoisting or luffing wire rope enters the boom head after bypassing the conversion section, the load of the boom is reduced by the pull of the wire rope. The example of derrick crane with maximum rated lifting capacity of 500 t is given, calculation of the boom shaft pressure, boom dead weight bending moment, wire rope tension and other loads on the boom chord of the magnitude of the axial force exerted, and analyze its proportion. It shows that the effect of hoisting or luffing wire rope can effectively reduce the dead weight bending moment of the boom, and offset part of the boom chord and belly rod axial force, improve the overall stability and bearing capacity of the boom, thus the design of the boom is optimized.

With the wide application of target detection technology in unmanned construction and other scenarios, traditional target detection algorithms face challenges such as low recognition accuracy, large computational volume, and slow processing speed in complex engineering environments. Based on these challenges, this paper proposes a target detection method based on improved YOLOv8 for engineering scenes, which improves the C2f structure by introducing the star block in YOLOv8, significantly reducing the number of model parameters and computational volume while ensuring the detection accuracy. Based on this, this paper introduces a lightweight shared and detail-enhanced convolutional detection head, which further improves the detail-capturing ability of the detection head and significantly reduces the computational burden. The experimental results show that compared with YOLOv8n on Roboflow-based engineering scene dataset, the mAP@0.5 and mAP@0.5: 0.95 of the improved model improves by 0.3% and 2.0%, while the number of parameters and computational volume decreases by 36.7% and 34.6%, and improves the frames per second (FPS) by 23.3% accordingly, which verifies the superiority of the improved algorithm in terms of lightweight and detection accuracy.

In shield construction, the tunneling attitude of the shield tunnel is an important parameter affecting the quality of the tunneling, which directly affects the track and the quality of the tunnel. Taking an earth pressure balance tunnel boring machine (TBM) as an example, the relationship between the weight of the main machine and the earth pressure and the bearing capacity of the foundation is determined from the theoretical level at the design of the shield machine, which is based on the analysis of the floating and sinking. The influence of the uneven mass distribution on the center of gravity is further analyzed. Finally, through the comprehensive study of the relationship between the force of the host and the thrust of the cylinder under the soil pressure model, the necessary conditions for the control of the driving attitude of the shield machine are determined. The results of this paper have important practical siginificance for improving the design and manufacturing of the shield machine and the construction level of the shield method in China.

This paper proposes a robotic grasping technique based on object recognition and fully convolutional grasp quality convolutional neural network (FC-GQCNN). To address the limitations of traditional GQCNN, such as low computational efficiency and redundant feature calculations, an improved FC-GQCNN is developed. By replacing the fully connected layers in GQCNN with 1×1 convolutional layers, the proposed network can handle input images of arbitrary sizes. Furthermore, the integration of FC-GQCNN with the YOLOv8 object detection algorithm forms a YOLOv8-FCGQCNN cascade structure, effectively solving the challenges of object recognition and localization in complex environments. Experimental results demonstrate that this method achieves an 86% grasp success rate across 10 different objects, with an average detection time of 0.09 s per frame, which is 22 times faster than traditional GQCNN, significantly improving system efficiency. This method can accurately detect the grasping position of the object of interest and has higher reliability than the baseline method.

Middle outrigger is the main support leg of tunnel erecting machine, and hydraulic system plays an important role in the erection process of prefabricated utility tunnel sections. To solve the problems of slow action and low positioning accuracy of hydraulic cylinder of middle outrigger, the hydraulic system of tunnel erecting machine is optimized through on-site experiments and AMESim simulation analysis. According to the erection process and hydraulic system principle of tunnel erecting machine, a preliminary analysis and on-site measurements of original middle outrigger hydraulic system are conducted, and an optimized system scheme applying high-frequency response proportional valve and accumulator is proposed. Then, the reasonable accumulator working parameters of optimized hydraulic system are explored, and the high-frequency response proportional valve control strategy based on feedforward compensation is studied. Finally, the optimized hydraulic system is simulated and compared with measurement data. The results show that the combination of high-frequency response proportional valve and accumulator can significantly improve the response characteristics and position control accuracy of hydraulic system. The hydraulic cylinder displacement of optimized system is increased by 82.2% within 0.5 s of system startup, and the maximum hoisting positioning error is ±2.0 mm, which can meet the erection and installation requirements of utility tunnels.

Aiming at the problem of motor failure caused by complex factors interacting and interfering during the operation of pure electric mining trucks, a method based on principal component analysis (PCA) and random forest (RF) is proposed for predictive diagnosis. A dataset is constructed based on the actual collected motor failures of electric mining trucks, and the eigenvalue extraction and dimensionality reduction of the failure data are carried out using principal component analysis to reduce the dimensional redundancy of the data; the random forest prediction model is used to train and test the dimensionality-reduced data, and to predict the motor failure categories. The results show that the accuracy of motor fault type diagnosis using PCA-RF method reaches more than 97%, which is significantly improved compared with the accuracy of the method without dimensionality reduction processing. The accuracy of the above method for motor fault diagnosis of electric mining trucks is confirmed.