Search

Advancements in autonomous vehicles and deep learning have notably improved vehicle trajectory prediction accuracy. However, extracting interaction features in complex driving scenarios, such as vehicle-to-vehicle interactions and lane constraints, presents challenges. Deep learning-based methods struggle to achieve optimal predictive performance under limited computational resources. This study introduces a global attention mechanism to enhance feature extraction from driving scene encodings, focusing the decoder on interactive behaviours and boosting long-term prediction performance. An adaptive scheduled sampling model is employed, using actual driving scenarios probabilistically for training, addressing slow learning of actual driving behaviours and lack of initial feature correction. This method increases attention to actual interactions, reducing reliance on natural scenes and improving model generalizability. On the NGSIM dataset, sampling attention encoder-decoder (SAED) achieves a 1–5 s average displacement error (ADE) of 1.34 m, with 4 s and 5 s final displacement errors (FDEs) of 1.64 and 2.06 m, respectively. Compared to methods based on long short-term memory (LSTM), SAED reduces the model's storage space by 24.68% under the same network layer count. That demonstrates its effectiveness in extracting interactive behaviours in complex scenarios and enhances the accuracy of long-term predictions.

Research on electric wheel loaders (EWLs) has predominantly focused on battery management, hybrid technologies, and energy recovery. However, the influence of motor types and drivetrains on the drive performance of EWLs has received little attention in previous studies. This case study addresses this gap by examining different EWL configurations and analyzing the drive theory and force requirements by integrating classic vehicle theory with EWL-specific characteristics. The study compares an original EWL, equipped with Permanent Magnet Synchronous Motors (PMSMs) on both the front and rear axles with identical transmission ratios of 22.85, to a modified EWL, which features a Switched Reluctance Motor (SRM) on the front axle and a transmission ratio of 44.05. Walking and shoveling tests were conducted to evaluate performance. The walking test results reveal that, at motor speeds of 200 rpm, 400 rpm, and 600 rpm, energy consumption in R-drive mode is 68.56%, 71.88%, and 74.87% of that in F-drive mode when two PMSMs are used. When an SRM is applied with a transmission ratio of 44.05, these values shift to 73.90%, 70.35%, and 67.72%, respectively. This demonstrates that using the rear motor alone for driving under walking conditions can yield greater energy savings. The shoveling test results indicate that distributing torque according to wheel load reduces rear wheel slippage, and the SRM with a transmission ratio of 44.05 delivers sufficient drive force while operating within a high-efficiency speed range for the EWL.

During the operation of a wheel loader, the external load acting on the bucket undergoes many changes, resulting in significant changes in the load ratio on the front and rear axles. For this reason, controlling a standard wheel loader is not trivial. In addition, in the case of a distributed electric wheel loader (DEWL), the operating control algorithm is often complex and is, therefore, the subject of optimization studies. This study compared the electric power consumption across different vertical loads, speeds, and travel directions for single-front, single-rear, and dual-motor configurations, both during transporting and pre-shoveling operations. The analysis led to the development of control rules based on energy-saving objectives. Under the shoveling condition, it was observed that vertical loads can lead to an insufficient driving force and skidding, necessitating the proposal of a new optimized control scheme. The results revealed that the optimal solution for transporting is the single-motor drive control scheme without a mechanical connection between the front and rear motor. With the single-motor control scheme, comparing the preferred controlled motor with the unselected motor under different loads, the average electrical power savings for forward, backward, and circling were at least 3.51%, 3.12%, and 0.34%, respectively. Under the pre-shoveling condition, the optimal control scheme was identified as the single rear motor control scheme, effectively reducing electrical power consumption. In response to the issues encountered during the shoveling condition, an economical solution involving the modification of the front axle transmission ratio has been proposed, along with an optimized control scheme based on vertical load variations.

The electric wheel loader is a new prototype in powertrains and drivetrains that saves energy consumption and diminishes emissions as earthmoving machinery. Dual-motor drive in the front and rear axles of electric wheel loaders helps the distribution of drive torque. However, challenges arise during shoveling conditions, particularly when one motor generates torque exceeding the ground’s adhesion force, leading to tire slippage. This study thoroughly examines the mechanical structure of the working unit and elucidates the correlation between wheel load and hydraulic pressure in the base chamber of the tilt cylinder. This analysis is accomplished through a combination of theoretical derivations and experimental tests. The experiments involve a 5 ton rated load electric wheel loader tested across five running cases as well as weighing tests on a 15 ton rated load electric wheel loader. Based on the experiment discoveries, a dual-motor drive electric wheel loader is designed with specific transmission ratios for the front and rear drivetrains, and a torque distribution strategy is proposed based on wheel load during shoveling. Running condition tests demonstrate sufficient drive force for the new electric wheel loader, and shoveling tests reveal a significant reduction in tire slippage when employing the proposed torque distribution strategy compared to evenly distributed torque in the front and rear axles. Moreover, the driving force during the shoveling process remains undiminished. This indicates that the newly designed loader, in conjunction with the proposed strategy, exhibits excellent shoveling efficiency.

Wheel loaders consume a large amount of energy, and research on energy savings in wheel loaders has been carried out for decades. This paper introduces several types of wheel loaders and compares their structures. The research progress of the energy savings of three different forms of wheel loaders is reviewed, including a diesel engine wheel loader, a hybrid wheel loader, and an electric wheel loader. In particular, the energy-saving control methods of an electric wheel loader in the working cycle are analyzed, as construction machinery electrification is an emerging trend. Based on the analysis of the driving features and the working process of a wheel loader, energy-saving control methods are introduced including the resistance reduction method, optimized control strategies, intelligent control, and unmanned WL research. Comparing various energy-saving research methods and the advantages of electric wheel loaders, the pure electric wheel loaders are advised to be researched at present and in the future. Controlling the torque distribution of the front and rear motors of electric wheel loaders and assistant drive control are proposed to be significant research prospects for energy savings in wheel loaders usage.

The presented research on electric wheel loaders lacks a detailed analysis of drive energy-saving during the shovel preparation phase, which is characterized by a high probability of loader tire skidding. To address this issue, this study examines the energy consumption efficiency of a two-motor distributed drive wheel loader under three drive modes including front motor drive, rear motor drive, and dual-motor drive, taking into account the change in the drive force demand caused by the bucket landing. This study finds that the motor energy conversion efficiency is the greatest in single-motor drive mode when the bucket does not generate positive pressure with the ground. In dual-motor drive mode, the total torque overcome is greater, but the motor energy conversion efficiency is the greatest when the bucket generates the greatest positive pressure with the ground. This study suggests that in future designs of electric loaders, two motors can be used to distribute the drive, but the front and rear motors should be designed to participate in the drive with a certain torque distribution ratio at different speeds and resistance to avoid the phenomenon of the bucket pressing the ground too much.

To achieve energy-saving control of non-hybrid Hydrostatic Transmission Construction Vehicles (HST-CVs) with traditional closed-loop Hydrostatic Transmission (HST) for both propulsion and working systems, this paper presents a control strategy for non-hybrid HST-CVs by referring to the power follower method of the hybrid Energy Management Strategy (EMS). Through the implementation of the presented control strategy by coordinated control of the engine speed and hydraulic pump displacement, the engine can be controlled to operate at the pre-set low Brake Specific Fuel Consumption (BSFC) area, similar to that of the hybrid vehicles adopting a power follower control strategy but without the additional installation of accumulators in the hydraulic system. The effect of the control strategy is verified via experimental tests and MATLAB/SIMULINK–AMESIM COLlaborative SIMulation (COSIM). The simulation results show that the proposed control strategy can achieve the expected control target under both highway and off-road conditions.

In recent decades, freak waves, characterized by their unusual high amplitude, sharp crest, and concentrated energy, have attracted researchers’ attention due to their potential threat to marine structures. Green-water loads caused by freak waves can be significant and may lead to local damage to the ship structures. Therefore, this paper focuses on the study of green-water loads and examines the structural responses of ship bow structures under the influence of the green-water loads caused by freak waves. Firstly, a three-dimensional numerical wave tank is established in which the superposition model is used to generate freak waves. Validations on the freak-wave generation, ship motion response and the wave loading are carried out to verify the present solvers. The simulation on the interaction between the freak wave and the ship are conducted to obtain the interaction process and green-water loads. Secondly, a finite element (FEM) model of the ship bow is built, on which the green-water loads are applied to calculate the structural responses. Finally, the displacement and stress of the deck and breakwater structures are analyzed. It is found that green water events caused by freak waves can generate enormous impact forces on the bow deck and breakwater, resulting in severe structural responses and even possible damage to the structures. The local strength of structures under freak waves needs to be considered in practical engineering applications.

Estimation of the center of gravity (CG) is the basis for intelligent control of the front-and-rear-axis-independent electric driving wheel loaders (FREWLs). This paper presents a novel real-time method for estimating the CG of FREWLs, which is suitable for driving and spading conditions on bumpy roads. A FREWL dynamical model is proposed to set up the state-space model. The CG estimator is used to estimate the longitudinal tire force using the state-space model and the improved square-root unscented Kalman filter (ISR-UKF) algorithm. The simulation and experimental results indicate that this method is suitable for FREWL dynamics and operational characteristics, and the estimated value of CG basically converges to the reference value. Finally, the probable reasons for error occurring in two experiments and the practical challenges of this method are discussed. The research in this paper establishes a partial theoretical basis for intelligent control of construction machinery.

With the increasing attention of energy saving and emission reduction technology, the recent application of hybrid powertrain technology affects the development of construction machinery industry. This article reviews these publications and provides comprehensive references. This article reviews the state-of-art for the hybrid wheel loader and excavator, which focuses on powertrain configuration, energy storage devices, and energy management strategies. The basis of classification and characteristic of each powertrain configuration are described. Advantages and disadvantages of batteries, supercapacitors, hydraulic accumulators, and flywheel used in hybrid construction machinery are summarized. The existing energy management strategies for hybrid construction machinery are also elaborated. The technological challenges and developing trends in the near future for hybrid construction machinery are discussed.

In typical metal foundry applications, sand casting is still the most used technology. The related binder plays a very important role as its performances can directly influence the quality of castings. Among many binders, glues of animal origin have attracted much attention in recent years due to their reduced environmental impact. However, they display some drawbacks such as the tendency to coagulate easily at room temperature and a relatively low strength. In this study, a novel gas-hardening casting binder was prepared using an animal glue and anhydrous potassium carbonate as a hydrolyzing agent to avoid undesired agglomeration. Moreover, sodium pyrophosphate and furfuryl alcohol were exploited as modifiers to obtain a binder with a high compressive strength. The best modification conditions, determined by means of an orthogonal design matrix approach, were 4 g of Na2CO3, sodium pyrophosphate, furfuryl alcohol and animal glue with a ratio of 4:12:100, at 85°C and with a duration of 115 min, respectively. The viscosity of the mixture obtained under these optimized conditions was 1250 mPa•s. The compressive strength of the binder, hardened by CO2 gas, was 4.00MPa. Its gas evolution at 850°C was 15 ml•g-1, and its residual strength after 10 min calculation at 800°C was 0.01 MPa, which is high enough to meet the requirement of core-making in foundry. Moreover, after hydrolysis and further modification, animal glue and modifiers displayed a grafting reaction and an esterification reaction, respectively, which made the adhesive network denser and improved its thermal stability. [ABSTRACT FROM AUTHOR]

Multi-bridge centralized drive wheel loaders can produce parasitic power to waste energy and aggravate tire wear. Distributed Electric Wheel Loader(DEWL) is a new structure with two drive motors that can be controlled independently or in concert. Hence, this study investigates the mechanical characteristics of DEWL in its shoveling condition. Firstly, for the DEWL, dynamic models are established including running and shoveling conditions, on the basis of automobile theory. Secondly, a simplified structural model of DEWL is used to construct the mechanical equations, and the theoretical derivation is utilized to analyze the forces on wheels during different driving modes of running and shoveling conditions. Finally, the free shoveling of dry sands and gravel materials is tested by a ZL50GV-EV DEWL, and the drive forces of three drive modes on horizontal concrete pavement are tested. The results show that the parasitic power is generated when the driving motor has a larger speed than that of the other motor, which is caused by the movement of the loader's center of gravity. The driving torques generated by the motors are basically the same when the DEWL is in front-drive mode and rear-drive mode at the setting speed of 600rpm, whether it is running forward or backward, with a torque fluctuation of 0.16%-1.28% and a power fluctuation of 0.02%-1.29%. The DEWL consumes more power in dual-drive mode than in single drive if it is controlled in speed-target mode. [ABSTRACT FROM AUTHOR]