Explore the vast range of titles available.

Modeling forest fire spread is a very complex problem, and the existing models usually need some input parameters which are hard to get. How to predict the time series of forest fire spread rate based on passed series may be a key problem to break through the current technical bottleneck. In the process of forest fire spreading, spread rate and wind speed would affect each other. In this paper, three kinds of network models based on Long Short-Term Memory (LSTM) are designed to predict fire spread rate, exploring the interaction between fire and wind. In order to train these LSTM-based models and validate their effectiveness of prediction, several outdoor combustion experiments are designed and carried out. Process data sets of forest fire spreading are collected with an infrared camera mounted on a UAV, and wind data sets are recorded using a anemometer simultaneously. According to the close relationship between wind and fire, three progressive LSTM based models are constructed, which are called CSG-LSTM, MDG-LSTM and FNU-LSTM, respectively. A Cross-Entropy Loss equation is employed to measure the model training quality, and then prediction accuracy is computed and analyzed by comparing with the true fire spread rate and wind speed. According to the performance of training and prediction stage, FNU-LSTM is determined as the best model for the general case. The advantage of FNU-LSTM is further demonstrated by doing comparison experiments with the normal LSTM and other LSTM based models which predict both fire spread rate and wind speed separately. The experiment has also demonstrated the ability of the model to the real fire prediction on the basis of two historical wildland fires.

We developed a robust tri-platform co-simulation framework that integrates Simulink, AMESim, and RecurDyn to address the dynamic inconsistencies observed in traditional tensioning models for tracked vehicles. The proposed framework synchronizes nonlinear hydraulic dynamics, closed-loop control, and track–ground interactions within a unified time step, thereby ensuring causal consistency along the pressure–flow–force–displacement power chain. Five representative operating conditions—including steady tension tracking, random road excitation, steering/braking pulses, supply-pressure drops, and parameter perturbations—were analyzed. The results show that the tri-platform model reduces tracking error by up to 60%, shortens recovery time by 35%, and decreases energy consumption by 12–17% compared with dual-platform models. Both simulations and full-scale experiments confirm that strong cross-domain coupling enhances system stability, robustness, and energy consistency under variable supply pressure and parameter uncertainties. The framework provides a high-fidelity validation tool and a transferable modeling paradigm for electro-hydraulic actuation systems in tracked vehicles and other multi-domain machinery.

In electrical discharge milling (ED-milling), the flow field of the working medium plays an important role in the removal of discharge eroded particles from the discharge gap. In this work, a flow field model between the electrode and workpiece was established based on analysis of the moving path of the eroded particles in the discharge gap. The influence of the single-layer cutting thickness and electrode diameter on the flow field and machining performance was studied via simulations and experiments. Three kinds of new structure electrodes containing multiple holes were designed to improve the eroded particle removal efficiency. The flow field and machining performance of ED-milling with these new electrodes were studied via simulations and experiments. Through the design of multiple holes surrounding the electrode outer wall, the flushing flow field was more conducive to the removal process of the eroded particles. By adopting the newly designed electrode, the ED-milling machining efficiency was improved by 33%.

With the increasing demand for takeaway delivery, more merchants are developing their takeaway delivery system to manage order fulfillment and enhance the consumer online experience. This study presents a mathematical model for merchant-operated takeaway delivery, using an improved ant colony algorithm integrated with K-means to cluster customer locations and determine optimal routes. We propose two fairness strategies—order quantity and travel distance—to ensure equitable workload distribution among riders. The K-means algorithm is enhanced by reallocating cluster assignments based on the nodes’ distances to all cluster centers. The simulation results demonstrate that the designed algorithm and strategies generate efficient optimal delivery plans for merchants.

Based on the analysis of complex terrains and current forest transportation equipment, a forest tracked vehicle prototype LY1352JP was developed. The road model and the virtual prototype of the chassis were constructed using dynamic simulation software RecurDyn. The optimal tension of the vehicle as well as its capabilities for crossing trenches, climbing vertical walls, uphill and downhill slopes were simulated. The simulation results showed that the optimum tension force of the chassis of the vehicle was 63 kN (kilonewton), accounting for 45% of the total vehicle weight. The maximum trench crossing width and vertical obstacle climbing height were 1.35 m and 0.45 m, respectively. The maximum uphill and downhill angles were 50° and 45°, respectively. Tests on the prototype capacity for crossing trenches, and uphill and downhill driving were carried out. The test results were in agreement with the simulation results. A cross-country performance of a fire truck based on the tracked vehicle chassis was conducted in an old-growth forest. Tests verified that the vehicle has a strong forest trafficability performance and can meet the needs for forest transportation.

At present, most studies are focused on converting the vehicle kinetic energy into electrochemical energy for battery storage. During each deceleration period, the kinetic energy is first converted into electromagnetic energy and then stored in the chemical form before being released as the kinetic energy in next acceleration period, which leads to a low transmission efficiency. Secondly, the efficiency of the kinetic energy recovery is limited by the rated capacity of electric drive devices. Thirdly, a single-axis front-drive electric powertrain can only recover the kinetic energy of front wheels. The system proposed in this paper, which included a flywheel, an electromagnetic coupler, and two gear pairs, was arranged in the rear axis. This new configuration could recycle the kinetic energy of the rear wheels for front-driving vehicles. Most of the energy between the wheels and the flywheel was transmitted in the form of mechanical energy, and the power transmitted by the mechanical port of the electromagnetic coupler was not limited by its rated power. Moreover, the battery only needs to recover the slip power of the coupler. Finally, a test bench based on the proposed system was designed and built under deceleration and cruising conditions. The experimental results also proved the functionality of the proposed system.

The simulation of forest fire spread is a key problem for the management of fire, and Cellular Automata (CA) has been used to simulate the complex mechanism of the fire spread for a long time. The simulation of CA is driven by the rate of fire spread (ROS), which is hard to estimate, because some input parameters of the current ROS model cannot be provided with a high precision, so the CA approach has not been well applied yet in the forest fire management system to date. The forest fire spread simulation model LSTM-CA using CA with LSTM is proposed in this paper. Based on the interaction between wind and fire, S-LSTM is proposed, which takes full advantage of the time dependency of the ROS. The ROS estimated by the S-LSTM is satisfactory, even though the input parameters are not perfect. Fifteen kinds of ROS models with the same structure are trained for different cases of slope direction and wind direction, and the model with the closest case is selected to drive the transmission between the adjacent cells. In order to simulate the actual spread of forest fire, the LSTM-based models are trained based on the data captured, and three correction rules are added to the CA model. Finally, the prediction accuracy of forest fire spread is verified though the KAPPA coefficient, Hausdorff distance, and horizontal comparison experiments based on remote sensing images of wildfires. The LSTM-CA model has good practicality in simulating the spread of forest fires.

A single VLP-16 LiDAR estimation method based on a single-frame 3D laser point cloud is proposed to address the problem of estimating negative obstacles’ geometrical features in structured environments. Firstly, a distance measurement method is developed to determine the estimation range of the negative obstacle, which can be used to verify the accuracy of distance estimation. Secondly, the 3D point cloud of a negative obstacle is transformed into a 2D elevation raster image, making the detection and estimation of negative obstacles more intuitive and accurate. Thirdly, we compare the effects of a StatisticalOutlierRemoval filter, RadiusOutlier removal, and Conditional removal on 3D point clouds, and the effects of a Gauss filter, Median filter, and Aver filter on 2D image denoising, and design a flowchart for point cloud and image noise reduction and denoising. Finally, a geometrical feature estimation method is proposed based on the elevation raster image. The negative obstacle image in the raster is used as an auxiliary line, and the number of pixels is derived from the OpenCV-based Progressive Probabilistic Hough Transform to estimate the geometrical features of the negative obstacle based on the raster size. The experimental results show that the algorithm has high accuracy in estimating the geometric characteristics of negative obstacles on structured roads and has a practical application value for LiDAR environment perception research.

Fire spread prediction is a crucial technology for fighting forest fires. Most existing fire spread models focus on making predictions after a specific time, and their predicted performance decreases rapidly in continuous prediction due to error accumulation when using the recursive method. Given that fire spread is a dynamic spatiotemporal process, this study proposes an expanded neural network of long short-term memory based on self-attention (SA-EX-LSTM) to address this issue. The proposed model predicted the combustion image sequence based on wind characteristics. It had two detailed feature transfer paths, temporal memory flow and spatiotemporal memory flow, which assisted the model in learning complete historical fire features as well as possible. Furthermore, self-attention mechanisms were integrated into the model’s forgetting gates, enabling the model to select the important features associated with the increase in fire spread from massive historical fire features. Datasets for model training and testing were derived from nine experimental ground fires. Compared with the state-of-the-art spatiotemporal prediction models, SA-EX-LSTM consistently exhibited the highest predicted performance and stability throughout the continuous prediction process. The experimental results in this paper have the potential to positively impact the application of spatiotemporal prediction models and UAV-based methods in the field of fire spread prediction.

In electrical discharge machining (EDM), the working medium plays an important role in the material removal process. Lots of methods have been utilized to study this process, but a widely accepted explanation about this process has not been yet accomplished. In this study, the acoustic emission (AE) sensor was fixed on EDM machine to study the material removal process by observing the expansion and contraction process of gas bubble surrounding the discharge plasma. The machining performance in different working mediums was studied for Ti-6Al-4V machining in air, kerosene, and water-based emulsion. Discharge in different working mediums would result in different material removal rates and surface quality. The difference of AE wave frequency domain distribution for discharge in different working mediums was studied. It was observed that the frequency of acoustic emission wave generated by discharge in different working mediums would be different. The characteristic difference of single AE wave generated by discharge in air, kerosene, and water-based emulsion was compared. It was found that the duration time and peak amplitude of acoustic emission wave generated by discharge in different working mediums were different, and the acoustic emission wave generated by discharge in water-based emulsion would last longer and get higher peak amplitude compared to discharge in air and kerosene. The significant difference of AE wave generated by discharge in water-based emulsion from that in kerosene was found. Based on the acoustic emission wave observation, the special characteristic of the material removal process for discharge in water-based emulsion was found.