Search

Path planning and obstacle avoidance are fundamental problems in unmanned ground vehicle path planning. Aiming at the limitations of Deep Reinforcement Learning (DRL) algorithms in unmanned ground vehicle path planning, such as low sampling rate, insufficient exploration, and unstable training, this paper proposes an improved algorithm called Dual Priority Experience and Ornstein–Uhlenbeck Soft Actor-Critic (DPEOU-SAC) based on Ornstein–Uhlenbeck (OU noise) and double-factor prioritized sampling experience replay (DPE) with the introduction of expert experience, which is used to help the agent achieve faster and better path planning and obstacle avoidance. Firstly, OU noise enhances the agent's action selection quality through temporal correlation, thereby improving the agent's detection performance in complex unknown environments. Meanwhile, the experience replay is based on double-factor preferential sampling, which has better sample continuity and sample utilization. Then, the introduced expert experience can help the agent to find the optimal path with faster training speed and avoid falling into a local optimum, thus achieving stable training. Finally, the proposed DPEOU-SAC algorithm is tested against other deep reinforcement learning algorithms in four different simulation environments. The experimental results show that the convergence speed of DPEOU-SAC is 88.99% higher than the traditional SAC algorithm, and the shortest path length of DPEOU-SAC is 27.24, which is shorter than that of SAC. [ABSTRACT FROM AUTHOR]

To address the anti-swing issue of the payload in bridge cranes, Proportional–Integral–Derivative (PID) control is a commonly used method. However, parameter tuning of the PID controller relies on empirical knowledge and often leads to system overshoot. This paper proposes an Improved Sparrow Search Algorithm (ISSA) to optimize the gains of PID controllers, alleviating adverse effects on payload oscillation and trolley positioning during the operation of overhead cranes. First, tent map chaos mapping is introduced to initialize the sparrow population, enhancing the algorithm's global search capability. Then, by integrating sine and cosine concepts along with nonlinear learning factors, the updating mechanism of discoverer positions is dynamically adjusted, expediting the solving process. Finally, the Lévy flight strategy is employed to update follower positions, thereby enhancing the algorithm's local escape capability. Additionally, a fitness function containing overshoot penalties is proposed to address overshoot issues. Simulation results indicate that the overshoot rates of all algorithms remain less than 3%. Moreover, compared with the Sparrow Search Algorithm (SSA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), and Whale optimization Algorithm (WOA), the optimized PID control system with the ISSA algorithm exhibits superior control performance and possesses certain robustness and adaptability. [ABSTRACT FROM AUTHOR]

The current steel brake disk and Cu‐based powder metallurgy brake pad used in high‐speed trains suffer fading coefficient of friction (COF) and excessive wear, resulting in a shorten lifetime and numerous exhausted brake disks. High‐velocity oxygen fuel (HVOF) spray‐prepared coatings have proven their ability to improve COF and decrease wear rate. In this article, Cr3C2‐NiCr coating was sprayed on a steel brake disk, and a series of emergency braking tests under dry and wet conditions were performed on a subscale brake dynamometer, to comprehensively evaluate the braking performance of coated brake disk. The results showed that the coated brake disk exhibits a higher COF at 380 km/h, which effectively inhibits the COF fade compared to the steel brake disk case. The coated brake system also achieves a lower wear rate of the brake pad at 380 km/h, showing the desired high COF and low wear rate properties of the braking system. Additionally, the coated brake disk maintained surface integrity even after severe braking tests, highlighting its potential in the braking system. Based on the characterizations of wear debris and brake pads, a harder and thinner oxide friction film plays a crucial role in achieving the excellent braking performance in coated brake disk cases. [ABSTRACT FROM AUTHOR]

In this paper, the engine-in-the-loop (EIL) methodology was used to study real driving emissions of a heavy-duty vehicle on an engine test bed. The virtual vehicle was combined with the actual engine to establish an EIL test platform. The result of the vehicle speed followability shows that the difference between the EIL simulated vehicle speed and the actual vehicle speed is within ±2 km/h, indicating that the vehicle cycle can be well reproduced on the engine test bed by EIL method. The EIL method shows high coincidence of engine operating points. Compared with real driving, the CO2, NOx and PN of EIL is 3.6%, 72.3% and 40% lower for this vehicle, respectively. Analysis shows that equipment difference is the key influencing factor for PN test accuracy of EIL, while the control of exhaust temperature and intercooler temperature play important roles in NOx test accuracy of EIL.

A 6.2 L diesel engine that meets China VI emission standard was selected to run world harmonized transient cycle (WHTC) and California Low Load Cycle (LLC) to measure the pollutants. The brake specific emission under the two cycles were compared, and nitrogen oxides (NOx) emission were analyzed carefully. The results show that the NOx emission of the LLC of this engine is about 15 times than that of the hot WHTC, and 4.7 times than that of the limitation of current China VI emission standard. The low inlet temperature of selective catalytic reduction (SCR) is the predominant reason for the high NOx emission in the LLC. The SCR inlet temperature of lower than 200°C in LLC accounts for 52% of the total time with an average inlet temperature of only 190°C. While the inlet temperature of lower than 200°C of the hot WHTC only accounts for 7% with the average inlet temperature of 275°C. The average SCR catalytic efficiency calculated by NOx sensor amounted on the upstream and downstream of LLC is only 75%, while the efficiency is 98% for hot WHTC. It is necessary to focus on thermal management of the aftertreatment system and the SCR catalytic performance at low temperature.

Real driving emissions of a heavy-duty vehicle with a maximum total mass of 18000 kg were investigated by the engine-in-the-loop (EIL) methodology. Virtual vehicle model, driver model and real road model was established, then to combined with the actual engine and emission test equipment to fulfill the vehicle emission evaluation on engine test bed. The results indicate the road driving can be well reproduced on engine laboratory with good vehicle speed followability, engine speed and torque consistence. However, the emission results show a larger difference with a 3.6 gap for CO2, a 72.3% gap for NOx and a 40% gap for PN., respectively. Analysis shows that the intercooler temperature, the exhaust temperature and equipment difference has a combined effect on the emission accuracy.

Pollutants and carbon dioxide (CO2) under different vehicle loading were investigated on a dump truck with a maximum designed total mass of 18000 kg. An engine-in-the-loop (EIL) methodology was applied to achieve the test consistency because EIL can use the same road, driver and vehicle model. The results show that the total CO2 emission increases while the brake specific CO2 emission decrease as the vehicle loading increases. Both the total and specific emissions of PN increase when vehicle loading increases. The effect regularity of increasing vehicle loading on NOx, THC and CO is not significant. It is necessary to comprehensively consider the changes in the raw exhaust due to the engine operation points changes and in the SCR catalytic efficiency derived from the SCR inlet temperature variation. The DPF generation is also need to be concerned because the CO2, PN and NOx emissions will rapidly increase during this period.

The time-dependent population transfer process of N2+ generated in an intense laser pulse has been investigated using the quasi-stationary Floquet theory by assuming that N2+ experiences an intense laser pulse with the sudden turn-on. A light-dressed B state is formed with a significant amount of population when pulse is suddenly turned on and is adiabatically transformed to the vibrational ground state (v = 0) of the field-free B state when the pulse vanishes. In addition, a part of the population is transferred to the electronically excited A state through one-photon resonance, which also contributes to decreasing the final population in the X state, facilitating the population inversion between the B state and the X state.

In order to determine the stress state and the specific dynamic corrosion behaviors of the cooling pump impeller in the liquid lead‐bismuth eutectic alloy (LBE), the numerical and the experimental investigations on the fast‐flowing LBE corrosion behaviors of the SiC impeller were conducted. The distributions of stress and displacement of the SiC impeller were simulated, and then the microstructure and mechanical properties of the corroded impeller were characterized. The results indicated that the SiC impeller met the strength requirement of 1000 rpm in LBE, and the dynamic LBE corrosion had little effect upon structure safety of the SiC impeller. The maximum stresses of the SiC impeller without and with LBE loading were.452 and 9.736 MPa, respectively. The maximum displacements of the SiC impeller without and with LBE loading were 76.385 and 4.096 μm, respectively. The LBE loading reduced the axial displacement of the impeller and acted as an impeller stabilizer to some extent. Blade elongating and flapping were the main vibration mode of the SiC impeller. The mechanical properties of the SiC impellers before and after corrosion were basically the same. [ABSTRACT FROM AUTHOR]