基于循环一致性对抗网络的室内火焰图像场景迁移

基于深度学习的视频火灾探测模型的训练依赖于大量的正负样本数据,即火灾视频和带有干扰的场景视频。由于很多室内场合禁止点火,导致该场景下的火灾视频样本不足。本文基于生成对抗网络,将其他相似场景下录制的火焰迁移到指定场景,以此增广限制性场合下的火灾视频数据。文中提出将火焰内核预先植入场景使之具备完整的内容信息,再通过添加烟雾和地面反射等风格信息,完成场景与火焰的融合。该方法克服了现有多模态图像转换方法在图像转换过程中因丢失信息而造成的背景失真问题。同时为减少数据采集工作量,采用循环一致性生成对抗网络以解除训练图像必须严格匹配的限制。实验表明,与现有多模态图像转换相比,本文方法可以保证场景中火焰形态的多样性,迁移后的场景具有较高的视觉真实性,所得结果的FID与LPIPS值最小,分别为119.6和0.134 2。     

Novel navigation signal design based on spreading code time shift position modulation

A novel navigation signal design method based on spread code time shift position modulation was proposed,which inherits the idea of separating the pilot signal component and the data signal component,and applies time shift position of the spread code to carry data information.The old pattern of using carrier phase to carry information was changed,the power efficiency of data signal components and the performances of the satellite navigation system were improved.Theoretical analysis and simulation results show that the proposed method can significantly improve the transmission rate of data signal component or power ratio of the pilot signal component to data signal component without increasing the total transmission power.Then,the transmission rate,acquisition and tracking performance,positioning accuracy and other technical indicators of the satellite navigation system can be further improved.     

Conversion of biodiesel synthesis waste to hydrogen in membrane reactor: Theoretical study of glycerol steam reforming

Hydrogen production from waste glycerol, mainly producible as a by-product of biodiesel synthesis, is investigated as an attractive opportunity for exploiting renewable energy sources for further applications. Glycerol steam reforming using membrane technology was modeled by taking into accounts the maim transport phenomena, thermodynamic criteria and chemical process kinetics. A sensitivity analysis of operating conditions was made for key performance metrics such as glycerol conversion, hydrogen yield and hydrogen recovery. Glycerol conversion intensifies with enhancement of operating pressure and temperature, whereas high feed molar ratio and sweep ratio have limiting effect. Hydrogen permeation and subsequently, hydrogen recovery facilitates with increasing sweep gas ratio and sweep gas temperature. Hydrogen recovery enhances from 70% to 99% with increasing temperature from 350 to 500 °C at feed molar ratio of 3. Also, hydrogen recovery improves from 50% to 71% with increasing sweep ratio from 0 to 20 at 350 °C and 1 bar.     

Performance evaluation of a solarized gas turbine system integrated to a high temperature electrolyzer for hydrogen production

In this paper, the performance of a solar gas turbine (SGT) system integrated to a high temperature electrolyzer (HTE) to generate hybrid electrical power and hydrogen fuel is analyzed. The idea behind this design is to mitigate the losses in the electrical power transmission and use the enthalpy of exhaust gases released from the gas turbine (GT) to make steam for the HTE. In this context, a GT system is coupled with a solar tower including heliostat solar field and central receiver to generate electrical power. To make steam for the HTE, a flameless boiler is integrated to the SGT system applying the SGT extremely high temperature exhaust gases as the oxidizer. The results indicate that by increasing the solar receiver outlet temperature from 800 K to 1300 K, the solar share increases from 22.1% to 42.38% and the overall fuel consumption of the plant reduces from 7 kg/s to 2.7 kg/s. Furthermore, flameless mode is achievable in the boiler while the turbine inlet temperature (TIT) is maintained at the temperatures higher than 1314 K. Using constant amounts of the SGT electrical power, the HTE voltage decreases by enhancing the HTE steam temperature which result in the augmentation of the overall hydrogen production. To increase the HTE steam temperature from 950 K to 1350 K, the rate of fuel consumption in the flameless boiler increases from 0.1 m/s to 0.8 m/s; however, since the HTE hydrogen production increases from 4.24 mol/s to 16 mol/s it can be interpreted that the higher steam temperatures would be affordable. The presented hybrid system in this paper can be employed to perform more thermochemical analyses to achieve insightful understanding of the hybrid electrical power-hydrogen production systems.     

Multi objective optimization of a tri-reforming process with the maximization of H2 production and minimization of CO2 emission & power loss

In this study, the process optimization of a tri-reformer reactor is conducted for the synthesis of hydrogen gas from natural gas using multi-objective optimization (MOO) approach. Specifically, four MOO problems are solved using three objective functions, namely maximization of H₂, minimization of CO₂, and minimization of power loss. It should be noticed that the power loss is an important economic factor due the large pressure drop and flowrates in packed bed reactors. However, it has not been used as an objective function for the optimization based design and/or operation of fixed bed reactor for reforming process to the best of authors’ knowledge. Three of the four MOO problems are 2-objective in nature with all the permutation and combination of the three objectives. The fourth MOO problem is solved considering all the three objectives, simultaneously. For all the MOO problems, feed conditions of O₂, H₂O, and Temperature are considered as the optimization variables. The results obtained with 3 objective functions are observed to be superior to the ones obtained from 2 objective problems.     

Transient performances of the gas turbine recuperating waste heat through hydrogen rich fuels

Operational rules and control strategies of the chemically recuperated gas turbine (CRGT) in the marine propulsion are investigated in this paper. The Minimization of Gibbs free energy method is used to calculate the diesel-steam reforming reaction which products synthetic hydrogen rich fuels, and a universal model of the chemical regenerator which is easily applied to different application environments is created. The hydrogen production and hydrogen molar fraction are investigated to verify that the CRGT improve the combustion performances under low working conditions. Off-design calculations are performed to derive proper operational rules, and transient calculations are performed to investigate the best control strategies for the systems. The modelling approach of the chemical regenerator can be generally used in the chemically recuperated gas turbine. The elaborate operational rules can greatly improve the thermal efficiencies under every working condition. The system using synchronous control strategies have better regulation speed and operation stability than that using asynchronous control strategies.     

基于SVD和SSA-VMD降噪的轴承故障特征提取

针对强噪声背景下轴承故障特征提取困难的问题，提出一种基于奇异值分解和参数优化变分模态分解联合降噪的轴承故障特征提取方法(SSVMD)：首先，对原始信号进行奇异值分解(Singular Value Decomposition，SVD)处理，运用奇异值差分谱法选取有效奇异值并将原始信号重构得到初步降噪信号；其次，为防止故障信息丢失，将残余信号进行麻雀算法(Sparrow Search Algorithm，SSA)优化的变分模态分解(Variational Mode Decomposition，VMD）算法处理，得到最佳的模态个数K和惩罚参数α，选取峭度值最大、包络熵最小的IMF分量与初步降噪信号叠加得到最终降噪信号，并对信号进行包络分析；最后，通过仿真和试验数据分析得出，该方法能在信噪比很低的情况下降低噪声含量并提取轴承故障特征，为设备的状态监测和故障诊断提供理论依据。     

混流式喷水推进泵叶轮刮擦故障诊断方法

针对喷水推进泵的叶顶间隙过大或者过小都会影响喷水推进船航速的问题,提出一种利用泵壳体振动和输入轴力矩参量对叶轮刮擦故障进行识别的方法。在介绍混流式喷水推进泵叶轮径向摩擦振动机理的基础上,对装有2台喷泵的某高速巡逻艇的实船试航,通过获取的靠近叶轮的壳体振动信号以及输入轴力矩信号分析,得到了具体的故障特征指标。该分析结果为使用人员及时对这类异常状态做出快速、准确的判断,及时调整叶轮安装的状态以防止更大事故的发生提供了参考。     

遗传-蚁群算法在目标分配问题中的应用研究

针对传统算法很难满足大型水面舰艇编队防空武器的武器目标分配(weapon target assignment,WTA)问题,提出一种将遗传算法融入蚁群算法的混合算法。分析了遗传算法和蚁群算法的优缺点、利用遗传算法快速全局随机搜索能力生成一组粗略解,用其作为蚁群算法的初始信息素,再利用蚁群算法的并行性、正反馈机制,最后求得最优解,并对遗传-蚁群算法与蚁群算法、遗传算法这3种方法进行仿真比较。分析结果证明:遗传-蚁群算法用更少的时间获得最优的火力分配方案,缩短了武器系统反应时间,在求解质量方面有较大优势。     

混合故障模式下劣化系统维修更换策略

劣化系统在自身发生劣化的同时还可能受到来自外部的冲击,劣化系统的故障是这两个过程共同作用的结果,不同的故障原因采取的维修方式也不相同。为了进一步降低系统长期运行维修费用率,对传统的基于时间的寿命更换策略进行了扩展,提出了混合故障模式下考虑系统劣化程度的(A,T)维修策略,并以长期运行维修费用率最低为目标对维修策略进行了优化。算例表明:该方法能根据冲击到来时系统的劣化程度选择合理的维修方式,进行最小维修或者修复性维修,且操作简单,可为加强装备维护提供参考。