基于粒子群优化BP神经网络的风电机组齿轮箱故障诊断方法

提出了一种基于粒子群优化BP神经网络风电机组齿轮箱故障诊断方法。粒子群算法不需要计算梯度,可以兼顾全局寻优和局部寻优。利用粒子群算法对BP网络权值和偏置进行优化,减少了BP神经网络算法陷入局部最优解的风险,提高了神经网络的训练效率,加快了网络的收敛速度。考虑风电齿轮箱振动信号的不确定性、非平稳性和复杂性,提取功率谱熵、小波熵、峭度、偏度、关联维数和盒维数作为故障特征。经测试,算法诊断结果正确,表明了PSO优化BP神经网络用于风电机组齿轮箱故障诊断的有效性和实用性。     

BP神经网络改进算法的探讨

针对标准BP神经网络收敛速度慢的局限性,提出了几种基于MATLAB语言的BP神经网络改进算法,搭建了相应的网络诊断模型;将铁道车辆典型齿轮箱故障信号作为神经网络的测试数据,用改进的BP神经网络进行仿真测试,结果表明,LM优化算法与其他改进算法相比较,具有较好的诊断效率和精度,基本达到了对铁道车辆齿轮箱故障诊断的目的.     

CQPSO-BP算法在风电机组齿轮箱故障诊断中的应用

为实现风电机组齿轮箱故障模式的有效识别,提出一种基于混沌量子粒子群优化BP神经网络(CQPSOBP)的故障诊断方法。在该算法中,利用混沌序列来初始化粒子的初始角位置,可提高种群的遍历性;通过引入变异操作,避免算法陷入早熟收敛,并依此来对BP神经网络的初始权值和阈值进行优化。实例表明,同粒子群优化BP神经网络(PSO-BP)与BP网络的诊断结果相比,CQPSO-BP算法具有收敛速度快、识别精度高的优点,可有效用于风电机组齿轮箱的故障诊断系统中。     

基于AFOA-BP神经网络的燃气轮机研制风险预测

为提高燃气轮机研制过程中的风险管理能力,针对果蝇算法（Fruit Fly Optimization Algorithm,FOA）及BP神经网络的缺陷,构建了自适应果蝇算法（Adaptive Fruit Fly Optimization Algorithm,AFOA）,提出基于自适应果蝇算法优化BP神经网络的风险预测模型,利用自适应果蝇算法优化BP神经网络的阈值和权值。挖掘燃气轮机研制风险因素及风险事件之间的关系,并根据风险因素的权重预测风险事件的权重。利用燃气轮机研制风险的相关历史数据进行验证,表明该模型具有较高的预测精度和应用价值。     

蝗虫优化神经网络在变压器故障诊断中的应用

针对变压器故障诊断中传统BP神经网络算法准确率低、收敛速度慢、易陷入局部极小值及对初始参数较为敏感等的不足,提出一种基于蝗虫优化（GOA）算法的BP神经网络故障诊断方法。建立以变压器故障特征气体为输入、故障类别为输出的故障诊断模型,利用GOA高效的计算性能和优良的全局搜索能力对BP神经网络的权值和阈值进行参数优化。仿真结果表明,GOA优化后的BP神经网络模型相比于传统BP神经网络和基于遗传算法优化的BP神经网络,能够在保留广泛映射能力的前提下,提升网络的学习速度和全局搜索能力,进而缩短训练所需时间,提高故障诊断精度。     

基于蜻蜓算法优化BP神经网络的燃气轮机故障诊断

为了提高燃气轮机故障诊断的准确率,提出了一种基于蜻蜓算法(Dragonfly algorithm,DA)和BP(Back Propagation)神经网络的燃气轮机故障诊断方法。针对BP神经网络容易陷入局部极值的问题,采用蜻蜓算法(DA)对BP神经网络的权值和阈值进行参数优化。仿真结果表明:基于蜻蜓算法的DA-BP神经网络的燃气轮机故障诊断准确率高达97.78%,训练误差为0.03%,与基于粒子群算法的PSO-BP故障诊断和标准BP算法的故障诊断相比,DA-BP模型诊断的准确率最高,训练误差最小。实例证明,采用DA-BP模型实现燃气轮机气路故障诊断具有良好的诊断速率和诊断准确率,具有一定的应用价值。     

基于轴承温度的风机齿轮箱故障预警研究

齿轮箱轴承作为能量传递的关键部件,对风机状态评估具有重要意义。文章针对齿轮箱故障,提出了基于改进的粒子群算法(APSO)优化的BP神经网络齿轮箱轴承温度预测模型。首先,基于主成分分析法,选取SCADA系统中影响齿轮箱轴承温度的参数,建立正常状态下的齿轮箱轴承温度预测模型,通过对轴承温度残差值进行分析,得出风机故障告警和报警阈值,从而实现对齿轮箱故障的有效预警;最后,利用华北某风电场的数据进行实验仿真,对比分析粒子群(PSO)优化的BP神经网络预测模型和传统BP神经网络预测模型。结果表明,提出的预测方法拥有精度高、收敛速度快等优点。     

基于改进人工蜂群算法的Elman神经网络风机故障诊断

在风机齿轮箱故障诊断过程中,针对由于故障数据稀疏导致模型建立困难的问题,提出一种使用改进人工蜂群算法(IABC)优化Elman神经网络的故障诊断模型。该模型通过建立齿轮箱正常状态下的温度模型,采用残差分析,得到齿轮箱的故障状态,降低了建立模型的复杂度。采用IABC对Elman神经网络的相关参数进行优化,解决了Elman网络收敛速率慢、易陷入局部最优的问题。在IABC算法中,观察蜂阶段采用动态搜索策略,实现搜索能力和开发能力的平衡;在侦查蜂阶段,通过引入混沌变量扰动,增大种群多样性,进而达到全局最优。通过华北某风电场历史数据进行实验,结果表明,IABC与Elman神经网络的结合可对风机齿轮箱故障状态进行识别,且诊断正确率较高,可应用于实际故障诊断。     

基于果蝇算法与自适应性遗传算法组合优化神经网络的光伏电站短期出力预测

光伏电站的输出功率会随着很多因素发生波动,若能够提高光伏系统出力预测的准确性,则能有效地降低光伏电站并网后对电网造成的冲击,提高电力系统的稳定性。建立了果蝇算法与自适应遗传算法组合优化的BP神经网络的预测模型。从预测结果可以发现,采用组合优化算法的BP神经网络模型能够有效避免地BP神经网络易陷入局部极小值点的缺陷,相比于仅优化权值和阈值的BP神经网络模型提高了预测精度,具有一定的应用价值。     

基于粒子群优化神经网络的水轮机振动故障诊断

为了提高水轮机振动故障诊断正判率,提出粒子群算法优化BP神经网络的水轮机振动故障诊断方法,即把通过特征提取获得的机组故障特征量作为神经网络的输入,然后利用训练好的粒子群算法优化后的神经网络进行水轮机振动故障类型诊断。诊断结果表明,该方法具有良好的分类效果,比BP神经网络诊断模型诊断精度高。     

Ash-forming elements in four Scandinavian wood species. Part 1: Summer harvest

Woody biomass in Finland and Sweden comprises mainly four wood species: spruce, pine, birch and aspen. To study the ash, which may cause problems for the combustion device, one tree of each species were cut down and prepared for comparisons with fuel samples. Well-defined samples of wood, bark and foliage were analyzed on 11 ash-forming elements: Si, Al, Fe, Ca, Mg, Mn, Na, K, P, S and Cl. The ash content in the wood tissues (0.2–0.7%) was low compared to the ash content in the bark tissues (1.9–6.4%) and the foliage (2.4–7.7%). The woods’ content of ash-forming elements was consequently low; the highest contents were of Ca (410–1340 ppm) and K (200–1310), followed by Mg (70–290), Mn (15–240) and P (0–350). Present in the wood was also Si (50–190), S (50–200) and Cl (30–110). The bark tissues showed much higher element contents; Ca (4800–19,100 ppm) and K (1600–6400) were the dominating elements, followed by Mg (210–2400), P (210–1200), Mn (110–1100) and S (310–750), but the Cl contents (40–330) were only moderately higher in the bark than in the wood. The young foliage (shoots and deciduous leaves) had the highest K (7100–25,000 ppm), P (1600–5300) and S (1100–2600) contents of all tissues, while the shoots of spruce had the highest Cl contents (820–1360) and its needles the highest Si content (5000–11,300). This paper presented a new approach in fuel characterization: the method excludes the presence of impurities, and focus on different categories of plant tissues. This made it possible to discuss the contents of ash element in a wide spectrum of fuel-types, which are of large importance for the energy production in Finland and Sweden.     

NEXT GENERATION ENGINEERED MATERIALS FOR ULTRA SUPERCRITICAL STEAM TURBINES

正1 ABSTRACT To reduce the effect of global warming on our climate,the levels of CO2emissions should be reduced.One way to do this is to increase the efficiency of electricity production from fossil fuels.This will in turn reduce the amount of CO2emissions for a given power output.Using US practice for efficiency calculations,then a move from a typical US plant running at 37%efficiency to a 760℃/38.5 MPa(1 400/5 580 psi)plant running at 48%efficiency would reduce CO2emissions by 170kg/MW.hr or 25%.     

Contents in Volume 23,2014

<正>~~     

Aerodynamic performance effects of leading-edge geometry in gas-turbine blades

The purpose of this paper is to illustrate the advantages of the direct surface-curvature distribution blade-design method, originally proposed by Korakianitis, for the leading-edge design of turbine blades, and by extension for other types of airfoil shapes. The leading edge shape is critical in the blade design process, and it is quite difficult to completely control with inverse, semi-inverse or other direct-design methods. The blade-design method is briefly reviewed, and then the effort is concentrated on smoothly blending the leading edge shape (circle or ellipse, etc.) with the main part of the blade surface, in a manner that avoids leading-edge flow-disturbance and flow-separation regions. Specifically in the leading edge region we return to the second-order (parabolic) construction line coupled with a revised smoothing equation between the leading-edge shape and the main part of the blade. The Hodson–Dominy blade has been used as an example to show the ability of this blade-design method to remove leading-edge separation bubbles in gas turbine blades and other airfoil shapes that have very sharp changes in curvature near the leading edge. An additional gas turbine blade example has been used to illustrate the ability of this method to design leading edge shapes that avoid leading-edge separation bubbles at off-design conditions. This gas turbine blade example has inlet flow angle 0°, outlet flow angle −64.3°, and tangential lift coefficient 1.045, in a region of parameters where the leading edge shape is critical for the overall blade performance. Computed results at incidences of −10°,   −5°,   +5°,   +10° are used to illustrate the complete removal of leading edge flow-disturbance regions, thus minimizing the possibility of leading-edge separation bubbles, while concurrently minimizing the stagnation pressure drop from inlet to outlet. These results using two difficult example cases of leading edge geometries illustrate the superiority and utility of this blade-design method when compared with other direct or inverse blade-design methods.     

Hydrogen production by steam-gasification of carbonaceous materials using concentrated solar energy – V. Reactor modeling,optimization, and scale-up

A chemical reactor for the steam-gasification of carbonaceous particles (e.g. coal, coke) is considered for using concentrated solar radiation as the energy source of high-temperature process heat. A two-phase reactor model that couples radiative, convective, and conductive heat transfer to the chemical kinetics is applied to optimize the reactor geometrical configuration and operational parameters (feedstock's initial particle size, feeding rates, and solar power input) for maximum reaction extent and solar-to-chemical energy conversion efficiency of a 5 kW prototype reactor and its scale-up to 300 kW. For the 300 kW reactor, complete reaction extent is predicted for an initial feedstock particle size up to 35 μm at residence times of less than 10 s and peak temperatures of 1818 K, yielding high-quality syngas with a calorific content that has been solar-upgraded by 19% over that of the petcoke gasified.     

汽轮机数字电液调节系统挂闸异常的技术完善

分析了200MW汽轮机数字电液调节系统在运行中存在的挂闸异常问题,采取了相应的技术处理措施,且运行实践效果良好。     

新型高压共轨ECU升压模块的数字化开发与优化

为了提高喷油器电磁阀的响应速率,提出了一种基于CPLD(复杂可编程逻辑器件)应用于高压共轨ECU的数字升压模块。鉴于该升压电路结构参数多,其升压电压的恢复响应要求高等特征,基于Pspice建立了升压电路的仿真模型,研究了不同电路参数下升压模块的输出特性,全面优化了该升压模块的性能。结果显示,该升压模块的最大转换效率可以达90%以上。在柴油发动机上对ECU的试验表明,升压电压最大波动不超过10%,其恢复时间仅为1.3ms,功率管最大温升仅为41℃,满足整机运行范围内ECU的需求。     

Assessment methods of material ageing using Sdobyrev''s creep rupture model

The physical aspects of the activation energy, in higher and high temperatures, of the metal creep process were examined. The research results of creep-rupture in a uniaxial stress state and the criterion of creep-rupture in biaxial stress states, at two temperatures, are then presented. For these studies creep-rupture, taking case iron as an example the energy and pseudoenergy activation was determined. For complex stress states the criterion of creep-rupture was taken to be Sdobyrev's, i.e. σ_red = σ₁ β + (1 − β)σ_i, where: σ₁-maximal principal stress, σ_i-stress intensity, β-material constant (at variable temperature β = β(T)). The methods of assessment of the material ageing grade are given in percentages of ageing of new material in the following mechanical properties: 1) creep strength in uniaxial stress state, 2) activation energy in uniaxial stress state, 3) criterion creep strength in complex stress states, 4) activation pseudoenergy in complex stress states. The methods 1) and 3) are the relatively simplest because they result from experimental investigations only at nominal temperature of the structure work, however, for methods 2) and 4) it is necessary to perform the experimental investigations at least at two temperatures.     

Production of hydrogen from sewage biosolids in a continuously fed bioreactor: Effect of hydraulic retention time and sparging

Hydrogen was produced from primary sewage biosolids via mesophilic anaerobic fermentation in a continuously fed bioreactor. Prior to fermentation the sewage biosolids were heated to 70 °C for 1 h to inactivate methanogens and during fermentation a cellulose degrading enzyme was added to improve substrate availability. Hydraulic retention times (HRT) of 18, 24, 36 and 48 h were evaluated for the duration of hydrogen production. Without sparging a hydraulic retention time of 24 h resulted in the longest period of hydrogen production (3 days), during which a hydrogen yield of 21.9 L H₂ kg⁻¹ VS added to the bioreactor was achieved. Methods of preventing the decline of hydrogen production during continuous fermentation were evaluated. Of the techniques evaluated using nitrogen gas to sparge the bioreactor contents proved to be more effective than flushing just the headspace of the bioreactor. Sparging at 0.06 L L min⁻¹ successfully prevented a decline in hydrogen production and resulted in a yield of 27.0  L H₂ kg⁻¹ VS added, over a period of greater than 12 days or 12 HRT. The use of sparging also delayed the build up of acetic acid in the bioreactor, suggesting that it serves to inhibit homoacetogenesis and thus maintain hydrogen production.     

Trace metal chemistry and silicification of microorganisms in geothermal sinter, Taupo Volcanic Zone, New Zealand

As part of a pilot study investigating the role of microorganisms in the immobilisation of As, Sb, B, Tl and Hg, the inorganic geochemistry of seven different active sinter deposits and their contact fluids were characterised. A comprehensive series of sequential extractions for a suite of trace elements was carried out on siliceous sinter and a mixed silica-carbonate sinter. The extractions showed whether metals were loosely exchangeable or bound to carbonate, oxide, organic or crystalline fractions. Hyperthermophilic microbial communities associated with sinters deposited from high temperature (92–94°C) fluids at a variety of geothermal sources were investigated using SEM. The rapidity and style of silicification of the hyperthermophiles can be correlated with the dissolved silica content of the fluid. Although high concentrations of Hg and Tl were found associated with the organic fraction of the sinters, there was no evidence to suggest that any of the heavy metals were associated preferentially with the hyperthermophiles at the high temperature (92–94°C) ends of the terrestrial thermal spring ecosystems studied.