Soil NOx Emission Prediction via Recurrent Neural Networks

This paper presents designing sequence-to-sequence recurrent neural network(RNN)architectures for a novel study to predict soil NOx emissions,driven by the imperative of understanding and mitigating environmental impact.The study utilizes data collected by the Environmental Protection Agency(EPA)to develop two distinct RNN predictive models:one built upon the long-short term memory(LSTM)and the other utilizing the gated recurrent unit(GRU).These models are fed with a combination of historical and anticipated air temperature,air moisture,and NOx emissions as inputs to forecast future NOx emissions.Both LSTM and GRU models can capture the intricate pulse patterns inherent in soil NOx emissions.Notably,the GRU model emerges as the superior performer,surpassing the LSTM model in predictive accuracy while demonstrating efficiency by necessitating less training time.Intriguingly,the investigation into varying input features reveals that relying solely on past NOx emissions as input yields satisfactory performance,highlighting the dominant influence of this factor.The study also delves into the impact of altering input series lengths and training data sizes,yielding insights into optimal configurations for enhanced model performance.Importantly,the findings promise to advance our grasp of soil NOx emission dynamics,with implications for environmental management strategies.Looking ahead,the anticipated availability of additional measurements is poised to bolster machine-learning model efficacy.Furthermore,the future study will explore physical-based RNNs,a promising avenue for deeper insights into soil NOx emission prediction.

基于神经网络的重型车辆远程监控NOx传感器露点保护过程数据修复方法

为解决重型车辆远程监控数据中NOx传感器露点保护过程的数据无效问题,利用一辆国六重型车辆的PEMS测试对露点保护期间的高NOx排放问题进行探究,验证了利用神经网络算法修复数据和提高远程监测数据利用率的可行性。结果表明,NOx传感器露点保护过程会导致30%以上的NOx排放量未被统计;在露点保护期间,超过90%的数据显示车辆速度低于54 km/h、发动机冷却液温度低于82℃、SCR入口温度低于245℃、SCR出口温度低于225℃。神经网络算法可有效修复露点保护过程中失效的NOx测量值,对发动机原始排放和车辆尾管排放的累计排放量误差都在4%以内。

基于某装载机高原环境下NOx排放的模拟研究

为了探讨工程机械在高原环境下的燃烧排放特性,本文以某装载机柴油发动机为原型,建立高原环境下的数值计算模型,研究该柴油机在高原环境下的燃烧排放特性。结果表明:NOx的产生与发动机缸内温度密切相关。且当发动机转速不变时,随着海拔的上升,发动机NOx的排放有着先上升后下降的趋势;当海拔不变时,发动机转速提高,其NOx的排放也逐渐增加。

Numerical Study on NOx Emissions of Methane Re-Combustion in a 600 MWe Coal-Fired Boiler

The fuel staging combustion technology is a promising low NOx combustion technology for coal-fired boiler. In order to reduce NOx emissions, the burners of a 600?MWe coal-fired boiler are retrofitted in which methane gas is selected as a secondary fuel for re-combustion. The CFD models of combustion process are built to investigate?effects of the methane gasratio on combustion process and NOx emissions. A total of 4 cases are numerically studied, including the pure coal combustion case, the coal combustion with 7.5%, 10%, 12.5% of methane gas re-combustion cases respectively. The results show that the re-combustion of methane can reduce the temperature at primary combustion zone, but increase the temperatures at the re-combustion area and the furnace outlet. The NOx concentration at the furnace outlet reduces with the increasing methane gas ratio.?Methane re-combustion can greatly benefit to the NOx emissions reduction.

Angle Scattering Method for Soot Concentration Measurement under Ultra-Low Emissions Condition

Aiming at the problem of soot concentration measurement under ultra-low emission conditions,a forward small angle soot concentration measurement method is proposed.Taking a typical boiler emission of 0.1μm-3.0μm bimodal distribution soot as an object,the particle scatter simulation calculation under different parameters is carried out,and the influence of detection angle and particle size on the angular scatteringmeasurement of ultra-low emission soot is analyzed.The influence of detection angle and particle size on the angular scatteringmeasurement of ultra-lowemission soot is analyzed.Preferably,thewavelength of incident light is 650 nm,and the forward detection angle parameter is 15◦for the design of forward small angle soot concentration measurement system.An experimental system for measuring soot with standard concentration is built.Experiments of particle concentration measurement of 1.0μm and 3.0μm under ultra-low emission conditions are carried out.The results show that the average deviation of soot concentration measurement is less than 0.10 mg/m3 under the condition of ultra-low emission by using 15◦of forward detection,which provides an effective way for monitoring ultra-low emission soot concentration in coal-fired power plants.

Combined Effect of a Catalytic Reduction Device with Waste Frying Oil-Based Biodiesel on NOx Emissions of Diesel Engines

Internal combustion engines with application in automobiles and other relevant industries constitute significant environmental pollution via the release of toxic exhaust gasses like carbon monoxide (CO), hydrocarbons (HC), particulate matter (PM), and nitrogen oxide (NOx). Engine researchers and manufacturers are challenged to develop external and internal measures to ensure environmentally friendly solutions to accommodate and conform to the growing list of emission standards. Therefore, this work presents an experimental investigation of the NOx emission profile of a diesel engine that is fuelled and fitted with waste frying oil-based biodiesel and catalytic converter. Using a single-cylinder, four-stroke air-cooled CI engine at a constant speed of 1900 rpm and different loadings of 25%, 50%, 75%, and 100%;fitted with a catalytic converter at the exhaust outlet of the engine and linked to a dynamometer and a gas analyser, an experiment was conducted at biodiesel/diesel volume blends of B0 (0/10), B5 (5/95), B20 (20/80), B30 (30/70), B70 (70/30), B100 (100/0);and 30% concentration (v/v), 0.5 litre/hr flow rate of aqueous urea from the catalytic converter. The results show an increasing NOx emission as the biodiesel component increased in the blend. The catalytic converter showed a downward NOx reduction with a significant 68% reduction in efficiency at high exhaust gas temperatures. It is concluded that the combined utilisation of waste frying oil-based biodiesel and the catalytic converter yields substantial NOx emission reduction.

基于智能算法的重型车辆NOx排放量预测方法

重型车辆NOx排放量的传统预测方法中,由于没有利用误差反馈来修正预测算法,导致预测出的NOx排放量数据与真实数据相差较大。为此提出基于智能算法的重型车辆NOx排放量预测方法。收集大量的重型车辆真实的NOx排放数据,计算出重型车辆NOx综合排放因子,基于智能算法构建BP人工神经网络,设置隐含模式的工作层,输入收集到的真实数据对智能算法进行训练,利用BP神经网络误差反传的功能对每个数据对进行训练,通过误差反馈修正算法的预测误差。设计道路预测实验,将基于智能算法得出的重型车辆NOx排放量数据与真实排放量数据进行对比,得出两者数据结果高度一致的结论,表明该方法的预测数据误差较小,能够进行有效的重型车辆Nox排放量预测。

带式焙烧机球团NOx超低排放技术研究现状与展望

总结了带式焙烧机NOx的产生机制,揭示了带式焙烧机产生NOx的主要因素,探索从焙烧过程中可降低NOx产生的措施;并结合最新烟气强化脱硝技术和强化手段,为带式焙烧机烟气脱硝技术改造做理论支持和铺垫。

基于BWOA-GAM-BiGRU的火电厂SCR系统出口NOx排放预测

提出了一种基于数据驱动结合全局注意力机制与双向门控循环单元深度神经网络的选择性催化还原系统出口NOx排放预测模型,并使用黑寡妇优化算法对网络超参数进行自动寻优。对某300MW电厂选择性催化还系统的历史运行数据进行深度挖掘,确定模型输入变量并校准各输入变量与NOx排放量之间的时延并重构样本序列。实验结果显示,所提出模型的预测结果比典型预测模型具有更高预测精度和更好的泛化能力。

Study on effect of heat transfer space non-uniformity of combustion chamber components on in-cylinder NOx emission formation in internal combustion engine

The components of combustion chamber (cylinder head-cylinder liner-piston assembly-oil film) were taken as a coupled body.Based on the three-dimensional heat transfer numerical simulation of the coupled body,a coupled three-dimensional calculation model for in-cylinder working process and the combustion chamber components was built with domain decomposition and boundary coupled method,which implements the coupled three-dimensional simulation of in-cylinder working process and the combustion chamber components.The model was applied in the influence investigation of the space non-uniformity in heat transfer among combustion chamber components on the generation of in-cylinder emissions:NOx.The results showed that the heat transfer space non-uniformity of combustion chamber components directly influences the formation of in-cylinder NOx.The main area being influenced was the accessory area on the wall,while the influence on the generation of NOx in the central area couold be omitted.

Atmospheric Carbon Dioxide and Nitrogen Oxides Emissions Data for 2003-2005 Model Year Trucks

Heavy-duty trucks account for a substantial portion of the atmospheric carbon dioxide (CO2) and nitrogen oxides (NOx) inventory. The data presented in this paper will help the research community be interested in developing models that predict the NOx and CO2 levels in real use. Continuous data of emissions were recorded from chassis dynamometer testing of five 2003-2005 model year (MY) heavy-duty trucks. The instantaneous emissions rate was plotted against axle power in all cases. The effect of vehicle test weight and the drive cycle employed on the relation between emissions rate (grams per sec) and axle power was studied. The NOx/CO2 ratio was found to be independent of the test cycle. The average NOx/CO2 ratio for the 2003-2005 MY trucks was found to be 0.0051, which agrees reasonably well with the estimated ratio of 0.0048, based on certification standards. The data were compared to those from 1994-2002 MY trucks;the average NOx/CO2 ratio for those trucks was 0.0141. For the 2003-2005 MY trucks, the distance specific NOx (grams per mile) and the fuel economy (miles per gallon) were less than those of 1994-2002 MY trucks.

Re-understanding and Thinking about Environmental Impact of Coal-fired Power Plants under Ultra-low Emission

From the perspective of development background,concepts and related policies of ultra-low emission,according to work practice,some issues and difficulties that need to be paid attention to in the environmental impact assessment of ultra-low-emission thermal power projects were discussed from the aspects of evaluation criteria,evaluation grade and scope,pollution control technical lines,environmental benefit accounting,and total emission control,and corresponding recommendations were put forward.

米勒循环降低船用中速柴油机NOx排放研究

降低中速柴油机NOx排放的研究具有重要的现实意义。利用AVL BOOST软件,以Wartsila4L20型中速柴油机为模拟原型建立仿真模型,通过台架试验数据验证模型模拟的准确性,并利用所建立的模型,在综合考虑柴油机经济性和可靠性的基础上,研究米勒循环降低船用中速柴油机NOx排放的有效途径。

NH_(3)/CH_(4)/CH_(3)OH多孔介质燃烧特性模拟研究

氨(NH_(3))是一种无碳燃料,有望作为热能发电的替代燃料降低碳排放。多孔介质燃烧是一种可提高燃烧速率和稳定性的燃烧技术,实验表明其用于氨与反应性更强的燃料进行混燃可以同时提高燃烧强度和燃烧稳定性,但缺乏相应的模型研究。该文基于多孔介质导热强度高的特性,其内部燃烧满足一维假设,建立了一维多孔介质燃烧模型,对NH_(3)分别与甲烷(CH_(4))、甲醇(CH_(3)OH)掺混时的燃烧特性进行模型计算。计算结果显示多孔介质对两种混合燃料的作用不同,对于CH_(4)/NH_(3)燃料,多孔介质可以明显提高燃烧速率并降低富燃状态的NH_(3)残留;对于CH_(3)OH/NH_(3)燃料,提高燃烧速率和降低NH_(3)残留的效果较差;对两种混合燃料,可燃气体预混后直接送入多孔介质燃烧都增加一定的NOx排放,增加效果相同,而分级燃烧可以显著降低NOx排放。

基于组合时域特征提取和Stacking集成学习的燃煤锅炉NO_(x)排放浓度预测

为提高火电厂锅炉出口NO_(x)排放浓度的预测精度,提出一种考虑组合时域特征的Stacking集成学习模型。首先,为挖掘数据深层信息,采用时序分析、完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise analysis,CEEMDAN)和统计学计算数据标准差、偏度等特征的方法进行组合时域特征提取以构建重构数据;其次,考虑到重构数据中存在的冗余变量对模型的精度有所影响,利用遗传算法(genetic algorithm,GA)对重构数据进行特征降维;最后,为充分发挥各个模型的优势以提高模型的预测精度,构建以极限学习机(extreme learning machines,ELM)、深度神经网络(deep neural networks,DNN)、多层感知器(multilayer perceptron,MLP)、极限梯度提升算法(extreme gradient boosting,XGBoost)为基模型和以回声状态网络(echo state network,ESN)为元模型的Stacking集成学习NOx排放浓度预测模型。实验结果表明:该预测模型在不同数据集下都有着不错的预测效果,预测误差均小于2%,能够对锅炉NOx排放浓度实现精准预测。

中国燃煤电厂NOx排放估算方法及排放量研究

综合考虑影响燃煤电厂NOx生成的煤质、燃烧方式、单机容量等客观因素,建立以燃煤发电机组实际排放水平为核心的计算NOx排放量方法,运用数理统计方法,估算出我国2005年燃煤电厂NOx排放量(以NO2计)为671万～781万t。并以2005年为基准,预测在环保要求不变和趋严2种情况下,2010年我国燃煤电厂NOx排放量分别为846万～1003万t和651万～767万t。

稀燃汽油机降低NOx排放技术方案分析研究

采用吸附还原催化转化器和三效催化转化器的不同组合,对一台改装的16气门电控燃油喷射稀燃汽油机进行了降低富氧下NOx排放的实验研究。结果表明:三效催化转化器位于吸附还原催化转化器之前的布置方案具有较好的降低稀燃汽油机NOx排放的效果。

锅炉燃烧调整对NOx排放和锅炉效率影响的试验研究

在2台典型的1025t／h锅炉上进行了燃烧调整降低NOx排放浓度的试验研究，通过改变过量空气系数、辅助风配风方式、运行负荷和制粉系统运行方式等，测定了锅炉尾部烟道NOx排放浓度，分析了锅炉运行工况、运行方式对NOx排放的影响．结果表明：降低过量空气系数，烟煤锅炉NOx减排效果比贫煤锅炉好得多；降低负荷，烟煤锅炉的NOx排放量降低值较大；缩腰式配风的NOx排放浓度比均匀配风方式约降低10％；制粉系统的运行方式影响炉内燃料的燃烧状态和温度分布，也影响NOx的生成和排放．在不降低锅炉效率的前提下，调整燃烧工况，可降低锅炉排放NOx浓度10％～20％．

中国大气NH3和NOx排放的时空分布特征

根据我国不同氨源的数量、燃料消费量和相应的氨与氮氧化物排放因子,计算了我国大陆地区1995~2004年历年的氨（NH3）排放量与1985~2005年历年的氮氧化物（NOx）排放量,在此基础上模拟了2006~2010年的NOx排放量,并分析了NH3和NOx排放强度的空间分布.结果表明：2004年,我国NH3排放量为12.0Tg,比1995年的10.6Tg增加了大约13.2%;2004年的NOx排放量为20.6Tg,比1995年的12.2Tg增加了大约68.9%,比1985年的6.2Tg增加了大约2.3倍.在1996年以前,我国NH3和NOx的排放量基本相当,但是此后NH3的年排放量在经历了1997~1999年的下降之后,变化比较平稳,而NOx的排放量自2000年之后呈逐年迅速增加的趋势.2004年全国NH3的排放总量中,畜禽排泄、氮肥施用、人类粪便、氮肥与合成氨生产的贡献率分别为69.2%、15.2%、13.9%和1.9%;2004年全国NOx的排放总量中,由于受到我国能源消费结构的制约,煤炭来源的NOx占到了排放总量的77.4%.NH3和NOx的排放强度都具有明显的空间差异,表现在中东部地区的排放强度明显高于西部地区,这与中东部地区人口多、能源消费量大以及畜禽养殖数量大有关.