Adaptive Air-Fuel Ratio Control with MLP Network

This paper presents an application of adaptive neural network model-based predictive control (MPC) to the air-fuel ratio of an engine simulation. A multi-layer perceptron (MLP) neural network is trained using two on-line training algorithms: a back propagation algorithm and a recursive least squares (RLS) algorithm. It is used to model parameter uncertainties in the nonlinear dynamics of internal combustion (IC) engines. Based on the adaptive model, an MPC strategy for controlling air-fuel ratio is realized, and its control performance compared with that of a traditional PI controller. A reduced Hessian method, a newly developed sequential quadratic programming (SQP) method for solving nonlinear programming (NLP) problems, is implemented to speed up nonlinear optimization in the MPC. Keywords Air-fuel ratio control - IC engine - adaptive neural networks - nonlinear programming - model predictive control Shi-Wei Wang PhD student, Liverpool John Moores University; MSc in Control Systems, University of Sheffield, 2003; BEng in Automatic Technology, Jilin University, 2000; Current research interests automotive engine control, model predictive control, sliding mode control, neural networks.Ding-Li Yu obtained B.Eng from Harbin Civil Engineering College, Harbin, China in 1981, M.Sc from Jilin University of Technology, Changchun, China in 1986 and PhD from Coventry University, U.K. in 1995, all in control engineering. He is currently a Reader in Process Control at Liverpool John Moores University, U.K. His current research interests are in process control, engine control, fault detection and adaptive neural nets. He is a member of SAFEPROCESS TC in IFAC and an associate editor of the IJMIC and the IJISS.

Transient Air-Fuel Ratio Control in a CNG Engine Using Fuzzy Neural Networks

The fuzzy neural networks has been used as means of precisely controlling the air-fuel ratio of a lean-burn compressed natural gas (CNG) engine. A control algorithm, without based on engine model, has been (utilized) to construct a feedforward/feedback control scheme to regulate the air-fuel ratio. Using fuzzy neural networks, a fuzzy neural hybrid controller is obtained based on PI controller. The new controller, which can adjust parameters online, has been tested in transient air-fuel ratio control of a CNG engine.

车用稀燃增压单一燃料CNG发动机电控系统的研究

为深入研究 CNG发动机稀薄燃烧特性 ,进一步降低天然气发动机的有害排放 ,设计了车用增压天然气发动机电控系统。该系统采用高能点火模块来获得天然气着火所需的点火能量 ,电控喷射单元采用模糊控制器来获得比较精确的空燃比控制 ,实现对天然气发动机的顺序多点喷射。运用该系统对增压单一燃料 CNG发动机的燃烧和排放性能进行了试验研究 ,结果表明了该系统的有效性。

SI发动机空燃比联合非线性模型预测控制

针对火花塞点火(SI)发动机空燃比(AFR)控制系统提出了一种变采样间隔的Modified Volterra模型,并以此为基础,提出了一种基于RBFNN和Modified Volterra模型的SI发动机AFR的联合NMPC控制方法。该方法既具有RBFNN模型计算量小、预测精度高的特点,又具有可直接计算NMPC最优控制序列的优势,明显地提高了SI发动机AFR的控制精度,大大地减少了常规迭代寻优算法的计算时间。在dSPACE实时仿真试验平台上对平均值发动机模型进行仿真试验,结果表明:本文所提出的NMPC控制方法对SI发动机AFR的控制效果明显优于单独基于Modified Volterra和RBFNN模型的NMPC控制方法。

基于排气成分的发动机性能研究

根据气体分析仪测量发动机5种排气成分(HC、CO、NOx、CO2、O2)的干浓度、由台架实验得到发动机的动力性和燃油消耗特性参数,基于这些测试参数,推导出发动机排气性质、混合气空燃比、充气效率、污染物比排放等计算模型,并对模型开展了灵敏度分析。由此,开发了以发动机台架测功和气体分析仪为硬件平台的发动机综合性能(动力性、燃油经济性和排放性能)测试及分析的软硬件系统,并实现对某增压柴油发动机增压性能的评价、某摩托车汽油发动机化油器的改进。

基于OBD系统的汽油车油耗实时在线监测方法

建立了基于车辆在线故障诊断(OBD)系统的实时油耗计算方法。对不同型号车辆的OBD实时信息进行了采集分析。针对车辆OBD信息的差异性适配特征,根据汽油发动机空气燃料比(AFR)原理,建立了4种同源的汽油车实时油耗计算方法。针对部分OBD信息适配度不高的车型,对油耗计算中OBD系统缺失的车辆参数,提出了实验参数标定方法。对于此类汽油车油耗监测方法进行了实车实验验证。结果表明:此类油耗监测方法可对绝大多数汽油车进行实时在线油耗监测,瞬时油耗误差在±8%以内,其误差在±3%以内。

白蛋白与纤维蛋白原比值与乳腺癌患者总生存期的关系

目的探讨白蛋白与纤维蛋白原比值(albumin to fibrinogen ratio,AFR)与乳腺浸润性导管癌患者总生存期的关系。方法收集2009年1月—2012年4月河北医科大学第四医院乳腺中心收治的230例乳腺浸润性导管癌患者血液及临床资料,回顾性分析患者术前临床资料,计算AFR,Kaplan-Meier法及Cox比例回归风险模型进行生存分析,采用二分类方式,分为AFR<13.1与AFR≥13.1两组,采用单因素及多因素分析其与患者的生存关系,并建立预后模型。结果AFR≥13.1时患者生存率降低,AFR是改善总生存期(OS)的独立预后因素,将多因素分析里P<0.05的变量,即将AFR、白细胞(WBC)、雌激素受体(ER)孕激素受体(PR)、TNM分期、核分级、p53及脉管瘤栓7个指标建立OS预测模型,其受试者工作特征曲线(ROC)面积为0.882。结论AFR低表达是改善乳腺癌OS的独立预后因素,AFR、WBC、ER或PR、TNM、核分级、p53及脉管瘤栓7个指标建立OS预测模型,具有很好预测乳腺浸润性导管癌患者生存率的作用。

基于Simulink及RTW的空燃比自适应逆控制仿真

根据汽油机油膜的动力学原理,在SIMULINK下建立了其不含代数环的子模型,并把该子模型添加到汽油机的一种通用平均值模型上,从而完善了汽油机的平均值模型。在SIMULINK下建立了基于C语言的S函-数空燃比自适应逆控制器,仿真结果表明该控制器达到了较高的控制精度。RTW下生成的通用实时代码,加速了仿真过程,在实际ECU开发上有一定的实用价值。

夏利2000发动机稀薄燃烧电控系统的研制与应用

研制了一套适用于稀燃汽油机的电子控制系统.系统控制单元ECU参考Siemens公司电控系统设计方案,以C167系列单片机作为微处理器,对发动机的控制采用集中控制,可以实现高级轿车发动机ECU所有功能.本电子控制系统主要应用于丰田8A16气门EFI发动机进行稀燃匹配实验.实验结果表明,该系统基本达到了对控制的速度和精度的要求,得到的稀燃节油和降低排放效果十分明显;且系统性能可靠、抗干扰性强、功能完善、操作方便.

稀燃汽油机电控系统的硬件设计

为了充分发挥稀燃汽油机的性能,研制了一套适用于稀燃汽油机的电子控制系统。系统控制单元ECU参考Siemens公司电控系统设计方案,以C167系列单片机作为微处理器,对发动机的控制采用集中控制,可以实现发动机ECU所有功能,它适用于稀燃汽油机的空燃比、喷油和点火等参数的控制。

Air-fuel ratio control with stochastic L_2 disturbance attenuation in gasoline engines

In this paper, the problem of stochastic L2 disturbance attenuation of the air-fuel ratio is investigated with consideration of cyclic variation of the residual gas fraction （RGF）. A stochastic robust controller is designed based on a discrete-time dynamic model in which the RGF is modeled as a stochastic process with Markovian property. Finally, the sampling process-based statistical analysis for the RGF and the validation of the proposed control law are presented through the experiments conducted on a gasoline engine test bench.

术前白蛋白与纤维蛋白原比值对三阴性乳腺癌患者的预后影响和临床意义

目的:探讨术前白蛋白与纤维蛋白原比值(albumin to fibrinogen,AFR)对三阴性乳腺癌患者的预后影响和临床意义。方法:回顾性分析我院自2010年1月至2013年12月间就诊的195例三阴性乳腺癌患者。用受试者工作特性曲线(ROC)确定AFR的最佳临界值。采用卡方检验或Fisher精确检验分析比较计数资料。Kaplan-Meier方法和Log rank方法用于分析生存曲线。单因素和多因素分析(Cox比例风险回归模型)用于评估独立的预后因素。结果:ROC曲线确定AFR最佳临界值为15.00,依此分两组,即低AFR组(AFR<15.00)和高AFR组(AFR≥15.00)。单因素和多因素分析显示AFR是三阴性乳腺癌DFS(P=0.045,HR:0.627,95%CI:0.397~0.990;P=0.026,HR:0.595,95%CI:0.377~0.940)和OS(P=0.039,HR:0.238,95%CI:0.061~0.927;P=0.001,HR:0.385,95%CI:0.221~0.670)的独立预后因素。高AFR组患者术后中位DFS和OS显著高于低AFR组患者,差异具有显著统计学意义(χ^(2)=8.190,P=0.004;χ^(2)=8.720,P=0.003)。散点图分析显示,AFR与ALB呈显著正相关(R^(2)=0.028,P=0.020),AFR与FIB呈显著负相关(R^(2)=0.516,P<0.0001)。此外,对伴有淋巴管侵犯的患者,高AFR组患者比低AFR组患者术后生存时间长,预后更好。结论:术前AFR是影响患者预后的独立因素。AFR具有操作简单、易于推广、成本低、可重复性好等优点,具有潜在的临床应用价值。

Study on Oil Film Model of Electronic Fuel Injection Motorcycle Engine Cylinder

Based on the principles of heat transfer,an oil film model in the engine cylinder was established.Under the condition of cold state,the influence of factors such as engine fuel injection,fuel drop point,cylinder inner wall temperature,and inlet fluid on the oil film is comprehensively considered to establish an oil film quality prediction model.Based on the measurement of the compensation oil quantity in the transition conditions,the variation of the oil film during the transition is analyzed.The experimental results show that the velocity of the air-flow in the intake port and the temperature and pressure on the wall of the intake port are the main factors affecting the oil film in the cylinder.Based on the abovementioned experimental and theoretical studies,an oil film distribution model for each cycle of the transition condition was established based on the engine inlet oil film model.The experimental measurement curve and model prediction curve for the fuel compensation per cycle in the transition condition from 10%load to 30%load.The model established can be in good agreement with the experimental results and meet the fuel compensation trend in the transition condition.While realizing the fuel compensation for the transient conditions,this work is definitely helpful to achieve accurate control of the air-fuel ratio.

Computer Analysis of a Methane Fired Crucible Furnace

Two design factors and one operation parameter of a methane fired crucible furnace are numerically explored in this work. These are the number of burners, the location of the exhaust gas exit, and the air-fuel ratio, respectively. Three dimensional steady state Computational Fluid Dynamics simulations are carried out in order to analyze the influence of the above factors on the mean cavity temperature in absence of thermal load, the methane content and the oxygen content of the exit gas.

Effects of Hydrogen Addition on Power and Emissions Outputs from Diesel Engines

Energy efficiency and environmental impact have become dominant topics in internal combustion engines development. Among many strategies to improve power and emissions outputs from diesel engines is the partial mix of hydrogen and air as fresh charge components to form extremely lean and homogenous mixture, which resist the spontaneous combustion, while diesel fuel is injected directly inside combustion chamber using the conventional fuel injection systems. This contribution presents an analytical and experimental investigation for the effects of adding hydrogen on diesel engines power output and the reduction of emissions. Parametric analysis is used based on lamped parameters modeling of intake manifold to estimate in cylinder trapped charge. The fuel energy flow to engine cylinders is compared for a range of loads and concentrations to simulate relevant case studies. Diesel fuel reduction for significant range of part-load operation can be achieved by introducing hydrogen, along with power improvement emission reductions are affected positively as well. This is achievable without compromising the engine maximum efficiency, given that most engines are operated at small and part-load during normal driving conditions, which allow for introducing more hydrogen instead of large quantities of excess air during such operation conditions that also can be further improved by charge boosting.

Simple adaptive air-fuel ratio control of a port injection SI engine with a cylinder pressure sensor

The problem of air-fuel ratio(AFR) control of the port injection spark ignition(SI) engine is still of considerable importance because of stringent demands on emission control. In this paper, the static AFR calculation model based on in-cylinder pressure data and on the adaptive AFR control strategy is presented. The model utilises the intake manifold pressure, engine speed, total heat release, and the rapid burn angle, as input variables for the AFR computation. The combustion parameters, total heat release,and rapid burn angle, are calculated from in-cylinder pressure data. This proposed AFR model can be applied to the virtual lambda sensor for the feedback control system. In practical applications, simple adaptive control(SAC) is applied in conjunction with the AFR model for port-injected fuel control. The experimental results show that the proposed model can estimate the AFR, and the accuracy of the estimated value is applicable to the feedback control system. Additionally, the adaptive controller with the AFR model can be applied to regulate the AFR of the port injection SI engine.

Effect of rich air/fuel ratio and temperature on NO_x desorption of lean NO_x trap

An experimental and model-based study of the effect of rich air/fuel ratios(AFRs) and temperature on the NOx slip of a lean NOx trap(LNT) was conducted in a lean-burn gasoline engine with an LNT after-treatment system. The emissions of the engine test bench and the inlet temperature of the LNT were used as the major inlet boundary conditions of the LNT. The engine periodically operated between a constant lean AFR of 23 with alterable rich AFRs of 10, 11, 12, 13, and 14. A decrease in the rich AFR of the engine strengthened the desorption atmosphere in the LNT, an effect closely related to the number of reductants, and further heightened the NOx desorption of the LNT, but with a penalty in fuel consumption. To eliminate that penalty, the inlet boundary conditions of the LNT were varied by adjusting the inlet temperature within a range between 200℃ and 400℃. An increase in inlet temperature heightened the NOx desorption of the LNT, and a NOx breakthrough occurred after the inlet temperature exceeded 390℃. To control NOx breakthrough, the inlet temperature can be adjusted to offset the strong desorption atmosphere in the LNT commonly created by a rich AFR.

Improving Energy Efficiency of Tunnel Furnace by Using Heat Optimization Model

Reheating furnace of an integrated steel plant consumes intensive fuel as input energy to heat up stocks prior to hot rolling process. In current scenario, the elevated cost of productivity due to increasing fuel price is emerging as a key concern for the steel industry. A continuous improvement in reduction of fuel consumption is one of the key objectives for the manufacturing units. Numerous research work is going on worldwide to increase the energy efficiency of reheating furnaces. Computational Fluid Dynamics (CFD) and numerical modelling are mostly being used for predicting thermal and reactive fluid characteristic inside a furnace. However, the said methods are very expensive and require a huge infrastructure to compute the results. In addition, these results are not available on real time basis to take corrective action due to high computational time. In this article, an alternative approach has been adopted where complete heat and mass balance of entire tunnel type reheating furnace has been carried out. This study includes first principle-based model where heat conduction, convection and radiation with combustion reactions of the fuel components have been considered. Based on these theoretical calculations, the model is used to identify heat losses at various locations of the furnace. Moreover, a method to optimize the mixing ratio of air and fuel (mixed gas) along with monitoring of heat recovery from combined recuperator have been covered. Based on the model outcome, a significant improvement in furnace efficiency has been achieved, leading to reduction in fuel consumption in the range of 12%.

白蛋白与纤维蛋白原表达比对230例乳腺浸润性导管癌预后影响分析

目的选择合适的预后指标对提高乳腺癌患者的生活质量具有重要意义。本研究探讨白蛋白与纤维蛋白原比(albumin to fibrinogen ratio,AFR)在乳腺浸润性导管癌组织中的表达及预后意义。方法选取河北医科大学第四医院乳腺中心2009-01-01-2012-04-30行手术切除的230例原发性乳腺浸润性导管癌患者石蜡包埋组织为研究对象,收集术前患者血清的纤维蛋白原和白蛋白数值,并采用Kaplan-Meier法及Cox比例回归风险模型进行生存分析,探讨AFR表达与无病生存率(disease free survival,DFS)的关系,并根据多因素结果,将P <0.05建立DFS预后模型。结果 AFR采用二分类法,将AFR分为2组,当AFR≥13.1时,无病生存期为(59.97±17.19)个月,当AFR<13.1时,无病生存期为(65.30±13.74)个月,二者相比差异有统计学意义,Z=1.178,P=0.010。单因素分析结果表明红细胞(Wald=3.962,P=0.047)、AFR(Wald=44.042,P=0.008)、TNM(Wald=6.754,Ⅰ期与Ⅱ期P=0.016,Ⅰ期与Ⅲ期P=0.014)、核分级(Wald=16.947,1级与2级P=0.099,1级与3级P=0.001)、p53(Wald=19.481,<25%与≥25%~<50%P=0.471,<25%与≥50%~<75%P=0.072,<25%与≥75%P=0.014)、Ki-67(Wald=9.223,P=0.002)及脉管瘤栓(Wald=21.171,P<0.001)与无病生存期相关。多因素结果表明AFR(HR=1.346,95%CI为1.107~1.636,P=0.003)、TNM(Ⅰ期与Ⅱ期HR=5.604,95%CI为1.859~16.891,P=0.002;Ⅰ期与Ⅲ期HR=3.674,95%CI为0.856~15.766,P=0.080)、核分级(1级与2级HR=4.450,95%CI为0.749~26.447,P=0.101;1级与3级HR=25.315,95%CI为3.483~183.984,P=0.001)、p53(<25%与≥25%~<50%HR=0.343,95%CI为0.100~1.174,P=0.088;<25%与≥50%~<75%HR=0.051,95%CI为0.009~0.308,P=0.001;<25%与≥75%HR=6.235,95%CI为2.112~18.405,P<0.001)、Ki-67(HR=7.934,95%CI为1.483~42.457,P=0.016)及脉管瘤栓(HR=11.336,95%CI为4.602~27.924,P<0.001)与无病生存期相关,以多因素分析里P<0.05的因素为变量建立乳腺浸润性导管癌患者DFS预后模型,预测患者3年及5年DFS,模型受试者工作特征曲线(receiver operating characteristic curve,ROC)下面积为0.834。结论 AFR低表达是改善乳腺癌DFS的独立预后因素,预后模型预测效能良好。

Research on ammonia emissions characteristics from light-duty gasoline vehicles

In this study,ammonia emissions characteristics of typical light-duty gasoline vehicles were obtained through laboratory vehicle bench test and combined with New European Driving Cycle(NEDC)condition and Worldwide Harmonized Light Vehicles Test Cycle(WLTC)condition.The influence of ambient temperature on ammonia emissions is mainly concentrated in the cold start stage.The influence of ambient temperature on ammonia emission is shown that the ammonia emissions of light-duty gasoline vehicles under ambient temperature conditions(14 and 23℃)are lower than those under low ambient temperature conditions(-7℃)and high ambient temperature conditions(35 and 40℃).The influence of TWC on ammonia emission is shown that ammonia is a by-product of the catalytic reduction reaction of conventional gas pollutants in the exhaust gas in the TWC.Under NEDC operating conditions and WLTC operating conditions,ammonia emissions after the catalyst are 45 times and 72 times that before the catalyst,respectively.In terms of ammonia emissions control strategy research,Pd/Rh combination can reduce NH3 formation more effectively than catalyst with a single Pd formula.Precise control of the engine’s air-fuel ratio and combination with the optimized matched precious metal ratio TWC can effectively reduce ammonia emissions.