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.

Air flow control based on optimal oxygen excess ratio in fuel cells for vehicles

Air flow control is one of the most important control methods for maintaining the stability and reliability of a fuel cell system, which can avoid oxygen starvation or oxygen saturation. The oxygen excess ratio （OER） is often used to indicate the air flow condition. Based on a fuel cell system model for vehicles, OER performance was analyzed for different stack currents and temperatures in this paper, and the results show that the optimal OER was affected weakly by the stack temperature. In order to ensure the system working in optimal OER, a control scheme that includes an optimal OER regulator and a fuzzy control was proposed. According to the stack current, a reference value of air flow rate was obtained with the optimal OER regulator and then the air compressor motor voltage was controlled with the fuzzy controller to adjust the air flow rate provided by the air compressor. Simulation results show that the control method has good dynamic and static characteristics.

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.

Study on a Closed-Loop Air-Fuel Control System of Gasoline Engines by Simulation

In order to study the factors that influence the air fuel ratio(A/F), the amplitude and frequency of A/F fluctuation, to reform the control strategy, and to improve the efficiency of three way catalyst(TWC), a model of closed loop control system including the engine, air fuel mixing and transportation, oxygen sensor and controller, etc., is developed. Various factors that influence the A/F control are studied by simulation. The simulation results show that the reference voltage of oxygen sensor will influence the mean value of A/F ratio, the controller parameters will influence the amplitude of A/F fluctuation, and the operating conditions of the engine determine the frequency of A/F fluctuations, the amplitude of A/F fluctuation can be reduced to within demanded values by logical selection of the signal acquisition method and controller parameters. Higher A/F fluctuation frequency under high speed and load can be reduced through software delay in the controller. The A/F closed loop control system based on the simulation results, accompanied with a rare earth element TWC, gives a better efficiency of conversion against harmful emissions.

汽油机碳罐冲洗控制策略仿真与试验

以某汽油机碳罐冲洗控制策略为研究对象,基于Simulink平台以模块化建模思路搭建了包含目标冲洗率计算、目标冲洗流量计算和电磁阀流量特性标定模块的控制策略仿真模型.使用流量计实测车辆转毂循环工况冲洗流量,验证模型控制精度与空燃比控制效果,进而基于模型优化控制特征参数,探究提升冲洗流量途径.研究表明:模型仿真与实测累积冲洗流量分别为402.69 L、373.62 L,仿真误差为7.78%;常规冲洗率因子、电磁阀开启速度、电磁阀最大开度限制和初始冲洗率因子均对冲洗过程产生重要影响,且相互独立;基于模型综合优化控制策略特征参数,累积冲洗量由373.62 L提升至499.61 L,且空燃比控制效果良好.试验为在保持空燃比控制在当量比的前提下,尽可能提高汽油机碳罐冲洗流量的控制策略设计提供参考.

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.

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.

热风炉空燃比并行协作粒子群滑模控制策略

针对热风炉燃烧控制存在的纯滞后、大惯性和强干扰等问题,提出了一种基于并行协作骨干粒子群(Parallel Cooperative Bare-Bones Particle Swarm Optimization,PCBBPSO)优化全局滑模控制(Global Sliding Mode Control,GSMC)的热风炉空燃比控制策略;为改善热风炉空燃比控制系统动态特性,引入全局滑模策略,对燃烧系统进行优化控制,以提高系统稳定性,同时,基于热风炉燃烧系统存在的强干扰特性,利用并行协作骨干粒子群对干扰补偿进行调节以减小其对系统的影响,并求取最优控制率;仿真结果表明:与普通粒子群优化全局滑模和普通粒子群优化PID相比,该控制方法达到稳定用时分别减少了26.4 s和9.3 s,能够保持没有超调量,拥有良好稳定的跟踪和抗干扰效果;将该控制策略应用于某钢铁有限公司2200 m 3高炉配套热风炉,工程数据表明:在该空燃比策略的控制下,热风炉空燃比上下波动幅度仅为8.20%,拥有波动小、稳定性好和抗干扰性强等特点,动态响应较好,能够满足热风炉工程实际应用的需要。

串联型滑模结构的燃料电池供气系统控制研究

针对燃料电池空气供给系统动态性能易受负载变化和外界环境因素影响的问题,设计了一种由超螺旋滑模控制与终端滑模控制相结合的串联型控制策略。建立了面向控制的五阶动态模型,提出了在负载变化时供气系统跟踪最佳过氧比、最大净输出功率和阴极压力测量的控制问题;提取最佳期望值并设计控制器,利用Lyapunov方法进行闭环稳定性验证。仿真分析可知,所搭建的观测器扰动估计值与理论实际值误差在0.01%以内,且本文方法与PID控制相比过氧比跟踪最佳期望值响应时间提高了6.9%,最大净功率输出值提高0.2%,阴极压力响应时间相比提高了60%。由结果可得,本文策略在负载变化时可以有效的控制供气系统过氧比跟踪最佳期望值并输出最大净功率,能够准确、迅速的估计阴极压力,能够较好的估计扰动,具有较强的抗干扰能力。

基于转矩需求和进气量广义预测的汽车发动机空燃比神经网络控制方法

分析燃烧特性与温度值,进行汽车发动机空燃比控制,但是忽略了发动机内部喷输油过程的延迟性影响,导致控制结果空燃比与理想值偏差较大。因此,提出基于转矩需求和进气量广义预测的汽车发动机空燃比神经网络控制方法。基于转矩需求分析汽车动力系数,针对发动机喷输油过程对发动机进气量进行广义上的预测,根据预测值对喷输油延迟进行补偿,优化空燃比控制律实现控制过程。实验结果表明:本文方法应用后得出的控制结果,表现出的空燃比变化与理想的14.7空燃比十分接近,控制效果较为优质,满足了汽车发动机燃烧质量的实际需求。

Application of Optimization Technology for Ratio of Air to Fuel Combining Feedforward with Feedback in Heating Furnace

The thermal characteristics of heating furnace using gas as fuel are discussed in detail in this paper. Combining the technique of fuzzy control with calorific value of feedforward and oxygen concentration of waste gas feedback, the optimization model for ratio of air to fuel is developed and utilized in practice. According to the practical operation, the model can effectively control the oxygen concentration of waste gas, enhance the quality of product and decrease the fuel consumption.

车用汽油发动机电子控制系统研究现状与展望

发动机电子控制系统是高性能、高可靠性发动机开发的核心研究内容,是保证发动机动力性、经济性和排放性的重要因素之一.针对车用汽油发动机,本文首先分析了典型的车用汽油发动机电子控制系统结构,然后围绕电子节气门控制系统、燃油喷射控制系统、点火控制系统、空燃比控制系统、怠速控制系统、涡轮增压控制系统、爆震检测与控制系统以及汽油机先进燃烧模式控制这8项关键问题展开论述,并着重介绍了近年来国内外的研究内容和研究成果.最后对车用汽油发动机电子控制系统的发展前景和发展方向进行了展望.

车用汽油机过渡工况空燃比的神经网络控制研究

针对车用汽油机过渡工况空燃比难于精确控制的特点,提出了一种空燃比的神经网络复合控制策略。控制系统通过神经网络控制和常规PI控制实现前馈反馈控制,常规PI控制器利用氧传感器信号实现反馈控制,保证系统的稳定性,且抑制扰动;神经网络控制实现前馈控制,提高控制系统过渡工况时的响应能力。神经网络采用径向基神经网络,其输入为影响汽油机进气量的两个主要因素发动机转速与节气门开度。通过在线学习常规PI控制输出,使系统的总控制输出由神经网络产生,系统具有较高的自适应功能,有效避免目前过渡工况空燃比控制需进行大量标定的不足。仿真结果表明该控制方法是有效的。

基于神经网络的汽油HCCI发动机空燃比控制策略

均质压缩燃烧(HCCI)在控制上存在难点,其中关键是基于循环的空燃比实时控制。HCCI汽油机没有能直接表征发动机每循环进气量的参数,因此,采用动态递归神经网络(Elman网络)预测HCCI发动机每循环的进气量。通过氧传感器闭环和瞬态工况中的油膜补偿,实现对HCCI发动机的稳态及瞬态工况下空燃比的精确控制。试验表明:汽油HCCI发动机神经网络预测模型及空燃比控制策略能满足HCCI发动机实时控制的需求。

瞬态空燃比控制策略研究及智能控制的应用

介绍了基于平均值模型的汽油发动机瞬态空燃比控制策略,及人工智能和神经网络技术在模型参数辨识中的应用。

航空活塞式发动机瞬态空燃比控制与实验研究

针对航空活塞式直喷发动机瞬态空燃比难以精确控制、动态超调大等问题,采用PID神经网络控制策略对发动机瞬态工况空燃比进行控制.PID神经网络用于瞬态空燃比控制具有易于实现、较强自适应能力等优点.该策略包含前馈控制和反馈控制,并由前馈控制确定基本喷油量,PID神经网络作为反馈控制,实现瞬态工况的燃油补偿.在一台航空活塞式单缸机上进行了发动机瞬态空燃比控制实验,结果表明,瞬态工况下,相比于PID控制,PID神经网络控制下的过量空气系数超调量可以减小25%左右;节气门开度在5%~30%,之间以不同开度变化速率变化时,PID神经网络也能实现良好的控制效果.

氧传感器响应变慢自适应空燃比闭环控制方法研究

分析了汽油发动机空燃比闭环PI控制器的数学模型,提出了自适应空燃比闭环控制算法,研究了阶跃型氧传感器响应变慢对汽油机空燃比和排放的影响。研究结果表明:当氧传感器信号从稀到浓变慢时,过量空气系数相对于正常值会减小,同时HC和CO排放浓度会增大;当氧传感器信号从浓到稀变慢时,过量空气系数相对于正常值会增大,同时氨氧化物(NOx)排放浓度会增大。试验结果表明:设计的自适应空燃比PI控制器减小了在氧传感器响应变慢时过量空气系数偏离正常值的幅度,能够减少有害气体排放。

神经网络在汽油机瞬态空燃比控制中的应用

为了对稀薄燃烧汽油机的瞬态空燃比进行精确控制,提出了一个稀燃汽油机空燃比神经网络-滑模控制方案,该方案采用神经网络实现对瞬态过程中实际进入气缸内进气量的精确预测和进气管内油膜动态特性的前馈补偿.在一台稀燃发动机上进行了瞬态空燃比实验,节气门急速变化时的空燃比超调最大为1个空燃比单位,最小为0.2个空燃比单位;空燃比调整时间一般在3 s以内,最快可达到1 s.控制结果达到了对稀燃发动机瞬态空燃比的精确控制。

基于BP神经网络进气预估的汽油机瞬态空燃比控制研究

针对某款单缸大排量摩托车发动机,在Matlab/Simulink中建立带油膜补偿器的基于BP神经网络进气量预估模型,对上述组成的空燃比控制模型进行了仿真研究。结果表明,基于BP神经网络的进气量预估控制模型能将超调量控制在10%以内,并能够在1.4s内将混合气恢复至当量比,避免了传统PID控制可能出现的震荡情况,表明基于进气预估的空燃比控制效果良好;加入油膜补偿后,其空燃比超调量不超过5%,能够在1.2s内将混合气恢复至当量比,说明加入油膜补偿前馈控制能够有效降低燃油传输动态特性带来的影响,提高控制精度。

基于PCS7的加热炉燃烧控制策略及仿真研究

针对加热炉控制系统中存在的燃烧效率不高,控制响应延迟大的问题。设计了一套基于某公司SIMATIC PCS7控制系统的加热炉燃烧控制策略。系统针对加热炉燃烧控制中的主要参数:物料出口温度,空燃比,炉膛压力分别采用串级双交叉比值限幅控制策略,模糊控制策略和前馈控制策略进行控制。控制过程采用高级多功能过程实训系统(SMPT)仿真加热炉,利用SIMATIC PCS7控制系统实施加热炉的控制方案并利用上位机软件WinCC进行在线的实时监控。控制过程自动运行,根据控制过程和仿真结果表明,方案安全可靠,控制效果和可行性较好。比较于传统的基于数学模型的加热炉控制策略,方案提供了一种新型的控制策略,在很大程度上解决了加热炉燃烧效率不高,控制响应延迟大的问题。