Trained Neural network air/fuel control system
    1.
    发明授权
    Trained Neural network air/fuel control system 失效
    训练神经网络空气/燃料控制系统

    公开(公告)号:US5781700A

    公开(公告)日:1998-07-14

    申请号:US597080

    申请日:1996-02-05

    摘要: An electronic engine control (EEC) module executes both open loop and closed loop neural network processes to control the air/fuel mixture ratio of a vehicle engine to hold the fuel mixture at stoichiometry. The open loop neural network provides transient air/fuel control to provide a base stoichiometric air/fuel mixture ratio signal in response to throttle position under current engine speed and load conditions. The base air/fuel mixture ratio signal from the open loop network is additively combined with a closed loop trimming signal which varies the air/fuel mixture ratio in response to variations in the sensed exhaust gas oxygen level. Each neural network function is defined by a unitary data structure which defines the network architecture, including the number of node layers, the number of nodes per layer, and the interconnections between nodes. In addition, the data structure holds weight values which determine the manner in which network signals are combined. The network definition data structures are created by a network training system which utilizes an external training processor which employs gradient methods to derive network weight values in accordance with a cost function which quantitatively defines system objectives and an identification network which is pretrained to provide gradient signals representative of the behavior of the physical plant. The training processor executes training cycles asynchronously with the operation of the EEC module in a representative test vehicle.

    摘要翻译: 电子发动机控制(EEC)模块执行开环和闭环神经网络过程,以控制车辆发动机的空气/燃料混合比,以将燃料混合物保持在化学计量比。 开环神经网络提供瞬时空气/燃料控制,以在当前发动机转速和负载条件下响应于节气门位置提供基本化学计量的空气/燃料混合比信号。 来自开环网络的基本空气/燃料混合比信号与闭环修整信号相加地组合,所述闭环修整信号响应于所检测的废气氧气水平的变化而改变空气/燃料混合比。 每个神经网络功能由定义网络架构的单一数据结构定义,包括节点层的数量,每层节点的数量以及节点之间的互连。 此外,数据结构保存了确定网络信号组合方式的权重值。 网络定义数据结构由网络训练系统创建,该网络训练系统利用外部训练处理器,该外部训练处理器采用梯度方法根据量化定义系统目标的成本函数和预训练的识别网络来提供梯度信号, 的物理植物的行为。 训练处理器在代表性测试车辆中与EEC模块的操作异步执行训练周期。

    Generic neural network training and processing system
    2.
    发明授权
    Generic neural network training and processing system 失效
    通用神经网络训练处理系统

    公开(公告)号:US5745653A

    公开(公告)日:1998-04-28

    申请号:US596535

    申请日:1996-02-05

    摘要: A electronic engine control (EEC) module executes a generic neural network processing program to perform one or more neural network control funtions. Each neural network funtion is defined by a unitary data structure which defines the network architecture, including the number of node layers, the number of nodes per layer, and the interconnections between nodes. In addition, the data structure holds weight values which determine the manner in which network signals are combined. The network definition data structures are created by a network training system which utilizes an external training processor which employs gradient methods to derive network weight values in accordance with a cost function which quantitatively defines system objectives and an identification network which is pretrained to provide gradient signals representative the behavior of the physical plant. The training processor executes training cycles asynchronously with the operation of the EEC module in a representative test vehicle.

    摘要翻译: 电子引擎控制(EEC)模块执行通用神经网络处理程序来执行一个或多个神经网络控制功能。 每个神经网络功能由定义网络架构的单一数据结构定义,包括节点层的数量,每层节点的数量以及节点之间的互连。 此外,数据结构保存了确定网络信号组合方式的权重值。 网络定义数据结构由网络训练系统创建,网络训练系统利用外部训练处理器,该外部训练处理器采用梯度方法根据量化定义系统目标的成本函数和预培训的识别网络来提供梯度信号, 物理植物的行为。 训练处理器在代表性测试车辆中与EEC模块的操作异步执行训练周期。

    Trained neural network engine idle speed control system
    3.
    发明授权
    Trained neural network engine idle speed control system 失效
    训练神经网络发动机怠速控制系统

    公开(公告)号:US6092018A

    公开(公告)日:2000-07-18

    申请号:US597095

    申请日:1996-02-05

    摘要: A electronic engine control (EEC) module executes a neural network processing program to control the idle speed of an internal combustion engine by controlling the bypass air (throttle duty cycle) and the engine's ignition timing. The neural network is defined by a unitary data structure which defmes the network architecture, including the number of node layers, the number of nodes per layer, and the interconnections between nodes. To achieve idle speed control, the neural network processes input signals indicating the current operating state of the engine, including engine speed, the intake mass air flow rate, a desired engine speed, engine temperature, and other variables which influence engine speed, including loads imposed by power steering and air conditioning systems. The network definition data structure holds weight values which determine the manner in which network signals, including the input signals, are combined. The network definition data structures are created by a network training system which utilizes an external training processor which employ dynamic gradient methods to derive network weight values in accordance with a cost function which quantitatively defines system objectives and an identification network which is pretined to provide gradient signals representative of the behavior of the physical plant. The training processor executes training cycles asynchronously with the operation of the EEC module in a representative test vehicle.

    摘要翻译: 电子发动机控制(EEC)模块通过控制旁路空气(节气门占空比)和发动机的点火正时来执行神经网络处理程序来控制内燃机的怠速。 神经网络由统一的数据结构定义,该结构限定了网络架构,包括节点层数,每层节点数以及节点间的互连。 为了实现怠速控制,神经网络处理指示发动机的当前操作状态的输入信号,包括发动机速度,进气质量空气流量,期望的发动机转速,发动机温度和影响发动机转速的其它变量,包括负载 由动力转向和空调系统施加。 网络定义数据结构保持重量值,其确定包括输入信号的网络信号的组合方式。 网络定义数据结构由网络训练系统创建,该网络训练系统利用外部训练处理器,该外部训练处理器采用动态梯度方法来根据量化定义系统目标的成本函数和预先提供梯度信号的识别网络来导出网络权重值 代表物理工厂的行为。 训练处理器在代表性测试车辆中与EEC模块的操作异步执行训练周期。

    Method for identifying misfire events of an internal combustion engine
    5.
    发明授权
    Method for identifying misfire events of an internal combustion engine 失效
    识别内燃机失火事件的方法

    公开(公告)号:US5732382A

    公开(公告)日:1998-03-24

    申请号:US744258

    申请日:1996-11-06

    IPC分类号: G01M15/11 F02D15/00 G01M15/00

    CPC分类号: G01M15/11 F02D41/1405

    摘要: A method for identifying engine combustion failure of an internal combustion engine having a plurality of cylinders, a crankshaft and a crankshaft position sensor includes the steps of operating the internal combustion engine to rotate the crankshaft, measuring rotational quantities of the crankshaft corresponding to events created by each of the plurality of cylinders during operation of the internal combustion engine, correcting the rotational quantities measured to remove periodic position irregularities to generate a corrected temporal signal, generating an acceleration signal of the crankshaft using the corrected temporal signals, and identifying combustion failures as a function of the acceleration signal. A time-lagged recurrent neural network utilizes the acceleration signal, along with other engine parameters to identify the cylinder-specific misfire events.

    摘要翻译: 用于识别具有多个气缸,曲轴和曲轴位置传感器的内燃机的发动机燃烧故障的方法包括以下步骤:操作内燃机以使曲轴旋转,测量曲轴的旋转量,对应于由 在内燃机的运行期间,多个气缸中的每一个,校正测量的旋转量以消除周期性位置不规则以产生校正的时间信号,使用校正的时间信号产生曲轴的加速度信号,以及将燃烧故障识别为 加速度信号的功能。 时间延迟的循环神经网络利用加速度信号以及其他发动机参数来识别气缸特定的失火事件。

    Nonlinear dynamic transform for correction of crankshaft acceleration
having torsional oscillations
    6.
    发明授权
    Nonlinear dynamic transform for correction of crankshaft acceleration having torsional oscillations 失效
    具有扭转振动的曲轴加速度校正的非线性动力学变换

    公开(公告)号:US5699253A

    公开(公告)日:1997-12-16

    申请号:US417361

    申请日:1995-04-05

    摘要: Irregularities in crankshaft velocity introduced when measuring crankshaft rotation at a section of a crankshaft in an internal combustion engine that is less damped to torsional oscillations than is another more accessible crankshaft section are corrected by performing a nonlinear transformation via a neural network to predict rotation measurements that would have been obtained at the inaccessible section from data actually collected at the accessible crankshaft section. Thus, the effects of torsional oscillations in the crankshaft are substantially filtered away, resulting in crankshaft acceleration values that form the basis of a misfire detector having nearly maximum signal-to-noise performance.

    摘要翻译: 通过经由神经网络执行非线性变换来校正在比内部燃料发动机曲轴减小扭转振荡的曲轴的曲轴转动时引入曲轴速度的不规则性,以通过神经网络进行非线性变换来预测旋转测量, 将在可访问曲轴部分实际收集的数据的不可接近部分获得。 因此,曲轴中的扭转振荡的影响基本上被过滤掉,导致曲轴加速度值形成具有几乎最大的信噪比性能的失火探测器的基础。

    Method of controlling cyclic variation in engine combustion
    8.
    发明授权
    Method of controlling cyclic variation in engine combustion 失效
    控制发动机燃烧循环变化的方法

    公开(公告)号:US5921221A

    公开(公告)日:1999-07-13

    申请号:US75291

    申请日:1998-05-08

    IPC分类号: F02D41/14 F02M7/00

    摘要: Cyclic variation in combustion of a lean burning engine is reduced by detecting an engine combustion event output such as torsional acceleration in a cylinder (i) at a combustion event (k), using the detected acceleration to predict a target acceleration for the cylinder at the next combustion event (k+1), modifying the target output by a correction term that is inversely proportional to the average phase of the combustion event output of cylinder (i) and calculating a control output such as fuel pulse width or spark timing necessary to achieve the target acceleration for cylinder (i) at combustion event (k+1) based on anti-correlation with the detected acceleration and spill-over effects from fueling.

    摘要翻译: 通过使用检测到的加速度来检测在燃烧事件(k)中的气缸(i)中的扭转加速度的发动机燃烧事件输出来减少燃烧发动机的燃烧中的循环变化,以预测气缸 下一个燃烧事件(k + 1),通过与气缸(i)的燃烧事件输出的平均相位成反比的校正项来修正目标输出,并计算诸如燃料脉冲宽度或火花时间之类的控制输出, 基于与检测到的加速和加油溢出效应的反相关,实现燃烧事件(k + 1)下气缸(i)的目标加速度。

    Feed forward method for canister purge compensation within engine air/fuel ratio control systems having fuel vapor recovery

    公开(公告)号:US06523531B1

    公开(公告)日:2003-02-25

    申请号:US09997797

    申请日:2001-12-03

    IPC分类号: F02D4114

    摘要: A method for air/fuel operation of an engine. The engine is supplied fuel from both a fuel purging system to purge fuel in a fuel supply and feed such purged fuel to an intake manifold of the engine and a fuel injection system to inject fuel from such fuel supply into a cylinder of such engine. The method includes producing a first air/fuel ratio control signal in accordance with measured exhaust gas oxygen emission from the engine; producing a second air/fuel ratio control signal in accordance with fuel transport delay through the fuel purging system; combining the first and second air/fuel ratio control signals into a composite control signal; and feeding such composite control signal to the fuel injection system. Producing the first air/fuel ratio control signal comprises determining fuel flow rate through the purge system. The purge system includes a valve, such valve passing the fuel in the purging system to the intake manifold at a rate relate to a duty cycle of a control signal fed to such valve and wherein the flow rate is determined in response to the duty cycle the control signal fed to the valve. The purge system includes a hydrocarbon sensor responsive to fuel in the purging system and wherein the first air/fuel ratio control signal is produced in accordance with an output of such sensor. The method includes determining a species of hydrocarbon in the fuel being purged and adjusting the first air/fuel ratio control signal in accordance with the determined species. The species determination comprises determining from the exhaust gas oxygen a deviation of the engine emissions from stoichiometry. The method includes providing a model of the engine. The model represents a relationship between: (1) a signal model LAMBSE, representative of estimated air/fuel ratio of the engine relative to a stoichiometric air/fuel ratio for the engine; and, (2) fuel injected into the cylinder of the engine. Exhaust gas oxygen emission from the engine is measured during operation of such engine. Actual LAMBSE produced by such engine during operation of such engine is produced as a function of such measured oxygen. The actual LAMBSE is compared with the model LAMBSE provided by the model in response to fuel injected into the engine to produce a model error signal. The fuel injected into the engine is adjusted in accordance with the error signal.