Ford Global Technolgoies, LLC

Ford Motor Company Limited

Lockheed Martin Energy Research Corporation

Ford Global Tech.inc

Lee Albert Feldkamp

Gintaras Vincent Puskorius

Leighton Ira Davis, Jr

Kenneth A Marko

Timothy Mark Feldkamp

John V James

Fumin Yuan

Gerald Jesion

Dinu Petre Madau

Dimitar Petrov Filev

Kwaku O Prakah-Asante

Francis Thomas Connolly

John W Hoard

James W Butler

Charles Stuart Daw

Raoul Tawel

Yelena Mordechai Rodin

James Calvey Carnes

Sam Ebenstein

Greg Smith

Nazeeh Aranki

Danll Valentinovich Prokhorov

Tomas Larsson

Steven H Seippel

Ma Lixing

Christine A Gierdzak

Charles Eagen

Danil Valentinovich Prokhorov

Various methods are described for monitoring cylinder valve deactivation in an engine, the engine including at least a cylinder valve actuator for deactivating at least a cylinder of the engine. One example method comprises indicating degradation of the valve actuator based on crankshaft acceleration.

Methods for variable displacement engine diagnostics

A system for detecting the presence of a human in a vehicle is provided. The system includes a vibration sensor that is configured to detect vibrations of the vehicle, and to output signals related to the sensed vibrations. A processor is configured to receive the signals output from the vibration sensor. The processor also operates a neural network that has a plurality of nodes, at least some of which are recurrent. The use of the recurrent nodes allows the output of a recurrent node to be fed back into itself, or another node. In addition, the output that is fed back can be combined with other inputs entering the node. In this way, the neural network can quickly learn to distinguish between various conditions, including an occupied state and an unoccupied state of the vehicle. The neural network provides an output indicating whether the vehicle is occupied.

System and method for detecting presence of a human in a vehicle

A method is provided of adaptively controlling a paint system for painting vehicle bodies. The method includes the steps of obtaining an estimated Jacobian that identifies characteristics of the paint system and using the estimated Jacobian to determine initial conditions to be implemented for the next vehicle body to be painted in the paint system. The method also includes the steps of storing a database of appropriate initial conditions that resulted in satisfactory transient response in a rule-base and using the rule-base at start-up of the paint system or if the paint system fails to be satisfactorily controlled.

Method of adaptively controlling paint system

A method for air/fuel operation of an engine. 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.

Method for canister purge compensation using internal model control

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.

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

An engine diagnostic system includes a bit-serial based recurrent neuroprocessor for processing data from an internal combustion engine in order to diagnose misfires in real-time and reduces the number of neurons required to perform the task by time multiplexing groups of neurons from a candidate pool of neurons to achieve the successive hidden layers of the recurrent network topology.

Automotive engine misfire detection system including a bit-serial based recurrent neuroprocessor

An engine misfire detection system (,) for detecting engine misfire. System (,) includes a conventional controller (,) having a memory unit (,) and a plurality of sensors (,). Controller (,) includes a plurality of neural networks, which are trained by system (,), and which determine whether a firing event is a misfire based upon events occurring before the firing event and events occurring after the firing event. The neural networks are adaptively trained to compensate for the effects of engine variability and aging.

Method for adaptive detection of engine misfire

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.

Trained neural network engine idle speed control system

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.

Method of controlling cyclic variation in engine combustion

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.

Trained Neural network air/fuel control system

A method of automating the calibration of lookup tables containing correction values to be used in an on-board vehicle system is disclosed. The method includes training a neural network to model engine behavior by outputting cylinder specific crankshaft acceleration correction values in response to any engine speed and load input conditions. The correction values generated are stored in a memory device. The training takes place off-board the vehicle, using a data set previously obtained from operating a representative engine under normal operating conditions.

Method of generation correction tables for misfire detection using

A microcontroller-based fuzzy logic processing module for generating control signal values in response to variable input signal values in accordance with constraints imposed by propositions or 'rules' stored in memory in a standardized format. Each rule consists of one or more input conditions and an output directive. The input conditions and the output directive for a given rule are 'fuzzified' by determining the degree of membership of each in fuzzy sets defined by membership functions. Fuzzy logic processing is accomplished by determining the extent to which the input conditions are satisfied by the current values of the input signals in order to develop a rule strength value, and then performing a 'center-of-gravity' determination based on the rule strength values assigned to the output membership functions. The center-of-gravity determination performed by representing each output membership function by a discrete value whose magnitude is adjusted to reflect the non-linear relationship between a rule's strength and its influence on the command output value. Using the discrete values weighted in accordance with their pre-calculated area centers, with an adjustment for overlap between adjacent output functions, the center-of-gravity is accurately approximated without requiring piece-wise integration of the output centroid.

Fuzzy logic output defuzzification

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.

Generic neural network training and processing system

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.

Method for identifying misfire events of an internal combustion engine

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.

Growing community of inventors

Plymouth, MI, United States of America

Lee Albert Feldkamp