Abstract: Optimization control of a control system by improving evolution efficiency while retaining the advantages of genetic optimization is described. An optimizer for evolving control parameters affecting the characteristics of a control system uses actual user fitness evaluations of various control parameters or control parameters arranged as chromosomes. Parameters or chromosomes for a next generation are pre-processed using an evaluation model that estimates the fitness of new chromosomes before the chromosomes are presented to the user. Chromosomes that have a low estimated fitness value are modified or deleted, thereby reducing the number of low-quality chromosomes evaluated by the user.

Abstract: A powertrain controller of a vehicle provides fuel injection pulses based on gasoline operation. The pulse widths of the fuel injection pulses are modified with reference to air temperature, engine speed, and exhaust gas oxygen (EGO) content to control fuel injectors for an alternative fuel such as natural gas. The EGO content, based on alternative fuel operation, is detected and compared to a desired air-fuel ratio or desired fuel trims to provide error information that is used to adjust the modification of the pulse widths. In response to the error information, a neural network (as an example) dynamically adjust the pulse widths of the alternative fuel injection based on the weights of measured, detected engine speed, EGO, universal exhaust gas oxygen, or air temperatures. The engine operating on alternative fuel is provided with the proper mixture of alternative fuel and air to respond to various engine loads and meet emission standards.

Abstract: A manipulation variable generating unit 7 for generating a target air-fuel ratio KCMD to converge the output of an oxygen concentration sensor 5 disposed downstream of a catalytic converter 3 in an exhaust system E as a plant to a given target value has a plurality of estimators for generating data indicating estimated values of the output of the oxygen concentration sensor after a dead time of the exhaust system E or a total dead time which is the sum of the dead time of the exhaust system E and a dead time of a system comprising an engine control unit 8 and an internal combustion engine 1, according to respective different algorithms. The manipulation variable generating unit 7 generates the target air-fuel ratio KCMD according to an adaptive sliding mode control process using a value selected from the estimated values or a combined value representing a combination of the estimated values.

Abstract: A method, system, and machine-readable storage medium for determining a predetermined operating condition of an internal combustion engine are disclosed. In operation, the method, system and machine-readable storage medium measure a cylinder pressure in at least one combustion chamber at a predetermined point in a combustion cycle. Next, the method, system, and machine-readable storage medium determine at least a first value for an operating parameter of the engine using the measured cylinder pressure, determine a second value for the operating parameter of the engine using data received from at least one engine sensor, and then generate a predetermined signal if a difference between the first value and the second value has a predetermined relationship.

Abstract: A reduced control system suitable for control of an engine as a nonlinear plant is described. The reduced control system is configured to use a reduced sensor set for controlling the plant without significant loss of control quality (accuracy) as compared to an optimal control system with an optimum sensor set. The control system calculates the information content provided by the reduced sensor set as compared to the information content provided by the optimum set. The control system also calculates the difference between the entropy production rate of the plant and the entropy production rate of the controller. A genetic optimizer is used to tune a fuzzy neural network in the reduced controller. A fitness function for the genetic optimizer provides optimum control accuracy in the reduced control system by minimizing the difference in entropy production while maximizing the sensor information content.

Abstract: The present invention is directed to a method and device for operating an engine of a motor vehicle. Firstly, driving condition parameters of the engine and/or the motor vehicle are collected over a predetermined period of time. After that the probabilities of parameters for the future operation of the engine in relation to the captured driving condition parameters are ascertained. Finally, operating parameters of the engine are adjusted in relation to the ascertained probability values for the parameters.

Abstract: The invention relates to a process for controlling at least two production units whose outputs are connected in parallel in order to produce a common output flow which is intended to feed a consumer plant. It controls the common output flow as a function of a predetermined target value (u) and includes the steps consisting in measuring at least one variable representing the common output flow; for each unit, determining a control instruction corresponding to one operating state of the unit among a finite set of predetermined operating states; and controlling the units with the control instructions determined. Two variables representing the common output flow are measured and the control instructions are determined by a fuzzy-logic controller. Application to controlling a set of compressors.

Abstract: A method of controlling an internal combustion engine includes determining the pressure within the cylinder with a pressure sensor which samples at specific positions of the piston indicating the properties of the thermodynamic cycle. The engine is controlled and operating condition diagnosed in real time based on that series of cylinder pressures at corresponding piston positions.

Abstract: An improved control system for controlling a machine such as a fuel injection system and a robot system. In a primary feature, the control system comprises means for actuating the subject, a partial learning system for learning an control parameter determining an input and output of the means for actuating the subject based upon an error between an objective amount and an output amount of the subject as educator data to adjust the control parameter and a whole learning system for learning an adjustment coefficient based upon the error as educator data to adjust the adjustment coefficient.

Abstract: A method for determining internal pressure in the cylinders of an internal combustion engine by measuring and analyzing structure borne noise signals using a neural network.

Abstract: A manipulation variable generating unit 7 for generating a target air-fuel ratio KCMD to converge the output of an oxygen concentration sensor 5 disposed downstream of a catalytic converter 3 in an exhaust system E as a plant to a given target value has a plurality of estimators for generating data indicating estimated values of the output of the oxygen concentration sensor after a dead time of the exhaust system E or a total dead time which is the sum of the dead time of the exhaust system E and a dead time of a system comprising an engine control unit 8 and an internal combustion engine 1, according to respective different algorithms. The manipulation variable generating unit 7 generates the target air-fuel ratio KCMD according to an adaptive sliding mode control process using a value selected from the estimated values or a combined value representing a combination of the estimated values.

Abstract: An exhaust emission control system for an internal combustion engine having an exhaust system is disclosed. The control system may include an exhaust gas purifying device provided in the exhaust system and an oxygen concentration sensor provided downstream of the exhaust gas purifying device. The exhaust gas purifying device may include at least an oxygen storing ability or a nitrogen oxide storing ability. An air-fuel ratio of an air-fuel mixture supplied to the engine may be enriched with respect to the stoichiometric air-fuel ratio, so as to reduce the oxygen or nitrogen oxides stored in the exhaust gas purifying device. A predicted value of the output from the oxygen concentration sensor may be calculated using a predictor based on the fuzzy logic reasoning. The completion of the reduction of the oxygen or nitrogen oxides stored in said exhaust gas purifying device may be determined according to the predicted value.

Abstract: A data estimation capability using a FNN to estimate engine state data for an engine control system is described. The data estimation capability provides for making data relating to the engine state available as control parameters in a simple, inexpensive manner. The data estimation includes using data from one or more sensors as inputs to a FNN to estimate unmeasured engine operating states. The data estimates are provided as control parameters to an engine control system. The FNN can be used to provide data estimates for engine state values (e.g. the exhaust air fuel ratio, the exhaust NOx. value, the combustion chamber temperature, etc.) that are too difficult or too expensive to measure directly. Each FNN can be configured using a genetic optimizer to select the input data used by the FNN and the coupling weights in the FNN.

Abstract: An integrated control system for a machine such as an engine. The machine is composed of plurality of components such as a throttle valve and a fuel injector. The control system has a plurality of control modules for controlling the respective components and finally controlling the machine through the control of the components. Each control module is associated with at least one parameter for controlling each component. The parameter is evolved under genetic algorithm so as to be adapted to at least one of a predetermined characteristic that is a target of the machine, a characteristic of a user who uses the machine, a using condition and an environmental condition of the machine.

Abstract: In a method for operating a four-stroke internal combustion engine, a homogeneous lean basic mixture of air and fuel is ignited by compression ignition. The fuel is introduced by direct fuel injection into a combustion space delimited by a cylinder with a piston guided sealingly therein. In the case of homogeneous mixture formation, due to the supply of energy as a result of compression a homogeneous ignition performance is established, and pronounced self-accelerating energy release takes place as a result.

Abstract: A reduced control system suitable for control of an engine as a nonlinear plant is described. The reduced control system is configured to use a reduced sensor set for controlling the plant without significant loss of control quality (accuracy) as compared to an optimal control system with an optimum sensor set. The control system calculates the information content provided by the reduced sensor set as compared to the information content provided by the optimum set. The control system also calculates the difference between the entropy production rate of the plant and the entropy production rate of the controller. A genetic optimizer is used to tune a fuzzy neural network in the reduced controller. A fitness function for the genetic optimizer provides optimum control accuracy in the reduced control system by minimizing the difference in entropy production while maximizing the sensor information content.

Abstract: A method and system for optimizing performance of vehicle control systems based on the dynamics of the specific vehicle include a sensor for sensing a predetermined parameter associated with any one of the vehicle control systems during a predetermined trigger event. A control logic determines a critical vibration mode characteristic for the vehicle control system based on the sensed parameter and operates the vehicle control system based on the determined critical vibration mode characteristic.

Abstract: An engine misfire detection system (10) for detecting engine misfire. System (10) includes a conventional controller (12) having a memory unit (14) and a plurality of sensors (16). Controller (12) includes a plurality of neural networks, which are trained by system (10), 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.

Abstract: A system and method for use in a motor vehicles is disclosed for calculating a fuel multiplier during transient engine operation. The fuel multiplier modifies the amount of fuel released from a fuel actuator into an engine. The fuel control system uses neural network logic to establish the fuel multiplier. The neural network logic involves taking inputs from engine sensors, processing the inputs through an input layer, a hidden layer and an output layer resulting in a fuel multiplier.

Abstract: An apparatus for predicting cylinder pressure for on-vehicle control of an internal combustion engine includes a piston sensor, a cylinder pressure sensor, and a controller. The piston sensor is coupled to a piston located in the engine. The piston sensor detects the piston position and generates a piston position signal. The cylinder pressure sensor is coupled to a cylinder located in the engine. The cylinder pressure sensor detects the cylinder pressure and generates a cylinder pressure signal. The controller receives both the piston position signal and the cylinder pressure signal. A neural network, located in the controller, uses this data to predict an undesirable cylinder pressure during a future combustion event. The controller then modifies the future combustion event in response to the predicted undesirable cylinder pressure.

Abstract: A virtual vehicle sensor includes a neural network which produces a sensor output based on a linear combination of non-linear physical signals generated by conventional physical sensors. Instead of determining an output directly, the neural network determines the polynomial coefficients as functions of the physical signals indicative of other engine operating parameters. The sensor is manufactured using relatively limited data collection to calibrate a simulation model. The output of the simulation model is used for model-based mapping to generate more comprehensive maps used for training the neural network. The trained neural network is embedded in a controller and acts as the virtual sensor to monitor engine parameters which are difficult to measure or for which conventional physical sensors do not currently exist. The virtual sensor may be used to sense parameters such as in-cylinder residual mass fraction, emission levels, in-cylinder pressure rise during combustion, and exhaust gas temperature.

Abstract: A reduced control system suitable for control of an engine as a nonlinear plant is described. The reduced control system is configured to use a reduced sensor set for controlling the plant without significant loss of control quality (accuracy) as compared to an optimal control system with an optimum sensor set. The control system calculates the information content provided by the reduced sensor set as compared to the information content provided by the optimum set. The control system also calculates the difference between the entropy production rate of the plant and the entropy production rate of the controller. A genetic optimizer is used to tune a fuzzy neural network in the reduced controller. A fitness function for the genetic optimizer provides optimum control accuracy in the reduced control system by minimizing the difference in entropy production while maximizing the sensor information content.

Abstract: An integrated control for a subject such as an engine installed in a vehicle or vessel is conducted by the steps of: determining the characteristics of a user and/or using conditions; and changing characteristics of a control system of a subject in accordance with the determined characteristics. Normally, the control system includes: a reflection hierarchy for outputting a basic output; a learning hierarchy for learning and operation; and an evolutionary-adaptation hierarchy for selecting the most adaptable module. The subject is "trained" to suit the characteristics of the user and/or the using conditions.

Abstract: A fuel injection control system of an engine includes: (a) an intake air quantity estimation unit for estimating the quantity of intake air; (b) an intake fuel quantity estimation unit for estimating the quantity of intake fuel; (c) an estimated air-fuel ratio calculation unit for calculating an estimated air-fuel ratio; (d) a target air-fuel ratio setting unit for setting a target air-fuel ratio; (e) a feedback control unit for providing a fuel injection signal to the engine, which fuel injection signal is outputted also to the intake fuel quantity estimation unit as one of the predetermined signals; and (f) an actual air-fuel ratio deviation estimation unit for estimating a deviation of an actual air-fuel ratio or a factor correlated thereto from a predetermined level, which unit is programmed to output a deviation signal based on predetermined signals.

Abstract: A system and method for use in a motor vehicles is disclosed for calculating a fuel multiplier during transient engine operation. The fuel multiplier modifies the amount of fuel released from a fuel actuator into an engine. The fuel control system uses neural network logic to establish the fuel multiplier. The neural network logic involves taking inputs from engine sensors, processing the inputs through an input layer, a hidden layer and an output layer resulting in a fuel multiplier.

Abstract: A simplified fault logic accomodation control which utilizes fuzzy logic to assist in calculating a preselected weighted average of the values of two redundant sensors that are sensing the same parameter. A synthesized, third, predicted value of the parameter is used in the fuzzy logic to arbitrate between the two sensed values.

Abstract: A control system for a motor vehicle has several components for carrying out different tasks to control the vehicle. The data, which are necessary from the components, are acquired independently by the components either via data interrogation or via request relationships.

Abstract: An output parameter estimation apparatus for estimating an output parameter from an input data set that is composed of a plurality of input parameters and that is obtained whenever sampling time series input data. In this output parameter estimation apparatus, a fuzzy inference rule is used to calculate a fitness degree of the input data set in one of a plurality of fields included in a space that is formed using at least one input parameter. According to the calculated fitness degree, introduction routes through which the input data set is to be inputted into a neural network are selected. The neural network is set in a connection condition corresponding to the field to which the input data set belongs, the connection condition having been determined in advance as a result of learning process. With this connection condition, the neural network estimates the output parameter from the input data set inputted through the selected introduction routes.

Abstract: An integrated control for a subject such as an engine installed in a vehicle or vessel is conducted by the steps of: determining the characteristics of a user and/or using conditions; and changing characteristics of a control system of a subject in accordance with the determined characteristics. Normally, the control system includes: a reflection hierarchy for outputting a basic output; a learning hierarchy for learning and operation; and an evolutionary-adaptation hierarchy for selecting the most adaptable module. The subject is "trained" to suit the characteristics of the user and/or the using conditions.

Abstract: An engine control system includes an inverse model which includes a forward model and a feedback loop, wherein an actuating parameter, such as the quantity of fuel injected from a fuel injector, outputted from the forward model is used as a controlled variable, such as the air-fuel ratio in an exhaust system, inputted into the inverse model through the feedback loop. The forward model has preferably a learning function using condition-indicating factors such as engine speed and throttle angle. Accuracy of the inverse model is improved and appropriate engine control can be realized even during a transient state of the engine.

Abstract: A model-based control system for controlling a state of an operating subject such as an engine, characterized by forming an inverse model using a forward model and a feedback control system. The subject is modeled using first-order lag elements and dead time, and dead time is removed from the feedback control system. Responsiveness is high not only during a stable state but also during a transient state.

Abstract: An air/fuel ratio control apparatus for executing auxiliary control of an air/fuel ratio by compensating an injected fuel amount set by a control system for maintaining the air/fuel ratio at a preset value. The air/fuel ratio control apparatus includes a state detecting unit for detecting a plurality of physical values which can be measured at low temperature and which show a state of an engine, an air/fuel ratio estimating unit for receiving a plurality of physical values detected by the state detecting means as input parameters and for estimating the air/fuel ratio using a neural network, and a compensatory fuel amount calculating unit for calculating a compensatory fuel amount for the injected fuel amount from the estimated air/fuel ratio. Here, low temperature refers to a temperature at which an air/fuel sensor cannot operate.

Abstract: The invention provides a process and apparatus for controlling combustion in an Otto combustion engine in which the control variables that control combustion are determined for a particular power cycle as a function of the detected combustion course of a preceding power cycle. According to the invention, a desired burn-through function value for a particular power cycle is precalculated based on values of pertaining influence factors detected in a preceding power cycle, to determine an actual burn-through function value of the particular power cycle in real time. The desired burn-through function is compared with the actual burn-through function and actualized values for the burn-through function influence factors are determined. These factors are used to determine the control variable values for a subsequent power cycle.

Abstract: A system for controlling operation of engine fuel injectors that includes a feed-forward control unit responsive to signals from sensors on the engine for supplying a basic electronic control signal for the injectors. A neural network is connected in parallel with the feed-forward control unit for receiving the sensor signals and multiplying the sensor signals by associated weighting factors. The sensor signals multiplied by the weighting factors are combined to produce a network output signal, which in turn is combined with the basic control signal from the feed-forward control unit to control operation of the fuel injectors. The weighting factors in the neural network are modified as a function of inputs from the engine sensors so as to reduce any errors in the sensor output signals as compared with desired values.