Abstract: The shift control method of an automatic transmission calculates a shift-pattern-adjusting coefficient using a modular neural network. The shift-pattern adjusting coefficient is based on a plurality of input signals input from a plurality of detectors. It is then determined if shifting is required based on an adjusted shift-pattern. The adjusted shift-pattern being adjusted based on the shift-pattern adjusting coefficient. A target shift-speed when shifting is required is calculated based on the adjusted shift-pattern. Finally, a shifting signal for shifting to the target shift-speed is generated.

Abstract: The present invention aims to enable the accurate learning of a true torque point in a wet friction clutch (3), prevent the clutch connection shock by absorbing the response delay upon an ordinary clutch connection control, and to successfully combine the time lag and shock. In the present invention, the value (D) itself of the duty ratio of the duty pulse output from the ECU (16) is learned as the torque point (Dm). In a power transmission device of a vehicle having a fluid coupling (2) and the wet friction clutch (3)provided in series between the engine (E) and transmission (T/M), the value (Dm) of the duty ratio at the time when the clutch input side revolution (Nt) decreases to a value lower than the engine revolution (Ne) by a prescribed revolution (Nm) during the process of gradually connecting the clutch 3 is learned as the torque point. Preferably, learning is conducted after the elapse of a prescribed waiting time (&Dgr;t1).

Abstract: An assembly 10 which allows a vehicular damper to be virtually created and evaluated. Particularly, the assembly 10 includes a torque producer 31, a frequency filter generator 50, and analyzers32, 34, 36 and 38. The torque produce 31selectively produces a torque signal which is combined with a selected frequency filter provided by the generator 50, thereby producing a dampened signal which is communicated to a transmission assembly 14. The analyzer detects noise and vibration and allows a designer to evaluate the chosen frequency filter. Other filters may be used and a filter is selected based upon the noise and vibration measurements made by the analyzers 32, 34, 36, and 38. An actual damper is then constructed having a frequency characteristic which is substantially similar to the frequency characteristic of the chosen frequency filter.

Abstract: The invention includes an adaptive control system used to control a plant. The adaptive control system includes a hedge unit that receives at least one control signal and a plant state signal. The hedge unit generates a hedge signal based on the control signal, the plant state signal, and a hedge model including a first model having one or more characteristics to which the adaptive control system is not to adapt, and a second model not having the characteristic(s) to which the adaptive control system is not to adapt. The hedge signal is used in the adaptive control system to remove the effect of the characteristic from a signal supplied to an adaptation law unit of the adaptive control system so that the adaptive control system does not adapt to the characteristic in controlling the plant.

Abstract: Estimated change in operating fluid volume within a primary fluid chamber over a predetermined period of time during gear change operation is calculated using a physical model. On the other hand, detected change in operating fluid volume within the primary fluid chamber over this predetermined period of time is calculated. Then the deviation of the detected change from the estimated change is calculated, and learning and correction of the difference between the characteristic stored in an electronic control unit and that of an actual flow control unit are performed based on this deviation.

Abstract: A method for controlling a powertrain of a vehicle is described. The method determines a desired vehicle condition based on three driver actuated elements. In a preferred embodiment the first element can be pedal position, the second element can be a brake actuator or, more specifically, brake actuation duration, and the third element can be a gear selection lever. Further, the desired vehicle condition can be desired powertrain output, vehicle acceleration, or various other parameters.

Abstract: A shift control apparatus comprises clutches driven by shift solenoids and whether or not the raising of the rotation speed occurs in an internal combustion engine is determined. If the raising of the engine rotation speed is detected, a hydraulic pressure learn correction is made to engagement hydraulic pressure and a time learn correction is made to the hydraulic pressure supply preparation time. The correction ratio of the energization-hydraulic pressure characteristic (I-P characteristic) of clutch clearance and the shift solenoid is set so as to become an appropriate distribution ratio and the learning is started based thereon.

Abstract: A system and method of optimizing fuel economy for an automobile is provided. Driver torque request input data is received and is accumulated over a period of time to generate accumulated torque request data. Torque data is extracted from the accumulated torque request data. The torque data is processed to generate driver habit data from the torque data. The driver habit data is stored and used to optimize fuel economy.

Abstract: A method including providing force and acceleration sensors in a vehicle-enclosing device; transmitting data produced by the sensors during actual operation of the vehicle-enclosing device attached to a specific vehicle for subsequent analysis by a computer; and creating a force-and-acceleration map based on the sensor-based data.

Abstract: When a contradictory event in which raising of the engine rotation speed is detected and the inertia phase start time is early occurs (8), a learn correction is made to engagement hydraulic pressure (ON side). If the raising of the engine rotation speed cannot be canceled still after the learn correction is made, release hydraulic pressure (OFF side) is increased for correction.

Abstract: The present invention aims to enable the accurate learning of a true torque point in a wet friction clutch (3), prevent the clutch connection shock by absorbing the response delay upon an ordinary clutch connection control, and to successfully combine the time lag and shock. In the present invention, the value (D) itself of the duty ratio of the duty pulse output from the ECU (16) is learned as the torque point (Dm). In a power transmission device of a vehicle having a fluid coupling (2) and the wet friction clutch (3)provided in series between the engine (E) and transmission (T/M), the value (Dm) of the duty ratio at the time when the clutch input side revolution (Nt) decreases to a value lower than the engine revolution (Ne) by a prescribed revolution (Nm) during the process of gradually connecting the clutch 3 is learned as the torque point. Preferably, learning is conducted after the elapse of a prescribed waiting time (&Dgr;t1).

Abstract: A CVT control method includes the steps of calculating a target speed ratio of a CVT between maximum and minimum values of a plurality of speed ratios preset corresponding to a plurality of engine operation modes, and controlling the CVT according to the target speed ratio.

Abstract: A vehicle transmission (302) is equipped with an actuator (303) for shifting the transmission (302). A controller (306) causes the actuator (303) to shift the transmission (302) based on movement of a shift lever (308). A learning unit (306) memorizes a gear position of when a vehicle is stopped, a brake pedal is stamped, an accelerator pedal (307) is not stamped, and a certain transmission gear is selected, as a start gear. The vehicle moves from that start gear and stops. When the vehicle is restarted, the learning unit (306) selects the memorized start gear and the controller causes the actuator (303) to shift the transmission to that start gear. The learning unit (306) separately memorizes the gear position of when the vehicle tows another vehicle and the gear position of when the vehicle does not tow any vehicle.

Abstract: A method is described for controlling a powertrain of a vehicle. In particular, the method attempts to minimize transmission gear separation, or “clunk”. Under some circumstances, it is determined whether torque converter output speed has become greater than torque converter input speed while the torque converter was unlocked. Such a situation represents a change from positive powertrain output to negative powertrain output. If such a situation has occurred, under certain circumstances, the torque converter is then locked.

Abstract: An improved method for estimating an input torque to the continuously variable transmission (CVT) is presented. The method includes calculating torque adaptation coefficients when the torque converter clutch is unlocked, and an accurate torque value can be obtained based on the torque converter characteristics. The adaptation coefficients are then used to correct the transmission torque estimate, which is then used to determine proper CVT clamping forces. This method improves fuel economy, transmission durability, and customer satisfaction.

Abstract: Within the scope of the method for including the temperature in the calculation of the definite, operating-point dependent maximum and minimum adjustment speeds in a continuously variable belt-drive transmission, the actual limiting values for the maximum possible adjustment gradient are continuously calculated in every operating state by a physical-mathematical pattern wherein the hydraulic routes of the variator, the clutches integrated in the transmission and the lubrication are modeled as laminar inserts and the route of the control unit leakage as coupled laminar and turbulent hydraulic transmission elements.

Abstract: A method, system and computer-readable medium for controlling a control subsystem of a vehicle. The control subsystem includes at least one propulsion, aerodynamic, or other control effector. The system also includes sensors for sensing vehicle position and motions and operating conditions, a control input device for generating control signals, and a generator for generating desired vehicle forces/moments from the sensed vehicle position and motions and operating conditions, and the generated control input signals based on predefined vehicle compensation and control laws. Also included is a neural network controller for generating control subsystem commands for the at least one propulsion, aerodynamic, or other control effector based on the generated desired forces/moments, wherein said neural network controller was trained based on pregenerated vehicle control distribution data. The neural network controller is also trained to compensate for one or more failed control effectors.

Abstract: A vehicle transmission (302) is equipped with an actuator (303) for shifting the transmission (302). A controller (306) causes the actuator (303) to shift the transmission (302) based on movement of a shift lever (308). A learning unit (306) memorizes a gear position of when a vehicle is stopped, a brake pedal is stamped, an accelerator pedal (307) is not stamped, and a certain transmission gear is selected, as a start gear. The vehicle moves from that start gear and stops. When the vehicle is restarted, the learning unit (306) selects the memorized start gear and the controller causes the actuator (303) to shift the transmission to that start gear. The learning unit (306) separately memorizes the gear position of when the vehicle tows another vehicle and the gear position of when the vehicle does not tow any vehicle.

Abstract: A method is disclosed for computer-based control of the timing and level of gear shifts in a multi-speed automatic transmission operated in combination with an internal combustion engine and interposed fluid torque converter. The computer containing power control module signals gear shifts in response to its repeated cyclic processing of engine and transmission operation parameters including torque converter slippage. Here, such slippage is estimated using a neural network with suitable such parameters as input data. In preferred modes of operation, different neural networks are available for selection and use by the computer in different modes of engine-transmission operation.

Abstract: A learning controller makes learning correction based on a time tST between start of a shift control routine and detection of start of a change in rotational speed of the transmission input shaft and further based on the amount of rotational speed change &ohgr;S′ at the detected start of the rotational speed change. When the time tST is longer than a basic time and when the rotational change amount &ohgr;S′ is too large, it is determined that a servo piston has not been sufficiently advanced and the shift control is corrected so that the time tST is lengthened. When the time tST to the detected start of the rotational speed change &ohgr;S′ is too small, it is determined that, while the piston has been advanced properly, the target engagement pressure PTA in torque phase control is too low because of a miscalculation, and the shift control is corrected so that the target engagement pressure is raised.

Abstract: The system includes a memory in which curves are stored which define the conditions for each gear change, corresponding to at least two reference styles of driving, sensors for operating parameters of the motor vehicle, and second processing devices set up to estimate the value of a first index which identifies the kind of driving of the motor vehicle and, respectively, the value of a second index which defines the manner or style of driving of the driver, and a processing and control unit.

Abstract: A simplified method and system for determining a loading condition on a powertrain of a machine resulting from a loading condition on an implement thereof. The method includes the steps of inputting a predetermined plurality of parameter signals representative of the loading condition on the implement into an implement loading model to determine a plurality of implement loading modeled values as a function of the inputted loading parameter signals and inputting the implement loading modeled values into a kinematic linkage model to determine a plurality of modeled linkage loading values as a function of the inputted implement loading modeled values and a plurality of known linkage parameter values and inputting the modeled linkage loading values into a machine powertrain loading model to determine a plurality of powertrain loading modeled values indicative of the loading condition on the powertrain.

Abstract: A method and system for controlling a propulsion system of a vehicle. The propulsion system includes at least one propulsion effector. The system also includes sensors for sensing vehicle position and motions, a control device for generating control signals, and a generator for generating desired vehicle forces/moments from the sensed vehicle position and motions and the generated control signals based on predefined vehicle compensation and control laws. Also included is a neural network controller for generating propulsion commands for the at least one propulsion effector based on the generated desire forces/moments, wherein said neural network controller was trained based on pregenerated vehicle control distribution data.

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 apparatus for controlling the pressure of a hydraulically operated frictional coupling device which is released or engaged to achieve a shifting action of an automatic transmission, by first rapidly reducing or increasing the pressure to a predetermined level, holding the pressure at this level for a predetermined time and then continuously reducing or increasing the pressure to complete the shifting action, wherein a learning compensation device is provided to update, by learning compensation, a selected control parameter influencing a pattern of change of the pressure of the coupling device during the shifting action such that the shifting action is achieved in a predetermined manner.

Abstract: An apparatus for deciding a shift pattern suitable for a driver's habit using a neural network operation and fuzzy inference and a control method thereof which perform a neural network operation by inputting a driver's driving operation quantity as a deciding condition of a shift pattern, and decide an optimal shift pattern by performing fuzzy inference from the output from the a neural network operation.

Abstract: A gear shifting system for a human-powered chain- or belt-driven vehicle includes a wheel speed sensor, a cadence sensor, a gear changer position sensor, a tension sensor, a clinometer, a controller and a gear changer actuator. The wheel speed sensor senses a speed of a wheel, while the cadence sensor senses a drive rate that a torque drive member drives a torque-transmitting member. The gear changer position sensor senses a position of a gear changer that positions the torque-transmitting member with respect to a plurality of gears. The tension sensor senses a tension of the torque-transmitting member that is transmitting a torque applied to the torque-transmitting drive member to a gear. The clinometer senses an inclination of the vehicle. The controller generates a control signal based on the sensed wheel speed, the sensed torque-member drive rate, the sensed torque-transmitting member tension, the sensed vehicle inclination and the sensed gear changer position.

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 intersection information supply apparatus includes a table indicating relationships between approaching directions of a vehicle to an intersection and signal forms, an approaching direction detecting unit detecting an approaching direction in which the vehicle is approaching the intersection, a transmission unit transmitting a signal having a signal form indicated in the table so as to correspond to the approaching direction detected by the approaching direction detecting unit, a signal obtaining unit selectively obtaining, from among signals externally arriving at the vehicle, a signal having a signal form indicated in the table so as to correspond to an approaching direction relevant to the approaching direction detected by the approaching direction detecting unit and an information output unit outputting information about presence of another vehicle when the signal obtaining unit obtains the signal.

Abstract: An automatic load measuring device includes an actual load calculating device. The actual load calculating device includes a multi-layer feed-forward type neural network having an input layer, an intermediate layer and an output layer arranged in a hierarchial manner. Also, the actual load calculating device, by use of the multi-layer feed-forward type neural network, can previously execute learning relating to the correction of a carrying load of a vehicle to be measured by automatic load measuring sensors respectively used to measure the carrying loads of the vehicle using measured load information measured by the automatic load measuring sensors, and, based on the result of the learning, can correct the carrying loads measured by the automatic load measuring sensors so as to find the actual load of the vehicle.

Abstract: A self-organizing fuzzy logic controller develops an adaptive pressure adder that modifies the magnitude of pressure supplied to a friction element of an automatic transmission. The controller uses a turbine speed versus engine torque table in KAM to store the adaptive pressure adder for each shift. Tables in KAM represent fuzzy rules which are altered based on shift performance criteria to produce a self-organizing fuzzy logic controller. The criteria, which define shift performance, include the ratio change slip time and torque converter turbine speed flare. The desired slip time is determined from a calibratable matrix. After a shifting event, an adaptive pressure adjustment is determined for the next shifting event of the same types. A two-input (slip time and turbine speed flare) fuzzy logic controller is used to determine the pressure adjustment. The adaptive pressure adjustment from the fuzzy controller is then increased if stage time is greater than a calibratable value.

Abstract: Apparatus for controlling a vehicle hybrid drive system having a transmission disposed between a vehicle drive wheel and an assembly of an engine and a motor/generator, the apparatus including a torque reduction control device for reducing an input torque of the transmission during a shifting action of the transmission, wherein the torque reduction control device includes a first torque reducing device for reducing the input torque by controlling the engine, a second torque reducing device for reducing the input torque by controlling the motor/generator, and a torque reduction mode selecting device for enabling the first torque reducing device and/or the second torque reducing device to operate to reduce the input torque, according to a predetermined selecting condition.

Abstract: A control architecture having improved fault detection and correction capabilities is disclosed. The system comprises primary and monitor control systems, each having an associated control signal. A fault detector generates an alarm signal based upon differences observed between the primary and monitor control signal. The detector comprises an integrator and a memory means, and alarm signals are generated based upon the total amount of difference observed over a predetermined period of time. In one embodiment of the invention, primary and monitor control signals are averaged to provide a signal that is more fault tolerant than the individual control signals.

Abstract: A method and apparatus for analysing a sample, in which a neural network is trained to correct for measurement drift of a given analytical instrument (e.g., a mass spectrometer). The training is carried out using first and second sets of data obtained by the instrument from samples of known compositions at initial and subsequent instants of time, respectively. The trained neural network is used to transform data, obtained by the instrument from a sample of unknown composition at said subsequent instant of time, to an estimate of the data which would have been obtained by the instrument from that sample at the initial instant of time. The transformed dasta is then analysed to analyse the sample of unknown composition.

Abstract: An automatic transmission control system is equipped with a pressure modulating valve for regulating the engaging pressure to be supplied to frictional engagement elements for setting respective gear stages of the automatic transmission, a signal pressure output valve for providing signal pressure, and a switching valve.

Abstract: Transmission output speed and engine throttle position are inputs to a control which determines acceleration and input speed. Fuzzy logic has acceleration and throttle membership functions and a set of upshift and downshift values, and rules for weighting each of the values in accordance with the degree of membership of acceleration and throttle position in certain of the functions to determine a downshift point and an upshift point. The input speed is compared to the shift points to decide whether to order a shift. Two or more sets of shift values are stored and are selectable for different performance options. The shift values are stated in terms of a percentage of engine governed speed to allow different engines to be coupled to the transmission. Lockup clutch apply and release logic controls converter lockup to maintain converter mode when significant torque multiplication is occurring and generally to maintain lockup mode when the transmission range is at or above the lowest allowable lockup range.

Abstract: Apparatus and method for estimating an attribute associated with a mobile machine. The machine has an engine and a powertrain. The powertrain includes a torque converter coupled to the engine. The apparatus and method sense a plurality of parameters of the machine and responsively produce a plurality of respective parameter signals and calculating an estimated value of the attribute as a function of the parameter signals using a computer based model. The apparatus and method further calculates first and second estimated values of a torque converter input torque, compares the first and second torque converter input torque estimate signals and responsively calibrates the computer based model.

Abstract: Apparatus for estimating a drive mode of a motor vehicle desired by an operator of the motor vehicle, including a variable calculating device and a drive mode estimating device, wherein the variable calculating device calculates at least one of drive mode indicating variables such as a drive force of the vehicle desired by the operator upon starting of the vehicle, a maximum rate of increase of the drive force, a maximum deceleration of the vehicle upon operation of a manually operated member for brake application to the vehicle, a coasting run time of the vehicle and a steady run time of the vehicle, and wherein the drive mode estimating device includes a neural network which receives the drive mode indicating variable or variables calculated by the variable calculating device, so that the drive mode estimating device estimates the drive mode of the motor vehicle desired by the operator on the basis of an output of the neural network.

Abstract: A method and system for controlling shift in an automatic transmission that can establish a plurality of gear ratios by selectively supplying a hydraulic pressure for a plurality of frictional engaging elements.

Abstract: The hydroplaning-occurring speed of a vehicle is estimated by detecting an amount of water on a wet road surface on which the vehicle is traveling, and estimating a speed of the vehicle at and above which a hydroplaning phenomenon can occur, based on the detected amount of water. The possibility of occurrence of a hydroplaning phenomenon of a vehicle is detected by detecting an amount of water on a wet road surface on which the vehicle is traveling, detecting the speed of the vehicle, and determining whether there is a possibility that a hydroplaning phenomenon can occur, based on the detected amount of water and the detected speed of the vehicle.