KR100251918B1 - Transmission control system and the control method - Google Patents

Abstract

PURPOSE: A shift gear control system and a control method therefor are provided to make input variable of plural sensors as two output values by delta rule generalized with error reducing method and to improve reliability of shift gear control by outputting and comparing purpose of a driver with inferential value of fuzzy logic. CONSTITUTION: A shift lever control system of an automatic transmission includes an input unit, a transmission control unit(3) and an output unit(5). A method for controlling the shift lever control system comprises a first process inputting a fuzzy data the same as a shift gear of a present transmission, vehicle speed and open voltage changed amount of a throttle valve to calculate a travelling condition; a second process inputting a neural data as a load degree of an engine, braking force and cornering degree to calculate a travelling condition; a third process inputting acceleration and deceleration data as control of brake and acceleration switches; a forth process outputting travel mode digitizing the fuzzy data as fuzzy membership function and then, detecting up-hill and down-hill with the neural data; and a fifth process deciding whether the neural output value is over an established value to operate selected mode.

Description

Shift stage control system and automatic control method for vehicle automatic transmission {TRANSMISSION CONTROL SYSTEM AND THE CONTROL METHOD}

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a shift stage control system and a control method of an automatic transmission for a vehicle. More particularly, the present invention relates to two output values using a delta rule generalized by an error reduction method. The present invention relates to a shift stage control system and a control method of an automatic transmission for a vehicle that can improve the reliability of the automatic transmission shift stage control by outputting the driver's will and the inference value of the fuzzy logic.

In general, an automatic transmission is a multi-speed gear mechanism that changes and transmits a rotational force transmitted to an input shaft to a drive shaft. The automatic transmission includes a planetary gear set and a hydraulic control system for controlling a hydraulically operated friction element determined by the planetary gear set.

For example, the planetary gear set includes a double pinion planetary gear and a single pinion planetary gear. The planetary gear set is configured to transmit a shifted rotational force to an output element using one element as an input element and another element as a reaction force element. Certain elements in the set are actuated by hydraulically actuated friction elements to determine each of these elements as input, reaction and output elements.

The hydraulically actuated friction element is actuated or deactivated by the hydraulic pressure supplied or discharged in the hydraulic control system and consists of a plurality of clutches and brakes.

The automatic transmission is shifted by operating or deactivating the clutch and the brake, and the shift stage is determined by the state of the vehicle and the driver's operation to drive the vehicle.

Accordingly, in order to control the shift stage of the automatic transmission, the output value is protruded using a neural network as one output layer using four input layers and five intermediate layers, and the engine brake is used as the output value. After determining the goodness of fit, it is input to the fuzzy logic to act as a decisive factor in shift control.

However, in the related art, the driver's satisfaction with the driver's intention is not reflected, and a shift which does not match the driver's intention may occur, thereby reducing the reliability of each driver.

Accordingly, an object of the present invention is to solve such a problem in the related art, and an object of the present invention is to determine the driver's will and the fuzzy logic by using the delta rule generalized by the error reduction method as an input variable from a plurality of sensors. The present invention relates to a shift stage control system for an automatic transmission for a vehicle and a method of controlling the same so as to improve the reliability of the automatic transmission shift stage control by outputting the result in comparison with the inference value.

In order to achieve the above object, the present invention provides information about the opening amount of the throttle valve, information about the speed of the vehicle, information about the current shift stage, information about the load degree generated in the vehicle, deceleration of the vehicle Alternatively, the input unit includes a plurality of sensors for outputting information on speed increase and cornering of the vehicle, and calculates a driving state by receiving an output value output from the input unit, and calculates a fuzzy mode. A transmission stage control system for an automatic transmission for a vehicle comprising a transmission control unit which performs a comparison operation and compares and judges this purge mode, and an output unit which controls the automatic transmission according to a mode calculated from the transmission control unit.

In addition, the present invention provides an input step of inputting fuzzy data for calculating driving conditions, neural data for calculating driving conditions, acceleration and deceleration data for a driver's learning module, and driving mode and neural with data input from the input step. A calculation step of calculating an output value, a determination step of comparing and determining the neural output value calculated in this calculation step with a set value set by the driving mode, and a transition step of controlling the automatic transmission by the mode determined in the determination step. Provided is a control method of a shift stage control system of an automatic transmission for a vehicle.

1 is a block diagram showing a shift stage control system for an automatic transmission for a vehicle according to the present invention.

2 is a flowchart illustrating a control method of a shift stage control system of an automatic transmission for a vehicle according to the present invention.

<Description of the symbols for the main parts of the drawings>

1 input unit 3 transmission control unit

5: output unit 7: driver learning module

9: neural control unit 11: fuzzy control unit

Exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings.

1 is a configuration diagram showing a shift stage control system of an automatic transmission for a vehicle according to the present embodiment, and the control system is configured to shift control according to a driver's intention and driving tendency of a best drive using neural control and fuzzy control.

The control system is a multi-stage gearing mechanism that changes and transmits the rotational force transmitted to the input shaft to the drive shaft. In the hydraulic control system for controlling the planetary gear set and the hydraulically actuated friction element determined by the planetary gear set, the throttle valve Outputting information about the opening amount of the vehicle, information about the speed of the vehicle, information about the current gear stage, information about the load degree generated in the vehicle, information about the deceleration or increase of the vehicle, information about the cornering of the vehicle Receives an input unit 1 composed of a plurality of sensors and an output value outputted from the input unit 1, calculates a driving situation, calculates a fuzzy mode, and compares and calculates driving conditions and information on acceleration and deceleration, and compares with this fuzzy mode. By the transmission control unit 3 and the mode calculated from this transmission control unit An output unit 5 that is to control the automatic transmission.

Although not shown, the input unit 1 includes a throttle position sensor for detecting an opening amount of a throttle valve, a vehicle speed sensor for detecting a speed of a vehicle, an air flow sensor for detecting a mass of air supplied to a cylinder, and left and right sides of a wheel It consists of a wheel speed sensor installed at each of the brakes, a brake switch for detecting brake operation, and an Excel switch for automatically detecting an accelerator pedal.

From the throttle position sensor, the opening amount and the change amount of the throttle valve are calculated, the current vehicle speed is calculated from the vehicle speed sensor, and the filling efficiency of the engine is calculated from the air flow sensor. The torque of the shaft is calculated, and the load and full load of the engine are calculated, and the degree of cornering generated by the steering of the driver is calculated from two or more wheel speed sensors. Is used to determine the driver's intention.

On the other hand, the transmission control unit outputs a signal from the driver learning module 7 when the brake pedal or accelerator pedal which senses the driver's deceleration or acceleration intention is pressed, and the engine load degree, full load degree, and vehicle acceleration The delta rule generalized by the loss function error reduction method through the five input layers of cornering calculated using the calculated brake force, the current vehicle speed, and the left and right speed of the wheel, and the seven intermediate layers based on this input side. The neural control unit 9, which is calculated as two output layers, compares the signals output from the driver learning module unit 7, and the information on the throttle opening amount, the throttle opening degree change amount, the current vehicle speed, and the current shift stage is provided. A fuzzy membership function calculated based on data on driving conditions to determine this driving mode by calculating this information. The control unit 11 has a structure in which the output values of the neural control unit 9 are compared and judged.

2 is a flowchart illustrating a control method of the present embodiment, in which the control method of the present embodiment inputs fuzzy data for calculating driving conditions, neural data for calculating driving conditions, and acceleration and deceleration data for a driver's learning module. In the input step, the calculation step of calculating the driving mode and the neural output value from the data input from the input step, the judgment step of comparing and judging the neural output value calculated in this calculation step with the set value set by the driving mode, and in the determination step The determined mode is roughly divided into transition stages that control the automatic transmission.

In order to calculate the driving situation, fuzzy data such as the amount of opening of the throttle valve, the amount of change in the opening of the throttle valve, the speed of the vehicle, and the data of the shift stage of the current transmission are input (S10).

In order to calculate the driving situation, neural data such as data on the load of the engine, the full load of the engine, the braking force, the speed of the vehicle, and the cornering degree are input (S20).

Then, in order to use the driver's intention included in the driving situation, acceleration and deceleration data such as an interruption of the brake switch or the accelerator switch are input (S30).

The driving mode that receives the fuzzy data and digitizes the fuzzy membership function is calculated (S40).

The neural data is received to calculate the uphill and downhill using the delta rule of the loss function error reduction method (S50).

Thus, in order to implement the modes determined in the above-described steps (S40, S50), it is determined whether the neural output value is equal to or larger than a set value set by the driving mode (S60).

When the step S60 is satisfied, the automatic transmission is controlled by the driving mode determined by the fuzzy controller, and when the step S60 is not satisfied, the system is recalculated to determine again.

As described above, the present invention outputs the input variables from a plurality of sensors as two output values using the delta rule generalized by the error reduction method and compares them with the inference value of the driver's will and fuzzy logic. It works according to the will and many driving situations, and has the advantage of improving reliability.

It is apparent to those skilled in the art that the present invention is not limited to the described embodiments, and that various modifications and changes can be made without departing from the spirit and scope of the present invention. Therefore, such modifications or variations will have to belong to the claims of the present invention.

Claims (5)

Information about the opening amount of the throttle valve, information about the speed of the vehicle, information about the current shift stage, information about the load level generated by the vehicle, information about the deceleration or increase of the vehicle, and information about the cornering of the vehicle. An input unit comprising a plurality of sensors for outputting; The driver receives the output value output from this input unit, calculates the driving condition, calculates the fuzzy mode, and compares the driving condition with the information about acceleration and deceleration and compares the fuzzy mode with the driver to press the brake pedal or the accelerator pedal after the mode transition. Driver's learning module to output the power, the engine's load and full load, the braking force calculated by calculating the acceleration of the vehicle, the current vehicle's speed, and the cornering calculated by using the left and right speed of the wheel, and this input. It is calculated as two output layers by the delta rule generalized by the loss function error reduction method through seven intermediate floors based on the floors, and the neural control unit comparing with the driver learning module unit, the throttle opening amount, the throttle opening degree change amount, Based on data on driving conditions based on speed and current speed A transmission control unit including a fuzzy control unit which calculates the driving mode by calculating the information with the calculated fuzzy membership function and compares the driving mode with an output value of the neural control unit; And And an output unit configured to control the automatic transmission in accordance with the mode calculated from the transmission control unit. An input step of inputting fuzzy data for calculating driving conditions, neural data for calculating driving conditions, acceleration and deceleration data for the driver's learning module, An operation step of calculating the driving mode and the neural output value from the data input from the input step; A judgment step of judging and comparing the neural output value calculated in this calculation step with a set value set by the driving mode, And a transition step of controlling the automatic transmission in accordance with the mode determined in the determining step. The method of claim 2, wherein the input step comprises: a fuzzy data input step of inputting data on an opening amount of a throttle valve, an opening degree change amount of a throttle valve, a vehicle speed, and a shift stage of a current transmission; A neural data input step of inputting data on an engine load diagram, an engine full load, a brake force, a vehicle speed, and a cornering degree, And an acceleration and deceleration data input step of inputting an interruption of a brake switch or an accelerator switch, and a control method of the vehicle automatic transmission. The method of claim 2, wherein the calculating comprises calculating the driving mode using the fuzzy data as a fuzzy membership function. And calculating the up-hill and down-hill from the neural data by using a delta rule of the loss function error reduction method of the automatic transmission shift control system of the vehicle. Control method. 3. The shift stage control system of an automatic transmission for a vehicle according to claim 2, wherein the determination step includes determining whether the neural output value is equal to or larger than a set value set by the driving mode in order to perform the mode determined in the calculation step. Way.

Images