JPH09137860A - Shift control device for automatic transmission for vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To favorably control both the up-shift and the down-shift according to the feeling of a driver by facilitating the operation without any troublesome constitution. SOLUTION: A shift control device is provided with the manual mode to switch the shift position by the operation of a driver and the automatic mode to automatically switch the shift position according to the operational condition of a vehicle. In addition, the shift control device is also provided with a learning means (S19) to learn the shift pattern reflecting the taste for the shift of the driver by the neural network with the shift condition at least in either of the manual mode and the automatic mode as the parameter, a target shift position setting means (S22) to set the target shift based on the output from the learning means and the operational condition of the vehicle in the automatic mode, and shift control means (S24, S30) to control the shift of an automatic transmission based on the target shift position.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a shift control device for an automatic transmission for a vehicle, and more particularly to a shift control device for an automatic transmission having a manual mode and an automatic mode.

[0002]

2. Description of the Related Art Conventionally, as a vehicle transmission, an automatic transmission in which a shift operation is automated has been frequently used. In the case of small vehicles, the mainstream of this automatic transmission employs a torque converter instead of the clutch. On the other hand, in large vehicles such as buses and trucks, transmission of drive torque is performed. Since the amount is large, it is difficult for the torque converter to sufficiently transmit the driving torque.

Therefore, in a mechanical transmission similar to a manual transmission, an automatic transmission having a structure in which an actuator for automatically connecting / disconnecting a clutch is provided and thereby the clutch pedal is discharged is developed for a large vehicle. Has been done. Normally, in such a shift control device for a mechanical automatic transmission, the target shift speed is set according to the vehicle speed and the accelerator opening. However, in many cases, the intention of the driver is not sufficiently reflected in this target shift speed. Therefore, in this case, there is a possibility that a gearshift contrary to the driver's will is performed.

From the above, fuzzy inference is performed on the basis of information such as road inclination, vehicle speed, accelerator opening, and brake operating condition, and the shift characteristics of the shift map are switched according to the obtained fuzzy rules. Accordingly, a shift control device configured to shift gears by reflecting the driver's intention is disclosed in JP-A-1-255748, JP-A-2-3738, and the like.

[0005]

As described above, in the shift control device for an automatic transmission disclosed in the above publications or the like, the shift is reflected in accordance with the driver's intention. It is not the basis for shifting gears according to driver preferences. That is, in the case of a manual transmission, the timing of gear shifting operation is usually slightly different for each driver, but in the above automatic transmission, the gear shifting timing is set to a predetermined timing regardless of the driver's preference. Therefore, some drivers feel uncomfortable.

Therefore, in recent years, an automatic transmission has been developed which is mainly adapted to automatic shifting, but which is also capable of manual shifting according to the driver's preference. Furthermore, an automatic transmission has been developed in which the driver's preference is learned and stored based on the content of the manual shift, and the stored value can be applied during the automatic shift. By the way, in order to favorably reflect the driver's preference in gear shifting, many input parameters are required, and learning of both upshifts and downshifts is required. Therefore, the calculation during learning may be enormous and complicated, which is not preferable.

The present invention has been made based on the above-mentioned circumstances, and its object is to easily perform both upshifting and downshifting according to the driver's preference without making a complicated structure. (EN) Provided is a controllable shift control device for an automatic transmission for a vehicle.

[0008]

In order to achieve the above-mentioned object, the invention of claim 1 is connected to an engine and is automatically operated in response to a manual mode in which a gear is switched by a driver's operation and a driving state of a vehicle. In a shift control device for an automatic transmission for a vehicle having an automatic mode in which gears are automatically switched, a driver's shift preference is reflected by a neural network using a shift state in at least one of the manual mode and the automatic mode as a parameter. Learning means for learning a shift pattern, target shift speed setting means for setting a target shift speed based on the output from the learning means and the operating state of the vehicle in the auto mode, and the automatic transmission based on the target shift speed And a gear shift control means for performing the gear shift control.

Accordingly, the shift state in at least one of the manual mode and the automatic mode is used as a parameter, and the shift pattern learning reflecting the shift preference of the driver is performed by the neural network. The output by this learning and the vehicle in the automatic mode are learned. The target shift speed is set based on the operating state. Then, the shift control of the automatic transmission is satisfactorily performed based on this target shift speed.

Further, in the invention of claim 2, the learning means selects one of the manual mode and the automatic mode in accordance with the frequency of shift operation by the driver in the manual mode. It is characterized by setting it as a parameter. Therefore, according to the frequency of the shift operation by the driver in the manual mode, the shift state of one of the manual mode and the automatic mode is used as a parameter, and the shift pattern learning is favorably performed.

Further, according to the invention of claim 3, the learning means uses the shift state in the manual mode as a parameter when the frequency of the shift operation by the driver in the manual mode is larger than a predetermined value. . Therefore, when the frequency of the shift operation by the driver in the manual mode is higher than the predetermined value, the shift state in the manual mode is used as a parameter, and the shift pattern learning is performed well.

[0012] According to a fourth aspect of the present invention, an engine speed detecting means for detecting an engine speed of the engine is further provided, and the learning means is set as a speed change state in the manual mode at least when a driver performs a speed change operation. The shift pattern learning is performed using the engine speed as a parameter. Therefore, at least the engine speed at the time of the shift operation of the driver is used as a parameter as the shift state in the manual mode, and the shift pattern learning is satisfactorily performed.

Further, in the invention of claim 5, the learning means uses the shift state in the automatic mode as a parameter when the frequency of the shift operation by the driver in the manual mode is smaller than a predetermined value. . Therefore, when the frequency of the shift operation by the driver in the manual mode is smaller than the predetermined value, the shift state in the automatic mode is used as a parameter, and the shift pattern learning is satisfactorily performed.

Further, according to the invention of claim 6, there is further provided an accelerator opening detecting means for detecting an accelerator opening of the engine, wherein the learning means is at least at the time of switching the shift speed as a shift state in the automatic mode. The shift pattern learning is performed using the accelerator opening as a parameter. Therefore, at least the accelerator opening at the time of switching the shift speed is used as a parameter as the shift state in the automatic mode, and the shift pattern learning is favorably performed.

Further, the invention according to claim 7 is characterized in that the learning means carries out the shift pattern learning by including the current shift pattern information in a parameter. Therefore, the current shift pattern information is used as the reference parameter for shift pattern learning, and the shift pattern learning is favorably performed. Further, in the invention of claim 8, the vehicle further comprises a flat road detecting means for detecting whether or not the vehicle is traveling on a flat road, and the learning means is configured to perform the shift pattern when the vehicle is traveling on the flat road. It is characterized by learning.

Therefore, the shift pattern learning is satisfactorily performed only when the vehicle is traveling on a flat road where the driver's preference is likely to appear. Further, in the invention of claim 9, the target shift speed setting means has a plurality of types of shift maps having different shift patterns, and selects an optimum map from the plurality of types of shift maps according to the output from the learning means. In addition, the target shift speed is set based on the optimum map and the operating state of the vehicle.

Therefore, the optimum map is selected from a plurality of types of shift maps according to the output from the learning means, and the target shift speed is set favorably based on this optimum map and the operating state of the vehicle. Further, according to the invention of claim 10, there is further provided a flat road detecting means for detecting whether or not the vehicle is traveling on a flat road, and the target shift speed setting means is provided when the vehicle is not traveling on the flat road. The target shift speed is set based on the shift map selected last time and the operating state of the vehicle.

Therefore, when the vehicle is not traveling on a flat road where the driver's preference is likely to appear, the target shift speed is favorably set based on the previously selected shift map and the operating state of the vehicle. Further, in the invention of claim 11, the learning means uses the neural network as a parameter for the shift state in at least one of the manual mode and the automatic mode to perform shift pattern learning reflecting the shift preference of the driver during upshifting. It is characterized by doing.

Therefore, the shift pattern learning reflecting the shift preference of the driver at the time of upshifting is favorably performed by the neural network using the shift state in at least one of the manual mode and the automatic mode as a parameter. Further, according to the invention of claim 12, it further comprises a vehicle speed detecting means for detecting a vehicle speed and a brake operating state detecting means for detecting an operating state of the brake, and the learning means has the brake operating state turned on and When the amount of decrease in the vehicle speed is equal to or more than a predetermined amount, the shift pattern learning reflecting the shift preference of the driver during downshifting is performed.

Therefore, when the brake operating state is on and the amount of decrease in vehicle speed is equal to or greater than the predetermined amount, the shift pattern learning reflecting the shift preference of the driver during downshifting is favorably performed. Further, in the invention of claim 13, the learning means uses the frequency of shift operation to the downshift side of the driver in the manual mode at least until the reduction amount of the vehicle speed reaches the predetermined amount as a parameter to perform the shift operation. It is characterized by performing pattern learning.

Therefore, the frequency of the shift operation to the downshift side by the driver in the manual mode at least until the reduction amount of the vehicle speed reaches the predetermined amount is used as a parameter, and the shift pattern learning is satisfactorily performed. Further, in the invention of claim 14, the learning means uses the frequency of mode switching from the auto mode to the manual mode by the driver at least until the decrease amount of the vehicle speed reaches the predetermined amount as a parameter. It is characterized by performing pattern learning.

Therefore, the frequency of mode switching from the automatic mode to the manual mode by the driver at least until the amount of decrease in vehicle speed reaches the predetermined amount is used as a parameter, and the shift pattern learning is performed well. Further, the invention according to claim 15 is characterized in that the shift control means includes fuzzy control means for correcting the target shift speed by using fuzzy inference based on vehicle information.

Therefore, the fuzzy inference is performed based on the vehicle information, the target shift speed is appropriately corrected according to the result of the fuzzy inference, and the favorable shift control is performed.

[0024]

BEST MODE FOR CARRYING OUT THE INVENTION A shift control device for an automatic transmission for a vehicle according to an embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a schematic block diagram showing the configuration of the main part, and FIG. 2 is a schematic configuration diagram showing the overall configuration. First, the overall configuration of the shift control device of the present invention will be described with reference to FIG.

As shown in FIG. 2, the shift control device of the present invention is a diesel engine (hereinafter referred to as an engine).
This is a system for automatically changing the rotational driving force of 11 using a gear type transmission (hereinafter referred to as a speed change mechanism) 17 having a clutch 15. Here, the speed change mechanism 17 has seven forward speeds in addition to the reverse speed, and not only automatic speed change but also manual speed change is possible.

The engine 11 is provided with a fuel injection pump (hereinafter referred to as an injection pump) 21 having a pump input shaft 19 that rotates at a speed half that of the engine output shaft 13, and this injection pump 21. An electromagnetic actuator 25 is connected to the control rack 23. A rack position detection sensor 123 for detecting the position of the control rack 23 is also provided. Further, the pump input shaft 19 is provided with an engine rotation sensor 27 for detecting a rotation speed signal of the output shaft 13 of the engine 11.

An exhaust pipe 12a for guiding exhaust gas through the exhaust manifold 12 extends from the engine 11, and an exhaust brake device 119 which is one of engine auxiliary brakes is interposed in the exhaust pipe 12a. .
The clutch 15 is provided with an air cylinder 33 as a clutch actuator. This clutch 15
Is a state in which the clutch plate 31 is pressed against the flywheel 29 by a well-known sandwiching means (not shown) to be in a connected state. That is, when the air cylinder 33 shifts from the non-actuated state to the actuated state, the holding means operates in the releasing direction, whereby the clutch 15 changes from the connected state to the disengaged state.

A clutch stroke sensor 35 is attached to the clutch 15 to detect disconnection and connection information based on the clutch stroke amount. A clutch touch sensor 37 may be used instead of the clutch stroke sensor 35. Transmission mechanism 1
A clutch rotation sensor 41 for detecting the rotation speed of the input shaft 39 is attached to the No. 7 input shaft 39.

By the way, an air passage 43 is connected to the air cylinder 33, and the air cylinder 33 is provided with a pair of air tanks 47 as an air source via a check valve 45.
It is connected to 49. In the middle of the air passage 43, solenoid valves X1 and X2 that are duty-controlled to supply operating air and function as opening and closing means, and solenoid valves Y1 and Y that are duty-controlled to open the air in the air cylinder 33 to the atmosphere.
2 is provided, and a three-way solenoid valve W is provided upstream of the solenoid valves X1 and X2.

As shown in the figure, the solenoid valves X1,
X2 are connected in parallel with each other and are normally closed. The solenoid valves Y1 and Y2 are also connected in parallel with each other and are normally open. When the air cylinder 33 is turned on, the solenoid valve W has an air tank 47,
The air passage 33 is controlled so as to connect the air passage 49 to the air passage. When the air cylinder 33 is off, the air passage is opened to the atmosphere.

Here, the solenoid valves X1 and X2 and the solenoid valves Y1 and Y2 are used alternately, so that the solenoid valves X1, X2, Y1 and Y2 can be used for a long period of time. Further, when one of the solenoid valves X1 and X2 fails, or when one of the solenoid valves Y1 and Y2 fails, the other solenoid valve is used. The reliability of the entire device is maintained.

Of the pair of air tanks 47, 49, the air tank 49 is an emergency tank, and if the main air tank 47 runs out of air for some reason, the solenoid valve 55 is opened to remove air from the emergency air tank 49. Supply. For this reason, air sensors 57 and 59 are attached to the air tanks 47 and 49, which output an ON signal when the internal air pressure falls below a specified value.

Further, the air passage 47 is provided in the air tank 47.
Is connected to an air passage branching into two systems on the downstream side, and the tip of this air passage is connected to a braking system (air over hydraulic type) via a pair of solenoid valves MVQ111, 111. A pair of air masters 109, 10
9 is connected. These air masters 109, 10
9 is a strong brake pedal force sensor (BPS sensor) 106.
Is installed. The BPS sensor 106 is configured as a diaphragm-type opening / closing switch that is turned on when receiving information on a strong brake pedal force corresponding to an air pressure when a strong braking force exceeding a set value is required.

The change lever 61 is a select lever of the speed change mechanism 17, and as shown in FIG. 3, can be moved in the select direction and a direction orthogonal to the select direction, and further can be moved in the orthogonal direction. The position can be moved in the shift direction parallel to the select direction. The select pattern and shift pattern in each of these directions are set to the N (neutral) range, the R (reverse) range, and the D (drive) range corresponding to the automatic shift mode (auto mode) in the select direction. In the shift direction, the change lever 6 moves from the D (drive) range to the orthogonal direction.
1 is set to the moved position, and the I-type shift pattern having the UP (shift up) position and the DOWN (shift down) position is set across the M (manual) range corresponding to the manual shift mode (manual mode). ing.

In such a select pattern and shift pattern, the change lever 61 located in the N range, R range, and D range is held in that position and stopped even if the driver's hand is released after the operation to that position. On the other hand, when the M range is selected and the shift operation is performed to the UP position or the DOWN position,
After the operation, when the driver's hand is released, the driver automatically returns to the M range and is held at that position (indicated by HOLD in FIG. 3). The detection of each range and position of the change lever 61 is performed by the gear shift stage selection switch 63, whereby the gear shift unit 65 is operated and the gears in the transmission mechanism 17 are switched according to the select range and shift position.

The gear shift unit 65 has a plurality of solenoid valves (only one is shown in FIG. 2) which are operated by an operation signal from a control unit 71 as a shift control means.
73, and a pair of power cylinders (not shown) for operating a select fork and a shift fork (both not shown) in the speed change mechanism 17. This power cylinder is provided with the above-mentioned air tank 47,
It operates when high-pressure operating air is supplied from 49. That is, each power cylinder is operated by the operation signal given to the solenoid valve 73, and the meshing state of the gear type speed change mechanism 17 is changed in the order of select and shift.

Further, the gear shift unit 65 is provided with a gear position switch 75 as a gear position sensor for detecting each shift stage, and a gear position signal from this gear position switch 75 is output to the control unit 71. Further, the output shaft 77 of the speed change mechanism 17 is provided with a vehicle speed sensor 79 for detecting a vehicle speed signal, and the accelerator pedal 81 is further provided with an accelerator opening for detecting the depression amount (accelerator opening VA) as engine load information. Degree sensor 8
5 are provided. This accelerator opening sensor 85
The resistance change corresponding to the depression amount of the accelerator pedal 81 is detected as a voltage value (VA), and this is converted into a digital signal by the A / D converter 83 and output. FIG. 4 shows a map showing the relationship between the accelerator opening and the voltage value (VA), and the accelerator opening VA is set based on this map.

A brake sensor 87, which outputs a high-level brake signal when the brake pedal 69 is depressed, is attached to the brake pedal 69. The engine 11 engages with the ring gear on the outer circumference of the flywheel 29 at appropriate times. A starter 89 for starting the is installed. The starter 89 is provided with a starter relay 91, and this starter relay 91 is connected to the control unit 71.

Reference numerals 120 and 121 in the figure respectively denote an exhaust brake device 11 which is an engine auxiliary brake.
9. Exhaust brake on / off switch (engine auxiliary brake operation detecting means) and engine brake auxiliary device for switching the engine brake auxiliary device, that is, the compression release type engine auxiliary brake device (not shown) between the operation standby state and the non-operation state On / off switches, which are arranged near the driver's seat.

Reference numeral 93 in FIG. 2 denotes an engine control unit provided separately from the control unit 71. Information from each sensor and the control unit 71 for the electronic governor 25 in the injection pump 21 are shown.
The drive control of the engine 11 is performed according to the accelerator opening information VA and the like from That is, in the electronic governor 25 that receives the command signal from the engine control unit 93, the control rack 23 operates to perform the fuel increase / decrease operation, and the increase / decrease in the rotation speed of the output shaft 13 of the engine 11 is controlled.

The control unit 71 is composed of a microcomputer (hereinafter referred to as CPU) 95, a memory 97, and an interface 99 as an input / output signal processing circuit. In the input port (input interface) 101 of the interface 99, the above-described gear position selection switch 63, brake sensor 87, accelerator sensor 85, engine rotation sensor 27, clutch rotation sensor 41, gear position switch 75, vehicle speed sensor 79, clutch. Stroke sensor 35, clutch touch sensor 37
(Used when the connection / disconnection information of the clutch 15 is output instead of the clutch stroke 35), the air sensors 57, 5
9, BRS sensor 10 that outputs information on the strong brake pedal force
6, an exhaust brake on / off switch 120, an engine brake auxiliary device on / off switch 121, a rack position detection sensor 123, and a slope start switch 103 described later.
Are connected, and detection information is input to the control unit 71 from each of these sensors.

The slope start switch 103 is for operating a system (hereinafter referred to as AUS) for preventing backward movement when the vehicle starts uphill. This AUS is
Air master 1 for a plurality of wheel brakes 107, 107
09,109 is supplied with air by a pair of solenoid valves MVQ
This is a system for starting a vehicle while controlling it via 111, 111.

On the other hand, the output port (output interface) 113 is provided with the engine control unit 93, the starter relay 91, the solenoid valves X1, X2, Y described above.
1, Y2, W and solenoid valves 55, 73, 111 are connected respectively. In the figure, reference numeral 115 indicates an air warning lamp which is lit by receiving a detection signal from the air sensors 57 and 59 when the air pressure in the air tanks 47 and 49 has not reached a set value, and reference numeral 117 indicates wear of the clutch 15. A clutch warning lamp, which lights when receiving the detection signal when the amount exceeds a specified value, indicates a stop lamp switch which is turned on when the brake pedal 69 is depressed.

The memory 97 is composed of a read-only ROM in which various flowcharts are written as programs and data and a writable RAM. In the ROM, in addition to the control program, the duty ratios of the solenoid valves X1, X2, Y1, Y2 corresponding to the accelerator opening information VA are stored in advance as a map.
Reads the appropriate value from this map as appropriate.

The shift stage selection switch 63 described above outputs a select signal and a shift signal as shift signals, and the shift stage positions corresponding to a pair of these two signals are stored in advance in the ROM as a data map. ing.
Therefore, when the control unit 71 receives the select signal and the shift signal, the CPU 95 calculates an output signal from this map, and further gives this output to each solenoid valve 73 of the gear shift unit 65 to set the target shift speed corresponding to the shift signal. Match the gear. The gear position signal from the gear position switch 75 is output when the shift is completed, and it is determined whether all the gear position signals corresponding to the select signal and the shift signal have been output. That is, this gear position signal is used to generate a signal indicating whether the meshing is normal.

Further, the ROM also has a shift map for determining the optimum shift speed based on the values of the vehicle speed V, accelerator opening VA and engine speed Ne when the target shift speed in the D range exists. Remembered As the shift map, Table 1 is a selection map according to the on / off states of the foot brake signal and the exhaust brake signal from the brake sensor 87 and the exhaust brake on / off switch 120.
As shown in, three types of # 1, # 2, and # 3 are set. The three types are set in this manner in order to improve the driving feeling on a downhill. Normally, the selection map # 1 is applied when the braking is not performed.

[0047]

[Table 1]

Further, since the drive torque required for buses and trucks usually changes according to the loading condition and the operating condition, the loading condition (for example, vehicle load degree αVL, which will be described later) is stored in the ROM. There is also stored a shift map that can be switched automatically or based on the driver's intention, depending on the situation and the driver's preference described later. There are three types of shift maps according to the loading condition, the driving condition, and the like, for example, an economy mode in which fuel efficiency is emphasized, a normal mode, and a power mode in which acceleration is emphasized.
It is provided for each shift map of 1, # 2, and # 3.
That is, in the ROM, for example, the vehicle speed V and the accelerator opening V
In relation to A, a total of 9 types of shift maps are stored. FIGS. 5 to 13 show these nine types of shift maps, FIGS. 5 to 7 show the shift maps of # 1, # 2, and # 3 in the economy mode, and FIGS. Is # 1, # 2, # in normal mode
3 shows each shift map, and FIGS. 11 to 13 show each shift map # 1, # 2, # 3 in the power mode. That is, the CPU 95 appropriately selects a shift map according to the situation from these shift map groups. In these shift maps, shift-up shift characteristics are shown by solid lines, and shift-down shift characteristics are shown by broken lines.

By the way, the basic operation of the above-described automatic transmission is known, and a detailed description thereof will be omitted here.
This automatic transmission operates, for example, in the same manner as that disclosed in Japanese Utility Model Laid-Open No. 2-49663. Next, the control content of the control unit 71, which is an essential part of the present invention, will be described.

As shown in FIG. 1, for the control unit 71 of this automatic transmission, a suitable shift map is selected from the above shift map group, the vehicle speed information V from the vehicle speed sensor 79 and the accelerator opening sensor 89 are selected. A target shift speed setting means 3 for setting a target shift speed from the selected map based on the accelerator opening information VA, and an optimum shift speed determining means 1 capable of correcting the target shift speed by reflecting the driver's intention. Has been.

The target shift speed setting means 3 is provided with a storage means 3A for storing a shift map and a learning type selection means 3B, and the storage means 3A has other than the shift map group shown in FIGS. 5 to 13. In addition, a shift down regulation map (see FIG. 33) that regulates 5-4 down shift and 4-3 down shift as described later is stored for each mode of the selection map # 1. Therefore, the target shift speed setting means 3 is configured as a map type storage means.

Further, the learning type selection means 3B of the target shift speed setting means 3 has a function of performing learning according to the driving preference of the driver and selecting one of the above shift maps. . The driver's driving preference refers to, for example, a driving method such as whether he / she wants to shift up early with an emphasis on fuel consumption, or whether he / she wants to drive with emphasis on acceleration. Therefore, the learning formula selecting means 3B learns the driving operation of the driver using the driving operation information by the driver as input information, and selects the optimum one from the plurality of shift maps in the storage means 3A according to the driver's preference and personality. Select the shift map.

More specifically, the learning type selection means 3B is shown in FIG.
It is configured to include a plurality of neural networks as shown in FIG. 30. When various driving operation information is input to these neural networks, arithmetic processing including learning is performed in the neural network, and as a result, the driver is operated. The optimum output signal (judgment output) according to the user's preference is output. Then, a shift map corresponding to the output signal from each neural network is selected, and the target shift speed corresponding to the vehicle speed V and the accelerator opening degree VA is set based on this shift map.

The optimum shift stage determining means 1 determines the driver's intention and the running state of the vehicle using the fuzzy theory, and can correct the target shift stage set by the target shift stage setting means 3 by using the fuzzy formula optimum. It is configured as a gear stage determining means. In this fuzzy type optimum shift speed determining means 1, a fuzzy rule described below is applied using vehicle information having vehicle load information as a parameter. As vehicle load information, the vehicle accelerates on a straight flat road in an empty state. The difference between the acceleration α0 in this case and the actual acceleration α when the vehicle is actually accelerated (= vehicle load αVL) is used as a parameter.

For this reason, the control unit 71 is provided with a vehicle load degree calculating means 2 for calculating the vehicle load degree αVL, as shown in FIG. The vehicle load degree calculating means 2 comprises an engine torque calculating means 4, a driving force calculating means 5, an air resistance calculating means 6, a straight flat road empty vehicle equivalent acceleration calculating means 7, and a subtracting means 8. Of these, the engine torque calculation means 4 calculates the engine torque Te from the position information SRC of the control rack 23 and the engine speed information Ne supplied from the rack position detection sensor 123, and is a target shift speed setting means. Similar to No. 3, it is configured as a map type storage means.

Here, the position information SRC of the control rack 23 is used to calculate the engine torque Te, but the position information SRC which is the actual rack position and voltage value is used.
And have a relationship as shown in FIG. Further, when using this position information SRC, filter processing for the purpose of noise removal is performed. Specifically, as the filter, a known low-pass filter (Butterworth type first-order digital filter) as shown in FIG. 15 is used. In this low pass filter, the processing coefficients a and b
Are represented by the following equations.

A = ωc / (ωc + 2) b = (ωc-2) / (ωc + 2) where ωc is a cutoff frequency, for example, 0.0
628 rad / sec. FIG. 16 shows a flowchart of the low-pass filter processing routine of FIG. 15, but the filter processing will be briefly described based on this figure.

At step F10, an initial value 0 is set in the processing variables buffer1 and buffer2. And step F
In step 12, the processing coefficients a and b are calculated based on the above equation, and in step F14, the processing variable buffer2 is temporarily set to the processing variable buffer1.
And In step F16, the processing variable buffer1 is set from the following equation based on the processing variable buffer2 obtained as described above.

Buffer1 = buffer2 (-b) + (input value) Then, in step F18, the final output value, that is, SRC, is obtained from the following equation. (Output value) = SRC = (buffer1 + buffer2) .a In this way, the positional information SRC that is the voltage value is filtered, but these steps F14, F16, F1 are performed.
In the process of 8, the determination result in step F20 is true (Yes
It continues as long as there is an input value in s).

The same filtering process is performed on the engine speed information Ne. The engine torque Te is obtained from the filter-processed position information SRC and the engine speed information Ne based on a preset map (not shown). The engine torque Te is the exhaust brake or the compression opening type engine auxiliary. Since it depends on the use of the brake, in a situation where the exhaust brake or the compression release type engine auxiliary brake is used, a map (not shown) set separately according to this situation is used.

The values obtained from the above maps are subjected to first-order delay processing. The low-pass filter and the processing routine shown in FIGS. 15 and 16 are applied to the first-order lag processing. At this time, the processing coefficients a and b are the exhaust brake (EXB) and the compression opening type engine auxiliary brake (P).
It is set as shown in Table 2 according to the usage status of T).

[0062]

[Table 2]

Here, T represents a calculation cycle, and τA, τB,
τC is a time constant preset for each usage of the exhaust brake (EXB) and the compression release type engine auxiliary brake (PT). However, in this case, exhaust brake (EXB) and compression release type engine auxiliary brake (PT)
At the time of switching of the use status of the process variables buffer1 and b of step F10 of the process routine shown in FIG.
The initial value of uffer2 is calculated by the following equation using the processing coefficients a and b.

Buffer1 = y / a-buffer2 buffer2 = (y / ax) / (1-b) where x is an input value immediately before switching and y is an output value immediately before switching.

Further, the driving force calculation means 5 has the engine torque information Te obtained by the engine torque calculation means 4.
The driving force F of the vehicle is calculated based on the following equation. The driving force F is calculated, for example, by the following formula. F = (Te · it · if · η) / R where it is the gear ratio of the gear, if is the final reduction gear ratio (differential gear ratio), η is the power transmission efficiency, and R is the tire radius.

The air resistance calculating means 6 calculates the air resistance Rl as the running resistance of the vehicle from the actual vehicle speed information V, and is calculated by the following equation. Rl = λ · A · V ² where λ is the air resistance coefficient, A is the front projected area of the vehicle, and V is
Is the actual vehicle speed. Next, the straight flat road empty vehicle equivalent acceleration calculation means 7 (hereinafter, referred to as acceleration calculation means) 7 will be described. The acceleration calculation means 7 includes the driving force information F calculated by the driving force calculation means 5 and the air resistance. From the air resistance coefficient information Rl calculated by the calculation means 6, the acceleration α0 when the vehicle accelerates on a straight flat road in an empty state, that is, the straight flat road empty vehicle equivalent acceleration is calculated. This straight flat road empty vehicle equivalent acceleration α0 is calculated by the following equation using the driving force F of the vehicle.

Α0 = g {F- (μW0 + Rl)} / (W0 + Wr) where g is gravitational acceleration, μ is a road surface friction coefficient, W0 is an empty vehicle weight, and Wr is a rotating portion weight. Then, in the subtracting means 8, the straight flat empty vehicle equivalent acceleration information α 0 calculated by the acceleration calculating means 7 and the actual acceleration information α from the vehicle speed sensor 79.
The vehicle load degree information αVL is calculated based on the following equation. The vehicle load degree information αVL corresponds to the weight of the vehicle and the gradient resistance of the vehicle.

ΑVL = α0−α That is, if αVL> 0, the vehicle load is heavy, and if αVL <0, the vehicle load is light. Then, from the magnitude of the value of αVL, it is determined how heavy (or light) the vehicle load is. Here, FIGS. 17 to 19 are all examples calculated by simulating the vehicle load degree αVL, where the horizontal axis is the total vehicle weight gvw (gloss vehicle weight) and the vertical axis is the vehicle load degree αVL. FIG.
Is a flat road, FIG. 18 is a 10% uphill road, and FIG. 19 is 1
It is an example of calculating the vehicle load degree αVL on a 0% slope downhill road, and is calculated under the condition that the vehicle is constant except for the vehicle weight.

When the vehicle load degree αVL is calculated by the vehicle load degree calculating means 2 in this way, the fuzzy optimum gear shift stage determining means 1 adds the accelerator opening information VA, in addition to the vehicle load degree αVL. Accelerator opening change information ΔVA, vehicle speed information V, brake information, and current shift speed information are fetched and correction is performed on the target shift speed set by the target shift speed setting means 3. As the brake information, in addition to the foot brake operation information input from the brake sensor 87, operation information such as an exhaust brake and a compression opening type engine auxiliary brake is also input. The information is also taken into consideration for correction.

That is, the optimum shift stage determination means 1 corrects the target shift stage by fuzzy inference based on predetermined fuzzy rules for each information. 20 to 22 are membership functions of the respective information αVL, VA, ΔVA which are input to the optimum shift stage determining means 1 as parameters of the driving information. Of these, FIG. 20 shows a membership function of the vehicle load degree αVL. Here, α1, α2, α3, α4 of the vehicle load αVL,
α5 and α6 are preset values, and these values are different for each of the seven forward gears.
That is, each shift speed has its own membership function with respect to the vehicle load degree αVL.

FIG. 23 shows a membership function for correcting the shift speed by reflecting the driver's intention. The membership function of the vehicle speed information V is omitted. In this optimum shift stage determining means 1, the target shift stage is corrected by the fuzzy inference method using the min-max combined center of gravity method. Here, FIG. 24 shows the min-max combined centroid method.
A brief description will be given step by step using (a) to (c).

1) First, the goodness of fit of the membership function to the input value of the antecedent part of the fuzzy rule is obtained for all fuzzy rules. For example, if the outputs from the sensors at a certain time t are a1 (t), a2 (t), ..., As shown in FIGS. 24 (a) and 24 (b), the fuzzy rules R1, R2 ,. .., the membership grades (fitness) A1 and A2 for a1 (t) and a2 (t) are obtained from each membership function.

2) Next, the minimum value m of the goodness of fit for each rule
ask for in. That is, the fuzzy rule R in FIG.
In the antecedent part of 1, the goodness-of-fit A1 for a1 (t) is smaller than the goodness-of-fit A2 for a2 (t), and therefore the parameters of the fuzzy rule are a1 (t), a2.
In the case of only two of (t), A1 becomes the minimum value min. Similarly, as shown in FIG. 24B, in the fuzzy rule R2, the goodness of fit A2 for a2 (t) is the minimum value mi.
n.

3) The membership function of the consequent part is defined by the minimum value min. Then, of the conformance of the membership function of the consequent part, the part having the minimum value min or more obtained in 2) above is cut to define the membership function of the consequent part. Again, as shown in FIGS. 24 (a) and 24 (b),
This is performed for each fuzzy rule R1, R2, ...

4) The graphs obtained by the fuzzy rules are overlaid to obtain the max figure. Here, FIG.
As shown in (c), the graph (figure) obtained in 3) is overlaid to find the maximum value of the membership function. 5) Obtain the position of the center of gravity of the figure in 4) above. Then, the figure centroid C1 of the membership function shown in FIG. 24 (c) is obtained to obtain the fuzzy rules R1, R2,
It is possible to perform weighting according to the degree of conformity in. Then, in the membership function of the consequent part, the driver's intention is determined from the degree of conformity corresponding to the output C1.

The membership functions shown in FIGS. 24A to 24C described above are for explaining the min-max combined centroid method, and are the members of this embodiment shown in FIGS. 20 to 23. It does not always match the ship function. By the way, as shown in FIG. 25, as fuzzy rules, 15 rules R1 to R15 are set. Among these, in each rule of R1 to R10, the target shift speed obtained from the shift maps shown in FIGS. 5 to 13 (that is, the shift speed set by the normal target shift speed setting means 3)
Even if the current shift speed is different, the optimum shift speed determining means 1 estimates that the driver does not have much intention to shift, and outputs a correction signal so as to maintain the current shift speed.

The fuzzy rules R1 to R10 will be described below. In the first fuzzy rule R1, the vehicle load degree αVL> 0, the absolute value is medium, the accelerator opening VA is large, and When the target shift speed is higher than the current shift speed and the shift-up is instructed based on the shift map of the target shift speed setting means 3 (for example, the selection map of # 1 described above), the optimum shift speed determining means is determined. In 1,
It is estimated that the vehicle is traveling on an uphill road or is traveling in a loaded state. In this case, even if the target shift speed setting means 3 gives an instruction to shift up, the optimum shift speed determining means 1 estimates that the driver has no intention to shift up and sets the gear shift speed to the current state. The gear shift command signal from the target gear stage setting means 3 is corrected so as to hold it. As a result, the shift-up of the shift speed is suppressed and the current shift speed (the optimum shift speed) is maintained.

In the second fuzzy rule R2, the vehicle load degree αVL> 0, the absolute value thereof is medium, the accelerator opening degree VA is medium, and the shift map of the target shift speed setting means 3 (for example, # When the shift up is instructed based on 1), the first fuzzy rule R described above is used.
As in the case of 1, the vehicle is estimated to be traveling on an uphill road or in a loaded state by the optimum gear position determining means 1, but in this case also, the optimum gear position determining means 1 gives the driver an intention to shift up. It is estimated that the gear shift stage is not present, and the gear shift stage is maintained in the current state as the optimum shift stage.

As described above, in the first and second fuzzy rules R1 and R2, unnecessary upshifting is suppressed and drivability is improved during traveling on an uphill road or traveling in a loaded state. In the third fuzzy rule R3, the absolute value of the vehicle load degree αVL <0 is small, and the accelerator opening degree VA is small.
Is small, and when the shift-up is instructed based on the shift map of the target shift speed setting means 3 (for example, # 1), it is estimated that the vehicle is traveling on a downhill road in the optimum shift speed determining means 1. To do. Also in this case, it is estimated that the driver has no intention of upshifting, the shift command signal from the target shift stage setting means 3 is corrected, and the gear shift stage is held in the current state.

In the fourth fuzzy rule R4, the vehicle load degree αVL <0 has a medium absolute value and the accelerator opening V
When A is small and the shift-up is instructed based on the shift map (for example, # 1) of the target shift speed setting means 3, the optimum shift speed determining means 1 is the same as the above-mentioned third fuzzy rule R3. Then, it is estimated that the vehicle is traveling on a downhill road. Then, similarly to the above, the shift command signal from the target shift speed setting means 3 is corrected, and the gear shift speed is held in the current state.

As described above, in the third and fourth fuzzy rules R3 and R4, unnecessary shift-up is suppressed during traveling on a downhill road, and thus effective engine braking can be obtained. become. Therefore,
This improves vehicle safety and drivability. Next, the fifth fuzzy rule R5 will be described. In the fifth fuzzy rule R5, the accelerator opening VA is small, the vehicle speed V is low, and the shift map of the target shift stage setting means 3 (for example, , # 1), the optimum shift stage determining means 1 estimates that the vehicle is traveling on a congested road. In this case, the optimum shift stage determining means 1 estimates that the driver has no intention of upshifting, and corrects the shift command signal from the target shift stage setting means 3 so as to keep the gear shift stage in the current state. As a result, the shift-up of the shift speed is suppressed and the current shift speed is maintained as the optimum shift speed. Therefore, unnecessary shift-up on a congested road is suppressed and drivability is improved.

In the sixth fuzzy rule R6, the vehicle load degree αVL> 0, the absolute value is small, and the accelerator opening change Δ
When VA <0, the absolute value is large, and the target shift speed setting means 3
When the shift-up is instructed based on the shift map of (1), the corner flag fc has the value 1
Is set, and it is estimated that the vehicle has decelerated before the curve in the optimum gear position determination means 1. In this case as well, it is presumed that the driver does not intend to shift up, and the gear shift stage is corrected so as to be maintained in the current state. Therefore, the shift-up of the shift speed is prohibited, and the current shift speed is maintained as the optimum shift speed. As described above, in the sixth fuzzy rule R6, when the vehicle decelerates before the curve, the gear does not shift up, effective engine braking can be obtained, and drivability is improved.

In the seventh fuzzy rule R7, the vehicle load degree αVL <0, the absolute value is large, the accelerator opening VA is small, and either the exhaust brake or the compression opening type engine auxiliary brake is used. When the auxiliary brake is on and the shift-up is instructed based on the shift map of the target shift stage setting means 3 (for example, the selection map of # 3), the vehicle is turned on by the auxiliary brake in the optimum shift stage determining means 1. It is presumed that the vehicle is traveling on a steep downhill road in which the vehicle speed is further increased despite the above. In this case as well, it is presumed that the driver does not intend to shift up, and the gear shift stage is corrected so as to be maintained in the current state. Therefore, the shift-up of the shift speed is prohibited, and the current shift speed is maintained as the optimum shift speed. In other words, according to the seventh fuzzy rule R7, even if the target shift speed is a shift up side from the current shift speed, the shift speed is one shift speed lower than the target shift speed, that is, The shift command signal is corrected so that the current shift speed is maintained as the optimum shift speed.
Therefore, it becomes possible to continuously and satisfactorily obtain the engine brake at the current gear position.

In the eighth fuzzy rule R8, the accelerator opening change ΔVA> 0, the absolute value is small, the vehicle speed V is low, and the target gear is smaller than the current gear, that is, When the downshift is instructed based on the shift map of the target shift speed setting means 3 (for example, the selection map of # 1), the optimum shift speed determining means 1 performs the re-acceleration after decelerating the vehicle once. Presumed to be. And
In this case, it is estimated that the driver does not have the intention of downshifting, and the gear shift stage is corrected so as to be maintained in the current state. Therefore, the downshift of the shift speed is suppressed, and the current shift speed is maintained as the optimum shift speed. This is also based on the consideration of traveling mainly in a traffic jam, and is based on the fact that in such a traffic jam, deceleration often occurs immediately even if a gear shift is executed.

In the ninth fuzzy rule R9, the accelerator opening change ΔVA> 0, the absolute value is medium, the vehicle speed V is low, and downshifting is instructed based on the shift map (eg, # 1). If the vehicle is still in motion, it is estimated that the vehicle is once decelerated again during a traffic jam or the like, and the vehicle is decelerated again, and the current gear is held. That is, with the eighth and ninth fuzzy rules R8 and R9, unnecessary downshifting can be suppressed during acceleration during traffic jams, etc., and drivability is also improved. There is also an advantage that fuel efficiency can be improved by suppressing downshift.

In the tenth fuzzy rule R10, the operation of the auxiliary brake such as the exhaust brake and the compression release type engine auxiliary brake is turned on, the foot brake is turned off, and the downshift is performed based on the shift map (eg, # 3). When instructed, it is presumed that the vehicle is about to be decelerated lightly, and the shift command signal from the target shift stage setting means 3 is corrected so as to maintain the gear shift stage in the current state. As a result, downshifting of the shift speed is suppressed,
The current gear stage (optimum gear stage) is maintained. Therefore, it is possible to suppress a large deceleration that goes against the driver's intention,
It is possible to prevent a shift shock due to downshifting, and drivability is improved.

The eleventh fuzzy rule R11 to the fourteenth fuzzy rule R14 will be described. In these fuzzy rules, the shift speed set based on the shift maps shown in FIGS. 5 to 13 and the current shift speed are set. Even if they coincide with each other, the optimum shift stage determining means 1 estimates that the driver has an intention to shift, and outputs a correction signal to shift to a shift stage one speed lower than the current shift stage. .

That is, in the eleventh fuzzy rule R11,
When the vehicle load degree αVL> 0, the absolute value is large, the accelerator opening VA is large, and there is no shift instruction from the target shift stage setting means 3, that is, the shift set based on the shift map (for example, # 1). When the speed and the current shift speed match, the optimum shift speed determining means 1 estimates that the vehicle is traveling on a steep uphill road or in a loaded state. In this case, even if the target shift speed setting means 3 does not set a command to change the shift speed,
The optimum shift stage determining means 1 estimates that the driver has the intention of downshifting, and the gear shift stage is set to be 1 more than the current shift stage.
The shift command signal is corrected so that the gear is shifted to the lower gear. As a result, the shift speed is shifted down to the optimum shift speed, and it becomes possible to obtain a larger drive torque, so that the acceleration performance in traveling on a steep uphill road or traveling in a loaded state is improved. .

In the twelfth fuzzy rule R12,
When the vehicle load degree αVL <0, the absolute value is large, the auxiliary brake is on, and there is no shift instruction based on the shift map (for example, # 3) of the target shift speed setting means 3, the optimum shift speed determining means 1 determines , It is estimated that the vehicle is traveling on a steep downhill road. By the way, in this case, since there is no shift instruction to the upshift side even though the vehicle is on a steep downhill road, the auxiliary brake is applied more than in the case of the above-mentioned seventh fuzzy rule R7, which is also presumed to be a steep downhill road. It seems to work well. However, even in such a case, the optimum shift stage determining means 1 estimates that the driver has the intention to shift down, and the gear shift stage is one gear lower than the current shift stage which is the target shift stage. That is, the shift command signal is corrected so as to shift to the shift stage. This makes it possible to reliably obtain a larger engine brake.

In the thirteenth fuzzy rule R13,
When the vehicle load degree αVL <0, the absolute value is large, the auxiliary brake is turned on, the foot brake is turned on, and there is no shift instruction based on the shift map of the target shift stage setting means 3 (for example, the selection map of # 2). In this case, the optimum shift stage determining means 1 estimates that the vehicle is traveling on a steep downhill road as in the case of the twelfth fuzzy rule R12. However,
In this case, the driver is operating the foot brake in addition to the case of the fuzzy rule R12, and it is estimated that the vehicle is traveling on a steep downhill road. Therefore, the optimum shift stage determining means 1 still estimates that the driver has the intention of downshifting, and shifts the gear shift stage to the shift stage one speed lower than the current shift stage. Correct the signal. This makes it possible to reliably obtain a larger engine brake.

As described above, in the twelfth and thirteenth fuzzy rules R12 and R13, the shift stage is shifted down to the optimum shift stage, so that a large engine brake can be obtained and the load on the foot brake is reduced. As a result, it is possible to achieve a safer traveling state. In the fourteenth fuzzy rule R14, the vehicle load degree αVL> 0 has a small absolute value, the accelerator opening VA is medium, and the accelerator opening change ΔVA> 0 has a large absolute value, and the vehicle speed V is medium. ,
In addition, the shift map of the target shift speed setting means 3 (for example, #
If there is no shift instruction based on 1), the optimum shift stage determination means 1 estimates that the vehicle is going to perform overtaking acceleration, and shifts the gear shift stage one speed lower than the current shift stage. The shift command signal is corrected so as to shift to the next gear. As a result, a shift to the low speed stage side is executed, and smooth acceleration can be performed.

In the fifteenth fuzzy rule R15, the vehicle load degree αVL> 0, the absolute value thereof is large, and the target shift speed is higher than the current shift speed. When the shift-up is instructed based on # 1) of No. 1), the vehicle is traveling on a steep uphill road or in the loaded state, regardless of the accelerator opening degree VA or the like. It is estimated that the vehicle is running at. In this case, even if the shift-up command is issued by the target shift-speed setting means 3, the optimum shift-speed determining means 1 estimates that the driver does not intend to shift up and sets the gear shift speed to the current state. The gear shift command signal from the target gear stage setting means 3 is corrected so that As a result, the shift-up of the shift speed is suppressed and the current shift speed, which is the optimum shift speed, is maintained.

In the shift control device for an automatic transmission for a vehicle as one embodiment of the present invention, the target shift speed is corrected and the optimum shift speed is determined as described above. Is determined by the control unit 71 according to the flowchart of the main routine as shown in FIG. The procedure for determining the automatic shift, that is, the optimum shift stage in the D range will be described in detail below with reference to FIG.

First, in step S10, the engine torque Te is calculated by the engine torque calculating means 4 as described above. Then, in step S12, the driving force calculation means 5 calculates the driving force F of the vehicle, and in the next step S14, the air resistance calculation means 6 calculates the air resistance Rl of the vehicle. In step S16, the linear flat road empty vehicle equivalent acceleration α0 is calculated by the linear flat road empty vehicle equivalent acceleration calculating means 7 from the driving force information F calculated in step S12 and the air resistance information Rl calculated in step S14.
Is calculated.

Then, in step S18, step S
The load degree information αVL of the vehicle is calculated on the basis of the straight flat road empty vehicle equivalent acceleration α0 calculated in 16 and the actual acceleration information α from the vehicle speed sensor 79. In the next step S19, the learning formula selection means 3B of the target shift speed setting means 3 performs learning control of the shift according to the driver's preference, and
The optimum shift map is selected from the storage means 3A. Below, regarding the learning control of the shift according to the driver's preference,
This will be described based on the flowchart of FIG.

First, in step S70 of FIG. 27, data necessary for learning the shift according to the driver's preference is calculated. The following are examples of learning data.
Since the learning effect is great, 2-3 upshifts and 3-4 upshifts are the learning targets for upshift learning, and when driving on a flat road where the driver's preference is easy to disperse. Is intended for. (1) M range usage frequency FMU: Usage frequency FMU is the usage frequency of the M (manual) range at the time of upshifting, and the number of times the M range has been used during the last 10 2-3 upshifts and 3-4 upshifts. Ask for. (2) 2-3 accelerator opening average AVA (23): 2-3 accelerator opening average AVA (23) is the average value of accelerator opening VA at the time of shifting from the 2nd gear to the 3rd gear in the D range. Then, the average of the past five flat roads is calculated from the following equation.

AVA (23) = (VA (23) 0 + VA (23) 1+ ..
.. + VA (23) 4) / 5 (3) 2-3 standard deviation SVA (23): 2-3 standard deviation SV
A (23) is the standard deviation (3σ) of the accelerator opening VA when shifting from the 2nd speed to the 3rd speed in the D range. Again, the standard deviation of the past 5 times on a flat road is calculated from the following equation. Ask.

SVA (23) = 3 · ((1/5) · Σ (VA (2
3) i-AVA (23)) ² ) ^1/2 , i = 0 to 4 (4) 3-4 Average accelerator opening AVA (34): 3-4 Average accelerator opening AVA (34) is in D range Is an average value of the accelerator opening degree VA at the time of shifting from the 3rd speed stage to the 4th speed stage. Again, the average of the past 5 times on a flat road is obtained from the following formula.

AVA (34) = (VA (34) 0 + VA (34) 1+ ..
.. + VA (34) 4) / 5 (5) 3-4 standard deviation SVA (34): 3-4 standard deviation SV
A (34) is the standard deviation (3σ) of the accelerator opening VA when shifting from the 3rd gear to the 4th gear in the D range. Again, the standard deviation of the past 5 flat roads is calculated from the following equation. Ask.

SVA (34) = 3 · ((1/5) · Σ (VA (3
4) i-AVA (34)) ² ) ^1/2 , i = 0 to 4 (6) 2-3 engine rotation average ANe (23): 2-3 engine rotation average ANe (23) is manual in M range The average value of the engine speed at the time of shifting from the second speed to the third speed by the operation, and the average value on the past five flat roads is calculated from the following formula. Specifically, it is obtained from the average value of the engine rotation speed Ne immediately before the start of the shift.

ANe (23) = (Ne (23) 0 + Ne (23) 1 + ...
・ + Ne (23) 4) / 5 (7) 3-4 engine rotation average ANe (34): 3-4 engine rotation average ANe (34) is changed from the third gear to the fourth gear by manual operation in the M range. It is the average value of the engine speed at the time of shifting, and again, the average value on the past five flat roads is obtained from the following formula. Similarly to the above, it is obtained from the average value of the engine rotation speed Ne immediately before the shift starts.

ANe (34) = (Ne (34) 0 + Ne (34) 1 + ...
・ + Ne (34) 4) / 5 (8) Hold range (HOLD range) Frequency of use F
H: HOLD range usage frequency FH, that is, the frequency of switching to the M range side, the vehicle speed V from the predetermined value V2 (eg 40 km / h) to the predetermined value V1 (eg 1
It is the ratio of the total time ts when it becomes 0 km / h) to the HOLD range use time tH, and the average value of the past 5 times is calculated from the following formula.

FHi = tHi / tsi, i = 0 to 4 FH = (FH0 + FH1 + ... + FH4) / 5 (9) Frequency of use of M range during shift down FMD: Frequency of use of M range during shift down FMD is a foot brake Is the frequency of manual downshifts while the vehicle speed V is from the predetermined value V2 (for example, 40 km / h) to the predetermined value V1 (for example, 10 km / h) while turning on, and the average value of the past five times is calculated as follows. Calculate from the formula.

FMDi = NMDi / NDi, i = 0 to 4 FMD = (FMD0 + FMD1 + ... + FMD4) / 5 where NMDi is the number of downshifts by manual operation in the above period, and NDi is all shifts including manual operation. The number of times down. Then, in the next step S72, it is determined whether or not the vehicle is traveling on a flat road for the above reason. Here, it is determined whether or not the vehicle load degree αVL is within a predetermined range (near the zero value) set for each shift speed. By thus determining whether or not the vehicle is traveling on a flat road, it is possible to limit the learning only to the flat road on which the driver's preference greatly appears.

If the determination result of step S72 is false (No),
That is, when it is determined that the vehicle load degree αVL is out of the predetermined range and the vehicle is not traveling on a flat road, the process proceeds to step S82 without performing the shift-up learning. on the other hand,
When the determination result of step S72 is true (Yes), that is, when it is determined that the vehicle load degree αVL is within the predetermined range and the vehicle is traveling on a flat road, the process proceeds to step S74.

At step S74, M at the time of upshift is set.
It is determined whether or not the usage frequency FMU of the range is small. Specifically, it is determined whether the usage frequency FMU is less than or equal to a predetermined threshold. If the determination result is true, it can be determined that the frequency of use of the M range is small during upshifting, and in this case, the process proceeds to step S76. In step S76, the preference for shift up is learned based on the shift up by the D range operation, and the output necessary for selecting the shift map, that is, the determination output is set. That is, here
Since the frequency of use of the M range is low, learning based on the automatic shift is not performed, but learning based on the use of the M range is not performed. More specifically, the first neural network shown in FIG. 28 performs learning based on the backpropagation learning method and calculation of the judgment output. The processing in the first neural network will be described below.

In the input layer of the first neural network of FIG. 28, the previously selected shift map information, the above-mentioned 2
-3 Accelerator opening average AVA (23), 2-3 standard deviation SV
A (23), 3-4 accelerator opening average AVA (34) and 3-4
Input values I1, I2, I3, I4, I of standard deviation SVA (34)
5 is entered. Here, the shift map information selected last time is the determination output of the previous time, and has the character as the reference value for the learning of this time. Then, these input values of I1 to I5 are normalized by the following equation to obtain Ii '
And input to the middle layer consisting of three pieces.

Ii '= (Ii-Iimin) / (Iimax-Iimi
n), i = 1 to 5 where Iimin is the minimum value of Ii, that is, the minimum value of each input value of I1 to I5, and Iimax is the maximum value of Ii, that is, I1.
It is the maximum value of each input value of I5. Then, when inputting to the three intermediate layers, different coupling coefficients Wij (i = 1 to 5, j = 1 to 3) are added to the respective intermediate layer input values Ii '. That is, 1 is input to each of the input values Ii ′ input from the 5 input layers to the 3 intermediate layers in advance by experiments or the like.
Five coupling coefficients Wij (W11, W12, W13, W2)
1. W22 ... W53) corresponding coupling coefficient Wij is integrated.

Output values O1, O2, O3 calculated by the sigmoid function of the following equation are output from the three intermediate layers. Oj = 1 / (1 + exp (-Xj)), j = 1 to 3, where Xj = W1j.I1 '+ W2j.I2' + ... + W5j.
I5 '-[theta] j, j = 1 to 3 Here, [theta] j (j = 1 to 3) is a predetermined threshold value set in advance by experiments or the like.

Then, for these output values O1, O2, O3 as well, the preset coupling coefficient Wj4 (j = 1 to 3) is integrated and inputted to the output layer, and the judgment calculated from the following equation from the output layer is made. Output O4 is output. O4 = (1 / (1 + exp (-Y4))). (Omax-Om
in) + Omin However, Y4 = W14 * O1 + W24 * O2 + W34 * O3- [theta] 4 where Omax is the maximum value of the judgment output O4 and Omin is the minimum value of the judgment output O4. Further, θ4 is a predetermined threshold value set in advance by experiments or the like.

The above-mentioned Iimin, Iimax, Omin, Om
Detailed descriptions of ax, Wij, Wj4, θj, and θ4 are omitted here. However, since the input value I1 and the judgment output value O4 corresponding to the previously selected shift map information among the input values Ii take values between 1 and 3 as described later, the minimum of the input value I1 is obtained. The value I1min and the minimum value Omin of the output value O4 are the value 1, while the maximum value I1max of the input value I1 and the maximum value Omax of the output value O4 are value 3.
Becomes

As described above, when the frequency of use of the M range at the time of the shift up by the driver is small, learning is performed based on the shift up by the D range operation instead of the M range operation, and the shift map is selected. output,
That is, the judgment output O4 is set to be good and stable. On the other hand, if the determination result of step S74 is false and it is determined that the M range is frequently used during upshifting, it can be determined that the driver frequently uses the M range and is not satisfied with the D range alone. Then, the process proceeds to step S78.

In this step S78, step S74
Based on the fact that the frequency of use of the M range is increased in step 1, the preference for shift up is learned based on M range operation, that is, manual shift up, and an output for selecting a shift map, that is, a determination output is set. . Specifically, the learning and the judgment output are calculated by the second neural network as shown in FIG. 29 provided separately from the first neural network. Less than,
The processing in the second neural network will be described.

In the input layer of the second neural network of FIG. 29, the previously selected shift map information, the above-mentioned 2
Input values I'1, I'2, I'3 of the -3 engine rotation average ANe (23) and 3-4 engine rotation average ANe (34) are input. Here, similarly to the above, the shift map information selected last time is the determination output of the previous time, and has the character as the reference value of the current learning. Then, these input values of I1 to I5 are normalized by the following equation to be I'i ', and are input to the intermediate layer composed of three pieces.

Then, through the intermediate layer, the output value O'1,
O'2 and O'3 are obtained, and the judgment output O'4 is finally derived. The arithmetic processing in this second neural network is the same as that in the first neural network. The detailed description is omitted here. In this way, when the M range is frequently used during shift up, learning is performed based on the manual shift up by the M range operation, and it is determined whether to select the shift map according to the driver's preference. The output O'4 will be set appropriately.
That is, the output indicating which of the economy mode, the standard mode, and the power mode shift map is selected is set according to the operating condition of the M range by the driver.

When the determination outputs O4 and O'4 regarding the upshift are set by the processing of the first neural network or the second neural network as described above, the process proceeds to step S80. In step S80,
A shift map is selected according to the judgment outputs O4 and O'4. That is, any one of the economy mode, standard mode, and power mode shift maps is selected here.

Specifically, the shift map is selected based on the graph showing the relationship between the judgment outputs O4 and O'4 and the selection map as shown in FIG. For example, the judgment outputs O4 and O'4 from the first neural network or the second neural network are 1 or more and less than 1.5 (1≤O.
When 4, O'4 <1.5), the economy mode shift map is selected, and the judgment output O4, O'4 value is 1.5 or more and less than 2.5 (1.5 ≤ O4, O'4 <. In the case of 2.5), the shift map of the standard mode is selected and the judgment output O
4, O'4 value is 2.5 or more and less than 3 (2.5≤O4, O'4 <
In the case of 3), the power mode shift map is selected.

Here, the economy mode selection map is a shift map that emphasizes fuel consumption as described above, and the shift timing at each shift speed is lower than the standard mode having the same shift timing as the normal D range. Is set to the side. In addition, the power mode selection map is a shift map that emphasizes acceleration, and the upshift timing of each shift stage is set to the high vehicle speed side with respect to the standard mode. That is, when the judgment outputs O4 and O'4 change due to the learning, the shift timing in the D range (automatic shift) is suitably switched to the shift pattern according to the driver's preference.

In the next step S82, it is determined whether or not the foot brake is on and the vehicle speed V has changed from a predetermined value V2 (for example, 40 km / h) to a predetermined value V1 (for example, 10 km / h). This determination is a determination as to whether or not to carry out a shift-down favorite learning. The determination result of step S82 is false, and the vehicle speed V is the predetermined value V2 while the foot brake is on.
(Eg, 40 km / h) to a predetermined value V1 (eg, 10 km / h)
If it does not change to h), it can be determined that it is not necessary to learn the downshift preference. In this case,
Exit this routine without doing anything.

On the other hand, the determination result of step S82 is true,
The vehicle speed V from the predetermined value V2 (for example, 40 km / h) to the predetermined value V1 (for example, 10 km / h) while the foot brake is on.
If it is changed to, it can be determined that the learning for the downshift preference is performed, and in this case, step S8 is performed next.
Proceed to 4. In step S84, the downshift preference is determined. That is, the shift-down preference learning is performed according to the driver's use of the M range, and the judgment output necessary for selecting the shift map is set. Specifically, the learning and the calculation of the judgment output are performed by the third neural network shown in FIG. The processing in the third neural network will be described below.

In the input layer of the third neural network of FIG. 30, the previously selected shift map information, the above-mentioned H
The input values I "1, I" 2, I "3 of the OLD range use frequency FH and the M range use frequency FMD are input. Here, similarly to the above, the previously selected shift map information is the reference value for this learning. And these I "1,
The input values of I "2 and I" 3 are normalized by the following equation and I "i '
And input to the middle layer consisting of three pieces.

Then, through the intermediate layer, output values O "1, O" 2,
O "3 is obtained and the judgment output O" 4 is finally derived. The arithmetic processing in this third neural network is similar to the arithmetic processing in the first and second neural networks. The description is omitted here. However, here, the input value I "1 and the judgment output value O" 4 corresponding to the shift map information selected last time out of the input value I "i are values between 1 and 2 as will be described later. Since it is taken, the minimum value I "1 of the input value I" 1 and the output value O "
The minimum value O "min of 4 is the value 1, while the maximum value I" 1max of the input value I "1 and the maximum value O" max of the output value O "4 are the value 2.

In this way, the learning regarding the shift down is performed based on the use state of the M range during the shift down, and the judgment output O "4 for selecting the shift map according to the driver's preference is set. In other words, here, 5-4 downshift and 4-3
The output as to whether or not to select the downshift restriction map that restricts downshift is set. Here, the shift-down regulation map is provided for each economy mode, standard mode, and power mode selection map # 1 as described above, and is a shift map different from the maps of FIG. 5, FIG. 8, and FIG. 11 described above. is there.

In FIG. 33, the shift-down map in the economy mode is shown as a representative, but as shown in the figure, in the shift-down regulation map, the accelerator opening V
When A is small, 5-4 downshift and 4-3
The downshift shift timing is shifting to the lower vehicle speed side. That is, the timing of 5-4 downshift and the timing of 4-3 downshift are the same as the timing of 3-2 downshift. Therefore, in this shift-down regulation map, the fifth speed or the fourth speed is held unless the vehicle speed V becomes extremely low, and the 5-4 downshift and the 4-3 downshift are not executed.

Then, in step S86, it is determined whether or not the shift down is possible according to the determination output O "4, and the normal economy mode, the standard mode, the power mode selection map # 1 and the shift provided for each mode. One of the down regulation maps is selected.
From the graph showing the relationship between the judgment output O "4 and the shift down propriety as shown in Fig. 2, the shift down propriety according to the judgment output O" 4 is selected, and the shift down regulation map is appropriately selected based on this result. To be done. In other words, if the judgment output O "4 value is 0 or more and less than 0.5 (0≤O" 4 <0.5), the shift down restriction map is selected because the shift down is prohibited, while the judgment output O " 4 values are 0.5 or more and 1 or less (0.5
If ≦ O ″ 4 ≦ 1), downshifting is possible and the normal economy mode, standard mode, and power mode selection map # 1 is selected.

For example, when the driver frequently performs a manual downshift in the M mode during deceleration, the normal economy mode, standard mode, and power mode selection map # 1 is selected.
At this time, in the D range, 5--
4, 4-3 downshift is executed, whereby the engine brake works properly. On the other hand, during deceleration,
When the driver often operates the foot brake while holding the HOLD range, that is, when the driver does not like the shock of the downshift, the downshift restriction map is selected. At this time, in the D range In other words, regardless of the decrease in the vehicle speed V, the fifth speed and the fourth speed are favorably maintained, and discomfort such as shift shock is appropriately prevented.

As described above, when learning is added and the selection of the shift map according to the driver's preference is completed,
Next, the process proceeds to step S20 in FIG. This step S2
From 0 onward, the routine becomes an optimum shift stage setting routine mainly based on the operating state of the vehicle. In step S20, it is determined whether the corner flag fc has a value of 1 and the vehicle is approaching a corner. As described above, the corner flag fc is set to the value 1 based on the sixth fuzzy rule R6, and is set in step S32, which will be described later, in which the driver intention inference is performed in this routine. The determination result of step S20 is true (Yes), and the corner flag f
If c is the value 1, that is, if the vehicle is approaching a corner and it is determined that the vehicle is decelerating before the corner, then step S26 is performed.
Proceed to.

In step S26, post-corner processing is performed. In this corner post-processing, the corner flag fc is set to 0.
The processing is to reset the corner flag fc here when the following condition is satisfied. fc reset condition: vehicle load degree αVL is less than a predetermined value TH2 (αVL <TH2), accelerator opening VA is a predetermined value TH3 or more (VA ≧ TH3), or the target shift speed matches the current gear (current = target). ) The predetermined value TH3 is equal to the actual accelerator opening of 75
Corresponds to% open state.

Normally, immediately after the corner flag fc is set to the value 1, the condition for resetting the corner flag fc is not satisfied, and in this case, the corner flag fc is held at the value 1 without being reset. Then, the process proceeds to step S28. In step S28, the final target stage is set to the current stage. As a result, the above step S2
If the corner flag fc is the value 1 and it is determined that the vehicle is decelerating before the corner by the determination of 0,
Even if the target gear is larger than the current gear, that is, when the upshift is instructed, the gear is maintained as it is regardless of the target gear without performing driver's intention inference described below. (6th fuzzy rule R6).

On the other hand, the determination result of step S20 is false (N
In o), if the corner flag fc is set to the value 0 by executing step S26 and it is determined that the vehicle is traveling straight, the process proceeds to step S22. Step S
At 22, the target shift speed suitable for the traveling state is obtained from the shift map selected as described above by the target shift speed setting means 3 based on the vehicle speed V and the accelerator opening degree VA.

Then, in step S24, step S
10 In addition to the vehicle load degree αVL obtained in step S18, the traveling state of the vehicle is estimated based on the above-mentioned fuzzy rules R1 to R15 based on the information from each sensor and the target shift speed, and the driver's intention to drive is estimated. presume. In step S30, the shift command to the target shift speed is corrected for each of the fuzzy rules R1 to R15 based on the driver's intention estimated in step S24 described above (see FIG. 25). Specifically, in this step S30, the target shift speed correction subroutine shown in FIGS. 34 and 35 is executed. Less than,
The procedure for correcting the target shift speed will be described with reference to FIGS.

In step S32 of FIG. 34, it is determined whether or not a predetermined time t1 (for example, 3 seconds) has elapsed since the last shift was completed. If the determination result is false and it is determined that the predetermined time t1 (for example, 3 seconds) has not elapsed after the shift is completed, the shift is continuously performed to prevent the shift shock from occurring. Step S4
Proceed to 2 and hold the final target stage at the current stage. On the other hand, if the determination result is true and it is determined that the predetermined time t1 (for example, 3 seconds) has elapsed after the end of the shift, the process proceeds to step S34.

In step S34, a predetermined time t2 (for example, from the on / off switching of the auxiliary brake such as the exhaust brake or the compression release type engine auxiliary brake) is carried out.
It is determined whether or not 3 sec) has elapsed. If the determination result is false and it is determined that the predetermined time t2 (for example, 3 seconds) has not elapsed after the on / off switching of the auxiliary brake, the process also proceeds to step S42 and the final target stage is held at the current stage. That is, as described above, the engine torque Te is calculated based on the map according to the on / off of the auxiliary brake such as the exhaust brake and the compression opening type engine auxiliary brake, but immediately after this on / off switching,
There is a delay in the operation of the exhaust brake and compression release type engine auxiliary brake, and there is a mismatch between the calculated engine torque Te and the actual engine torque, which may result in unnecessary gear shifting contrary to the driver's intention. It is preventing.

The determination result of step S34 is true and a predetermined time t2 (for example, 3 sec) has elapsed after the auxiliary brake is turned on and off.
If it is determined that has passed, then step S36
Proceed to. In step S36, the output value of fuzzy inference,
That is, it is determined whether or not the membership grade (fitness) of each membership function described above is greater than a predetermined value TH0 (for example, a value 0) and is equal to or less than a predetermined value TH1 (for example, a value 0.5). That is, it is determined whether or not the driver's intention is to keep the gear position as it is.

The determination result of step S36 is true, the output value is greater than a predetermined value TH0 (for example, a value 0) and less than or equal to a predetermined value TH1 (for example, a value 0.5) (TH1 ≧ output value> TH).
If it is determined to be 0), the process proceeds to step S42 and the final target stage is held at the current stage. On the other hand, the determination result of step S36 is false, and the output value is the predetermined value TH0 (for example, the value 0).
Alternatively, if it is determined that it is larger than the predetermined value TH1 (for example, the value 0.5), the process proceeds to step S38.

In step S38, the output value of the fuzzy inference, that is, the membership grade (degree of conformity) is a predetermined value TH.
It is determined whether or not it is larger than 1 (for example, a value of 0.5).
In other words, it is determined whether or not the driver's intention is to shift down the shift speed by one speed. The determination result of step S38 is true, and the output value is a predetermined value TH1 (for example, the value 0.
5) When it is determined that it is larger than (output value> TH1), the process proceeds to step S40.

In step S40, it is determined whether the vehicle speed V is equal to or higher than the overrun vehicle speed. If the determination result is true, the process proceeds to step S42 and the final target stage is held at the current stage. On the other hand, if the determination result is false, the process proceeds to step S44. In step S44, step S38
The output value is determined to be a predetermined value TH1 (for example, the value 0.
5) Based on the determination that it is larger than (output value> TH1), the final target gear is downshifted to the gear lower by one gear than the current gear.

If it is determined that the output value is not greater than the predetermined value TH1 (for example, the value 0.5), the process proceeds to step S46.
In such a situation, that is, when the output value is equal to the predetermined value TH0 (for example, the value 0), in this case, it is not necessary to apply each of the fuzzy rules, and step S4 is performed.
At 6, the final target gear is set to the target gear determined in step S22 in FIG.

As described above, the optimum shift speed reflecting the driver's intention with respect to the target shift speed is set based on the fuzzy rules R1 to R15. That is, even when the target shift speed setting means 3 sets a target shift speed different from the current traveling shift speed and a downshift or upshift command signal is input to the optimum shift speed determining means 1, When it is estimated that the optimum shift speed reflecting the intention corresponds to the current traveling shift speed, the optimum shift speed determination means 1 makes a correction to prohibit the shift command to the target shift speed. Therefore, in this case, the vehicle runs while maintaining the current gear, and the most appropriate gear according to the load condition of the vehicle and road conditions (uphill road, downhill road, presence of a curve, congested road, etc.) It becomes possible to drive in.

Further, even when the target shift speed set by the target shift speed setting means 3 coincides with the current traveling shift speed and the shift command signal is not inputted to the optimum shift speed determining means 1, When the optimum shift speed reflecting the intention is different from the current traveling shift speed (here, the target shift speed), the optimum shift speed determination means 1 sets a correction signal for executing the shift operation. As a result, the speed change mechanism 17 executes the speed change operation, and again, it becomes possible to travel at the most suitable speed according to the load condition of the vehicle and the road condition.

If the target shift speed and the optimum shift speed match, the target shift speed naturally becomes the optimum shift speed, and the shift operation to this target shift speed is performed. FIG.
In step S50, it is determined whether or not a jump shift-up command (for example, 4 steps → 6 steps) has been output. That is, in step S46, the final target speed is set as the target shift speed based on the shift map, but it is determined whether or not the target shift speed at this time is not a shift command for each shift step but a jump shift up command.

When the result of the determination in step S50 is false and it is determined that the jump shift up command is not output, the routine is ended and the process returns to the main routine of FIG. On the other hand, if the determination result of step S50 is true and it is determined that the jump shift-up command is output, the process proceeds to step S52.

In step S52, it is determined whether or not a predetermined time t3 (for example, 3 seconds) has elapsed since the jump shift-up command was output and the jump shift flag fj described later has a value of 1. If the determination result is false, that is, until the predetermined time t3 (for example, 3 seconds) elapses immediately after the jump shift-up command is output, the next step S
In 54, it is assumed that the final target stage is simply upshifted by one stage from the current stage, regardless of the jump shift up command. As a result, the jump shift-up is the predetermined time t3.
It is prohibited (for example, 3 seconds), and the deterioration of the shift feeling is suitably prevented. Then, in step S56, the jump shift flag fj is set to the value 1 in order to store the fact that the final target stage is shifted up by one stage from the current stage.

Then, the routine is executed next time, and a predetermined time t3 (for example, 3 seconds) has elapsed since the jump shift-up command was output, and the jump shift flag fj has the value 1 according to the determination in step S52. If it is determined that the jump shift flag fj is reset to 0 in step S58. As described above in detail, in the shift control device for an automatic transmission for a vehicle according to the present invention, learning is performed based on the back propagation learning method using a neural network, so that a driver that is slightly different for each driver can be detected. The optimum shift map according to the driver's preference is selected from a plurality of shift maps in consideration of the taste, and the target shift speed obtained by this shift map is further corrected by the desired fuzzy rule using the vehicle load degree αVL as a parameter. Therefore, the optimum shift speed can be appropriately determined by reflecting not only the driver's taste but also the driver's intention. Therefore, in the shift control device for the vehicle automatic transmission, although the automatic transmission is used,
It is possible to perform shift control extremely close to shift up and shift down of a manual transmission, which is mainly a manual operation, and it is possible to significantly improve drivability.

Further, a neural network for performing learning control preferred by the driver is subjected to learning based on the M range and a first neural network for performing learning based on the D range operation according to the use frequency FMU of the M range. The learning control at the time of upshift is performed separately from the second neural network, and the learning control at the time of downshift is individually performed by another third neural network, which makes the neural network complicated. It is possible to easily learn the driver's liking without any trouble, and to always set the optimum shift speed satisfactorily to smoothly perform the shift control of the automatic transmission.

[0146]

As described above, according to the shift control device for an automatic transmission for a vehicle of the first aspect of the present invention, there is provided a manual mode in which the shift stage is switched by a driver's operation and a driving mode connected to the engine. In a shift control device for an automatic transmission for a vehicle equipped with an automatic mode in which a shift speed is automatically switched according to a shift mode in at least one of a manual mode and an automatic mode as a parameter, a driver's shift preference is reflected by a neural network. Learning means for performing the learned shift pattern, target shift speed setting means for setting the target shift speed based on the output from the learning means and the operating state of the vehicle in the automatic mode, and shift control of the automatic transmission based on the target shift speed. Since it is equipped with a shift control means for performing the shift control, the shift pattern learning reflecting the driver's shift preference is favorable. Can be done, it can be preferably set the target gear position based on the driving state of the vehicle at the output and the automatic mode by the learning. As a result, the shift control of the automatic transmission can be approximated to the shift operation of the manual transmission.

Further, according to the shift control device for an automatic transmission for a vehicle of claim 2, the learning means selects one of the manual mode and the automatic mode in accordance with the frequency of shift operation by the driver in the manual mode. Since the shift state of 1 is selected and used as a parameter, good shift pattern learning can be performed by using one of the shift modes of the manual mode and the automatic mode as a parameter according to the frequency of shift operation by the driver in the manual mode.

According to the shift control device for a vehicle automatic transmission of the third aspect, the learning means uses the shift state in the manual mode as a parameter when the frequency of shift operation by the driver in the manual mode is larger than a predetermined value. Therefore, when the frequency of gear shift operation by the driver in the manual mode is higher than a predetermined value, good gear shift pattern learning can be performed using the gear shift state in the manual mode as a parameter.

According to the shift control device for an automatic transmission for a vehicle of claim 4, the engine speed detecting means for detecting the engine speed of the engine is further provided, and the learning means is
As the gear shift state in the manual mode, the gear shift pattern learning is performed using at least the engine speed at the time of the gear shift operation of the driver as a parameter. Shift pattern learning can be implemented.

Further, according to the shift control device for an automatic transmission for a vehicle of claim 5, the learning means uses the shift state in the automatic mode as a parameter when the frequency of shift operation by the driver in the manual mode is smaller than a predetermined value. Because
When the frequency of shift operation by the driver in the manual mode is smaller than a predetermined value, good shift pattern learning can be performed using the shift state in the automatic mode as a parameter.

Further, according to the shift control device of the automatic transmission for a vehicle of claim 6, the accelerator opening detecting means for detecting the accelerator opening of the engine is further provided, and the learning means is at least a shift state in the automatic mode. Since the gear shift pattern learning is performed using the accelerator opening at the time of gear shift switching as a parameter, it is possible to perform a good gear shift pattern learning using at least the accelerator opening at gear shift as a parameter in the gear shift state in the automatic mode.

According to the shift control device for an automatic transmission for a vehicle of claim 7, since the learning means performs the shift pattern learning by including the current shift pattern information in the parameter,
Good shift pattern learning can be performed using the current shift pattern information as a reference parameter for shift pattern learning. Further, according to the shift control device for an automatic transmission for a vehicle of claim 8, the vehicle further comprises a flat road detecting means for detecting whether or not the vehicle is traveling on a flat road, and the learning means allows the vehicle to drive on a flat road. Since the shift pattern learning is performed while the vehicle is running, the shift pattern learning can be favorably performed when the vehicle is running on a flat road where the driver's preference is likely to appear.

According to the shift control device for an automatic transmission for a vehicle of claim 9, the target shift speed setting means has a plurality of types of shift maps having different shift patterns, and the target shift speed setting means has a plurality of shift maps according to the output from the learning means. The optimum map is selected from a plurality of types of shift maps, and the target shift speed is set based on this optimum map and the operating state of the vehicle. Therefore, the optimum map is selected from a plurality of types of shift maps according to the output from the learning means. The target shift speed can be favorably set based on this optimum map and the operating state of the vehicle.

According to the shift control device for an automatic transmission for a vehicle of claim 10, the vehicle further comprises flat road detecting means for detecting whether or not the vehicle is traveling on a flat road, and the target shift speed setting means is When the vehicle is not traveling on a flat road, the target shift speed is set based on the previously selected shift map and the operating state of the vehicle. Therefore, when the vehicle is not traveling on a flat road where the driver's preference is likely to appear. The target shift speed can be favorably set based on the previously selected shift map and the operating state of the vehicle.

According to the shift control device for an automatic transmission for a vehicle of claim 11, the learning means uses a neural network as a parameter for the shift state in at least one of the manual mode and the automatic mode when the driver shifts up. Since the shift pattern learning that reflects the shift preference is performed, the shift pattern learning that reflects the shift preference at the time of the driver's upshift can be satisfactorily performed by the neural network using the shift state in at least one of the manual mode and the automatic mode as a parameter. it can.

According to the shift control device for an automatic transmission for a vehicle of claim 12, vehicle speed detecting means for detecting a vehicle speed,
Brake operating state detecting means for detecting the operating state of the brake is further provided, and the learning means reflects the shift preference of the driver during downshifting when the brake operating state is ON and the reduction amount of the vehicle speed is equal to or more than a predetermined amount. Since the gear shift pattern learning is performed, when the brake operating state is ON and the reduction amount of the vehicle speed is equal to or more than the predetermined amount, the gear shift pattern learning that reflects the driver's shift preference at the time of downshifting can be performed. .

According to the shift control device for a vehicle automatic transmission of the thirteenth aspect, the learning means shifts to the downshift side of the driver in the manual mode at least until the reduction amount of the vehicle speed reaches the predetermined amount. Since the shift pattern learning is performed using the shift operation frequency as a parameter, a good shift pattern learning is performed using the shift operation frequency to the downshift side of the driver in the manual mode at least until the vehicle speed reduction amount reaches the predetermined amount as a parameter. Can be implemented.

According to the shift control device for an automatic transmission for a vehicle of claim 14, the learning means changes from the automatic mode by the driver to the manual mode at least until the reduction amount of the vehicle speed reaches a predetermined amount. Since the shift pattern learning is performed using the mode switching frequency as a parameter, good shift pattern learning is performed using the mode switching frequency from the auto mode to the manual mode by the driver at least until the vehicle speed reduction amount reaches the predetermined amount as a parameter. it can.

Further, according to the shift control device for an automatic transmission for a vehicle of claim 15, the shift control means includes fuzzy control means for correcting the target shift stage by using fuzzy inference based on the vehicle information. The fuzzy inference is performed based on the vehicle information, and the target shift speed can be appropriately corrected according to the result of the fuzzy inference, and good shift control can be realized.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a main configuration of a shift control device for an automatic transmission for a vehicle according to an embodiment of the present invention.

FIG. 2 is a configuration diagram showing an overall configuration of a shift control device for an automatic transmission for a vehicle as an embodiment of the present invention.

FIG. 3 is a diagram showing a select pattern of a change lever.

FIG. 4 is a graph showing the relationship between accelerator opening and VA.

FIG. 5 is a graph showing shift map # 1 in economy mode.

FIG. 6 is a graph showing shift map # 2 in economy mode.

FIG. 7 is a graph showing shift map # 3 in economy mode.

FIG. 8 is a graph showing shift map # 1 in a normal mode.

FIG. 9 is a graph showing shift map # 2 in the normal mode.

FIG. 10 is a graph showing shift map # 3 in the normal mode.

FIG. 11 is a graph showing shift map # 1 in power mode.

FIG. 12 is a graph showing shift map # 2 in power mode.

FIG. 13 is a graph showing shift map # 3 in power mode.

FIG. 14 is a graph showing the relationship between rack position and SRC.

FIG. 15 is a diagram showing a configuration of a low-pass filter.

FIG. 16 is a flowchart showing a filter processing procedure of a low-pass filter.

FIG. 17 is a diagram showing a characteristic of a vehicle load degree as a shift control parameter on a flat road.

FIG. 18 is a diagram showing a characteristic of a vehicle load degree as a shift control parameter on a 10% uphill road.

FIG. 19 is a diagram showing a characteristic of a vehicle load degree as a shift control parameter on a 10% downhill road.

FIG. 20 is a diagram showing a membership function of a vehicle load degree.

FIG. 21 is a diagram showing a membership function of accelerator opening.

FIG. 22 is a diagram showing a membership function of accelerator opening change.

FIG. 23 is a diagram showing a membership function of driver's intention.

FIG. 24 is a diagram for explaining fuzzy inference.

FIG. 25 is a diagram showing a fuzzy rule.

FIG. 26 is a flowchart showing a main routine of shift control.

27 is a flowchart showing a learning control routine in FIG. 26. FIG.

FIG. 28 is a diagram showing a first neural network.

FIG. 29 is a diagram showing a second neural network.

FIG. 30 is a diagram showing a third neural network.

FIG. 31 is a graph showing the relationship between judgment outputs O4 and O′4 and a selection map.

FIG. 32 is a graph showing the relationship between the judgment output O ″ 4 and the possibility of downshifting.

FIG. 33 is a graph showing a shift-down regulation map corresponding to shift map # 1 in economy mode.

FIG. 34 is a part of a flowchart showing a subroutine of target shift speed correction in FIG. 26.

FIG. 35 is the remaining part of the flowchart showing the target gear shift correction subroutine continued from FIG. 34;

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Optimal shift speed determination means (shift control means) 2 Vehicle load degree calculation means 3 Target shift speed setting means 3A Storage means 3B Learning formula selection means (learning means) 4 Engine torque calculation means 5 Driving force calculation means 6 Air resistance calculation means 7 Straight Flat Road Empty Vehicle Equivalent Acceleration Calculating Means 8 Subtracting Means 11 Diesel Engine (Engine) 17 Gear Transmission (Transmission Mechanism) 27 Engine Rotation Sensor (Engine Rotation Speed Detection Means) 61 Change Lever 63 Gear Shift Selection Switch 65 Gear Shift Unit 71 Control Unit 79 Vehicle speed sensor (vehicle speed detecting means) 81 Accelerator pedal 85 Accelerator opening sensor (accelerating opening detecting means) 87 Brake sensor (brake operating state detecting means)

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI technical display area F16H 59:42 59:44 59:54 59:66

Claims (15)

[Claims] 1. A shift control of an automatic transmission for a vehicle, which is connected to an engine and has a manual mode in which a shift stage is switched by a driver's operation and an automatic mode in which a shift stage is automatically switched according to a driving state of a vehicle. In the device, learning means for learning a shift pattern reflecting a driver's shift preference by a neural network using a shift state in at least one of the manual mode and the automatic mode as a parameter, and output from the learning means and in the auto mode. A target gear position setting means for setting a target gear speed based on the operating state of the vehicle, and a gear shift control means for performing gear shift control of the automatic transmission based on the target gear speed. Gear change control device for transmission. 2. The learning means selects one of the manual mode and the automatic mode as a parameter in accordance with the frequency of shift operation by the driver in the manual mode. The shift control device for an automatic transmission for a vehicle according to claim 1. 3. The vehicle according to claim 2, wherein the learning means uses a shift state in the manual mode as a parameter when the frequency of shift operations by the driver in the manual mode is larger than a predetermined value. Gear shift control device for automatic transmission. 4. The engine rotation speed detection means for detecting the engine rotation speed of the engine is further provided, and the learning means uses at least the engine rotation speed at the time of a shift operation of a driver as a parameter as a shift state in the manual mode. The shift control device for an automatic transmission for a vehicle according to claim 3, wherein the shift pattern learning is performed. 5. The vehicle according to claim 2, wherein the learning means uses the shift state in the automatic mode as a parameter when the frequency of the shift operation by the driver in the manual mode is smaller than a predetermined value. Gear shift control device for automatic transmission. 6. An accelerator opening detection means for detecting an accelerator opening of the engine is further provided, and the learning means uses the accelerator opening as a parameter at least when a shift stage is set as a shift state in the automatic mode. The shift control device for an automatic transmission for vehicles according to claim 5, wherein shift pattern learning is performed. 7. The shift control of an automatic transmission for a vehicle according to claim 1, wherein the learning means performs the shift pattern learning by including a current shift pattern information in a parameter. apparatus. 8. The vehicle further comprises flat road detection means for detecting whether or not the vehicle is traveling on a flat road, and the learning means carries out the shift pattern learning when the vehicle is traveling on the flat road. A shift control device for an automatic transmission for a vehicle according to any one of claims 1 to 7, characterized in that. 9. The target shift speed setting means has a plurality of types of shift maps having different shift patterns, selects an optimum map from the plurality of types of shift maps according to the output from the learning means, and 8. The shift control device for an automatic transmission for a vehicle according to claim 1, wherein the target shift speed is set based on an optimum map and a driving state of the vehicle. 10. The vehicle further comprises flat road detection means for detecting whether or not the vehicle is traveling on a flat road, and the target shift speed setting means, when the vehicle is not traveling on the flat road, the previously selected shift. The shift control device for an automatic transmission for a vehicle according to claim 9, wherein the target shift speed is set based on a map and a driving state of the vehicle. 11. The learning means performs shift pattern learning that reflects a shift preference of a driver during upshifting by the neural network using a shift state in at least one of the manual mode and the automatic mode as a parameter. Claims 1 to 1
0. A shift control device for an automatic transmission for a vehicle according to 0. 12. A vehicle speed detecting means for detecting a vehicle speed, and a brake operating state detecting means for detecting an operating state of a brake, wherein the learning means has the brake operating state turned on and the reduction amount of the vehicle speed. The gear shift control device for an automatic transmission for a vehicle according to claim 1, wherein the gear shift pattern learning reflecting the driver's gear shift preference at the time of downshifting is performed when is greater than or equal to a predetermined amount. 13. The learning means carries out the shift pattern learning using at least a frequency of a shift operation to a downshift side of a driver in the manual mode until a reduction amount of the vehicle speed reaches the predetermined amount as a parameter. 13. A shift control device for an automatic transmission for a vehicle according to claim 12, wherein: 14. The learning means carries out the shift pattern learning using as a parameter the mode switching frequency from the automatic mode to the manual mode by the driver until at least the reduction amount of the vehicle speed reaches the predetermined amount. 13. A shift control device for an automatic transmission for a vehicle according to claim 12, wherein: 15. The shift control means includes fuzzy control means for correcting the target shift speed by using fuzzy inference based on vehicle information.
15. A shift control device for a vehicle automatic transmission according to any one of claims 14 to 14.