CN107161150B - A method and device for controlling the starting of a vehicle - Google Patents

Abstract

The present invention provides a method and device for controlling the start of a vehicle, wherein the method includes acquiring the opening value of the accelerator pedal pressed by the driver multiple times within a preset time length before the start of the vehicle; The ratio of the acquisition time length of all the opening values greater than or equal to each opening value and the preset time length is respectively determined; according to the determined ratio of multiple time lengths, the vehicle is controlled to start. In the present invention, the used acquisition time length can reflect the starting intention of the driver, therefore, when the vehicle is controlled to start, the starting intention of the driver is considered, so that the combination of the throttle valve of the engine and the automatic clutch and the driver's acceleration The operation of the pedals is matched, thereby reducing the phenomenon of running and shaking when the vehicle starts, and realizing the smooth start of the vehicle.

Description

A method and device for controlling the starting of a vehicle

technical field

The present invention relates to the technical field of automobiles, in particular to a method and device for controlling the starting of a vehicle.

Background technique

When a vehicle is started, especially when a vehicle equipped with an Automated Mechanical Transmission (AMT) is started, the throttle opening of the engine and the combination of the automatic clutch must cooperate with each other, so as to achieve a smooth start.

In the prior art, when the vehicle is started, it generally can only start according to a predetermined mode, so that the starting mode cannot respond to the driver's starting intention, that is, the combination of the throttle opening of the engine and the automatic clutch cannot respond to the driver's intention. The operation of the accelerator pedal makes the vehicle prone to problems such as vehicle movement and vibration when starting, which makes it impossible to achieve a smooth start.

To sum up, in the prior art, when the vehicle is started, problems such as vehicle movement and vibration are prone to occur, thus making it impossible to achieve a smooth start of the vehicle.

Contents of the invention

In view of this, the purpose of the embodiments of the present invention is to provide a method and device for controlling the starting of a vehicle, so as to solve or try to alleviate the above-mentioned problems.

In a first aspect, an embodiment of the present invention provides a method for controlling the start of a vehicle, wherein the method includes:

Before the vehicle starts, obtain the opening value of the accelerator pedal pressed by the driver multiple times within a preset period of time;

According to a plurality of preset opening values, respectively determine the ratio of the acquisition time length of all opening values greater than or equal to each of the opening values to the preset time length;

According to the determined ratios, the vehicle is controlled to start.

In combination with the first aspect, the embodiment of the present invention provides a first possible implementation of the above first aspect, wherein, according to the preset multiple opening values, respectively determine a value greater than or equal to each of the opening The ratio of the acquisition time length of all opening values taken to the value to the preset time length includes:

According to a plurality of preset opening values, respectively determine the number of all opening values greater than or equal to each of the opening values;

calculating the ratio of each said number to the number of opening values acquired within the preset time length;

The ratio of the numbers is determined as the ratio of the acquisition time length to the preset time length.

In combination with the first aspect, the embodiment of the present invention provides a second possible implementation of the above first aspect, wherein the controlling the vehicle to start according to the determined multiple ratios includes:

Calculate the driver's starting intention value according to the weight conversion coefficient of the ratio and the pre-established neural network model;

determining the starting mode of the vehicle according to the starting intention value of the driver;

The vehicle is controlled to start according to the starting mode.

With reference to the second possible implementation of the first aspect, the embodiment of the present invention provides a third possible implementation of the first aspect above, wherein, according to the value of the driver's intention to start, determine the The starting mode, including:

Select a starting mode corresponding to the driver's starting intention value;

or,

Determine the driver's starting intention according to the driver's starting intention value and the mapping relationship between the preset starting intention value and the starting intention;

Select the starting mode that matches the driver's starting intention.

In combination with the second possible implementation of the first aspect or the third possible implementation of the first aspect, the embodiment of the present invention provides a fourth possible implementation of the first aspect above, wherein, according to the following steps Build the neural network model:

Set up the input layer, hidden layer and output layer of described neural network model;

Obtain a pre-trained sample set, the pre-trained sample set includes a plurality of training samples, each of which includes multiple opening values of the accelerator pedal and the driver's starting intention value;

According to the multiple opening values of the accelerator pedal and the driver's starting intention value, determine the first conversion weight coefficient from the output layer to the hidden layer and the second conversion weight coefficient from the hidden layer to the input layer conversion weight factor;

The neural network model is established according to the first conversion weight coefficient, the second conversion weight coefficient, the input layer, the hidden layer and the output layer.

In a second aspect, an embodiment of the present invention provides a device for controlling vehicle starting, wherein the device includes:

The first acquisition module is used to acquire the opening value of the accelerator pedal pressed by the driver multiple times within a preset time length before the vehicle starts;

The first determination module is configured to determine, according to a plurality of preset opening values, the ratio of the acquisition time length of all opening values greater than or equal to each of the opening values to the preset time length;

A control module, configured to control the vehicle to start according to the determined multiple ratios.

With reference to the second aspect, the embodiment of the present invention provides a first possible implementation of the second aspect above, wherein the first determination module includes:

The first determination unit is configured to respectively determine the number of all opening values greater than or equal to each of the opening values according to a plurality of preset opening values;

A first calculation unit, configured to calculate the ratio of each said number to the number of opening values acquired within the preset time length;

The second determining unit is configured to determine the ratio of the number as the ratio of the collection time length to the preset time length.

With reference to the second aspect, the embodiment of the present invention provides a second possible implementation of the above second aspect, wherein the control module includes:

The second calculation unit is used to calculate the driver's starting intention value according to the ratio and the weight conversion coefficient of the pre-established neural network model;

A third determining unit, configured to determine the starting mode of the vehicle according to the driver's starting intention value;

A control unit, configured to control the vehicle to start according to the starting mode.

With reference to the second possible implementation of the second aspect, the embodiment of the present invention provides a third possible implementation of the first aspect above, wherein the third determining unit is specifically configured to:

Select a starting mode corresponding to the driver's starting intention value;

or,

Determine the driver's starting intention according to the driver's starting intention value and the mapping relationship between the preset starting intention value and the starting intention;

Select the starting mode that matches the driver's starting intention.

In combination with the second possible implementation of the second aspect or the third possible implementation of the second aspect, the embodiment of the present invention provides a fourth possible implementation of the second aspect above, wherein the device Also includes:

The first building module is used to set up the input layer, hidden layer and output layer of the neural network model;

The second acquisition module is used to acquire a pre-trained sample set, the pre-trained sample set includes a plurality of training samples, and each of the training samples includes a plurality of opening values of the accelerator pedal and a driver's starting intention value;

The second determination module is used to determine the first conversion weight coefficient from the output layer to the hidden layer and the first conversion weight coefficient from the hidden layer to a second conversion weight coefficient of the input layer;

A second establishing module, configured to establish the neural network model according to the first conversion weight coefficient, the second conversion weight coefficient, the input layer, the hidden layer and the output layer.

In the method and device for controlling the start of the vehicle provided in the embodiments of the present invention, the length of acquisition time used can reflect the driver's start intention. Therefore, when the vehicle is controlled to start, the driver's start intention is considered, so that the engine's The combination of the throttle valve and the automatic clutch matches with the driver's operation on the accelerator pedal, thereby reducing the phenomenon of shuddering and shaking when the vehicle starts, and realizing the smooth start of the vehicle.

In order to make the above-mentioned objects, features and advantages of the present invention more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus It should be regarded as a limitation on the scope, and those skilled in the art can also obtain other related drawings based on these drawings without creative work.

FIG. 1 shows a flow chart of a method for controlling a vehicle to start provided by an embodiment of the present invention;

Fig. 2 shows the flow chart of controlling the starting of the vehicle in the method for controlling the starting of the vehicle provided by the embodiment of the present invention;

Fig. 3 shows the variation curve of throttle opening and clutch engagement over time in the method for controlling vehicle starting provided by an embodiment of the present invention;

Fig. 4 shows a schematic diagram of the first structure of the control vehicle start provided by the embodiment of the present invention;

Fig. 5 is a schematic diagram of a second structure for controlling vehicle starting provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is a part of embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

It is considered that, in the prior art, when the vehicle is started, problems such as vehicle movement and vibration are prone to occur, thus making it impossible to achieve a smooth start of the vehicle. Based on this, the embodiments of the present invention provide a method and device for controlling the starting of a vehicle, which will be described below through the embodiments.

Referring to FIG. 1 , an embodiment of the present invention provides a method for controlling the start of a vehicle. The method includes steps S110-S130, specifically as follows:

S110, before the vehicle starts, acquire the opening value of the accelerator pedal pressed by the driver multiple times within a preset time length;

S120. According to a plurality of preset opening values, respectively determine ratios of acquisition time lengths of all opening values greater than or equal to each opening value to a preset time length.

S130. Control the vehicle to start according to the determined ratios.

Wherein, when the driver depresses the accelerator pedal, the opening degree of the accelerator pedal will gradually increase, and before the driver depresses the accelerator pedal, the opening degree of the accelerator pedal is zero.

In the embodiment of the present invention, a position sensor is provided on the accelerator pedal of the vehicle, and the position sensor is used to collect the opening value of the accelerator pedal. Specifically, what the position sensor collects is the voltage value on the accelerator pedal, and the voltage value is used for To characterize the opening of the accelerator pedal, according to the conversion relationship between the voltage value and the opening of the accelerator pedal, the opening value corresponding to each voltage value can be obtained, so the output from the position sensor is the opening of the accelerator pedal .

When the vehicle is powered on, the position sensor starts to collect the opening value of the accelerator pedal.

The execution subject of the embodiment of the present invention is the controller of the AMT.

In the above step S110, before the vehicle starts and after the vehicle is powered on, the controller will obtain the opening value of the accelerator pedal pressed by the driver multiple times within a preset time length. Obtain the opening value of the accelerator pedal once from the position sensor.

Wherein, each interval of the above-mentioned certain time may be an interval of 1 ms, or other values, and the specific time value of the above-mentioned interval may be set according to the actual application scenario, and the embodiment of the present invention does not limit the specific value of the above-mentioned interval time.

Preferably, the preset time length is 600 ms, which is within 600 ms from when the driver depresses the accelerator pedal.

In the above step S120, according to a plurality of preset opening values, respectively determine the ratio of the acquisition time length of all opening values greater than or equal to each opening value to the preset time length, specifically including:

According to a plurality of preset opening values, respectively determine the number of all opening values greater than or equal to each opening value;

Calculate the ratio of each of the above numbers to the number of opening values obtained within the preset time length;

The ratio of the above numbers is determined as the ratio of the above collection time length to the preset time length.

In the above step S120, the preset multiple opening values can be 10, 15 or 20, and the specific number can be set according to the actual application scenario. The embodiment of the present invention does not set the preset opening values. The specific number of values is limited.

Generally, when the vehicle starts, the accelerator pedal that the driver usually depresses has a maximum opening value of 20%. Therefore, in the embodiment of the present invention, 0-20% can be divided evenly, and multiple opening values can be obtained. Each opening value corresponds to a grade, so that the corresponding opening value of each grade can be determined. For example, if 0-20% is divided into 10 grades on average, the value corresponding to the first grade can be 2%, the value corresponding to the second grade can be 4%, and the value corresponding to the third grade can be 6%, and so on, determine the opening value corresponding to each grade.

Of course, the above is just a method for setting the opening value. In the embodiment of the present invention, 0-20% can be equally divided, or 0-30% can be equally divided. The above-mentioned 20% is just one of the implementations. For example, in practical applications, any value greater than 20% can also be selected as a maximum opening value for the above-mentioned division. Specifically, when dividing, a selected maximum opening value for dividing may be set according to actual applications, which is not limited in this embodiment of the present invention.

In the above step S120, respectively determining the corresponding collection time lengths of all opening values greater than or equal to each opening value can be achieved in the following manner, specifically including:

Here we still take the opening value corresponding to the above average division level as an example for illustration. The opening value corresponding to the first level is 2%, the opening value corresponding to the second level is 4%, and the third level The opening value corresponding to each level is 6%, and by analogy, the opening value corresponding to each level can be determined.

In the embodiment of the present invention, for example, 10 opening values are obtained in step S110, which are 1%, 1.2%, 2%, 2.1%, 2.5%, 3%, 3.6%, 4.5%, and 5.2%. , 5.6%, according to the opening value set in the above example, it can be determined that all opening values greater than or equal to the first opening value are 2%, 2.1%, 2.5%, 3%, 3.6%, 4.5% %, 5.2%, 5.6%, all the opening values greater than or equal to the second opening value are 4.5%, 5.2%, 5.6%, and there are eight opening values greater than or equal to 2%, and The number of opening values acquired within the preset time is 10, therefore, 8/10=0.8 can be determined as the acquisition time length of all opening values greater than or equal to the first opening value and the preset The ratio of the length of time. In the same way, the ratios of the acquisition time lengths of all the opening values greater than or equal to each opening value to the preset time length are respectively calculated, and multiple ratios can be determined through the above method.

Of course, the above is just one of the methods to determine the above ratio. In addition, it can also be realized in the following ways:

For example, in step S110, 10 opening values are obtained, which are 1%, 1.2%, 2%, 2.1%, 2.5%, 3%, 3.6%, 4.5%, 5.2%, and 5.6%, according to the above example If the opening value is set, it can be determined that all opening values greater than or equal to the first opening value are 2%, 2.1%, 2.5%, 3%, 3.6%, 4.5%, 5.2%, 5.6% These eight, all opening values greater than or equal to the second opening value are 4.5%, 5.2%, 5.6%, and there are eight opening values greater than or equal to 2%. If the acquisition time interval is 1ms, it can be determined that the acquisition time length greater than or equal to the first opening value is 8ms, and the ratio of 8ms to the preset time length can be calculated.

Therefore, a series of ratios can be obtained in the above step S120.

Referring to Figure 2, in step S130, according to the determined ratios, the vehicle is controlled to start, including steps S210-S230, as follows:

S210, calculate the driver's starting intention value according to the above ratio and the weight conversion coefficient of the pre-established neural network model;

S220. Determine the starting mode of the vehicle according to the starting intention value of the driver;

S230, control the vehicle to start according to the above starting mode.

In the embodiment of the present invention, the aforementioned pre-established neural network model is a BP (Back Propagation) neural network model.

The neural network model in the embodiment of the present invention is divided into input layer, hidden layer and output layer three parts, and input layer comprises a plurality of input nodes, and hidden layer comprises a plurality of input nodes, and the output node of output layer is also a plurality of, preferred , the output layer of the neural network model used in the embodiment of the present invention has two output nodes, of course, the specific value of the number of nodes in each layer can be set according to the actual situation.

In the embodiment of the present invention, according to the above-mentioned series of ratios and the weight conversion coefficient of the neural network model, the driver's starting intention value is calculated by the following formula:

Among them, in the above formula, w _ij represents the transformation weight coefficient between the input node i and the hidden node j of the neural network model, v _jk represents the transformation weight coefficient between the hidden node and the output node of the neural network model, and i represents is the input node of the input layer, i=1,2,...,N, N represents the number of the above ratio, j represents the node of the hidden layer, the number of nodes of the hidden layer can be set according to the actual situation, in In the embodiment of the present invention, M represents the number of nodes in the hidden layer, j=1, 2,..., M, α is the preset threshold of the hidden layer, β is the preset threshold of the output layer, p _i represents the ratio calculated above, s _i represents the activation value of the hidden layer node, o _k is the activation value of the output layer node, b _j represents the output value of the hidden layer, and y _k represents the output layer output value.

In the above formula, the function f is defined as follows:

In the embodiment of the present invention, the output value y _k of the above output layer represents the driver's starting intention value, and, in the embodiment of the present invention, the value of k is 1 and 2, that is, the output of the neural network model The value is [y ₁ ,y ₂ ].

Specifically, the above-mentioned starting mode of the vehicle is determined according to the driver's starting intention value, which specifically includes the following two situations:

In the first case,

Select the starting mode corresponding to the driver's starting intention value;

In this case, the mapping relationship between the starting intention value and the vehicle starting mode is established in advance. In this way, when the starting intention value of the driver is determined, according to the starting intention value, the above mapping relationship is used to find the corresponding The starting mode of the vehicle corresponding to the starting intention value, and the found starting mode is used as the starting mode of the vehicle.

In the second case,

Determine the driver's starting intention according to the driver's starting intention value and the mapping relationship between the preset starting intention value and the starting intention;

Select the launch mode that matches the driver's launch intention.

In this case, what is established in advance is the mapping relationship between the starting intention and the starting mode. Therefore, it is first necessary to determine the starting intention of the driver corresponding to the starting intention value according to the calculated starting intention value of the driver. Specifically, the driver's start intention includes slow start intention, medium start intention and quick start intention, and different [y ₁ , y ₂ ] values correspond to different start intentions, for example, [0,1] can correspond to slow start Intent, [1,0] corresponds to medium start intention, [1,1] corresponds to emergency start intention, [0,0] corresponds to no start intention.

In the embodiment of the present invention, the mapping relationship between the starting intention value and the starting intention is preset. According to the calculated starting intention value and the mapping relationship, the driver's starting intention can be determined. Since the calculated starting intention Values may have decimal places, so the calculated starting intent value is rounded to 0 or 1.

After the driver's starting intention is determined, the starting mode matching the driver's starting intention is determined according to the driver's starting intention and the pre-established mapping relationship between the starting intention and the starting mode.

After the starting mode matching the driver's starting intention is determined, the vehicle is controlled to start according to the starting mode.

Referring to Fig. 3, it is the change curve of the throttle opening and the clutch combination over time corresponding to each starting intention, and Fig. 3 (a) is the change curve of the throttle opening and the clutch combination over time corresponding to the slow start intention, Figure 3(b) is the time-varying curve of the throttle opening and the clutch corresponding to the moderate starting intention, and Figure 3(c) is the changing curve of the throttle opening and the clutch corresponding to the sudden starting intention.

In addition, in the method provided by the embodiment of the present invention, multiple opening levels and the value range corresponding to each opening level can also be preset, and each opening level can be determined according to the value range corresponding to each opening level. The opening value contained in each opening level; according to the opening value contained in each opening level, determine the difference between the collection time corresponding to the lowest opening value and the collection time corresponding to the highest opening value in each opening level. The second acquisition time length between, then calculate the second ratio between the second acquisition time length and the preset acquisition time length, and use the second ratio as the input value of the pre-established neural network model to determine the driver's starting intention , and control the vehicle to start according to the driver's starting intention.

Specifically, the neural network model adopted in the embodiment of the present invention is obtained through the establishment of the following steps (1)-step (4):

(1) Establish the input layer, hidden layer and output layer of the neural network;

(2) Obtain a pre-trained sample set, the pre-trained sample set includes a plurality of training samples, each training sample includes a plurality of opening values of the accelerator pedal and the starting intention value of the driver;

(3) According to a plurality of opening values of the above-mentioned accelerator pedal and the starting intention value of the driver, determine the first conversion weight coefficient from the output layer to the hidden layer and the second conversion weight coefficient from the hidden layer to the input layer;

(4) Establish the above neural network model according to the first conversion weight coefficient, the second conversion weight coefficient, the input layer, the hidden layer and the output layer.

In the embodiment of the present invention, the input layer, the hidden layer and the output layer of the neural network model established, in the embodiment of the present invention, what establishes is a three-layer neural network model, after that, according to the sample set obtained in the vehicle starting experiment The first conversion weight coefficient from the output layer to the hidden layer in the above neural network model, and the second conversion weight coefficient from the hidden layer to the output layer are calibrated to determine the first conversion of the neural network model used in the embodiment of the present invention The weight coefficient and the second conversion weight coefficient, the specific process is as follows:

Firstly, a sample set is obtained by conducting a large number of vehicle starting experiments. The sample set includes multiple training samples, and each training sample includes the value of the driver's starting intention and the opening of the accelerator pedal when the driver operates the accelerator pedal when starting. value;

Adopt the same method as above-mentioned step S120 to process the opening value of the above-mentioned accelerator pedal, obtain a series of acquisition time lengths and the ratio between the entire acquisition time length of the opening value of the accelerator pedal when starting, and use the series The ratio is determined as the input value of the neural network, and a corresponding relationship between the input value and the output value (the driver's starting intention value) can be determined according to each training sample. Specifically, the input value of the neural network can be recorded as The output value of the neural network is recorded as Wherein, r represents the rth training sample. In the embodiment of the present invention, the number of input nodes in the input layer is set to 10, and the number of output nodes in the output layer is set to 2.

Afterwards, the activation value s _j and the output value b _j of the hidden layer nodes are calculated by the following formula;

Among them, in the above formula, Represents the activation value of the hidden layer node calculated using the rth training sample, Represents the output value of the hidden node calculated using the rth training sample, j represents the output node of the hidden layer, i represents the input node of the hidden layer, α ^r represents the preset hidden layer threshold, Indicates the conversion weight coefficient from the hidden layer to the input layer.

Calculate the activation value o _k and output value y _k of the output layer node by the following formula;

Among them, in the above formula, Represents the activation value of the output layer node calculated using the rth training sample, Represents the output value of the output layer node calculated using the rth training sample, k represents the output node of the output layer, β ^r represents the preset threshold of the output layer, Represents the conversion weight coefficient from the output layer to the hidden layer.

Afterwards, the correction errors of the output layer and the hidden layer are calculated by the following formula:

Among them, in the above formula Represents the correction error of the output layer calculated using the rth training sample, Represents the correction error of the hidden layer calculated using the rth training sample, and f' represents the derivative of the function f.

Next, the correction amount of the first conversion weight coefficient from the output layer to the hidden layer and the correction amount of the output layer threshold are calculated by the following formula;

Among them, in the above formula, Indicates the correction amount of the first conversion weight coefficient calculated by using the ^rth training sample, λ1 represents the feedback correction coefficient from the output layer to the hidden layer, and _Δβr represents the correction amount of the threshold value of the output layer.

Calculate the correction amount of the second conversion weight coefficient from the hidden layer to the input layer and the hidden layer threshold by the following formula;

Among them, in the above formula, Indicates the correction amount of the _second conversion weight coefficient calculated using the rth training sample, λ2 indicates the feedback correction coefficient from the hidden layer to the input layer, and Δα ^r indicates the correction value calculated using the rth training sample Amount of correction for hidden layer thresholding.

After the above training, the new first conversion weight coefficient and the second conversion weight coefficient, as well as the hidden layer threshold and the output layer threshold can be calculated,

Among them, in the above formula, Indicates the new second weight conversion coefficient, Represents the new first weight conversion coefficient, α ^r+1 represents the threshold of the new hidden layer, and β ^r+1 represents the threshold of the new output layer.

Finally, judge whether the correction errors of the above hidden layer and output layer meet the following conditions:

Wherein, in the above formula, I _th represents a preset error upper limit threshold.

If satisfied, the training process ends, and the Determined as the second weight conversion coefficient, the Determined as the first weight conversion coefficient, α ^r+1 is determined as the threshold of the hidden layer, β ^r+1 is determined as the threshold of the output layer, if not satisfied, add 1 to the above sample number r, and re-determine the first conversion weight coefficient, The second converts the weight coefficients and the threshold of the output layer, the threshold of the hidden layer.

After the first conversion weight coefficient, the second conversion weight coefficient and the threshold of the neural network model are determined, the neural network model is obtained.

In the method for controlling the starting of the vehicle provided by the embodiments of the present invention, the length of acquisition time used can reflect the starting intention of the driver. Therefore, when controlling the starting of the vehicle, the starting intention of the driver is considered, so that the engine's throttle valve and automatic The combination of the clutch is matched with the driver's operation on the accelerator pedal, thereby reducing the phenomenon of running and shaking when the vehicle starts, and realizing the smooth start of the vehicle.

Referring to Figure 4, an embodiment of the present invention also provides a device for controlling vehicle start, which is used to implement the method for controlling vehicle start provided by the embodiment of the present invention, specifically, the device may be a controller of an AMT vehicle , the device includes a first acquisition module 410, a first determination module 420 and a control module 430;

The above-mentioned first acquisition module 410 is used to acquire the opening value of the accelerator pedal pressed by the driver multiple times within a preset time length before the vehicle starts;

The above-mentioned first determination module 420 is configured to respectively determine the ratio of the acquisition time length of all opening values greater than or equal to each opening value to the preset time length according to a plurality of preset opening values;

The above-mentioned control module 430 is configured to control the vehicle to start according to the determined multiple ratios.

Wherein, as an embodiment, the ratio determined by the above-mentioned first determination module 420 is realized by the first determination unit, the first calculation unit and the second determination unit, specifically including:

The above-mentioned first determination unit is used to respectively determine the number of all opening values greater than or equal to each opening value according to a plurality of preset opening values; the above-mentioned first calculation unit is used to respectively calculate each A ratio of the above-mentioned number to the number of opening values acquired within a preset time length; the second determination unit is configured to determine the ratio of the above-mentioned number as the ratio of the above-mentioned acquisition time length to a preset time length.

Specifically, as shown in FIG. 5 , in the embodiment of the present invention, the above-mentioned control module 430 controls the vehicle to start according to the determined multiple ratios, which can be realized by the second calculation unit 431 , the third determination unit 432 and the control unit 433. Specifically include:

The second calculation unit 431 is used to calculate the driver's starting intention value according to the ratio and the weight conversion coefficient of the pre-established neural network model; the second determination unit 432 is used to determine the driver's starting intention value according to the driver's starting intention value. The starting mode of the vehicle; the control unit 433 is configured to control the vehicle to start according to the starting mode.

In the embodiment of the present invention, the above-mentioned third determination unit controls the above-mentioned vehicle to start according to the above-mentioned starting mode, which is specifically realized in the following two ways:

In the first case,

Select the starting mode corresponding to the starting intention value of the above-mentioned driver;

In the second case,

Determine the driver's starting intention according to the driver's starting intention value and the mapping relationship between the preset starting intention value and the starting intention;

Select the launch mode that matches the driver's launch intention.

Wherein, in the embodiment of the present invention, the establishment of the neural network model is realized by the first establishment module, the second acquisition module, the second determination module and the second establishment module, specifically including:

The above-mentioned first building module is used to build the input layer, hidden layer and output layer of the above-mentioned neural network model; the above-mentioned second acquisition module is used to obtain a pre-trained sample set, the pre-trained sample set includes a plurality of training samples, Each training sample includes multiple opening values of the accelerator pedal and the driver's starting intention value; the second determination module is used to determine the above output according to the multiple opening values of the accelerator pedal and the driver's starting intention value The first conversion weight coefficient from the layer to the hidden layer and the second conversion weight coefficient from the hidden layer to the input layer; the above-mentioned second building module is used for according to the above-mentioned first conversion weight coefficient, the above-mentioned second conversion weight coefficient, the above-mentioned input layer, The aforementioned hidden layer and output layer are used to establish the aforementioned neural network model.

In the device for controlling the starting of the vehicle provided in the embodiment of the present invention, the used acquisition time length can reflect the starting intention of the driver. Therefore, when controlling the starting of the vehicle, the starting intention of the driver is considered, so that the engine's throttle and The combination of the automatic clutch matches with the driver's operation on the accelerator pedal, thereby reducing the phenomenon of running and shaking when the vehicle starts, and realizing the smooth start of the vehicle.

The device for controlling the starting of the vehicle provided in the embodiment of the present invention may be specific hardware on the device or software or firmware installed on the device. The implementation principles and technical effects of the device provided by the embodiment of the present invention are the same as those of the foregoing method embodiment. For brief description, for the parts not mentioned in the device embodiment, reference may be made to the corresponding content in the foregoing method embodiment. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the above-mentioned method embodiments, and will not be repeated here.

In the embodiments provided in the present invention, it should be understood that the disclosed devices and methods may be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments provided by the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .

It should be noted that like numerals and letters denote similar items in the following drawings, therefore, once an item is defined in one drawing, it does not require further definition and explanation in subsequent drawings, In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions, and should not be construed as indicating or implying relative importance.

Finally, it should be noted that: the above-described embodiments are only specific implementations of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting them, and the scope of protection of the present invention is not limited thereto, although referring to the foregoing The embodiment has described the present invention in detail, and those skilled in the art should understand that any person familiar with the technical field can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention Changes can be easily imagined, or equivalent replacements can be made to some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. All should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (10)

1. A method for controlling a vehicle to start, characterized in that the method comprises: Before the vehicle starts, obtain the opening value of the accelerator pedal pressed by the driver multiple times within a preset period of time; According to a plurality of preset opening values, respectively determine the ratio of the acquisition time length of all opening values greater than or equal to each of the opening values to the preset time length; According to the determined ratios, the vehicle is controlled to start. 2. The method according to claim 1, wherein the acquisition time lengths of all opening values greater than or equal to each of the opening values are respectively determined according to a plurality of preset opening values The ratio to the preset time length includes: According to a plurality of preset opening values, respectively determine the number of all opening values greater than or equal to each of the opening values; calculating the ratio of each said number to the number of opening values acquired within the preset time length; The ratio of the numbers is determined as the ratio of the acquisition time length to the preset time length. 3. The method according to claim 1, wherein the controlling the vehicle to start according to the determined multiple ratios comprises: Calculate the driver's starting intention value according to the weight conversion coefficient of the ratio and the pre-established neural network model; determining the starting mode of the vehicle according to the starting intention value of the driver; The vehicle is controlled to start according to the starting mode. 4. The method according to claim 3, wherein the determining the starting mode of the vehicle according to the starting intention value of the driver comprises: Select a starting mode corresponding to the driver's starting intention value; or, Determine the driver's starting intention according to the driver's starting intention value and the mapping relationship between the preset starting intention value and the starting intention; Select the starting mode that matches the driver's starting intention. 5. according to the described method of claim 3 or 4, it is characterized in that, set up described neural network model according to the following steps: Set up the input layer, hidden layer and output layer of described neural network model; Obtain a pre-trained sample set, the pre-trained sample set includes a plurality of training samples, each of which includes multiple opening values of the accelerator pedal and the driver's starting intention value; According to the multiple opening values of the accelerator pedal and the driver's starting intention value, determine the first conversion weight coefficient from the output layer to the hidden layer and the second conversion weight coefficient from the hidden layer to the input layer conversion weight factor; The neural network model is established according to the first conversion weight coefficient, the second conversion weight coefficient, the input layer, the hidden layer and the output layer. 6. A device for controlling starting of a vehicle, characterized in that the device comprises: The first acquisition module is used to acquire the opening value of the accelerator pedal pressed by the driver multiple times within a preset time length before the vehicle starts; The first determination module is configured to determine, according to a plurality of preset opening values, the ratio of the acquisition time length of all opening values greater than or equal to each of the opening values to the preset time length; A control module, configured to control the vehicle to start according to the determined multiple ratios. 7. The device according to claim 6, wherein the first determining module comprises: The first determination unit is configured to respectively determine the number of all opening values greater than or equal to each of the opening values according to a plurality of preset opening values; A first calculation unit, configured to calculate the ratio of each said number to the number of opening values acquired within the preset time length; The second determining unit is configured to determine the ratio of the number as the ratio of the collection time length to the preset time length. 8. The device according to claim 6, wherein the control module comprises: The second calculation unit is used to calculate the driver's starting intention value according to the ratio and the weight conversion coefficient of the pre-established neural network model; A third determining unit, configured to determine the starting mode of the vehicle according to the driver's starting intention value; A control unit, configured to control the vehicle to start according to the starting mode. 9. The device according to claim 8, wherein the third determining unit is specifically configured to: Select a starting mode corresponding to the driver's starting intention value; or, Determine the driver's starting intention according to the driver's starting intention value and the mapping relationship between the preset starting intention value and the starting intention; Select the starting mode that matches the driver's starting intention. 10. The device according to claim 8 or 9, wherein the device further comprises: The first building module is used to set up the input layer, hidden layer and output layer of the neural network model; The second acquisition module is used to acquire a pre-trained sample set, the pre-trained sample set includes a plurality of training samples, and each of the training samples includes a plurality of opening values of the accelerator pedal and a driver's starting intention value; The second determination module is used to determine the first conversion weight coefficient from the output layer to the hidden layer and the first conversion weight coefficient from the hidden layer to a second conversion weight coefficient of the input layer; A second establishing module, configured to establish the neural network model according to the first conversion weight coefficient, the second conversion weight coefficient, the input layer, the hidden layer and the output layer.