Acceleration torque-limiting fuel-saving method based on big data analysis

Abstract

The present invention relates to the technical field of big data analysis. Disclosed is an acceleration torque-limiting fuel-saving method based on big data analysis. The method comprises the following steps: step S101, acquiring a data collection time period for a vehicle; step S102, acquiring driving data of the vehicle at a preset time interval within the data collection time period; step S103, preprocessing the driving data of the vehicle; step S104, on the basis of the preprocessed driving data of the vehicle, constructing an intercept-form acceleration boundary curve; and step S105, selecting the intercept-form acceleration boundary curve as a target curve, obtaining a target expected acceleration on the basis of the speed of the current vehicle, and comparing the target expected acceleration with an actual acceleration to perform PID torque limiting. In the present invention, big data analysis is performed on historical operation data of a vehicle of a user to generate acceleration boundary curve parameters matching driving habits of the current user, and remote upgrade and PID torque limiting are performed, thereby ensuring the driving safety of the user.

Description

A fuel-saving method for acceleration torque limitation based on big data analysis Technical Field

[0001] The present invention relates to the technical field of big data analysis, and more specifically, to an acceleration torque limiting and fuel saving method based on big data analysis. Background Art

[0002] The existing technical solution for obtaining the target acceleration-related parameters of the engine is to have engine supporting engineers conduct power tests according to different engine models through vehicle manufacturer supporting tests, and roughly calculate the target acceleration-related parameters of the engine based on the corresponding relationship between vehicle speed and acceleration.

[0003] However, the above solution has the following disadvantages:

[0004] 1. Parameters are calibrated for a specific engine model based solely on the experience of supporting engineers. However, for vehicles with the same engine model, specific usage scenarios and driver habits may vary, resulting in calibration parameters that are not universally applicable.

[0005] 2. Supporting engineers are required to conduct repetitive tests in various power scenarios to calibrate parameters. However, parameter calibration is labor-intensive and time-consuming, and there are subjective judgment factors based on human observation, resulting in the speed and acceleration curve parameters being not necessarily optimal. Summary of the Invention

[0006] The present invention provides an acceleration torque limiting and fuel saving method based on big data analysis, which solves the technical problems in the above-mentioned background technology.

[0007] The present invention provides an acceleration torque limiting and fuel saving method based on big data analysis, comprising the following steps: step S101, obtaining a data collection time period of a vehicle;

[0008] Step S102: Acquire vehicle driving data at preset time intervals within a data collection period; the vehicle driving data includes: speed, acceleration, mileage, and fuel consumption at each time point;

[0009] Step S103, pre-processing the vehicle driving data;

[0010] Step S104, constructing an intercept-type acceleration boundary curve based on the pre-processed vehicle driving data;

[0011] The intercept-type acceleration boundary curve has a horizontal axis representing vehicle speed in km / h and a vertical axis representing acceleration in m / s². A one-dimensional curve is fitted as an envelope, represented by an Nth-order polynomial. This envelope is then shifted upward three times to obtain curves for 70%, 80%, and 90% coverage, respectively.

[0012] In step S105, one of the envelope curve, 70% coverage curve, 80% coverage curve, and 90% coverage curve is selected as the target curve, and the target curve is retrieved according to the current vehicle speed to obtain the target expected acceleration of the current vehicle. The target expected acceleration is compared with the actual acceleration of the current vehicle to perform PID torque limiting.

[0013] Furthermore, obtaining the data collection time period of the vehicle includes the following steps:

[0014] Step S201, taking the current time as the end time point, and calculating forward to a preset time threshold as the first start time point;

[0015] Step S202, obtaining the accumulated mileage at the first starting time point and the ending time point;

[0016] Step S203, determine whether the cumulative mileage is greater than a preset distance threshold. When the cumulative mileage is greater than or equal to the preset distance threshold, the time period between the first starting time point and the end time point is used as the data collection time period. Otherwise, the time point when the vehicle reaches the cumulative mileage is calculated forward as the second starting time point, and the time period between the second starting time point and the end time point is used as the data collection time period.

[0017] Furthermore, the preset time threshold and the preset distance threshold are both custom parameters.

[0018] Furthermore, the preset time interval is a custom parameter.

[0019] Furthermore, the acceleration of the vehicle is obtained through an acceleration sensor, and the mileage and fuel consumption of the vehicle are obtained through an on-board diagnostic system.

[0020] Furthermore, pre-processing the vehicle driving data includes the following steps:

[0021] Step S301, calculating the difference in mileage between two time points, and when the difference is less than or equal to 0, deleting the driving data of the vehicle at these two time points;

[0022] Step S302, calculating the difference in fuel consumption between two time points, and when the difference is less than or equal to 0, deleting the driving data of the vehicle at these two time points;

[0023] Step S303: The vehicle driving data also includes the vehicle engine model. According to the preset fuel consumption reference value of the engine, if the fuel consumption of the vehicle at each time point is greater than or equal to the fuel consumption reference value, the vehicle driving data at that time point is deleted; otherwise, the driving data of the vehicle at that time point is retained.

[0024] Step S304: When the speed of the vehicle at each time point is less than 0, or the acceleration is less than 0, or the mileage is less than 0, or the fuel consumption is less than 0, the driving data of the vehicle at that time point is directly deleted.

[0025] Furthermore, the fuel consumption reference value is set by the engine manufacturer.

[0026] Furthermore, fitting a one-dimensional curve as an envelope line includes the following steps:

[0027] Step S401: construct an Nth-order polynomial of the envelope; the Nth-order polynomial of the envelope is expressed as:

[0028] ,in represents the i-th weight coefficient, Represent the 1st to Nth weight coefficients respectively, represents the i-th power of the vehicle's speed at the j-th time point, They represent the 1st to N-1th powers of the vehicle’s speed at the jth time point, represents the acceleration of the vehicle at the jth time point;

[0029] Step S402, constructing the observation vector A and augmented matrix B;

[0030] The observation vector A is expressed as: , respectively represent the acceleration of the vehicle from the 1st time point to the Nth time point; the augmented matrix B is expressed as: ,in Respectively represent the speed of the vehicle from the 1st time point to the Nth time point, Respectively represent the acceleration of the vehicle from the 1st time point to the Nth time point;

[0031] Step S403: Calculate the weight coefficient vector C of the Nth-order polynomial of the envelope based on the observation vector A and the augmented matrix B. The weight coefficient vector C is expressed as: ,in Represent the 1st weight coefficient to the Nth weight coefficient respectively;

[0032] The calculation formula for the weight coefficient vector C of the Nth-order polynomial of the envelope based on the observation vector A and the augmented matrix B is as follows: , where A represents the observation vector, B represents the augmented matrix, and T represents the transpose operation of the matrix.

[0033] Furthermore, a first bias parameter is added to the Nth-order polynomial of the envelope to obtain a first expression, wherein the first bias parameter is a real number greater than 0. The speeds of all vehicles are substituted into the first expression to obtain the first acceleration of the vehicle, and the proportion of the vehicle acceleration less than or equal to the first acceleration of the vehicle is calculated until the proportion reaches 70%, and the corresponding first expression is determined as the 70% coverage curve. The second bias parameter and the second expression are determined respectively in the above manner, and the second expression is used as the 80% coverage curve. The third bias parameter and the third expression are determined respectively in the above manner, and the third expression is used as the 90% coverage curve.

[0034] Furthermore, the difference between the target desired acceleration and the actual acceleration of the current vehicle is calculated as input, and then the torque adjustment value is output according to the parameters of the PID controller, including the proportional coefficient, integral coefficient and differential coefficient, to adjust the torque output of the current vehicle, so that the actual acceleration of the current vehicle gradually approaches the target desired acceleration.

[0035] The beneficial effects of the present invention are as follows: the present invention generates acceleration boundary curve parameters that conform to the current user's driving habits by performing big data analysis on the user's vehicle's historical operating data, and ensures the user's driving safety and improves the user's driving experience through remote upgrades and PID torque limiting. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] FIG1 is a flow chart of an acceleration torque limiting and fuel saving method based on big data analysis according to the present invention;

[0037] FIG2 is a flow chart of obtaining a vehicle data collection time period according to the present invention;

[0038] FIG3 is a flow chart of pre-processing vehicle driving data according to the present invention;

[0039] FIG4 is a flow chart of fitting a one-dimensional curve as an envelope of the present invention;

[0040] FIG5 is a schematic diagram of an intercept-type acceleration boundary curve of the present invention;

[0041] FIG6 is a point-slope acceleration boundary curve of the present invention. DETAILED DESCRIPTION

[0042] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0043] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprising" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, but do not exclude other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0044] As shown in Figures 1 to 6, a method for accelerating torque limiting and saving fuel based on big data analysis includes the following steps:

[0045] Step S101, obtaining a vehicle data collection time period;

[0046] Step S102: Acquire vehicle driving data at preset time intervals within a data collection period; the vehicle driving data includes: speed, acceleration, mileage, and fuel consumption at each time point;

[0047] Step S103, pre-processing the vehicle driving data;

[0048] Step S104, constructing an intercept-type acceleration boundary curve based on the pre-processed vehicle driving data;

[0049] As shown in Figure 5, the intercept-type acceleration boundary curve has a horizontal axis representing vehicle speed in km / h and a vertical axis representing acceleration in m / s². By fitting a one-dimensional curve as an envelope represented by an Nth-order polynomial, the envelope is shifted upward three times to obtain the 70% coverage curve, the 80% coverage curve, and the 90% coverage curve, respectively.

[0050] In step S105, one of the envelope curve, 70% coverage curve, 80% coverage curve, and 90% coverage curve is selected as the target curve, and the target curve is retrieved according to the current vehicle speed to obtain the target expected acceleration of the current vehicle. The target expected acceleration is compared with the actual acceleration of the current vehicle to perform PID torque limiting.

[0051] In one embodiment of the present invention, as shown in FIG2 , obtaining the data collection time period of a vehicle includes the following steps:

[0052] Step S201, taking the current time as the end time point, and calculating forward to a preset time threshold as the first start time point;

[0053] Step S202, obtaining the accumulated mileage at the first starting time point and the ending time point;

[0054] Step S203, determine whether the cumulative mileage is greater than a preset distance threshold. When the cumulative mileage is greater than or equal to the preset distance threshold, the time period between the first starting time point and the end time point is used as the data collection time period. Otherwise, the time point when the vehicle reaches the cumulative mileage is calculated forward as the second starting time point, and the time period between the second starting time point and the end time point is used as the data collection time period.

[0055] In one embodiment of the present invention, the preset time threshold and the preset distance threshold are both custom parameters. Preferably, the preset time threshold is set to 30 days, and the preset distance threshold is set to 6000 km.

[0056] In one embodiment of the present invention, the preset time interval is a custom parameter. Preferably, the preset time interval is set to 1 second.

[0057] In one embodiment of the present invention, the vehicle speed is obtained through a vehicle speed sensor, the vehicle acceleration is obtained through an acceleration sensor, and the vehicle mileage and fuel consumption are obtained through an on-board diagnostic system (OBD); the vehicle acceleration can also be obtained by calculating the difference between the speeds at two time points and dividing it by the difference between the times at the two time points; the acceleration sensor can be an IMU sensor, etc.

[0058] In one embodiment of the present invention, as shown in FIG3 , pre-processing the driving data of the vehicle includes the following steps:

[0059] Step S301, calculating the difference in mileage between two time points, and when the difference is less than or equal to 0, deleting the driving data of the vehicle at these two time points;

[0060] Step S302, calculating the difference in fuel consumption between two time points, and when the difference is less than or equal to 0, deleting the driving data of the vehicle at these two time points;

[0061] Step S303: The vehicle driving data also includes the vehicle engine model. According to the preset fuel consumption reference value of the engine, if the fuel consumption of the vehicle at each time point is greater than or equal to the fuel consumption reference value, the vehicle driving data at that time point is deleted; otherwise, the driving data of the vehicle at that time point is retained.

[0062] Step S304: When the speed of the vehicle at each time point is less than 0, or the acceleration is less than 0, or the mileage is less than 0, or the fuel consumption is less than 0, the driving data of the vehicle at that time point is directly deleted.

[0063] In one embodiment of the present invention, a fuel consumption reference value may be pre-set for each engine model. Specifically, the fuel consumption reference value is established by the engine manufacturer.

[0064] In one embodiment of the present invention, a point-slope acceleration boundary curve may also be constructed based on the pre-processed vehicle driving data;

[0065] As shown in Figure 6, the horizontal axis of the point-slope acceleration boundary curve represents vehicle speed in km / h, and the vertical axis represents acceleration in m / s². By fitting a one-dimensional curve as the envelope and using the coordinate point with the maximum vehicle speed as the center of rotation of the envelope, 70% coverage curves, 80% coverage curves, and 90% coverage curves are generated, respectively.

[0066] In one embodiment of the present invention, as shown in FIG4 , fitting a one-dimensional curve as an envelope line includes the following steps:

[0067] Step S401, constructing an Nth-order polynomial of the envelope;

[0068] The Nth-order polynomial of the envelope is expressed as:

[0069] ,in represents the i-th weight coefficient, Represent the 1st to Nth weight coefficients respectively, represents the i-th power of the vehicle's speed at the j-th time point, They represent the 1st to N-1th powers of the vehicle’s speed at the jth time point, represents the acceleration of the vehicle at the jth time point;

[0070] Step S402, constructing the observation vector A and augmented matrix B;

[0071] The observation vector A is expressed as: , respectively represent the acceleration of the vehicle from the 1st time point to the Nth time point;

[0072] The augmented matrix B is expressed as: ,in Respectively represent the speed of the vehicle from the 1st time point to the Nth time point, Respectively represent the acceleration of the vehicle from the 1st time point to the Nth time point;

[0073] Step S403, calculating a weight coefficient vector C of an Nth-order polynomial of an envelope based on the observation vector A and the augmented matrix B;

[0074] The weight coefficient vector C is expressed as: ,in Represent the 1st weight coefficient to the Nth weight coefficient respectively;

[0075] The calculation formula for the weight coefficient vector C of the Nth-order polynomial of the envelope based on the observation vector A and the augmented matrix B is as follows: , where A represents the observation vector, B represents the augmented matrix, and T represents the transpose operation of the matrix.

[0076] For example: the speed and acceleration of a group of vehicles are expressed as: (x1,y1)=(1,2), (x2,y2)=(2,5), (x3,y3)=(3,10);

[0077] The quadratic polynomial that constructs the envelope is expressed as: ;

[0078] The observation vector A is constructed as: A={2, 5, 10};

[0079] Constructing the augmented matrix B is expressed as: ;

[0080] The weight coefficient vector C of the quadratic polynomial of the envelope calculated based on the observation vector A and the augmented matrix B is expressed as: {1, -3, 2};

[0081] Therefore, the quadratic polynomial of the envelope is: .

[0082] In one embodiment of the present invention, the accuracy of the Nth-order polynomial of the envelope may be evaluated by the mean square error.

[0083] In one embodiment of the present invention, the envelope can be obtained by fitting through a support vector machine or a neural network model.

[0084] In one embodiment of the present invention, a first bias parameter is added to the Nth-order polynomial of the envelope to obtain a first expression, wherein the first bias parameter is a real number greater than 0, the speeds of all vehicles are substituted into the first expression to obtain the first acceleration of the vehicle, and the proportion of the vehicle acceleration less than or equal to the first acceleration of the vehicle is calculated until the proportion reaches 70%, and the corresponding first expression is determined as the 70% coverage curve, the second bias parameter and the second expression are determined respectively by the above method, and the second expression is used as the 80% coverage curve, the third bias parameter and the third expression are determined respectively by the above method, and the third expression is used as the 90% coverage curve.

[0085] In one embodiment of the present invention, an OTA upgrade package is generated according to the target curve and sent to the current vehicle via a wireless network for software upgrade, thereby achieving the target expected acceleration according to the current vehicle speed.

[0086] In one embodiment of the present invention, the difference between the target desired acceleration and the actual acceleration of the current vehicle is calculated as input, and then according to the parameters of the PID controller, including the proportional coefficient, the integral coefficient and the differential coefficient, the torque adjustment value is output to adjust the torque output of the current vehicle, so that the actual acceleration of the current vehicle gradually approaches the target desired acceleration.

[0087] The above describes the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. A method for accelerating torque limiting and saving fuel based on big data analysis, characterized in that: The following steps are involved: Step S101, obtaining a vehicle data collection time period; Step S102, obtaining driving data of the vehicle at preset time intervals within a data collection period; The vehicle’s driving data includes: speed, acceleration, mileage, and fuel consumption at each point in time; Step S103, pre-processing the vehicle driving data; Step S104, constructing an intercept-type acceleration boundary curve based on the pre-processed vehicle driving data; The intercept-type acceleration boundary curve has a horizontal axis representing vehicle speed in km / h and a vertical axis representing acceleration in m / s². A one-dimensional curve is fitted as an envelope, represented by an Nth-order polynomial. This envelope is then shifted upward three times to obtain curves for 70%, 80%, and 90% coverage, respectively. In step S105, one of the envelope curve, 70% coverage curve, 80% coverage curve, and 90% coverage curve is selected as the target curve, and the target curve is retrieved according to the current vehicle speed to obtain the target expected acceleration of the current vehicle. The target expected acceleration is compared with the actual acceleration of the current vehicle to perform PID torque limiting.

2. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1 is characterized in that: Obtaining the data collection period for a vehicle includes the following steps: Step S201, taking the current time as the end time point, and calculating forward to a preset time threshold as the first start time point; Step S202, obtaining the accumulated mileage at the first starting time point and the ending time point; Step S203, determine whether the cumulative mileage is greater than a preset distance threshold. When the cumulative mileage is greater than or equal to the preset distance threshold, the time period between the first starting time point and the end time point is used as the data collection time period. Otherwise, the time point when the vehicle reaches the cumulative mileage is calculated forward as the second starting time point, and the time period between the second starting time point and the end time point is used as the data collection time period.

3. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 2 is characterized in that: The preset time threshold and preset distance threshold are both custom parameters.

4. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1 is characterized in that: The preset time interval is a custom parameter.

5. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1 is characterized in that The vehicle speed is obtained through the speed sensor, the vehicle acceleration is obtained through the acceleration sensor, and the vehicle mileage and fuel consumption are obtained through the on-board diagnostic system.

6. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1 is characterized in that: Preprocessing the vehicle's driving data includes the following steps: Step S301, calculating the difference in mileage between two time points, and when the difference is less than or equal to 0, deleting the driving data of the vehicle at these two time points; Step S302, calculating the difference in fuel consumption between two time points, and when the difference is less than or equal to 0, deleting the driving data of the vehicle at these two time points; Step S303: The vehicle driving data also includes the vehicle engine model. According to the preset fuel consumption reference value of the engine, if the fuel consumption of the vehicle at each time point is greater than or equal to the fuel consumption reference value, the vehicle driving data at that time point is deleted; otherwise, the driving data of the vehicle at that time point is retained. Step S304: When the speed of the vehicle at each time point is less than 0, or the acceleration is less than 0, or the mileage is less than 0, or the fuel consumption is less than 0, the driving data of the vehicle at that time point is directly deleted.

7. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 6 is characterized in that: The fuel consumption reference value is set by the engine manufacturer.

8. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1 is characterized in that: Fitting a one-dimensional curve as an envelope involves the following steps: Step S401: construct an Nth-order polynomial of the envelope; the Nth-order polynomial of the envelope is expressed as: ,in represents the i-th weight coefficient, Represent the 1st to Nth weight coefficients respectively, represents the i-th power of the vehicle's speed at the j-th time point, They represent the 1st to N-1th powers of the vehicle’s speed at the jth time point, represents the acceleration of the vehicle at the jth time point; Step S402, constructing the observation vector A and augmented matrix B; The observation vector A is expressed as: , respectively represent the acceleration of the vehicle from the 1st time point to the Nth time point; the augmented matrix B is expressed as: ,in Respectively represent the speed of the vehicle from the 1st time point to the Nth time point, Respectively represent the acceleration of the vehicle from the 1st time point to the Nth time point; Step S403: Calculate the weight coefficient vector C of the Nth-order polynomial of the envelope based on the observation vector A and the augmented matrix B. The weight coefficient vector C is expressed as: ,in Represent the 1st weight coefficient to the Nth weight coefficient respectively; The calculation formula for the weight coefficient vector C of the Nth-order polynomial of the envelope based on the observation vector A and the augmented matrix B is as follows: , where A represents the observation vector, B represents the augmented matrix, and T represents the transpose operation of the matrix.

9. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1 is characterized in that: A first bias parameter is added to the Nth-order polynomial of the envelope to obtain a first expression, wherein the first bias parameter is a real number greater than 0. The speeds of all vehicles are substituted into the first expression to obtain the first acceleration of the vehicle, and the proportion of the vehicle acceleration less than or equal to the first acceleration of the vehicle is calculated until the proportion reaches 70%, and the corresponding first expression is determined as the 70% coverage curve. The second bias parameter and the second expression are determined respectively in the above manner, and the second expression is used as the 80% coverage curve. The third bias parameter and the third expression are determined respectively in the above manner, and the third expression is used as the 90% coverage curve.

10. The acceleration torque limiting and fuel saving method based on big data analysis according to claim 1, characterized in that: The difference between the target desired acceleration and the actual acceleration of the current vehicle is calculated as input, and then the torque adjustment value is output according to the parameters of the PID controller, including the proportional coefficient, integral coefficient and differential coefficient, to adjust the torque output of the current vehicle, so that the actual acceleration of the current vehicle gradually approaches the target desired acceleration.

Images