Integrated hybrid control system for motorcycle

Abstract

The invention relates to the technical field of vehicle control, and discloses an integrated hybrid control system for a motorcycle, which comprises the following steps: acquiring a road image, and judging whether a driving front road section is an uphill road section or not according to the road image to obtain a first judgment result; if the first judgment result is an upslope road section, estimating a future moment when the motorcycle arrives at the upslope road section, and determining a road section gradient of the upslope road section according to the corresponding road image; predicting required power of the motorcycle passing through the uphill road section based on the slope of the road section, and judging whether the motorcycle meets a switching condition of a hybrid power mode or not according to the required power to obtain a second judgment result; when it is displayed that the power switching condition is met, the optimal power output ratio of a battery to an engine in the hybrid power mode is obtained, and the motorcycle is controlled to be switched to the hybrid power mode from the pure electric power mode at the future moment; according to the invention, the fuel consumption of the motorcycle passing through the uphill road section is reduced while the excessive load of the battery is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and more specifically, to an integrated hybrid control system for a motorcycle. Background Art

[0002] At present, most motorcycles rely mainly on pure electric mode for daily use; with the development of battery technology, pure electric motorcycles have gradually become the mainstream means of transportation for urban commuting due to their zero emissions, low noise and low operating costs; however, pure electric motorcycles are difficult to continuously provide sufficient power on long distances or in more complex road conditions (such as climbing and steep slopes) due to the limitations of battery capacity and power, and are prone to problems such as insufficient cruising range and insufficient climbing power.

[0003] Hybrid motorcycles were born to address this problem. By combining two power sources, batteries and engines, hybrid motorcycles can use batteries to provide driving force on daily flat roads, extend cruising range, and reduce energy consumption. They can also use the engine to provide additional power support when the vehicle requires higher power output (such as climbing, high-speed driving, etc.). This power distribution method not only improves the adaptability of the motorcycle, but also has achieved remarkable results in reducing carbon emissions and saving fuel. However, for small hybrid motorcycles, challenges are often encountered, especially when climbing hills. Since the battery and engine power of small hybrid vehicles are relatively small, when the vehicle is on an uphill section, if it is still running in pure electric mode, the power provided by the battery often cannot meet the needs of climbing, which may cause the vehicle to fail to pass smoothly or the battery to overheat or over-consume due to overload. Therefore, how to intelligently switch to hybrid mode when climbing and reasonably distribute the power output of the battery and engine has become an urgent problem to be solved for small hybrid motorcycles. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an integrated hybrid control system for a motorcycle.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An integrated hybrid control system for a motorcycle, the system comprising:

[0007] The data acquisition module is used to obtain a road image of a road section ahead of the motorcycle when the motorcycle is running in a pure electric power mode, and determine whether the road section ahead is an uphill section according to the road image to obtain a first determination result;

[0008] A slope detection module, for estimating a future time when the motorcycle will reach the uphill section if the first judgment result is an uphill section, and determining the section slope of the uphill section according to the corresponding road image;

[0009] A power prediction module is used to predict the power required for the motorcycle to pass through the uphill section based on the slope of the road section, and judge whether the motorcycle meets the switching condition of the hybrid power mode according to the power required, and obtain a second judgment result; the second judgment result includes one of satisfying and not satisfying the power switching condition;

[0010] The mode switching module is used to obtain the optimal power output ratio of the battery and the engine in the hybrid power mode when the judgment result shows that the power switching conditions are met, and control the motorcycle to switch from the pure electric power mode to the hybrid power mode at a future time.

[0011] Further, the determining whether the road ahead is an uphill road section includes:

[0012] Extract road images;

[0013] Inputting the road image into a pre-trained road condition recognition model to obtain a first judgment result;

[0014] The generation logic of the road condition recognition model is as follows:

[0015] Acquire historical road condition recognition training data, and divide the historical road condition recognition training data into a road condition recognition training set and a road condition recognition test set; the historical road condition recognition training data includes a plurality of road images and their corresponding annotation labels;

[0016] The marking labels include "0" and "1", where "0" represents a non-uphill section and "1" represents an uphill section;

[0017] Construct a classifier, use the road images in the road condition recognition training set as the input of the classifier, and use the annotation labels in the road condition recognition training set as the output of the classifier, train the classifier, and obtain an initial classification network;

[0018] The initial classification network is tested using the road condition recognition test set, and the output of the initial classification network that is greater than or equal to the preset test accuracy threshold is used as the trained road condition recognition model.

[0019] Furthermore, the estimating the future time when the motorcycle reaches the uphill section includes:

[0020] When the first judgment result shows an uphill section, the current time is recorded and marked as T1;

[0021] Get the speed of the motorcycle and the distance from the motorcycle to the uphill section at the current moment;

[0022] Input the vehicle speed, current time and the distance from the motorcycle to the uphill section into a preset mathematical calculation model to obtain the future time when the motorcycle arrives at the uphill section;

[0023] The mathematical calculation model is expressed as follows:

[0024]

[0025] Where: T represents the future time when the motorcycle arrives at the uphill section, T1 is the current time, V is the vehicle speed, S is the distance from the motorcycle to the uphill section, and α is a time correction factor greater than zero.

[0026] Further, the determining the road section slope of the uphill road section includes:

[0027] Inputting a road image of the road ahead into a preconfigured depth estimation model to obtain a depth map;

[0028] Filter out key pixel points from the depth map, wherein the key pixel points include near-view pixel points P1 (x1, y1) and far-view pixel points P2 (x2, y2);

[0029] Calculate the depth difference between the near-view pixel P1 (x1, y1) and the far-view pixel P2 (x2, y2) in the horizontal and vertical directions. The calculation formula is as follows:

[0030]

[0031] Where: DRpth(x1,y1) and DRpth(x2,y1) are the depth values ​​of the near-view pixel and the far-view pixel in the horizontal direction; DRpth(x1,y2) and DRpth(x1,y1) are the depth values ​​of the near-view pixel and the far-view pixel in the horizontal direction; ΔZ x is the depth difference in the horizontal direction, ΔZ y is the depth difference in the vertical direction;

[0032] Obtain the actual distance between the near-view pixel point P1 (x1, y1) and the far-view pixel point P2 (x2, y2), and substitute the actual distance, the depth difference in the horizontal direction, and the depth difference in the vertical direction into a preset geometric relationship calculation model to obtain the road section slope of the uphill section;

[0033] The geometric relationship calculation model is expressed as follows:

[0034]

[0035] Where SlopR is the slope of the uphill section, Δx and Δy are the actual distances between the near-view pixel and the far-view pixel in the horizontal and vertical directions, respectively, and arctan is the inverse tangent function.

[0036] Furthermore, the step of selecting key pixels from the depth map includes:

[0037] Divide the depth map into two equal parts to obtain the upper half and the lower half;

[0038] Using the K-means clustering algorithm to distinguish pixels in the upper half of the area, and taking the area formed by clustering the pixels as the first candidate sub-area, to obtain multiple first candidate sub-areas;

[0039] Obtain a preset target color for the road section ahead, and select multiple road section regions G from multiple first candidate sub-regions according to the target color:

[0040]

[0041] Where: I ij is the pixel value of the first candidate sub-region at position (i, j), 1 represents the target color, and 0 represents the non-target color;

[0042] Obtain the pixel area of ​​each road section area, sort them from large to small according to the pixel area, take the road section area with the largest pixel area as the first target area, and obtain the centroid of the first target area;

[0043] The centroid of the first target area is marked as the near-view pixel.

[0044] Furthermore, the step of selecting key pixels from the depth map further includes:

[0045] The K-means clustering algorithm is used to distinguish the pixels in the lower half of the area, and the area formed by clustering the pixels is used as the second candidate sub-area, thereby obtaining multiple second candidate sub-areas;

[0046] According to the target color, multiple road segment regions G are screened out from multiple second candidate sub-regions:

[0047] Obtain the pixel area of ​​each road section area, sort them from large to small according to the pixel area, take the road section area with the largest pixel area as the second target area, and obtain the centroid of the second target area;

[0048] The centroid of the second target area is marked as the distant pixel.

[0049] Furthermore, the prediction of the power required for a motorcycle to pass an uphill section includes:

[0050] Obtain climbing driving force impact data;

[0051] The climbing driving force influencing data include the mass of the motorcycle, the acceleration of gravity and the friction coefficient of the uphill section;

[0052] The climbing driving force influence data and the road section slope are obtained as the required power characteristic data, and input into the pre-trained power prediction model to obtain the required power for the motorcycle to pass the uphill section;

[0053] The generation logic of the power prediction model is as follows:

[0054] Acquire historical demand power training data, and divide the historical demand power training data into a demand power training set and a demand power test set, wherein the historical demand power training data includes demand power characteristic data and its corresponding demand power;

[0055] A regression network is constructed, the demand power characteristic data in the demand power training set is used as the input of the regression network, and the demand power in the demand power training set is used as the output of the regression network, and the regression network is trained to obtain an initial regression network;

[0056] The demand power test set is used to verify the model of the initial regression network, and the output of the initial regression network that is less than or equal to the preset test error threshold is used as the trained power prediction model.

[0057] Furthermore, the step of judging whether the motorcycle satisfies the switching condition of the hybrid power mode includes:

[0058] Setting demand power thresholds;

[0059] comparing the power required for the motorcycle to pass through the uphill section with a power required threshold;

[0060] If the required power is greater than or equal to the required power threshold, it is determined that the motorcycle meets the switching condition;

[0061] If the required power is less than the required power threshold, it is determined that the motorcycle does not meet the switching condition.

[0062] Furthermore, the optimal power output ratio of the battery and the engine in the hybrid power mode is obtained by optimizing using a preconfigured genetic algorithm;

[0063] The processing logic of the genetic algorithm is as follows:

[0064] a1: Initialize the population: randomly generate an original population, wherein the original population contains R individuals, each of which represents the power output ratio of a battery and an engine, and R is an integer greater than zero;

[0065] a2: Fitness evaluation: Under each individual, obtain the battery temperature of the battery and the fuel consumption of the engine; input the battery temperature and fuel consumption into the pre-built fitness function to calculate the fitness of each individual;

[0066] The calculation formula of the pre-constructed fitness function is: Where: Fitness is fitness, I A is the battery temperature, I B is the temperature reference, Q A is the fuel consumption, Q B is the reference amount of fuel consumption;

[0067] a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother;

[0068] a4: Crossover: Perform crossover operation on the father and mother to produce new individuals;

[0069] a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2;

[0070] a6: Repeat steps a2 to a5 above until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the power output ratio of the battery and the engine represented by the corresponding individual as the optimal power output ratio.

[0071] An integrated hybrid control method for a motorcycle is implemented based on any one of the above-mentioned integrated hybrid control systems for a motorcycle, and the method comprises:

[0072] When the motorcycle is running in the pure electric power mode, a road image of the road section ahead of the motorcycle is obtained, and whether the road section ahead of the motorcycle is an uphill section is determined according to the road image to obtain a first determination result;

[0073] If the first judgment result is an uphill section, then estimating the future time when the motorcycle reaches the uphill section, and determining the section slope of the uphill section according to the corresponding road image;

[0074] Predicting the power required for the motorcycle to pass through the uphill section based on the road section slope, and judging whether the motorcycle meets the switching condition of the hybrid power mode according to the power required, and obtaining a judgment result; the judgment result includes one of satisfying and not satisfying the power switching condition;

[0075] When the judgment result shows that the power switching conditions are met, the optimal power output ratio of the battery and the engine in the hybrid power mode is obtained, and the motorcycle is controlled to switch from the pure electric power mode to the hybrid power mode at any time in the future.

[0076] Compared with the prior art, the present invention has the following beneficial effects:

[0077] (1) The present application discloses an integrated hybrid control system for a motorcycle, comprising: acquiring a road image, and judging whether the road ahead is an uphill section based on the road image, to obtain a first judgment result; if the first judgment result is an uphill section, estimating the future time when the motorcycle will arrive at the uphill section, and determining the road section slope of the uphill section based on the corresponding road image; predicting the required power of the motorcycle to pass the uphill section based on the road section slope, and judging whether the motorcycle meets the switching condition of the hybrid power mode based on the required power, to obtain a second judgment result; when it is shown that the power switching condition is met, obtaining the optimal power output ratio of the battery and the engine in the hybrid power mode, and controlling the motorcycle to switch from the pure electric power mode to the hybrid power mode at a future time; Based on the above technical features, the present invention is conducive to predicting the required power of the motorcycle to pass the uphill section when the motorcycle encounters an uphill section, and judging whether it is necessary to switch to the hybrid power mode; through such automatic judgment, the system can switch to the hybrid power mode in time when the battery power is insufficient, avoiding the situation of insufficient power in the pure electric mode, thereby helping to avoid excessive load on the battery while reducing the fuel consumption of the motorcycle when passing the uphill section.

[0078] (2) The present application discloses an integrated hybrid control system for a motorcycle, which determines whether an uphill section appears through a road image, and determines the slope of the uphill section, which is beneficial to provide reliable data support for subsequent power distribution and power mode switching, thereby facilitating the realization of automatic power switching control of the motorcycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A module structure diagram of the integrated hybrid control system for a motorcycle provided by the present invention;

[0080] Figure 2 This is a flow chart of the integrated hybrid control method for motorcycle provided by the present invention. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0082] Example 1

[0083] See also Figure 1 As shown, this embodiment discloses an integrated hybrid control system for a motorcycle, the system comprising:

[0084] The data acquisition module 101 is used to obtain a road image of a road section ahead of the motorcycle when the motorcycle is running in a pure electric power mode, and determine whether the road section ahead is an uphill section according to the road image to obtain a first determination result;

[0085] The road image is acquired by a camera mounted on a motorcycle, and the first judgment result includes one of an uphill section and a non-uphill section;

[0086] In implementation, the step of determining whether the road ahead is an uphill road section includes:

[0087] Extract road images;

[0088] Inputting the road image into a pre-trained road condition recognition model to obtain a first judgment result;

[0089] The generation logic of the road condition recognition model is as follows:

[0090] Acquire historical road condition recognition training data, and divide the historical road condition recognition training data into a road condition recognition training set and a road condition recognition test set; the historical road condition recognition training data includes a plurality of road images and their corresponding annotation labels;

[0091] The marking labels include "0" and "1", where "0" represents a non-uphill section and "1" represents an uphill section;

[0092] It should be noted that: the road images in the historical road condition recognition training data are collected in advance by technical personnel, and the annotation labels in the historical road condition recognition training data are generated by technical personnel or AI data annotators after annotating each collected road image with "0" or "1";

[0093] Construct a classifier, use the road images in the road condition recognition training set as the input of the classifier, and use the annotation labels in the road condition recognition training set as the output of the classifier, train the classifier, and obtain an initial classification network;

[0094] The initial classification network is tested using the road condition recognition test set, and the initial classification network with an accuracy greater than or equal to a preset test accuracy threshold is output as a trained road condition recognition model;

[0095] The classifier is specifically one of the classification algorithm models such as convolutional neural network, recurrent neural network or naive Bayes.

[0096] The slope detection module 102 is used to estimate the future time when the motorcycle reaches the uphill section if the first judgment result is an uphill section, and determine the section slope of the uphill section according to the corresponding road image;

[0097] In implementation, the estimating the future time when the motorcycle reaches the uphill section includes:

[0098] When the first judgment result shows an uphill section, the current time is recorded and marked as T1;

[0099] Get the speed of the motorcycle and the distance from the motorcycle to the uphill section at the current moment;

[0100] It should be noted that: the speed of the motorcycle is acquired by the on-board speed sensor, the distance from the motorcycle to the uphill section at the current moment is acquired by the on-board distance sensor, or the distance from the motorcycle to the uphill section is obtained by identifying the starting point of the uphill section using a pre-configured depth estimation model and calculating the position of the motorcycle from the starting point to the current moment;

[0101] Input the vehicle speed, current time and the distance from the motorcycle to the uphill section into a preset mathematical calculation model to obtain the future time when the motorcycle arrives at the uphill section;

[0102] The mathematical calculation model is expressed as follows:

[0103]

[0104] Where: T represents the future time when the motorcycle arrives at the uphill section, T1 is the current time, V is the vehicle speed, S is the distance from the motorcycle to the uphill section, and α is a time correction factor greater than zero, which is used to adjust the error caused by the environment or other factors (such as calculation processing time, etc.);

[0105] In implementation, determining the road section slope of the uphill road section includes:

[0106] Inputting a road image of the road section ahead into a preconfigured depth estimation model to obtain a depth map; wherein the value of each pixel in the depth map represents the depth relative to the camera;

[0107] It should be noted that the pre-configured depth estimation model is an existing monocular depth estimation model, such as MiDaS and MonodRpth2, etc. These depth estimation models can estimate the depth of a scene from a single image;

[0108] Filter out key pixel points from the depth map, wherein the key pixel points include near-view pixel points P1 (x1, y1) and far-view pixel points P2 (x2, y2);

[0109] In a specific implementation, the step of selecting key pixels from the depth map includes:

[0110] Divide the depth map into two equal parts to obtain the upper half and the lower half;

[0111] It should be noted that the depth map is divided into two equal parts by horizontal segmentation. Assuming that the depth map is W (width) × H (height), the depth map is horizontally segmented with H / 2 as the symmetry axis to obtain the upper half area and the lower half area.

[0112] Using the K-means clustering algorithm to distinguish pixels in the upper half of the area, and taking the area formed by clustering the pixels as the first candidate sub-area, to obtain multiple first candidate sub-areas;

[0113] Obtain a preset target color for the road section ahead, and select multiple road section regions G from multiple first candidate sub-regions according to the target color:

[0114]

[0115] Where: I ij is the pixel value of the first candidate sub-region at position (i, j), 1 represents the target color, and 0 represents the non-target color (i.e., other colors);

[0116] It should be noted that the target color preset for the road section ahead is manually determined in advance by a technician, and the real color of the actual road section is used as the target color;

[0117] Obtain the pixel area of ​​each road section area, sort them from large to small according to the pixel area, take the road section area with the largest pixel area as the first target area, and obtain the centroid of the first target area;

[0118] Mark the centroid of the first target area as a near-view pixel point;

[0119] In another specific implementation, the step of selecting key pixels from the depth map further includes:

[0120] The K-means clustering algorithm is used to distinguish the pixels in the lower half of the area, and the area formed by clustering the pixels is used as the second candidate sub-area, thereby obtaining multiple second candidate sub-areas;

[0121] According to the target color, multiple road segment regions G are screened out from multiple second candidate sub-regions:

[0122] Obtain the pixel area of ​​each road section area, sort them from large to small according to the pixel area, take the road section area with the largest pixel area as the second target area, and obtain the centroid of the second target area;

[0123] Mark the centroid of the second target area as a distant pixel point;

[0124] It can be understood that: screening near-view pixels and far-view pixels through the above process is conducive to effectively filtering out information in non-road areas, such as pedestrians, vehicles, buildings and other interfering objects; this can ensure that the screened pixels are more stable and accurate, and are not easily disturbed by the surrounding environment, and further, it is conducive to improving the accuracy of subsequent road section slope calculation;

[0125] Calculate the depth difference between the near-view pixel P1 (x1, y1) and the far-view pixel P2 (x2, y2) in the horizontal and vertical directions. The calculation formula is as follows:

[0126]

[0127] Where: DRpth(x1,y1) and DRpth(x2,y1) are the depth values ​​of the near-view pixel and the far-view pixel in the horizontal direction; DRpth(x1,y2) and DRpth(x1,y1) are the depth values ​​of the near-view pixel and the far-view pixel in the horizontal direction; ΔZ x is the depth difference in the horizontal direction, ΔZ y is the depth difference in the vertical direction;

[0128] Obtain the actual distance between the near-view pixel point P1 (x1, y1) and the far-view pixel point P2 (x2, y2), and substitute the actual distance, the depth difference in the horizontal direction, and the depth difference in the vertical direction into a preset geometric relationship calculation model to obtain the road section slope of the uphill section;

[0129] The geometric relationship calculation model is expressed as follows:

[0130]

[0131] Where SlopR is the slope of the uphill section, Δx and Δy are the actual distances between the near-view pixel and the far-view pixel in the horizontal and vertical directions, respectively, and arctan is the inverse tangent function.

[0132] The power prediction module 103 is used to predict the power required for the motorcycle to pass through the uphill section based on the road section slope, and determine whether the motorcycle meets the switching condition of the hybrid power mode according to the power required, and obtain a second judgment result; the second judgment result includes one of satisfying and not satisfying the power switching condition;

[0133] In implementation, the method of predicting the power required for a motorcycle to pass an uphill section includes:

[0134] Obtain climbing driving force impact data;

[0135] The climbing driving force influencing data include the mass of the motorcycle, the acceleration of gravity and the friction coefficient of the uphill section;

[0136] The climbing driving force influence data and the road section slope are obtained as the required power characteristic data, and input into the pre-trained power prediction model to obtain the required power for the motorcycle to pass the uphill section;

[0137] The generation logic of the power prediction model is as follows:

[0138] Acquire historical demand power training data, and divide the historical demand power training data into a demand power training set and a demand power test set, wherein the historical demand power training data includes demand power characteristic data and its corresponding demand power;

[0139] It should be noted that in the historical demand power training data, the mass of the motorcycle is collected by a gravity (pressure) sensor, and the gravity acceleration is 9.81 m / s 2 The friction coefficient of the uphill section is determined according to the corresponding value of the road surface type of the uphill section. The corresponding value of each road surface type is determined by the technicians according to the experimental situation. For example, the friction coefficient of the asphalt road surface is 0.7, and the friction coefficient of the concrete road surface is 0.8.

[0140] The demand power in the historical demand power training data is calculated and recorded in real time by the technicians. It is calculated based on the Newtonian mechanics principle in classical physics. The calculation formula is: F 需求 =m×g×sin(θ)+μ×m×g×cos(θ); where: F 需求 is the required power, m is the mass, g is the acceleration due to gravity, μ is the friction coefficient, θ is the slope of the road section, sin(·) and cos(·) are the sine function and cosine function respectively;

[0141] A regression network is constructed, the demand power characteristic data in the demand power training set is used as the input of the regression network, and the demand power in the demand power training set is used as the output of the regression network, and the regression network is trained to obtain an initial regression network;

[0142] The initial regression network is verified using the demand power test set, and the initial regression network with an output value less than or equal to the preset test error threshold is used as the trained power prediction model;

[0143] The regression network is specifically one of the regression algorithm models such as polynomial regression, decision tree, random forest, support vector machine and neural network;

[0144] In implementation, the step of determining whether the motorcycle meets the switching condition of the hybrid power mode includes:

[0145] Setting demand power thresholds;

[0146] The power demand threshold is set by a technician based on experimental data, or is determined based on the maximum output power of the battery in pure electric power mode, and the maximum output power of the battery is determined based on the setting of the battery before leaving the factory;

[0147] comparing the power required for the motorcycle to pass through the uphill section with a power required threshold;

[0148] If the required power is greater than or equal to the required power threshold, it is determined that the motorcycle meets the switching condition;

[0149] If the required power is less than the required power threshold, it is determined that the motorcycle does not meet the switching condition;

[0150] It should be understood that: when the demand power is greater than or equal to the demand power threshold, it means that if the motorcycle continues to be driven in pure electric power mode, it will not be able to safely pass the uphill section, which will cause battery output overload or overheating, or in other words, the motorcycle cannot be driven through the uphill section in pure electric power mode; on the contrary, when the demand power is less than the demand power threshold, it means that the slope of the uphill section has little effect on the demand power, and the motorcycle can still safely pass the uphill section by continuing to drive in pure electric power mode. In other words, the motorcycle in pure electric power mode can meet the demand power for passing the uphill section.

[0151] The mode switching module 104 is used to obtain the optimal power output ratio of the battery and the engine in the hybrid power mode when the judgment result shows that the power switching condition is met, and control the motorcycle to switch from the pure electric power mode to the hybrid power mode at a future time;

[0152] Wherein, the optimal power output ratio of the battery and the engine in the hybrid power mode is obtained by optimizing using a preconfigured genetic algorithm;

[0153] Specifically, the processing logic of the genetic algorithm is as follows:

[0154] a1: Initialize the population: randomly generate an original population, wherein the original population contains R individuals, each of which represents the power output ratio of a battery and an engine, and R is an integer greater than zero;

[0155] The optimal power output ratio of the battery and the engine satisfies: β1+β2=1, where β1 is the power output ratio of the battery, and β2 is the power output ratio of the engine;

[0156] a2: Fitness evaluation: Under each individual (i.e., the optimal power output ratio of each battery and engine in the original population), obtain the battery temperature of the battery and the fuel consumption of the engine; input the battery temperature and fuel consumption into the pre-built fitness function to calculate the fitness of each individual;

[0157] The calculation formula of the pre-constructed fitness function is: Where: Fitness is fitness, I A is the battery temperature, I B is the temperature reference, Q A is the fuel consumption, Q B is the reference amount of fuel consumption;

[0158] The temperature reference and fuel consumption reference are set by technicians based on actual experimental conditions.

[0159] a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother;

[0160] a4: Crossover: Perform crossover operation on the father and mother to produce new individuals;

[0161] It should be noted that the crossover operation on the paternal parent and the maternal parent is implemented based on a crossover operation, and the crossover operation includes but is not limited to one of a single-point crossover, a uniform crossover or a sequential crossover, etc.;

[0162] a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2;

[0163] In genetic algorithms, mutation operations are used to introduce genetic diversity and prevent the algorithm from falling into a local optimum. The mutation operation on new individuals is implemented by uniform mutation or Gaussian mutation.

[0164] a6: Repeat steps a2 to a5 above until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the power output ratio of the battery and the engine represented by the corresponding individual as the optimal power output ratio;

[0165] For example: Assume that the maximum number of iterations is 100 times, and record the individual with the highest fitness in the current population and its fitness value after each iteration; if it is found that the fitness value has not changed significantly in a certain generation, it is considered that the convergence condition is met, the iteration is stopped, and the power output ratio of the battery and the engine represented by the corresponding individual is output as the optimal power output ratio;

[0166] It can be understood that: when a motorcycle encounters an uphill section with a large slope, by controlling the motorcycle to switch from pure electric power mode to hybrid power mode, and controlling the battery and engine to output hybrid power according to the optimal power output ratio, the present invention is beneficial to reducing the fuel consumption of the motorcycle when passing through the uphill section while ensuring battery performance and avoiding excessive battery load, reducing carbon emissions and improving the economic benefits of motorcycle driving.

[0167] Example 2

[0168] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses an integrated hybrid control method for a motorcycle. For details not provided in this embodiment, please refer to the relevant part of the above embodiment 1. The method includes:

[0169] S201: When the motorcycle is running in the pure electric power mode, a road image of a road section ahead of the motorcycle is obtained, and whether the road section ahead of the motorcycle is an uphill section is determined according to the road image to obtain a first determination result;

[0170] S202: If the first judgment result is an uphill section, estimating the future time when the motorcycle reaches the uphill section, and determining the section slope of the uphill section according to the corresponding road image;

[0171] S203: predicting the power required for the motorcycle to pass through the uphill section based on the road section slope, and judging whether the motorcycle meets the switching condition of the hybrid power mode according to the power required, and obtaining a judgment result; the judgment result includes one of satisfying and not satisfying the power switching condition;

[0172] S204: When the judgment result shows that the power switching condition is met, the optimal power output ratio of the battery and the engine in the hybrid power mode is obtained, and the motorcycle is controlled to switch from the pure electric power mode to the hybrid power mode at a future time.

[0173] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0174] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0175] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0176] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0177] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0178] 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 distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0180] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in 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.

[0181] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An integrated hybrid control system for a motorcycle, characterized in that: The system comprises: The data acquisition module is used to obtain a road image of a road section ahead of the motorcycle when the motorcycle is running in a pure electric power mode, and determine whether the road section ahead is an uphill section according to the road image to obtain a first determination result; A slope detection module, for estimating a future time when the motorcycle will reach the uphill section if the first judgment result is an uphill section, and determining the section slope of the uphill section according to the corresponding road image; A power prediction module is used to predict the power required for the motorcycle to pass through the uphill section based on the slope of the road section, and judge whether the motorcycle meets the switching condition of the hybrid power mode according to the power required, and obtain a second judgment result; the second judgment result includes one of satisfying and not satisfying the power switching condition; The mode switching module is used to obtain the optimal power output ratio of the battery and the engine in the hybrid power mode when the judgment result shows that the power switching conditions are met, and control the motorcycle to switch from the pure electric power mode to the hybrid power mode at a future time.

2. The integrated hybrid control system for motorcycle according to claim 1, characterized in that: The determining whether the road ahead is an uphill road section comprises: Extract road images; Inputting the road image into a pre-trained road condition recognition model to obtain a first judgment result; The generation logic of the road condition recognition model is as follows: Acquire historical road condition recognition training data, and divide the historical road condition recognition training data into a road condition recognition training set and a road condition recognition test set; the historical road condition recognition training data includes a plurality of road images and their corresponding annotation labels; The marking labels include "0" and "1", where "0" represents a non-uphill section and "1" represents an uphill section; Construct a classifier, use the road images in the road condition recognition training set as the input of the classifier, and use the annotation labels in the road condition recognition training set as the output of the classifier, train the classifier, and obtain an initial classification network; The initial classification network is tested using the road condition recognition test set, and the output of the initial classification network that is greater than or equal to the preset test accuracy threshold is used as the trained road condition recognition model.

3. The integrated hybrid control system for motorcycle according to claim 2, characterized in that: The estimated future time when the motorcycle arrives at the uphill section includes: When the first judgment result shows an uphill section, the current time is recorded and marked as T1; Get the speed of the motorcycle and the distance from the motorcycle to the uphill section at the current moment; Input the vehicle speed, current time and the distance from the motorcycle to the uphill section into a preset mathematical calculation model to obtain the future time when the motorcycle arrives at the uphill section; The mathematical calculation model is expressed as follows: Where: T represents the future time when the motorcycle arrives at the uphill section, T1 is the current time, V is the vehicle speed, S is the distance from the motorcycle to the uphill section, and α is a time correction factor greater than zero.

4. The integrated hybrid control system for motorcycle according to claim 3, characterized in that: Determining the road section slope of the uphill road section includes: Inputting a road image of the road ahead into a preconfigured depth estimation model to obtain a depth map; Filter out key pixel points from the depth map, wherein the key pixel points include near-view pixel points P1 (x1, y1) and far-view pixel points P2 (x2, y2); Calculate the depth difference between the near-view pixel P1 (x1, y1) and the far-view pixel P2 (x2, y2) in the horizontal and vertical directions. The calculation formula is as follows: Where: DRpth(x1,y1) and DRpth(x2,y1) are the depth values ​​of the near-view pixel and the far-view pixel in the horizontal direction; DRpth(x1,y2) and DRpth(x1,y1) are the depth values ​​of the near-view pixel and the far-view pixel in the horizontal direction; ΔZ x is the depth difference in the horizontal direction, ΔZ y is the depth difference in the vertical direction; Obtain the actual distance between the near-view pixel point P1 (x1, y1) and the far-view pixel point P2 (x2, y2), and substitute the actual distance, the depth difference in the horizontal direction, and the depth difference in the vertical direction into a preset geometric relationship calculation model to obtain the road section slope of the uphill section; The geometric relationship calculation model is expressed as follows: Where SlopR is the slope of the uphill section, Δx and Δy are the actual distances between the near-view pixel and the far-view pixel in the horizontal and vertical directions, respectively, and arctan is the inverse tangent function.

5. The integrated hybrid control system for motorcycle according to claim 4, characterized in that: The step of selecting key pixels from the depth map includes: Divide the depth map into two equal parts to obtain the upper half and the lower half; Using the K-means clustering algorithm to distinguish pixels in the upper half of the area, and taking the area formed by clustering the pixels as the first candidate sub-area, to obtain multiple first candidate sub-areas; Obtain a preset target color for the road section ahead, and select multiple road section regions G from multiple first candidate sub-regions according to the target color: Where: I ij is the pixel value of the first candidate sub-region at position (i, j), 1 represents the target color, and 0 represents the non-target color; Obtain the pixel area of ​​each road section area, sort them from large to small according to the pixel area, take the road section area with the largest pixel area as the first target area, and obtain the centroid of the first target area; The centroid of the first target area is marked as the near-view pixel.

6. The integrated hybrid control system for motorcycle according to claim 5, characterized in that: The step of selecting key pixels from the depth map further includes: The K-means clustering algorithm is used to distinguish the pixels in the lower half of the area, and the area formed by clustering the pixels is used as the second candidate sub-area, thereby obtaining multiple second candidate sub-areas; According to the target color, multiple road segment regions G are screened out from multiple second candidate sub-regions: Obtain the pixel area of ​​each road section area, sort them from large to small according to the pixel area, take the road section area with the largest pixel area as the second target area, and obtain the centroid of the second target area; The centroid of the second target area is marked as the distant pixel.

7. The integrated hybrid control system for a motorcycle according to claim 6, characterized in that: The method of predicting the power required for a motorcycle to pass an uphill section includes: Obtain climbing driving force impact data; The climbing driving force influencing data include the mass of the motorcycle, the acceleration of gravity and the friction coefficient of the uphill section; The climbing driving force influence data and the road section slope are obtained as the required power characteristic data, and input into the pre-trained power prediction model to obtain the required power for the motorcycle to pass the uphill section; The generation logic of the power prediction model is as follows: Acquire historical demand power training data, and divide the historical demand power training data into a demand power training set and a demand power test set, wherein the historical demand power training data includes demand power characteristic data and its corresponding demand power; A regression network is constructed, the demand power characteristic data in the demand power training set is used as the input of the regression network, and the demand power in the demand power training set is used as the output of the regression network, and the regression network is trained to obtain an initial regression network; The demand power test set is used to verify the model of the initial regression network, and the output of the initial regression network that is less than or equal to the preset test error threshold is used as the trained power prediction model.

8. The integrated hybrid control system for a motorcycle according to claim 7, characterized in that: The step of judging whether the motorcycle meets the switching condition of the hybrid power mode includes: Setting demand power thresholds; comparing the power required for the motorcycle to pass through the uphill section with a power required threshold; If the required power is greater than or equal to the required power threshold, it is determined that the motorcycle meets the switching condition; If the required power is less than the required power threshold, it is determined that the motorcycle does not meet the switching condition.

9. The integrated hybrid control system for a motorcycle according to claim 8, characterized in that: The optimal power output ratio of the battery and the engine in the hybrid mode is obtained by optimizing using a preconfigured genetic algorithm; The processing logic of the genetic algorithm is as follows: a1: Initialize the population: randomly generate an original population, wherein the original population contains R individuals, each of which represents the power output ratio of a battery and an engine, and R is an integer greater than zero; a2: Fitness evaluation: Under each individual, obtain the battery temperature of the battery and the fuel consumption of the engine; input the battery temperature and fuel consumption into the pre-built fitness function to calculate the fitness of each individual; The calculation formula of the pre-constructed fitness function is: Where: Fitness is fitness, I A is the battery temperature, I B is the temperature reference, Q A is the fuel consumption, Q B is the reference amount of fuel consumption; a3: Selection: Use the roulette method to select two individuals with high fitness in the original population as the father and mother; a4: Crossover: Perform crossover operation on the father and mother to produce new individuals; a5: Mutation: Perform mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 above until the fitness of the individuals in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and output the power output ratio of the battery and the engine represented by the corresponding individual as the optimal power output ratio.

10. An integrated hybrid control method for a motorcycle, characterized in that: The method is implemented based on the integrated hybrid control system for motorcycle according to any one of claims 1 to 9, and the method comprises: When the motorcycle is running in the pure electric power mode, a road image of the road section ahead of the motorcycle is obtained, and whether the road section ahead of the motorcycle is an uphill section is determined according to the road image to obtain a first determination result; If the first judgment result is an uphill section, then estimating the future time when the motorcycle reaches the uphill section, and determining the section slope of the uphill section according to the corresponding road image; Predicting the power required for the motorcycle to pass through the uphill section based on the road section slope, and judging whether the motorcycle meets the switching condition of the hybrid power mode according to the power required, and obtaining a judgment result; the judgment result includes one of satisfying and not satisfying the power switching condition; When the judgment result shows that the power switching conditions are met, the optimal power output ratio of the battery and the engine in the hybrid power mode is obtained, and the motorcycle is controlled to switch from the pure electric power mode to the hybrid power mode at any time in the future.

Images