Adaptive energy distribution management method and device based on working condition recognition and computer program product

Abstract

The invention discloses a self-adaptive energy distribution management method and device based on working condition recognition and a computer program product, and the method comprises the steps: dividing a plurality of time periods based on the historical driving data of a vehicle, carrying out the continuous sampling of vehicle speed data in the plurality of time periods, and obtaining a plurality of feature blocks; performing working condition division on the plurality of feature blocks according to vehicle speeds in different intervals, and calculating a clustering center of each working condition by adopting a clustering algorithm; for each working condition, selecting a preset equivalent factor with the minimum oil consumption as an initial equivalent factor of the working condition; calculating a linearly changed SOC reference trajectory; acquiring current vehicle speed data in real time, matching the current vehicle speed data with the clustering center of each working condition, matching the current vehicle speed data to the nearest clustering center to determine the category of the current working condition, and correcting the initial equivalent factor under the working condition based on the SOC reference trajectory to obtain a self-adaptive equivalent factor; and according to the self-adaptive equivalent factors, optimal output power of the engine and the motor is distributed in real time so as to minimize equivalent oil consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of energy control for hybrid vehicles, and particularly to a management method, device and computer program product for adaptive energy distribution based on driving condition recognition. Background Art

[0002] With the intensification of the global energy crisis and environmental problems, hybrid vehicles have become a key development direction in the automotive industry due to their advantages in energy conservation and emission reduction. As a core control technology, the energy management strategy directly affects the vehicle's fuel economy by coordinating the power distribution between the engine and the motor. Traditional strategies generally adopt the equivalent consumption minimization algorithm (ECMS), which globally optimizes by equivalently converting the electric energy consumption into virtual fuel consumption through a fixed equivalent factor. This equivalent factor is usually calibrated offline based on standard test driving conditions (such as NEDC, WLTC) and remains constant throughout the entire life cycle.

[0003] However, the actual operating conditions have significant dynamic characteristics: frequent starts and stops on urban roads result in instantaneous power demand fluctuations of more than 300%, continuous high-load demands exist during highway cruising, and mountain roads need to cope with continuous energy feedback caused by slopes. The fixed equivalent factor cannot perceive real-time road condition changes, leading to energy distribution deviating from the optimal trajectory. Existing improvement schemes such as fuzzy logic control can achieve dynamic adjustment, but there are problems such as the construction of the rule base relying on expert experience and difficulty in parameter tuning. These technical defects cause existing hybrid vehicles to be unable to fully exert their energy-saving potential under actual complex road conditions, seriously restricting the improvement of energy conservation and emission reduction effects. Therefore, developing a dynamic equivalent factor optimization method with environmental adaptability has become a key technical bottleneck for improving the energy management efficiency of hybrid vehicles. Summary of the Invention

[0004] Aiming at the deficiencies of the above-mentioned existing technologies, the technical problem to be solved by the present invention is: how to provide a management method for adaptive energy distribution based on driving condition recognition that can identify driving conditions, dynamically adjust the fuel-electric equivalent factor, optimize the power distribution between the engine and the motor, and reduce fuel consumption.

[0005] To solve the above technical problems, the present invention adopts the following technical solutions:

[0006] A management method for adaptive energy distribution based on driving condition recognition includes the following steps:

[0007] (1) Based on the vehicle's historical driving data, divide several time periods and continuously sample the vehicle speed data within each time period to obtain several feature blocks. Divide the several feature blocks into n driving conditions according to different speed intervals, where n≥2 and n is a positive integer, and use the k-means clustering algorithm to calculate the clustering center of each driving condition;

[0008] (2) For each working condition, screen the preset equivalent factors of each feature block within this working condition, and select the preset equivalent factor with the minimum fuel consumption as the initial equivalent factor for this working condition;

[0009] (3) Calculate the linearly varying SOC reference trajectory based on the total mileage between the current driving starting point and the destination, the mileage traveled after the vehicle starts, the initial SOC of the battery, and the target SOC of the battery;

[0010] (4) Collect the current vehicle speed data in real time, match it with the clustering center of each working condition obtained in step (1), match to the nearest clustering center to determine the current working condition category, and correct the initial equivalent factor under this working condition based on the SOC reference trajectory to obtain the adaptive equivalent factor;

[0011] (5) According to the adaptive equivalent factor, allocate the optimal output power of the engine and the motor in real time to minimize the equivalent fuel consumption.

[0012] As an optimization, in step (1), the feature block is sampled at intervals of (1 to 1.5) s.

[0013] As an optimization, in step (2), the traversal method is used to screen the preset equivalent factor that minimizes the fuel consumption among the preset equivalent factors,

[0014] As an optimization, in step (3), the calculation formula of the SOC reference trajectory is as follows:

[0015]

[0016] where SOC init is the SOC at the initial stage of the journey, SOC end is the target SOC at the end of the journey, L is the total mileage, and X is the mileage traveled.

[0017] As an optimization, in step (4), the calculation formula of the adaptive equivalent factor is as follows:

[0018]

[0019] where s0 is the initial equivalent factor, α is the estimated correction coefficient, SOC(t) is the current actual SOC value, and SOC ref (t) is the reference trajectory value.

[0020] As an optimization, in step (5), the power distribution of the engine and the motor is as shown in the following formula:

[0021]

[0022] where, and The optimal control power of the engine and the motor at time t, P e (t) and P b (t) are the powers of the engine and the motor at time t respectively, and b e (t) is the fuel consumption rate of the engine, Q lhv is the calorific value constant of the engine, and s(t) is the adaptive equivalent factor.

[0023] A computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computer, the method as described above is implemented.

[0024] A computer program product, including a computer program. When the computer program is executed by a computer, the method as described above is implemented.

[0025] Compared with the prior art, the present invention has the following beneficial effects: The present invention can identify the driving conditions and dynamically adjust the equivalent factor, so that the vehicle always distributes the powers of the engine and the motor in an optimal manner under different road conditions, thereby improving the fuel economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] To make the objectives, 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 with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention usually described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present invention provided in the drawings here is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0028] As Figure 1 shown, the management method of adaptive energy distribution based on driving condition identification in this specific embodiment includes the following steps:

[0029] (1) Based on the historical driving data of the vehicle, several time periods are divided, and the vehicle speed data within several time periods are continuously sampled respectively to obtain several feature blocks. The sampling time interval of the sampling block is 1 s, and the vehicle speeds at 10 time points are collected. The input feature v involved in the k-means clustering algorithm can be specifically expressed as v = [v t , v t-1 , … v t-8,v t-9 , the vehicle speed in different intervals is used to divide several characteristic blocks into 3 working conditions, and the k-means clustering algorithm is used to calculate the clustering center of each working condition. The three clustering centers are c1 = [c 1,1 ,c 1,2 ,…,c 1,10 , c2 = [c 2,1 ,c 2,2 ,…,c 2,10 , c3 = [c 3,1 ,c 3,2 ,…,c 3,10 ;

[0030] (2) For each working condition, the preset equivalent factors of each characteristic block within the working condition are screened, and the preset equivalent factor with the minimum fuel consumption is selected as the initial equivalent factor of the working condition, denoted as s1, s2, and s3 respectively;

[0031] (3) According to the total mileage between the current driving starting point and the destination, the mileage traveled after the vehicle starts, the initial SOC of the battery, and the target SOC of the battery, calculate the linearly varying SOC reference trajectory;

[0032] (4) Real-time collect the current vehicle speed data, collect the working condition characteristic parameters [x1, x2, …, x 10 at 10 vehicle speed points, and calculate the distance from the current moment to each clustering center: Among them, j = 1, 2, 3, corresponding to the three clustering centers respectively, and match with the clustering center of each working condition obtained in step (1). Match to the nearest clustering center to determine the current working condition category. The current working condition block is the category with the smallest center distance from which clustering center. Based on the SOC reference trajectory, correct the initial equivalent factor under this working condition to obtain the adaptive equivalent factor;

[0033] (5) According to the adaptive equivalent factor, allocate the optimal output power of the engine and the motor in real time to minimize the equivalent fuel consumption.

[0034] In this specific embodiment, in step (1), the characteristic block is sampled at intervals of (1 - 1.5) s.

[0035] In this specific embodiment, in step (2), the traversal method is used to screen the preset equivalent factor with the minimum fuel consumption among the preset equivalent factors,

[0036] In this specific embodiment, in step (3), the calculation formula of the SOC reference trajectory is as follows:

[0037]

[0038] Among them, SOCinit is the SOC at the beginning of the journey, and SOC end is the target SOC at the end of the journey, L is the total mileage, and X is the mileage already traveled.

[0039] In this specific embodiment, in step (4), the calculation formula of the adaptive equivalent factor is as follows:

[0040]

[0041] where s0 is the initial equivalent factor, α is the estimated correction coefficient, SOC(t) is the current actual SOC value, and SOC ref (t) is the reference trajectory value.

[0042] In this specific embodiment, in step (5), the power distribution between the engine and the motor is shown as follows:

[0043]

[0044] where and are the optimal control powers of the engine and the motor at time t, and P e (t) and P b (t) are the powers of the engine and the motor at time t respectively, b e (t) is the fuel consumption rate of the engine, Q lhv is the calorific value constant of the engine, and s(t) is the adaptive equivalent factor.

[0045] A computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computer, the method as described above is implemented.

[0046] A computer program product, including a computer program. When the computer program is executed by a computer, the method as described above is implemented.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Those of ordinary skill in the art should understand that any modifications or equivalent replacements made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions should be covered within the scope of the claims of the present invention.

Claims

1. A management method for adaptive energy distribution based on working condition recognition, characterized in that: Including the following steps: (1) Based on the historical driving data of the vehicle, divide several time periods and continuously sample the vehicle speed data within each time period respectively to obtain several feature blocks. Divide the several feature blocks into n working conditions according to different interval vehicle speeds, where n≥2 and is a positive integer. Use the k-means clustering algorithm to calculate the clustering center of each working condition; (2) For each working condition, screen the preset equivalent factors of each feature block within the working condition, and select the preset equivalent factor with the minimum fuel consumption as the initial equivalent factor of the working condition; (3) Calculate the linearly varying SOC reference trajectory according to the total mileage between the current driving starting point and the destination, the mileage traveled after the vehicle starts, the initial SOC of the battery, and the target SOC of the battery; (4) Real-time collect the current vehicle speed data, match it with the clustering center of each working condition obtained in step (1), match to the nearest clustering center to determine the current working condition category, and correct the initial equivalent factor under this working condition based on the SOC reference trajectory to obtain the adaptive equivalent factor; (5) According to the adaptive equivalent factor, allocate the optimal output power of the engine and the motor in real time to minimize the equivalent fuel consumption.

2. The management method for adaptive energy allocation based on working condition identification according to claim 1, characterized in that: In step (1), the feature block is sampled at intervals of (1 to 1.5) s.

3. The management method for adaptive energy allocation based on working condition recognition according to claim 1, characterized in that: In step (2), the traversal method is used to screen the preset equivalent factor that minimizes the fuel consumption among the preset equivalent factors.

4. The management method for adaptive energy allocation based on working condition recognition according to claim 1, characterized in that: In step (3), the calculation formula of the SOC reference trajectory is as follows: Among them, SOC init is the SOC at the start of the journey, and SOC end is the target SOC at the end of the journey. L is the total mileage, and X is the mileage already traveled.

5. The management method for adaptive energy allocation based on working condition recognition according to claim 4, characterized in that: In step (4), the calculation formula of the adaptive equivalent factor is as follows: Among them, s0 is the initial equivalent factor, α is the estimated correction coefficient, SOC(t) is the current actual SOC value, and SOC ref (t) is the reference trajectory value.

6. The management method for adaptive energy allocation based on working condition recognition according to claim 1, characterized in that: In step (5), the power distribution of the engine and the motor is shown in the following formula: Among them, and are the optimal control powers of the engine and the motor at time t, P e (t) and P b (t) are the powers of the engine and the motor at time t respectively, b e (t) is the fuel consumption rate of the engine, Q lhv is the calorific value constant of the engine, and s(t) is the adaptive equivalent factor.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer, the method described in any one of claims 1 to 6 is implemented.

8. A computer program product, characterized in that: Including a computer program, when the computer program is executed by a computer, the method described in any one of claims 1 to 6 is implemented.

Images