Plug-in hybrid electric vehicle gear shifting and energy saving control method, device and system

Abstract

The invention discloses a gear-shifting and energy-saving control method, device and system for a plug-in hybrid electric vehicle. The method comprises the following steps: acquiring vehicle driving data; c-means clustering analysis is carried out on the vehicle driving data; according to the vehicle driving data after clustering analysis, a BP neural network is constructed, and the BP neural network is utilized to carry out on-line optimization on a gear shifting sequence; determining a reference curve of the SOC, and comparing the reference curve with the current SOC to iteratively update the equivalent factor; and gear shifting and power distribution are optimized through real-time updating of the equivalent fuel oil minimum strategy. By the adoption of the technical scheme, the plug-in hybrid electric vehicle adapts to different working conditions, gear shifting and power distribution are optimized, the problem of mixed integers in a control algorithm is avoided, and better fuel economy is shown under hybrid drive.

Description

Technical Field

[0001] The present invention belongs to the technical field of hybrid electric vehicle energy management, and in particular relates to a plug-in hybrid electric vehicle shifting and energy-saving control method, device and system. Background Art

[0002] Under the background of carbon peak and carbon neutrality policies, the popularity and market growth of hybrid electric vehicles have achieved remarkable development. Due to the existence of multiple power sources, the shift control and energy management strategy of plug-in hybrid electric vehicles have a great impact on the fuel economy and power of the vehicle.

[0003] Currently, in vehicle operation, gear shift control is usually designed based on rules or expert experience. When designing the energy management strategy of hybrid vehicles, if the gear shift sequence is taken into consideration, the optimization problem will become more complicated. Because the gear shift sequence is a discrete decision process, it involves selecting different gear ratios to adapt to different driving conditions. This choice usually causes the optimization problem to become a mixed integer problem, that is, there are both integer variables and continuous variables in the problem. Mixed integer problems are usually more difficult to solve than pure continuous optimization problems because they may have multiple local optimal solutions and the solution process may require more computing resources. Since mixed integer problems are more complex than continuous optimization problems, the amount of computation required to solve such problems will increase significantly. This may mean that it takes longer to find the optimal solution or more powerful computing equipment may be required.

[0004] In addition, due to the complexity and unpredictability of traffic conditions, it is difficult to determine an optimal equivalence factor. The equivalence factor is an indicator of energy distribution efficiency, which affects the fuel consumption performance of the car under different driving conditions. The unpredictable SOC trajectory of the battery increases the difficulty of determining the optimal equivalence factor because it is necessary to take into account multiple possible driving conditions and battery states. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a plug-in hybrid electric vehicle shifting and energy-saving control method, device and system, which can adapt the plug-in hybrid electric vehicle to different working conditions, optimize shifting and power distribution, avoid mixed integer problems in the control algorithm, and show better fuel economy under hybrid drive.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] A plug-in hybrid electric vehicle shifting and energy-saving control method, comprising:

[0008] Collect vehicle driving data;

[0009] Perform C-means cluster analysis on vehicle driving data;

[0010] According to the vehicle driving data after cluster analysis, a BP neural network is constructed, and the shift sequence is optimized online using the BP neural network;

[0011] Determine the reference curve of SOC and compare it with the current SOC to iteratively update the equivalent factor;

[0012] Real-time updates of the fuel-minimization strategy optimize gear shifting and power distribution.

[0013] Preferably, the vehicle driving data includes the vehicle driving speed, accelerator pedal opening, brake pedal opening, engine speed, accelerator opening change rate, and brake opening change rate.

[0014] As a preferred embodiment, through the finder behavior mechanism, follower behavior mechanism and detection warning mechanism of the sparrow search algorithm, the equivalent factor is iteratively updated by comparing the reference curve of the optimized SOC with the current SOC.

[0015] The present invention also provides a plug-in hybrid electric vehicle shifting and energy-saving control device, comprising:

[0016] An acquisition module is used to collect vehicle driving data;

[0017] Preprocessing module, used to perform C-means cluster analysis on vehicle driving data;

[0018] The first processing module is used to construct a BP neural network based on the vehicle driving data after cluster analysis, and use the BP neural network to perform online optimization of the shift sequence;

[0019] The second processing module is used to determine a reference curve of the SOC and compare it with the current SOC to iteratively update the equivalent factor;

[0020] The third processing module is used for real-time updating of the equivalent fuel minimum strategy to optimize gear shifting and power distribution.

[0021] Preferably, the vehicle driving data includes the vehicle driving speed, accelerator pedal opening, brake pedal opening, engine speed, accelerator opening change rate, and brake opening change rate.

[0022] Preferably, the second processing module is used to iteratively update the equivalent factor by comparing the reference curve of the optimized SOC with the current SOC through the finder behavior mechanism, follower behavior mechanism and detection warning mechanism of the sparrow search algorithm.

[0023] The present invention also provides a plug-in hybrid electric vehicle shifting and energy-saving control system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes the plug-in hybrid electric vehicle shifting and energy-saving control method when executed by the processor.

[0024] Compared with the prior art, the technical effects of the present invention are as follows:

[0025] 1. Optimize the shifting strategy to achieve a smoother and more efficient shifting process, reduce the impact and delay of shifting, and improve driving comfort and vehicle performance. Predict driving needs through intelligent algorithms, adjust the working status of the engine and motor in time, and ensure the continuity and stability of power transmission.

[0026] 2. Improved energy management, effective use of battery energy, and extended EV driving range through precise energy distribution strategies. Under different working conditions, such as urban congestion, high-speed cruising or mountain climbing, the proportion of power source usage is automatically adjusted to maximize energy efficiency.

[0027] 3. Avoid mixed integer problems, reduce computational complexity, and make the control system more efficient and easy to implement. Avoid dealing with complex integer programming problems in real-time control, and improve the response speed and reliability of the control system.

[0028] 4. Enhanced fuel economy: In hybrid drive mode, the optimized power distribution strategy significantly reduces fuel consumption and emissions. Even when the battery power is low, it can maintain high energy efficiency and improve overall energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0030] Figure 1 The present invention is a flowchart of a method for controlling gear shifting and energy saving of a plug-in hybrid electric vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] Embodiment 1:

[0034] like Figure 1 As shown, an embodiment of the present invention provides a plug-in hybrid electric vehicle shifting and energy-saving control method, and the specific steps are as follows:

[0035] Step S1, collecting vehicle driving data;

[0036] Step S2, performing C-means cluster analysis on the collected data;

[0037] Step S3, according to the C-means cluster analysis results, 70% of the data is used as a training set, 15% of the data is used as a validation set, and 15% is used as a test set;

[0038] Step S4: construct a BP neural network and use the BP neural network to perform online optimization on the shift sequence.

[0039] Step S5, using the sparrow search algorithm to determine the reference curve of SOC, and compare it with the current SOC to iteratively update the equivalent factor;

[0040] Step S6: Real-time update of the equivalent fuel minimum strategy optimizes the gear shift and power distribution, showing better fuel economy under hybrid drive and achieving energy saving effect.

[0041] Furthermore, in the step S1, the vehicle driving data is collected, and the test equipment mainly includes a GPS sensor, an information collection instrument, a power supply, etc. The information collection instrument collects signals such as the vehicle driving speed, accelerator pedal opening, brake pedal opening, engine speed, accelerator opening change rate, brake opening change rate, etc. through CAN communication;

[0042] Furthermore, in step S2, C-means cluster analysis is performed on the collected data, which mainly includes initializing cluster centers, calculating membership matrix, updating cluster centers, and iterating to obtain cluster results.

[0043] The initialization of cluster centers uses a random selection method to select c data points from the data set as initial cluster centers. The cluster center vector V is a c×d matrix, where c is the number of cluster centers and d is the characteristic dimension of the data.

[0044] The membership matrix is ​​calculated by calculating the membership of the data point according to the current cluster center. The membership matrix U is an n×c matrix, where n is the total number of data points. iTo each cluster center v j The membership degree u ij The calculation is as follows:

[0045]

[0046] Among them, d(x i ,v j ) is the data point x i and cluster center v j The Euclidean distance between them, m is the fuzziness factor, set to 2, and ∈ is a small constant added to avoid division by zero errors.

[0047] The cluster center is updated by using the membership matrix U to update the position of each cluster center. The new cluster center is estimated The calculation is as follows:

[0048]

[0049] Among them, x i is the ith data point.

[0050] The iterative clustering result is obtained by repeatedly calculating the membership matrix and updating the cluster center steps until the change of the membership matrix U or the cluster center vector V is less than the set threshold δ, that is, |V new -V old |<δ or |U new -U old When |<δ, the iteration ends and the clustering analysis results are obtained.

[0051] Furthermore, in step S4, a BP neural network is constructed, the network structure is determined, including the number of nodes in the input layer, hidden layer and output layer, and a suitable activation function is determined.

[0052] Furthermore, in step S5, the current SOC can be calculated by a vehicle model formula, and the calculation formula is as follows:

[0053]

[0054] Among them, SOC i is the initial SOC of the power battery, Q bat is the power battery capacity, I b is the power battery output current.

[0055]

[0056] Among them, U oc is the open circuit voltage of the power battery, R int is the internal resistance of the power battery, P bat It is the output power of the power battery.

[0057] Furthermore, in step S5, the sparrow search algorithm is divided into three steps: "discoverer behavior", "follower behavior" and "detection warning mechanism", and finally the equivalent factor is iteratively updated by comparing the reference curve of the optimized SOC with the current SOC;

[0058] The behavior of the discoverer, the position of each sparrow is X = (x 1 ,x 2 ,…x D ), fitness value f i =f(x 1 ,x 2 ,…x D ). There are N sparrows in this group of sparrows. In each generation, PN sparrows with the best position in the population are selected as discoverers, and the remaining N-PN sparrows are selected as followers.

[0059]

[0060] in, represents the d-dimensional position of the i-th individual in the t-th generation in the population, α is a uniform random number in (0,1], iter max is the constant with the largest number of iterations, Q is a standard normal distribution random number, R 2 is a uniform random number in [0,1], and ST is the warning threshold in the range of [0.5,1].

[0061] The follower behavior is that after the discoverer behavior is updated, the remaining sparrows adopt the follower behavior.

[0062]

[0063] Among them, xw is the worst position of the sparrows in the current population, and xb is the optimal position of the sparrows in the population.

[0064] The detection and early warning mechanism is that when danger approaches, both the discoverer and the follower will abandon the current position and move to a new position.

[0065]

[0066] Among them, β is a random number that conforms to the standard normal distribution, K is a uniform random number between [-1,1], ε is a small number to prevent the denominator from being unique, and f w is the fitness value of the sparrow in the worst position.

[0067] Furthermore, in step S6, the instantaneous equivalent fuel consumption It can be expressed as follows:

[0068]

[0069] in, is the instantaneous fuel consumption, is the equivalent fuel consumption of electricity, s(t) is the efficiency chain of fuel conversion into electricity, Q ln v is the low calorific value of the fuel, p is the penalty factor introduced, and the value of p is determined by the vehicle's current SOC and SOC ref Decide.

[0070] The constraints that the optimal control problem should satisfy are:

[0071]

[0072] Among them, T e_min and T e_max are the minimum and maximum torque of the engine, ω e_min and ω e_max are the minimum and maximum engine speed, T dm_min and T dm_max are the maximum and minimum torque of the driving motor, ω dm_min and ω dm_max They are the maximum and minimum speed of the drive motor, SOC min and SOC max They are the maximum and minimum SOC values ​​of the power battery set by the energy management strategy.

[0073] Embodiment 2:

[0074] The embodiment of the present invention further provides a plug-in hybrid electric vehicle shifting and energy-saving control device, comprising:

[0075] An acquisition module is used to collect vehicle driving data;

[0076] Preprocessing module, used to perform C-means cluster analysis on vehicle driving data;

[0077] The first processing module is used to construct a BP neural network based on the vehicle driving data after cluster analysis, and use the BP neural network to perform online optimization of the shift sequence;

[0078] The second processing module is used to determine a reference curve of the SOC and compare it with the current SOC to iteratively update the equivalent factor;

[0079] The third processing module is used for real-time updating of the equivalent fuel minimum strategy to optimize gear shifting and power distribution.

[0080] As an implementation method of an embodiment of the present invention, the vehicle driving data includes the vehicle driving speed, accelerator pedal opening, brake pedal opening, engine speed, accelerator opening change rate, and brake opening change rate.

[0081] As an implementation method of an embodiment of the present invention, the second processing module is used to iteratively update the equivalent factor by comparing the reference curve of the optimized SOC with the current SOC through the finder behavior mechanism, follower behavior mechanism and detection and warning mechanism of the sparrow search algorithm.

[0082] Embodiment 3:

[0083] An embodiment of the present invention further provides a plug-in hybrid electric vehicle shifting and energy-saving control system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes the plug-in hybrid electric vehicle shifting and energy-saving control method when executed by the processor.

[0084] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A plug-in hybrid electric vehicle shifting and energy-saving control method, characterized in that: include: Collect vehicle driving data; Perform C-means cluster analysis on vehicle driving data; According to the vehicle driving data after cluster analysis, a BP neural network is constructed, and the shift sequence is optimized online using the BP neural network; Determine the reference curve of SOC and compare it with the current SOC to iteratively update the equivalent factor; Real-time updates of the fuel-minimization strategy optimize gear shifting and power distribution.

2. The plug-in hybrid electric vehicle shifting and energy-saving control method according to claim 1, characterized in that: The vehicle driving data includes the vehicle driving speed, accelerator pedal opening, brake pedal opening, engine speed, accelerator opening change rate, and brake opening change rate.

3. The plug-in hybrid electric vehicle shifting and energy-saving control method according to claim 2, characterized in that: Through the discoverer behavior mechanism, follower behavior mechanism and detection and early warning mechanism of the sparrow search algorithm, the equivalent factor is iteratively updated by comparing the reference curve of the optimized SOC with the current SOC.

4. A plug-in hybrid electric vehicle shifting and energy-saving control device, characterized in that: include: An acquisition module is used to collect vehicle driving data; Preprocessing module, used to perform C-means cluster analysis on vehicle driving data; The first processing module is used to construct a BP neural network based on the vehicle driving data after cluster analysis, and use the BP neural network to perform online optimization of the shift sequence; The second processing module is used to determine a reference curve of the SOC and compare it with the current SOC to iteratively update the equivalent factor; The third processing module is used for real-time updating of the equivalent fuel minimum strategy to optimize gear shifting and power distribution.

5. The plug-in hybrid electric vehicle shifting and energy-saving control device according to claim 4, characterized in that: The vehicle driving data includes the vehicle driving speed, accelerator pedal opening, brake pedal opening, engine speed, accelerator opening change rate, and brake opening change rate.

6. The plug-in hybrid electric vehicle shifting and energy-saving control device according to claim 5, characterized in that: The second processing module is used to iteratively update the equivalent factor by comparing the reference curve of the optimized SOC with the current SOC through the finder behavior mechanism, follower behavior mechanism and detection warning mechanism of the sparrow search algorithm.

7. A plug-in hybrid electric vehicle shifting and energy-saving control system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the plug-in hybrid electric vehicle shifting and energy-saving control method as described in any one of claims 1 to 3 is executed.

Images