An ecms strategy optimization method based on working condition clustering results of navigation information

Abstract

This invention provides an ECMS strategy optimization method based on navigation information-based condition clustering results, comprising: performing offline simulation based on real vehicle test data to obtain the segmentation of each test data segment; training a condition recognition neural network model on the test segments; cleaning and repairing key road condition signals in the navigation information to obtain repaired data; dividing the mileage window based on the repaired data to obtain corrections for congestion and gradient; calculating the condition characteristic parameters of each time window under the actual navigation repair data using the time windows divided based on the actual navigation repair data in steps three and four; clustering the test conditions according to the condition characteristic parameters and the neural network model, and matching the corresponding optimal equivalent factor according to the database in step one; and correcting the navigation clustering test condition output results based on the optimal equivalent factor obtained from historical vehicle speed clustering. This invention significantly reduces fuel consumption.

Description

Technical Field

[0001] This invention mainly relates to ECMS strategy optimization methods, and more particularly to an ECMS strategy optimization method based on the working condition clustering results of navigation information. Background Technology

[0002] Hybrid electric vehicles (HEVs) consist of a drive system comprised of multiple power sources. The rational distribution and coordination of power and energy among these sources enables the vehicle to optimize fuel economy while meeting power demands. Existing Equivalent Fuel Consumption Minimization Strategy (ECMS) optimizes energy consumption based on standard driving cycles. However, actual driving conditions differ significantly from standard driving cycles, making it difficult for existing ECMS strategies to adapt to these conditions and further optimize energy consumption specifically for real-world driving scenarios. Summary of the Invention

[0003] Therefore, this invention introduces navigation information to implement a navigation-based working condition clustering method and ECMS strategy optimization based on the clustering results. It consists of two parts: the first part involves obtaining a sample library of fuel consumption and state of charge (SOC) corresponding to different fuel consumption factors under different working conditions through offline simulation using real vehicle data; the second part involves segmenting and clustering the road conditions to be driven based on navigation information, and matching the optimal ECMS fuel consumption conversion factor based on the clustering results. In the part involving obtaining the sample library of fuel consumption and SOC corresponding to different fuel consumption factors under different working conditions through offline simulation using real vehicle data, the real vehicle driving data is first preprocessed. Then, in the simulation environment, based on the processed data, an iterative shooting algorithm (ISA) is used to obtain the sample library of fuel consumption and SOC corresponding to different fuel consumption factors under different working conditions. In the part of segmenting and clustering the road conditions to be driven based on navigation information, and matching the optimal fuel consumption conversion factor such as ECMS based on the clustering results, the navigation data first needs to be preprocessed and segmented into the nearest row. Based on the segmentation results, the operating characteristics of each operating window are calculated and clustered to obtain the corresponding sample operating conditions, and the corresponding optimal fuel consumption factor is selected.

[0004] It should be understood that the general description above and the detailed description below are exemplary and illustrative, and are intended to provide further explanation of this disclosure.

[0005] To address the aforementioned technical problems, this invention provides an ECMS strategy optimization method based on navigation information and condition clustering results, characterized in that the method includes:

[0006] Step 1: Perform offline simulation based on real vehicle data to obtain the segment division of each segment of vehicle data.

[0007] Step 2: Train the operating condition recognition neural network model on the running segment;

[0008] Step 3: Clean and repair key traffic signals in the navigation information to obtain repaired data;

[0009] Step 4: Based on the repaired data, divide the mileage window to obtain corrections for congestion and gradient;

[0010] Step 5: Using the time windows divided based on the actual navigation repair data in Steps 3 and 4, calculate the operating condition characteristic parameters of each time window under the actual navigation repair data.

[0011] Step six: Based on the working condition characteristic parameters of step five and the neural network model of step two, perform clustering of working conditions, and match the corresponding optimal equivalent factor according to the database of step one.

[0012] Step 7: Correct the navigation clustering output results based on the optimal equivalent factor obtained from historical vehicle speed clustering.

[0013] Preferably, this invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that the calculation methods for the working condition characteristic parameters of each time window used in step five and step two include:

[0014] Average vehicle speed:

[0015]

[0016] Average acceleration:

[0017]

[0018] Average deceleration:

[0019]

[0020] Idle time ratio:

[0021]

[0022] Average driving speed

[0023]

[0024] speed standard deviation

[0025]

[0026] Acceleration standard deviation

[0027]

[0028] Deceleration standard deviation

[0029]

[0030] Where v_i is the vehicle speed at time i in the running segment, t_acc is the acceleration time of the running segment, t_dec is the deceleration time of the running segment, t is the duration of the running segment, t' is the time during which the vehicle speed is not zero, N1 is the time during which the total speed change of the running segment is not zero, N2 is the time during which the acceleration of the running segment is not zero, and N3 is the time during which the deceleration of the running segment is not zero. It is the positive acceleration value at time i in the runtime segment. It is the reverse acceleration value at time i of the running segment, with the positive direction being the direction of vehicle movement.

[0031] Preferably, the present invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that step three further includes:

[0032] Clean and repair key traffic signals in navigation information. Traffic information for each road segment includes average vehicle speed, road speed limit, gradient and congestion level.

[0033] The removed data is replaced with data predicted using the quadratic exponential smoothing method.

[0034] Preferably, the present invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that step four further includes:

[0035] Based on the repair data from step three, the mileage window is divided, and the division is adjusted according to road congestion and gradient.

[0036] The data repair process involves dividing the data into time windows, with adjustments made based on road congestion and gradient.

[0037] Preferably, this invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that the cleaning rules in step three include:

[0038] When the average vehicle speed exceeds the maximum speed limit by 1.1, clear the data for that road segment.

[0039] When the average vehicle speed is greater than the maximum vehicle speed limit × 0.7, the congestion level is 4, and the data for that road segment is cleared.

[0040] When the average vehicle speed is less than 0.2 times the maximum speed limit, the congestion level is 1, and the data for that road segment is cleared.

[0041] Preferably, the present invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that step one further includes:

[0042] Step 11: Divide each segment of sports car data into running segments according to certain division rules. The division rules include: if the time between a car starting and stopping is greater than 60 seconds, then 60 seconds is considered as one running segment; if the time between a car starting and stopping is less than 60 seconds, then one car starting and stopping is considered as one running segment.

[0043] Step 12: Based on the data after segmentation, conduct simulation experiments. Record the final SOC and fuel consumption of each running segment under different discharge and charging equivalent factors using the cyclic shooting method. Finally, obtain a database of SOC and fuel consumption corresponding to different equivalent factors under each running segment.

[0044] Preferably, the present invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that the cyclic shooting method in step 12 includes:

[0045] The initial condition is SOC = 50%, the incremental condition is discharge equivalent factor 2.0 to 4.0, charge equivalent factor 2.0 to 4.0, and the incremental step size is 0.5.

[0046] Preferably, the present invention further provides an ECMS strategy optimization method based on the working condition clustering results of navigation information, characterized in that step two further includes:

[0047] The obtained working condition characteristic parameters and the labels of each running segment in step one are used as inputs to train and validate the neural network model.

[0048] The hidden layer and output layer of the neural network model are selected with 10 and 4 neurons respectively. After 46 iterations, a neural network model capable of performing working condition clustering is obtained.

[0049] Compared with existing technologies, the present invention has the following advantages: it performs working condition clustering based on different navigation information such as road congestion and slope, and uses this as an ECMS strategy optimization method, which greatly reduces fuel consumption. Attached Figure Description

[0050] Embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. Preferred embodiments of the present disclosure will now be described in detail, examples of which are illustrated in the drawings. Wherever possible, the same reference numerals will be used in all the drawings to denote the same or similar parts. Furthermore, although the terminology used in this disclosure is selected from commonly known and used terminology, some terms referenced in this disclosure may have been chosen by the applicant at his or her judgment, and their detailed meanings are explained in the relevant sections of the description herein. Moreover, this disclosure should be understood not only by the actual terms used, but also by the meaning implied by each term.

[0051] The above and other objects, features and advantages of the present invention will become apparent to those skilled in the art from the detailed description thereof, with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart of the ECMS strategy optimization method based on the working condition clustering results of navigation information according to the present invention;

[0053] Figure 2(1) shows the data of a certain actual sports car;

[0054] Figure 2(2) shows the results of segmenting actual sports car data according to the segmentation rules;

[0055] Figure 3(1) is a fuel consumption table with different charge-discharge equivalent factors under a certain working condition (JP_JE05_SHIQU_923S);

[0056] Figure 3(2) shows the fuel consumption surface plots with different charge-discharge equivalent factors;

[0057] Figure 3(3) is a table of the final SOC values ​​of different charge-discharge equivalent factors under a certain operating condition (JP_JE05_SHIQU_923S);

[0058] Figure 3(4) shows the surface plots of the final SOC values ​​for different charge-discharge equivalence factors;

[0059] Figure 4 A schematic diagram showing the iterative results of the neural network model for clustering working conditions and the results of working condition identification;

[0060] Figure 5 A diagram illustrating real-time data cleaning and repair for navigation. Detailed Implementation

[0061] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this application. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0062] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include plural forms. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0063] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0064] In the description of this application, it should be understood that the orientation or positional relationship indicated by directional terms such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is usually based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this application and simplifying the description. Unless otherwise stated, these directional terms do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the scope of protection of this application; the directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0065] For ease of description, spatial relative terms such as "above," "on top of," "on the upper surface of," "above," etc., are used herein to describe the spatial positional relationship of a device or feature as shown in the figures to other devices or features. It should be understood that spatial relative terms are intended to encompass different orientations in use or operation beyond the orientation of the device as described in the figures. For example, if the device in the figures were inverted, a device described as "above" or "on top of" other devices or structures would subsequently be positioned as "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below." The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatial relative descriptions used herein will be interpreted accordingly.

[0066] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is merely for the purpose of distinguishing the corresponding components. Unless otherwise stated, these terms have no special meaning and therefore should not be construed as limiting the scope of protection of this application. In addition, although the terminology used in this application is selected from commonly known and used terms, some terms mentioned in this application's specification may have been chosen by the applicant according to his or her judgment, and their detailed meanings are explained in the relevant sections of this description. Moreover, this application should be understood not only through the actual terms used, but also through the meaning implied by each term.

[0067] Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, various steps can be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more steps may be removed from these processes.

[0068] This invention introduces navigation information to implement a navigation-information-based working condition clustering method and an ECMS strategy optimization based on the clustering results, consisting of two parts:

[0069] The first part is to obtain the fuel consumption and SOC sample library corresponding to different fuel consumption factors under different working conditions based on offline simulation of real vehicle data.

[0070] The second part involves segmenting and clustering the road conditions to be driven based on navigation information, and matching the optimal ECMS fuel consumption conversion factor based on the clustering results. In the part where fuel consumption and SOC sample libraries corresponding to different fuel consumption factors under different operating conditions are obtained through offline simulation of real vehicle data, the real vehicle driving data is first preprocessed. Then, in the simulation environment, based on the processed data, an iterative shooting algorithm (ISA) is used to obtain the fuel consumption and SOC sample libraries corresponding to different fuel consumption factors under different operating conditions. In the part where segmenting and clustering the road conditions to be driven based on navigation information and matching the optimal ECMS fuel consumption conversion factor based on the clustering results, the navigation data first needs to be preprocessed and segmented. Based on the segmentation results, the operating characteristics of each operating window are calculated and clustered to obtain the corresponding sample operating conditions, and the corresponding optimal fuel consumption factor is selected.

[0071] Please see Figure 1 The diagram shown is a control flowchart of the present invention, and the steps described in conjunction with the flowchart are as follows:

[0072] Step 1: Perform offline simulation based on real-world sports car data;

[0073] First, the running segments are divided. Then, a database of SOC and fuel consumption corresponding to different equivalent factors is established for each running segment, which serves as the training and validation database for the clustering recognition neural network model.

[0074] The offline simulation step in this process, which generates a database of SOC and fuel consumption corresponding to different equivalent factors under different runtime segments, further includes:

[0075] Step 11: First, the running segments of each sports car data segment need to be divided.

[0076] The specific division rules are as follows: if the time between a car starting and stopping is greater than 60 seconds, then 60 seconds is considered one running segment; if the time between a car starting and stopping is less than 60 seconds, then one running segment is considered one running segment. Figure 2(1) and 2(2) As shown, Figure 2(1) is a data of a certain sports car, and Figure 2(2) is the result of segmenting the actual sports car data according to the segmentation rules; where 5A and 6A represent the number of segments, 5A means 5 segments and 6A means 6 segments.

[0077] Each segment of sports car data was obtained from the actual vehicle under four preset operating conditions. Therefore, the labels for each segment of data were obtained based on preset conditions, namely: urban congestion, smooth urban traffic, suburbs, and highways.

[0078] Step 12: Based on the data after segmentation, conduct simulation experiments using a cyclic firing method. Initial conditions: SOC = 50%; Incremental conditions: Discharge equivalent factor 2.0–4.0; Charging equivalent factor 2.0–4.0; Incremental step size: 0.5. Record the final SOC and fuel consumption for each running segment under different discharge and charging equivalent factors. Finally, obtain a database of SOC and fuel consumption corresponding to different equivalent factors for each running segment, such as... Figures 3(1) to 3(4) As shown.

[0079] Figure 3(1) is a fuel consumption table for different charge-discharge equivalent factors under a certain working condition (JP_JE05_SHIQU_923S), with the horizontal axis representing the charge equivalent factor and the column axis representing the discharge equivalent factor; Figure 3(2) is a fuel consumption surface diagram for different charge-discharge equivalent factors, with the X-axis and Y-axis representing the charge equivalent factor and the discharge equivalent factor, respectively, and the Z-axis representing the fuel consumption under the corresponding charge-discharge factor combination in this cycle working condition; Figure 3(3) is a table of the final SOC values ​​for different charge-discharge equivalent factors under a certain working condition (JP_JE05_SHIQU_923S); and Figure 3(4) is a surface diagram of the final SOC values ​​for different charge-discharge equivalent factors.

[0080] Step 2: Train the working condition recognition neural network model based on the running segments obtained in Step 1.

[0081] The training steps for the working condition recognition neural network model are as follows:

[0082] Step S21: Calculate the feature parameters for each running segment. The parameter names and calculation formulas are as follows:

[0083] Average vehicle speed:

[0084]

[0085] Average acceleration:

[0086]

[0087] Average deceleration:

[0088]

[0089] Idle time ratio:

[0090]

[0091] Average driving speed

[0092]

[0093] speed standard deviation

[0094]

[0095] Acceleration standard deviation

[0096]

[0097] Deceleration standard deviation

[0098]

[0099] In the formulas for the above characteristic parameters, v_i is the vehicle speed at time i of the running segment, t_acc is the acceleration time of the running segment, t_dec is the deceleration time of the running segment, t is the duration of the running segment, t' is the time during which the vehicle speed of the running segment is not zero, N1 is the time during which the total speed change of the running segment is not zero, N2 is the time during which the acceleration of the running segment is not zero, and N3 is the time during which the deceleration of the running segment is not zero.

[0100] Step 22: Using the feature parameters of each running segment obtained in Step 21 and the labels of each running segment obtained in Step 11 as inputs to the neural network model for training and validation. The hidden layer and output layer are selected with 10 and 4 neurons respectively. After 46 iterations, a neural network model capable of clustering operating conditions is obtained, as shown below. Figure 4 As shown.

[0101] This is the fuel consumption and final SOC value of a certain simulated urban cycle (JP_JE05_shiqu_923s). The X-axis and Y-axis are the charging equivalent factor and discharging equivalent factor, respectively, and the Z-axis is the fuel consumption (curve a) and final SOC (curve b) under the corresponding charging and discharging factor combination in this cycle.

[0102] Step 3: Clean and repair key traffic signals in the navigation information.

[0103] In this step, key road condition signals in the navigation information are cleaned and repaired. The traffic information for each road segment includes the following four levels: average vehicle speed, road speed limit, gradient, and congestion.

[0104] The congestion levels here range from 1 to 4, indicating that traffic congestion gradually worsens, with 1 representing smooth traffic and 4 representing congestion.

[0105] The signal cleaning and repair steps further include:

[0106] Step 31, data cleaning is performed according to the following rules:

[0107] Rule 1: If the average vehicle speed is greater than the maximum speed limit * 1.1, then clear the data for that road segment.

[0108] Rule 2: If the average vehicle speed is greater than the maximum speed limit * 0.7 and the congestion level is 4, then the data for that road segment should be cleared.

[0109] Rule 3: If the average vehicle speed is less than the maximum speed limit * 0.2, and the congestion level is 1, then the data for that road segment should be cleared.

[0110] Step 32: Replace the removed data with data predicted using the quadratic exponential smoothing method. The formula for quadratic exponential smoothing is as follows:

[0111] F (t+T) =a t +b t *T (9)

[0112] Among them, F (t+T0 It is the predicted value for period t+T, a t ,b t It is an intermediate variable, which can be obtained by the following formula:

[0113] a t =2*S t (1)-S t (2) (10)

[0114]

[0115] Where S_t(1) and S_t(2) are the first exponential smoothing value and the second exponential smoothing value in period t, respectively, and can be obtained by the following formula:

[0116] S t (1)=α*Y t-1 +(1-α)*S t-1 (1) (12)

[0117] S t (2)=α*S t (1)+(1-α)*S t-1 (2) (13)

[0118] Where α is the smoothing coefficient, with a value range of (0, 1), which can be selected based on empirical values.

[0119] Data cleaning and repair, such as Figure 5 As shown.

[0120] Step 4: Divide the mileage window based on the repaired data from Step 3. The division is adjusted according to road congestion, slope, etc.

[0121] In this step, time windows are divided based on the repair data from step 3, and the division is adjusted according to road congestion, slope, etc.

[0122] The unit time window M = 5s, the initial time window is M0 = 6M = 30s, and the actual time window size M i = M * C, where C is a correction factor. The correction factor varies with road congestion, gradient, and speed limit. The more congested the road, the lower the speed limit, the steeper the gradient, the smaller C is, and the smaller the time window, and vice versa. The correction factor C varies between 0.5 and 1.5.

[0123] Step 5: Calculate the operating condition characteristic parameters for each mileage window.

[0124] In step 5, the operating condition characteristic parameters for each time window under the actual navigation repair data are calculated using the time windows divided based on the actual navigation repair data calculated in steps 3 and 4, and the operating condition characteristic parameter calculation method for each time window in step 21. These parameters include the average vehicle speed, average acceleration, average deceleration, idling time ratio, and average driving speed for each actual navigation data time window.

[0125] In step 6, the working conditions are clustered based on the working condition characteristic parameters calculated in step 5 and the neural network model obtained in step 2, and the corresponding optimal equivalent factor is matched according to the database in step 1.

[0126] Step 7: Correct the navigation clustering output results based on the optimal equivalent factor obtained from historical vehicle speed clustering.

[0127] Through the above scheme, this invention designs a working condition clustering method based on navigation information and an ECMS strategy optimization based on the clustering results. Specifically, the method of segmenting real-vehicle test data to obtain the neural network model training set is worthy of protection; the method of extracting feature parameters from the segmented data and performing mean clustering to label the neural network model training set is worthy of protection; the equivalent factor cyclic targeting method based on a hardware-in-the-loop test bench is worthy of protection to obtain the SOC and fuel consumption database corresponding to different fuel consumption factors under different working conditions; and the method of correcting the navigation prediction results based on the working condition identification results using historical vehicle speeds to enable the hybrid strategy optimization strategy to be corrected according to the driver's actual driving conditions is worthy of protection.

[0128] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0129] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0130] Some aspects of this application can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The aforementioned hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." The processor may be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. Furthermore, aspects of this application may manifest as computer products residing in one or more computer-readable media, including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), optical discs (e.g., compressed CDs, digital multifunction DVDs, etc.), smart cards, and flash memory devices (e.g., cards, sticks, key drives, etc.).

[0131] A computer-readable medium may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and so on, or suitable combinations thereof. A computer-readable medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or similar media, or any combination of the above media.

[0132] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0133] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0134] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0135] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of scope in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0136] Although this application has been described with reference to specific embodiments, those skilled in the art should recognize that the above embodiments are only used to illustrate this application, and various equivalent changes or substitutions can be made without departing from the spirit of this application. Therefore, any changes or modifications to the above embodiments within the essential spirit of this application will fall within the scope of the claims of this application.

Claims

1. An ECMS strategy optimization method based on navigation information and condition clustering results, characterized in that, The method includes: Step 1: Perform offline simulation based on real vehicle data. Divide the running segments of each segment of the running data according to the preset division rules. Based on the divided running segments, conduct simulation experiments using the cyclic shooting method to obtain a database of SOC and fuel consumption corresponding to different equivalent factors under each running segment. Step 2: Train the operating condition recognition neural network model on the running segment; Step 3: Clean and repair key traffic signals in the navigation information to obtain repaired data; Step four: Divide the mileage window based on the repair data from step three, and adjust the division according to road congestion and gradient. The data repair process involves dividing the data into time windows, with adjustments made based on road congestion and gradient. Step 5: Based on the time windows divided by the actual navigation repair data in Steps 3 and 4, calculate the operating condition characteristic parameters of each time window under the actual navigation repair data. Step six: Based on the working condition feature parameters from step five and the neural network model trained in step two, cluster the working conditions and match the corresponding optimal equivalent factor according to the database obtained in step one. Step 7: Correct the navigation clustering output results based on the optimal equivalent factor obtained from historical vehicle speed clustering; Step one further includes: Step 11: Divide each segment of sports car data into running segments according to certain division rules. The division rules include: if the time between a car starting and stopping is greater than 60 seconds, then 60 seconds is considered as one running segment; if the time between a car starting and stopping is less than 60 seconds, then one car starting and stopping is considered as one running segment. Step 12: Conduct simulation experiments based on the data after segmentation. Record the final SOC and fuel consumption of each running segment under different discharge and charge equivalent factors using the cyclic shooting method. Finally, obtain a database of SOC and fuel consumption corresponding to different equivalent factors under each running segment.

2. The ECMS strategy optimization method based on navigation information and working condition clustering results according to claim 1, characterized in that, The calculation methods for the operating condition characteristic parameters of each time window used in step two and step five include: Average vehicle speed: Average acceleration: , Average deceleration: ， Idle time ratio: ， Average driving speed ， speed standard deviation ， Acceleration standard deviation ， Deceleration standard deviation ， in, Let i be the vehicle speed at time i in this runtime segment. The acceleration time of this runtime segment, The deceleration time of this runtime segment, The duration of this running segment, For the time segment in which the vehicle speed is not zero, The time during which the total velocity change of this runtime segment is not zero. The time during which the acceleration of this runtime segment is not zero. The time during which the deceleration of this runtime segment is not zero. It is the positive acceleration value at time i in the runtime segment. It is the reverse acceleration value at time i of the running segment, with the positive direction being the direction of vehicle movement.

3. The ECMS strategy optimization method based on navigation information and working condition clustering results according to claim 1, characterized in that, Step three further includes: Clean and repair key traffic signals in navigation information. Traffic information for each road segment includes average vehicle speed, road speed limit, gradient and congestion level. The removed data is replaced with data predicted using the quadratic exponential smoothing method.

4. The ECMS strategy optimization method based on navigation information and working condition clustering results according to claim 3, characterized in that, The cleaning rules in step three include: When the average vehicle speed exceeds the maximum speed limit by 1.1, clear the data for that road segment. When the average vehicle speed is greater than the maximum vehicle speed limit × 0.7, the congestion level is 4, and the data for that road segment is cleared. When the average vehicle speed is less than 0.2 times the maximum speed limit, the congestion level is 1, and the data for that road segment is cleared.

5. The ECMS strategy optimization method based on navigation information and working condition clustering results according to claim 1, characterized in that, The cyclic shooting method in step 12 includes: The initial condition is SOC=50%, the incremental condition is discharge equivalent factor 2.0~4.0, charge equivalent factor 2.0~4.0, and the incremental step size is 0.

5.

6. The ECMS strategy optimization method based on navigation information and working condition clustering results according to claim 5, characterized in that, Step two further includes: The obtained working condition characteristic parameters and the labels of each running segment in step one are used as inputs to train and validate the neural network model. The hidden layer and output layer of the neural network model are selected with 10 and 4 neurons respectively. After 46 iterations, a neural network model capable of performing working condition clustering is obtained.

Images