Scenario-based operating condition construction method and energy management system based thereon

Abstract

This invention provides a method for constructing scenario operating conditions and a vehicle energy management system based on the method. The method includes: S1, collecting real-world vehicle operating conditions in a certain park scenario and constructing a real-world vehicle operating condition database; S2, based on the real-world vehicle operating condition database, constructing an operating condition state recognition method based on micro-travel segments, and generating an operating condition state sequence library by recognizing the state of micro-travel operating condition segments; S3, establishing an algorithm for mining frequent transition sequences based on historical state sequences, processing the operating condition state sequence library, and extracting frequently occurring operating condition state sequences from the real-world vehicle operating condition database; S4, extracting operating condition segments corresponding to the frequently occurring operating condition state sequences from the real-world vehicle operating condition database, and splicing them together to form scenario operating conditions. This invention realizes the construction of scenario operating conditions for new energy vehicles in park application scenarios, thereby realizing the construction of a scenario operating condition that can represent the kinematic and dynamic characteristics of new energy vehicles in application scenarios.

Description

Technical Field

[0001] This invention relates to the field of automotive energy-saving control technology, specifically to a method for constructing scenario operating conditions and an energy management system based on the method applicable to new energy vehicles. Background Technology

[0002] With rapid economic development, industrial parks have sprung up. Creating low-carbon, energy-saving, and green industrial parks has become an effective way to alleviate energy shortages. The number of parks and their dedicated vehicles is increasing year by year, leading to rising energy consumption, especially in the transportation sector. Therefore, electrifying dedicated vehicles in industrial parks and reducing energy consumption has become a key technological approach.

[0003] Vehicle Energy Management (EMS) is the core of energy consumption optimization for new energy vehicles. The EMS of new energy vehicles is often calibrated based on extensive standard operating condition tests. The calibration strategy is stored in the controller in the form of rule tables related to operating conditions and vehicle status. During vehicle operation, real-time control quantities are solved according to the rule tables and actual vehicle operating conditions. To ensure that the calibrated EMS closely matches the vehicle's operating conditions for higher economic efficiency, the calibration conditions must comprehensively and accurately cover the kinematic and temporal characteristics of the actual driving scenarios. For vehicles operating in industrial parks, their operating conditions are distinctly unique. Constructing scenario conditions that encompass these characteristics is crucial for improving the calibration efficiency and energy saving of EMS for special-purpose vehicles in industrial parks.

[0004] However, current calibration conditions mostly use standard operating conditions, such as the Worldwide Harmonized Light Vehicle Test Cycle (WLTC) and the China Light Vehicle Driving Cycle (CLTC). These standard operating conditions cannot fully and accurately represent the application scenarios in the park. The maximum speeds of WLTC and CLTC are approximately 130 km / h and 90 km / h, respectively, far exceeding the speed limits of the park. Moreover, their idling rates are only about 13% and 20%, respectively, but the speed limits in the park are low, the traffic flow is high, and the idling ratio of shuttle buses is relatively high. Therefore, standard operating conditions cannot reflect the driving conditions in the park, and EMS calibrated based on them cannot achieve energy saving for vehicles in the park.

[0005] The current mainstream method for constructing scenario operating conditions follows this process: First, the operating conditions in the real vehicle operating condition database are segmented into short-stroke segments; then, the short-stroke segments are identified and numbered; next, the Markov-Monte Carlo (MMC) principle is used to concatenate short-stroke segments with different state numbers; finally, the corresponding state operating condition segments are extracted from the database to form the scenario operating conditions. However, this method has problems. The short-stroke segments start and end at the idling speed segment and include operating condition segments of various driving modes, which can be further segmented into micro-stroke segments. When solving for the operating condition features of short-stroke segments, the features of micro-stroke segments with different modes or large feature differences are easily neutralized, making the solution results unable to reflect the true features and making it difficult to construct scenario operating conditions that reflect the true kinematic features of the scenario. Furthermore, MMC has strong randomness and cannot find frequently occurring operating condition state sequences in the scenario database. When constructing operating conditions, the time series features of the scenario cannot be considered, resulting in the existing method being unable to construct scenario operating conditions that reflect the true time series features of the scenario, and the calibrated EMS is difficult to adapt to the application scenario.

[0006] A patent search revealed invention patent CN107463992B, which discloses a method for predicting the driving conditions of hybrid vehicles based on segment waveform training. This method includes: dividing the entire vehicle driving condition into a combination of several driving condition segments, where each segment refers to the process from vehicle start-up to the first braking stop, comprising a starting phase, a driving phase, and a braking phase; training a neural network using these driving condition segments; then, leveraging the neural network's powerful fitting ability, analyzing and calculating the input historical driving condition information, and matching the historical information with the trained driving condition segments; finally, finding the segment in the trained driving condition segments that most closely matches the historical information, and outputting the subsequent driving condition information of that segment as the prediction result, thus completing the prediction of future driving conditions. This patent focuses on predicting vehicle driving conditions but does not delve into specific scenario conditions and related energy management.

[0007] In summary, in view of the problems of the existing technology, it is urgent to solve the key task of researching a scenario construction method and an energy management system for new energy vehicles based on the method. Summary of the Invention

[0008] To address the shortcomings of existing technologies, the purpose of this invention is to provide a method for constructing scenario conditions and an energy management system based on the method suitable for new energy vehicles.

[0009] A scenario condition construction method provided by the present invention includes:

[0010] Step S1: Collect real-world vehicle operating conditions data for vehicles in a specific park setting and build a real-world vehicle operating condition database.

[0011] Step S2: Based on the real vehicle operating condition database, construct an operating condition status recognition method based on micro-travel segments, and generate an operating condition status sequence library by recognizing the status of micro-travel operating condition segments;

[0012] Step S3: Establish a frequent transition sequence mining algorithm based on historical state sequences, process the working condition state sequence library, and extract the frequently occurring working condition state sequences in the actual vehicle working condition database.

[0013] Step S4: Extract the working condition segments corresponding to the frequently occurring working condition state sequences from the real vehicle working condition database and splice them together to form the scene working condition.

[0014] Preferably, step S2 includes the following sub-steps:

[0015] Step S2.1: Based on the real vehicle operating condition database, the real vehicle operating conditions are divided into short-stroke segments;

[0016] Step S2.2: Divide each short-trip segment into micro-trip segments according to different driving modes;

[0017] Step S2.3: Perform k-means clustering on the micro-travel segments under different driving modes, and label the category number of each micro-travel segment as the working condition status;

[0018] Step S2.4: Based on the micro-travel segments with the labeled category number, the micro-travel segments of each working condition in the real vehicle working condition database are labeled with a status, that is, the real vehicle working condition sequence is transformed into a working condition status sequence, and a working condition status sequence library is obtained.

[0019] Preferably, in step S2.1, the short-stroke segment is a working condition segment where both the starting and ending segments are idling segments; the idling segment is a segment where the real-time vehicle speed is less than or equal to 4 km / h and the absolute value of the acceleration is less than or equal to 0.15 m / s². 2 The vehicle speed sequence.

[0020] Preferably, in step S2.2, the driving mode classification criteria are as follows: acceleration mode is defined as a real-time vehicle speed greater than 4 km / h and a real-time acceleration greater than 0.15 m / s². 2 The vehicle speed sequence was divided into acceleration micro-stroke segments according to the actual vehicle conditions, based on the acceleration mode; the deceleration mode was defined as a real-time vehicle speed greater than 4 km / h and a real-time acceleration less than -0.15 m / s². 2 The vehicle speed sequence was divided into deceleration micro-stroke segments according to the actual vehicle conditions based on the deceleration mode; the cruise mode is defined as a real-time vehicle speed greater than 4 km / s and a real-time acceleration absolute value less than 0.15 m / s². 2 The vehicle speed sequence was segmented according to the actual vehicle conditions to obtain cruise micro-travel segments; the idle speed mode was defined as a real-time vehicle speed less than or equal to 4 km / h and an absolute acceleration value less than or equal to 0.15 m / s².2 The vehicle speed sequence is divided into idle speed micro-stroke segments according to the idle speed mode and the actual vehicle conditions.

[0021] Preferably, in step S2.3, the acceleration micro-stroke segments are divided into 3 categories based on acceleration time, initial velocity, and average velocity characteristics; the deceleration micro-stroke segments are divided into 4 categories based on deceleration time, final velocity, and average velocity characteristics; and the cruise micro-stroke segments are divided into 3 categories based on average velocity and cruise time characteristics.

[0022] Preferably, in step S2.3, the operating conditions of the acceleration micro-stroke segment are marked as 1, 2, and 3 respectively; the operating conditions of the deceleration micro-stroke segment are marked as 4, 5, 6, and 7 respectively; the operating conditions of the cruise micro-stroke segment are marked as 8, 9, and 10 respectively; and the operating conditions of the idling micro-stroke segment are marked as 11.

[0023] Preferably, step S3 includes the following sub-steps:

[0024] Step S3.1: For each short stroke segment in the working condition state sequence library, determine the starting segment and record the working condition state of the starting segment. Set the idling micro-stroke segment as the starting segment of the short stroke segment and mark the working condition state as 11.

[0025] Step S3.2: Based on the operating condition sequence library, calculate the transition probability between every two of the 11 operating conditions determined in step S2.3, as shown in the following formula:

[0026]

[0027] Where, p i,j z represents the transition probability from operating condition i to operating condition j; i,j This represents the number of times the transition from operating condition i to operating condition j occurs in the operating condition sequence library.

[0028] Step S3.3: For any working state i among the 11 working states, arrange the transition probabilities of working state i to each of the other working states in descending order.

[0029] Step S3.4: Starting from working condition 11, find the next working condition that is easy to transition to in the working condition sequence library. The next working condition that is easy to transition to is the working condition with a higher transition probability calculated according to step S3.3. Record working condition 11 as the m-th level historical state sequence and record the next working condition that is easy to transition to as the n-th level easy transition state.

[0030] Step S3.5: Add the nth level easily transitioned state to the end of the mth level historical state sequence to form a new historical state sequence. The historical state sequence is defined as the (m+1)th level historical state sequence.

[0031] Step S3.6: Find the next level working condition that the (m+1)th level historical state sequence is easy to transition to in the working condition state sequence library, and construct the next level historical state sequence.

[0032] Step S3.7, repeat steps S3.5 to S3.6 until the working condition corresponding to the idling micro-stroke segment is found, i.e., working condition 11, then stop.

[0033] This invention also provides an energy management system suitable for new energy vehicles, based on the above-mentioned scenario-based operating condition construction method, including:

[0034] Module M1 collects real-world vehicle operating conditions in a specific park setting and builds a real-world vehicle operating condition database.

[0035] Module M2, based on a real vehicle operating condition database, constructs an operating condition status recognition method based on micro-travel segments. By recognizing the status of micro-travel operating condition segments, it generates an operating condition status sequence library.

[0036] Module M3 establishes a frequent transition sequence mining algorithm based on historical state sequences to process the working condition state sequence library and extract the frequently occurring working condition state sequences in the real vehicle working condition database.

[0037] Module M4 extracts working condition segments corresponding to frequently occurring working condition state sequences from the real vehicle working condition database and splices them together to form scene working conditions.

[0038] Module M5, based on scenario conditions, uses rule learning algorithms to calibrate energy management strategies, outputs a calibrated rule table, and constructs an energy management system suitable for new energy vehicles in application scenarios.

[0039] Preferably, module M5 includes:

[0040] Unit M5.1, based on a fuel cell hybrid vehicle, uses a dynamic programming algorithm to solve the scenario conditions and obtain the optimal control law. The optimal control law includes the SOC trajectory, fuel cell output power, and demand power. The combination of the SOC trajectory value, fuel cell output power value, and demand power value at each moment is used as a sample.

[0041] Unit M5.2, based on samples, uses a rule-based learning algorithm to learn the relationship between fuel cell output power, power demand, and SOC.

[0042] Preferably, unit M5.2 includes the following sub-units:

[0043] Subunit M5.2.1 uses a subtractive clustering algorithm to cluster samples, thereby obtaining the number of categories for SOC, fuel cell output power, and power demand.

[0044] Subunit M5.2.2, based on the number of categories, sets SOC and demand power as inputs to the energy management strategy, and sets the output power of the fuel cell as the output. For each type of input combination formed by SOC and demand power, it finds the fuel cell output power type with the highest frequency of occurrence and forms a rule table of types.

[0045] Subunit M5.2.3, based on the number of categories, solves the cluster center of each category, fills the value of the cluster center into the corresponding type in the rule table, and forms the calibration rules of the energy management strategy.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. This invention realizes the construction of scenario conditions for new energy vehicles in park application scenarios, thereby realizing the construction of a scenario condition that can represent the kinematic and dynamic characteristics of new energy vehicles in application scenarios.

[0048] 2. The scene condition construction algorithm provided by this invention proposes a state recognition method based on micro-condition segments, which can preserve the significant kinematic features of the scene condition.

[0049] 3. This invention also realizes the consideration of state transition probability in the construction of scene conditions and realizes the mining of frequent state transition sequences in the database, thereby preserving the time series features in the database. Attached Figure Description

[0050] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0051] Figure 1 This is a flowchart illustrating a method for constructing scene conditions according to an embodiment of the present invention;

[0052] Figure 2 This is a schematic diagram of the frequent transition sequence mining algorithm based on historical state sequences in an embodiment of the present invention. Detailed Implementation

[0053] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the scope of protection of the present invention.

[0054] This invention discloses a method for constructing scenario conditions for new energy vehicles based on micro-particle feature recognition and frequent transfer sequence mining, and develops an energy management system for new energy vehicles based on this method.

[0055] Example 1:

[0056] Figure 1 This is a flowchart illustrating a scenario construction method according to an embodiment of the present invention.

[0057] like Figure 1 As shown, this embodiment provides a method for constructing scene conditions, including the following steps:

[0058] Step S1: Collect real-world vehicle operating conditions in a certain park setting and build a real-world vehicle operating condition database.

[0059] Step S2: Based on the real vehicle operating condition database, construct an operating condition status recognition method based on micro-travel segments, and generate an operating condition status sequence library by recognizing the status of micro-travel operating condition segments.

[0060] Specifically, step S2 includes the following sub-steps:

[0061] Step S2.1: Based on the real vehicle operating condition database, the real vehicle operating conditions are divided into short-stroke segments.

[0062] In this embodiment, the short-stroke segment is a working condition segment where both the initial and final segments are idling segments; the idling segment is a segment where the real-time vehicle speed is less than or equal to 4 km / h and the absolute value of the acceleration is less than or equal to 0.15 m / s². 2 The vehicle speed sequence.

[0063] Step S2.2: Divide each short-trip segment into micro-trip segments according to different driving modes.

[0064] In this embodiment, the driving mode classification criteria are as follows: acceleration mode is defined as a real-time vehicle speed greater than 4 km / h and a real-time acceleration greater than 0.15 m / s². 2 The vehicle speed sequence was divided into acceleration micro-stroke segments according to the actual vehicle conditions, based on the acceleration mode; the deceleration mode was defined as a real-time vehicle speed greater than 4 km / h and a real-time acceleration less than -0.15 m / s². 2 The vehicle speed sequence was divided into deceleration micro-stroke segments according to the actual vehicle conditions based on the deceleration mode; the cruise mode is defined as a real-time vehicle speed greater than 4 km / h and a real-time acceleration absolute value less than 0.15 m / s². 2 The vehicle speed sequence was segmented according to the actual vehicle conditions to obtain cruise micro-travel segments; the idle speed mode was defined as a real-time vehicle speed less than or equal to 4 km / h and an absolute acceleration value less than or equal to 0.15 m / s². 2 The vehicle speed sequence is divided into idle speed micro-stroke segments according to the idle speed mode and the actual vehicle conditions.

[0065] Step S2.3: Perform k-means clustering on the micro-travel segments under different driving modes, and label the category number of each micro-travel segment as the working condition status.

[0066] Specifically, acceleration micro-travel segments are classified into three categories based on acceleration time, initial velocity, and average velocity characteristics; deceleration micro-travel segments are classified into four categories based on deceleration time, final velocity, and average velocity characteristics; and cruising micro-travel segments are classified into three categories based on average velocity and cruising time characteristics.

[0067] In this embodiment, the operating conditions of the acceleration micro-stroke segment are marked as 1, 2, and 3, respectively; the operating conditions of the deceleration micro-stroke segment are marked as 4, 5, 6, and 7, respectively; the operating conditions of the cruise micro-stroke segment are marked as 8, 9, and 10, respectively; and the operating conditions of the idling micro-stroke segment are marked as 11.

[0068] Step S2.4: Based on the micro-travel segments with the labeled category number, the micro-travel segments of each working condition in the real vehicle working condition database are labeled with a status, that is, the real vehicle working condition sequence is transformed into a working condition status sequence, and a working condition status sequence library is obtained.

[0069] Step S3: Establish a frequent transition sequence mining algorithm based on historical state sequences, process the working condition state sequence library, and extract the frequently occurring working condition state sequences in the actual vehicle working condition database.

[0070] Figure 2 This is a schematic diagram of the frequent transition sequence mining algorithm based on historical state sequences in an embodiment of the present invention.

[0071] like Figure 2 As shown, step S3 includes the following sub-steps:

[0072] Step S3.1: For each short stroke segment in the working condition state sequence library, determine the starting micro-stroke segment and record the working condition state of the starting micro-stroke segment. Set the idling micro-stroke segment as the starting segment of the short stroke segment and mark the working condition state as 11.

[0073] Step S3.2: Based on the operating condition state sequence library, calculate the transition probability between every two states among the 11 operating conditions determined in step S2.3, as shown in the following formula:

[0074]

[0075] Where, p i,j z represents the transition probability from operating condition i to operating condition j; i,j This represents the number of times the transition from operating condition i to operating condition j occurs in the operating condition sequence library.

[0076] Step S3.3: For any working state i among the 11 working states, arrange the transition probabilities of working state i to each of the other working states in descending order.

[0077] Step S3.4: Starting from operating state 11, find the next operating state that is easy to transition to in the operating state sequence library. The next operating state that is easy to transition to is the operating state with a higher transition probability calculated according to step S3.3. Record operating state 11 as the m-th level historical state sequence and record the next operating state that is easy to transition to as the n-th level easy-to-transition state.

[0078] In this embodiment, the criterion for determining "easy to switch to" is to select the top two working conditions with the highest probability of switching; m=1, n=1.

[0079] Step S3.5: Add the nth level easily transitioned state to the end of the mth level historical state sequence to form a new historical state sequence. The historical state sequence is defined as the (m+1)th level historical state sequence.

[0080] Step S3.6: Find the next level of working condition that the (m+1)th level of historical state sequence is easy to transition to in the working condition state sequence library, and construct the next level of historical state sequence.

[0081] Step S3.7, repeat steps S3.5 to S3.6 until the working condition corresponding to the idling micro-stroke segment is found, i.e., working condition 11, then stop.

[0082] Step S4: Extract the working condition segments corresponding to the frequently occurring working condition state sequences from the real vehicle working condition database and splice them together to form the scene working condition.

[0083] Example 2:

[0084] This embodiment provides an energy management system suitable for new energy vehicles, based on a scenario condition construction method in Embodiment 1 above, including:

[0085] Module M1 collects real-world vehicle operating conditions in a specific park setting and builds a real-world vehicle operating condition database.

[0086] Module M2, based on a real vehicle operating condition database, constructs an operating condition status recognition method based on micro-travel segments. By recognizing the status of micro-travel operating condition segments, it generates an operating condition status sequence library.

[0087] Module M3 establishes a frequent transition sequence mining algorithm based on historical state sequences to process the working condition state sequence library and extract the frequently occurring working condition state sequences in the actual vehicle working condition database.

[0088] Module M4 extracts operating condition segments corresponding to frequently occurring operating condition state sequences from the real vehicle operating condition database and splices them together to form scene operating conditions.

[0089] Module M5, based on scenario conditions, uses rule learning algorithms to calibrate energy management strategies, outputs a calibrated rule table, and constructs an energy management system suitable for new energy vehicles in application scenarios.

[0090] Specifically, module M5 includes:

[0091] Unit M5.1, based on a fuel cell hybrid vehicle, uses a dynamic programming algorithm to solve the scenario conditions and obtain the optimal control law. The optimal control law includes the SOC trajectory, fuel cell output power, and demand power. The combination of the SOC trajectory value, fuel cell output power value, and demand power value at each moment is used as a sample.

[0092] Unit M5.2, based on samples, uses a rule-based learning algorithm to learn the relationship between fuel cell output power, power demand, and SOC.

[0093] Furthermore, unit M5.2 includes the following sub-units:

[0094] Subunit M5.2.1 uses a subtractive clustering algorithm to cluster samples, thereby obtaining the number of categories for SOC, fuel cell output power, and power demand.

[0095] Subunit M5.2.2, based on the number of categories, sets SOC and demand power as inputs to the energy management strategy, and sets the output power of the fuel cell as the output. For each type of input combination formed by SOC and demand power, it finds the fuel cell output power type with the highest occurrence frequency and forms a rule table for the type.

[0096] Subunit M5.2.3, based on the number of categories, solves the cluster center of each category, fills the value of the cluster center into the corresponding type in the rule table, and forms the calibration rules of the energy management strategy.

[0097] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0098] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for constructing scene conditions, characterized in that, Includes the following steps: Step S1: Collect real-world vehicle operating conditions in the park setting and build a real-world vehicle operating condition database; Step S2: Based on the real vehicle operating condition database, construct an operating condition status recognition method based on micro-travel segments, and generate an operating condition status sequence library by recognizing the status of micro-travel operating condition segments; Step S3: Establish a frequent transition sequence mining algorithm based on historical state sequences, process the working condition state sequence library, and extract the frequently occurring working condition state sequences in the actual vehicle working condition database. Step S4: Extract the working condition segments corresponding to the frequently occurring working condition state sequences from the real vehicle working condition database, and splice them together to form the scene working condition. Step S2 includes the following sub-steps: Step S2.1: Based on the real vehicle operating condition database, the real vehicle operating conditions are divided into short-stroke segments; Step S2.2: Divide each short-trip segment into micro-trip segments according to different driving modes; Step S2.3: Perform k-means clustering on the micro-travel segments under different driving modes, and label the category number of each micro-travel segment as the working condition status; Step S2.4: Based on the micro-travel segments with the marked category number, the micro-travel segments of each working condition in the real vehicle working condition database are marked with a status, that is, the real vehicle working condition sequence is transformed into a working condition status sequence to obtain a working condition status sequence library. Step S3 includes the following sub-steps: Step S3.1: For each short stroke segment in the working condition state sequence library, determine the starting segment and record the working condition state of the starting segment. Set the idling micro-stroke segment as the starting segment of the short stroke segment and mark the working condition state as 11. Step S3.2: Based on the operating condition state sequence library, calculate the transition probability between every two states among the 11 operating conditions determined in step S2.3, as shown in the following formula: in, This represents the transition probability from operating condition i to operating condition j; This represents the number of times the transition from operating condition i to operating condition j occurs in the operating condition sequence library. Step S3.3: For any working condition i among the 11 working conditions, arrange the transition probabilities of working condition i to each of the other working conditions from largest to smallest. Step S3.4: Starting from working condition 11, find the next working condition that is easy to transition to in the working condition sequence library. The next working condition that is easy to transition to is the working condition with a high transition probability calculated according to step S3.

3. Record working condition 11 as the m-th level historical state sequence and record the next working condition that is easy to transition to as the n-th level easy-to-transition state. Step S3.5: Add the nth level easily transitioned state to the end of the mth level historical state sequence to form a new historical state sequence, which is defined as the (m+1)th level historical state sequence. Step S3.6: Find the next level of working condition that the (m+1)th level historical state sequence is easy to transition to in the working condition state sequence library, and construct the next level of historical state sequence. Step S3.7, repeat steps S3.5 to S3.6 until the working condition corresponding to the idling micro-stroke segment is found, i.e., working condition 11, then stop.

2. The method for constructing a scene and working conditions according to claim 1, characterized in that, In step S2.1, the short-stroke segment is a working condition segment where both the initial and final segments are idling segments; the idling segment is a segment where the real-time vehicle speed is less than or equal to 4 km / h and the absolute value of the acceleration is less than or equal to 0.15 m / s². 2 The vehicle speed sequence.

3. The method for constructing a scene and working conditions according to claim 2, characterized in that, In step S2.2, the driving mode classification criteria are as follows: acceleration mode is defined as a real-time vehicle speed greater than 4 km / h and a real-time acceleration greater than 0.15 m / s². 2 The vehicle speed sequence is used to cut the actual vehicle conditions according to the acceleration mode to obtain acceleration micro-stroke segments; The deceleration mode is when the real-time vehicle speed is greater than 4 km / h and the real-time acceleration is less than -0.15 m / s². 2 The vehicle speed sequence is used to cut the actual vehicle operating condition according to the deceleration mode to obtain the deceleration micro-stroke segment; Cruise control mode is when the real-time vehicle speed is greater than 4 km / h and the absolute value of the real-time acceleration is less than 0.15 m / s². 2 The vehicle speed sequence is used to cut the actual vehicle conditions according to the cruise mode to obtain cruise micro-travel segments; The idle mode is for vehicles with a real-time speed of less than or equal to 4 km / h and an absolute acceleration of less than or equal to 0.15 m / s². 2 The vehicle speed sequence is used to cut the actual vehicle operating conditions according to the idle speed mode to obtain the idle speed micro-stroke segment.

4. The method for constructing a scene and working conditions according to claim 3, characterized in that, In step S2.3, the acceleration micro-travel segments are classified into three categories based on acceleration time, initial velocity, and average velocity characteristics; the deceleration micro-travel segments are classified into four categories based on deceleration time, final velocity, and average velocity characteristics; and the cruise micro-travel segments are classified into three categories based on average velocity and cruise time characteristics.

5. The method for constructing a scene and working conditions according to claim 4, characterized in that, In step S2.3, the operating conditions of the acceleration micro-stroke segment are marked as 1, 2, and 3 respectively; the operating conditions of the deceleration micro-stroke segment are marked as 4, 5, 6, and 7 respectively; the operating conditions of the cruise micro-stroke segment are marked as 8, 9, and 10 respectively; and the operating conditions of the idling micro-stroke segment are marked as 11.

6. An energy management system suitable for new energy vehicles, based on a scenario operating condition construction method according to any one of claims 1 to 5, characterized in that, include: Module M1 collects real-world vehicle operating conditions in the park setting and builds a real-world vehicle operating condition database. Module M2, based on the real vehicle operating condition database, constructs an operating condition status recognition method based on micro-travel segments, and generates an operating condition status sequence library by recognizing the status of micro-travel operating condition segments; Module M3 establishes a frequent transition sequence mining algorithm based on historical state sequences to process the working condition state sequence library and extract the frequently occurring working condition state sequences in the real vehicle working condition database. Module M4 extracts working condition segments corresponding to the frequently occurring working condition state sequences from the real vehicle working condition database and splices them together to form scene working conditions. Module M5, based on the aforementioned scenario conditions, uses a rule learning algorithm to calibrate energy management strategies, outputs a calibrated rule table, and constructs an energy management system suitable for new energy vehicles in the application scenario.

7. An energy management system suitable for new energy vehicles according to claim 6, characterized in that, The module M5 includes: Unit M5.1, based on a fuel cell hybrid vehicle, uses a dynamic programming algorithm to solve the scenario conditions and obtain the optimal control law. The optimal control law includes the SOC trajectory, fuel cell output power, and demand power. The combination of the SOC trajectory value, fuel cell output power value, and demand power value at each moment is used as a sample. Unit M5.2, based on the sample, uses a rule learning algorithm to learn the relationship between fuel cell output power, demand power, and SOC.

8. An energy management system suitable for new energy vehicles according to claim 7, characterized in that, The unit M5.2 includes the following sub-units: Subunit M5.2.1 uses a reduced clustering algorithm to cluster the samples, thereby obtaining the number of categories for SOC, fuel cell output power, and required power; Subunit M5.2.2, based on the number of categories, sets the SOC and the required power as inputs to the energy management strategy, sets the output power of the fuel cell as the output, and for each type of input combination formed by the SOC and the required power, finds the fuel cell output power type with the highest frequency of occurrence and forms a rule table of types. Subunit M5.2.3, based on the number of categories, solves the cluster center of each category, fills the value of the cluster center into the corresponding type in the rule table, and forms the calibration rules of the energy management strategy.

Images