Method and device for predicting endurance mileage and electronic equipment

Abstract

The invention belongs to the field of electric vehicles, and discloses an endurance mileage prediction method and device and electronic equipment, and the method comprises the steps: dividing micro fragments according to historical vehicle driving data; a Markov Monte Carlo model is used for prediction according to the micro-fragments; and determining a corresponding energy consumption prediction value according to the obtained driving state prediction result, and determining a corresponding endurance mileage prediction value according to the energy consumption prediction value. The present invention captures subtle changes in driving characteristics by dividing historical vehicle driving data into microfragments. And then, by utilizing the random simulation capability of a Markov Monte Carlo model, predicting the driving state of the vehicle according to the micro-fragments, and finally, calculating an endurance mileage prediction value by predicting the driving state. The method can adapt to the change of the driving condition in real time, provides the endurance mileage prediction which is more in line with the actual driving scene, enables the prediction result to be more accurate, facilitates the optimization of the energy management of the electric vehicle and the improvement of the overall performance, and improves the user satisfaction at the same time.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicles, and in particular to a method, device, electronic device and computer-readable storage medium for predicting a cruising range. Background Art

[0002] With the popularity of electric vehicles, range prediction has become a key factor in evaluating electric vehicle performance. Range not only affects consumers' purchasing decisions, but is also an important consideration in the daily use of electric vehicles. At present, the electric vehicle range prediction methods on the market are mainly based on historical vehicle driving data, which is used to estimate the vehicle's energy consumption and remaining range under different conditions by analyzing these data.

[0003] However, existing range prediction methods have some limitations. First, these methods often rely on simplified energy consumption models and fail to fully consider the complex factors in the actual driving process. At the same time, traditional prediction methods cannot update and adapt to new driving conditions in real time, resulting in a large deviation between the prediction results and the actual range.

[0004] Therefore, how to improve the accuracy of electric vehicle range prediction is a technical problem to be solved by those skilled in the art. Summary of the invention

[0005] In order to solve the problem of low accuracy in predicting the cruising range of electric vehicles in the prior art, the present invention provides a method, device, electronic device and computer-readable storage medium for predicting the cruising range.

[0006] A method for predicting a cruising range, comprising:

[0007] Acquire historical vehicle travel data, and divide micro-segments according to the historical vehicle travel data;

[0008] Using a Markov Monte Carlo model to make predictions based on the micro-segments, a driving state prediction result is obtained;

[0009] A corresponding energy consumption prediction value is determined according to the driving state prediction result, and a corresponding cruising range prediction value is determined according to the energy consumption prediction value.

[0010] Optionally, the using of the Markov Monte Carlo model to predict according to the micro-segment to obtain a driving state prediction result includes:

[0011] Calculating a first characteristic parameter of each micro-segment; the first characteristic parameter includes at least one of an average vehicle speed, a difference between an end speed and a start speed, an average acceleration, a maximum acceleration, and a minimum acceleration;

[0012] Clustering the first characteristic parameter of each micro-segment using a fuzzy C-means clustering algorithm to obtain a first corresponding relationship between a driving state category and the first characteristic parameter;

[0013] Determine the driving state category of each of the micro-segments according to the first corresponding relationship to obtain a first driving state sequence;

[0014] The driving state transition probability is calculated according to the first driving state sequence, and the Markov Monte Carlo model is used to predict the second driving state sequence within a preset time period according to the driving state transition probability.

[0015] Optionally, determining a corresponding energy consumption prediction value according to the driving state prediction result includes:

[0016] Acquire a second corresponding relationship between the vehicle speed state and the vehicle speed;

[0017] Determining a first vehicle speed state sequence corresponding to different types of driving states according to the second corresponding relationship;

[0018] Calculating the vehicle speed state transition probability corresponding to each type of driving state according to the first vehicle speed state sequence;

[0019] Predicting a second vehicle speed state sequence corresponding to the second driving state sequence according to a vehicle speed state transition probability corresponding to each type of driving state using the Markov Monte Carlo model;

[0020] generating a corresponding vehicle speed-time curve according to the second vehicle speed state sequence;

[0021] The corresponding energy consumption prediction value is determined according to the vehicle speed-time curve.

[0022] Optionally, the using the Markov Monte Carlo model to predict the second vehicle speed state sequence corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state includes:

[0023] Repeatedly using the Markov Monte Carlo model to predict multiple second vehicle speed state sequences corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state;

[0024] The generating of the corresponding vehicle speed-time curve according to the second vehicle speed state sequence correspondingly includes:

[0025] Generate a plurality of the vehicle speed-time curves according to the plurality of the second vehicle speed state sequences;

[0026] The determining of the corresponding energy consumption prediction value according to the vehicle speed-time curve includes:

[0027] Determine the energy consumption prediction value corresponding to each of the vehicle speed-time curves, and determine the average value of the multiple energy consumption prediction values ​​as the final energy consumption prediction value.

[0028] Optionally, determining the corresponding energy consumption prediction value according to the vehicle speed-time curve includes:

[0029] Dividing the vehicle speed-time curve according to preset short trips to obtain a plurality of first short trip segments;

[0030] Calculating a second characteristic parameter of each of the first short trip segments; the second characteristic parameter includes at least one of average ambient temperature, average vehicle speed, average acceleration, 5% quantile of speed, 95% quantile of speed, 5% quantile of acceleration, and 95% quantile of acceleration;

[0031] Inputting each of the second characteristic parameters into a pre-trained energy consumption prediction model to obtain an energy consumption prediction value of each of the first short-trip segments output by the energy consumption prediction model;

[0032] The energy consumption prediction value corresponding to the vehicle speed-time curve is calculated according to the energy consumption prediction value of each of the first short-trip segments.

[0033] Optionally, the training process of the energy consumption prediction model includes:

[0034] Dividing the historical vehicle travel data according to the preset short trips to obtain a plurality of second short trip segments;

[0035] Calculating a second characteristic parameter and an energy consumption of each of the second short-trip segments;

[0036] Filtering the second short-trip segments according to the second characteristic parameter according to a preset filtering rule;

[0037] Normalizing the second characteristic parameters of the filtered second short-stroke segments to obtain training data;

[0038] Based on a meta-heuristic algorithm, a relationship between the training data and the energy consumption is established to obtain the energy consumption prediction model.

[0039] Optionally, determining a corresponding range prediction value according to the energy consumption prediction value includes:

[0040] Obtaining the battery meter power of the vehicle, and calculating the remaining battery energy based on the battery meter power;

[0041] The remaining driving range is calculated based on the remaining battery energy combined with the energy consumption prediction value corresponding to the vehicle speed-time curve.

[0042] A device for predicting a cruising range, comprising:

[0043] An acquisition module, used for acquiring historical vehicle driving data and dividing micro-segments according to the historical vehicle driving data;

[0044] A driving state prediction module, used for making predictions based on the micro-segments using a Markov Monte Carlo model to obtain a driving state prediction result;

[0045] The cruising range prediction module is used to determine the corresponding energy consumption prediction value according to the driving state prediction result, and to determine the corresponding cruising range prediction value according to the energy consumption prediction value.

[0046] An electronic device, comprising:

[0047] A processor and a memory, wherein the memory is used to store at least one instruction, and when the instruction is loaded and executed by the processor, the method for predicting the range as described in any one of the above is implemented.

[0048] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for predicting a range as described in any one of the above.

[0049] The method for predicting the range provided by the embodiment of the present invention divides the historical vehicle driving data into micro-segments, and uses the Markov Monte Carlo model to predict based on the micro-segments, then determines the corresponding energy consumption prediction value based on the obtained driving state prediction result, and finally determines the corresponding range prediction value based on the energy consumption prediction value. The present invention obtains and analyzes historical vehicle driving data, divides it into micro-segments to capture subtle changes in driving characteristics. Then, the random simulation capability of the Markov Monte Carlo model is used to predict the vehicle's driving state based on these micro-segments, and finally the range prediction value is calculated by predicting the driving state. The present invention can adapt to changes in driving conditions in real time, provide a range prediction that is more in line with actual driving scenarios, make the prediction results more accurate, help optimize the energy management of electric vehicles and improve overall performance, and at the same time improve user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A flowchart of a method for predicting a cruising range provided by an embodiment of the present invention;

[0052] Figure 2 for Figure 1 A flowchart of a practical expression of S02 in a provided method for predicting a range of mileage;

[0053] Figure 3 This is a rendering of a clustering number of 3 provided by an embodiment of the present invention;

[0054] Figure 4 for Figure 1 A flowchart of a practical expression of S03 in a provided method for predicting a range of mileage;

[0055] Figure 5 A schematic diagram of multiple vehicle speed-time curves provided by an embodiment of the present invention;

[0056] Figure 6 for Figure 4 A flowchart of a practical expression of step S26 in the method shown;

[0057] Figure 7 A flowchart of a training process of an energy consumption prediction model provided by an embodiment of the present invention;

[0058] Figure 8 A schematic diagram of the structure of a cruising range prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0060] It should be clear that the described embodiments are only some embodiments of the present invention, not all 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.

[0061] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0062] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0063] With the popularity of electric vehicles, range prediction has become a key factor in evaluating electric vehicle performance. Range not only affects consumers' purchasing decisions, but is also an important consideration in the daily use of electric vehicles. At present, the electric vehicle range prediction methods on the market are mainly based on historical vehicle driving data, which is used to estimate the vehicle's energy consumption and remaining range under different conditions by analyzing these data.

[0064] However, existing range prediction methods have some limitations. First, these methods often rely on simplified energy consumption models and fail to fully consider the complex factors in the actual driving process. At the same time, traditional prediction methods cannot update and adapt to new driving conditions in real time, resulting in a large deviation between the prediction results and the actual range.

[0065] Therefore, the present invention provides a method for predicting cruising range to solve the above problems.

[0066] Please refer to Figure 1 , is a flow chart of a method for predicting a cruising range provided by an embodiment of the present invention, comprising the following steps:

[0067] Step S01: acquiring historical vehicle driving data, and dividing the historical vehicle driving data into micro segments.

[0068] In this embodiment, the historical vehicle driving data is the data generated by the vehicle during the actual driving process. The historical vehicle driving data can be acquired by using a data reading module, and may include driving timestamp, vehicle speed, battery voltage, battery current, battery SOC, ambient temperature, etc.

[0069] These continuous driving data are divided into smaller time periods, called "micro segments". Each micro segment contains driving characteristics within a specific period of time. This division helps to identify and analyze the behavior patterns of vehicles under different driving conditions, and provides a detailed and representative data basis for subsequent energy consumption and range prediction.

[0070] In this embodiment, the purpose of obtaining historical vehicle driving data and dividing it into micro-segments is to build a refined database for analyzing and predicting the energy consumption and cruising range of electric vehicles under different driving conditions. By dividing the driving data into micro-segments, rapid changes and details in the driving process can be captured, such as acceleration, deceleration, constant speed driving, and idling. These micro-segments contain rich information, such as speed changes, acceleration, ambient temperature, etc. By analyzing these micro-segments, the energy consumption performance of the vehicle under similar conditions can be more accurately simulated and predicted, because short acceleration or deceleration events, such as these, have a significant impact on energy consumption. This method enables the prediction model to be trained and optimized based on these detailed driving patterns, thereby improving the accuracy and reliability of the cruising range prediction.

[0071] In some embodiments, data can be segmented into micro-segments using a specific time interval or event-driven method. For example, micro-segments can be divided according to vehicle start and stop, significant changes in speed, or a preset time window (such as 10 seconds or 1 minute). Each micro-segment represents a specific stage in the driving process, such as an acceleration stage, a constant speed cruising stage, or a deceleration stage.

[0072] On this basis, in order to improve the accuracy of the prediction, machine learning technology can be used to further classify and extract features from micro-fragments to identify key factors affecting energy consumption and range. This approach enables the prediction model to be trained and optimized based on these detailed driving patterns, thereby improving the accuracy and reliability of range prediction.

[0073] Step S02: using the Markov Monte Carlo model to make predictions based on the micro-segments to obtain a driving state prediction result.

[0074] In this embodiment, the Markov chain Monte Carlo (MCMC) model combines the memoryless assumption of the Markov chain and the randomness of the Monte Carlo simulation, so that it can predict the possible future driving state of the vehicle under the premise of knowing the current driving state without considering all previous driving history. By analyzing micro-segments in historical vehicle driving data, the MCMC model can simulate the transition probability of the vehicle under different driving states.

[0075] In the prediction process, the MCMC model uses random sampling combined with the randomness of Monte Carlo simulation to predict the various states that the vehicle may encounter in the future. This prediction takes into account the uncertainty and complexity of vehicle driving, such as traffic conditions, driving behavior, and environmental changes. Through multiple iterations and simulations, the MCMC model can provide a series of possible driving state sequences, thereby obtaining the predicted results of the driving state, which provides an important basis for the subsequent determination of the vehicle's energy consumption and cruising range, making the cruising range prediction more accurate and reliable.

[0076] Step S03, determining a corresponding energy consumption prediction value according to the driving state prediction result, and determining a corresponding cruising range prediction value according to the energy consumption prediction value.

[0077] Because traditional energy consumption predictions may rely too much on theoretical models or simplified assumptions without fully considering the dynamic changes in actual driving, the accuracy of electric vehicle range predictions is low.

[0078] In this embodiment, determining the energy consumption of the vehicle is closely related to the driving state, that is, different driving states, such as acceleration, deceleration, constant speed driving or idling, will have a significant impact on the battery consumption of the electric vehicle. Therefore, this embodiment can more accurately estimate the remaining energy of the battery and the distance that the vehicle can continue to travel by accurately predicting the energy consumption of the vehicle in various driving states.

[0079] By combining the prediction results of driving status, the energy consumption prediction value can reflect the actual energy consumption of the vehicle under specific driving conditions. Subsequently, using these energy consumption prediction values, the range prediction value can be calculated, which provides electric vehicle users with more reliable mileage information, helping them to better plan their trips and avoid inconveniences caused by insufficient power. In addition, this prediction method can also provide data support for the vehicle's energy management system, optimize battery usage strategies, extend battery life, and improve overall energy efficiency.

[0080] Based on the above technical solution, the method for predicting the range provided by the embodiment of the present invention is to divide the historical vehicle driving data into micro-segments, and use the Markov Monte Carlo model to predict based on the micro-segments, and then determine the corresponding energy consumption prediction value based on the obtained driving state prediction results, and finally determine the corresponding range prediction value based on the energy consumption prediction value. The present invention obtains and analyzes historical vehicle driving data, divides it into micro-segments to capture subtle changes in driving characteristics. Then, the random simulation capability of the Markov Monte Carlo model is used to predict the driving state of the vehicle based on these micro-segments, and finally the range prediction value is calculated by predicting the driving state. The present invention can adapt to changes in driving conditions in real time, provide a range prediction that is more in line with actual driving scenarios, make the prediction results more accurate, help optimize the energy management of electric vehicles and improve overall performance, and at the same time improve user satisfaction.

[0081] Please refer to Figure 2 ,for Figure 1 A flowchart of an actual performance of S02 in a method for predicting a range of mileage is provided. In some embodiments, step S02 mentions using a Markov Monte Carlo model to predict based on micro-segments to obtain a driving state prediction result, which may specifically include the following steps:

[0082] Step S11, calculating the first characteristic parameter of each micro-segment.

[0083] The first characteristic parameter includes at least one of an average vehicle speed, a difference between an end speed and a start speed, an average acceleration, a maximum acceleration, and a minimum acceleration.

[0084] In this embodiment, the vehicle driving data is analyzed to extract the first characteristic parameter of each micro segment, and the first characteristic parameter can quantitatively describe the driving characteristics of the vehicle during the micro segment.

[0085] By processing the large amount of collected vehicle driving data, it is possible to identify variables that significantly affect energy consumption and driving status. For example, the average speed reflects the average driving speed of the vehicle over a period of time, while the maximum and minimum values ​​of acceleration reveal the severity of the vehicle's acceleration and deceleration during that period of time. Through these parameters, the vehicle's driving behavior can be understood in more detail, and specific patterns and trends in vehicle driving can be identified. For example, frequent acceleration and deceleration may increase energy consumption, while smooth driving can help reduce energy consumption. These parameters provide basic data for subsequent driving state clustering and energy consumption prediction, allowing the prediction model to more accurately simulate the behavior of the vehicle under different driving conditions.

[0086] In some embodiments, the vehicle acceleration can be calculated by formula (1):

[0087]

[0088] Among them, V t+1 is the vehicle speed at time t+1, V t-1 is the vehicle speed at time t-1, in km / h, a t is the acceleration at time t, in m / s 2 .

[0089] Step S12: clustering the first characteristic parameter of each micro-segment using a fuzzy C-means clustering algorithm to obtain a first corresponding relationship between the driving state category and the first characteristic parameter.

[0090] In this embodiment, the first characteristic parameters of the micro-segments are used as input variables, and they are assigned to different driving state categories through a fuzzy C-means algorithm (FCM) algorithm to form a corresponding relationship between the driving state category and the first characteristic parameter.

[0091] The FCM algorithm is a clustering method based on fuzzy logic. It automatically classifies samples by optimizing the objective function to obtain the membership of each sample point to all class centers. The FCM algorithm allows a data point to belong to multiple clusters with different memberships, which is particularly useful when dealing with driving states with fuzzy boundaries. For example, a micro-segment may be similar to both an acceleration state and a uniform speed state in terms of characteristics. In this way, different driving states, such as smooth driving, rapid acceleration or rapid deceleration, can be more accurately identified and distinguished, thereby providing a more detailed classification basis for energy consumption prediction and range prediction.

[0092] In some embodiments, after the first characteristic parameter of each micro-segment is clustered using the fuzzy C-means clustering algorithm, the effect of the classification may be tested using the silhouette coefficient.

[0093] The silhouette coefficient is an indicator for evaluating clustering effects. It is used to measure the closeness and separation of data points in a cluster. The value of the silhouette coefficient ranges from -1 to 1, where a value close to 1 indicates that the point matches its own cluster well. Please refer to Figure 3 , which is a rendering of a clustering number of 3 provided by an embodiment of the present invention. On this basis, the mean values ​​of the first characteristic parameters of various driving states after clustering are shown in Table 1:

[0094]

[0095] Table 1. Mean values ​​of the first characteristic parameters in different driving conditions

[0096] Step S13: determining the driving state category of each micro-segment according to the first corresponding relationship to obtain a first driving state sequence.

[0097] In this embodiment, a driving state category is assigned to each micro-segment by using the classification result obtained after processing by the FCM algorithm, that is, the first characteristic parameter of the micro-segment is matched with the driving state category determined by the FCM algorithm, so as to identify the driving state to which each micro-segment most likely belongs, such as driving state 1, driving state 2 or driving state 3.

[0098] Through this matching, a first driving state sequence can be constructed, which records in detail the changes in the vehicle's driving state in a series of micro-segments. The first driving state sequence provides a detailed description of the vehicle's driving behavior, allowing the model to predict the vehicle's subsequent driving state based on these state changes. This process is the basis for calculating the probability of driving state transition. Only after the driving state of each micro-segment is clarified can the transition probability between these driving states be further analyzed and counted.

[0099] Step S14, calculating the driving state transition probability according to the first driving state sequence, and using the Markov Monte Carlo model to predict the second driving state sequence within a preset time period according to the driving state transition probability.

[0100] In this embodiment, the driving state transition probability is a key parameter in the range prediction, which describes the possibility of the vehicle switching from one driving state to another. By analyzing the first driving state sequence, the regularity of the driving state transition can be identified, thereby predicting the state change of the vehicle in future driving.

[0101] The driving state transition probability is then used in the MCMC model to simulate and predict the driving state sequence of the vehicle within a preset time period. By combining the memoryless characteristics of the Markov chain and the randomness of the Monte Carlo simulation, the MCMC model can generate the possible driving state sequence of the vehicle within the future preset time period, namely the second driving state sequence. The second driving state sequence can provide a more accurate basis for the subsequent prediction of energy consumption and cruising range.

[0102] In some embodiments, the transition probability between driving states can be calculated according to formula (2):

[0103]

[0104] Among them, p ij is the probability of transition from driving state i to driving state j, M ij is the number of times driving state i is transferred to driving state j, M i is the total number of transitions of driving state i.

[0105] The calculated transition probabilities between driving states are shown in Table 2:

[0106] Driving state 1 Driving status 2 Driving state 3 Driving state 1 0.681 0.010 0.309 Driving status 2 0.188 0.692 0.120 Driving state 3 0.203 0.489 0.308

[0107] Table 2. Driving state transition probability

[0108] In some embodiments, the Markov model can be used to predict the next driving state according to formula (3):

[0109]

[0110] Where M is the total number of driving states, n is a random number between 0 and 1 generated by Monte Carlo; p ah is the probability of transitioning from driving state a to driving state h; k represents the sequence number of the next driving state.

[0111] Based on the above technical solution, this embodiment provides an accurate and efficient means of predicting the driving state of electric vehicles by combining the Markov Monte Carlo model and the fuzzy C-means clustering algorithm. It can identify and classify the driving state by analyzing the first characteristic parameters of the micro-segment (such as average vehicle speed, speed difference, acceleration, etc.), thereby constructing a first correspondence between the driving state category and the first characteristic parameter. The first correspondence enables the model to more accurately understand and predict the driving behavior of the vehicle. In addition, by calculating the driving state transition probability and using the MCMC model to predict the second driving state sequence in the future time period, this method can provide a more accurate data basis for energy consumption and cruising range prediction. This not only improves the accuracy of the prediction, but also enhances the adaptability of the model to different driving conditions.

[0112] Please refer to Figure 4 ,for Figure 1 A flowchart of an actual performance of S03 in a method for predicting a range of mileage is provided. In some embodiments, step S03 mentioned that the corresponding energy consumption prediction value is determined according to the driving state prediction result, which may specifically include the following steps:

[0113] Step S21, obtaining a second corresponding relationship between the vehicle speed state and the vehicle speed.

[0114] Vehicle speed is one of the key factors affecting the energy consumption and driving range of electric vehicles. Different vehicle speeds will lead to different energy consumption levels. Therefore, this embodiment obtains the second correspondence between the vehicle speed state and the vehicle speed, the purpose of which is to predict the specific vehicle speed at each moment in each micro-segment based on the historical vehicle speed data. The second correspondence enables the model to determine the vehicle speed state based on the historical vehicle driving data.

[0115] In some embodiments, considering the maximum speed limit, the daily driving speed does not exceed 130 km / h, so the 1 km / h interval can be used as a speed state, and the speed state can be divided into 130 speed state intervals. The second corresponding relationship can be shown in Table 3:

[0116] Table 3. Second correspondence

[0117] Step S22: determining a first vehicle speed state sequence corresponding to different types of driving states according to the second corresponding relationship.

[0118] In this embodiment, the second corresponding relationship is used to classify the vehicle speeds in the micro-segments corresponding to different types of driving states. This process involves matching the vehicle speed data in the micro-segments with the predefined vehicle speed states, thereby determining a corresponding vehicle speed state for each vehicle speed data point in the micro-segment, and then constructing a first vehicle speed state sequence for the vehicle speed data set in the entire micro-segment. The first vehicle speed state sequence records in detail the vehicle speed states at different time points in the micro-segment. The first vehicle speed state sequence corresponding to different types of driving states provides a detailed description of the changes in the vehicle speed state of the vehicle in different driving states, so that the model can predict the changes in the vehicle speed state in the micro-segments corresponding to different types of driving states.

[0119] Step S23: calculating the vehicle speed state transition probability corresponding to each type of driving state according to the first vehicle speed state sequence.

[0120] In this embodiment, the speed state transition probability is a key parameter in the range prediction, which describes the possibility of the vehicle switching from one speed state to another. By analyzing the first speed state sequence, the regularity of the speed state transition corresponding to the driving state can be identified, thereby predicting the speed change of the vehicle in each type of driving state.

[0121] In some embodiments, the transition probability between vehicle speed states may also be calculated according to the above formula (2).

[0122] Step S24: using the Markov Monte Carlo model to predict the second vehicle speed state sequence corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state.

[0123] In this embodiment, the MCMC model is used to simulate and predict the speed state changes of the vehicle in future driving. This process is based on the vehicle speed state transition probability corresponding to each type of driving state calculated in step S23, and these probabilities describe the possibility of the vehicle switching between different speed states under different driving conditions.

[0124] By taking the vehicle speed state transition probability corresponding to each micro-segment in the second driving state sequence as the input parameter of the model in turn, the MCMC model can generate a series of possible vehicle speed state sequences, which reflect the speed changes that the vehicle may experience in the future driving process.

[0125] For example, assuming that the predicted second driving state sequence is [driving state 1, driving state 3, driving state 2], where the duration of each driving state is 4 seconds, the corresponding vehicle speed state sequences can be calculated according to the vehicle speed state transition probabilities corresponding to driving state 1, driving state 2, driving state 1, and driving state 3, respectively, as [speed state 10, speed state 15, speed state 20, speed state 33], [speed state 35, speed state 40, speed state 44, speed state 45], [speed state 33, speed state 32, speed state 30, speed state 20], then the second vehicle speed state sequence corresponding to the second driving state sequence can be determined to be [speed state 10, speed state 15, speed state 20, speed state 33, speed state 35, speed state 40, speed state 44, speed state 45, speed state 33, speed state 32, speed state 30, speed state 20].

[0126] Since energy consumption is closely related to vehicle speed, predicting the vehicle speed helps to build a more accurate energy consumption model, making the range prediction more accurate and reliable.

[0127] Step S25: generating a corresponding vehicle speed-time curve according to the second vehicle speed state sequence.

[0128] In this embodiment, the predicted vehicle speed state is converted into a specific vehicle speed value and plotted on the time axis to form a curve reflecting the change of vehicle speed over time, namely, the vehicle speed-time curve. The generated vehicle speed-time curve can show the speed change of the vehicle in a preset time period in detail. By analyzing the vehicle speed-time curve, the energy consumption under different driving conditions can be calculated more accurately, thereby providing data support for the energy management and driving strategy of electric vehicles.

[0129] In some embodiments, the predicted vehicle speed state can be converted into vehicle speed according to formula (4):

[0130] v s =[(s-1)+n]×△d Formula (4)

[0131] Among them, v s is the speed value corresponding to the vehicle speed state s; n is a random number between 0 and 1 generated by Monte Carlo; Δd is the interval length corresponding to the vehicle speed state s.

[0132] Step S26, determining the corresponding energy consumption prediction value according to the vehicle speed-time curve.

[0133] In this embodiment, the energy consumption of the electric vehicle under specific driving conditions is estimated by using the vehicle speed-time curve. This process is based on the speed change information provided by the vehicle speed-time curve, combined with the vehicle's energy consumption model, to calculate the energy consumption at different speeds and time intervals.

[0134] Specifically, the energy consumption prediction value will take into account the energy consumption characteristics of the vehicle at each speed state. For example, the energy consumption may be higher during the acceleration phase, while the energy consumption may be lower during the constant speed or deceleration phase. By matching the speed at each time point on the speed-time curve with the energy consumption characteristics of the vehicle, the energy consumption in each time period can be calculated. By adding up the energy consumption in these time periods, the total energy consumption prediction value for the entire driving process can be obtained.

[0135] Based on the above technical solution, this embodiment can more carefully understand the speed change mode under different driving conditions by obtaining the second corresponding relationship between the speed state and the speed. This method not only considers the conversion of the driving state, but also goes deep into the level of the speed state, providing richer data support for energy consumption prediction.

[0136] In some embodiments, as mentioned in step S24, the Markov Monte Carlo model is used to predict the second vehicle speed state sequence corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state, which can be specifically:

[0137] The Markov Monte Carlo model is repeatedly used to predict multiple second vehicle speed state sequences corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state.

[0138] On this basis, as mentioned in step S25, a corresponding vehicle speed-time curve is generated according to the second vehicle speed state sequence, and the corresponding curve may be:

[0139] A plurality of vehicle speed-time curves are correspondingly generated according to the plurality of second vehicle speed state sequences.

[0140] Please refer to Figure 5 , which is a schematic diagram of multiple vehicle speed-time curves provided in an embodiment of the present invention.

[0141] On this basis, as mentioned in step S26, the corresponding energy consumption prediction value is determined according to the vehicle speed-time curve, which can be:

[0142] The energy consumption prediction value corresponding to each vehicle speed-time curve is determined, and the average value of multiple energy consumption prediction values ​​is determined as the final energy consumption prediction value.

[0143] In this embodiment, by repeatedly predicting multiple second vehicle speed state sequences, the behavior of the vehicle under different driving conditions can be more comprehensively simulated. By generating multiple vehicle speed-time curves, the changes in vehicle speed during driving can be captured, providing richer data for energy consumption prediction. By determining the energy consumption prediction value corresponding to each vehicle speed-time curve, and taking the average of these energy consumption prediction values ​​as the final energy consumption prediction value, the randomness of a single prediction result can be reduced, and the accuracy and reliability of the energy consumption prediction can be improved. This method takes into account the uncertainty and variability in the driving process, and provides a more robust energy consumption prediction by integrating the information of multiple prediction curves.

[0144] Please refer to Figure 6 ,for Figure 4 A flowchart of an actual performance of step S26 in the method shown. Based on the above embodiment, in some embodiments, the step S26 mentioned that the corresponding energy consumption prediction value is determined according to the vehicle speed-time curve, which may specifically include the following steps:

[0145] Step S31 : dividing the vehicle speed-time curve according to preset short trips to obtain a plurality of first short trip segments.

[0146] In this embodiment, the continuous vehicle speed-time curve is divided into a series of smaller time intervals of equal or unequal lengths, each of which represents a short travel segment. These short travel segments are intended to capture the driving characteristics of the vehicle in a specific time period, such as acceleration, deceleration or constant speed driving.

[0147] This division allows for a more detailed analysis of the vehicle's driving behavior and energy consumption patterns. Each short trip segment can be independently feature extracted and analyzed for energy consumption, providing more accurate data input for the energy consumption prediction model. This embodiment takes into account dynamic changes during driving, allowing for a more refined assessment of the vehicle's energy consumption rather than simply averaging the data for the entire trip. Such segmentation helps identify and quantify key driving stages that may affect energy consumption, providing support for optimizing the energy management of electric vehicles and improving the accuracy of range predictions.

[0148] Step S32, calculating the second characteristic parameter of each first short-stroke segment.

[0149] Among them, the second characteristic parameter includes at least one of the average ambient temperature, the average vehicle speed, the average acceleration, the speed 5% quantile, the speed 95% quantile, the acceleration 5% quantile, and the acceleration 95% quantile.

[0150] In this embodiment, the second characteristic parameter is a series of key indicators that can describe the driving characteristics of the vehicle in a short travel segment. The calculation of the second characteristic parameter helps to deeply understand the performance of the vehicle under different driving conditions. For example, the average speed reflects the average driving speed of the vehicle in the time period, and the acceleration percentile reveals the severity of the vehicle's acceleration or deceleration. By analyzing the second characteristic parameter, the energy consumption characteristics of the vehicle can be more accurately evaluated, providing the necessary input for the energy consumption prediction model, so that the model can predict energy consumption based on the actual driving behavior of the vehicle, thereby improving the accuracy of the range prediction.

[0151] Step S33: input each second characteristic parameter into a pre-trained energy consumption prediction model to obtain an energy consumption prediction value of each first short trip segment output by the energy consumption prediction model.

[0152] In this embodiment, the second characteristic parameter is provided as an input variable to an energy consumption prediction model that has been trained with historical data, and the energy consumption prediction model is able to predict the energy consumption of the vehicle in the corresponding short trip segment. The model's prediction is based on the patterns and relationships it has learned from the training data, which reveal the association between the second characteristic parameter and energy consumption. In this way, the energy consumption prediction model can provide an energy consumption prediction value for each short trip segment, which integrates the driving characteristics of the vehicle during the time period and the impact of environmental conditions on energy consumption.

[0153] Step S34, calculating the energy consumption prediction value corresponding to the vehicle speed-time curve according to the energy consumption prediction value of each first short trip segment.

[0154] In this embodiment, the total energy consumption prediction of the entire driving cycle is obtained by integrating the energy consumption prediction values ​​of the vehicle in each short trip segment. This process first relies on the energy consumption data provided by the energy consumption prediction model for each short trip segment, which reflects the energy consumption of the vehicle in a specific time period and driving state.

[0155] By accumulating the energy consumption prediction values ​​of all short trip segments or taking a weighted average according to the time period, the energy consumption prediction value of the entire vehicle speed-time curve can be obtained. This total energy consumption prediction value provides a comprehensive estimate of the vehicle's energy consumption under specific driving conditions and is a key indicator for evaluating the range of electric vehicles.

[0156] Based on the above technical solution, this embodiment can more accurately capture the details of energy consumption changes during driving by subdividing the vehicle speed-time curve into multiple first short-trip segments. By inputting the second characteristic parameter into a pre-trained energy consumption prediction model, an energy consumption prediction value can be generated for each first short-trip segment. Finally, by summarizing the energy consumption prediction values ​​of each short-trip segment, the energy consumption prediction value corresponding to the entire vehicle speed-time curve can be obtained. This embodiment takes into account subtle changes during driving and uses a machine learning model to improve the accuracy of the prediction, which can provide more accurate energy consumption predictions.

[0157] On this basis, as mentioned in step S03, determining the corresponding range prediction value according to the energy consumption prediction value may specifically include the following steps:

[0158] Step S41, obtaining the battery meter display power of the vehicle, and calculating the battery remaining energy according to the battery meter display power.

[0159] In some embodiments, the remaining battery energy can be calculated based on the current battery meter power of the vehicle according to formula (5):

[0160] E r =E T SOC formula (5)

[0161] Among them, E r is the remaining energy of the battery, E T is the total energy of the battery (kWh), and SOC is the current displayed power (%).

[0162] Step S42, calculating the remaining driving range according to the remaining battery energy and the energy consumption prediction value corresponding to the vehicle speed-time curve.

[0163] In some embodiments, the remaining driving range can be calculated according to formula (6) in combination with the energy consumption prediction value corresponding to the vehicle speed-time curve:

[0164] S r =E T / E predict Formula (5)

[0165] Among them, S r is the remaining driving range, E predict It is the predicted energy consumption value corresponding to the vehicle speed-time curve.

[0166] In this embodiment, the remaining energy of the battery can be accurately calculated by obtaining the battery meter display power of the vehicle. By combining the energy consumption prediction value corresponding to the vehicle speed-time curve, the energy consumption of the vehicle under different driving conditions under the current battery remaining energy can be calculated. This combination takes into account the actual driving behavior and energy consumption characteristics of the vehicle, so that the calculation of the remaining driving range is closer to the actual driving situation.

[0167] Please refer to Figure 7 , is a flow chart of a training process of an energy consumption prediction model provided by an embodiment of the present invention. Based on the above embodiment, in some embodiments, the training process of the energy consumption prediction model mentioned in step S33 may specifically include the following steps:

[0168] Step S51 , dividing the historical vehicle travel data according to preset short trips to obtain a plurality of second short trip segments.

[0169] In this embodiment, the collected historical vehicle driving data is divided into a series of time periods of fixed lengths, which are called second short-trip segments, and each segment contains the driving information of the vehicle in the time period.

[0170] Through this division, micro driving patterns can be extracted from macro driving data, so that each second short trip segment can independently reflect the driving characteristics of the vehicle in a specific time period. This method allows the model training process to focus on the behavior of the vehicle under specific driving conditions, rather than the average or overall characteristics of the entire trip. In subsequent analysis, factors affecting energy consumption can be more accurately identified and quantified, providing a more detailed and richer data foundation for the energy consumption prediction model, thereby improving the accuracy and reliability of the model prediction.

[0171] Step S52, calculating the second characteristic parameter and energy consumption of each second short trip segment.

[0172] In this embodiment, each second short trip segment is analyzed in detail to extract key driving characteristics (i.e., second characteristic parameters) and energy consumption data. This process first determines the second characteristic parameters of each short trip segment, which may include average ambient temperature, average vehicle speed, average acceleration, 5% and 95% quantiles of speed, 5% and 95% quantiles of acceleration, etc., which can fully reflect the driving conditions of the vehicle in this time period.

[0173] In this embodiment, the energy consumption of each second short trip segment can be calculated by analyzing the charge and discharge state of the battery, the kinetic energy change of the vehicle, and possible energy recovery. This calculation process requires accurate measurement or estimation of the energy consumption of the vehicle during each short trip segment to provide actual energy consumption data for model training.

[0174] In some embodiments, the energy consumption data of the second short trip segment can be calculated by formula (7):

[0175]

[0176] Among them, E is energy consumption data, U t is the battery voltage corresponding to time t; I t is the battery current corresponding to time t; D is the mileage of the second short trip segment.

[0177] By calculating the second characteristic parameter and the energy consumption, a rich training data can be provided for the energy consumption prediction model, which will be used to establish the relationship between the vehicle driving characteristics and the energy consumption. This embodiment is based on actual driving data and detailed energy consumption analysis, so that the energy consumption prediction model can more realistically reflect the energy consumption behavior of the vehicle under different driving conditions.

[0178] Step S53: screening the second short-trip segments according to the second characteristic parameter according to a preset screening rule.

[0179] In this embodiment, the most representative and relevant short trip segments are selected by applying a series of pre-defined criteria or rules to exclude data that distorts the model training results due to abnormalities, erroneous records or unrepresentative driving conditions.

[0180] In some embodiments, the preset screening rules may be as shown in Table 4:

[0181]

[0182] Table 4. Preset screening rules

[0183] The second short-trip segment is a combination of an idle segment and a motion segment. The time from a stationary vehicle to the next start-up is considered an idle segment, and the time from a start-up to the next stop of the vehicle is defined as a motion segment.

[0184] In some embodiments, the preset screening rules may also include multiple conditions, such as excluding those clips recorded under extreme ambient temperatures, or based on the rationality of energy consumption, such as excluding those clips with abnormally high or low energy consumption, which may be caused by sensor failure or data entry errors. In this way, the quality of data used for model training can be ensured, thereby improving the accuracy and reliability of the energy consumption prediction model.

[0185] The screening process helps to concentrate the information in the training data, making it more focused on those short trip segments that can reflect the energy consumption characteristics of the vehicle under normal driving conditions. This not only improves the efficiency of model training, but also helps to build a more robust and accurate energy consumption prediction model, providing electric vehicle users with more accurate range predictions.

[0186] Step S54, normalizing the second characteristic parameters of the filtered second short-stroke segments to obtain training data.

[0187] In this embodiment, normalization is a data preprocessing technique that scales the numerical value of a feature parameter to a specific range, usually from 0 to 1. The purpose of this step is to ensure that all feature parameters have the same importance in model training, and to avoid certain features from having too much weight in the model due to large differences in parameter numerical ranges. Normalization allows the model to more fairly evaluate the contribution of each feature to energy consumption prediction, which helps to improve the efficiency and accuracy of model training. At the same time, the normalized data can speed up the convergence of the optimization algorithm and improve the generalization ability of the model.

[0188] After normalization, the second characteristic parameter together with the corresponding energy consumption data constitutes the training data set of the model. This data set will be used to train the energy consumption prediction model so that it can learn the relationship between characteristic parameters and energy consumption, so as to accurately predict unknown data in practical applications. The benefit of this method is that it can provide more accurate and reliable energy consumption predictions, help optimize the energy management of electric vehicles and improve the accuracy of range predictions.

[0189] Step S55, establishing a relationship between training data and energy consumption based on a meta-heuristic algorithm to obtain an energy consumption prediction model.

[0190] In this embodiment, a meta-heuristic algorithm is a type of algorithm used to solve optimization problems. It simulates natural phenomena or social behaviors to find the optimal solution or satisfactory solution to the problem. Common meta-heuristic algorithms include genetic algorithms, particle swarm optimization, simulated annealing, etc.

[0191] In the process of training the energy consumption prediction model, the meta-heuristic algorithm is used to explore the mapping relationship between the second characteristic parameter and energy consumption. The algorithm continuously adjusts the model parameters through an iterative process to minimize the difference between the predicted energy consumption and the actual energy consumption. In this way, the model can learn the patterns in the data and establish a mathematical model that can accurately predict energy consumption.

[0192] Based on the above technical solution, this embodiment screens short-trip segments by preset screening rules, which can exclude abnormal or unrepresentative data and ensure the quality of training data. Normalizing the screened data can eliminate the dimensional influence between different feature parameters, making the data more standardized, which helps to improve the efficiency and accuracy of model training. By using a metaheuristic algorithm to establish the relationship between training data and energy consumption, the complex relationship between feature parameters and energy consumption can be discovered, and the model parameters can be optimized to obtain a model that can accurately predict energy consumption. In this way, the accuracy of energy consumption prediction can be significantly improved, providing strong support for energy management and user decision-making of electric vehicles.

[0193] Please refer to Figure 8 , is a schematic diagram of the structure of a cruising range prediction device provided by an embodiment of the present invention, and the cruising range prediction device may include:

[0194] An acquisition module 100 is used to acquire historical vehicle driving data and divide micro segments according to the historical vehicle driving data;

[0195] A driving state prediction module 200 is used to make predictions based on micro-segments using a Markov Monte Carlo model to obtain a driving state prediction result;

[0196] The cruising range prediction module 300 is used to determine the corresponding energy consumption prediction value according to the driving state prediction result, and to determine the corresponding cruising range prediction value according to the energy consumption prediction value.

[0197] Based on the above embodiments, in a specific embodiment, the driving state prediction module 200 can be specifically used for:

[0198] Calculating a first characteristic parameter of each micro-segment; the first characteristic parameter includes at least one of an average vehicle speed, a difference between an end speed and a start speed, an average acceleration, a maximum acceleration, and a minimum acceleration;

[0199] Clustering the first characteristic parameter of each micro-segment using a fuzzy C-means clustering algorithm to obtain a first corresponding relationship between the driving state category and the first characteristic parameter;

[0200] Determine the driving state category of each micro-segment according to the first corresponding relationship to obtain a first driving state sequence;

[0201] The driving state transition probability is calculated according to the first driving state sequence, and the second driving state sequence within a preset time period is predicted according to the driving state transition probability using a Markov Monte Carlo model.

[0202] Based on the above embodiments, in a specific embodiment, the cruising range prediction module 300 can be specifically used for:

[0203] Acquire a second corresponding relationship between the vehicle speed state and the vehicle speed;

[0204] Determining a first vehicle speed state sequence corresponding to different types of driving states according to the second corresponding relationship;

[0205] Calculate the vehicle speed state transition probability corresponding to each type of driving state according to the first vehicle speed state sequence;

[0206] Using a Markov Monte Carlo model, predicting a second vehicle speed state sequence corresponding to a second driving state sequence according to a vehicle speed state transition probability corresponding to each type of driving state;

[0207] generating a corresponding vehicle speed-time curve according to the second vehicle speed state sequence;

[0208] Determine the corresponding energy consumption prediction value based on the vehicle speed-time curve.

[0209] Based on the above embodiments, in a specific embodiment, the cruising range prediction module 300 can be specifically used for:

[0210] Repeatedly using the Markov Monte Carlo model to predict multiple second vehicle speed state sequences corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state;

[0211] Generate a plurality of vehicle speed-time curves according to the plurality of second vehicle speed state sequences;

[0212] The energy consumption prediction value corresponding to each vehicle speed-time curve is determined, and the average value of multiple energy consumption prediction values ​​is determined as the final energy consumption prediction value.

[0213] Based on the above embodiments, in a specific embodiment, the cruising range prediction module 300 can be specifically used for:

[0214] Dividing the vehicle speed-time curve according to preset short trips to obtain a plurality of first short trip segments;

[0215] Calculate a second characteristic parameter of each first short trip segment; the second characteristic parameter includes at least one of average ambient temperature, average vehicle speed, average acceleration, 5% quantile of speed, 95% quantile of speed, 5% quantile of acceleration, and 95% quantile of acceleration;

[0216] Inputting each second characteristic parameter into a pre-trained energy consumption prediction model to obtain an energy consumption prediction value of each first short trip segment output by the energy consumption prediction model;

[0217] The energy consumption prediction value corresponding to the vehicle speed-time curve is calculated according to the energy consumption prediction value of each first short trip segment.

[0218] Based on the above embodiments, in a specific embodiment, the cruising range prediction module 300 can be specifically used for:

[0219] Dividing the historical vehicle driving data according to the preset short trips to obtain a plurality of second short trip segments;

[0220] Calculating the second characteristic parameter and energy consumption of each second short trip segment;

[0221] The second short-trip segment is screened according to the second characteristic parameter according to a preset screening rule;

[0222] Normalizing the second characteristic parameters of the filtered second short-stroke segments to obtain training data;

[0223] Based on the meta-heuristic algorithm, the relationship between training data and energy consumption is established to obtain the energy consumption prediction model.

[0224] Based on the above embodiments, in a specific embodiment, the cruising range prediction module 300 can be specifically used for:

[0225] Obtain the battery meter power of the vehicle and calculate the remaining battery energy based on the battery meter power;

[0226] The remaining driving range is calculated based on the remaining battery energy and the energy consumption prediction value corresponding to the vehicle speed-time curve.

[0227] This embodiment provides an electronic device, including a processor and a memory, the memory is used to store at least one instruction, and when the instruction is loaded and executed by the processor, the above-mentioned method of mileage prediction is implemented. Its execution method and beneficial effects are similar and will not be repeated here.

[0228] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned method for predicting the range is implemented. The execution method and beneficial effects thereof are similar and will not be described in detail here.

[0229] It should be noted that although the above describes the various steps in a specific order, it does not mean that the various steps must be executed in the above specific order. In fact, some of these steps can be executed concurrently or even in a different order as long as the required functions can be achieved.

[0230] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting a cruising range, characterized in that: include: Acquire historical vehicle travel data, and divide micro-segments according to the historical vehicle travel data; Using a Markov Monte Carlo model to make predictions based on the micro-segments, a driving state prediction result is obtained; A corresponding energy consumption prediction value is determined according to the driving state prediction result, and a corresponding cruising range prediction value is determined according to the energy consumption prediction value.

2. The method according to claim 1, characterized in that The method of using the Markov Monte Carlo model to predict the driving state according to the micro-segment to obtain the driving state prediction result includes: Calculating a first characteristic parameter of each micro-segment; the first characteristic parameter includes at least one of an average vehicle speed, a difference between an end speed and a start speed, an average acceleration, a maximum acceleration, and a minimum acceleration; Clustering the first characteristic parameter of each micro-segment using a fuzzy C-means clustering algorithm to obtain a first corresponding relationship between a driving state category and the first characteristic parameter; Determine the driving state category of each of the micro-segments according to the first corresponding relationship to obtain a first driving state sequence; The driving state transition probability is calculated according to the first driving state sequence, and the Markov Monte Carlo model is used to predict the second driving state sequence within a preset time period according to the driving state transition probability.

3. The method according to claim 2, characterized in that The determining of the corresponding energy consumption prediction value according to the driving state prediction result includes: Acquire a second corresponding relationship between the vehicle speed state and the vehicle speed; Determining a first vehicle speed state sequence corresponding to different types of driving states according to the second corresponding relationship; Calculating the vehicle speed state transition probability corresponding to each type of driving state according to the first vehicle speed state sequence; Predicting a second vehicle speed state sequence corresponding to the second driving state sequence according to a vehicle speed state transition probability corresponding to each type of driving state using the Markov Monte Carlo model; generating a corresponding vehicle speed-time curve according to the second vehicle speed state sequence; The corresponding energy consumption prediction value is determined according to the vehicle speed-time curve.

4. The method according to claim 3, characterized in that The method of using the Markov Monte Carlo model to predict the second vehicle speed state sequence corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state includes: Repeatedly using the Markov Monte Carlo model to predict multiple second vehicle speed state sequences corresponding to the second driving state sequence according to the vehicle speed state transition probability corresponding to each type of driving state; The generating of the corresponding vehicle speed-time curve according to the second vehicle speed state sequence correspondingly includes: Generate a plurality of the vehicle speed-time curves according to the plurality of the second vehicle speed state sequences; The determining of the corresponding energy consumption prediction value according to the vehicle speed-time curve includes: Determine the energy consumption prediction value corresponding to each of the vehicle speed-time curves, and determine the average value of the multiple energy consumption prediction values ​​as the final energy consumption prediction value.

5. The method according to claim 3, characterized in that: The determining the corresponding energy consumption prediction value according to the vehicle speed-time curve includes: Dividing the vehicle speed-time curve according to preset short trips to obtain a plurality of first short trip segments; Calculating a second characteristic parameter of each of the first short trip segments; the second characteristic parameter includes at least one of average ambient temperature, average vehicle speed, average acceleration, 5% quantile of speed, 95% quantile of speed, 5% quantile of acceleration, and 95% quantile of acceleration; Inputting each of the second characteristic parameters into a pre-trained energy consumption prediction model to obtain an energy consumption prediction value of each of the first short-trip segments output by the energy consumption prediction model; The energy consumption prediction value corresponding to the vehicle speed-time curve is calculated according to the energy consumption prediction value of each of the first short-trip segments.

6. The method according to claim 5, characterized in that The training process of the energy consumption prediction model includes: Dividing the historical vehicle travel data according to the preset short trips to obtain a plurality of second short trip segments; Calculating a second characteristic parameter and an energy consumption of each of the second short-trip segments; Filtering the second short-trip segments according to the second characteristic parameter according to a preset filtering rule; Normalizing the second characteristic parameters of the filtered second short-stroke segments to obtain training data; Based on a meta-heuristic algorithm, a relationship between the training data and the energy consumption is established to obtain the energy consumption prediction model.

7. The method according to claim 5, characterized in that The determining a corresponding range prediction value according to the energy consumption prediction value includes: Obtaining the battery meter power of the vehicle, and calculating the remaining battery energy based on the battery meter power; The remaining driving range is calculated based on the remaining battery energy combined with the energy consumption prediction value corresponding to the vehicle speed-time curve.

8. A device for predicting cruising range, characterized in that: include: An acquisition module, used for acquiring historical vehicle driving data and dividing micro-segments according to the historical vehicle driving data; A driving state prediction module, used for making predictions based on the micro-segments using a Markov Monte Carlo model to obtain a driving state prediction result; The cruising range prediction module is used to determine the corresponding energy consumption prediction value according to the driving state prediction result, and to determine the corresponding cruising range prediction value according to the energy consumption prediction value.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store at least one instruction, and when the instruction is loaded and executed by the processor, the method for predicting the range as described in any one of claims 1 to 7 is implemented.

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

Images