A remaining range estimation method based on equivalent operating conditions of a vehicle-mounted hydrogen system

Abstract

The application provides a residual cruising range estimation method based on equivalent operation conditions of a vehicle-mounted hydrogen system, comprising: extracting features of current operation data of a target hydrogen energy vehicle to obtain a current user behavior portrait; inputting the current user behavior portrait and a driving mode to which the current user behavior portrait belongs into a pre-trained time series prediction model to obtain a predicted driving mode at a next time; reconstructing the predicted driving mode according to historical operation data corresponding to each driving mode to obtain reconstructed operation data under the predicted driving mode; determining feature behavior hydrogen consumption under the reconstructed operation data according to a mapping relationship between the reconstructed operation data and operation conditions and hydrogen consumption which is pre-constructed; and calculating a residual cruising range according to the feature behavior hydrogen consumption under the reconstructed operation data in a prediction time interval and a current residual hydrogen storage amount of the target hydrogen energy vehicle. The scheme introduces multi-dimensional user behavior to obtain reconstructed operation data more in line with the user driving style, thereby predicting the residual cruising range based on the reconstructed operation data, and improving the prediction accuracy and reliability.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology for vehicle-mounted hydrogen systems, and in particular to a method for estimating the remaining driving range based on equivalent operating conditions of vehicle-mounted hydrogen systems. Background Technology

[0002] Hydrogen systems and hydrogen fuel cells are a pollution-free form of energy, with water being the only byproduct of hydrogen combustion. Therefore, they represent a crucial technological path to achieving low-carbon or even zero-carbon emissions, bearing the heavy responsibility of carbon reduction and emission reduction in the transportation industry. Vehicles equipped with hydrogen systems and hydrogen fuel cells have gradually entered the commercial application stage. However, due to the underdeveloped hydrogen refueling infrastructure and the unique characteristics of hydrogen storage, current hydrogen refueling is difficult. Accurate estimation of remaining driving range is essential for rational planning and scheduling of hydrogen refueling, thereby ensuring normal vehicle operation and minimizing user inconvenience.

[0003] Existing methods for estimating the remaining driving range of hydrogen fuel cell vehicles, such as linear regression algorithms based on historical operating conditions and rule-based logic judgment theories based on average energy consumption, only estimate based on fixed operating conditions and lack consideration for user behavior, thus resulting in poor estimation accuracy and unreliable results. Summary of the Invention

[0004] This invention provides a method for estimating the remaining driving range based on the equivalent operating conditions of an on-board hydrogen system. By introducing multi-dimensional user behavior to reconstruct the operating conditions of the on-board hydrogen system, a more accurate prediction of the driving conditions is obtained, thereby predicting the remaining driving range based on the predicted operating conditions and hydrogen consumption, thus improving the accuracy and reliability of the prediction.

[0005] In a first aspect, the present invention provides a method for estimating the remaining driving range based on the equivalent operating conditions of an on-board hydrogen system, comprising:

[0006] Feature extraction is performed on the current operating data of the target hydrogen fuel cell vehicle to obtain a current user behavior profile;

[0007] The current user behavior profile and the driving mode to which the current user behavior profile belongs are input into a pre-trained time-series prediction model to obtain the predicted driving mode for the next moment.

[0008] Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode;

[0009] Based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under the reconstructed operating data is determined;

[0010] The remaining driving range is obtained based on the characteristic behavior hydrogen consumption under the reconstructed operating data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle.

[0011] Secondly, the present invention provides a remaining driving range estimation device based on the equivalent operating conditions of an on-board hydrogen system, comprising:

[0012] The feature extraction module is used to extract features from the current operating data of the target hydrogen fuel cell vehicle to obtain a current user behavior profile.

[0013] The prediction module is used to input the current user behavior profile and the driving mode to which the current user behavior profile belongs into a pre-trained time-series prediction model to obtain the predicted driving mode for the next moment.

[0014] The reconstruction module is used to reconstruct the operating conditions of the predicted driving mode based on the historical operating data corresponding to each driving mode, so as to obtain the reconstructed operating data under the predicted driving mode.

[0015] The hydrogen consumption calculation module is used to determine the characteristic behavior hydrogen consumption under the reconstructed operating data based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption.

[0016] The mileage calculation module is used to calculate the remaining driving range based on the characteristic behavior hydrogen consumption under the reconstructed operating data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle.

[0017] Thirdly, embodiments of the present invention also provide a computing device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method described in any of the first aspects of this specification.

[0018] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the methods described in any of the first aspects of this specification.

[0019] Fifthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects of this specification.

[0020] This invention provides a method for estimating remaining driving range based on equivalent operating conditions of an onboard hydrogen system. It introduces a multi-dimensional user behavior profile by extracting features from operating data and determining the driving mode associated with that profile. Then, a pre-trained time-series prediction model is used to obtain the predicted driving mode for the next moment based on the current user behavior profile and its associated driving mode. The predicted driving mode is then reconstructed to determine the reconstructed operating data under this preset driving mode. Finally, based on a pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under this reconstructed operating data is determined. This prediction process is repeated until all reconstructed operating data and their characteristic behavior hydrogen consumption within the prediction time interval are obtained. Thus, the remaining driving range can be predicted based on the current remaining hydrogen storage and the characteristic behavior hydrogen consumption under each reconstructed operating data. In this way, this invention obtains reconstructed operating data that better matches the user's driving style by considering multi-dimensional operating data prediction, and then predicts the remaining driving range based on the characteristic behavior hydrogen consumption of the reconstructed operating data, improving prediction accuracy and reliability. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for estimating the remaining driving range based on the equivalent operating conditions of an on-board hydrogen system, provided by an embodiment of the present invention.

[0023] Figure 2 This is a flowchart of another method for estimating the remaining driving range based on the equivalent operating conditions of an on-board hydrogen system, provided by an embodiment of the present invention.

[0024] Figure 3 This is a hardware architecture diagram of a computing device provided in an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of a remaining driving range estimation device based on the equivalent operating conditions of an on-board hydrogen system, provided in an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0027] The following describes the specific implementation of the concept in this application.

[0028] Please refer to Figure 1 This invention provides a method for estimating remaining driving range based on equivalent operating conditions of an onboard hydrogen system. The method includes:

[0029] Step 100: Extract features from the current operating data of the target hydrogen fuel cell vehicle to obtain a current user behavior profile;

[0030] Step 102: Input the current user behavior profile and the driving mode to which the current user behavior profile belongs into the pre-trained time-series prediction model to obtain the predicted driving mode for the next moment.

[0031] Step 104: Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode.

[0032] Step 106: Determine the characteristic behavior hydrogen consumption under the reconstructed operating data based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption;

[0033] Step 108: Calculate the remaining driving range based on the characteristic behavior hydrogen consumption under the reconstructed operation data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle.

[0034] This invention provides a method for estimating remaining driving range based on equivalent operating conditions of an onboard hydrogen system. It introduces a multi-dimensional user behavior profile by extracting features from operating data and determining the driving mode associated with that profile. Then, a pre-trained time-series prediction model is used to obtain the predicted driving mode for the next moment based on the current user behavior profile and its associated driving mode. The predicted driving mode is then reconstructed to determine the reconstructed operating data under this preset driving mode. Finally, based on a pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under this reconstructed operating data is determined. This prediction process is repeated until all reconstructed operating data and their characteristic behavior hydrogen consumption within the prediction time interval are obtained. This allows for the prediction of remaining driving range based on the current remaining hydrogen storage and the characteristic behavior hydrogen consumption under each reconstructed operating data. Thus, this invention improves prediction accuracy and reliability by considering multi-dimensional operating data prediction to obtain reconstructed operating data that better matches the user's driving style, and then predicting the remaining driving range based on the characteristic behavior hydrogen consumption of the reconstructed operating data.

[0035] The following description Figure 1 The execution method of each step is shown.

[0036] First, before step 100, the following is also included:

[0037] The historical operating data of the target hydrogen fuel cell vehicle is divided into equal time segments to obtain several historical operating segments that include time information and operating data per unit time.

[0038] Feature extraction is performed on several historical operation segments to obtain user profiles for those segments;

[0039] Density clustering algorithm is used to classify user profile fragments and determine the driving mode to which each user profile fragment belongs.

[0040] It should be noted that historical operating data includes vehicle data, onboard hydrogen system and hydrogen fuel cell data, power battery data, and motor data. Vehicle data includes vehicle speed, accelerator pedal travel, and brake pedal travel; onboard hydrogen system and hydrogen fuel cell data includes operating pressure, hydrogen consumption, hydrogen flow rate, and hydrogen sensor concentration; power battery data includes voltage, current, temperature, and state of charge (SOC); and motor data includes torque and speed. Each user profile segment corresponds one-to-one with the unit-time operating data, and the user profile segment is a unit-time operating data used to describe the user's driving style.

[0041] Specifically, each user profile segment is input into the DBSACAN algorithm for data classification, thereby determining the affiliation of each user profile segment. Each affiliation category is assigned to a specific driving mode, thus identifying the driving mode to which different user profile segments belong. Different driving modes include different user profile segments. For example, historical running data is divided into equal time segments (1 minute segmentation standard), resulting in 200 unit-time running data points (i.e., 200 historical running segments) including segment numbers. After feature extraction, 200 user profile segments are obtained. The DBSACAN algorithm is then used to classify all these user profile segments, ultimately dividing them into categories A (containing 60 user profile segments), B (containing 30 user profile segments), C (containing 40 user profile segments), D (containing 10 user profile segments), and E (containing 60 user profile segments).

[0042] In a preferred embodiment, feature extraction is performed on several historical execution segments to obtain several segment user profiles, including:

[0043] Acquire unit-time operation data for historical operation segments; the unit-time operation data includes unit-time operation data for the whole vehicle, hydrogen system, power battery, and motor.

[0044] Feature extraction is performed on the data for each unit of time to obtain several features; the number of features is the same as the number of data types included in the data for each unit of time.

[0045] After performing correlation analysis on the features, effective key features were obtained through screening.

[0046] Generate fragmented user profiles based on effective key features.

[0047] Specifically, the features include average vehicle speed characteristics, acceleration segment ratio, deceleration segment ratio, idling segment ratio, total accelerator pedal duration characteristics, total brake pedal duration characteristics, average accelerator pedal travel characteristics, average brake pedal travel characteristics, average operating pressure characteristics, average hydrogen consumption characteristics, average hydrogen flow rate characteristics, average hydrogen sensor concentration characteristics, average voltage characteristics, average current characteristics, average temperature characteristics, average state of charge (SOC) characteristics, average torque characteristics, and average speed characteristics. The number of effective key features shall not exceed the total number of features.

[0048] Specifically, effective key features can be obtained by screening after performing correlation analysis on the features; the following four methods can be used.

[0049] The first method: use principal component analysis algorithm to perform correlation analysis, and select features with a cumulative contribution rate greater than 90% as effective key features;

[0050] The second method is to use the Relief-F algorithm to perform correlation analysis and select features with a cumulative contribution rate greater than 90% as effective key features.

[0051] The third method: use partial principal component analysis algorithm to perform correlation analysis, and select features with a cumulative contribution rate greater than 90% as effective key features;

[0052] The fourth method is to use the Pearson correlation analysis algorithm to perform correlation analysis and select features with a correlation of less than 0.1 as effective key features.

[0053] In this invention, the current user behavior profile is a vector composed of effective key features obtained from the analysis of current running data. This invention extracts several features from multi-dimensional running data. Considering all features would increase the data volume; therefore, to reduce dimensionality while retaining as much information as possible, a correlation analysis method is further used to filter several features, obtaining effective key features.

[0054] Step 100 uses the feature extraction method described above to obtain the current user behavior profile under the current running data. It should be noted that the current user behavior profile is a segment user profile, that is, the time length corresponding to the current user behavior profile is a unit time length.

[0055] In step 102, the pre-trained time series prediction model is trained using the following method:

[0056] Based on the user profile of the segment and the driving mode to which the user profile of the segment belongs, generate several sets of first sample sets;

[0057] The Transformer architecture with a self-attention mechanism is trained using the first sample set to obtain a pre-trained time-series prediction model. The first sample set includes the current user profile segment and the driving mode to which the current user profile segment belongs as input, and the driving mode to which the next user profile segment belongs as output.

[0058] It should be noted that the temporal prediction model in step 102 is the user behavior prediction model. It learns the user's driving style by establishing a Self-attention Transformer algorithm. Its input is the user profile of the segment running at the current time and its corresponding driving mode, and its output is the driving mode of the user profile of the next segment running at the current time. The Self-attention Transformer algorithm refers to a series of data-driven models based on an encoder-decoder structure, including a series of stacked encoders and decoders. Each encoder module consists of a Self-attention layer and a feedforward neural network, while the decoder has an additional encoder-decoder attention module to establish the connection between encoding and decoding.

[0059] In this invention, the Transformer architecture with its self-attention mechanism can effectively capture short- and long-term dependencies in driving behavior, such as instantaneous operations like acceleration and braking, and long-term stable patterns like driving habits and routes. By coupling the self-attention mechanism, the Transformer can globally perceive data from all time steps when processing driving behavior, rather than relying on local neighborhood time steps. Furthermore, different attention heads in the multi-head attention mechanism can focus on different driving behavior features, thus enabling the effective fusion of multi-dimensional user profile segments using a parallel processing mode, thereby accurately predicting future driving patterns and conditions.

[0060] For step 104, the operating conditions of the predicted driving mode are reconstructed based on the historical operating data corresponding to each driving mode, resulting in reconstructed operating data under the predicted driving mode, including:

[0061] The historical operating data corresponding to each driving mode is determined from the historical operating data of the target hydrogen fuel cell vehicle, and the various historical operating segments included in the predicted driving mode for the next moment are obtained.

[0062] Calculate the similarity value between the current running segment and each historical running segment included in the predicted driving mode for the next time moment, and determine the highest similarity value;

[0063] The historical running segment corresponding to the highest similarity value is used to determine the running data per unit time of the running segment at the current moment as the reconstructed running data for the next moment.

[0064] In this invention, the Monte Carlo simulation method is used to reconstruct the operating conditions of the on-board hydrogen system at each moment. After determining the predicted driving mode for the next moment based on step 102, the operating conditions for the next moment are selected from the historical operating segments included in the predicted driving mode. That is, the unit-time operating data included in a historical operating segment is determined as the reconstructed operating data for the next moment. In this way, this invention can not only handle multidimensional and multivariate randomness, but also further improve the simulation accuracy by calculating the similarity value between the operating segments at the current moment and the next moment to select the most similar historical operating segments as the reconstructed operating data.

[0065] In step 106, the pre-built mapping relationship between operating conditions and hydrogen consumption is obtained through the following method:

[0066] Establish a nonlinear functional relationship with user profile segments as input and hydrogen consumption as output;

[0067] The optimal solution for the parameters of the nonlinear function relationship is obtained to determine the mapping relationship between the operating conditions and hydrogen consumption.

[0068] It should be noted that the mapping relationship between operating conditions and hydrogen consumption refers to a non-linear function relationship established using historical operating data as input, such as vehicle speed, accelerator pedal travel, and decelerator pedal travel, with hydrogen consumption as the output. The hydrogen consumption predicted under the user behavior profile in step 106 refers to the hydrogen consumption calculated based on the above mapping relationship, using the reconstructed predicted user behavior profile of the on-board hydrogen system as input. This hydrogen consumption is related to the user behavior profile, that is, related to characteristic behaviors, and varies among different users.

[0069] In step 106, based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under the reconstructed operating data is determined, including:

[0070] Feature extraction is performed on the reconstructed operational data to obtain a reconstructed user behavior profile under the predicted driving mode;

[0071] By inputting the reconstructed user behavior profile into the pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under the reconstructed user behavior profile is obtained.

[0072] In a preferred embodiment, finding the optimal solution for the parameters of the nonlinear functional relationship includes:

[0073] S1: Initialize the population, determine the feasible region of feasible solutions for initial temperature, temperature cooling rate, cutoff temperature, maximum number of iterations, initial energy of prey, and parameters, and randomly generate a set of potential feasible solutions within the feasible region;

[0074] S2: In the current iteration, the Harris Eagle algorithm is used to optimize the potential feasible solution within the feasible region to obtain the first updated feasible solution output in the exploration phase;

[0075] S3: Determine whether to switch from the exploration phase to the development phase based on the prey energy and iteration number of the current iteration; if yes, proceed to step S4; otherwise, proceed to step S1.

[0076] S4: Determine the optimization strategy based on the prey energy, and use the optimization strategy to optimize the first updated feasible solution to obtain the second updated feasible solution;

[0077] S5: Calculate the goodness of fit of the nonlinear function relationship using the optimal solution and the second updated feasible solution in the current iteration. If the goodness of fit of the second updated feasible solution is lower than that of the optimal solution in the current iteration, proceed to step S6; otherwise, proceed to step S7.

[0078] S6: Calculate the acceptance probability of the second updated feasible solution based on the initial temperature, temperature cooling rate, second updated feasible solution, and prey position in the current iteration, and accept the second updated feasible solution according to the acceptance probability; if the second updated feasible solution is accepted, proceed to step S7; if the second updated feasible solution is not accepted, retain the optimal solution in the current iteration, update the current temperature, and proceed to step S8.

[0079] S7: Determine the second updated feasible solution as the optimal solution for the current iteration;

[0080] S8: Determine whether the current iteration count has reached the maximum iteration count or whether the current temperature has reached the cutoff temperature. If so, output the optimal solution; otherwise, use the optimal solution as the initial solution for the next iteration and return to step S2.

[0081] It should be noted that in step S6, the prey position in the current iteration is the position of the individual with the optimal fitness.

[0082] In a preferred embodiment, the acceptance probability of the second updated feasible solution is determined by the following formula:

[0083] T t+1 =α·T t

[0084]

[0085] Specifically, P(T) t+1 ) represents the acceptance probability of the second updated feasible solution in the (t+1)th iteration; T0 is the initial temperature; T t+1 T t Let be the temperatures at the (t+1)th iteration and the tth iteration, respectively; α is the cooling rate, α∈[0,1]; k is the Boltzmann constant; EX(t+1) E represents the fitness value of the second updated feasible solution at the (t+1)th iteration. Xrabbit This is the fitness value of the current best fitness position.

[0086] In this invention, the Harris Eagle algorithm uses fewer parameters, exhibits high stability, and converges quickly. The algorithm switches between the search and development phases to adapt to constantly changing environments and prey escape patterns, thereby improving the efficiency and accuracy of obtaining the optimal solution. Furthermore, during the optimization process using the Harris Eagle algorithm, when calculating the feasible solution for the next time step from the feasible solution at the current time step, the acceptance probability of the feasible solution changes from 100% acceptance in the original algorithm to acceptance based on probability. The acceptance probability is calculated using the aforementioned formula, thereby improving local optimization capabilities, quickly determining better solutions, and increasing solution efficiency.

[0087] In step 108, as Figure 2 As shown, based on the characteristic behavior hydrogen consumption under the reconstructed operation data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle, the remaining driving range is calculated, including:

[0088] A1: Extract features from the current running data to obtain the current user behavior profile; then input the current user behavior profile and the driving mode to which the current user behavior profile belongs into the pre-trained time series prediction model to obtain the predicted driving mode for the next moment.

[0089] A2: Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode;

[0090] A3: Determine whether the current cumulative prediction time length is greater than the preset time threshold. If so, obtain the reconstruction operation data within the prediction time interval and execute step A4; otherwise, use the reconstruction operation data at the next moment as the current operation data and return to step A1.

[0091] A4: Input the reconstructed user behavior profile obtained by feature extraction of the reconstructed running data within the prediction time interval into the mapping relationship to obtain the characteristic behavior hydrogen consumption under each reconstructed running data;

[0092] A5: Accumulate the hydrogen consumption of characteristic behaviors under the reconstructed operation data according to the predicted time sequence to obtain the total hydrogen consumption; when the total hydrogen consumption is the same as the current remaining hydrogen storage, calculate the sum of the driving mileage of the reconstructed operation data included in the total hydrogen consumption to obtain the remaining driving range.

[0093] Specifically, the Monte Carlo simulation method continuously predicts reconfiguration operation data over a future period by repeatedly executing steps A1 to A3. Then, the reconfiguration operation data is stitched together in chronological order to obtain the equivalent operating condition within the predicted time interval. This equivalent operating condition is then converted into a power operating condition using an energy flow model to reconfigure the on-board hydrogen system's operating power condition. Next, feature extraction is performed on the reconfiguration operation data within this time interval to obtain a reconfiguration user behavior profile. This profile is then input into a mapping relationship to obtain the characteristic behavior hydrogen consumption for each reconfiguration operation data. For example, the current user behavior profile is used as the initial profile, and the current time is denoted as t0. After predicting the reconfiguration operation data at time t1 based on this initial profile, feature extraction is performed to obtain the reconfiguration user behavior profile at time t1. The reconfiguration operation data at time t2 is predicted based on the reconfiguration user behavior profile at time t1, and feature extraction is performed to obtain the reconfiguration user behavior profile at time t2. The reconfiguration operation data at time t3 is predicted based on the reconfiguration user behavior profile at time t2, and feature extraction is performed to obtain the reconfiguration user behavior profile at time t3. This process is repeated until a preset time threshold tn is reached, at which point the loop stops. It should be noted that the preset time threshold is determined based on the actual application.

[0094] In this invention, the remaining driving range of the vehicle is obtained by reading the current remaining hydrogen storage capacity of the target hydrogen fuel cell vehicle and the hydrogen consumption of each reconstructed operating data calculated in step 106, and summing the predicted user behavior profiles when the remaining hydrogen storage capacity is 0. The specific calculation formula is as follows:

[0095]

[0096] Where CapacityHremain represents the current remaining hydrogen storage, and CapacityH per_seg (i) represents the hydrogen consumption during the i-th reconstructed operation data, mileageremain represents the remaining driving range, and mileage per_seg (i) represents the mileage traveled in the i-th reconstructed running data. It should be noted that the reconstructed running data includes the vehicle speed per unit time, i.e., the average vehicle speed. Therefore, the mileage for each predicted user behavior profile can be determined based on the vehicle speed and the unit time.

[0097] After obtaining the remaining driving range in step 108, the following steps are also included:

[0098] Based on the characteristic behavior hydrogen consumption and the current remaining hydrogen storage under the reconfiguration operation data, calculate the instantaneous remaining driving range at the moment when the reconfiguration operation data is located;

[0099] Each reconstructed running data and the instantaneous remaining driving range at the time of that reconstructed running data are used as feature combinations, and the feature combinations are arranged in the order of time information to obtain a feature combination sequence;

[0100] A self-attention mechanism, the Transformer architecture, is used to extract features from the feature combination sequence to obtain high-dimensional features.

[0101] The feature combination sequence and the high-dimensional features are concatenated to obtain the high-dimensional feature vector;

[0102] The high-dimensional feature vector is input into the pre-trained XGboost model, and the corrected remaining driving range is output.

[0103] In a preferred embodiment, the pre-trained XGboost model is trained using the following method:

[0104] Based on historical operating data, obtain the actual remaining driving range of the target hydrogen fuel cell vehicle in each segment of the user profile;

[0105] Each user profile segment and the actual remaining driving range at the time of that user profile segment are used as training feature combinations, and the feature combinations are arranged in the order of time information to obtain the training feature combination sequence.

[0106] A self-attention mechanism, the Transformer architecture, is used to extract features from the training feature combination sequence to obtain high-dimensional training features.

[0107] The training feature combination sequence and the training high-dimensional features are concatenated to obtain the training high-dimensional feature vector;

[0108] Several sets of second sample sets are generated based on the training high-dimensional feature vector and the actual remaining driving range at the most recent running time corresponding to the training high-dimensional feature vector;

[0109] The XGboost model is trained using the second sample set to obtain a pre-trained XGboost model. The second sample set includes the training high-dimensional feature vector as input and the actual remaining driving range at the most recent running time corresponding to the training high-dimensional feature vector as output.

[0110] Specifically, the input to the Transformer needs to be constructed as a time series, i.e., a data sequence containing multiple time steps, representing changes in the vehicle's state over a past period. The feature dimension of a user profile segment is Q, the training feature combination is Q+1, the selected time window is n minutes, and the data batch size is m. Therefore, the shape of the input data is: Inputshape = (m, n, Q+1). Then, through the Transformer's self-attention mechanism, it can learn the correlation between features at each time step and features at other times. For example, it can capture the vehicle's acceleration behavior, speed fluctuations, SOC consumption patterns over a past period, and how these features affect the current vehicle state and range prediction. After encoding through multiple layers of Transformers, the Transformer outputs a data set with the shape: Transformeroutputshape = (m, n, d...). model ), where d model This is a high-dimensional feature dimension, representing the correlation between different input features. Although the Transformer extracts high-dimensional features from the time series, the original input features of each segment of the user profile also contain important instantaneous information. Therefore, it is necessary to concatenate the high-dimensional features generated by the Transformer with the original features at the current time step to obtain a more comprehensive high-dimensional feature vector, where Concatenatedshape = (m, n, d). model +Q+1).

[0111] Specifically, the training process of the XGBoost model involves iteratively building new regression trees, reducing the prediction error of the previous iteration by constructing a new tree each time.

[0112] 1) Initial prediction: Predict the remaining driving range using a simple average or other initial strategy;

[0113] 2) Calculate residuals: Calculate the residuals for each sample based on the difference between the initial predicted values ​​and the actual experimental results; the residuals represent the errors that the model needs to be further optimized.

[0114] 3) Fitting residuals: In each iteration, the model builds a new regression tree specifically to fit these residuals in an attempt to reduce errors;

[0115] 4) Update predictions: After the new regression tree is generated, the model's predictions will be updated to make them closer to the true results;

[0116] 5) Repeated process: This process will continuously iterate and build multiple regression trees until the predetermined number of trees is reached or the error converges.

[0117] In this invention, the calculated remaining driving range is also corrected using the Transformer-XGboost algorithm model. This combines the temporal feature extraction capability of Transformer and the regression capability of XGBoost with actual experimental test results to complete the correction, thereby improving the accuracy and precision of the remaining driving range. XGBoost also uses regularization techniques to prevent model overfitting. By constraining the complexity of the model, it ensures that the model performs well on the training set and maintains good generalization performance on the test set.

[0118] like Figure 3 , Figure 4 As shown, this invention provides a device for estimating remaining driving range based on the equivalent operating conditions of an onboard hydrogen system. The device can be implemented in software, hardware, or a combination of both. From a hardware perspective, such as... Figure 3 The diagram shown is a hardware architecture diagram of a computing device for estimating the remaining driving range based on the equivalent operating conditions of an onboard hydrogen system, provided in an embodiment of the present invention. Except for... Figure 3 In addition to the processor, memory, network interface, and non-volatile memory shown, the computing device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 4 As shown, a device in a logical sense is formed by the CPU of its computing device reading the corresponding computer program from non-volatile memory into memory and running it. This embodiment provides a remaining driving range estimation device based on the equivalent operating conditions of an on-board hydrogen system. The device includes:

[0119] The feature extraction module 400 is used to extract features from the current operating data of the target hydrogen fuel cell vehicle to obtain a current user behavior profile.

[0120] The prediction module 402 is used to input the current user behavior profile and the driving mode to which the current user behavior profile belongs into a pre-trained time-series prediction model to obtain the predicted driving mode for the next moment.

[0121] The reconstruction module 404 is used to reconstruct the operating conditions of the predicted driving mode based on the historical operating data corresponding to each driving mode, so as to obtain the reconstructed operating data under the predicted driving mode.

[0122] The hydrogen consumption calculation module 406 is used to determine the characteristic behavior hydrogen consumption under the reconstructed operating data based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption.

[0123] The mileage calculation module 408 is used to calculate the remaining driving range based on the characteristic behavior hydrogen consumption under the reconstructed operation data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle.

[0124] In some specific implementations, the feature extraction module 400 can be used to perform the above step 100, the prediction module 402 can be used to perform the above step 102, the reconstruction module 404 can be used to perform the above step 104, the hydrogen consumption calculation module 406 can be used to perform the above step 106, and the mileage calculation module 408 can be used to perform the above step 108.

[0125] In one embodiment of the present invention, the device further includes a preprocessing module, which performs the following operations:

[0126] The historical operating data of the target hydrogen fuel cell vehicle is divided into equal time segments to obtain several historical operating segments that include time information and operating data per unit time.

[0127] Feature extraction is performed on several historical operation segments to obtain user profiles for those segments;

[0128] Density clustering algorithm is used to classify user profile fragments and determine the driving mode to which each user profile fragment belongs.

[0129] In one embodiment of the present invention, the preprocessing module is further configured to perform the following operations:

[0130] Acquire unit-time operation data for historical operation segments; the unit-time operation data includes unit-time operation data for the whole vehicle, hydrogen system, power battery, and motor.

[0131] Feature extraction is performed on the data for each unit of time to obtain several features; the number of features is the same as the number of data types included in the data for each unit of time.

[0132] After performing correlation analysis on the features, effective key features were obtained through screening.

[0133] Generate fragmented user profiles based on effective key features.

[0134] In one embodiment of the present invention, the device further includes a first training module, which is further configured to perform the following operations:

[0135] Based on the user profile of the segment and the driving mode to which the user profile of the segment belongs, generate several sets of first sample sets;

[0136] The Transformer architecture with a self-attention mechanism is trained using the first sample set to obtain a pre-trained time-series prediction model. The first sample set includes the current user profile segment and the driving mode to which the current user profile segment belongs as input, and the driving mode to which the next user profile segment belongs as output.

[0137] In one embodiment of the present invention, the reconstruction module 404 is further configured to perform the following operations:

[0138] The historical operating data corresponding to each driving mode is determined from the historical operating data of the target hydrogen fuel cell vehicle, and the various historical operating segments included in the predicted driving mode for the next moment are obtained.

[0139] Calculate the similarity value between the current running segment and each historical running segment included in the predicted driving mode for the next time moment, and determine the highest similarity value;

[0140] The historical running segment corresponding to the highest similarity value is used to determine the running data per unit time of the running segment at the current moment as the reconstructed running data for the next moment.

[0141] In one embodiment of the present invention, the device further includes a second training module, which is also configured to perform the following operations:

[0142] The pre-built mapping relationship between operating conditions and hydrogen consumption is obtained through the following method:

[0143] Establish a nonlinear functional relationship with user profile segments as input and hydrogen consumption as output;

[0144] The optimal solution for the parameters of the nonlinear function relationship is obtained to determine the mapping relationship between operating conditions and hydrogen consumption.

[0145] In one embodiment of the present invention, the second training module is further configured to perform the following operations:

[0146] S1: Initialize the population, determine the feasible region of feasible solutions for initial temperature, temperature cooling rate, cutoff temperature, maximum number of iterations, initial energy of prey, and parameters, and randomly generate a set of potential feasible solutions within the feasible region;

[0147] S2: In the current iteration, the Harris Eagle algorithm is used to optimize the potential feasible solution within the feasible region, resulting in the first updated feasible solution output during the exploration phase and the second updated feasible solution output during the development phase.

[0148] S3: Determine whether to switch from the exploration phase to the development phase based on the prey energy and iteration number of the current iteration; if yes, proceed to step S4; otherwise, proceed to step S1.

[0149] S4: Determine the optimization strategy based on the prey energy, and use the optimization strategy to optimize the first updated feasible solution to obtain the second updated feasible solution;

[0150] S5: Calculate the goodness of fit of the nonlinear function relationship using the optimal solution and the second updated feasible solution in the current iteration. If the goodness of fit of the second updated feasible solution is lower than that of the optimal solution in the current iteration, proceed to step S6; otherwise, proceed to step S7.

[0151] S6: Calculate the acceptance probability of the second updated feasible solution based on the initial temperature, temperature cooling rate, second updated feasible solution, and prey position in the current iteration, and accept the second updated feasible solution according to the acceptance probability; if the second updated feasible solution is accepted, proceed to step S7; if the second updated feasible solution is not accepted, retain the optimal solution in the current iteration, update the current temperature, and proceed to step S8.

[0152] S7: Determine the second updated feasible solution as the optimal solution for the current iteration;

[0153] S8: Determine whether the current iteration count has reached the maximum iteration count or whether the current temperature has reached the cutoff temperature. If so, output the optimal solution; otherwise, use the optimal solution as the initial solution for the next iteration and return to step S2.

[0154] In one embodiment of the present invention, the reconstruction module 404 is further configured to perform the following operations:

[0155] Feature extraction is performed on the reconstructed operational data to obtain a reconstructed user behavior profile under the predicted driving mode;

[0156] By inputting the reconstructed user behavior profile into the pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under the reconstructed user behavior profile is obtained.

[0157] In one embodiment of the present invention, the remaining driving range is calculated based on the hydrogen consumption under the predicted user behavior profile within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle, including:

[0158] A1: Extract features from the current running data to obtain the current user behavior profile; then input the current user behavior profile and the driving mode to which the current user behavior profile belongs into the pre-trained time series prediction model to obtain the predicted driving mode for the next moment.

[0159] A2: Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode;

[0160] A3: Determine whether the current cumulative prediction time length is greater than the preset time threshold. If so, obtain the reconstruction operation data within the prediction time interval and execute step A4; otherwise, use the reconstruction operation data at the next moment as the current operation data and return to step A1.

[0161] A4: Input the reconstructed user behavior profile obtained by feature extraction of the reconstructed running data within the prediction time interval into the mapping relationship to obtain the characteristic behavior hydrogen consumption under each reconstructed running data;

[0162] A5: Accumulate the hydrogen consumption of characteristic behaviors under the reconstructed operation data according to the predicted time sequence to obtain the total hydrogen consumption; when the total hydrogen consumption is the same as the current remaining hydrogen storage, calculate the sum of the driving mileage of the reconstructed operation data included in the total hydrogen consumption to obtain the remaining driving range.

[0163] In one embodiment of the present invention, the mileage calculation module 408 is further configured to perform the following operations:

[0164] Based on the characteristic behavior hydrogen consumption and the current remaining hydrogen storage under the reconfiguration operation data, calculate the instantaneous remaining driving range at the moment when the reconfiguration operation data is located;

[0165] Each reconstructed running data and the instantaneous remaining driving range at the time of that reconstructed running data are used as feature combinations, and the feature combinations are arranged in the order of time information to obtain a feature combination sequence;

[0166] A self-attention mechanism, the Transformer architecture, is used to extract features from the feature combination sequence to obtain high-dimensional features.

[0167] The feature combination sequence and the high-dimensional features are concatenated to obtain the high-dimensional feature vector;

[0168] The high-dimensional feature vector is input into the pre-trained XGboost model, and the corrected remaining driving range is output.

[0169] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on a remaining driving range estimation device based on the equivalent operating conditions of an onboard hydrogen system. In other embodiments of the present invention, a remaining driving range estimation device based on the equivalent operating conditions of an onboard hydrogen system may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0170] The information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the method embodiment of the present invention, and the specific details can be found in the description of the method embodiment of the present invention, and will not be repeated here.

[0171] This invention also provides a computing device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a method for estimating the remaining driving range based on the equivalent operating conditions of an on-board hydrogen system, according to any embodiment of this invention.

[0172] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program causes the processor to perform a method for estimating the remaining driving range based on the equivalent operating conditions of an on-board hydrogen system, according to any embodiment of this invention.

[0173] Embodiments of this application also provide a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium and executes the computer program, causing the computer device to perform a remaining driving range estimation method based on equivalent operating conditions of an on-board hydrogen system as described in any of the above embodiments.

[0174] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0175] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0176] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0177] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0178] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0179] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0180] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for estimating remaining driving range based on equivalent operating conditions of an on-board hydrogen system, characterized in that, include: The historical operation data of the target hydrogen fuel cell vehicle is divided into equal time segments to obtain several historical operation segments including time information and unit time operation data; features are extracted from several historical operation segments to obtain several segment user profiles; a density clustering algorithm is used to classify the segment user profiles to determine the driving mode to which each segment user profile belongs; the segment user profiles; Feature extraction is performed on the current operating data of the target hydrogen fuel cell vehicle to obtain a current user behavior profile; The current user behavior profile and the driving mode to which the current user behavior profile belongs are input into a pre-trained time-series prediction model to obtain the predicted driving mode for the next moment. Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode; Based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under the reconstructed operating data is determined; this is obtained through the following method: establishing a nonlinear function relationship with the segmented user profile as input and hydrogen consumption as output; solving for the optimal solution of the parameters of the nonlinear function relationship to obtain the mapping relationship between the operating conditions and hydrogen consumption; The remaining driving range is obtained based on the characteristic behavior hydrogen consumption under the reconstructed operating data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle. The step of extracting features from several historical runtime segments to obtain several user profiles for those segments includes: Obtain the unit-time operation data of the historical operation segment; wherein, the unit-time operation data includes vehicle data, hydrogen system operation data, power battery data, and motor data; Feature extraction is performed on each unit time operation data to obtain several features; the features include average vehicle speed, acceleration segment ratio, deceleration segment ratio, idling segment ratio, total accelerator pedal duration, total brake pedal duration, average accelerator pedal travel, average brake pedal travel, average operating pressure, average hydrogen consumption, average hydrogen flow rate, average hydrogen sensor concentration, average voltage, average current, average temperature, average residual charge (SOC), average torque, and average speed. After performing correlation analysis on the features, effective key features were obtained by screening. The fragmented user profile is generated based on the effective key features.

2. The method according to claim 1, characterized in that, The pre-trained time series prediction model is trained using the following method: Based on the user profile of the segment and the driving mode to which the user profile of the segment belongs, generate several sets of first sample sets; The Transformer self-attention mechanism architecture is trained using the first sample set to obtain the pre-trained temporal prediction model; wherein, the first sample set includes the user profile of the segment at the current time as input and the driving mode to which the user profile of the segment belongs, and the driving mode to which the user profile of the segment at the next time as output.

3. The method according to claim 1, characterized in that, Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode, including: The historical operating data corresponding to each driving mode is determined from the historical operating data of the target hydrogen fuel cell vehicle, and the various historical operating segments included in the predicted driving mode for the next moment are obtained. Calculate the similarity value between the current running segment and each historical running segment included in the predicted driving mode for the next time moment, and determine the highest similarity value; The unit-time running data included in the historical running segment corresponding to the highest similarity value is determined as the reconstructed running data for the next moment corresponding to the running segment at the current moment.

4. The method according to claim 1, characterized in that, Based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption, the characteristic behavior hydrogen consumption under the reconstructed operating data is determined, including: Feature extraction is performed on the reconstructed running data to obtain the reconstructed user behavior profile under the predicted driving mode; The reconstructed user behavior profile is input into the pre-built mapping relationship between operating conditions and hydrogen consumption to obtain the characteristic behavior hydrogen consumption under the reconstructed user behavior profile.

5. The method according to claim 4, characterized in that, The optimal solution for the parameters of the nonlinear function relationship includes: S1: Initialize the population, determine the initial temperature, temperature cooling rate, cutoff temperature, maximum number of iterations, initial energy of prey, and the feasible region of feasible solutions for the parameters, and randomly generate a set of potential feasible solutions within the feasible region; S2: In the current iteration, the potential feasible solution is optimized within the feasible region based on the Harris Eagle algorithm to obtain the first updated feasible solution output in the exploration phase; S3: Determine whether to switch from the exploration phase to the development phase based on the prey energy and iteration number of the current iteration; if yes, proceed to step S4; otherwise, proceed to step S1. S4: Determine an optimization strategy based on the prey energy, and use the optimization strategy to optimize the first updated feasible solution to obtain a second updated feasible solution; S5: Calculate the goodness of fit of the nonlinear function relationship using the optimal solution in the current iteration and the second updated feasible solution respectively. If the goodness of fit of the second updated feasible solution is lower than the goodness of fit of the optimal solution in the current iteration, then proceed to step S6; otherwise, proceed to step S7. S6: Calculate the acceptance probability of the second updated feasible solution based on the initial temperature, the temperature cooling rate, the second updated feasible solution, and the prey position of the current iteration, and accept the second updated feasible solution according to the acceptance probability; if the second updated feasible solution is accepted, proceed to step S7; if the second updated feasible solution is not accepted, retain the optimal solution in the current iteration, update the current temperature, and proceed to step S8. S7: Determine the second updated feasible solution as the optimal solution for the current iteration; S8: Determine whether the current iteration count has reached the maximum iteration count or whether the current temperature has reached the cutoff temperature. If so, output the optimal solution; otherwise, use the optimal solution as the initial solution for the next iteration and return to step S2.

6. The method according to claim 1, characterized in that, The calculation of the remaining driving range based on the characteristic behavior hydrogen consumption under the reconstructed operating data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle includes: A1: Extract features from the current running data to obtain the current user behavior profile; then input the current user behavior profile and the driving mode to which the current user behavior profile belongs into the pre-trained time-series prediction model to obtain the predicted driving mode for the next moment. A2: Based on the historical operating data corresponding to each driving mode, the operating conditions of the predicted driving mode are reconstructed to obtain the reconstructed operating data under the predicted driving mode; A3: Determine whether the current cumulative prediction time length is greater than the preset time threshold. If so, obtain the reconstruction operation data within the prediction time interval and execute step A4; otherwise, take the reconstruction operation data at the next moment as the current operation data and return to step A1. A4: Input the reconstructed user behavior profile obtained by feature extraction of the reconstructed running data within the predicted time interval into the mapping relationship to obtain the characteristic behavior hydrogen consumption under each of the reconstructed running data; A5: Accumulate the hydrogen consumption of characteristic behaviors under the reconstructed operation data according to the predicted time sequence to obtain the total hydrogen consumption; when the total hydrogen consumption is the same as the current remaining hydrogen storage, calculate the sum of the driving mileage of the reconstructed operation data included in the total hydrogen consumption to obtain the remaining driving range.

7. The method according to any one of claims 2 to 6, characterized in that, After obtaining the remaining driving range, the process also includes: Based on the characteristic behavior hydrogen consumption under the reconfiguration operation data and the current remaining hydrogen storage, calculate the instantaneous remaining driving range at the time of the reconfiguration operation data. Each reconstructed operation data and the instantaneous remaining driving range at the time of the reconstructed operation data are used as a feature combination, and the feature combinations are arranged in the order of the time information to obtain a feature combination sequence; The Transformer architecture, employing a self-attention mechanism, is used to extract features from the feature combination sequence, resulting in high-dimensional features. The feature combination sequence and the high-dimensional feature are concatenated to obtain a high-dimensional feature vector; The high-dimensional feature vector is input into the pre-trained XGboost model, and the corrected remaining driving range is output.

8. A device for estimating remaining driving range based on equivalent operating conditions of an on-board hydrogen system, characterized in that, To implement the method as described in any one of claims 1-7, comprising: The feature extraction module is used to extract features from the current operating data of the target hydrogen fuel cell vehicle to obtain a current user behavior profile. The prediction module is used to input the current user behavior profile and the driving mode to which the current user behavior profile belongs into a pre-trained time-series prediction model to obtain the predicted driving mode for the next moment. The reconstruction module is used to reconstruct the operating conditions of the predicted driving mode based on the historical operating data corresponding to each driving mode, so as to obtain the reconstructed operating data under the predicted driving mode. The hydrogen consumption calculation module is used to determine the characteristic behavior hydrogen consumption under the reconstructed operating data based on the reconstructed operating data and the pre-built mapping relationship between operating conditions and hydrogen consumption. The mileage calculation module is used to calculate the remaining driving range based on the characteristic behavior hydrogen consumption under the reconstructed operating data within the predicted time interval and the current remaining hydrogen storage of the target hydrogen fuel cell vehicle.

9. A computing device comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method of any one of claims 1-7.

Images