A path planning method based on real-time hydrogen detection in new energy vehicles

Abstract

This invention provides a path planning method based on real-time hydrogen detection for new energy vehicles. The method includes real-time monitoring of the hydrogen quantity in the new energy vehicle to acquire hydrogen data; acquiring the real-time destination of the new energy vehicle and constructing a hydrogen consumption simulation framework based on the hydrogen data, destination, and transportation network; locating the new energy vehicle and, based on the hydrogen consumption simulation framework, acquiring the real-time planned path for the new energy vehicle, and transmitting the real-time planned path to a data transmission terminal. This invention can dynamically plan the real-time driving path of new energy vehicles based on their real-time hydrogen data. It is applicable to new energy vehicles and can continuously optimize the path based on energy supply data. It can reasonably monitor and remind energy sources when new energy supply equipment is insufficient. It can also perform real-time location tracking of new energy vehicles, enabling real-time calculation of energy supply and assessment of energy consumption status.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and in particular to a path planning method based on real-time hydrogen detection in new energy vehicles. Background Technology

[0002] Currently, hydrogen is a clean and efficient secondary energy source. With the development of hydrogen energy technology and the need to address increasingly severe global climate change, many developed countries have elevated the development of the hydrogen energy industry to the level of national energy strategy.

[0003] Hydrogen fuel cell vehicles convert chemical energy into electrical energy through a chemical reaction between hydrogen and oxygen, thereby driving an electric motor to power the vehicle. Compared to traditional gasoline and hybrid vehicles, the reaction byproduct of hydrogen fuel cell vehicles is water, achieving zero emissions. Furthermore, hydrogen is a renewable energy source, fully aligning with energy conservation and emission reduction requirements.

[0004] However, in real-world applications, if hydrogen is used as the energy source for new energy vehicles, it needs to be converted into electricity first and then into power. Therefore, in detecting hydrogen volume, the conversion efficiency of the car's electric motor can be used to determine the range that hydrogen can power. In contrast, traditional gasoline vehicles, which are directly powered by internal combustion engines, are not easy to calculate in terms of range and tend to have larger discrepancies.

[0005] While existing technologies can directly calculate mileage based on hydrogen levels, hydrogen differs from fuel oil. When hydrogen is converted into electricity, it is closely related to the surrounding environment, requiring real-time route planning based on hydrogen level detection. Summary of the Invention

[0006] This invention provides a path planning method based on real-time hydrogen detection in new energy vehicles to address the issues mentioned in the background section.

[0007] This invention proposes a path planning method based on real-time hydrogen detection in new energy vehicles, comprising:

[0008] Real-time monitoring of hydrogen levels in new energy vehicles to obtain hydrogen data;

[0009] Obtain the real-time destinations of new energy vehicles and construct a hydrogen consumption simulation framework based on hydrogen data, destinations, and transportation networks.

[0010] The system locates new energy vehicles and, based on a hydrogen consumption simulation framework, obtains their real-time planned paths, which are then transmitted to a data transmission terminal.

[0011] Preferably, the method further includes:

[0012] Construct an energy composition model for new energy vehicles;

[0013] Construct an energy supply model for new energy vehicles based on hydrogen conversion;

[0014] Construct a loss model for hydrogen conversion in new energy vehicles based on environmental data;

[0015] Based on the energy composition model, the hydrogen energy conversion constraints and the first objective function of energy composition for new energy vehicles are set.

[0016] Based on the energy supply model, hydrogen energy efficiency constraints for new energy vehicles and a second objective function for hydrogen conversion are set.

[0017] Based on the loss model, environmental constraints and a third objective function for environmental loss of new energy vehicles are set.

[0018] Based on the objective function and constraints, a model for optimizing the particle swarm optimization algorithm for hydrogen conversion was established using the Matlab platform to determine the real-time convertible mileage of hydrogen.

[0019] Preferably, the energy composition model includes the following construction steps:

[0020] The energy supply components of new energy vehicles are obtained, and the energy conversion rate evaluation index and energy supply priority classification of new energy vehicles are determined based on the components.

[0021] Based on the energy conversion rate evaluation index and energy supply priority classification, energy conversion data of new energy vehicles are collected to establish a sample dataset of energy supply for new energy vehicles, which is divided into training set and test set samples.

[0022] Multiple metaheuristic optimization algorithms were used to optimize the hyperparameters of the random forest model, and a corresponding energy composition model was established; among them...

[0023] The energy composition model is trained using training and test set samples to obtain energy supply priority ranking.

[0024] Preferably, the energy supply model includes the following construction steps:

[0025] Incorporating nonlinear hydrogen-electric energy processes into new energy vehicles; among which...

[0026] The nonlinear hydrogen-electric energy process includes the hydrogen conversion clock process, the hydrogen consumption calculation process, the electrical energy increment calculation process, and the hydrogen conversion rate calculation process.

[0027] Establish a hydrogen-electric coupling model for nonlinear hydrogen-electric energy processes;

[0028] Based on the hydrogen-electric coupling model, the hydrogen-electric conversion efficiency is determined, and an energy supply model is generated.

[0029] Preferably, the loss model includes the following construction steps:

[0030] Acquire environmental and power data of new energy vehicles under current driving conditions;

[0031] The environmental data includes: temperature, humidity, oxygen concentration, and altitude;

[0032] The power data includes: power status, power discharge efficiency, depth of discharge, and state of charge;

[0033] Convert environmental and power data under current driving conditions into corresponding feature data;

[0034] The feature data includes power loss data;

[0035] The converted feature data is input into the trained power loss model to obtain the amount of power loss during hydrogen-to-electricity conversion.

[0036] The capacity loss model is used to describe characteristic data, capacity loss, and hydrogen-to-electricity conversion relationship;

[0037] Based on the amount of power loss, construct the power loss equation;

[0038] The loss model is determined by the power loss equation.

[0039] Preferably, the loss model training steps are as follows:

[0040] Several environmental simulation spaces were established, and different environmental parameters were set in the environmental simulation spaces to determine the hydrogen-to-electricity conversion data;

[0041] Based on different environmental parameters, determine the different characteristic parameters under the corresponding environmental parameters;

[0042] The power loss model is trained using feature data. The training is completed when the fitting deviation between the capacity loss calculated based on the trained power loss model and the actual measured capacity loss is within a preset range.

[0043] Preferably, the real-time monitoring includes:

[0044] Hydrogen balance is monitored by a hydrogen balance monitoring module. The hydrogen balance at different times is time-series encoded, and each bit in the time-series encoding is used as a monitoring number.

[0045] The monitoring number will be sent to the vehicle terminal at preset intervals.

[0046] The vehicle terminal analyzes and processes the remaining hydrogen data to generate display data and alarm data.

[0047] Preferably, the hydrogen consumption simulation framework includes the following construction steps:

[0048] Based on hydrogen data, a time series model based on hydrogen-to-electricity conversion was established.

[0049] Based on the destination and the real-time location of the new energy vehicle, a route planning model based on the transportation network is constructed; among them,

[0050] The path planning model includes multiple routes for new energy vehicles to reach their destinations based on their real-time locations;

[0051] Based on time series models and path planning models, hydrogen consumption data of new energy vehicles on different routes at different times are determined, and a hydrogen consumption matrix based on time prediction is constructed.

[0052] Based on the hydrogen consumption matrix, a multi-combination model is traversed, and based on the traversed data, a hydrogen consumption simulation framework based on linear transformation is built.

[0053] Preferably, the real-time planned path includes:

[0054] Based on the hydrogen consumption simulation framework, path planning is carried out, and all road paths with hydrogen consumption lower than the real-time hydrogen reserve are considered as plannable routes based on the remaining hydrogen amount of new energy vehicles.

[0055] Based on the A* algorithm search, the hydrogen consumption data in the planarable routes are sorted, and the planned path with the minimum consumption cost is taken as the feasible optimal route.

[0056] Based on the location of the new energy vehicle, the starting point is continuously updated, and real-time route planning is carried out.

[0057] Preferably, the continuously updating starting point includes:

[0058] Receive the user's path planning instructions and generate a real-time floating ball based on the path planning;

[0059] Based on the real-time floating ball, the location information of new energy vehicles is received in real time;

[0060] Based on the location information, construct a mapping function for real-time route planning;

[0061] Generate a scatter sequence of hydrogen consumption that is no higher than the remaining hydrogen based on the location information in the mapping function;

[0062] Input the residual scatter sequence into the mapping function to solve for the dynamic positioning parameter sequence that satisfies the constraints;

[0063] Based on the dynamic positioning parameter sequence, the positioning data in the floating ball is continuously traversed, and the positioning information is continuously updated in real-time route planning.

[0064] The beneficial effects of this invention are as follows:

[0065] This invention can dynamically plan the real-time driving path of new energy vehicles based on their real-time hydrogen data.

[0066] This invention is applicable to new energy vehicles. It can continuously optimize routes based on energy supply data and reasonably monitor and remind users of energy availability when new energy supply equipment is insufficient.

[0067] This invention can locate new energy vehicles in real time, enabling real-time positioning of both vehicle energy supply and energy supply calculation to determine energy consumption status.

[0068] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0069] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0070] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0071] In the attached diagram:

[0072] Figure 1 This is a flowchart of a path planning method based on real-time hydrogen detection in new energy vehicles, as described in an embodiment of the present invention.

[0073] Figure 2 This is a flowchart illustrating the calculation of hydrogen convertible mileage in an embodiment of the present invention;

[0074] Figure 3 This is a flowchart illustrating the dynamic update of positioning in an embodiment of the present invention. Detailed Implementation

[0075] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0076] This invention proposes a path planning method based on real-time hydrogen detection in new energy vehicles, comprising:

[0077] Real-time monitoring of hydrogen levels in new energy vehicles to obtain hydrogen data;

[0078] Obtain the real-time destinations of new energy vehicles and construct a hydrogen consumption simulation framework based on hydrogen data, destinations, and transportation networks.

[0079] The system locates new energy vehicles and, based on a hydrogen consumption simulation framework, obtains their real-time planned paths, which are then transmitted to a data transmission terminal.

[0080] The working principle of the above technical solution is as follows:

[0081] As attached Figure 1 As shown, in this embodiment, the methods for real-time monitoring of hydrogen quantity include, but are not limited to, real-time hydrogen sensors, real-time calculation of hydrogen-to-electricity conversion and hydrogen loss in the environment, and monitoring data of insufficient hydrogen quantity.

[0082] In this embodiment, the hydrogen consumption simulation framework determines the hydrogen consumption simulation model on different planned routes during the dynamic process of the vehicle, under the existing environment and vehicle driving parameters, based on hydrogen data and real-time destination. It realizes the calculation of hydrogen consumption based on the route and the prediction of hydrogen consumption when planning different routes.

[0083] In this embodiment, the new energy vehicle is located, and the distance between the real-time driving location and the destination can be dynamically determined based on the real-time location. This allows for continuous optimization of the real-time driving route and real-time reduction of hydrogen consumption.

[0084] The beneficial effects of the above technical solution are as follows:

[0085] This invention can dynamically plan the real-time driving path of new energy vehicles based on their real-time hydrogen data.

[0086] This invention is applicable to new energy vehicles. It can continuously optimize routes based on energy supply data and reasonably monitor and remind users of energy availability when new energy supply equipment is insufficient.

[0087] This invention can locate new energy vehicles in real time, enabling real-time positioning of both vehicle energy supply and energy supply calculation to determine energy consumption status.

[0088] Preferably, the method further includes:

[0089] Construct an energy composition model for new energy vehicles;

[0090] Construct an energy supply model for new energy vehicles based on hydrogen conversion;

[0091] Construct a loss model for hydrogen conversion in new energy vehicles based on environmental data;

[0092] Based on the energy composition model, the hydrogen energy conversion constraints and the first objective function of energy composition for new energy vehicles are set.

[0093] Based on the energy supply model, hydrogen energy efficiency constraints for new energy vehicles and a second objective function for hydrogen conversion are set.

[0094] Based on the loss model, environmental constraints and a third objective function for environmental loss of new energy vehicles are set.

[0095] Based on the objective function and constraints, a model for optimizing the particle swarm optimization algorithm for hydrogen conversion was established using the Matlab platform to determine the real-time convertible mileage of hydrogen.

[0096] The working principle of the above technical solution is as follows:

[0097] As attached Figure 2 As shown in this embodiment, the energy composition model is used to construct the energy supply system model of new energy vehicles, determine whether the new energy vehicle is powered solely by hydrogen or by both electricity and gas, and realize combined energy supply calculation.

[0098] In this embodiment, the energy supply model is used to determine the hydrogen functional conversion efficiency under different environmental parameters.

[0099] In this embodiment, a loss model is used to determine the losses caused by hydrogen power supply under different environmental parameters.

[0100] In this embodiment, the hydrogen energy conversion constraints and the first objective function of the energy composition can be used to determine the hydrogen conversion efficiency and calculate the conversion function.

[0101] In this embodiment, the hydrogen energy efficiency constraint and the second objective function of hydrogen conversion can be determined based on the hydrogen-to-electricity conversion efficiency constraint, and the third objective function is the loss function of hydrogen-to-electricity conversion under different environmental conditions.

[0102] The beneficial effects of the above technical solution are as follows:

[0103] By using various energy models in the hydrogen-to-electricity conversion process, the energy conversion efficiency is determined and the energy conversion loss is calculated, thereby accurately determining the driving range of new energy vehicles with the current hydrogen reserve.

[0104] Preferably, the energy composition model includes the following construction steps:

[0105] The energy supply components of new energy vehicles are obtained, and the energy conversion rate evaluation index and energy supply priority classification of new energy vehicles are determined based on the components.

[0106] Based on the energy conversion rate evaluation index and energy supply priority classification, energy conversion data of new energy vehicles are collected to establish a sample dataset of energy supply for new energy vehicles, which is divided into training set and test set samples.

[0107] Multiple metaheuristic optimization algorithms were used to optimize the hyperparameters of the random forest model, and a corresponding energy composition model was established; among them...

[0108] The energy composition model is trained using training and test set samples to obtain energy supply priority ranking.

[0109] The working principle of the above technical solution is as follows:

[0110] In this embodiment, the energy supply components include different energy supply systems for new energy vehicles, and the energy conversion rate and priority of new energy vehicles are determined.

[0111] In this embodiment, the purpose of using multiple metaheuristic optimization algorithms to optimize the hyperparameters in the random forest model is to accurately calculate the priority of different energy sources during the process of multiple energy supply, thereby determining the energy supply priority.

[0112] Then, the energy composition model is trained using a network neural algorithm, employing conventional neural network algorithms, to achieve hierarchical processing of energy supply priorities.

[0113] The beneficial effects of the above technical solution are as follows:

[0114] When new energy vehicles have different energy systems, different energy sources can be allocated, thereby determining the priority of energy supply for different energy sources.

[0115] For new energy vehicles with hybrid fuels, this invention can perform optimization calculations during the driving process of the vehicle based on its energy composition, and determine the priority level of the energy source.

[0116] Preferably, the energy supply model includes the following construction steps:

[0117] Incorporating nonlinear hydrogen-electric energy processes into new energy vehicles; among which...

[0118] The nonlinear hydrogen-electric energy process includes the hydrogen conversion clock process, the hydrogen consumption calculation process, the electrical energy increment calculation process, and the hydrogen conversion rate calculation process.

[0119] Establish a hydrogen-electric coupling model for nonlinear hydrogen-electric energy processes;

[0120] Based on the hydrogen-electric coupling model, the hydrogen-electric conversion efficiency is determined, and an energy supply model is generated.

[0121] The working principle of the above technical solution is as follows:

[0122] In this embodiment, the nonlinear hydrogen-to-electric energy process is calculated based on a nonlinear hydrogen-to-electric conversion function.

[0123] In this embodiment, the hydrogen-electric coupling model determines the conversion efficiency during the hydrogen-electric conversion process by fitting the consumption curve of hydrogen to electrical energy and the generation curve of electrical energy.

[0124] The beneficial effects of the above technical solution are as follows:

[0125] This application can calculate the current hydrogen-to-electricity conversion efficiency of hydrogen by generating an energy supply model, thereby enabling the actual calculation and prediction of hydrogen and mileage.

[0126] Preferably, the loss model includes the following construction steps:

[0127] Acquire environmental and power data of new energy vehicles under current driving conditions;

[0128] The environmental data includes: temperature, humidity, oxygen concentration, and altitude;

[0129] The power data includes: power status, power discharge efficiency, depth of discharge, and state of charge;

[0130] Convert environmental and power data under current driving conditions into corresponding feature data;

[0131] The feature data includes power loss data;

[0132] The converted feature data is input into the trained power loss model to obtain the amount of power loss during hydrogen-to-electricity conversion.

[0133] The capacity loss model is used to describe characteristic data, capacity loss, and hydrogen-to-electricity conversion relationship;

[0134] Based on the amount of power loss, construct the power loss equation;

[0135] The loss model is determined by the power loss equation.

[0136] The working principle of the above technical solution is as follows:

[0137] In this embodiment, the loss model needs to combine the power data of the environmental data under the current driving conditions, so as to determine the hydrogen-to-electricity conversion loss based on the relevant influencing factors.

[0138] In this embodiment, the feature data is the energy loss feature data during the hydrogen-to-electricity conversion process;

[0139] Based on the loss characteristic data, a mathematical equation for power calculation is constructed to calculate the loss rate of hydrogen-to-electricity conversion.

[0140] The principle behind the above technical solution is as follows:

[0141] This application constructs an energy loss equation, which can determine the energy loss of new energy vehicles caused by different environmental factors and hydrogen consumption itself. Thus, it can more accurately determine the driving range that the remaining hydrogen can provide under the current operating environment and conditions.

[0142] Preferably, the loss model training steps are as follows:

[0143] Several environmental simulation spaces were established, and different environmental parameters were set in the environmental simulation spaces to determine the hydrogen-to-electricity conversion data;

[0144] Based on different environmental parameters, determine the different characteristic parameters under the corresponding environmental parameters;

[0145] The power loss model is trained using feature data. The training is completed when the fitting deviation between the capacity loss calculated based on the trained power loss model and the actual measured capacity loss is within a preset range.

[0146] The working principle of the above technical solution is as follows:

[0147] In this embodiment, the purpose of several environmental simulation spaces is to determine the efficiency of hydrogen-to-electricity conversion by setting different environmental parameters in the simulation spaces.

[0148] In this embodiment, different environmental parameters include, but are not limited to, various combinations of parameters under different temperatures, different humidity levels, and different vehicle speeds.

[0149] By training the power loss model with feature data, we can identify potential biases in the model, process those biases, and more accurately determine the loss outcome.

[0150] The beneficial effects of the above technical solution are as follows:

[0151] This invention can simulate different power loss parameters under different environmental parameters in a simulation space, and then build a loss model.

[0152] Preferably, the real-time monitoring includes:

[0153] Hydrogen balance is monitored by a hydrogen balance monitoring module. The hydrogen balance at different times is time-series encoded, and each bit in the time-series encoding is used as a monitoring number.

[0154] The monitoring number will be sent to the vehicle terminal at preset intervals.

[0155] The vehicle terminal analyzes and processes the remaining hydrogen data to generate display data and alarm data.

[0156] The working principle of the above technical solution is as follows:

[0157] In this embodiment, the present invention records the hydrogen balance at each moment by means of time-series coding and generates a hydrogen monitoring sequence.

[0158] In this embodiment, the present invention sends hydrogen remaining data to the vehicle terminal for analysis and alerts by monitoring the number and interval time.

[0159] Preferably, the hydrogen consumption simulation framework includes the following construction steps:

[0160] Based on hydrogen data, a time series model based on hydrogen-to-electricity conversion was established.

[0161] Based on the destination and the real-time location of the new energy vehicle, a route planning model based on the transportation network is constructed; among them,

[0162] The path planning model includes multiple routes for new energy vehicles to reach their destinations based on their real-time locations;

[0163] Based on time series models and path planning models, hydrogen consumption data of new energy vehicles on different routes at different times are determined, and a hydrogen consumption matrix based on time prediction is constructed.

[0164] Based on the hydrogen consumption matrix, a multi-combination model is traversed, and based on the traversed data, a hydrogen consumption simulation framework based on linear transformation is built.

[0165] The working principle of the above technical solution is as follows:

[0166] In this embodiment, the time series model is used to record the hydrogen conversion data at each moment, including but not limited to conversion efficiency, conversion loss and conversion amount;

[0167] In this embodiment, the path planning model is used to plan all drivable paths from the real-time location of the new energy vehicle to its destination.

[0168] In this embodiment, the hydrogen consumption matrix is ​​constructed from hydrogen consumption and driving route, which determines the predicted hydrogen consumption of different driving routes at different times.

[0169] In this embodiment, a multi-combination mode is used to traverse hydrogen consumption data under different combinations of environmental parameters.

[0170] In this embodiment, the hydrogen consumption simulation framework is used to simulate hydrogen consumption data under different driving routes.

[0171] Preferably, the real-time planned path includes:

[0172] Based on the hydrogen consumption simulation framework, path planning is carried out, and all road paths with hydrogen consumption lower than the real-time hydrogen reserve are considered as plannable routes based on the remaining hydrogen amount of new energy vehicles.

[0173] Based on the A* algorithm search, the hydrogen consumption data in the planarable routes are sorted, and the planned path with the minimum consumption cost is taken as the feasible optimal route.

[0174] Based on the location of the new energy vehicle, the starting point is continuously updated, and real-time route planning is carried out.

[0175] The working principle of the above technical solution is as follows:

[0176] In this embodiment, the plannable route is a planned route that the new energy vehicle can travel from the real-time location to the destination.

[0177] In this embodiment, the A* algorithm is used to search for the hydrogen consumption of different routes in a planarable route.

[0178] In this embodiment, the starting point is updated in real time to enable continuous replanning and updating of the driving route, thereby ensuring the lowest possible hydrogen consumption.

[0179] Preferably, the continuously updating starting point includes:

[0180] Receive the user's path planning instructions and generate a real-time floating ball based on the path planning;

[0181] Based on the real-time floating ball, the location information of new energy vehicles is received in real time;

[0182] Based on the location information, construct a mapping function for real-time route planning;

[0183] Generate a scatter sequence of hydrogen consumption that is no higher than the remaining hydrogen based on the location information in the mapping function;

[0184] Input the residual scatter sequence into the mapping function to solve for the dynamic positioning parameter sequence that satisfies the constraints;

[0185] Based on the dynamic positioning parameter sequence, the positioning data in the floating ball is continuously traversed, and the positioning information is continuously updated in real-time route planning.

[0186] The working principle of the above technical solution is as follows:

[0187] As attached Figure 3 As shown, in this embodiment, the real-time levitating ball is used to receive the positioning data of the new energy vehicle in real time and determine the driving path based on the positioning data;

[0188] In this embodiment, the mapping function is used to map the real-time parameters of hydrogen consumption under different circuits.

[0189] In this embodiment, the scatter plot sequence of the remaining amount is a scatter plot sequence of the remaining amount of hydrogen, which determines the dynamic parameters of the remaining amount of hydrogen.

[0190] In this embodiment, the path data is updated in real time based on the dynamic parameter of the hydrogen reserve.

[0191] The beneficial effects of the above technical solution are as follows:

[0192] This invention can update the driving route in real time based on the continuous updating of the real-time location, and thus achieve the positioning in the path planning through the floating ball.

[0193] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A path planning method based on real-time hydrogen detection in new energy vehicles, characterized in that, include: Real-time monitoring of hydrogen levels in new energy vehicles to obtain hydrogen data; Obtain the real-time destinations of new energy vehicles and construct a hydrogen consumption simulation framework based on hydrogen data, destinations, and transportation networks. The system locates new energy vehicles and, based on a hydrogen consumption simulation framework, obtains their real-time planned paths, which are then transmitted to a data transmission terminal. The method further includes: Construct an energy composition model for new energy vehicles; Construct an energy supply model for new energy vehicles based on hydrogen conversion; Construct a loss model for hydrogen conversion in new energy vehicles based on environmental data; Based on the energy composition model, the hydrogen energy conversion constraints and the first objective function of energy composition for new energy vehicles are set. Based on the energy supply model, hydrogen energy efficiency constraints for new energy vehicles and a second objective function for hydrogen conversion are set. Based on the loss model, environmental constraints and a third objective function for environmental loss of new energy vehicles are set. Based on the objective function and constraints, a model for optimizing the particle swarm optimization algorithm for hydrogen conversion was established using the Matlab platform to determine the real-time convertible mileage of hydrogen.

2. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 1, characterized in that, The energy composition model includes the following construction steps: The energy supply components of new energy vehicles are obtained, and the energy conversion rate evaluation index and the first energy supply priority classification of new energy vehicles are determined based on the components. Based on the energy conversion rate evaluation index and the first energy supply priority classification, energy conversion data of new energy vehicles are collected to establish a new energy vehicle energy supply sample dataset, which is divided into training set and test set samples. Multiple metaheuristic optimization algorithms were used to optimize the hyperparameters of the random forest model, and a corresponding energy composition model was established; among them... The energy composition model is trained using training and test set samples to obtain the second energy supply priority classification.

3. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 1, characterized in that, The energy supply model includes the following construction steps: Incorporating nonlinear hydrogen-electric energy processes into new energy vehicles; among which... The nonlinear hydrogen-electric energy process includes the hydrogen conversion clock process, the hydrogen consumption calculation process, the electrical energy increment calculation process, and the hydrogen conversion rate calculation process. Establish a hydrogen-electric coupling model for nonlinear hydrogen-electric energy processes; Based on the hydrogen-electric coupling model, the hydrogen-electric conversion efficiency is determined, and an energy supply model is generated.

4. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 1, characterized in that, The loss model includes the following construction steps: Acquire environmental and power data of new energy vehicles under current driving conditions; The environmental data includes: temperature, humidity, oxygen concentration, and altitude; The power data includes: power status, power discharge efficiency, depth of discharge, and state of charge; Convert environmental and power data under current driving conditions into corresponding feature data; The feature data includes power loss data; The converted feature data is input into the trained power loss model to obtain the amount of power loss during hydrogen-to-electricity conversion. The capacity loss model is used to describe characteristic data, capacity loss, and hydrogen-to-electricity conversion relationship; Based on the amount of power loss, construct the power loss equation; The loss model is determined by the power loss equation.

5. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 4, characterized in that, The training steps for the loss model are as follows: Several environmental simulation spaces were established, and different environmental parameters were set in the environmental simulation spaces to determine the hydrogen-to-electricity conversion data; Based on different environmental parameters, determine the different characteristic parameters under the corresponding environmental parameters; The power loss model is trained using feature data. The training is completed when the fitting deviation between the capacity loss calculated based on the trained power loss model and the actual measured capacity loss is within a preset range.

6. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 1, characterized in that, The real-time monitoring includes: Hydrogen balance is monitored by a hydrogen balance monitoring module. The hydrogen balance at different times is time-series encoded, and each bit in the time-series encoding is used as a monitoring number. The monitoring number will be sent to the vehicle terminal at preset intervals. The vehicle terminal analyzes and processes the remaining hydrogen data to generate display data and alarm data.

7. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 1, characterized in that, The hydrogen consumption simulation framework includes the following construction steps: Based on hydrogen data, a time series model based on hydrogen-to-electricity conversion was established. Based on the destination and the real-time location of the new energy vehicle, a route planning model based on the transportation network is constructed; among them, The path planning model includes multiple routes for new energy vehicles to reach their destinations based on their real-time locations; Based on time series models and path planning models, hydrogen consumption data of new energy vehicles on different routes at different times are determined, and a hydrogen consumption matrix based on time prediction is constructed. Based on the hydrogen consumption matrix, a multi-combination model is traversed, and based on the traversed data, a hydrogen consumption simulation framework based on linear transformation is built.

8. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 1, characterized in that, The real-time planning path includes: Based on the hydrogen consumption simulation framework, path planning is carried out, and all road paths with hydrogen consumption lower than the real-time hydrogen reserve are considered as plannable routes based on the remaining hydrogen amount of new energy vehicles. based on The algorithm searches and sorts the hydrogen consumption data in the planable routes, and selects the planable path with the lowest consumption cost as the feasible optimal route. Based on the location of the new energy vehicle, the starting point is continuously updated, and real-time route planning is carried out.

9. The path planning method based on real-time hydrogen detection in new energy vehicles as described in claim 8, characterized in that, The continuously updating starting point includes: Receive the user's path planning instructions and generate a real-time floating ball based on the path planning; Based on the real-time floating ball, the location information of new energy vehicles is received in real time; Based on the location information, construct a mapping function for real-time route planning; Generate a scatter sequence of hydrogen consumption that is no higher than the remaining hydrogen based on the location information in the mapping function; Input the residual scatter sequence into the mapping function to solve for the dynamic positioning parameter sequence that satisfies the constraints; Based on the dynamic positioning parameter sequence, the positioning data in the floating ball is continuously traversed, and the positioning information is continuously updated in real-time route planning.

Images