Typical working condition construction method and device and related product

Abstract

The invention provides a typical working condition construction method and device and a related product, and relates to the technical field of vehicles. The method comprises the following steps: acquiring historical vehicle parameter values which comprise vehicle latitude and longitude data, processing the historical vehicle parameter values to obtain historical vehicle working condition characteristic evaluation parameters, and dividing the historical vehicle working condition characteristic evaluation parameters by using a coacervate clustering algorithm and the vehicle latitude and longitude data to obtain a vehicle working condition characteristic evaluation result; obtaining historical vehicle working condition characteristic evaluation parameters of different types of vehicles in different scenes, and finally constructing a plurality of typical working conditions by using a multi-level two-dimensional Markov chain Monte Carlo method and the historical vehicle working condition characteristic evaluation parameters of different types of vehicles in different scenes. In this way, the real driving mode and the dynamic characteristics of the fuel cell vehicle can be accurately captured, and then the accuracy of fuel cell vehicle energy efficiency evaluation is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a typical operating condition construction method, device and related products. Background Art

[0002] The actual driving cycle and energy efficiency evaluation of fuel cell vehicles is an important part of improving their technical maturity and market promotion. In the existing technology, traditional driving cycle testing and simulation methods often fail to accurately reflect the complexity and variability of actual driving conditions, resulting in low accuracy in energy efficiency evaluation of fuel cell vehicles.

[0003] In summary, how to improve the accuracy of fuel cell vehicle energy efficiency evaluation is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0004] In view of this, the present application provides a typical operating condition construction method, device and related products, aiming to improve the accuracy of fuel cell vehicle energy efficiency evaluation.

[0005] In a first aspect, the present application provides a typical working condition construction method, comprising: Acquire historical vehicle parameter values; the vehicle parameter values ​​include vehicle latitude and longitude data; Processing the historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters; Using an agglomerative hierarchical clustering algorithm and the vehicle longitude and latitude data, the historical vehicle operating condition characteristic evaluation parameters are divided to obtain historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios; A plurality of typical operating conditions are constructed by using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of the different categories of vehicles in different scenarios.

[0006] Optionally, after constructing a plurality of typical operating conditions using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, the method further includes: Get the target vehicle parameter value; Processing the target vehicle parameter value to obtain a target vehicle operating condition characteristic evaluation parameter; The target vehicle operating condition characteristic evaluation parameter is matched with the multiple typical operating conditions to obtain a target typical operating condition; the target typical operating condition is a typical operating condition that is closest to the target vehicle operating condition.

[0007] Optionally, after matching the target vehicle operating condition characteristic evaluation parameter with the multiple typical operating conditions to obtain the target typical operating condition, the method further includes: An economic evaluation is performed on the target typical operating condition to obtain an economic evaluation result of the target typical operating condition.

[0008] Optionally, matching the target vehicle operating condition characteristic evaluation parameter with the multiple typical operating conditions to obtain the target typical operating condition includes: Based on the mean absolute percentage error and the Pearson correlation coefficient, the typical operating condition is matched with the target vehicle operating condition characteristic evaluation parameter to obtain the target typical operating condition.

[0009] Optionally, performing an economic evaluation on the target typical operating condition to obtain an economic evaluation result of the target typical operating condition includes: The Simulink simulation model and the environmental chamber bench test are used to conduct an economic evaluation of the target typical operating conditions, and the economic evaluation results of the target typical operating conditions are obtained.

[0010] Optionally, the vehicle parameter values ​​also include vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure.

[0011] Optionally, the historical vehicle operating condition characteristic evaluation parameters include maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0012] In a second aspect, the present application provides a typical working condition construction device, comprising: A first acquisition module is used to acquire historical vehicle parameter values; the vehicle parameter values ​​include vehicle latitude and longitude data; A first processing module, used for processing the historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters; A division module, used to divide the historical vehicle operating condition characteristic evaluation parameters by using an agglomerative hierarchical clustering algorithm and the vehicle longitude and latitude data, so as to obtain the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios; A construction module is used to construct multiple typical operating conditions using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios.

[0013] Optionally, the device further comprises: A second acquisition module is used to acquire a target vehicle parameter value; A second processing module is used to process the target vehicle parameter value to obtain a target vehicle operating condition characteristic evaluation parameter; A matching module is used to match the target vehicle operating condition characteristic evaluation parameters with the multiple typical operating conditions to obtain a target typical operating condition; the target typical operating condition is a typical operating condition that is closest to the target vehicle operating condition.

[0014] Optionally, the device further comprises: The evaluation module is used to perform an economic evaluation on the target typical operating condition to obtain an economic evaluation result of the target typical operating condition.

[0015] Optionally, the matching module includes: A matching unit is used to match the typical operating condition with the target vehicle operating condition characteristic evaluation parameter based on the mean absolute percentage error and the Pearson correlation coefficient to obtain the target typical operating condition.

[0016] Optionally, the evaluation module includes: The evaluation unit is used to perform an economic evaluation on the target typical working condition by using a Simulink simulation model and an environmental chamber bench test to obtain an economic evaluation result of the target typical working condition.

[0017] Optionally, the vehicle parameter values ​​also include vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure.

[0018] Optionally, the historical vehicle operating condition characteristic evaluation parameters include maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0019] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the typical operating condition construction method described in any one of the implementation methods in the first aspect of the embodiment of the present application.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes a typical operating condition construction method as described in any one of the implementation methods in the first aspect of the embodiment of the present application.

[0021] The present application provides a method for constructing a typical operating condition. When executing the method, first obtain historical vehicle parameter values, wherein the vehicle parameter values ​​include vehicle longitude and latitude data, then process the historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters, and then use the cohesive layer clustering algorithm and vehicle longitude and latitude data to divide the historical vehicle operating condition characteristic evaluation parameters to obtain historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, and finally use the multi-level two-dimensional Markov chain Monte Carlo method and the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios to construct multiple typical operating conditions. In this way, by using the cohesive layer clustering algorithm and the vehicle longitude and latitude data to divide the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, and then using the multi-level two-dimensional Markov chain Monte Carlo method to construct typical operating conditions, the real driving mode and dynamic characteristics of fuel cell vehicles can be accurately captured, thereby improving the accuracy of the energy efficiency evaluation of fuel cell vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flowchart of a typical working condition construction method provided in an embodiment of the present application; Figure 2 A flowchart of another typical working condition construction method provided in an embodiment of the present application; Figure 3 A two-bit codebook logic diagram provided for an embodiment of the present application; Figure 4 A radar diagram of the speed characteristics of a fuel cell bus provided in an embodiment of the present application; Figure 5 11 speed feature correlation heat maps of 10 fuel cell buses provided in the embodiment of the present application; Figure 6 A radar chart showing the speed characteristics of the first type of buses after the 10 fuel cell buses are classified according to the embodiment of the present application; Figure 7 A radar chart showing the speed characteristics of the second type of buses after classification of 10 fuel cell buses provided in an embodiment of the present application; Figure 8 A schematic diagram of speed characteristics of the first category of buses after 10 fuel cell buses are classified according to an embodiment of the present application; Fig. 9A schematic diagram of speed characteristics of the second type of buses after classification of 10 fuel cell buses provided in an embodiment of the present application; Fig.10 The state transition probability matrix and partial enlarged diagram of the first category of buses after classification of 10 fuel cell buses provided in the embodiment of the present application; Fig.11 The state transition probability matrix and partial enlarged diagram of the second category of buses after classification of 10 fuel cell buses provided in the embodiment of the present application; Fig.12 The speed and fuel cell power spectrum of the first category of buses after classification of the 10 fuel cell buses provided in the embodiment of the present application; Fig.13 The speed and fuel cell power spectrum of the second type of buses after classification of the 10 fuel cell buses provided in the embodiment of the present application; Fig.14 The speed and fuel cell power spectrum constructed by self-learning for the heavy truck provided in the embodiment of the present application; Fig.15 A schematic diagram of the structure of a typical working condition construction device provided in an embodiment of the present application; Fig.16 A computer device is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The present application provides a typical working condition construction method, device and related products for use in the field of vehicle technology. The above is only an example and does not limit the application field of the method and device name provided in the present application.

[0025] The actual driving cycle and energy efficiency evaluation of fuel cell vehicles is an important part of improving their technical maturity and market promotion. In the existing technology, traditional driving cycle testing and simulation methods often fail to accurately reflect the complexity and variability of actual driving conditions, resulting in low accuracy in energy efficiency evaluation of fuel cell vehicles.

[0026] After research, the inventor proposed the technical solution of this application. First, the historical vehicle parameter values ​​are obtained, wherein the vehicle parameter values ​​include the vehicle longitude and latitude data. Then, the historical vehicle parameter values ​​are processed to obtain the historical vehicle operating condition characteristic evaluation parameters. Then, the historical vehicle operating condition characteristic evaluation parameters are divided using the cohesive layer clustering algorithm and the vehicle longitude and latitude data to obtain the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios. Finally, a multi-level two-dimensional Markov chain Monte Carlo method and the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios are used to construct multiple typical operating conditions. In this way, by using the cohesive layer clustering algorithm and the vehicle longitude and latitude data to divide the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, and then using the multi-level two-dimensional Markov chain Monte Carlo method to construct typical operating conditions, the real driving mode and dynamic characteristics of fuel cell vehicles can be accurately captured, thereby improving the accuracy of the energy efficiency evaluation of fuel cell vehicles.

[0027] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0028] See also Figure 1 , Figure 1 A flowchart of a typical working condition construction method provided in an embodiment of the present application includes: S101: Obtain historical vehicle parameter values.

[0029] Obtain historical vehicle parameter values ​​transmitted from the vehicle-mounted T-Box to the data cloud storage, where the vehicle parameter values ​​include but are not limited to: vehicle latitude and longitude data, vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure.

[0030] Specifically, before executing step S101, it is necessary to first use the Clickhouse column storage database to create a fuel cell vehicle system parameter database project, collect the T-Box transmission signal of the fuel cell vehicle application module, and design a database table according to the signal type for data cloud storage. The attributes of the database table cover vehicle number, vehicle latitude and longitude data, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature, hydrogen bottle pressure and other characteristic parameter values.

[0031] In some embodiments, since the amount of data of a complete fuel cell vehicle is huge, in order to optimize each query time, each time the vehicle parameter values ​​are obtained, only the required vehicle parameter values ​​within a certain time period of some vehicles may be obtained according to actual needs.

[0032] S102: Process historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters.

[0033] The vehicle parameter values ​​obtained in step S101 are processed and extracted using Python language to obtain historical vehicle operating condition characteristic evaluation parameters, wherein the historical vehicle operating condition characteristic evaluation parameters include: maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0034] S103: Using an agglomerative hierarchical clustering algorithm and vehicle longitude and latitude data, the historical vehicle operating condition characteristic evaluation parameters are divided to obtain historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios.

[0035] The agglomerative hierarchical clustering algorithm AGNES and vehicle longitude and latitude data are used to divide the vehicle operating characteristic evaluation parameters, and the historical vehicle operating characteristic evaluation parameters of different categories of vehicles in different scenarios are obtained. Among them, the agglomerative hierarchical clustering algorithm AGNES is used to group and cluster the samples in the data set according to similarity. First, each sample is regarded as a single cluster, and then the most similar clusters are iteratively merged until all samples belong to one cluster. The agglomerative hierarchical clustering algorithm AGNES is conducive to generating a complete clustering hierarchy without knowing the number of clusters in advance, and is suitable for vehicle category classification.

[0036] The Ward method is a special case of the agglomerative hierarchical clustering algorithm AGNES. The Ward method is used for hierarchical clustering, in which clusters are merged based on the minimum increment of the within-cluster squared error. The within-cluster squared error (WSS) refers to the sum of the squares of the distances from all points in the cluster to the centroid of the cluster. At each merge, the Ward method selects the minimum increment of the within-cluster squared error. The two smallest clusters are merged. The specific formula is as follows: ; ; ; ; in, and are different clusters, i.e., the multi-dimensional feature data of each vehicle; represents the merged cluster; represents the sampling points in the cluster; , and Respectively represent clusters , and The centroid of and Respectively represent clusters and Cluster The number of elements in ; Indicates sampling point With the centroid The square of the Euclidean distance between them.

[0037] S104: Construct multiple typical operating conditions using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios.

[0038] Based on the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, the operating condition is constructed for each category and each operating scenario through a multi-level two-dimensional Markov chain Monte Carlo model. The specific implementation process is as follows: (1) Status code: Encode the historical vehicle speed or acceleration sequence into a discrete state sequence, Status of the moment is a speed including the vehicle and acceleration The two-dimensional group is denoted as , where the speed of the vehicle and acceleration The combination of Figure 3 As shown, Figure 3 A two-bit codebook logic diagram provided in an embodiment of the present application. The acceleration of the vehicle The calculation method is as follows: ; in, The vehicle is The speed of The vehicle is The speed of time.

[0039] (2) Calculation of state transfer matrix: The Markov chain gives the relationship between the current state and the next state, that is, from the current state To the next state The probability of , the formula is as follows: ; The Markov chain transition probability can be calculated by the following formula: ; The formula of the state transition matrix TPM composed of state transition probabilities is as follows: ; in, It’s time; From the current state To the next state The transition probability of From the state Transfer to state The number of samples; is the total number of states encoded.

[0040] (3) Status transition: Uses a Markov Chain Monte Carlo (MCMC) sampling method based on Metropolis Hastings (MH) that aims to sample from multidimensional distributions. MCMC uses a Markov chain to generate a series of states that converge to a steady-state distribution, which is usually the target distribution to be sampled from, i.e., the distribution obtained from the state transition matrix TPM. The core idea is to start from an initial state and, according to certain rules, accept or reject state transitions to eventually reach a steady state. This process generates samples that conform to the target distribution. The Markov chain starts from the state Transition to the next state The acceptance probability formula is as follows, otherwise keep in state : ; in and is the target distribution, and is the proposed distribution, and the normal distribution is adopted here.

[0041] (4) Status decoding: After obtaining the state distribution results at each time point, By decoding the state, a continuous velocity spectrum and acceleration spectrum can be obtained, that is, a typical working condition is established.

[0042] In the embodiment provided in the present application, historical vehicle parameter values ​​are first obtained, wherein the vehicle parameter values ​​include vehicle longitude and latitude data, then the historical vehicle parameter values ​​are processed to obtain historical vehicle operating condition characteristic evaluation parameters, and then the historical vehicle operating condition characteristic evaluation parameters are divided using the cohesive layer clustering algorithm and the vehicle longitude and latitude data to obtain historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, and finally a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios are used to construct multiple typical operating conditions. In this way, by using the cohesive layer clustering algorithm and the vehicle longitude and latitude data to divide the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios, and then using the multi-level two-dimensional Markov chain Monte Carlo method to construct typical operating conditions, the real driving mode and dynamic characteristics of fuel cell vehicles can be accurately captured, thereby improving the accuracy of the energy efficiency evaluation of fuel cell vehicles.

[0043] In addition, after constructing the typical working conditions, it is necessary to evaluate the typical working conditions. The specific steps are as follows: Figure 2 As shown, Figure 2 A flowchart of another typical working condition construction method provided in an embodiment of the present application includes: The implementation of steps S201 to S204 is the same as that of steps S101 to S104, and will not be repeated here.

[0044] S205: Obtain target vehicle parameter values.

[0045] First, it is necessary to obtain the vehicle parameter values ​​of the target vehicle, which include but are not limited to vehicle latitude and longitude data, vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure.

[0046] S206: Process the target vehicle parameter values ​​to obtain target vehicle operating condition characteristic evaluation parameters.

[0047] The vehicle parameter values ​​of the actual vehicle obtained in step S205 are processed and extracted using Python language to obtain the vehicle operating condition characteristic evaluation parameters of the actual vehicle, wherein the vehicle operating condition characteristic evaluation parameters include: maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0048] S207: Match the target vehicle operating condition characteristic evaluation parameters with a plurality of typical operating conditions to obtain a target typical operating condition.

[0049] The mean absolute percentage error and the Pearson correlation coefficient are used to compare the typical operating condition with the vehicle operating condition characteristic evaluation parameters of the actual vehicle to obtain the target typical operating condition, which is the typical operating condition closest to the actual vehicle operating condition.

[0050] S208: Performing an economic evaluation on the target typical operating condition to obtain an economic evaluation result of the target typical operating condition.

[0051] The economic evaluation of the target typical operating conditions is carried out through Simulink simulation (HiL) verification and environmental chamber bench test verification. Simulink simulation (HiL) is used to simulate the system performance under real conditions and provide key data for economic evaluation. The upper-level computer with Simulink model manages the energy spectrum, including lithium-ion battery and PEMFC system operation, and the test cabinet integrated with the fuel cell system is equipped with a hydrogen flow meter to accurately measure the hydrogen consumption. The environmental chamber bench test creates a controlled environment for comprehensive evaluation of the performance of the fuel cell system. This area is equipped with a PEMFC benchmark test system and an axial fan for simulating the vehicle's heat dissipation capacity, ensuring that the test conditions are very similar to the actual application scenario. Similarly, hydrogen flow meters are also used in this area to accurately record hydrogen consumption and further verify the economic performance of the system.

[0052] The target typical operating condition is input into the Simulink simulation (HiL) model to obtain the power spectrum and simulated hydrogen consumption of the fuel cell, and then the obtained power spectrum is input into the environmental chamber bench test to obtain the hydrogen consumption of the bench test. It is determined whether the hydrogen consumption error is within the required range. If it is within the required range, the typical operating condition with economic evaluation results is obtained; if it is not within the required range, the target typical operating condition is reselected.

[0053] In some implementations, in order to ensure consistency and comparability of the proposed method when performing Simulink simulation (HiL) verification and environmental chamber bench test verification, vehicle parameters of Simulink simulation (HiL) verification and environmental chamber bench test are kept the same.

[0054] The above introduces the typical working condition construction method provided in the embodiment of the present application. The following is an exemplary description of the typical working condition construction method in combination with a specific application scenario.

[0055] (1) Taking 10 fuel cell 18t buses as an example: First, a fuel cell vehicle system parameter database project is created through the Clickhouse column storage database to collect vehicle parameter values ​​transmitted by the fuel cell bus onboard T-Box in real time, such as vehicle latitude and longitude data, vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature, and hydrogen bottle pressure. Then, the vehicle parameter values ​​are processed using the Python programming language to obtain the operating condition characteristic evaluation parameters, such as Figure 4 As shown, Figure 4 The fuel cell bus speed characteristic radar chart provided in the embodiment of the present application includes the operating characteristic evaluation parameters including: maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0056] Next, the AGNES algorithm is used to perform cluster analysis on the operating condition characteristic evaluation parameters, and the vehicle is divided into different operating scenarios and categories in combination with the vehicle's GPS signal. The AGNES algorithm classifies vehicles by continuously merging the most similar clusters until all samples belong to a certain cluster. Figure 5 As shown, Figure 5 The heat map of the correlation of 11 speed characteristics of 10 fuel cell buses provided in the embodiment of the present application. The correlation of the speed characteristics of the 10 vehicles is summarized into two categories of vehicles through the AGNES algorithm, namely the first category of vehicles summarized by the yellow line (vehicle 4, vehicle 6, vehicle 7) and the second category of vehicles summarized by the blue line (vehicle 1, vehicle 2, vehicle 3, vehicle 5, vehicle 8, vehicle 9 and vehicle 10). The speed is divided into 60 segments and the acceleration is divided into 10 segments, so the total number of the two-dimensional code book is 600, as shown in Figure 6 , Figure 7 As shown, Figure 6 This is a radar chart of the speed characteristics of the first type of buses after the 10 fuel cell buses are classified according to the embodiment of the present application. Figure 7 The radar diagram of the speed characteristics of the second type of buses after the classification of 10 fuel cell buses provided in the embodiment of the present application. Figure 8 , Fig. 9 As shown, Figure 8 A schematic diagram of speed characteristics of the first category of buses after 10 fuel cell buses are classified according to an embodiment of the present application, Fig. 9 The speed characteristic diagram of the second type of buses after the classification of 10 fuel cell buses provided in the embodiment of the present application clearly shows that Figure 8 The acceleration fluctuation range of the first type of bus in all speed ranges is greater than Fig. 9 The second type of buses has a range of acceleration fluctuations in all speed intervals, so the operating conditions will be constructed for these two types of vehicles separately.

[0057] Then, based on the results of agglomerative hierarchical clustering and partitioning, a multi-level two-dimensional Markov chain Monte Carlo method is used to construct typical operating conditions for each category and each operating scenario. This process includes four steps: state encoding, calculation of the state transfer matrix, state transition, and state decoding. The specific steps have been described in detail in the previous article and will not be repeated here. Through this method, typical operating conditions that are highly similar to real driving conditions can be constructed. Fig.10 , Fig.11 As shown, Fig.10 The state transition probability matrix and partial enlarged diagram of the first category of buses after classification of 10 fuel cell buses provided in the embodiment of the present application, Fig.11 The state transition probability matrix and partial enlarged diagram of the second category of buses after the 10 fuel cell buses are classified according to the embodiment of the present application. Fig.10 In state 26 (i.e., speed range 0.83 to 1.66 km / h, acceleration range -1.18 to 0.13 m / s 2 ) to state 7 (speed 0km / h, acceleration range -0.13 to 0.93m / s 2 ) has a probability of 0.8, and the transition from state 26 to state 17 (speed range 0 to 0.83 km / h, acceleration range -0.13 to 0.93 m / s 2 ) is 0.14. Fig.10 , Fig.11 The state transition probability matrix provided constructs 1000 typical operating conditions of the speed spectrum of 1 hour according to the set duration (3600 seconds).

[0058] Then, the Pearson correlation coefficient and MAPE methods were used to evaluate the 1000 typical operating conditions. By comparing the characteristic parameters with the actual vehicle driving conditions, the optimal typical operating conditions closest to the actual vehicle driving conditions were obtained. The optimal typical operating conditions of the two types of vehicles are as follows: Fig.12 , Fig.13 As shown, Fig.12 The speed and fuel cell power spectrum of the first category of buses after the 10 fuel cell buses are classified according to the embodiment of the present application, Fig.13 The speed and fuel cell power spectrum of the second type of buses after the 10 fuel cell buses are classified according to the embodiment of the present application, Fig.12 The blue line represents the typical speed spectrum of the first type of bus. Fig.13 The blue line represents the typical speed spectrum condition of the second type of bus. Its eleven speed and acceleration characteristic indicators are close to the actual situation and conform to the speed time series variation law of the actual situation.

[0059] Finally, the optimal typical operating condition is input into the Simulink simulation (HiL) model to simulate the power spectrum and hydrogen consumption of the fuel cell, and the simulation results are compared with the hydrogen consumption obtained from the environmental chamber bench test to verify the economy of the constructed typical operating condition. If the hydrogen consumption error is within the required range, the verification is passed, otherwise the typical operating condition is reconstructed, such as Fig.12 , Fig.13 As shown, Fig.12 The speed and fuel cell power spectrum of the first category of buses after the 10 fuel cell buses are classified according to the embodiment of the present application, Fig.13 The speed and fuel cell power spectrum of the second type of buses after the 10 fuel cell buses are classified according to the embodiment of the present application, Fig.12 , Fig.13 The velocity spectrum of the blue line in the middle is used as input to obtain the corresponding Fig.12 , Fig.13 The fuel cell power spectrum in Figure 1, which is the green line.

[0060] (2) Taking a fuel cell 49t tractor as an example: First, a fuel cell vehicle system parameter database project is created through the Clickhouse column storage database to collect vehicle parameter values ​​transmitted by the fuel cell bus onboard T-Box in real time, such as vehicle latitude and longitude data, vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure, etc. Then, the vehicle parameter values ​​are processed using the Python programming language to obtain the operating condition characteristic evaluation parameters, which include: maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0061] Next, the AGNES algorithm is used to perform cluster analysis on the operating characteristic evaluation parameters, and the vehicle is divided into different operating scenarios and categories in combination with the vehicle's GPS signal. The AGNES algorithm classifies vehicles by continuously merging the most similar clusters until all samples belong to a certain cluster. This embodiment is for the historical data of a fully loaded vehicle, so there is no need to perform the step of clustering multiple vehicles.

[0062] Based on the results of agglomerative hierarchical clustering and partitioning, a multi-level two-dimensional Markov chain Monte Carlo method is used to construct typical operating conditions for each category and each operating scenario. This process includes four steps: state encoding, calculation of state transfer matrix, state transition, and state decoding. The specific steps have been described in detail in the previous article and will not be repeated here. Typical operating conditions that are highly similar to real driving conditions can be constructed. According to the set duration (3600 seconds), 1000 typical operating conditions of 1-hour speed spectra are constructed.

[0063] Then, the Pearson correlation coefficient and MAPE methods were used to evaluate the 1000 typical operating conditions generated, and the optimal typical operating conditions that were closest to the actual vehicle driving conditions were obtained by comparing the characteristic parameters with the actual vehicle driving conditions.

[0064] Finally, the optimal typical operating condition is input into the Simulink simulation (HiL) model to simulate the power spectrum and hydrogen consumption of the fuel cell, and the simulation results are compared with the hydrogen consumption obtained from the environmental chamber bench test to verify the economy of the constructed typical operating condition. If the hydrogen consumption error is within the required range, the verification is passed, otherwise it returns to reconstruct the typical operating condition. Fig.14 The speed and fuel cell power spectrum constructed by the self-learning of the heavy truck provided in the embodiment of the present application, Fig.14 The velocity spectrum of the blue line in the middle is used as input to obtain the corresponding Fig.14 The fuel cell power spectrum in Figure 1, which is the red line.

[0065] The above are some specific implementations of the typical working condition construction method provided in the embodiment of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiment of the present application will be introduced from the perspective of functional modularization.

[0066] See also Fig.15 , Fig.15 The schematic diagram of the structure of a typical working condition construction device provided in an embodiment of the present application is as follows. The typical working condition construction device 1100 includes: The first acquisition module 1110 is used to acquire historical vehicle parameter values; the vehicle parameter values ​​include vehicle latitude and longitude data; A first processing module 1120 is used to process the historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters; A division module 1130 is used to divide the historical vehicle operating condition characteristic evaluation parameters by using an agglomerative hierarchical clustering algorithm and the vehicle longitude and latitude data to obtain historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios; The construction module 1140 is used to construct a plurality of typical operating conditions by using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of the different categories of vehicles in different scenarios.

[0067] Optionally, the device 1100 further includes: A second acquisition module is used to acquire a target vehicle parameter value; A second processing module is used to process the target vehicle parameter value to obtain a target vehicle operating condition characteristic evaluation parameter; A matching module is used to match the target vehicle operating condition characteristic evaluation parameters with the multiple typical operating conditions to obtain a target typical operating condition; the target typical operating condition is a typical operating condition that is closest to the target vehicle operating condition.

[0068] Optionally, the device 1100 further includes: The evaluation module is used to perform an economic evaluation on the target typical operating condition to obtain an economic evaluation result of the target typical operating condition.

[0069] Optionally, the matching module includes: A matching unit is used to match the typical operating condition with the target vehicle operating condition characteristic evaluation parameter based on the mean absolute percentage error and the Pearson correlation coefficient to obtain the target typical operating condition.

[0070] Optionally, the evaluation module includes: The evaluation unit is used to perform an economic evaluation on the target typical working condition by using a Simulink simulation model and an environmental chamber bench test to obtain an economic evaluation result of the target typical working condition.

[0071] Optionally, the vehicle parameter values ​​also include vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure.

[0072] Optionally, the historical vehicle operating condition characteristic evaluation parameters include maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

[0073] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.

[0074] like Fig.16As shown, the computer device 01 is in the form of a general computing device. The components of the computer device 01 may include but are not limited to: one or more processors or processor units 03, a system memory 08, and a bus 04 connecting different system components (including the system memory 08 and the processor unit 03).

[0075] Bus 04 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0076] The computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 01, including volatile and non-volatile media, removable and non-removable media.

[0077] The system memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. The computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 11 may be used to read and write non-removable, non-volatile magnetic media ( Fig.16 not shown, usually called a "hard drive"). Although Fig.16 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 04 via one or more data medium interfaces. The system memory 08 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0078] A program / utility 12 having a set (at least one) of program modules 13 may be stored, for example, in system memory 08, such program modules 13 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 13 generally perform the functions and / or methods of the embodiments described herein.

[0079] The computer device 01 may also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), one or more devices that enable a user to interact with the computer device 01, and / or any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via input / output (I / O) interface 06. Furthermore, the computer device 01 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via network adapter 05. Fig.16 As shown, the network adapter 05 communicates with other modules of the computer device 01 via the bus 04. It should be understood that although Fig.16 Not shown, other hardware and / or software modules may be used in conjunction with computer device 01, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0080] The processor unit 03 executes various functional applications and data processing by running the programs stored in the system memory 08, for example, implementing a typical working condition construction method provided in an embodiment of the present application.

[0081] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0082] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0083] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0084] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A typical working condition construction method, characterized in that: include: Acquire historical vehicle parameter values; the vehicle parameter values ​​include vehicle latitude and longitude data; Processing the historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters; Using an agglomerative hierarchical clustering algorithm and the vehicle longitude and latitude data, the historical vehicle operating condition characteristic evaluation parameters are divided to obtain historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios; Using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of the different categories of vehicles in different scenarios, multiple typical operating conditions are constructed; Get the target vehicle parameter value; Processing the target vehicle parameter value to obtain a target vehicle operating condition characteristic evaluation parameter; Matching the target vehicle operating condition characteristic evaluation parameter with the multiple typical operating conditions to obtain a target typical operating condition; the target typical operating condition is a typical operating condition that is closest to the target vehicle operating condition; The step of matching the target vehicle operating condition characteristic evaluation parameter with the multiple typical operating conditions to obtain the target typical operating condition includes: Based on the mean absolute percentage error and the Pearson correlation coefficient, the typical operating condition is matched with the target vehicle operating condition characteristic evaluation parameter to obtain the target typical operating condition.

2. The method according to claim 1, characterized in that: After matching the target vehicle operating condition characteristic evaluation parameter with the multiple typical operating conditions to obtain the target typical operating condition, the method further includes: An economic evaluation is performed on the target typical operating condition to obtain an economic evaluation result of the target typical operating condition.

3. The method according to claim 2, characterized in that The economic evaluation of the target typical operating condition is performed to obtain the economic evaluation result of the target typical operating condition, including: The Simulink simulation model and the environmental chamber bench test are used to conduct an economic evaluation of the target typical operating conditions, and the economic evaluation results of the target typical operating conditions are obtained.

4. The method according to any one of claims 1 to 3, characterized in that: The vehicle parameter values ​​also include vehicle number, timestamp, vehicle speed, vehicle required power, fuel cell power, battery status, hydrogen bottle temperature and hydrogen bottle pressure.

5. The method according to claim 4, characterized in that The historical vehicle operating condition characteristic evaluation parameters include maximum speed, maximum acceleration, maximum deceleration, average operating speed, average acceleration, average deceleration, acceleration time proportion, deceleration time proportion, uniform speed time proportion and idling time proportion.

6. A typical working condition construction device, characterized in that: include: A first acquisition module is used to acquire historical vehicle parameter values; the vehicle parameter values ​​include vehicle latitude and longitude data; A first processing module, used for processing the historical vehicle parameter values ​​to obtain historical vehicle operating condition characteristic evaluation parameters; A division module, used to divide the historical vehicle operating condition characteristic evaluation parameters by using an agglomerative hierarchical clustering algorithm and the vehicle longitude and latitude data, so as to obtain the historical vehicle operating condition characteristic evaluation parameters of different categories of vehicles in different scenarios; A construction module for constructing a plurality of typical operating conditions using a multi-level two-dimensional Markov chain Monte Carlo method and historical vehicle operating condition characteristic evaluation parameters of the different categories of vehicles in different scenarios; A second acquisition module is used to acquire a target vehicle parameter value; A second processing module is used to process the target vehicle parameter value to obtain a target vehicle operating condition characteristic evaluation parameter; A matching module, used for matching the target vehicle operating condition characteristic evaluation parameter with the multiple typical operating conditions to obtain a target typical operating condition; The target typical operating condition is the typical operating condition closest to the target vehicle operating condition; The matching module comprises: A matching unit is used to match the typical operating condition with the target vehicle operating condition characteristic evaluation parameter based on the mean absolute percentage error and the Pearson correlation coefficient to obtain the target typical operating condition.

7. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the typical operating condition construction method as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the typical operating condition construction method as described in any one of claims 1 to 5.

Images