Vehicle energy flow analysis method and apparatus, device, and storage medium

Abstract

A vehicle energy flow analysis method and apparatus, a device, and a storage medium. The method comprises: a processing device acquiring data to be processed, wherein the data to be processed comprises a plurality of data files, each data file is collected from a sensor, and because the sensors have different sampling frequencies, the number of data contained in each data file is also different; on the basis of a data file obtained by the sensor having the highest sampling frequency, determining data corresponding to each moment in other data files; and then performing energy flow analysis on the basis of data in all the data files corresponding to the same moment. The method can implement effective analysis of collected data, thereby reducing deviations from an actual test result.

Description

A method, apparatus, device, and storage medium for analyzing vehicle energy flow. Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, device and storage medium for analyzing vehicle energy flow. Background Technology

[0002] In the field of vehicle analysis, especially in the road analysis technology of new energy vehicles, the road analysis technology of new energy vehicles is an important means to evaluate the performance and safety of new energy vehicles in real road environments. The road analysis technology of new energy vehicles includes range testing, charging testing, braking performance testing and noise and vibration testing.

[0003] Currently, different sensors are used for testing different parts of the vehicle, and these sensors have different sampling frequencies. This results in data collected by different sensors not being at the same time point, making effective analysis impossible. For example, a speed sensor collects one data point per second per minute, totaling 60 data points per minute (60 time points). A temperature sensor, on the other hand, collects one data point every two seconds per minute, totaling 30 data points per minute (30 time points). However, the speed sensor has no data for the temperature sensor for 30 of these time points. This discrepancy in the timing of data collection during the analysis of new energy vehicles leads to errors between the final analysis results and the actual results. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for analyzing vehicle energy flow, which can effectively analyze the collected data during the road analysis of new energy vehicles and reduce the error between the data and the actual test results.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, this application provides a method for analyzing the energy flow of new energy vehicles, the method comprising:

[0007] Acquire data to be processed, which includes at least a first data file and a second data file. The first data file includes multiple first data items and a time corresponding to each first data item. The second data file includes multiple second data items and a time corresponding to each second data item. The number of first data items is greater than the number of second data items.

[0008] Determine the T of the first data file n At time T, determine T in the second data file. n T of the moment n-1 Time and T n T of the momentn+1 At time T in the first data file n There is always corresponding first data, and T in the second data file. n There is no corresponding second data at any given time.

[0009] Determine T from the second data file n-1 The second data corresponding to time T and T n+1 The second data corresponding to the given time;

[0010] According to the T n Time, the T n-1 Time, the T n-1 The second data corresponding to time T n+1 Time and the T n+1 The second data corresponding to the time point determines the T of the second data file. n The second data corresponding to the given time;

[0011] Energy flow analysis was performed using the first and second data points at the same time.

[0012] In some possible implementations, the statement based on the T n Time, the T n-1 Time, the T n-1 The second data corresponding to time T n+1 Time and the T n+1 The second data corresponding to the time point determines the T of the second data file. n The second data corresponding to the time includes:

[0013] The second data file in T is calculated using the following formula. n Second data point at time: D n =C×D n-1 +B×D n+1

[0014] Among them, T n T n-1 And T n+1 T is a positive integer. n-1 Time T n The moment before time, T n+1 Time T n At the next time step, C has the first weight, B has the second weight, and D... n For T n The second data point corresponding to time point D n-1 For T n-1 The second data point corresponding to time point D n+1 For T n+1The second data corresponding to the time.

[0015] In some possible implementations, the determination of the first data file T n Moments, including:

[0016] In the second data file, iterate through the time corresponding to the first data in the first data file, and determine the time corresponding to the first data that has not been iterated through as T. n time.

[0017] In some possible implementations, obtaining the data to be processed includes:

[0018] Acquire a first data file collected by a first sensor and a second data file collected by a second sensor, wherein the sampling frequency of the first sensor is higher than that of the second sensor.

[0019] In some possible implementations, the data to be processed includes multiple data files, and the second data file is determined in T... n After the second data corresponding to the time point, the method further includes:

[0020] Based on data from multiple data files at the same time, generate multiple sets of sample indicator data and multiple sets of sample energy consumption data;

[0021] Determine the correlation between sample indicator data and sample energy consumption data;

[0022] Remove sample indicator data and sample energy consumption data with correlation below the correlation threshold from multiple sets of sample indicator data to obtain the remaining sample indicator data and remaining sample energy consumption data.

[0023] The vehicle energy consumption prediction model is trained using the remaining sample index data and the remaining sample energy consumption data.

[0024] In some possible implementations, determining the correlation between sample indicator data and sample energy consumption data includes:

[0025] Among them, V mic (x i ,y i X represents the correlation between the index data of the i-th sample and the energy consumption data of the i-th sample. i Let Y be the set of data for the i-th indicator. i Let i be the set of energy consumption data for the i-th vehicle. For X i The j-th sample indicator variable in For Y i The energy consumption variable of the j-th sample in the data. for The joint probability density, for marginal probability density, for The marginal probability density, G = (a, b), where the product of a and b equals the number of variables in Xi or Yi, a is the horizontal axis coordinate variable of grid G, b is the vertical axis coordinate variable of grid G, and a and b are both positive integers, f(q) = q 0.6 q is X i Or Y i The number of variables in q, where j is a positive integer, and j is less than or equal to q.

[0026] In some possible implementations, the method further includes:

[0027] Obtain the data of the indicator to be predicted;

[0028] The vehicle energy consumption prediction model is obtained by inputting the data of the indicator to be predicted into the vehicle energy consumption prediction model.

[0029] Secondly, this application provides a vehicle energy flow analysis device, the device comprising:

[0030] The acquisition module is used to acquire data to be processed, which includes at least a first data file and a second data file. The first data file includes multiple first data and a time corresponding to each first data. The second data file includes multiple second data and a time corresponding to each second data. The number of first data is greater than the number of second data.

[0031] The determination module is used to determine the T of the first data file. n At time T, determine T in the second data file. n T of the moment n-1 Time and T n T of the moment n+1 At time T in the first data file n There is always corresponding first data, and T in the second data file. n There is no corresponding second data at any given time; determine T from the second data file. n-1 The second data corresponding to time T and T n+1 The second data corresponding to the given time;

[0032] Calculation module, used to calculate based on T n Time, the T n-1 Time, the T n-1 The second data corresponding to time T n+1 Time and the T n+1The second data corresponding to the time point determines the T of the second data file. n The second data corresponding to the time; the analysis module, used to perform energy flow analysis based on the first and second data at the same time.

[0033] Thirdly, this application provides a computing device, including a memory and a processor;

[0034] In this application, one or more computer programs are stored in the memory, the computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects. In a fourth aspect, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0035] As can be seen from the above technical solution, this application has at least the following beneficial effects:

[0036] In this application, the processing device acquires data to be processed, which includes multiple data files. Each data file is collected from sensors with different sampling frequencies, and each data file contains a different number of data points. Based on the data file obtained by the sensor with the highest sampling frequency, the data corresponding to each moment in the other data files is determined. Then, energy flow analysis is performed based on the data from all data files corresponding to the same moment. Existing technologies directly perform energy flow analysis on the data acquired from the sensors. Because the sampling frequencies of the sensors differ, and the number of data points collected by each sensor varies, there will be a certain error between the energy flow analysis and the actual test results. Therefore, in this application, the calculation of data in other data files is determined based on the moment corresponding to the data in the data file obtained by the sensor with the highest sampling frequency, and then energy flow analysis is performed based on the data from all data files corresponding to the same moment. Thus, the solution in this application effectively analyzes the acquired data and reduces the error compared to the actual test results.

[0037] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0038] Figure 1 is a flowchart of a vehicle energy flow analysis method provided in an embodiment of this application;

[0039] Figure 2 is a schematic diagram of a vehicle data testing method provided in an embodiment of this application;

[0040] Figure 3 is a schematic diagram of a vehicle energy consumption prediction model provided in an embodiment of this application;

[0041] Figure 4 is a flowchart of a vehicle data management system provided in an embodiment of this application;

[0042] Figure 5 is a schematic diagram of a vehicle energy flow analysis device provided in an embodiment of this application;

[0043] Figure 6 is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0044] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0045] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0046] Currently, existing technology involves directly performing energy flow analysis on data collected from sensors. However, due to the different sampling frequencies of the sensors, the number of data points collected by each sensor also varies, resulting in some errors between the energy flow analysis and the actual test results.

[0047] In view of this, this application provides a method for analyzing vehicle energy flow. In this method, a processing device acquires data to be processed, which includes multiple data files. Each data file is collected from sensors, and the sensors have different sampling frequencies. The number of data points in each data file also varies. Based on the data file obtained by the sensor with the highest sampling frequency, the data corresponding to each moment in the other data files is determined. Then, energy flow analysis is performed based on the data from all data files corresponding to the same moment. However, existing technologies directly perform energy flow analysis on the data acquired from sensors. Because the sampling frequencies of the sensors differ, and the number of data points collected by each sensor also varies, there will be a certain error between the energy flow analysis and the actual test results. Therefore, in this application, the calculation of data in other data files is determined based on the moment corresponding to the data in the data file obtained by the sensor with the highest sampling frequency. Then, energy flow analysis is performed based on the data from all data files corresponding to the same moment. Thus, the solution of this application effectively analyzes the acquired data and reduces the error compared to the actual test results.

[0048] To make the technical solution of this application clearer and easier to understand, a method for analyzing vehicle energy flow provided in an embodiment of this application is described. As shown in Figure 1, this figure is a flowchart of a method for analyzing vehicle energy flow provided in an embodiment of this application. This method can be executed by a processing device and includes:

[0049] S101, The processing device acquires the data to be processed.

[0050] Processing equipment refers to hardware or software systems used to perform specific tasks or process data. In scenarios involving vehicle energy flow analysis, processing equipment may refer to a computer, server, or specific software platform specifically designed for calculating, simulating, or analyzing vehicle energy flow.

[0051] Before the processing device acquires the data to be processed in this application, high-voltage architecture research and sensor placement are required. First, the high-voltage system architecture and main low-voltage electrical components of the vehicle are determined, thereby determining the sensor placement scheme, as shown in Figure 2. This figure is a schematic diagram of a vehicle data testing method provided in an embodiment of this application. The vehicle architecture in the figure includes a transmission system architecture 201, a high-voltage component architecture 202, a low-voltage component architecture 203, and a CAN communication architecture 204. The sensor placement includes the arrangement of current sensors 211, voltage sensors 212, temperature sensors 213, pressure sensors 214, flow sensors 215, torque sensors 216, and a CAN communication interface 217. The purpose of placing current and voltage sensors is to calculate the power consumption. However, some signals are difficult to obtain through sensor placement, so signal analysis methods are needed to obtain information such as battery SOC, minimum battery temperature, maximum battery temperature, individual battery voltage, motor torque, motor speed, and compressor speed.

[0052] Specifically, the voltage sensor is deployed at the interfaces of both high-voltage and low-voltage electrical components. Since high-voltage power lines must not be damaged, as this would pose a danger, a customized test harness is used based on the interface model of the high-voltage components. This test harness, which includes a voltage sensor and a signal output harness, can be connected in series with the high-voltage power line. After installing the test harness, the signal output line is connected to the data acquisition module.

[0053] Current sensors are typically deployed in locations encompassing both high-voltage and low-voltage components. High-voltage components include the power battery, front drive module, rear drive module, high-voltage PTC, air conditioning compressor, and DC-DC input terminals. Low-voltage components include the DC-DC output terminals, cooling fans, motor water pumps, battery water pumps, air conditioning water pumps, blowers, and 12V batteries. Because different components have different rated power, when selecting the current sensor's range, it should be ensured that the sensor's range does not exceed 1.5 times the maximum current of either the high-voltage or low-voltage component.

[0054] Temperature sensors are primarily deployed at the inlet and outlet water ports of the battery, motor, radiator, and heat exchanger—major heat-generating and heat-dissipating components—to assist in analyzing the correlation between passenger compartment energy consumption, battery energy consumption, and temperature. Flow sensors are mainly located in the motor cooling circuit water pipes, battery cooling circuit water pipes, air conditioning circuit water pipes, and radiator water pipes. Combined with temperature sensors, they are used to analyze the heat dissipation and heat generation of different power components.

[0055] The CAN communication interface acquires CAN signals through the twisted wires on the connectors of key controllers such as the battery management system and battery controller. It generates data that changes with the characteristics of specific operating conditions. Then, the CAN communication interface calibrates the offset and ratio values ​​with sensors, external devices and other instruments. For example, when analyzing the battery SOC, it performs DC fast charging, observes the trend of CAN data changes, determines the signal ID and bytes, and then calibrates the CAN data based on the instrument values ​​and charging pile values.

[0056] The test investigated the actual road energy consumption of vehicles under various multi-factor matrices, including different temperatures (221), weather conditions (222), time periods (223), and routes (224). Typical temperatures included below -10℃, -5 to -10℃, 0 to -5℃, 0 to 10℃, 10 to 25℃, 25 to 35℃, and above 35℃. Weather factors included rain, snow, fog, haze, frost, and clear skies. Wind speeds included levels 0-2, 2-4, and above level 4. Time periods included morning rush hour (7:00-9:00), evening rush hour (17:00-19:30), off-peak hour (10:00-14:00), and nighttime (22:00-2:00). Routes included congested urban routes, suburban expressways, and mixed routes. The same test conditions were required for at least two consecutive days to avoid random errors. During the test, developed data acquisition equipment was used to simultaneously collect data from multiple vehicles. Specifically, the road energy consumption test adopted the test matrix shown in Table 1.

[0057] Table 1:

[0058] The test index calculations include vehicle energy consumption 231, high-voltage component energy consumption 232, low-voltage component energy consumption 233, and motor efficiency 234. S102, the processing equipment determines the T of the first data file. n At time T, determine T in the second data file. n T of the moment n-1 Time and T n T of the moment n+1 time.

[0059] The data to be processed includes at least a first data file and a second data file, but is not limited to two data files. The following calculations and analyses are performed using data collected from voltage and current sensors.

[0060] Acquire a first data file collected by a first sensor and a second data file collected by a second sensor, wherein the sampling frequency of the first sensor is higher than that of the second sensor.

[0061] For example, the first sensor is set to be a voltage sensor, the second sensor is a current sensor, the first data file is the voltage data and the corresponding time of the voltage data collected from the voltage sensor, and the second data file is the current data and the corresponding time of the current data collected from the current sensor.

[0062] In some embodiments, T can be determined in the following ways. n Time: In the time corresponding to the second data in the second data file, iterate through the time corresponding to the first data in the first data file, and determine the time corresponding to the first data that has not been iterated through as T. n time.

[0063] Table 2 below illustrates T. n Positional relationship at different times:

[0064] Table 2:

[0065] The current data in the current data file corresponds to the timestamps 1, 4, and 7; the voltage data in the voltage data file corresponds to the timestamps 1, 2, 3, 4, 5, 6, and 7. The current and voltage data files are compared based on time, and the timetamp corresponding to the current data in the current data file that does not contain current data is defined as T. n As can be seen in the table, the voltage data file contains values ​​at every moment, while the current data file does not contain values ​​at the 2nd, 3rd, 5th, and 6th seconds. Therefore, the 2nd, 3rd, 5th, and 6th seconds are determined to be T. n time.

[0066] According to T n T is determined in the current data file at all times. n Determine T by considering the time before and after the given time. n The time preceding time is T. n-1 At time, determine T n The time after time T is n+1 In the table, if we define the 2nd second as T... n The time is T, where the first second is T. n-1 The time, the 4th second is T n+1 time.

[0067] S103, The processing device determines T from the second data file. n-1 The second data corresponding to time T and T n+1 The second data corresponding to the time.

[0068] T is determined based on the second data collected from the second sensor and the time corresponding to the second data. n-1The second data corresponding to time T and T n+1 The second data corresponding to the time.

[0069] For example, as can be seen in the table, T n-1 The second data point corresponding to time T is the current data, and its value is 0.1A. n+1 The second data corresponding to the time is the current data and the value is 0.4A.

[0070] S104, Processing equipment according to T n Time, T n-1 Time, T n-1 The second data corresponding to time T n+1 Time and T n+1 The second data corresponding to the time point determines the T of the second data file. n The second data corresponding to the time.

[0071] The second data file in T is obtained by calculating using the following formula. n Second data point at time: D n =C×D n-1 +B×D n+1

[0072] Among them, T n T n-1 And T n+1 T is a positive integer. n-1 Time T n The moment before time, T n+1 Time T n At the next time step, C has the first weight, B has the second weight, and D... n For T n The second data point corresponding to time point D n-1 For T n-1 The second data point corresponding to time point D n+1 For T n+1 The second data corresponding to the time.

[0073] For example, T is calculated using the current data determined in S102 and S103 and the corresponding time of the current data through the above formula. n The second data D corresponding to time point n This refers to the missing values ​​in the current data in the table, as shown in Table 3 below:

[0074] Table 3:

[0075] S105. The processing equipment performs energy flow analysis based on the first and second data at the same time.

[0076] Energy flow analysis includes the power consumption of high-voltage and low-voltage components in new energy vehicles, the driving efficiency and braking efficiency of motors, battery internal resistance analysis, and the external heat generation and cooling capacity of batteries.

[0077] The following is a calculation of the electricity consumption of high-voltage and low-voltage components in new energy vehicles: Q hi =∫U h I hi dt Q li =∫U l I li dt

[0078] Among them, Q hi For the electricity consumption of high-voltage components in new energy vehicles, U h For the voltage of high-voltage components in new energy vehicles, I hi Q represents the current in the high-voltage components of new energy vehicles. li For the power consumption of low-voltage components in new energy vehicles, U l For the voltage of low-voltage components in new energy vehicles, I li For low-voltage components in new energy vehicles, t represents the test time.

[0079] For example, based on the table summarized in S104, energy flow analysis is performed on the voltage and current data at the same moment. At the 2nd second, the voltage data is 2V and the current data is 0.2A. Substituting these values ​​into the formula for calculating the power consumption yields Q. h2 =∫U h I h2 dt=∫2×0.2dt=0.8

[0080] The motor efficiency is calculated using the motor speed and torque on the CAN bus, along with the motor current and bus voltage collected by sensors. The following formula is used to calculate the motor's drive efficiency and braking efficiency:

[0081] Where η1 is the motor drive efficiency, η2 is the motor braking efficiency, T is the motor torque, n is the motor speed, U is the motor bus voltage, and I is the motor current. When I is negative, it is the braking current used to calculate the braking efficiency; when I is positive, it is the drive current used to calculate the drive efficiency.

[0082] Battery internal resistance analysis is based on the heat generated by the battery itself. Since driving involves both driving and braking, the battery discharges during driving and charges during braking. Because the charging and discharging internal resistances of the battery differ, the data is first divided into charging and discharging data. Then, because battery internal resistance is highly correlated with battery temperature, the test data is categorized according to battery temperature, using a certain temperature interval as the segmentation threshold, such as 5°C intervals. Then, based on the battery's current and voltage distribution, the internal resistance is fitted using the following formula; the slope of the fitted curve is the battery internal resistance. The internal resistance fitted to the charging data is the charging internal resistance, and the internal resistance fitted to the discharging data is the discharging internal resistance. bat =U1-RI bat

[0083] Among them, U bat I is the battery output voltage. bat R is the battery output current, and U1 is the coefficient to be fitted. R is the fitted battery internal resistance, and U1 is the fitted open-circuit voltage.

[0084] Based on the fitted battery internal resistance, a table of battery internal resistance varying with temperature can be obtained. Then, linear interpolation is performed to finally obtain a battery charging internal resistance map and a battery discharging internal resistance map for the entire temperature range.

[0085] According to formula Q b =I 2 bat R can be used to calculate the power consumption based on the battery's internal resistance. Where Q... b I represents the power consumption due to the battery's internal resistance. bat R is the battery output current, and R is the fitted battery internal resistance.

[0086] Based on the battery's inlet and outlet water temperatures, and the flow rate of the battery's thermal management circuit, the battery's heating and cooling capacities are calculated using the following formulas:

[0087] Among them, Q bo Here, c represents the external heating and cooling capacity of the battery, m represents the specific heat capacity of the coolant, and t represents the flow rate of the battery thermal management circuit. out_k Let t be the outlet temperature at second k. in_k Let t be the inlet temperature at the k-th second, and t be the test time.

[0088] The external heating and cooling efficiency of a battery can be calculated based on its external heat generation and cooling capacity, or its external heating or heat dissipation.

[0089] Where η3 is the battery's heating and cooling efficiency, and Q biThis refers to the heating or cooling power consumption of the external heat source, where the heating power consumption of the external heat source is the power consumption of the PTC, and the cooling power consumption of the external heat source is the power consumption of the compressor.

[0090] For example, the summarized vehicle energy flow indicators are shown in Table 4 below:

[0091] Table 4:

[0092] The correlation between the energy flow data and vehicle energy consumption data obtained by the above method is determined. The energy flow data consists of multiple sets of sample index data, and the vehicle energy consumption data consists of multiple sets of sample energy consumption data.

[0093] The correlation between sample indicator data and sample energy consumption data is determined using the following formula:

[0094] Among them, V mic (x i ,y i X represents the correlation between the index data of the i-th sample and the energy consumption data of the i-th sample. i Let Y be the set of data for the i-th indicator. i Let i be the set of energy consumption data for the i-th vehicle. For X i The j-th sample indicator variable in For Y i The energy consumption variable of the j-th sample in the data. for The joint probability density, for marginal probability density, for The marginal probability density, G = (a, b), where the product of a and b equals the number of variables in Xi or Yi, a is the horizontal axis coordinate variable of grid G, b is the vertical axis coordinate variable of grid G, and a and b are both positive integers, f(q) = q 0.6 q is X i Or Y i The number of variables in q, where j is a positive integer, and j is less than or equal to q.

[0095] Sample indicator data and sample energy consumption data with correlation below the correlation threshold are removed from multiple sets of sample indicator data to obtain the remaining sample indicator data and remaining sample energy consumption data.

[0096] For example, if the correlation threshold is set to 0.7, the correlation between the first sample indicator data and the first sample energy consumption data is 0.8, and the correlation between the second sample indicator data and the second sample energy consumption data is 0.6, the first sample indicator data and the first sample energy consumption data can be kept according to the magnitude of the correlation threshold, while the second sample indicator data and the second sample energy consumption data can be removed.

[0097] A vehicle energy consumption prediction model is trained using residual sample index data and residual sample energy consumption data. As shown in Figure 3, this figure is a schematic diagram of a vehicle energy consumption prediction model provided in an embodiment of this application. The model is divided into 7 layers. The first layer is the input layer, with K1 key energy flow indicators as input and K1 nodes. The second layer represents the fuzzy subspace, divided into 7 fuzzy subsets: positive large, positive medium, positive small, zero, negative small, negative medium, and negative large. Each node represents the membership function u of the fuzzy set. rs (where r is an integer, and u) rs For ≤K1, s=1,2,3,4,5,6,7), the membership function adopts the bell-shaped function, and the formula is as follows:

[0098] Among them, c rs δ is the center of membership. rs The width of the membership degree is 7×K1, and the number of nodes in this layer is 7×K1. The third layer is the inference layer, where each node outputs the applicability of each rule, and the number of nodes in this layer is... The fourth layer is a normalized calculation, with 1,000 nodes. The fifth layer is the output layer, with 1 node.

[0099] Once the training run is set to 100 times, a vehicle energy consumption prediction model can be obtained.

[0100] Based on the above description, this application provides a method for analyzing vehicle energy flow. In this method, a processing device acquires data to be processed, which includes multiple data files. Each data file is collected from sensors, and the sampling frequencies of these sensors differ, resulting in a different number of data points in each data file. Based on the data file obtained by the sensor with the highest sampling frequency, the data corresponding to each moment in the other data files is determined. Then, energy flow analysis is performed based on the data from all data files corresponding to the same moment. However, existing technologies directly perform energy flow analysis on the data acquired from sensors. Due to the different sampling frequencies of the sensors and the varying number of data points collected by each sensor, there will be a certain error between the energy flow analysis and the actual test results. Therefore, in this application, the calculation of data in other data files is determined based on the moment corresponding to the data in the data file obtained by the sensor with the highest sampling frequency, and then energy flow analysis is performed based on the data from all data files corresponding to the same moment. Thus, the solution of this application can effectively analyze the acquired data and reduce the error compared to the actual test results.

[0101] For example, this application also proposes a portable, low-cost, vehicle-mounted high-precision data management system, as shown in Figure 4. This figure is a flowchart of a vehicle data management system provided by an embodiment of this application. This enables multiple vehicles to test the energy flow of the same road simultaneously, avoiding the phenomenon that data cannot be compared due to different test times and different actual traffic conditions.

[0102] S401, Compilation of vehicle test data and test indicators.

[0103] This data management system includes a temperature measurement module, an analog signal acquisition module, a high voltage acquisition module, a CAN acquisition module, and a data logging module, supporting the acquisition and recording of signals such as temperature, current, voltage, flow rate, CAN, and CANFD. The vehicle test data and test indicators are organized according to the following test matrix.

[0104] The test examines the actual road energy consumption of vehicles under various multi-factor matrices, including different temperatures, weather conditions, time periods, and routes. Typical temperatures include below -10℃, -10℃ to -5℃, -5℃ to 0℃, 0℃ to 10℃, 10℃ to 25℃, 25℃ to 35℃, and above 35℃. Weather factors include rain, snow, fog, haze, frost, and clear skies. Wind speeds include levels 0-2, 2-4, and above level 4. Time periods include morning rush hour (7:00-9:00), evening rush hour (17:00-19:30), off-peak hour (10:00-14:00), and nighttime (22:00-2:00). Routes include congested urban routes, suburban expressways, and mixed routes. The same test conditions are required for at least two consecutive days to avoid random errors. During the test, developed data acquisition equipment is used to simultaneously collect data from multiple vehicles.

[0105] S402. Upload the organized data to the data management system.

[0106] The data management system can input vehicle energy flow data and indicators with one click, and has functions such as automatically analyzing the performance indicators and process data of different vehicles, analyzing the development trend of vehicle indicators, and generating analysis reports with one click.

[0107] Specifically, the test data is categorized according to test items, test conditions, test working conditions, and test methods. The categorized data is then stored separately into two categories: test indicators and test process data. Standard indicator names and parameter names are used to record each achieved indicator and process data. Then, all the data for a vehicle model is compressed and packaged, and uploaded to the data management system. The system can automatically identify the data according to the category and display the vehicle performance indicators and process data on the interface. It also supports switching test data on the interface according to test items, test conditions, test working conditions, and test methods.

[0108] S403, Vehicle Performance Demonstration.

[0109] You can select a specific vehicle model, determine the test items, test conditions, test operating conditions, and test methods. The system can intuitively display the vehicle's energy consumption, the energy consumption and proportion of each component, and the test process data.

[0110] S404, comparison of multiple models.

[0111] The data management system allows users to select multiple vehicles and compare different performance indicators under the same test items, conditions, operating states, and methods, as well as the magnitude of test data. By comparing the indicators of multiple vehicles, the differences between the indicators of different models can be clearly seen, thus identifying the performance indicators that need to be optimized.

[0112] S405, Intelligent Analysis.

[0113] Simultaneously, it can perform intelligent analysis on single test indicators. After selecting the vehicle model requiring intelligent analysis, then choosing the test items, determining the test indicators to be analyzed, and filtering test conditions, methods, and operating conditions, it can reflect the dispersion and distribution trend of vehicle test indicators by providing the maximum, minimum, average, median, standard deviation, kurtosis, and skewness of the indicator data for all vehicle models. The indicator data is displayed in the form of scatter plots, bar charts, and normal distribution plots. Furthermore, it supports trend analysis of vehicle indicators based on vehicle parameters such as wheelbase, year, and price. Through intelligent analysis, one can see the ranking of a particular vehicle model's test indicators among many models, thereby determining whether that indicator needs optimization.

[0114] Based on the above description, this application acquires data to be processed through a processing device. This data includes multiple data files, each collected from sensors with different sampling frequencies. The number of data points in each data file also varies. Based on the data file obtained by the sensor with the highest sampling frequency, the data corresponding to each moment in the other data files is determined. Then, energy flow analysis is performed based on the data from all data files corresponding to the same moment. However, existing technologies directly perform energy flow analysis on the data acquired from sensors. Because the sampling frequencies of the sensors differ, and the number of data points collected by each sensor also varies, there will be a certain error between the energy flow analysis and the actual test results. Therefore, in this application, the calculation of data in other data files is determined according to the moment corresponding to the data in the data file obtained by the sensor with the highest sampling frequency. Then, energy flow analysis is performed based on the data from all data files corresponding to the same moment. Thus, the solution of this application effectively analyzes the acquired data, reducing the error compared to the actual test results. As shown in Figure 5, this application embodiment also provides a schematic diagram of a vehicle energy flow analysis device. This vehicle energy flow analysis device includes an acquisition module 501, a determination module 502, a calculation module 503, and an analysis module 504, as shown in Figure 5. The acquisition module 501 is used to acquire data to be processed, which includes at least a first data file and a second data file. The first data file includes multiple first data and a time corresponding to each first data. The second data file includes multiple second data and a time corresponding to each second data. The number of first data is greater than the number of second data.

[0115] Module 502 is used to determine the T of the first data file. n At time T, determine T in the second data file. n T of the moment n-1 Time and T n T of the moment n+1 At time T in the first data file nThere is always corresponding first data, and T in the second data file. n There is no corresponding second data at any given time; determine T from the second data file. n-1 The second data corresponding to time T and T n+1 The second data corresponding to the given time;

[0116] Calculation module 503, used to calculate according to the T n Time, the T n-1 Time, the T n-1 The second data corresponding to time T n+1 Time and the T n+1 The second data corresponding to the time point determines the T of the second data file. n The second data corresponding to the given time;

[0117] Analysis module 504 is used to perform energy flow analysis based on first and second data at the same time.

[0118] Optionally, the acquisition module 501 is used to process data to be processed by the device, including:

[0119] Acquire a first data file collected by a first sensor and a second data file collected by a second sensor, wherein the sampling frequency of the first sensor is higher than that of the second sensor.

[0120] Optionally, the determining module 502 is used to determine the T of the first data file. n Moments, including:

[0121] In the second data file, iterate through the time corresponding to the first data in the first data file, and determine the time corresponding to the first data that has not been iterated through as T. n time.

[0122] Optionally, the analysis module 504 is used to process data including multiple data files, and to determine the T of the second data file. n After the second data corresponding to the time, multiple sets of sample index data and multiple sets of sample energy consumption data are generated based on the data of the same time in multiple data files;

[0123] Determine the correlation between sample indicator data and sample energy consumption data;

[0124] Remove sample indicator data and sample energy consumption data with correlation below the correlation threshold from multiple sets of sample indicator data to obtain the remaining sample indicator data and remaining sample energy consumption data.

[0125] The vehicle energy consumption prediction model is trained using the remaining sample index data and the remaining sample energy consumption data.

[0126] Optionally, the calculation module 503 is used to calculate based on the T n Time, the T n-1 Time, the T n-1 The second data corresponding to time T n+1 Time and the T n+1 The second data corresponding to the time point determines the T of the second data file. n The second data corresponding to the time includes:

[0127] The second data file in T is calculated using the following formula. n Second data point at time: D n =C×D n-1 +B×D n+1

[0128] Among them, T n T n-1 And T n+1 T is a positive integer. n-1 Time T n The moment before time, T n+1 Time T n At the next time step, C has the first weight, B has the second weight, and D... n For T n The second data point corresponding to time point D n-1 For T n-1 The second data point corresponding to time point D n+1 For T n+1 The second data corresponding to the time.

[0129] Optionally, the analysis module 504 is used to determine the correlation between sample indicator data and sample energy consumption data, including:

[0130] Among them, V mic (x i ,y i Let y be the correlation between the i-th sample index data and the i-th sample energy consumption data, Xi be the set of the i-th index data, and Y be the correlation between the i-th sample index data and the i-th sample energy consumption data. i Let i be the set of energy consumption data for the i-th vehicle. For X i The j-th sample indicator variable in For Y i The energy consumption variable of the j-th sample in the data. for The joint probability density, for marginal probability density, for The marginal probability density, G = (a, b), where the product of a and b equals X. i Or Y i The number of variables in the array, where a is the horizontal coordinate variable of grid G, b is the vertical coordinate variable of grid G, and both a and b are positive integers, f(q) = q 0.6 q is X i Or Y i The number of variables in q, where j is a positive integer, and j is less than or equal to q.

[0131] Optionally, the analysis module 504 is used to acquire the data of the indicator to be predicted;

[0132] The vehicle energy consumption prediction model is obtained by inputting the data of the indicator to be predicted into the vehicle energy consumption prediction model.

[0133] This application also provides a computing device. As shown in FIG6, which is a schematic diagram of a computing device provided in this application embodiment, the computing device 600 includes a bus 801, a processor 802, a communication interface 803, and a memory 804. The processor 802, the memory 804, and the communication interface 803 communicate with each other through the bus 801.

[0134] Bus 801 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 6, but this does not indicate that there is only one bus or one type of bus.

[0135] The processor 802 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0136] The communication interface 803 is used for external communication.

[0137] Memory 804 may include volatile memory, such as random access memory (RAM). Memory 804 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0138] The memory 804 stores executable code, which the processor 802 executes to perform a method for analyzing vehicle energy flow.

[0139] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct a computing device to execute a method for analyzing vehicle energy flow.

[0140] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0141] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0142] When the computer program product is executed by a computer, the computer performs any method of a vehicle energy flow analysis method. The computer program product can be a software installation package; when any method of a vehicle energy flow analysis method is required, the computer program product can be downloaded and executed on the computer.

[0143] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0144] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method of analyzing energy flow of a vehicle, characterized by, The method includes: Acquire data to be processed, which includes at least a first data file and a second data file. The first data file includes multiple first data and a time corresponding to each first data. The second data file includes multiple second data and a time corresponding to each second data. The number of first data is greater than the number of second data. Acquire the first data file collected by the first sensor and the second data file collected by the second sensor. The sampling frequency of the first sensor is higher than the sampling frequency of the second sensor. Determine T of the first data file n The time point of the second data of the second data file, and the time point of the first data in the first data file is traversed, and the time point of the first data which is not traversed is determined as T n The time point; determining T n the time T n-1 the time T n the time T n+1 the time T n the time T n the time T n-1 the time T n+1 the time T According to the T n moment, the T n-1 moment, the T n-1 moment, the T n+1 moment, and the T n+1 moment, the second data corresponding to the T n moment corresponding to the second data of the T Energy flow analysis was performed using the first and second data points at the same time.

2. The method of claim 1, wherein, The second data corresponding to the T n moment, the T n-1 moment, the T n-1 moment, the T n+1 moment, and the T n+1 moment, the T n moment corresponding to the second data of the second data file, comprising: The second data file at time T is calculated using the following equation: n ​ D n = C x D n-1 + B x D n+1 Among them, T n T n-1 And T n+1 T is a positive integer. n-1 Time T n The moment before time, T n+1 Time T n At the next time step, C has the first weight, B has the second weight, and D... n For T n The second data point corresponding to time point D n-1 For T n-1 The second data point corresponding to time point D n+1 For T n+1 The second data corresponding to the given time.

3. The method of claim 1, wherein, The to-be-processed data includes a plurality of data files, and after the second data corresponding to the T n moment of the second data file is determined, the method further includes: generating a plurality of sets of sample index data and a plurality of sets of sample energy consumption data according to the data of the same moment in the plurality of data files. Determine the correlation between sample indicator data and sample energy consumption data; Sample indicator data and sample energy consumption data with correlation below the correlation threshold are removed from multiple sets of sample indicator data to obtain the remaining sample indicator data and remaining sample energy consumption data; the remaining sample indicator data and remaining sample energy consumption data are used to train the vehicle energy consumption prediction model.

4. The method of claim 3, wherein, The determining the correlation between the sample index data and the sample energy consumption data comprises: wherein V mic (x i ,y i ) is the correlation between the i-th sample indicator data and the i-th sample energy consumption data, X i is the set of i-th indicator data, Y i is the set of i-th vehicle energy consumption data, for X i the jth sample indicator variable in X, for Y i the jth sample in Y For joint probability density of the parameters, For the marginal probability density of the edge, For the marginal probability density of X, G = (a, b), the product of a and b is equal to X i or Y i the number of variables in X 0.6 , q is the number of variables in X i or Y i the number of variables in X 5. The method of claim 3, wherein, The method further includes: Obtain the data for the indicator to be predicted; The vehicle energy consumption prediction model is obtained by inputting the data of the indicator to be predicted into the vehicle energy consumption prediction model.

6. An analysis device of a vehicle energy flow, characterized by The device includes: An acquisition module is used to acquire data to be processed, the data to be processed including at least a first data file and a second data file, the first data file including multiple first data and a time corresponding to each first data, the second data file including multiple second data and a time corresponding to each second data; the number of first data is greater than the number of second data; the module acquires the first data file collected by a first sensor and the second data file collected by a second sensor, the sampling frequency of the first sensor being higher than the sampling frequency of the second sensor; The determination module is used to determine the T of the first data file. n At time, within the time corresponding to the second data in the second data file, iterate through the time corresponding to the first data in the first data file, and determine the time corresponding to the first data that has not been reached as T. n Time; determine T in the second data file n T of the moment n-1 Time and T n T of the moment n+1 At time T in the first data file n There is always corresponding first data, and T in the second data file. n There is no corresponding second data at any given time; determine T from the second data file. n-1 The second data corresponding to time T and T n+1 The second data corresponding to the given time; a calculation module configured to determine, according to the T n moment, the second data corresponding to the T n-1 moment, the second data corresponding to the T n-1 moment, the second data corresponding to the T n+1 moment, and the second data corresponding to the T n+1 moment, the second data corresponding to the T n moment corresponding to the second data file; The analysis module is used to perform energy flow analysis based on the first and second data at the same time.

7. A computing device, comprising: Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 5.

Images