An engine calibration method, apparatus, electronic device and storage medium

Abstract

This invention discloses an engine calibration method, apparatus, electronic device, and storage medium. It includes: collecting vehicle driving data; dividing the driving data into scenarios to obtain driving data corresponding to multiple scenarios; for the driving data of a target scenario, determining and constructing transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario; and calibrating the engine based on the transient and steady-state operating conditions. This solution proposes a method that divides the actual driving data of a vehicle into scenarios to obtain driving data for different scenarios, then determines and constructs transient and steady-state operating conditions for different scenarios, and completes the engine calibration function based on the above operating conditions. This solves the problem of not being able to calibrate the engine specifically, avoids processing all driving data to complete the engine calibration work, and can achieve efficient and accurate engine data calibration, reduce the data calibration cycle, and improve the efficiency of engine calibration.

Description

Technical Field

[0001] This invention relates to the field of engine calibration technology, and in particular to an engine calibration method, apparatus, electronic device and storage medium. Background Technology

[0002] Engine calibration is a crucial step in engine development, directly determining important parameters such as fuel consumption, emissions, and power performance.

[0003] For engine calibration, the common method is to use point scanning, that is, to perform universal characteristic tests on the engine to determine or optimize engine calibration data, and to calibrate the operating conditions that the vehicle may encounter in actual driving.

[0004] While the existing technical solutions described above can calibrate the engine, they have drawbacks such as not being able to calibrate the engine specifically and requiring a large amount of manpower, material resources, time, and effort. Summary of the Invention

[0005] This invention provides an engine calibration method, apparatus, electronic device, and storage medium to solve the problems of existing engine calibration technologies being unable to perform targeted engine calibration and having poor calibration efficiency.

[0006] According to one aspect of the present invention, an engine calibration method is provided, comprising:

[0007] Collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively;

[0008] For the driving data of the target scenario, the transient and steady-state operating conditions under the target scenario are determined based on the driving data of the target scenario;

[0009] The engine is calibrated based on transient and steady-state operating conditions.

[0010] Optionally, the driving data can be segmented into scenarios, including:

[0011] Determine the vehicle's gear, load, and gradient during driving based on the vehicle's driving data;

[0012] Based on the vehicle type, gear position, load, and gradient during driving, as well as the scope of each scenario, the corresponding scenario for the driving data is determined.

[0013] Optionally, before determining and constructing the transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario, the following steps are also included:

[0014] Remove invalid data from the driving data. Invalid data includes data that exceeds the value range of each type of driving data and data that is located at a preset proportion at the edge of the data range.

[0015] Optionally, based on the driving data of the target scenario, the transient and steady-state operating conditions under the target scenario are determined and constructed, including:

[0016] Extract the feature road spectrum data of the driving data in the target scene, and form transient conditions from the feature road spectrum data;

[0017] Unqualified data in the driving data of the target scenario is removed, steady-state feature point data is extracted, and the steady-state feature point data is clustered to obtain clustering results. Steady-state operating conditions are formed based on the clustering results. Unqualified data includes data with negative torque values ​​and data that do not meet the acceleration threshold.

[0018] Optionally, after determining the transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario, the following steps are also included:

[0019] Verification was performed for both transient and steady-state operating conditions, among which...

[0020] The verification of transient operating conditions includes: comparing the actual speed and torque distribution with the transient operating condition distribution, and comparing the actual road spectrum parameters with the characteristic road spectrum parameters. The actual road spectrum parameters and characteristic road spectrum parameters include: average vehicle speed, speed, torque, and gear. The deviation between each parameter is calculated. If the deviation is less than the first preset deviation threshold, the transient operating condition is determined to be qualified.

[0021] The verification of steady-state operating conditions includes: weighting the fuel consumption based on the weighted data of the feature point data to obtain the weighted fuel consumption result, calculating the deviation with the actual average fuel consumption per 100 kilometers and the BSFC fuel consumption result respectively, and if the deviation meets the second preset deviation threshold, the steady-state operating condition is determined to be qualified.

[0022] Optionally, the engine can be calibrated based on transient and steady-state operating conditions, including:

[0023] Bench reproduction tests were conducted based on transient conditions, steady-state conditions, and data to be optimized to generate test data.

[0024] Data checks are performed based on the experimental data to obtain the target experimental data;

[0025] Data optimization analysis and processing are performed based on the target experimental data.

[0026] Optionally, data optimization analysis and processing can be performed based on the target experimental data, including:

[0027] Calculate the deviation between the target test data and the characteristic road spectrum data, and determine the reliability of the characteristic road spectrum data based on the deviation;

[0028] An engine simulation model is built based on the target test data, and the data is optimized through the engine simulation model to obtain optimized data;

[0029] Vehicle testing was conducted based on the optimized data to verify its reliability.

[0030] According to another aspect of the present invention, an engine calibration apparatus is provided, comprising:

[0031] The data acquisition module is used to collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios.

[0032] The driving condition construction module is used to determine and construct transient and steady-state driving conditions under the target scenario based on the driving data of the target scenario.

[0033] The engine calibration module is used to calibrate the engine based on transient and steady-state operating conditions.

[0034] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0035] At least one processor; and

[0036] A memory that is communicatively connected to at least one processor; wherein,

[0037] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the engine calibration method of any one of claims 1-7.

[0038] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the engine calibration method of any one of claims 1-7.

[0039] The technical solution of this invention divides the actual driving data of the vehicle into scenarios, obtains driving data for different scenarios, and then determines and constructs transient and steady-state operating conditions for different scenarios. Based on the above operating conditions, the engine calibration function is completed. This solves the problem of not being able to calibrate the engine in a targeted manner, avoids processing all driving data to complete the engine calibration work, and can achieve efficient and accurate engine data calibration, reduce the data calibration cycle, and improve the efficiency of engine calibration.

[0040] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of an engine calibration method provided in Embodiment 1 of the present invention;

[0043] Figure 2 This is a flowchart of an engine calibration method provided in Embodiment 2 of the present invention;

[0044] Figure 3 This is a schematic diagram of the structure of an engine calibration device provided in Embodiment 3 of the present invention;

[0045] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the engine calibration method of this invention. Detailed Implementation

[0046] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0047] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0048] Example 1

[0049] Figure 1 This is a flowchart of an engine calibration method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations requiring engine calibration. The method can be executed by an engine calibration device, which can be implemented in hardware and / or software. This engine calibration device can be configured in electronic devices such as computers and test benches. Figure 1 As shown, the method includes:

[0050] S110. Collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively.

[0051] Specifically, driving data refers to data collected during the actual driving process of the vehicle. This data can be acquired through onboard data acquisition equipment, for example, using the T-BOX (Telematics BOX) data acquisition equipment standard on China VI emission standard vehicles. Driving data includes, but is not limited to, vehicle speed, engine speed, torque, atmospheric pressure, throttle opening, braking data, clutch data, and GPS signals. Scene segmentation refers to the different scenarios set based on the different vehicle parameters in the driving data. Scenarios can be segmented based on parameters including, but not limited to, vehicle model, operating condition, load, and gradient. These parameters can be customized according to actual needs.

[0052] Specifically, the onboard T-BOX, standard equipment in China VI emission standard vehicles, collects vehicle speed, RPM, torque, atmospheric pressure, throttle opening, braking data, clutch data, GPS signal, and other driving data. No additional equipment is required. It combines the vehicle's engine and model information to record detailed data on actual road conditions and stores it on the vehicle network data platform. Based on the vehicle's parameters in the driving data, scenarios are segmented according to vehicle model, driving conditions, load, gradient, and other data. After scenario segmentation, the corresponding driving data for different scenarios can be obtained, allowing for the acquisition of specific driving data based on the required scenario.

[0053] Optionally, the method for segmenting driving data into scenarios can be: determining the vehicle's gear, load, and gradient during the driving process based on the vehicle's driving data; and determining the scenario corresponding to the driving data based on the vehicle's model, the vehicle's gear, load, and gradient during the driving process, and the segmentation range of each scenario.

[0054] Specifically, gear position analysis can be performed using vehicle speed and RPM ratio to determine the current vehicle's gear information; acceleration data can be obtained by differential calculation of time based on speed data; altitude data can be obtained by analyzing atmospheric pressure results; and vehicle weight data can be determined based on vehicle dynamics equations. Based on vehicle model, region, RPM, torque, and speed, information such as gear position, vehicle weight, and gradient can be calculated. Vehicles can be categorized by type (light or heavy), by operating conditions (urban, suburban, highway, port, etc.), by load (empty, half-loaded, fully loaded), and by gradient and altitude (mountain, plain, plateau), thus dividing driving data into multiple scenarios.

[0055] S120. For the driving data of the target scenario, determine and construct the transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario.

[0056] Specifically, the target scenario can be understood as the scenario selected from the scenario segmentation results as needed, in order to obtain the required driving data for engine calibration. Transient operating conditions can be understood as driving conditions where the vehicle speed changes continuously over a certain period of time; steady-state operating conditions can be understood as driving conditions where the vehicle speed remains constant over a certain period of time. These two types of operating conditions can be simulated by extracting feature data from the vehicle's driving data, or the required transient and steady-state operating conditions can be constructed using a mathematical model with preset values. Alternatively, transient and steady-state operating conditions can be constructed using Matlab software based on the acquired driving data. It should be noted that different vehicle models have different actual operating conditions; therefore, it is necessary to determine transient and steady-state operating conditions that conform to actual driving conditions in order to efficiently complete engine calibration.

[0057] Specifically, based on the selected target scenario, such as light vehicle, plain, or urban scenarios, the corresponding driving data for that scenario is obtained from the vehicle's driving data. Feature road spectrum extraction is performed on the driving data for the target scenario, and driving conditions are constructed using Matlab software. The Matlab program includes: a main program, a GUI interface, a filtering program, a gear calculation program, and a distribution map plotting program.

[0058] Optionally, before determining the transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario, the method further includes: removing invalid data from the driving data, wherein invalid data includes data that exceeds the value range of each type of driving data and data at a preset proportion located at the edge of the data range.

[0059] It should be noted that, since the data acquisition equipment may obtain data from both the engine CAN output and external sensors, there may be a synchronization problem between different devices. Therefore, invalid data needs to be removed from the vehicle's driving data.

[0060] Specifically, the range of values ​​for driving data can be understood as the range of parameter values ​​in the driving data. The threshold of the value range can be preset according to actual needs, and data that does not meet the threshold can be removed. A preset ratio of the edge of the data range can also be preset, that is, the data can be sorted in ascending or descending order, and the data located at both ends of the sorting result can be removed. A preset ratio can be set to remove the data within the preset ratio.

[0061] Specifically, based on actual data requirements, a threshold range can be preset. Each type of driving data is compared with the corresponding threshold range, and data that does not meet the threshold range is removed. Alternatively, a preset ratio threshold can be set to remove data that does not meet the requirements. For example, if the acquired driving data is sorted in descending order and a preset ratio of 2% is set, then the data with the lowest values ​​should be deleted, accounting for 2% of the driving data. Similarly, the data with the highest values ​​should be deleted, accounting for 2% of the driving data.

[0062] S130, calibrate the engine based on transient and steady-state operating conditions.

[0063] Specifically, engine calibration can be understood as the process of optimizing engine data to obtain highly reliable indicators.

[0064] Specifically, transient and steady-state operating conditions can be imported as input parameters into the bench control system for bench reproduction tests. By optimizing engine data calibration based on transient and steady-state operating condition tests, calibration data that conforms to the current scenario can be obtained.

[0065] For example, by using highly accurate and repeatable bench tests and vehicle wheel rotation tests, and taking the constructed operating conditions as the benchmark, data calibration and optimization can be performed on the vehicle and engine. Alternatively, the constructed operating conditions can be used as road spectrum inputs for simulation calculation models, and the design of the vehicle and engine can be optimized through simulation.

[0066] The technical solution of this embodiment divides the actual driving data of the vehicle into scenarios, obtains driving data in different scenarios, and then determines and constructs transient and steady-state operating conditions for different scenarios. Based on the above operating conditions, the engine calibration function is completed. This solves the problem of not being able to calibrate the engine in a targeted manner, avoids processing all driving data to complete the engine calibration work, and can achieve efficient and accurate engine data calibration, reduce the data calibration cycle, and improve the efficiency of engine calibration.

[0067] Example 2

[0068] Figure 2This is a flowchart of an engine calibration method provided in Embodiment 2 of the present invention. This embodiment is a further optimization of the method in the above embodiments. Optionally, for the driving data of the target scenario, feature road spectrum data of the driving data of the target scenario is extracted, and the feature road spectrum data forms transient operating conditions; unqualified data in the driving data of the target scenario is removed, steady-state feature point data is extracted, and the steady-state feature point data is clustered to obtain clustering results, and steady-state operating conditions are formed based on the clustering results; the transient operating conditions and steady-state operating conditions are verified; bench reproduction tests are performed based on the transient operating conditions, steady-state operating conditions, and data to be optimized to generate test data; data checks are performed based on the test data to obtain target test data; data optimization analysis is performed based on the target test data; such as... Figure 2 As shown, the method includes:

[0069] S210. Collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively.

[0070] S220. For the driving data of the target scenario, extract the feature road spectrum data of the driving data of the target scenario, and form the transient conditions from the feature road spectrum data.

[0071] Specifically, characteristic road spectrum data can be understood as data composed of the characteristic values ​​of driving data. The driving data can be processed by some mathematical methods. The preprocessed data can be selected by eigenvalue clustering to select actual road spectrum data or by probability distribution method to generate characteristic road spectrum similar to actual road spectrum data. These mathematical methods include, but are not limited to, data alignment methods, short-stroke partitioning methods, principal component analysis methods, and clustering algorithms constructed by membership degree and category weight factors. The characteristic road spectrum data includes, but is not limited to, speed data, torque data, etc.

[0072] Specifically, the driving data of the target scenario is read, and the driving data is aligned according to the data characteristics using methods such as extreme value location and regression analysis. Erroneous and invalid data in the aligned data are deleted. These abnormal data mainly include, but are not limited to, data with null or zero torque, fuel consumption data, and data with the engine not started. After the driving data is preprocessed, valid data is obtained. The valid data is then selected by eigenvalue clustering to select actual road spectrum data as feature road spectrum data, or by using probability distribution method to generate feature road spectrum data similar to actual road spectrum data. The obtained feature road spectrum data are combined to form transient operating conditions.

[0073] For selecting road spectrum data using eigenvalue clustering, the road spectrum is divided into multiple short-stroke segments using the short-stroke segmentation method. A short stroke is defined as the process of accelerating from 0 to 0. When decomposing effective data into short-stroke segments, the actual vehicle speed in the road spectrum data may fluctuate around 0, leading to small short strokes or multiple distinct segments not being separated. Therefore, in actual segmentation, the process of accelerating from 1 km / h to 1 km / h is often considered as a short stroke segment, and the segment length is calculated. Segments with a length shorter than a preset time threshold are deleted, for example, a preset time threshold of 20 seconds. Eigenvalues ​​are set according to actual needs; for example, the required eigenvalue content can be set on the visualization interface, and the corresponding eigenvalue results for each short stroke segment are calculated according to the eigenvalue calculation method. Commonly used eigenvalues ​​include, but are not limited to, average vehicle speed, speed range, acceleration, gear, average RPM, and average torque. The calculation method can be a pre-set eigenvalue calculation program. The calculated eigenvalue results for each short stroke are then standardized, converting all eigenvalue data columns to data with a mean of 0 and a standard deviation of 1. The calculation formula is as follows:

[0074]

[0075] Where, x n For the calculated eigenvalue data, μ is the mean of the eigenvalue data, and σ is the standard deviation of the eigenvalue data.

[0076] Principal component analysis (PCA) is performed on the standardized feature data to simplify the eigenvalue dimension. Orthogonal transformations can be used to convert the eigenvalue matrix into a set of linearly uncorrelated variables. Assume there are p random variables, denoted as X1, X2, ..., X... P Principal component analysis transforms the problem of p variables into a problem of discussing linear combinations of p indicators, and these new indicators are F1, F2, ..., F... P As shown in the following formula.

[0077] F1=μ 11 X1+μ 21 X2+……+μ p1 X p

[0078] F2=μ 12 X1+μ 22 X2+……+μ p2 X p

[0079] ...

[0080] F p =μ 1pX1+μ 2p X2+……+μ pp X p

[0081] Calculate the principal components F1, F2, ..., F based on the above system of equations. k (k≤p), the number of principal components is selected by calculating the cumulative contribution rate of the principal components. In some embodiments, the number of principal components depends on the amount of information that can reflect more than n% of the original variables. The value of n% can be set by the researchers themselves; for example, it can be set to 90%, meaning that the number of principal components is sufficient when the cumulative contribution rate is ≥90%. In this way, we transform a large matrix database into a smaller matrix database using the principal component method, facilitating subsequent cluster analysis. The cumulative contribution rate (ccn) refers to the proportion of the variance of the first k principal components in the total variance, reflecting the overall comprehensive ability of the first k principal components. The formula for calculating the cumulative contribution rate (ccn) is as follows:

[0082]

[0083] Based on the cumulative contribution rate of the principal components calculated using the above formula, the top N principal components are extracted for clustering calculation. For example, N can be set to 5. A clustering algorithm is constructed based on membership degree, category weight factor, and other methods to divide all short-distance segments into 3-7 classes. Each class of segments has similar feature values. Initial cluster points are selected using the Euclidean distance method. The membership degree of each short-distance segment feature value to that point is calculated. The position of the intermediate point is calculated using the membership degree, and the cluster center is updated. This process is iterated until the cluster center is stable. The accuracy of fuzzy clustering can be optimized by optimizing the distance algorithm, initial value, convergence criterion, etc. After selecting suitable segments from various short-distance segments using the feature value method, the road spectrum data is sorted according to the average vehicle speed or other parameters. Idle segments are inserted according to the target time length to complete the road spectrum data filling, so that the sum of the road spectrum data duration and the idle segment duration meets the target time length. The target time length can be set according to actual needs, for example, the target time length can be set to 1800s. It should be noted that when dividing short-distance segments, the idle ratio needs to be calculated to reserve the idle segment duration. The obtained complete road spectrum data is used as the instantaneous operating condition.

[0084] For obtaining characteristic road spectrum data using the probability distribution method, the operating points in the actual road spectrum data are discretized. For example, if the source data is continuous speed and torque, the speed is approximated to data points with an interval of 10 rpm, and the torque is approximated to data points with an interval of 5 Nm. Then, based on the discretized actual road spectrum data, the probability distribution of each operating condition transitioning to the next operating condition is statistically analyzed to determine the probability value of the next operating condition. Based on the probability transition matrix, the characteristic road spectrum of the target length and the overall operating condition transition probability distribution of the road spectrum are generated starting from the idle speed data point. If the overall operating condition transition probability distribution of the road spectrum is consistent with the actual road spectrum operating condition probability distribution, the current characteristic road spectrum data is derived; otherwise, the characteristic road spectrum data is regenerated to form transient operating conditions.

[0085] It should be noted that the method of selecting road spectrum data by using eigenvalue clustering and generating characteristic road spectrum data by using probability distribution can be flexibly selected by researchers based on the characteristics of the data.

[0086] S230. Remove unqualified data from the driving data of the target scenario, extract steady-state feature point data, perform clustering processing on the steady-state feature point data to obtain clustering results, and form steady-state operating conditions based on the clustering results.

[0087] The unqualified data includes data with negative torque values ​​and data that does not meet the acceleration threshold. The acceleration threshold includes positive acceleration threshold and negative acceleration threshold, which can be set according to the data characteristics.

[0088] Specifically, since the engine torque is being assigned a value and the engine is not injecting fuel, negative torque values ​​are eliminated when constructing a steady-state operating condition. Additionally, unqualified data is removed from the acceleration and deceleration data in the driving data; that is, data with acceleration less than a first acceleration threshold or greater than a second acceleration threshold are deleted. The first acceleration threshold is a negative acceleration threshold, for example, it can be set to -0.1 m / s². 2 The second acceleration threshold is a positive acceleration threshold, which can be set to 0.1 m / s². 2 After deleting the unqualified data, a clustering algorithm is used to cluster the data obtained by the above method, resulting in m clustering conditions. The value of m can be set according to actual needs, usually 13 or 15. These clustering conditions are combined to obtain steady-state conditions, and then the cluster center of each condition is obtained. The weight of each condition is calculated based on the proportion of each type of condition.

[0089] S240. Verify transient and steady-state operating conditions.

[0090] Specifically, after completing the construction of transient and steady-state operating conditions, it is necessary to verify the transient and steady-state operating conditions, including transient operating condition verification and steady-state operating condition verification, to ensure that the characteristic road spectrum data and steady-state feature point data obtained by the above methods are consistent with the actual road spectrum data.

[0091] The verification of transient operating conditions includes: comparing the actual speed and torque distribution with the transient operating condition distribution, and comparing the actual road spectrum parameters with the characteristic road spectrum parameters. The actual road spectrum parameters and characteristic road spectrum parameters include average vehicle speed, speed, torque, and gear. The deviation between each parameter is calculated. If the deviation is less than the first preset deviation threshold, the transient operating condition is determined to be qualified. The verification of steady-state operating conditions includes: weighting the fuel consumption based on the weighted data of the feature point data to obtain the weighted fuel consumption result, and calculating the deviation with the actual road spectrum average fuel consumption per 100 kilometers and BSFC (Brake Specific Fuel Consumption) fuel consumption results. If the deviation meets the second preset deviation threshold, the steady-state operating condition is determined to be qualified.

[0092] Specifically, the actual speed and torque operating condition distribution can be understood as the actual speed and torque operating condition distribution obtained by calculating and analyzing the operating condition probability distribution of actual driving data. The transient operating condition distribution comparison can be understood as the characteristic road spectrum operating condition distribution obtained by calculating and analyzing the operating condition probability distribution of characteristic road spectrum data.

[0093] Specifically, for transient operating condition analysis, the deviation between the actual speed and torque operating condition distribution and the characteristic road spectrum operating condition distribution is calculated. Furthermore, the deviations between the average vehicle speed, average speed, average torque, and gear position obtained from statistical analysis of the actual road spectrum data and the average vehicle speed, average speed, average torque, and gear position obtained from statistical analysis of the characteristic road spectrum data are calculated. If the error values ​​obtained above are less than a first preset deviation threshold, it can be determined that the currently obtained transient operating condition is consistent with the actual road spectrum and is a qualified transient operating condition. This condition can be used to characterize the transient operating condition of the actual road spectrum and for engine calibration. For example, the first preset deviation threshold can be set to 5%. This threshold can be set according to the accuracy requirements of the transient operating condition. A higher deviation threshold can be set for transient operating conditions requiring high accuracy, and vice versa.

[0094] For the verification of steady-state operating conditions, the fuel consumption is weighted according to the weight data of the feature point data to obtain the fuel consumption weighted result. The weighted fuel consumption result is then compared with the actual average fuel consumption per 100 kilometers and the BSFC fuel consumption result to calculate the deviation. If the obtained deviation meets the second preset deviation threshold, the steady-state operating condition can be judged to be qualified. The second preset deviation threshold can be set according to actual needs, for example, it can be set to 5%.

[0095] It should be noted that if either of the above two working conditions fails to meet the requirements, the corresponding working condition needs to be regenerated.

[0096] S250, based on transient conditions, steady-state conditions and data to be optimized, conduct bench reproduction tests to generate test data.

[0097] The data to be optimized can be understood as all the data items of the engine, including but not limited to rail pressure, timing, urea injection control and pneumatic actuator control data, which can be preset by researchers according to the needs of bench testing.

[0098] Specifically, after selecting transient and steady-state operating conditions, these conditions are imported into the bench control system. The bench test platform is then configured using the data to be optimized, preparing for bench tests under both transient and steady-state conditions. The bench platform generates and exports the test data. It should be noted that the exported characteristic road spectrum data format corresponding to the transient and steady-state operating conditions should be consistent with the bench requirements to ensure that the characteristic road spectrum data obtained from processing actual vehicle big data can be quickly imported into the bench control system.

[0099] S260. Based on the experimental data, perform data checks to obtain the target experimental data.

[0100] Specifically, the test data obtained from bench tests are checked, and any incorrect or missing data is supplemented to obtain accurate test data. This data check includes, but is not limited to, the temperatures and pressures of various engine air passages, coolant temperature, oil temperature, and emissions. Furthermore, the test data is standardized, with unified data names and units.

[0101] In this embodiment, the test data is inspected and processed, the engine data items are inspected, and the inspected test data is standardized to ensure the universality of the data.

[0102] S270. Perform data optimization analysis and processing based on target test data.

[0103] Data optimization analysis and processing includes steps such as model accuracy checking, data optimization, and data verification.

[0104] Specifically, after the engine calibration work is completed, the obtained target test data is optimized and analyzed, including model accuracy checks, data optimization, and data verification.

[0105] Optionally, for model accuracy checks, the deviation between the target test data and the characteristic road spectrum data is calculated, and the reliability of the characteristic road spectrum data is determined based on the deviation.

[0106] Specifically, the test results obtained from bench tests based on transient and steady-state operating conditions are compared with the derived results of the characteristic road spectrum. The deviations of the total fuel consumption of the road spectrum and the weighted fuel consumption of steady-state characteristic points under steady-state conditions from the derived results of the characteristic road spectrum are checked to ensure the reliability of the characteristic road spectrum data. For example, the preset deviation threshold can be set to 5%. If the test results and the derived results of the characteristic road spectrum do not meet the requirement of being less than the preset deviation threshold, the characteristic road spectrum and characteristic points need to be regenerated. An engine simulation model is constructed based on the bench test results. Simulation tests of the engine simulation model are conducted based on transient and steady-state operating conditions. The results obtained are compared with the target test results to ensure that the deviations of the fuel consumption and power performance results from the test results are less than the preset deviation threshold.

[0107] Optionally, for data optimization, an engine simulation model is built based on the target test data, and the data is optimized through the engine simulation model to obtain optimized data.

[0108] Specifically, data optimization is achieved through simulation models, including total fuel consumption and emissions at both transient and steady-state operating conditions. Simulation calculations can be performed quickly, yielding optimized data with reduced bench testing. Furthermore, during engine bench testing, specific data, including but not limited to thermal management optimization and DPF (Diesel Particulate Filter) regeneration optimization, can be specifically optimized to bring the calibration data to an optimal state. Data optimization brings engine performance, fuel consumption, emissions, reliability, and other parameters to a comprehensive optimal state, allowing the extraction of optimized data for the engine model under target scenarios, resulting in better vehicle performance in those scenarios.

[0109] Optionally, for data validation, vehicle testing can be conducted based on the optimized data to verify the reliability of the optimized data.

[0110] Specifically, after obtaining the optimized data, it is tested on a real vehicle, and its performance is tracked and recorded to verify the reliability of the optimized data. First, it is tested on an internal test vehicle. After the data is basically normal within one week, it is tested in depth on more than 10 user vehicles. After one month of testing, if the test results are normal and the actual results show improvement, it can be put into use.

[0111] The technical solution of this embodiment divides the actual driving data of the vehicle into scenarios, obtains driving data for different scenarios, and then determines and constructs transient and steady-state operating conditions for different scenarios. Based on the above operating conditions, it completes the functions of engine calibration and verification of optimized data, so that the obtained transient and steady-state operating conditions are consistent with the actual road spectrum data. It can accurately represent the actual road spectrum data of the vehicle and use it for bench testing to achieve engine calibration. This solves the problem of not being able to calibrate the engine in a targeted manner, avoids processing all driving data to complete the engine calibration work, and can achieve efficient and accurate engine data calibration, reduce the data calibration cycle, and improve the efficiency of engine calibration.

[0112] Example 3

[0113] Figure 3 This is a schematic diagram of an engine calibration device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0114] The data acquisition module 310 is used to collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively.

[0115] The working condition construction module 320 is used to determine and construct transient and steady-state working conditions under the target scenario based on the driving data of the target scenario.

[0116] Engine calibration module 330 is used to calibrate the engine based on transient and steady-state operating conditions.

[0117] Optionally, the data acquisition module 310 is specifically used for:

[0118] The vehicle's gear, load, and gradient during driving are determined based on the vehicle's driving data; the corresponding scenario is determined based on the vehicle's model, the gear, load, gradient during driving, and the scope of each scenario.

[0119] Optional, the working condition construction module 320 is specifically used for:

[0120] Remove invalid data from the driving data. Invalid data includes data that exceeds the value range of each type of driving data and data that is located at a preset proportion at the edge of the data range.

[0121] Based on the driving data of the target scenario, the transient and steady-state operating conditions under the target scenario are determined and constructed, including:

[0122] Extract the feature road spectrum data of the driving data in the target scene, and form transient conditions from the feature road spectrum data;

[0123] Unqualified data in the driving data of the target scenario is removed, steady-state feature point data is extracted, and the steady-state feature point data is clustered to obtain clustering results. Steady-state operating conditions are formed based on the clustering results. Unqualified data includes torque negative value points and data that do not meet the acceleration threshold.

[0124] Optionally, the working condition construction module 320 is also used to verify the transient and steady-state working conditions after determining the transient and steady-state working conditions under the target scenario based on the driving data of the target scenario. The verification of the transient working conditions involves comparing the actual speed and torque working condition distribution with the transient working condition distribution, and comparing the actual road spectrum parameters with the characteristic road spectrum parameters. The actual road spectrum parameters and characteristic road spectrum parameters include: average vehicle speed, speed, torque, and gear. The deviation between each parameter is calculated. If the deviation is less than a first preset deviation threshold, the transient working condition is determined to be qualified.

[0125] For the verification of steady-state operating conditions, the fuel consumption is weighted based on the weighted data of the feature point data to obtain the fuel consumption weighted result. The deviation is calculated with the actual average fuel consumption per 100 kilometers and the BSFC fuel consumption result. If the deviation meets the second preset deviation threshold, the steady-state operating condition is determined to be qualified.

[0126] Optional, engine calibration module 330, specifically used for:

[0127] Bench reproduction tests were conducted based on transient conditions, steady-state conditions, and data to be optimized to generate test data.

[0128] Data checks are performed based on the experimental data to obtain the target experimental data;

[0129] Data optimization analysis and processing are performed based on the target experimental data.

[0130] Calculate the deviation between the target test data and the characteristic road spectrum data, and determine the reliability of the characteristic road spectrum data based on the deviation;

[0131] An engine simulation model is built based on the target test data, and the data is optimized through the engine simulation model to obtain optimized data;

[0132] Vehicle testing was conducted based on the optimized data to verify its reliability.

[0133] The engine calibration device provided in the embodiments of the present invention can execute the engine calibration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0134] Example 4

[0135] Figure 4This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as engine calibration methods.

[0139] In some embodiments, the engine calibration method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the engine calibration method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the engine calibration method by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs used to implement the engine calibration method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] Example 5

[0143] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute an engine calibration method, the method comprising:

[0144] Collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively;

[0145] For the driving data of the target scenario, the transient and steady-state operating conditions under the target scenario are determined based on the driving data of the target scenario;

[0146] The engine is calibrated based on transient and steady-state operating conditions.

[0147] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0148] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0149] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0150] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0151] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0152] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An engine calibration method, characterized in that, include: Collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively; For the driving data of the target scenario, the transient and steady-state operating conditions under the target scenario are determined based on the driving data of the target scenario; The engine is calibrated based on the transient and steady-state operating conditions.

2. The method according to claim 1, characterized in that, The process of segmenting the driving data into scenarios includes: The vehicle's gear, load, and gradient during driving are determined based on the vehicle's driving data. Based on the vehicle model, the gear, load, and gradient of the vehicle during driving, and the division range of each scenario, the scenario corresponding to the driving data is determined.

3. The method according to claim 1, characterized in that, Before determining and constructing the transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario, the method further includes: Invalid data is removed from the driving data, including data that exceeds the value range of each type of driving data and data that is located at a preset proportion at the edge of the data range.

4. The method according to claim 1, characterized in that, The process of determining and constructing transient and steady-state operating conditions under the target scenario based on driving data of the target scenario includes: Extract the feature road spectrum data of the driving data of the target scene, and form the transient condition from the feature road spectrum data; Unqualified data in the driving data of the target scenario is removed, steady-state feature point data is extracted, and the steady-state feature point data is clustered to obtain clustering results. The steady-state operating condition is formed based on the clustering results. The unqualified data includes torque negative value point data and data that does not meet the acceleration threshold.

5. The method according to claim 1, characterized in that, After determining the transient and steady-state operating conditions under the target scenario based on the driving data of the target scenario, the method further includes: The transient and steady-state operating conditions are verified, wherein, The verification of the transient operating condition includes: comparing the actual speed and torque distribution with the transient operating condition distribution; comparing the actual road spectrum parameters with the characteristic road spectrum parameters, wherein the actual road spectrum parameters and the characteristic road spectrum parameters include: average vehicle speed, speed, torque, and gear; calculating the deviation between each parameter; if the deviation is less than a first preset deviation threshold, then the transient operating condition is determined to be qualified. The verification of the steady-state operating condition includes: weighting the fuel consumption based on the weighted data of the feature point data to obtain the fuel consumption weighted result, calculating the deviation with the actual road spectrum average fuel consumption per 100 kilometers and the BSFC fuel consumption result respectively, and if the deviation meets the second preset deviation threshold, then the steady-state operating condition is determined to be qualified.

6. The method according to claim 1, characterized in that, The calibration of the engine based on the transient and steady-state operating conditions includes: Based on the transient operating conditions, the steady-state operating conditions, and the data to be optimized, bench reproduction tests are conducted to generate test data. Based on the experimental data, data checks are performed to obtain the target experimental data; Data optimization analysis and processing are performed based on the target experimental data.

7. The method according to claim 6, characterized in that, The data optimization analysis and processing based on the target experimental data includes: Calculate the deviation between the target test data and the characteristic road spectrum data, and determine the reliability of the characteristic road spectrum data based on the deviation; An engine simulation model is built based on the target test data, and the data is optimized through the engine simulation model to obtain optimized data; Vehicle testing was conducted based on the optimized data to verify its reliability.

8. An engine calibration device, characterized in that, include: The data acquisition module is used to collect vehicle driving data, divide the driving data into scenarios, and obtain driving data corresponding to multiple scenarios respectively. The working condition construction module is used to determine and construct transient and steady-state working conditions under the target scenario based on the driving data of the target scenario. An engine calibration module is used to calibrate the engine based on the transient operating conditions and the steady-state operating conditions.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the engine calibration method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the engine calibration method according to any one of claims 1-7.

Images