Method for determining comprehensive transmission efficiency of electric drive axle based on characteristic parameters and typical times and related device

Abstract

The invention provides an electric drive axle comprehensive transmission efficiency determination method based on characteristic parameters and typical times and a related device, and belongs to the technical field of electric drive axle transmission efficiency determination. According to the method, representativeness of characteristic parameter distribution of the remaining times except the abnormal times and each time is evaluated, and typical times are determined; the rotating speed data and the torque data of the typical times are counted, and TN counting results of the typical times are obtained; obtaining the weight of the transmission efficiency of the electric drive axle under the TN classification based on the TN counting result of the typical times; performing finite element simulation or bench test on the TN counting result of the typical times to obtain the transmission efficiency of the electric drive axle under the TN grading; and obtaining the comprehensive transmission efficiency of the electric drive axle based on the weight of the transmission efficiency of the electric drive axle under the TN classification and the transmission efficiency of the electric drive axle under the TN classification. The problem that the accuracy of determining the comprehensive transmission efficiency of the electric drive axle is not high is solved.

Description

Technical Field

[0001] This invention belongs to the technical field of electric drive axle transmission efficiency determination, specifically relating to a method and related apparatus for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips. Background Technology

[0002] As a core component of commercial vehicle transmission systems, the accurate assessment and optimization of the electric drive axle's transmission efficiency is crucial. The efficiency spectrum, serving as the core basis for system efficiency characteristic analysis and product iteration optimization design, directly determines the actual effectiveness of optimization solutions based on its accuracy and representativeness. An efficiency spectrum that truly reflects actual user scenarios has irreplaceable value in guiding product design and improving energy efficiency.

[0003] Currently, the mainstream methods for constructing efficiency spectra in the industry mainly rely on the collection and statistics of vehicle operation data. However, these traditional methods have a series of inherent defects in data acquisition, feature recognition, spectrum construction, and engineering applicability, resulting in a significant deviation between the final constructed efficiency spectrum and the actual user experience, making it difficult to effectively guide product improvement.

[0004] Traditional efficiency spectrum construction methods suffer from the following problems: First, they rely on full-scale data calculation, resulting in large data volumes, low processing efficiency, and significant interference from abnormal user data. Second, they fail to consider the diversity of actual user operating conditions, leading to insufficient representativeness of the efficiency spectrum. Third, the directly constructed efficiency spectrum is coarse-grained, lacking precise characterization of core operating conditions, making it difficult to meet the actual needs of in-depth analysis of transmission system efficiency characteristics and precise product optimization design. Moreover, most existing methods use simple statistics or empirical formulas, ignoring the subdivision of operating conditions and the screening of data representativeness, failing to accurately reflect real user characteristics. This results in a large deviation between the determined electric drive axle transmission efficiency and the actual operating efficiency, hindering the technological upgrading and energy efficiency improvement of commercial vehicle transmission systems. Summary of the Invention

[0005] The purpose of this invention is to provide a method and related apparatus for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, in order to solve the problem of low accuracy in determining the comprehensive transmission efficiency of an electric drive axle in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, comprising the following steps: Obtain driving data from all users and design a stability coefficient based on this data. The minimum sample size required to obtain the transmission efficiency spectrum of the electric drive axle is obtained by iteratively calculating the stability coefficient. A feature parameter library is established based on the minimum sample size of full user driving data required for inputting the electric drive axle transmission efficiency spectrum per trip. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum, and the feature parameters for each trip are calculated. The characteristic parameters of each pass are analyzed to obtain effective characteristic parameters. The effective characteristic parameters are then dimensionality reduced to obtain principal component factors. After standardization of the principal component factors, cluster analysis is performed on the principal component factors to obtain the optimal number of clusters. Based on the optimal number of clusters, the cluster analysis results are determined. Based on the cluster analysis results, the Euclidean distance from each trip to the cluster center is calculated, and abnormal trips are removed based on the Euclidean distance from each trip to the cluster center. The representativeness of the characteristic parameter distribution of the remaining trips (excluding the abnormal trips) and each trip is evaluated to identify the typical trips. The speed and torque data of a typical trip are counted to obtain the TN (T represents torque, N represents speed) count result of the typical trip; Based on the TN counting results of typical trips, the weight of the electric drive axle transmission efficiency under the TN classification is obtained; Finite element simulation or bench test was performed on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under TN classification. The comprehensive transmission efficiency of the electric drive axle is obtained based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification.

[0007] A further improvement of this invention is that the formula for calculating the stability coefficient is:

[0008] in, Represents the stability coefficient. This represents the feature parameter values ​​of the sample set after adding new samples. This represents the feature parameter values ​​of the sample set before the addition of new samples. This indicates the number of feature parameters involved in the operation.

[0009] A further improvement of the present invention is that, before calculating the characteristic parameters of each trip, the full user driving data of the electric drive axle transmission efficiency spectrum with the minimum sample size is preprocessed. The preprocessing includes data cleaning, parking data filtering, outlier removal and resampling.

[0010] A further improvement of the present invention is that the characteristic parameters include speed, absolute value of motor torque, high load ratio, speed-torque correlation, number of rapid accelerations and number of rapid decelerations.

[0011] A further improvement of the present invention is that the analysis of the characteristic parameters of each trip to obtain effective characteristic parameters specifically involves: using principal component analysis to analyze the characteristic parameters of each trip to obtain effective characteristic parameters.

[0012] A further improvement of the present invention is that the evaluation of the representativeness of the characteristic parameter distribution of the remaining trips other than the abnormal trips and each trip to determine the typical trips is specifically: the representativeness of the characteristic parameter distribution of the remaining trips other than the abnormal trips and each trip is evaluated by using dynamic time warping distance to determine the typical trips.

[0013] A further improvement of this invention is that the formula for calculating the overall transmission efficiency of the electric drive axle is:

[0014] in, For the overall transmission efficiency of the electric drive axle, The transmission efficiency of the electric drive axle under the TN classification. The weight of the electric drive axle transmission efficiency under the TN classification. The value can be 1- .

[0015] Secondly, the present invention provides a system for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, comprising: The stability coefficient design module is used to acquire driving data from all users and design stability coefficients based on this data. The iterative calculation module is used to iteratively calculate the stability coefficients to obtain the minimum sample size required for the transmission efficiency spectrum of the electric drive axle. The feature parameter library establishment module is used to establish a feature parameter library based on the minimum sample size of full user driving data required for the input electric drive axle transmission efficiency spectrum in each trip. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum and calculates the feature parameters for each trip. The analysis module is used to analyze the characteristic parameters of each pass, obtain effective characteristic parameters, perform PCA dimensionality reduction on the effective characteristic parameters to obtain principal component factors, perform standardization on the principal component factors, perform cluster analysis on the principal component factors to obtain the optimal number of clusters, and determine the cluster analysis results based on the optimal number of clusters. The abnormal trip removal module is used to calculate the Euclidean distance from each trip to the cluster center based on the cluster analysis results, and remove abnormal trips based on the Euclidean distance from each trip to the cluster center. The evaluation module is used to evaluate the representativeness of the remaining trips (excluding abnormal trips) and the characteristic parameter distribution of each trip, and to identify typical trips. The counting module is used to count the speed and torque data of a typical trip to obtain the TN count result of a typical trip. The weight determination module is used to obtain the weight of the electric drive axle transmission efficiency under the TN classification based on the TN counting results of typical trips. The simulation test module is used to perform finite element simulation or bench test on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under the TN classification. The module for determining the overall transmission efficiency of the electric drive axle is used to obtain the overall transmission efficiency of the electric drive axle based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification.

[0016] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical passes as described above.

[0017] Fourthly, the present invention provides a storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical passes as described above.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The proposed method for determining the comprehensive transmission efficiency of electric drive axles based on characteristic parameters and typical trips involves two aspects. First, iterative calculation of the stability coefficient yields the minimum sample size required for the transmission efficiency spectrum of the electric drive axle. This operation not only ensures that the constructed transmission efficiency spectrum of the electric drive axle possesses sufficient statistical representativeness and stability, avoiding random bias caused by insufficient sample size, but also provides clear guidance for cost and resource control in engineering practice. It eliminates the need for blindly collecting massive amounts of data, significantly reducing data collection and computation costs while maintaining accuracy, thereby promoting rapid adoption and engineering application in the commercial vehicle industry. Second, based on the full range of user driving data input according to the minimum sample size required for the transmission efficiency spectrum of the electric drive axle, a characteristic parameter library is established, and the characteristic parameters for each trip are calculated. By calculating the characteristic parameters for each trip, this invention avoids the subjective bias of "selecting typical examples based on experience." On the other hand, the representativeness of the distribution of characteristic parameters for the remaining trips other than the abnormal trips is evaluated to identify typical trips. This operation not only ensures that the comprehensive transmission efficiency of the electric drive axle determined later can reflect the true benchmark efficiency and avoid interference from accidental data, but also reduces the amount of invalid data, thereby improving the accuracy of determining the comprehensive transmission efficiency of the electric drive axle. Attached Figure Description

[0019] Figure 1 This is a flowchart of the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, according to the present invention. Figure 2 This is a schematic diagram of the system for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, according to the present invention. Figure 3 This is a flowchart of the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips in Embodiment 4 of the present invention; Figure 4 This is a flowchart of the feature parameter calculation and verification process in Embodiment 4 of the present invention; Figure 5 This is a flowchart of principal component analysis and cluster analysis in Embodiment 4 of the present invention; Figure 6 This is the quantile chart of the number of rejection passes determined in Embodiment 4 of the present invention; Figure 7 This is the 128-level statistical histogram in Embodiment 4 of the present invention; Figure 8 This is the 8×8 test bench spectrum diagram in Embodiment 4 of the present invention; Figure 9 This is a schematic diagram of the structure of the electronic device of the present invention. Detailed Implementation

[0020] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0021] Example 1: The flowchart of the method for determining the comprehensive transmission efficiency of the electric drive axle based on characteristic parameters and typical passes in this invention is as follows: Figure 1 As shown, the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to the present invention includes the following steps: S1. Obtain driving data from all users and design a stability coefficient based on the driving data from all users; S2. Iteratively calculate the stability coefficient to obtain the minimum sample size required for the transmission efficiency spectrum of the electric drive axle; S3. Based on the full user driving data of the minimum sample size required for inputting the electric drive axle transmission efficiency spectrum per trip, establish a feature parameter library, which includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum, and calculate the feature parameters for each trip. S4. Analyze the characteristic parameters of each pass to obtain effective characteristic parameters, reduce the dimensionality of the effective characteristic parameters to obtain principal component factors, standardize the principal component factors, perform cluster analysis on the principal component factors to obtain the optimal number of clusters, and determine the cluster analysis results based on the optimal number of clusters. S5. Based on the cluster analysis results, calculate the Euclidean distance from each pass to the cluster center, and based on the Euclidean distance from each pass to the cluster center, remove abnormal passes; S6. Evaluate the representativeness of the remaining trips (excluding abnormal trips) and the characteristic parameter distribution of each trip to identify typical trips; S7. Count the speed and torque data of typical trips to obtain the TN count results of typical trips; S8. Based on the TN counting results of typical trips, obtain the weight of the electric drive axle transmission efficiency under the TN classification; S9. Perform finite element simulation or bench test on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under the TN classification. S10. Based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification, the comprehensive transmission efficiency of the electric drive axle is obtained.

[0022] Example 2: A schematic diagram of the system for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical passes is shown below. Figure 2 As shown, the system for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to this invention includes: The stability coefficient design module is used to acquire driving data from all users and design stability coefficients based on this data. The iterative calculation module is used to iteratively calculate the stability coefficients to obtain the minimum sample size required for the transmission efficiency spectrum of the electric drive axle. The feature parameter library establishment module is used to establish a feature parameter library based on the minimum sample size of full user driving data required for the input electric drive axle transmission efficiency spectrum in each trip. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum and calculates the feature parameters for each trip. The analysis module is used to analyze the characteristic parameters of each pass, obtain effective characteristic parameters, perform PCA dimensionality reduction on the effective characteristic parameters to obtain principal component factors, perform standardization on the principal component factors, perform cluster analysis on the principal component factors to obtain the optimal number of clusters, and determine the cluster analysis results based on the optimal number of clusters. The abnormal trip removal module is used to calculate the Euclidean distance from each trip to the cluster center based on the cluster analysis results, and remove abnormal trips based on the Euclidean distance from each trip to the cluster center. The evaluation module is used to evaluate the representativeness of the remaining trips (excluding abnormal trips) and the characteristic parameter distribution of each trip, and to identify typical trips. The counting module is used to count the speed and torque data of a typical trip to obtain the TN count result of a typical trip. The weight determination module is used to obtain the weight of the electric drive axle transmission efficiency under the TN classification based on the TN counting results of typical trips. The simulation test module is used to perform finite element simulation or bench test on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under the TN classification. The module for determining the overall transmission efficiency of the electric drive axle is used to obtain the overall transmission efficiency of the electric drive axle based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification.

[0023] Example 3: The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, as described in this invention, includes the following steps: S1. Obtain driving data from all users and design a stability coefficient based on the driving data from all users.

[0024] The formula for calculating the stability coefficient is:

[0025] in, Represents the stability coefficient. This represents the feature parameter values ​​of the sample set after adding new samples. This represents the feature parameter values ​​of the sample set before the addition of new samples. This indicates the number of feature parameters involved in the operation.

[0026] S2. Iteratively calculate the stability coefficients to obtain the minimum sample size required for the transmission efficiency spectrum of the electric drive axle.

[0027] S3. Based on the minimum sample size of full user driving data required for inputting the electric drive axle transmission efficiency spectrum per trip, establish a feature parameter library. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum, and calculate the feature parameters for each trip.

[0028] Before calculating the characteristic parameters for each trip, the full user driving data of the electric drive axle transmission efficiency spectrum with the minimum sample size is preprocessed. The preprocessing includes outlier removal, idle data removal, and resampling.

[0029] The characteristic parameters in this step include speed, absolute value of motor torque, high load ratio, speed-torque correlation, number of rapid accelerations, and number of rapid decelerations.

[0030] S4. Analyze the characteristic parameters of each pass to obtain effective characteristic parameters, reduce the dimensionality of the effective characteristic parameters to obtain principal component factors, standardize the principal component factors, perform cluster analysis on the principal component factors to obtain the optimal number of clusters, and determine the cluster analysis results based on the optimal number of clusters.

[0031] In this step, the characteristic parameters of each trip are analyzed to obtain effective characteristic parameters. Specifically, principal component analysis is used to analyze the characteristic parameters of each trip to obtain effective characteristic parameters.

[0032] S5. Based on the cluster analysis results, calculate the Euclidean distance from each pass to the cluster center, and based on the Euclidean distance from each pass to the cluster center, remove abnormal passes.

[0033] S6. Evaluate the representativeness of the remaining trips (excluding abnormal trips) and the characteristic parameter distribution of each trip to identify typical trips; This step evaluates the representativeness of the characteristic parameter distribution of the remaining trips (excluding the abnormal trips) and each trip to identify typical trips. Specifically, the dynamic time warping distance is used to evaluate the representativeness of the characteristic parameter distribution of the remaining trips (excluding the abnormal trips) and each trip to identify typical trips.

[0034] S7. Count the speed and torque data of typical trips to obtain the TN count results of typical trips.

[0035] S8. Based on the TN counting results of typical trips, obtain the weight of the electric drive axle transmission efficiency under the TN classification.

[0036] S9. Perform finite element simulation or bench test on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under the TN classification.

[0037] S10. Based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification, the comprehensive transmission efficiency of the electric drive axle is obtained.

[0038] The formula for calculating the overall transmission efficiency of an electric drive axle is:

[0039] in, For the overall transmission efficiency of the electric drive axle, The transmission efficiency of the electric drive axle under the TN classification. The weight of the electric drive axle transmission efficiency under the TN classification. The value can be 1- .

[0040] Example 4: The flowchart of the method for determining the comprehensive transmission efficiency of the electric drive axle based on characteristic parameters and typical passes in this invention is as follows: Figure 3 As shown below, the method of the present invention will be described in detail. The method for determining the comprehensive transmission efficiency of the electric drive axle based on characteristic parameters and typical passes includes the following steps: Step 1: Minimum Sample Size Analysis 1.1 When constructing the efficiency spectrum using driving data from all users, excessive computation, too much driving data from abnormal users, and too few samples all fail to accurately describe the actual operating conditions of users. Therefore, it is necessary to determine the minimum number of samples (the minimum number of samples required for the electric drive axle transmission efficiency spectrum) used in each calculation.

[0041] 1.2 Design a stability coefficient to describe the impact of adding a new sample to the original sample set on the characteristic parameters of the sample set. The formula for calculating the stability coefficient is:

[0042] in, Represents the stability coefficient. This represents the feature parameter values ​​of the sample set after adding new samples. This represents the feature parameter values ​​of the sample set before the addition of new samples. This indicates the number of feature parameters involved in the operation.

[0043] 1.3 Regarding the stability coefficient Perform iterative calculations For stability coefficient The specific process of iterative calculation is as follows: Starting with the initial sample, each time a new batch of samples is added, all feature parameter values ​​are recalculated, and then the stability coefficient is calculated according to the formula. Value. By observation The trend of value changes with increasing sample size, when When the value tends to stabilize and is less than 0.05, the sample size is considered to have met the requirements.

[0044] 1.4 Testing and Verification After testing and verifying data from multiple different vehicle models and operating areas, it was found that when the sample size reached 800 trips, the K value stabilized below 0.05, and further increasing the sample size had a negligible impact on the feature parameters. Therefore, it was determined that the sample size for each calculation should be at least 800 trips.

[0045] Step 2: Data Acquisition and Preprocessing for Each Trip 2.1 Data Acquisition The system acquires operational data (also known as driving data) from 800 trips of target users from the big data platform, including signals such as VCU_VehSpd (vehicle speed), DrivingAxle_MotSpd_ZhongQiao (middle axle speed), DrivingAxle_MotTq_ZhongQiao (middle axle torque), DrivingAxle_MotSpd_HouQiao (rear axle speed), DrivingAxle_MotTq_HouQiao (rear axle torque), DriveShaft_MotSpd (motor shaft speed), DriveShaft_MotTq (motor shaft torque), and FuelFlow (load rate).

[0046] 2.2 Trip Division In a continuous running dataset along the time dimension, if there exists a segment where the vehicle speed decreases from 0 km / h to 0 km / h, the stopping time exceeds half an hour, and the running distance exceeds ten kilometers, then these segments are divided into a new trip. All acquired data is iterated through, and based on the vehicle's running and stopping time information, the data is divided into several trips.

[0047] 2.3 Data Preprocessing (1) Outlier removal: The 3σ criterion is used to detect outliers in the collected data (speed data and torque data). For each data feature, its mean and standard deviation are calculated, and outliers exceeding the standard deviation are removed. Data within the specified range is identified as outliers and removed.

[0048] (2) Idle data removal: When the vehicle speed is below 0.1 km / h and the duration exceeds 10 seconds, it is judged as an idle state and removed.

[0049] (3) Resampling: The data is uniformly resampled to 1Hz using a linear interpolation method so that all data have a uniform time interval.

[0050] Step 3: Exception removal and feature parameter library construction 3.1 Construct a complete feature library containing 95 feature parameters, mainly divided into four categories: Time-related feature parameters (23) Running time, running distance, running speed, acceleration time, deceleration time, constant speed time, idling time, acceleration time ratio, deceleration time ratio, constant speed time ratio, idling time ratio, etc.

[0051] Vehicle speed and engine speed related characteristic parameters (32) Maximum speed, average speed, operating speed, speed standard deviation, maximum rotational speed, average rotational speed, rotational speed standard deviation, average acceleration during acceleration, average deceleration during deceleration, maximum acceleration, maximum deceleration, and standard deviation of absolute acceleration, etc.

[0052] Torque-related characteristic parameters (25) Maximum positive torque, average positive torque, torque standard deviation, average absolute value of motor torque, maximum absolute value of motor torque, standard deviation of absolute value of motor torque, high load ratio, speed-torque correlation, etc.

[0053] Load factor related characteristic parameters (15) Maximum load factor, average load factor, energy consumption per 100 kilometers, sum of load factors, sum of the squares of load factors, etc.

[0054] 3.2 Calculate the characteristic parameters for each trip The characteristic parameters include speed, absolute value of motor torque, high load percentage, speed-torque correlation, number of rapid accelerations, and number of rapid decelerations. The calculation formulas for each characteristic parameter are as follows: Average speed:

[0055] in, For average speed, For the first The velocity value at each sampling point This represents the total number of sampling points.

[0056] Maximum speed across all sampling points:

[0057] in, The maximum speed among all sampling points. For the first The velocity value of each sampling point.

[0058] Standard deviation of velocity:

[0059] in, The standard deviation of the velocity, For the first The velocity value at each sampling point For average speed, This represents the total number of sampling points.

[0060] Average absolute value of motor torque:

[0061] in, It is the average value of the absolute value of the motor torque (also called the average absolute value of the motor torque). For the first Motor torque at each sampling point This represents the total number of sampling points.

[0062] Maximum absolute value of motor torque:

[0063] in, This is the maximum absolute value of the motor torque among all sampling points (also called the maximum absolute value of the motor torque). For the first Motor torque at each sampling point.

[0064] Standard deviation of the absolute value of motor torque:

[0065] in, The standard deviation of the absolute value of the motor torque. For the first Motor torque at each sampling point The average value of the absolute value of the motor torque. This represents the total number of sampling points.

[0066] High load percentage:

[0067] in, The proportion of sampling points where the motor torque exceeds 0.8 times the maximum torque out of the total sampling points (also called high load proportion). This represents the number of sampling points where the motor torque is greater than 0.8 times the maximum torque. This represents the total number of sampling points.

[0068] Speed-torque correlation: ; in, It is the correlation coefficient between the absolute values ​​of speed and torque (also called speed-torque correlation). For the first The speed of each sampling point For average speed, For the first Motor torque at each sampling point The average value of the absolute value of the motor torque. This represents the total number of sampling points.

[0069] Number of rapid accelerations per kilometer:

[0070] in, The number of rapid accelerations per kilometer. This represents the number of sampling points with an acceleration greater than 1.5 m / s². This represents the total mileage traveled.

[0071] Number of times of sudden deceleration per kilometer:

[0072] in, The number of times of sudden deceleration occurs per kilometer. The number of sampling points with deceleration less than -1.5 m / s². This represents the total mileage traveled.

[0073] 3.3 Feature Parameter Verification A dual verification mechanism of independent calculation and iterative calculation is adopted. Independent calculation refers to directly calculating feature parameters from multiple batches of merged data; iterative calculation refers to calculating feature parameters separately for each batch and then summing them to obtain the feature parameters for the merged batch. When the error between the two methods exceeds 5%, the calculation is recalculated and the data quality is checked. The flowchart for feature parameter verification is as follows. Figure 4 As shown.

[0074] Step 4: Effective acquisition of feature parameters and principal component analysis 4.1 Effective feature parameter acquisition The characteristic parameters of each pass were analyzed using Principal Component Analysis (PCA) to obtain effective characteristic parameters, and a cumulative contribution threshold was set. =0.85, retaining the top 85% of feature parameters based on cumulative contribution. The specific process for analyzing the feature parameters for each trip includes: Standardize the feature matrix:

[0075] in, The original feature matrix, The mean of each feature (the 12 principal component factors obtained from PCA dimensionality reduction), The standard deviation for each feature, This is the standardized feature matrix.

[0076] Calculate the covariance matrix:

[0077] in, The standardized feature matrix, For the sample size, for transpose, Let be the covariance matrix.

[0078] Eigenvalue decomposition:

[0079] in, Let covariance matrix be the variance matrix. This is an eigenvector matrix, where each column represents an eigenvector, i.e., a principal component direction. It is a diagonal matrix, and the diagonal elements are eigenvalues. , for The transpose of .

[0080] Calculate the contribution of each principal component:

[0081] in, For the first The contribution of each principal component For the first The eigenvalue, corresponding to the eigenvalue ... i.e. the The variance of each principal component.

[0082] Set threshold Then select the smallest one. Make:

[0083] in, It represents the number of principal components retained.

[0084] 4.2 Using principal component analysis, 71 effective feature parameters were selected from the original 95 feature parameters. The cumulative contribution of these parameters reached more than 85%.

[0085] 4.3 PCA dimensionality reduction: PCA dimensionality reduction is performed on the selected feature matrix, retaining 12 principal component factors to obtain a 71×12 matrix.

[0086] Step 5: Cluster Analysis and Outlier Removal 5.1 Data Standardization Processing The 12 principal component factors after PCA dimensionality reduction were standardized:

[0087] in, The principal component factor matrix obtained after dimensionality reduction by PCA. Main component factor The mean vector (length is) ), Main component factor The standard deviation vector (length is) ).

[0088] 5.2 Determining the Optimal Number of Clusters The Calinski-Harabasz index is used to determine the optimal number of clusters. The calculation formula is as follows:

[0089] in, For inter-class variance, , For within-class variance, , The total number of samples, This represents the number of clusters.

[0090] By calculating the CH values ​​of k from 2 to 20, the one with the largest CH value is selected. =4 is considered the optimal number of clusters.

[0091] 5.3K-Means Cluster Analysis Clustering is performed using the K-Means algorithm, with the following parameters set: Distance metric: city block distance; Number of repetitions: 10,000; Initialization method: k-means++; Clustering objective function:

[0092] The flowcharts for Step 4 (Principal Component Analysis) and Step 5 (Cluster Analysis) are as follows: Figure 5 As shown.

[0093] 5.4 Removal of Abnormal Trips First, calculate the Euclidean distance to the cluster center for each pass, using the following formula:

[0094] in, For the first Each trip's Euclidean distance to its respective cluster center The feature dimension is the number of principal components retained after dimensionality reduction. For the first The first trip Values ​​on each feature For the first In the nth pass, at the cluster center to which cluster number c belongs... The value on each feature.

[0095] Then, based on the Euclidean distance from each pass to the cluster center, outlier passes are removed. Specifically, at most 60% of the passes sorted by the shortest distance to the cluster center are removed. The quantile map of the passes to be removed determined by this invention is shown below. Figure 6 As shown.

[0096] 6. Determine typical trips The representativeness of the characteristic parameter distribution of the remaining trips (excluding the abnormal trips) and each trip is evaluated by using the Dynamic Time Warping (DTW) distance, and typical trips are identified.

[0097] The DTW distance calculation process is as follows: The feature parameter sequence is normalized using a min-max method to obtain the normalized sequence. The calculation formula is as follows:

[0098] The normalized sequences are sorted, and the DTW distance of the feature parameter distributions before and after screening is calculated.

[0099] The recursive formula for DTW is:

[0100] Step 7: Construction of the transmission efficiency spectrum of the electric drive axle 7.1 Divide the speed-torque plane into 128×128 grids and calculate the loading frequency of each grid using the following formula:

[0101] in, Let i be the loading frequency in the speed-torque range of the i-th row and j-th column. This represents the number of data segments within the specified interval. For the time interval of the k-th segment, This represents the rotational speed at time t (unit: r / s).

[0102] (1) The speed range [0, 3000] rpm and the torque range [-2000, 2000] N·m are uniformly divided into 128×128 grids; (2) Determine the grid affiliation of the speed-torque time series data for each representative trip; (3) Calculate the time integral value within each grid; (4) Overlay the TN count results of all representative trips.

[0103] 7.2 Statistical efficiency spectrum histogram, showing the frequency of occurrence of each operating point, yields the frequency spectrum of TN. The sum of all items in the matrix of this frequency spectrum gives the total frequency N, and the weight under this TN level is obtained. The calculation formula is:

[0104] 7.3 Efficiency Spectrum Construction: The TN count results for all representative trips are statistically analyzed to generate a 128×128 efficiency spectrum statistical cloud map. Based on the efficiency spectrum statistical cloud map, an efficiency spectrum statistical histogram is plotted. The statistical histogram is shown below. Figure 7 As shown, the probability distribution of each operating point is calculated to obtain the speed and torque distribution operating points and the corresponding frequency proportions, which is the representative efficiency spectrum of all users.

[0105] Step 8: Determining the overall transmission efficiency of the electric drive axle 8.1 Finite Element Simulation Experiment Based on the TN classification corresponding to the 128×128 efficiency spectrum under different T-N values, the transmission efficiency of the electric drive axle under different TN classifications was obtained using finite element simulation software. .

[0106] 8.2 Bench Test Due to limitations in bench testing conditions, it is difficult to directly construct and test a complete mapping consisting of 128×128 fine-grained operating points. Therefore, the 128×128 matrix is ​​divided into blocks and aggregated, and the value of each 8×8 block is calculated to obtain an 8×8 bench spectrum, as shown below. Figure 8 As shown.

[0107] The 128×128 matrix is ​​divided into blocks and aggregated. The value of each 8×8 block is calculated to obtain an 8×8 pedestal spectrum. The specific process is as follows: For each 8×8 target block :

[0108] in, Each target block corresponds to 16×16 original grids.

[0109] Bench tests were conducted on the test bench to obtain the transmission efficiency of the electric drive axle under the TN classification. .

[0110] 8.3 Calculate the overall transmission efficiency of the electric drive axle The transmission efficiency of the electric drive axle simulated under TN classification. The representative efficiency spectrum of all users obtained above Alternatively, the overall transmission efficiency of the electric drive axle can be obtained by weighted summation of the corresponding positions of the electric drive axle transmission efficiency under the TN classification obtained from bench tests and bench spectra.

[0111] The formula for calculating the overall transmission efficiency of an electric drive axle is:

[0112] in, For the overall transmission efficiency of the electric drive axle, The transmission efficiency of the electric drive axle under the TN classification. The weight of the electric drive axle transmission efficiency under the TN classification. The value can be 1- .

[0113] Compared with the prior art, the present invention has the following beneficial effects: A. Improve the engineering applicability and scenario fit of the method by analyzing the minimum sample size based on convergence of pass characteristics.

[0114] Unlike traditional methods that use unordered segmentation based on fixed calendar cycles, such as monthly or weekly data, this invention pioneers a method using "trips" as the basic unit of analysis. This precisely aligns with the actual business logic of freight trucks completing a full transportation task from start to finish. This segmentation clearly and naturally expresses the load status, driving area, and driving style of each trip, ensuring a high degree of consistency between the work condition segmentation and real-world application scenarios. Furthermore, this invention introduces a stability coefficient K for feature convergence analysis, scientifically determining the minimum sample size (e.g., 800 trips) required to construct an effective efficiency spectrum. The advantages of this mechanism are twofold: firstly, it ensures that the constructed efficiency spectrum possesses sufficient statistical representativeness and stability, avoiding random bias caused by insufficient sample size; secondly, it provides clear guidance for cost and resource control in engineering practice, significantly reducing data collection and computation costs while maintaining accuracy, thereby promoting rapid adoption and engineering application in the commercial vehicle industry.

[0115] B. Improve the representativeness and accuracy of efficiency spectrum construction by combining feature identification (also called feature parameters) with typical passes.

[0116] Traditional methods process massive amounts of heterogeneous data in a mixed manner, leading to distorted efficiency spectra and low computational efficiency. This invention employs PCA and cluster analysis to perform fine-grained deconstruction of complex user operating conditions, achieving multi-dimensional and accurate identification of operational characteristics. Building upon this, a representative pass selection mechanism based on Dynamic Time Warping (DTW) distance is introduced to intelligently identify and remove outliers that deviate from the main characteristics, ensuring the purity and representativeness of the input data. This dual mechanism of feature identification and typical pass selection not only transforms the constructed efficiency spectrum from a traditional fuzzy average to a precise spectrum that clearly reflects the true efficiency characteristics of different user groups, but also reduces data processing volume by more than 60% and improves computational efficiency by over 70% by focusing on typical passes and using PCA dimensionality reduction.

[0117] C. The high-reliability, strongly correlated comprehensive transmission efficiency is determined by integrating the efficiency counting matrix with high-precision testing.

[0118] This invention abandons the traditional method of separating efficiency spectrum and load spectrum processing, and innovatively integrates and weights the TN counting matrix, which represents the user's actual driving habits, with the actual transmission efficiency, which reflects the physical characteristics of the transmission system. The TN counting matrix accurately captures the speed-torque distribution characteristics of the user in actual driving, while finite element simulation software tests or bench tests reveal the intrinsic efficiency characteristics of the transmission system at various operating points based on high-precision simulation. The integration of the two makes the final generated comprehensive transmission efficiency of the electric drive axle both behaviorally representative and physically realistic. It not only reflects what users frequently use, but also the actual response of the transmission system, thus faithfully reproducing the energy efficiency performance of actual roads and providing an unprecedented data foundation for precise efficiency optimization and reliability verification of the transmission system.

[0119] Example 5: Please see Figure 9 As shown, the present invention also provides an electronic device 100 for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0120] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for determining the comprehensive transmission efficiency of the electric drive axle based on characteristic parameters and typical passes as described in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0121] The at least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100, connecting various parts of the electronic device 100 via various interfaces and lines.

[0122] The memory 101 in the electronic device 100 stores multiple instructions to implement a method for determining the comprehensive transmission efficiency of the electric drive axle based on characteristic parameters and typical passes. The processor 102 can execute the multiple instructions to achieve the following: Obtain driving data from all users and design a stability coefficient based on this data. The minimum sample size required to obtain the transmission efficiency spectrum of the electric drive axle is obtained by iteratively calculating the stability coefficient. A feature parameter library is established based on the minimum sample size of full user driving data required for inputting the electric drive axle transmission efficiency spectrum per trip. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum, and the feature parameters for each trip are calculated. The characteristic parameters of each pass are analyzed to obtain effective characteristic parameters. The effective characteristic parameters are then dimensionality reduced to obtain principal component factors. After standardization of the principal component factors, cluster analysis is performed on the principal component factors to obtain the optimal number of clusters. Based on the optimal number of clusters, the cluster analysis results are determined. Based on the cluster analysis results, the Euclidean distance from each trip to the cluster center is calculated, and abnormal trips are removed based on the Euclidean distance from each trip to the cluster center. The representativeness of the characteristic parameter distribution of the remaining trips (excluding the abnormal trips) and each trip is evaluated to identify the typical trips. The speed and torque data of a typical trip are counted to obtain the TN count result of the typical trip; Based on the TN counting results of typical trips, the weight of the electric drive axle transmission efficiency under the TN classification is obtained; Finite element simulation or bench test was performed on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under TN classification. The comprehensive transmission efficiency of the electric drive axle is obtained based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification.

[0123] Example 6: If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0124] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0126] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, characterized in that, Includes the following steps: Obtain driving data from all users and design a stability coefficient based on this data. The minimum sample size required to obtain the transmission efficiency spectrum of the electric drive axle is obtained by iteratively calculating the stability coefficient. A feature parameter library is established based on the minimum sample size of full user driving data required for inputting the electric drive axle transmission efficiency spectrum per trip. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum, and the feature parameters for each trip are calculated. The characteristic parameters of each pass are analyzed to obtain effective characteristic parameters. The effective characteristic parameters are then dimensionality reduced to obtain principal component factors. After standardization of the principal component factors, cluster analysis is performed on the principal component factors to obtain the optimal number of clusters. Based on the optimal number of clusters, the cluster analysis results are determined. Based on the cluster analysis results, the Euclidean distance from each trip to the cluster center is calculated, and abnormal trips are removed based on the Euclidean distance from each trip to the cluster center. The representativeness of the characteristic parameter distribution of the remaining trips (excluding the abnormal trips) and each trip is evaluated to identify the typical trips. The speed and torque data of a typical trip are counted to obtain the TN count results for a typical trip; Based on the TN counting results of typical trips, the weight of the electric drive axle transmission efficiency under the TN classification is obtained; Finite element simulation or bench test was performed on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under TN classification. The comprehensive transmission efficiency of the electric drive axle is obtained based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification.

2. The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to claim 1, characterized in that, The formula for calculating the stability coefficient is as follows: in, Represents the stability coefficient. This represents the feature parameter values ​​of the sample set after adding new samples. This represents the feature parameter values ​​of the sample set before the addition of new samples. This indicates the number of feature parameters involved in the operation.

3. The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to claim 1, characterized in that, Before calculating the characteristic parameters for each trip, the full user driving data of the electric drive axle transmission efficiency spectrum with the minimum sample size is preprocessed. The preprocessing includes outlier removal, idle data removal, and resampling.

4. The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to claim 1, characterized in that, The characteristic parameters include speed, absolute value of motor torque, high load ratio, speed-torque correlation, number of rapid accelerations, and number of rapid decelerations.

5. The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to claim 1, characterized in that, The process of analyzing the characteristic parameters of each trip to obtain effective characteristic parameters specifically involves using principal component analysis to analyze the characteristic parameters of each trip and obtain effective characteristic parameters.

6. The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to claim 1, characterized in that, The evaluation of the representativeness of the characteristic parameter distribution of the remaining trips (excluding abnormal trips) and each trip, and the determination of typical trips, specifically involves using dynamic time warping distance to evaluate the representativeness of the characteristic parameter distribution of the remaining trips (excluding abnormal trips) and each trip, and determining typical trips.

7. The method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips according to claim 1, characterized in that, The formula for calculating the overall transmission efficiency of the electric drive axle is as follows: in, For the overall transmission efficiency of the electric drive axle, The transmission efficiency of the electric drive axle under the TN classification. The weight of the electric drive axle transmission efficiency under the TN classification. The value can be 1- .

8. A system for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical trips, characterized in that, include: The stability coefficient design module is used to acquire driving data from all users and design stability coefficients based on this data. The iterative calculation module is used to iteratively calculate the stability coefficients to obtain the minimum sample size required for the transmission efficiency spectrum of the electric drive axle. The feature parameter library establishment module is used to establish a feature parameter library based on the minimum sample size of full user driving data required for the input electric drive axle transmission efficiency spectrum in each trip. The feature parameter library includes the feature parameters used to construct the electric drive axle transmission efficiency spectrum and calculates the feature parameters for each trip. The analysis module is used to analyze the characteristic parameters of each pass, obtain effective characteristic parameters, perform PCA dimensionality reduction on the effective characteristic parameters to obtain principal component factors, perform standardization on the principal component factors, perform cluster analysis on the principal component factors to obtain the optimal number of clusters, and determine the cluster analysis results based on the optimal number of clusters. The abnormal trip removal module is used to calculate the Euclidean distance from each trip to the cluster center based on the cluster analysis results, and remove abnormal trips based on the Euclidean distance from each trip to the cluster center. The evaluation module is used to evaluate the representativeness of the remaining trips (excluding abnormal trips) and the characteristic parameter distribution of each trip, and to identify typical trips. The counting module is used to count the speed and torque data of a typical trip to obtain the TN count result of a typical trip. The weight determination module is used to obtain the weight of the electric drive axle transmission efficiency under the TN classification based on the TN counting results of typical trips. The simulation test module is used to perform finite element simulation or bench test on the TN count results of typical trips to obtain the transmission efficiency of the electric drive axle under the TN classification. The module for determining the overall transmission efficiency of the electric drive axle is used to obtain the overall transmission efficiency of the electric drive axle based on the weight of the electric drive axle transmission efficiency under the TN classification and the electric drive axle transmission efficiency under the TN classification.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical passes, as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for determining the comprehensive transmission efficiency of an electric drive axle based on characteristic parameters and typical passes, as described in any one of claims 1 to 7.

Images