Operation truck driving process analysis method and device and computer storage medium

Abstract

The embodiment of the invention discloses a running process analysis method and device of a commercial truck and a computer storage medium. The method comprises the steps that running data of multiple short travels in the running process are acquired; the driving data comprises the speed of the operating truck and the rotating speed of an engine; determining at least one working condition included in the short stroke according to the speed and the rotating speed of the engine; deleting data with the engine rotating speed smaller than a vehicle operation rotating speed threshold value from the driving data with the working condition being the idling working condition to obtain target driving data; and carrying out driving process analysis based on the target driving data of the plurality of short strokes to obtain an analysis result.

Description

Technical Field

[0001] The present application relates to the field of traffic driving, and in particular to a driving process analysis method and device for an operating truck, and a computer storage medium. Background Art

[0002] At present, the analysis of the vehicle driving process can reflect the actual driving characteristics of the vehicle on the road, and plays an important role in vehicle energy conservation and emission reduction. Among them, the short-trip method is usually used when constructing the working condition, and the vehicle's driving journey is divided into multiple short trips for analysis. Short trips are usually divided by speed. For example, from one idle start to the next idle start, a short trip represents a driving process of the vehicle. However, operating trucks need to operate in an idle state. The short trips divided by speed will include the operating state of the operating truck, rather than the driving state; this will cause the analysis results of the driving process to be inaccurate. Summary of the invention

[0003] The embodiments of the present application provide a method and device for analyzing the driving process of an operating truck, and a computer storage medium, which can improve the accuracy of the analysis results of the driving process of an operating truck.

[0004] The technical solution of this application is implemented as follows:

[0005] The present application embodiment provides a method for analyzing the driving process of an operating truck, including:

[0006] Acquire driving data of multiple short trips during the driving process; the driving data includes the speed and engine speed of the operating truck; determine at least one operating condition included in the short trip based on the speed and the engine speed; the at least one operating condition includes an idle condition; from the driving data of the idle condition, delete the data in which the engine speed is less than a threshold value of the vehicle operating speed to obtain target driving data; analyze the driving process based on the target driving data of the multiple short trips to obtain analysis results.

[0007] The embodiment of the present application provides a driving process analysis device for an operating truck, comprising:

[0008] An acquisition module, used to acquire driving data of a plurality of short trips during the driving process; the driving data includes the speed and engine speed of the operating truck;

[0009] A determination module, configured to determine at least one operating condition included in the short stroke according to the speed and the engine speed; the at least one operating condition includes an idle operating condition;

[0010] A deleting module, used to delete the data of the engine speed being less than the vehicle operating speed threshold from the driving data of the idle condition, so as to obtain target driving data;

[0011] The analysis module is used to analyze the driving process based on the target driving data of the multiple short trips to obtain analysis results.

[0012] The embodiment of the present application provides a driving process analysis device for an operating truck, comprising:

[0013] Memory for storing computer programs;

[0014] The processor is used to implement the steps of the above-mentioned operating truck driving process analysis method when executing the computer program stored in the memory.

[0015] An embodiment of the present application provides a computing and storage medium, wherein the storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement the steps of the above-mentioned operating truck driving process analysis method.

[0016] The embodiments of the present application provide a method and device for analyzing the driving process of an operating truck, and a computer storage medium. Since the short-trip driving data obtained by the analysis device includes the vehicle speed and the engine speed, after at least one operating condition is determined by the speed and the engine speed, the data in which the engine speed is less than the vehicle speed threshold can be deleted when the operating condition is an idle condition. In this way, the target driving data does not include the operating status of the operating truck, and the driving process analysis is performed based on the target driving data, which can improve the accuracy of the analysis of the driving process of the operating truck. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of an optional method for analyzing the driving process of an operating truck provided in an embodiment of the present application;

[0018] Figure 2 A schematic flow chart of an optional method for analyzing the driving process of an operating truck provided in an embodiment of the present application;

[0019] Figure 3 A schematic flow chart of an optional method for analyzing the driving process of an operating truck provided in an embodiment of the present application;

[0020] Figure 4 A schematic diagram of the structure of an optional driving process analysis device for an operating truck provided in an embodiment of the present application;

[0021] Figure 5 A schematic structural diagram of an optional operating truck driving process analysis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0023] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0024] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0026] In order to illustrate the technical solution of the embodiment of the present application, the technical background is first described below:

[0027] With the continuous development of the transportation industry, the demand for cargo transportation has also increased, resulting in excessive fuel consumption and emissions, causing energy shortages and air pollution. In particular, the high cost of commercial truck fuel consumption has led to how to reduce the fuel consumption of operating trucks. This has become an urgent problem to solve, so that drivers of operating vehicles can correct their driving behavior based on the predicted fuel consumption and establish more fuel-efficient driving habits. This can also monitor the future fuel consumption trends of operating vehicles and provide strong guidance for strengthening the industry management and operation of operating trucks, making the research on vehicle fuel consumption prediction more practical. In recent years, with the development of Internet of Vehicles technology, a large amount of vehicle operating status data can be collected by on-board sensors and concentrated on the Internet of Vehicles platform. The data is large in scale, contains many attributes and has strong time series. At present, vehicle fuel consumption prediction is usually predicted based on the analysis of the vehicle driving process, and the analysis of the vehicle driving process requires the driving process to be divided into short trips and analyzed. A short trip is from the start of one idle to the start of the next idle, representing a vehicle driving process. However, commercial trucks need to operate in an idling state, and the short trip divided by speed will include the operating state of the commercial truck rather than the driving state; thus, the analysis results of the driving process will be inaccurate.

[0028] The embodiment of the present application provides a method and device for analyzing the driving process of an operating truck, and a computer storage medium, which takes into account the situation that the operating truck operates at idle speed, improves the accuracy of short-trip division, and thus improves the accuracy of the driving process analysis. The following describes an exemplary application of the driving process analysis device for an operating truck provided in the embodiment of the present application (hereinafter described as an analysis device), which can be implemented as various types of electronic devices such as laptop computers, tablet computers, desktop computers, mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices, smart watches), etc.

[0029] Figure 1 An exemplary method for analyzing the driving process of an operating truck provided in an embodiment of the present application is shown, and the method may include: S101-S104.

[0030] S101. Acquire driving data of a plurality of short trips during driving; the driving data includes the speed and engine speed of the operating truck.

[0031] In an embodiment of the present application, an operating truck may include at least any one of the following: a truck, a tractor, a dump truck, a concrete mixer truck, etc.; an operating truck is not necessarily in a driving state when idling, but may also be in an operating state, for example, cargo loading, concrete mixing, etc.

[0032] In the embodiment of the present application, any operating truck can collect raw driving data during driving, wherein the raw driving data may include: speed and engine speed. Considering that operating trucks usually face complex traffic conditions during actual driving, the raw driving data is also constantly changing. In some embodiments, the raw driving data may also include: torque percentage, instantaneous fuel consumption, coolant temperature, engine load percentage and intake flow, etc.; this can be set according to actual needs, and the embodiment of the present application does not impose any restrictions. These driving data can be used to analyze the driving process of the vehicle, such as whether it is driving on a congested road section, or whether the driving road is a mountain road or a city road, etc.

[0033] In the embodiment of the present application, since the amount of original driving data collected is large, the collection process requires communication with the operating truck, and communication abnormalities may cause some data to be abnormal or missing, so the original driving data needs to be deleted, corrected or interpolated.

[0034] Exemplarily, if the speed of consecutive sampling points is in an increasing trend, and one of the sampling points has a speed of 0, then the point can be determined to be an outlier. The analysis device can directly delete or correct the point. In some embodiments, if the proportion of outliers in all sampling points is less than or equal to the deletion ratio threshold, the analysis device can delete the outliers, which will not cause a decrease in data quality; wherein the deletion ratio threshold can be set according to actual needs, and the embodiments of the present application are not limited. For example, the deletion ratio threshold can be 0.5%. If the proportion of outliers in all sampling points is greater than the deletion ratio threshold, the analysis device can predict the driving data of the outlier based on the adjacent sampling points of the outlier, obtain the predicted value, and use the predicted value to replace the value of the outlier, thereby improving the accuracy of the data. In some embodiments, the analysis device can use the pandas library function to delete outliers, the code is data.dropna(axis=0, how="any").

[0035] It should be noted that, since the data of various operating trucks may be collected and provided by various manufacturers, the data formats may be different when collected by each manufacturer, and the analysis device needs to convert the format of the same original driving data into a standard format.

[0036] In some embodiments, the format of the driving data includes units. For example, the units of speed are kilometers per hour (km / h) or meters per second (m / s), etc. This can be set according to actual needs and is not limited in the embodiments of the present application.

[0037] For example, Table 1 shows the original driving data of the standard format of the operating truck as a common cargo vehicle. The original data format of the common cargo vehicle is sampled once every 1 second, and Table 1 shows the original driving data of three consecutive sampling points.

[0038] Table 1 Original driving data

[0039]

[0040]

[0041] In the embodiment of the present application, the driving process of the commercial truck may last for a long time, such as one day, one week, one transportation cycle, etc. The analysis device may divide the driving process into a plurality of short trips according to the speed, and each short trip represents a movement of the vehicle.

[0042] In some embodiments, a short stroke may start from a state where the speed is 0 and end at a next state where the speed is 0. In some embodiments, a short stroke may start from a state where the engine speed is 0 and end at a next state where the engine speed is 0.

[0043] S102: Determine at least one operating condition included in the short stroke according to the speed and the engine speed.

[0044] In the embodiment of the present application, the operating truck usually has a low speed in the working state and a high engine speed, while in the driving state, the speed is high and the engine speed is not too high. The analysis device needs to delete the data in the working state from the driving data of the short trip, so as to obtain the target driving data in the driving state.

[0045] In an embodiment of the present application, the analysis device can determine various operating conditions that meet the operating condition classification conditions from a short stroke based on the speed and engine speed. Among them, the operating condition classification conditions include: if the acceleration is greater than or equal to the speed change threshold (positive value), and is not equal to 0, it is an acceleration condition; if the acceleration is less than or equal to the negative speed change threshold, and is not equal to 0, it is a deceleration condition; if the absolute value of the acceleration is less than the speed change threshold, and is not equal to 0, it is a uniform speed condition; if the speed is 0 and the engine speed is not 0, it is an idle condition. Among them, the speed change threshold can be set according to actual needs, and the embodiment of the present application does not limit it. It should be noted that each operating condition is a continuous process, which requires data from multiple sampling points to be determined; the data from a single sampling point does not constitute an operating condition.

[0046] In some embodiments, the speed change threshold is 0.15 m / s 2 .

[0047] In some embodiments of the present application, the short stroke may include multiple sampling points, and the analysis device may determine multiple accelerations according to the speeds of the multiple sampling points.

[0048] For example, the short trip includes m sampling points, and the speed of the i-th sampling point is v i(m-1≥i≥1, i is a positive integer), the velocity of the i+1th sampling point is v i+1 The analysis device can obtain m-1 accelerations a according to formula (1): i，i+1 .

[0049]

[0050] Among them, t i is the sampling time of the ith sampling point, t i+1 is the sampling time of the i+1th sampling point.

[0051] If the speed in the short-distance driving data is km / h, the sampling time is s, and the acceleration is m / s 2 , then formula (1) can be expressed as formula (2).

[0052]

[0053] Where n is the acquisition frequency in units (per second).

[0054] In the embodiment of the present application, the analysis device determines the m-1 accelerations a of the short stroke. i，i+1 Afterwards, various operating conditions in the short stroke can be determined based on acceleration, speed, engine speed and operating condition classification conditions.

[0055] For example, m is 5, each sampling point has a velocity, and 5 velocities determine 4 accelerations a. 1,2 、a 2，3 、a 3，4 and a 4，5 , where a 1，2 and a 2，3 Greater than the speed change threshold of 0.15m / s 2 , the working condition is the acceleration condition; a 1，2 and a 2，3 The absolute value is less than the speed change threshold of 0.15m / s 2 , the working condition is uniform speed condition.

[0056] S103 . Delete data in which the engine speed is less than the vehicle operating speed threshold from the driving data in the idling condition, to obtain target driving data.

[0057] In some embodiments, the analysis device can determine that the state where the speed is less than the idle threshold and the engine speed is higher than the vehicle operating speed threshold is the operating state. The idle threshold and the vehicle operating speed threshold can be set according to actual needs, and the embodiments of the present application do not limit this.

[0058] In some embodiments, the idle threshold may be 5 km / h.

[0059] In some embodiments, different types of commercial trucks may set different vehicle operating speed thresholds according to actual conditions during operation.

[0060] In some embodiments, the vehicle operating speed threshold may be 800 r / min.

[0061] In some embodiments, the greater the gross mass of the operating truck, the greater the vehicle operating speed threshold.

[0062] In the embodiment of the present application, for any type of commercial truck, the greater the total mass, the higher the tonnage level, and the greater the engine speed required during operation. Therefore, the vehicle operating speed threshold also needs to be set larger, thereby reducing the data of the operating status of the commercial vehicle in the target driving data and improving the accuracy of the target driving data.

[0063] In some embodiments, the analysis device may also determine the corresponding vehicle operating speed threshold value based on the total mass, torque and air intake of the operating truck. Here, the analysis device may be provided with a correspondence between the vehicle parameters of the operating truck and the vehicle operating speed threshold value; thus, for any operating truck determined by the vehicle parameters, the analysis device may determine the corresponding vehicle operating speed threshold value.

[0064] In the embodiment of the present application, the analysis device can delete the driving data in the idle state where the engine speed is less than the vehicle operating speed threshold to obtain the target driving data. In this way, the target driving data does not include the driving data in the operating state of the operating truck.

[0065] S104: Analyze the driving process based on the target driving data of multiple short trips to obtain analysis results.

[0066] In the embodiment of the present application, after obtaining multiple short-trip target driving data, the analysis device can perform data conversion on each short-trip target driving data to obtain driving characteristic data. The driving characteristic data is used to characterize various traffic information in the original driving data, including hidden information such as the traffic conditions of the road and the driving habits of the driver, so that the operating conditions of the constructed operating truck are more in line with the actual operating conditions.

[0067] In the embodiment of the present application, the driving characteristic data may include the maximum value, mean value, standard deviation and various distribution ratios of speed, acceleration and engine speed. This can be set as needed, and the embodiment of the present application does not limit it. In some embodiments, the analysis device can convert the speed into speed characteristic data, and use the speed characteristic data as the driving characteristic data.

[0068] Exemplarily, the extreme values ​​of speed may include a maximum speed and a minimum speed, the mean of speed may include an average speed and a running average speed, and various distribution ratios of speed may include: a uniform speed distribution ratio of a speed less than 25 km / h, a uniform speed distribution ratio of a speed greater than 25 km / h, etc.

[0069] In some embodiments, the analysis device can perform dimensionality reduction processing on multiple driving characteristic data of a short trip to obtain at least one high-characteristic data. The number of high-characteristic data is less than the number of driving characteristic data. Here, the dimensionality reduction processing method may include any one of the following: Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), t-distributed Stochastic Neighbor Embedding (t-SNE), Locally Linear Embedding (LLE), Multidimensional Scaling (MDS), Singular Value Decomposition (SVD), etc.; in this regard, it can be set according to actual needs, and the embodiments of the present application are not limited.

[0070] In an embodiment of the present application, the analysis device can perform clustering based on high-feature data, and classify short trips with the same driving characteristics into one category. Here, the clustering method can be a hierarchical clustering method, a mean shift clustering method, a fuzzy clustering method, a K-means algorithm, a density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) algorithm, etc., which can be set as needed and are not limited in the embodiment of the present application. Then, based on the similar features of each category, the driving status of the operating truck is determined. For example, a certain type of short trip is the driving status of an operating truck on a highway, or the driving status in a congested area of ​​a city road, etc.

[0071] It can be understood that since the short-trip driving data obtained by the analysis device includes the vehicle speed and engine speed, the driving data under the driving state of the operating truck is filtered out together with the speed and engine speed as the target driving data; in this way, the target driving data does not include the operating status of the operating truck, and the driving process analysis based on the target driving data can improve the accuracy of the analysis of the driving process of the operating truck.

[0072] In some embodiments of the present application, the driving data of multiple short trips during driving in S101 is obtained, for example: Figure 2 As shown, it may include: S201-S202.

[0073] S201. Divide the driving process into a plurality of short trips according to original driving data during the driving process.

[0074] In an embodiment of the present application, the analysis device may divide the driving process into a plurality of short trips according to the speed, or divide the driving process into a plurality of short trips according to the engine speed.

[0075] S202 , selecting original driving data satisfying effective analysis conditions from a plurality of original driving data of short trips to obtain a plurality of driving data of short trips.

[0076] In an embodiment of the present application, the original driving data that meets the effective analysis conditions is used to characterize the effective driving data of an effective short trip. It should be noted that if the duration of the short trip is too short, or the driving distance is short, and the vehicle fails to operate effectively, then the contribution to the analysis of the driving process is small and can be ignored. If the speed of the short trip is too high and exceeds the maximum speed that the operating truck can actually reach during driving, it is also regarded as an invalid short trip and is not analyzed. The original driving data may contain data that does not conform to the actual driving conditions. This data may be caused by communication anomalies and is erroneous driving data, which will cause analysis errors in the driving process. These short trips and original driving data can be deleted to improve the accuracy of the driving data.

[0077] In some embodiments, the effective short trip includes at least one of the following: a short trip with a duration greater than a short trip duration threshold; a short trip with a maximum speed greater than a maximum speed threshold. Effective driving data includes: an absolute value of acceleration less than an effective acceleration threshold; when the duration of idling is greater than or equal to the idle duration threshold, the preset effective duration in the duration is used as the actual duration of the idle condition. Among them, the maximum speed threshold, the short trip duration threshold, the idle duration threshold, any effective duration, and the effective acceleration threshold can be set as needed, and the embodiments of the present application are not limited.

[0078] In some embodiments, the maximum speed threshold may be 3.6 km / h; the short trip time threshold may be 10 seconds; the idle time threshold may be 10 minutes; any effective time may be a preset effective time, which may be 1 minute; the effective acceleration threshold may be 4 m / s 2 .

[0079] In some embodiments of the present application, in S103, a driving process analysis is performed based on a plurality of short-trip target driving data to obtain an analysis result, such as Figure 3As shown, it may include: S301-S303.

[0080] S301, converting the speed in the target driving data of a short trip into a plurality of speed characteristic data.

[0081] In the embodiment of the present application, after determining the target travel data of the short trip, the analysis device can perform data conversion based on the speed in the target travel data to obtain multiple speed characteristic data. In the embodiment of the present application, the multiple speed characteristic data may include: maximum speed, maximum acceleration, average speed, average running speed, average acceleration, average deceleration, speed standard deviation, acceleration standard deviation, acceleration ratio, deceleration ratio, uniform speed ratio, idle speed ratio, and various speed distribution ratios. In this regard, it can be set as needed, and the embodiment of the present application does not limit it.

[0082] In the embodiment of the present application, the analysis device can determine the maximum speed according to the speed, see formula (3); determine the average speed according to the speed, see formula (4); determine the running average speed according to the speed, see formula (5); and then determine the speed standard deviation according to the speed and the average speed, see formula (6).

[0083] v max =max{v1, v2, ..., v k}Formula (3)

[0084] Where k is the number of sampling points in the short trip.

[0085] v m =mean{v1, v2, …, v k}Formula (4)

[0086] v me =mean{v j |v j ≠0}Formula (5)

[0087] Among them, k≥j≥1; j is a positive integer.

[0088] Among them, v e For {v1, v2, …, v k} is not equal to 0.

[0089]

[0090] In the embodiment of the present application, the analysis device determines k-1 accelerations a based on formula (1) or (2): i，i+1 After that, we can use k-1 accelerations a i，i+1 Determine the maximum acceleration, see formula (7); based on k-1 accelerations a i，i+1Determine the average acceleration, see formula (8); based on k-1 accelerations a i，i+1 Determine the average deceleration, see formula (9); based on k-1 accelerations a i，i+1 Determine the acceleration standard deviation, see formula (10).

[0091] a max =max{a 1，2 , a 2，3 , …, a k-1，k}Formula (7)

[0092] a a =mean{a e，e+1 |a e，e+1 ≥y}Formula (8)

[0093] Among them, k-1≥e≥1; e is a positive integer; y is a positive number, which is the speed change threshold.

[0094] a d =mean{a e，e+1 |a e，e+1 ≤-y}Formula (9)

[0095]

[0096] In the embodiment of the present application, after the analysis device divides the short stroke, the duration T of the short stroke can be determined. After determining various working conditions of the short stroke, the duration of various working conditions is determined, including: acceleration duration T a , deceleration time T d , idling time T e and uniform speed duration T u , and then determine the acceleration ratio P a , reduction ratio P d , uniform speed ratio P e and idle speed ratio P u , see formulas (11)-(14).

[0097]

[0098]

[0099] In the embodiment of the present application, the analysis device can determine the number of interval sampling points of the speed in any interval, and divide the number of interval sampling points by the total number of sampling points in the short stroke to obtain the speed distribution ratio of the interval.

[0100] For example, the number of sampling points in the speed distribution interval between 25 km / h and 35 km / h is shown in formula (15).

[0101] k e-30 = count{vj |35>v j ≥25}Formula (15)

[0102] The speed distribution ratio in the range of 25km / h to 35km / h is shown in formula (16).

[0103]

[0104] In some embodiments, the calculation of the above formula can be implemented by programming in Python to convert the speed into speed characteristic parameters.

[0105] S302, based on the principal component analysis method and a data matrix composed of multiple speed characteristic data of multiple short trips, perform dimensionality reduction processing on the driving characteristic data to obtain multiple groups of high-characteristic data; the number of the multiple groups is less than the number of the multiple driving characteristic data.

[0106] In the embodiment of the present application, the analysis device can use the principal component analysis method to convert the driving characteristic data in the high-dimensional space into the low-dimensional space to obtain multiple sets of target characteristic data. The principal component analysis method is described by the following steps:

[0107] Step 1. Determine the correlation matrix based on the data matrix.

[0108] In the embodiment of the present application, multiple (F) short trips and multiple (P) driving characteristic data form a data matrix X F×P , the analysis device can calculate any two elements X in the data matrix f and X P The covariance or correlation coefficient C between fp , and obtain the correlation matrix C composed of covariance or correlation coefficients p×p ; Among them, F≥f≥1, P≥p≥1, and F, P, f and p are all positive integers.

[0109] Step 2. Calculate the correlation matrix C p×p The eigenvalue λ p and the eigenvector ξ p ,.

[0110] The analysis device can calculate the eigenvalue λ of the correlation matrix p and the eigenvector ξ p , arrange all eigenvalues ​​in descending order: λ1≥λ2≥…≥λ P ≥0; each eigenvector ξ p is a unit vector.

[0111] Step 3: Calculate the principal component contribution rate and cumulative contribution rate.

[0112] The qth principal component Y qIt can be expressed as formula (17).

[0113] Y q =C.ξ q Formula (17)

[0114] Wherein, P≥q≥1, q is a positive integer.

[0115] The contribution rate of the hth principal component can be calculated by formula (18), where h is a positive integer.

[0116]

[0117] The cumulative contribution rate of the first s principal components can be calculated by formula (19), where s is a positive integer.

[0118]

[0119] When the cumulative contribution rate of the first s principal components is greater than the contribution rate threshold, the first s principal components can be selected to reflect the information of multiple driving characteristic data; these s principal components are s groups of high-characteristic data. Each group of high-characteristic data can contain at least one driving characteristic data. It should be noted that the contribution rate threshold can be set according to actual needs, and the embodiment of the present application does not limit it.

[0120] In some embodiments, the contribution rate threshold is 80%.

[0121] In the embodiment of the present application, the analysis device can interpret the new s principal components through the proportion of each driving characteristic data stored in the principal component, that is, the principal component load interpretation, see formula (20).

[0122]

[0123] Among them, ξ hp Represents ξ h The pth variable of .

[0124] In some embodiments, the data model encoding can be performed by the principal component analysis (PCA) related functions in Python's Scikit-Learn library. PCA encoding is as follows:

[0125] from sklearn import preprocessing

[0126] df = pd.read_excel(r". / Vehicle Summary Table.xlsx")

[0127] Df = preprocessing.scale (df) # data standardization

[0128] covX=np.around(np.corrcoef(df.T),decimal=3)

[0129] #Solve the covariance matrix, keep 3 as a decimal

[0130] featValue,featVec=np.linalg.eig(covX,T)

[0131] featValue=sorted(featValue)[::-1]

[0132] #Solve the coefficient correlation matrix eigenvalues ​​and eigenvectors, eigenvalues ​​are sorted from high to low

[0133] gx=featValue / np.sum(featValue)

[0134] Lg = np.cumsum(gx)

[0135] #Solve the eigenvalue contribution rate and cumulative contribution rate

[0136] k=[i for iin range(len(lg))if lg[i]≤0.80]

[0137] #Select the principal component with cumulative contribution rate greater than 0.8

[0138] selectVec=np.matrix(featValue.T[k]).T

[0139] selectVec=selectVec*(-1)

[0140] #Build the principal component loading matrix

[0141] The data model is encoded using principal component analysis (PCA) and related functions in Python's Scikit-Learn library.

[0142] S303: Analyze the driving process of multiple groups of high-feature data to obtain analysis results.

[0143] In some embodiments, after obtaining multiple sets of high-feature data, the analysis device may use a clustering method to perform cluster analysis on the multiple sets of high-feature data to obtain cluster analysis results; and use the cluster analysis results as analysis results of the driving process.

[0144] In some embodiments, the analysis device may input multiple sets of high-feature data into the analysis network, and the analysis network may output the analysis results. The analysis network may be trained according to actual needs, and this is not limited in the embodiments of the present application.

[0145] It can be understood that after the analysis device performs data conversion on the target driving data, it then performs data dimensionality reduction, so that the dimensions of multiple groups of high-feature data used for trip analysis are greatly reduced while retaining sufficient information on the target driving data; in this way, the amount of calculation in the analysis process can be reduced and the consumption of computing resources can be reduced.

[0146] In some embodiments of the present application, the analysis device may perform cluster analysis on multiple groups of high-feature data to obtain multiple driving categories corresponding to multiple short trips; and use the multiple driving categories as analysis results.

[0147] In the embodiment of the present application, the analysis device performs cluster analysis on short trips based on multiple groups of high-feature data, and can classify multiple short trips into multiple driving categories, and different categories can reflect different driving characteristics. In some embodiments, different driving characteristics can reflect the traffic status of the vehicle. The analysis device can classify according to the similarity of the high-feature data.

[0148] In some embodiments, the analysis device can use the K-Means clustering algorithm designed for large amounts of data in the Scikit-Learn library to process high-feature data and implement cluster analysis.

[0149] Step 1: Randomly select r initial center points;

[0150] Step 2: Calculate the distance from each point to the center point, and assign the point to the cluster with the closest center point;

[0151] Step 3: Calculate the average value of each cluster as the new center point;

[0152] Step 4: Repeat the process of Step 2 and Step 3 until the center point no longer changes.

[0153] Among them, the K-Means algorithm has a ready-made function in the sklearn.cluster package, which can be called. The function and its parameters are as follows:

[0154] The selection of the main parameters is described as follows:

[0155] n_clusters=3: number of clusters;

[0156] init = 'K-Means++': Initialization method {'K-Means++'};

[0157] max_iter=300: maximum number of iterations;

[0158] n_init=10: the number of times the algorithm is run for the initial centroid;

[0159] algorithm = 'auto': Automatically select 'full' or 'elkan' depending on whether the data values ​​are sparse or dense.

[0160] Exemplarily, Table 2 is the speed characteristic data of the short stroke of a truck, including 595 short strokes. Table 3 is the speed characteristic data of the short stroke of a dump truck and a concrete mixer truck, including 86 short strokes. Table 4 is the speed characteristic data of the short stroke of a tractor, including 203 short strokes. The speed characteristic data of each short stroke includes 20: 0, maximum speed; 1, maximum acceleration; 2, average speed; 3, average running speed; 4, average acceleration; 5, average deceleration; 6, speed standard deviation; 7, acceleration standard deviation; 8, acceleration ratio; 9, deceleration ratio; 10, uniform speed ratio; 11, idle ratio; 12, speed distribution ratio less than 25; 13, speed distribution ratio between 25-35; 14, speed distribution ratio between 35-45, ...; 18, speed distribution ratio between 75-85; 19, speed distribution ratio greater than 85.

[0161] Table 2

[0162]

[0163] Table 3

[0164]

[0165] Table 4

[0166]

[0167]

[0168] By performing data dimensionality reduction on the 20 speed characteristic data of all operating trucks in Table 2-4, we can obtain the contribution rate of each principal component and the cumulative contribution rate as shown in Table 5.

[0169] Table 5

[0170] principal component Contribution rate (%) Cumulative contribution rate (%) S1 43.966 43.966 S2 20.100 64.065 S3 9.859 73.924 S4 6.382 80.306 S5 4.146 84.452 … … …

[0171] If the contribution rate threshold is 80%, it can be seen from Table 5 that the cumulative contribution rate of S1-S4 is greater than 80%, which can be used as multiple sets of high-feature data. In this way, the analysis device can reduce the dimension of 20 speed feature data to 4-dimensional high-feature data.

[0172] The analysis device continues to determine the principal component loads as shown in Table 6. The 20 velocity characteristic data are represented by 0-19.

[0173] Table 6

[0174]

[0175]

[0176] In some embodiments, the analysis device can determine the speed characteristic data greater than 0.2 in the principal component load as the speed characteristic data contained in the corresponding principal component. According to the principal component load in Table 6, it can be seen that S1 includes speed characteristic data 5, 8, 9, 10, 12-14; S2 includes speed characteristic data: 6 and 12; S3 speed characteristic data includes: 10, 12, 18 and 20; S4 speed characteristic data includes: 16 and 17.

[0177] Based on the four principal components, the analysis device performs cluster analysis on the 884 short trips of the three types of operating trucks in Tables 2 to 4, and three categories of short trips can be obtained. The first category includes 243 short trips, the second category includes 184 short trips, and the third category includes 455 short trips. In each category of short trips, the index value of the principal component is shown in Table 7; the index value is used to characterize the importance of each principal component in the three categories of short trips after clustering.

[0178] Table 7

[0179] principal component Category I Category II Category 3 S1 -3.94 3.34 0.76 S2 0.40 2.02 -1.03 S3 0.55 0.73 -0.59 S4 -0.01 -0.15 0.07

[0180] According to the speed characteristic parameters corresponding to the main components, the characteristics of each of the three types of short trips can be determined. Among them, the index values ​​of the main components S1 and S2 of the first type of short trip are lower than those of the other two types of short trips, while the index values ​​of S3 and S4 are higher. It can be observed that the first type of short trip mainly describes the driving state of the car on the highway; in addition, the proportion of idling and some low speeds is slightly higher, which also matches the current characteristics of queuing and low-speed driving at toll stations. It can be determined that the first type of short trip describes the high-speed driving state on the highway. The index values ​​of the main components S1 and S2 of the second type of short trip are the highest among the three types of short trips. It can be inferred that this type of short trip reflects the slow driving state of the car in the urban traffic congestion area, and may also occur during holidays or morning and evening rush hours. The index values ​​of the main components S1-S3 of the third type of short trip are lower among the three types of short trips, while the index value of the main component S4 is the highest among the three types. Combining these indicator data and motion characteristics, it can be determined that the third type of short-trip description group is a medium-speed driving condition on suburban roads or in urban areas with relatively smooth traffic.

[0181] From the above analysis, we can see that most of my country's current operating trucks travel in suburban areas and expressways, and the proportion of traffic congestion in urban areas is relatively small, which is also consistent with the actual driving conditions and vehicle management requirements of my country's operating trucks. The analysis method of the operating truck driving process in this case can provide technical solutions and strong data support for the competent authorities' technical management requirements for operating trucks and the adjustment of the actual operating condition coefficient of the "Limits and Measurement Methods for Fuel Consumption of Operating Vehicles".

[0182] Based on the above embodiments, the present application provides a driving process analysis device for an operating truck, such as Figure 4 As shown, the analysis device 50 comprises:

[0183] An acquisition module 501 is used to acquire driving data of a plurality of short trips during the driving process; the driving data includes the speed and engine speed of the operating truck;

[0184] A determination module 502 is used to determine at least one operating condition included in the short stroke according to the speed and the engine speed; the at least one operating condition includes an idle operating condition;

[0185] A deleting module 503 is used to delete the data of the engine speed being less than the vehicle operating speed threshold from the driving data of the idle condition, so as to obtain target driving data;

[0186] The analysis module 504 is used to analyze the driving process based on the target driving data of the multiple short trips to obtain analysis results.

[0187] In some embodiments, the greater the total mass of the operating truck, the greater the vehicle operating speed threshold.

[0188] In some embodiments, the short trip includes multiple sampling points, each sampling point corresponds to a set of driving data; the determination module 502 is also used to determine multiple accelerations based on the speeds corresponding to the multiple sampling points; and determine the at least one operating condition based on the acceleration, speed and engine speed.

[0189] In some embodiments, the determination module 502 is also used to determine the operating condition in which the acceleration is greater than or equal to the speed change threshold and the acceleration is not equal to 0 as an acceleration condition; determine the operating condition in which the acceleration is less than or equal to the negative value of the speed change threshold and the acceleration is not equal to 0 as a deceleration condition; determine the operating condition in which the absolute value of the acceleration is less than the speed change threshold and is not equal to 0 as a uniform speed condition; and determine the operating condition in which the speed is 0 and the engine speed is not 0 as the idle condition.

[0190] In some embodiments, the acquisition module 501 is also used to divide the driving process into multiple short trips based on the original driving data during the driving process; filter the original driving data that meets the effective analysis conditions from the original driving data of the multiple short trips to obtain the driving data of the multiple short trips.

[0191] In some embodiments, the effective analysis conditions include:

[0192] The maximum speed of the short stroke is greater than or equal to the maximum speed threshold;

[0193] The duration of the short trip is greater than a short trip duration threshold;

[0194] The absolute value of the acceleration of the short stroke is less than the effective acceleration threshold;

[0195] When the duration of the idle condition is greater than or equal to the idle duration threshold, a preset effective duration in the duration is used as the actual duration of the idle condition.

[0196] In some embodiments, the analysis module 504 is also used to convert the speed in the target driving data of the short trip into multiple speed feature data; based on the principal component analysis method and the data matrix composed of the multiple short-trip speed feature data, the driving feature data is subjected to dimensionality reduction processing to obtain multiple groups of high-feature data; the number of the multiple groups is less than the number of the multiple driving feature data; the driving process analysis is performed on the multiple groups of high-feature data to obtain analysis results.

[0197] In some embodiments, the analysis module 504 is further used to perform cluster analysis on the multiple groups of high-feature data to obtain multiple driving categories corresponding to the multiple short trips; and use the multiple driving categories as the analysis results.

[0198] Figure 5 The schematic diagram of the structure of the driving process analysis device of the operating truck of the embodiment of the present application is as follows: Figure 2 ,like Figure 5 As shown, the analysis device 50 includes a memory 517, a processor 518, and a computer program stored in the memory 517 and executable on the processor 518; wherein, when the processor 518 is used to run the computer program, it executes the driving process analysis method of the operating truck in the aforementioned embodiment.

[0199] It is understood that the analysis device 50 also includes a bus system 519; the various components in the terminal 9 are coupled together through the bus system 519. It is understood that the bus system 519 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 519 also includes a power bus, a control bus and a status signal bus.

[0200] It can be understood that the memory in this embodiment can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0201] The method disclosed in the above embodiment of the present application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0202] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer-readable storage medium is located in a driving process analysis device for an operating truck, the computer program, when executed by a processor, implements the steps in the driving process analysis method for an operating truck in an embodiment of the present application.

[0203] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or modules can be electrical, mechanical or other forms.

[0204] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for analyzing the driving process of an operating truck, characterized in that: include: Acquiring driving data of a plurality of short trips during the driving process; the driving data including the speed and engine speed of the operating truck; Determining at least one operating condition included in the short stroke according to the speed and the engine speed; the at least one operating condition includes an idle operating condition; From the driving data of the idle condition, data in which the engine speed is less than a vehicle operating speed threshold is deleted to obtain target driving data; A driving process analysis is performed based on the target driving data of the plurality of short trips to obtain an analysis result.

2. The method according to claim 1, characterized in that The greater the total mass of the operating truck, the greater the vehicle operating speed threshold.

3. The method according to claim 1, characterized in that The short trip includes a plurality of sampling points, each sampling point corresponding to a set of driving data; Determining at least one operating condition included in the short stroke according to the speed and the engine speed includes: Determining a plurality of accelerations according to the velocities corresponding to the plurality of sampling points; The at least one operating condition is determined based on the acceleration, speed and engine speed.

4. The method according to claim 3, characterized in that Determining the at least one operating condition according to the acceleration, speed and engine speed includes: Determining a working condition in which the acceleration is greater than or equal to the speed change threshold and the acceleration is not equal to 0 as an acceleration working condition; Determining a working condition in which the acceleration is less than or equal to the negative value of the speed change threshold and the acceleration is not equal to 0 as a deceleration working condition; Determine the operating condition where the absolute value of the acceleration is less than the speed change threshold and is not equal to 0 as a uniform speed operating condition; The operating condition in which the speed is 0 and the engine speed is not 0 is determined as the idle operating condition.

5. The method according to claim 1, characterized in that: The obtaining of the driving data of a plurality of short trips during the driving process includes: Dividing the driving process into a plurality of short trips according to the original driving data during the driving process; The original driving data satisfying the effective analysis condition is selected from the original driving data of the plurality of short trips to obtain the driving data of the plurality of short trips.

6. The method according to claim 5, characterized in that The effective analysis conditions include at least one of the following: The maximum speed of the short stroke is greater than or equal to the minimum speed threshold; The duration of the short trip is greater than a short trip duration threshold; The absolute value of the acceleration of the short stroke is less than the effective acceleration threshold; When the duration of the idle condition is greater than or equal to the idle duration threshold, a preset effective duration in the duration is used as the actual duration of the idle condition.

7. The method according to claim 1, characterized in that The driving process analysis based on the target driving data of the plurality of short trips is performed to obtain the analysis result, including: converting the speed in the target driving data of the short trip into a plurality of speed characteristic data; Based on the principal component analysis method and the data matrix composed of the plurality of short-trip speed characteristic data, the driving characteristic data is subjected to dimensionality reduction processing to obtain a plurality of groups of high-characteristic data; the number of the plurality of groups is less than the number of the plurality of driving characteristic data; The driving process analysis is performed on the multiple groups of high-feature data to obtain analysis results.

8. The method according to claim 7, characterized in that The performing of the driving process analysis on the plurality of sets of high-feature data to obtain analysis results includes: Cluster analysis is performed on the multiple groups of high-feature data to obtain multiple driving categories corresponding to the multiple short trips; and the multiple driving categories are used as the analysis results.

9. A driving process analysis device for an operating truck, characterized in that: include: An acquisition module, used for acquiring driving data of a plurality of short trips during the driving process; The driving data includes the speed and engine speed of the operating truck; A determination module, configured to determine at least one operating condition included in the short stroke according to the speed and the engine speed; the at least one operating condition includes an idle operating condition; A deleting module, used to delete the data of the engine speed being less than the vehicle operating speed threshold from the driving data of the idle condition, so as to obtain target driving data; The analysis module is used to analyze the driving process based on the target driving data of the multiple short trips to obtain analysis results.

10. A computer storage medium, characterized in that: One or more computer programs are stored, and the one or more computer programs can be executed by one or more processors to implement the steps of any one of claims 1-8.

Images