Method and device for determining bad road proportion of whole road network based on half-shaft vibration

Abstract

The invention relates to the technical field of traffic transportation, in particular to a full road network bad road proportion determination method and device based on half-axis vibration, and the method comprises the steps: obtaining the actual road driving data and half-axis vibration signals of vehicles in a full road network of a target city, according to the actual road driving data and the half-axle vibration signal, extracting a driving segment containing the half-axle vibration signal; extracting a main component of a half-axis vibration characteristic according to the driving segment, and obtaining a half-axis vibration signal cluster based on the main component of the half-axis vibration characteristic; and determining a bad road proportion result of the whole road network of the target city according to the half-shaft vibration signal cluster and the current longitude and latitude information of the vehicle. Therefore, the problems of high manual or model training cost, low recognition and positioning efficiency, high time and energy consumption, difficulty in meeting the requirement of determining the proportion of the bad roads in the whole road network, how to realize positioning and proportion acquisition of the bad roads in the whole road network in a lower data cost and more efficient manner and the like in a method in the related technology are solved.

Description

Technical Field

[0001] The present application relates to the field of transportation technology, and in particular to a method and device for determining the bad road proportion of the entire road network based on semi-axle vibration. Background Art

[0002] The road traffic system is the pillar of national economic development. With the acceleration of urbanization and the popularization of transportation, the safety and reliability of the road traffic system have become the focus of people's attention. The generation of bad roads such as cracks and potholes is an inevitable problem in the process of road use, which has a serious negative impact on the driving and riding comfort of vehicles and even causes traffic accidents. Therefore, timely locating the location of bad roads in the entire road network and determining the proportion of bad roads in the entire road network can provide guidance for urban road repair, which is of great significance to the safety and reliability of the urban road traffic system.

[0003] In related technologies, the identification and location of bad roads in the road network are mainly achieved through manual detection or deep learning algorithms to extract road surface features.

[0004] However, the methods in related technologies have high manual or model training costs, or low identification and positioning efficiency, and consume too much time and energy, while it is difficult to meet the needs of determining the proportion of bad roads in the entire road network. How to locate and obtain the proportion of bad roads in the entire road network with lower data costs and in a more efficient manner needs to be solved urgently. Summary of the invention

[0005] The present application provides a method and device for determining the proportion of bad roads in the entire road network based on semi-axis vibration, so as to solve the problems in the related technologies such as high manual or model training costs, low identification and positioning efficiency, excessive consumption of time and energy, and difficulty in achieving the demand for determining the proportion of bad roads in the entire road network, and how to locate and obtain the proportion of bad roads in the entire road network in a lower data cost and more efficient manner.

[0006] The first aspect of the present application provides a method for determining the bad road proportion of the entire road network based on semi-axle vibration, comprising the following steps: obtaining actual road driving data and semi-axle vibration signals of vehicles in the entire road network of a target city, extracting driving segments containing the semi-axle vibration signals based on the actual road driving data and the semi-axle vibration signals; extracting semi-axle vibration characteristic principal components based on the driving segments, so as to obtain semi-axle vibration signal clustering clusters based on the semi-axle vibration characteristic principal components; and determining the bad road proportion result of the entire road network of the target city based on the semi-axle vibration signal clustering clusters and the current latitude and longitude information of the vehicle.

[0007] Through the above technical means, the embodiment of the present application can determine the location distribution results and proportion results of bad roads in the entire road network through the semi-axle vibration signal in the vehicle driving data. By extracting the driving segments containing the semi-axle vibration signal, the main components of the semi-axle vibration characteristics, and other information, the redundant data is effectively screened out while improving the accuracy of the results obtained in the embodiment of the present application. Clustering the main components of the semi-axle vibration characteristics into semi-axle vibration signal clusters effectively reduces the cost and time of bad road identification and improves the efficiency of bad road identification. The proportion result also includes the location distribution result, which is helpful for repairing bad roads and other operations. It is extremely practical and has a wide range of applications.

[0008] Optionally, in one embodiment of the present application, the extracting the driving segment containing the semi-axle vibration signal according to the actual road driving data and the semi-axle vibration signal includes: cutting the actual road driving data to obtain an initial driving segment; acquiring the corresponding semi-axle vibration signal according to the start and end time of the initial driving segment, and performing low-pass filtering on the corresponding semi-axle vibration signal to obtain the semi-axle vibration signal that meets preset processing conditions; matching and combining the semi-axle vibration signal with the initial driving segment to obtain the driving segment.

[0009] Through the above-mentioned technical means, the embodiment of the present application can use the fragment cutting method to cut the actual road driving data and obtain the corresponding half-axle vibration signal to filter it, which effectively improves the efficiency of data processing and the reliability of the half-axle vibration signal, and then matches and combines the two to provide effective driving fragments as data information support for subsequent processing processes.

[0010] Optionally, in one embodiment of the present application, extracting the main components of the semi-axle vibration characteristics based on the driving segment includes: using the driving segment to calculate the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency of the semi-axle vibration signal and the average vehicle speed and average acceleration of the driving segment; extracting the main components of the semi-axle vibration characteristics based on the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency and the average vehicle speed and average acceleration of the driving segment.

[0011] Through the above-mentioned technical means, the embodiment of the present application can use the driving segment containing the half-axle vibration signal to extract the half-axle vibration characteristics, and then extract the main components of the half-axle vibration characteristics, which can be used as the input of the subsequent clustering analysis to prepare information for the subsequent bad road identification.

[0012] Optionally, in one embodiment of the present application, obtaining the clustering clusters of semi-axle vibration signals based on the principal components of the semi-axle vibration characteristics includes: using a target neural network to perform an initial clustering analysis on the principal components of the semi-axle vibration characteristics to obtain a target neural network clustering result; based on the target neural network clustering result, mapping the driving segment to a competition layer node of the target neural network to obtain a vibration energy average value and a vibration energy standard deviation of the semi-axle vibration signal of the competition layer node; based on the vibration energy average value and the vibration energy standard deviation, obtaining the clustering clusters of the semi-axle vibration signal.

[0013] Through the above-mentioned technical means, the embodiment of the present application can obtain the clustering clusters of the half-shaft vibration signals based on the main components of the half-shaft vibration characteristics, using the target neural network and a certain clustering method, thereby obtaining the differences in vibration characteristics under roads with different degrees of damage. Furthermore, the vibration characteristics of the half-shaft under different fault conditions can be identified by analyzing the clustering clusters, thereby providing strong support for bad road detection.

[0014] Optionally, in one embodiment of the present application, determining the bad road proportion result of the entire road network of the target city based on the semi-axle vibration signal clustering clusters and the current longitude and latitude information of the vehicle includes: locating the bad road position according to the semi-axle vibration signal clustering clusters and the longitude and latitude information of the vehicle; determining the bad road position distribution result of the entire road network of the target city according to the bad road position; and generating the proportion result according to the bad road position distribution result.

[0015] Through the above-mentioned technical means, the embodiment of the present application can locate the bad road position according to the clustering clusters of the half-axle vibration signal and the latitude and longitude information of the vehicle, so as to obtain the bad road position distribution results and bad road proportion results of the entire road network in the target city, reduce the implementation cost of bad road positioning and proportion acquisition in the entire road network, improve the efficiency of bad road identification, and at the same time help to use the bad road position for road surface maintenance, greatly improving the practicality and scope of application of the present application.

[0016] The second aspect of the present application provides a device for determining the bad road proportion of the entire road network based on semi-axle vibration, including: an extraction module, used to obtain actual road driving data and semi-axle vibration signals of vehicles in the entire road network of a target city, and extract driving segments containing the semi-axle vibration signals based on the actual road driving data and the semi-axle vibration signals; an acquisition module, used to extract semi-axle vibration characteristic principal components based on the driving segments, so as to obtain semi-axle vibration signal clustering clusters based on the semi-axle vibration characteristic principal components; a determination module, used to determine the bad road proportion result of the entire road network of the target city based on the semi-axle vibration signal clustering clusters and the current longitude and latitude information of the vehicle.

[0017] Through the above technical means, the embodiment of the present application can determine the location distribution results and proportion results of bad roads in the entire road network through the semi-axle vibration signal in the vehicle driving data. By extracting the driving segments containing the semi-axle vibration signal, the main components of the semi-axle vibration characteristics, and other information, the redundant data is effectively screened out while improving the accuracy of the results obtained in the embodiment of the present application. Clustering the main components of the semi-axle vibration characteristics into semi-axle vibration signal clusters effectively reduces the cost and time of bad road identification and improves the efficiency of bad road identification. The proportion result also includes the location distribution result, which is helpful for repairing bad roads and other operations. It is extremely practical and has a wide range of applications.

[0018] Optionally, in one embodiment of the present application, the extraction module includes: a cutting unit, used to cut the actual road driving data to obtain an initial driving segment; a first processing unit, used to obtain a corresponding half-axle vibration signal according to the start and end time of the initial driving segment, and perform low-pass filtering on the corresponding half-axle vibration signal to obtain the half-axle vibration signal that meets preset processing conditions; a second processing unit, used to match and combine the half-axle vibration signal with the initial driving segment to obtain the driving segment.

[0019] Through the above-mentioned technical means, the embodiment of the present application can use the fragment cutting method to cut the actual road driving data and obtain the corresponding half-axle vibration signal to filter it, which effectively improves the efficiency of data processing and the reliability of the half-axle vibration signal, and then matches and combines the two to provide effective driving fragments as data information support for subsequent processing processes.

[0020] Optionally, in one embodiment of the present application, the acquisition module includes: a calculation unit, used to calculate the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency of the semi-axle vibration signal and the average vehicle speed and average acceleration of the driving segment using the driving segment; an extraction unit, used to extract the main components of the semi-axle vibration characteristics based on the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency and the average vehicle speed and average acceleration of the driving segment.

[0021] Through the above-mentioned technical means, the embodiment of the present application can use the driving segment containing the half-axle vibration signal to extract the half-axle vibration characteristics, and then extract the main components of the half-axle vibration characteristics, which can be used as the input of the subsequent clustering analysis to prepare information for the subsequent bad road identification.

[0022] Optionally, in one embodiment of the present application, the acquisition module includes: a clustering unit, used to perform initial clustering analysis on the principal components of the half-axle vibration characteristics using a target neural network to obtain a target neural network clustering result; a mapping unit, used to map the driving segment to a competition layer node of the target neural network based on the target neural network clustering result to obtain the vibration energy average value and vibration energy standard deviation of the half-axle vibration signal of the competition layer node; an acquisition unit, used to obtain the clustering cluster of the half-axle vibration signal based on the vibration energy average value and the vibration energy standard deviation.

[0023] Through the above-mentioned technical means, the embodiment of the present application can obtain the clustering clusters of the half-shaft vibration signals based on the main components of the half-shaft vibration characteristics, using the target neural network and a certain clustering method, thereby obtaining the differences in vibration characteristics under roads with different degrees of damage. Furthermore, the vibration characteristics of the half-shaft under different fault conditions can be identified by analyzing the clustering clusters, thereby providing strong support for bad road detection.

[0024] Optionally, in one embodiment of the present application, the determination module includes: a positioning unit, used to locate the bad road position according to the half-axle vibration signal clustering cluster and the latitude and longitude information of the vehicle; a determination unit, used to determine the bad road position distribution result of the entire road network of the target city according to the bad road position; and a generation unit, used to generate the proportion result according to the bad road position distribution result.

[0025] Through the above-mentioned technical means, the embodiment of the present application can locate the bad road position according to the clustering clusters of the half-axle vibration signal and the latitude and longitude information of the vehicle, so as to obtain the bad road position distribution results and bad road proportion results of the entire road network in the target city, reduce the implementation cost of bad road positioning and proportion acquisition in the entire road network, improve the efficiency of bad road identification, and at the same time help to use the bad road position for road surface maintenance, greatly improving the practicality and scope of application of the present application.

[0026] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the proportion of bad roads in the entire road network based on semi-axle vibration as described in the above embodiment.

[0027] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above method for determining the bad road proportion of the entire road network based on semi-axis vibration.

[0028] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above method for determining the bad road proportion of the entire road network based on semi-axle vibration.

[0029] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0031] Figure 1 A flowchart of a method for determining the bad road proportion of the entire road network based on half-axle vibration provided according to an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a method for cutting a driving segment and a method for intercepting a half-axle vibration signal according to an embodiment of the present application;

[0033] Figure 3 This is a schematic diagram of clustering results of an embodiment of the present application;

[0034] Figure 4 A schematic diagram of bad road location distribution results according to an embodiment of the present application;

[0035] Figure 5 This is a flow chart of a method for determining the bad road ratio of the entire road network based on a vehicle half-axle vibration signal according to an embodiment of the present application;

[0036] Figure 6 It is a structural schematic diagram of a device for determining the bad road proportion of the entire road network based on semi-axle vibration according to an embodiment of the present application;

[0037] Figure 7 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application.

[0038] Reference numerals:

[0039] 10-Device for determining the bad road proportion of the entire road network based on semi-axle vibration: 100-extraction module, 200-acquisition module and 300-determination module; 701-memory, 702-processor and 703-communication interface. DETAILED DESCRIPTION

[0040] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0041] The following describes the method and device for determining the proportion of bad roads in the whole road network based on semi-axle vibration according to the embodiment of the present application with reference to the accompanying drawings. In view of the fact that the methods in the related technologies mentioned in the above background technology have high manual or model training costs, or low recognition and positioning efficiency, and the time and energy consumption are too high while it is difficult to achieve the demand for determining the proportion of bad roads in the whole road network, how to achieve the problem of positioning and proportion acquisition of bad roads in the whole road network with lower data costs and more efficient methods, the present application provides a method for determining the proportion of bad roads in the whole road network based on semi-axle vibration, in which the position distribution results and proportion results of bad roads in the whole road network can be determined by semi-axle vibration signals in vehicle driving data. By extracting information such as driving segments containing semi-axle vibration signals and main components of semi-axle vibration characteristics, redundant data is effectively screened out while improving the accuracy of the results obtained in the embodiment of the present application. Clustering the main components of semi-axle vibration characteristics into clusters of semi-axle vibration signals effectively reduces the cost and time of bad road identification, improves the efficiency of bad road identification, and obtains the proportion result while also including the position distribution result, which is helpful for repairing bad roads, etc., and has extremely high practicality and scope of application. This solves the problem that the methods in the related technologies have high manual or model training costs, or low identification and positioning efficiency, and it is difficult to achieve the demand for determining the proportion of bad roads in the entire road network while consuming too much time and energy. It also solves the problem of how to locate and obtain the proportion of bad roads in the entire road network with lower data costs and in a more efficient manner.

[0042] Specifically, Figure 1 A flow chart of a method for determining the bad road proportion of the entire road network based on half-axle vibration provided in an embodiment of the present application.

[0043] like Figure 1 As shown, the method for determining the bad road proportion of the entire road network based on half-axle vibration includes the following steps:

[0044] In step S101, actual road driving data and half-axle vibration signals of vehicles in the entire road network of the target city are obtained, and driving segments containing half-axle vibration signals are extracted based on the actual road driving data and the half-axle vibration signals.

[0045] It is understood by professionals in this technical field that the target city here can be understood as the city where the bad road ratio of the entire road network needs to be determined. The half-axle vibration signal refers to the mechanical vibration generated by the operation of the half-axle and its related components (such as bearings, universal joints, etc.) during the vehicle's driving, and the electrical signal captured by the sensor. These signals contain rich information, such as the frequency, amplitude, phase, etc. of the vibration, which can be used to analyze the working status and potential faults of the half-axle.

[0046] In some embodiments, when the vehicle passes through cracks, potholes and other bad roads, the vehicle's half-axle will produce an impact vibration response. For example, the half-axle will shake or become unbalanced, and the driver will obviously feel the vibration of the steering wheel, seat or body. Or when the vehicle is driving on a rugged road, the half-axle shaking may be accompanied by abnormal noises such as clicking or metal friction. This can preliminarily identify whether there is any abnormality in the road surface.

[0047] Based on this, the embodiment of the present application can obtain the actual road driving data and half-axle vibration signal of the vehicle, thereby obtaining the driving section containing the half-axle vibration signal, that is, the driving section that may produce bad roads. Among them, the driving data includes but is not limited to parameters such as the vehicle's driving time, speed, acceleration, and longitude and latitude, and the driving data collection frequency can be but is not limited to being set to 1Hz, etc. The half-axle vibration signal can be but is not limited to being collected by a vibration acceleration sensor installed on the vehicle half-axle during the vehicle's driving process, and the collection frequency can be but is not limited to being set to 500Hz, etc., such as relevant sensors installed near the half-axles such as bearing seats and universal joints.

[0048] The embodiment of the present application can obtain driving segments containing half-axle vibration signals, and discover faults of the half-axle and its related driving sections by collecting vibration signals, effectively improving the efficiency of bad road identification, and helping to further realize accurate identification of bad roads.

[0049] Optionally, in one embodiment of the present application, a driving segment containing a half-axle vibration signal is extracted based on actual road driving data and the half-axle vibration signal, including: cutting the actual road driving data to obtain an initial driving segment; acquiring the corresponding half-axle vibration signal according to the start and end time of the initial driving segment, and performing low-pass filtering on the corresponding half-axle vibration signal to obtain a half-axle vibration signal that meets preset processing conditions; matching and combining the half-axle vibration signal with the initial driving segment to obtain a driving segment.

[0050] It is understandable that the preset processing conditions here can be understood as a series of conditions or standards, rules, etc. that need to be met when processing the semi-axis vibration signal. For example, the signal noise needs to be reduced to a certain extent. It can be set and adjusted by professional and technical personnel in this field according to actual conditions or calibrated by experiments, etc., and the embodiments of this application are only illustrative and not specifically limited.

[0051] In some embodiments, when extracting driving segments containing half-axle vibration signals, the present application may, but is not limited to, first segment the actual road driving data to obtain initial driving segments that are easier to process. For example, the mileage of the driving data is calculated by the time and vehicle speed in the acquired actual road driving data, and then the driving data may be segmented based on the mileage length threshold, such as the mileage length threshold a is 50 meters, and then a number of initial driving segments with a mileage length a may be obtained.

[0052] When obtaining the initial driving segments, the start and end time of each initial driving segment can be recorded at the same time, so as to obtain the half-axle vibration signal corresponding to each initial driving segment according to the start and end time of each initial driving segment. Figure 2 The figure shows a schematic diagram of a method for cutting a driving segment and a method for intercepting a half-axle vibration signal according to an embodiment of the present application.

[0053] Furthermore, in order to ensure the validity and practical applicability of the semi-axle vibration signal, the embodiment of the present application can also perform low-pass filtering on the corresponding semi-axle vibration signal obtained. For example, the semi-axle vibration signal is subjected to low-pass filtering with a cutoff frequency of 30 Hz using a Butterworth filter, thereby obtaining a corresponding semi-axle vibration signal that meets certain processing conditions. Finally, the corresponding semi-axle vibration signal after filtering is matched and combined with the corresponding initial driving segment, and the driving segment containing the semi-axle vibration signal required by the embodiment of the present application can be obtained.

[0054] The embodiment of the present application can use the fragment cutting method to cut the actual road driving data and obtain the corresponding half-axle vibration signal to filter it, which effectively improves the efficiency of data processing and the reliability of the half-axle vibration signal, and then matches and combines the two to provide effective driving fragments as data information support for subsequent processing processes.

[0055] Step S102 , extracting the principal components of the semi-axle vibration characteristics according to the driving segments, so as to obtain the clustering clusters of the semi-axle vibration signals based on the principal components of the semi-axle vibration characteristics.

[0056] In some embodiments, considering that the information in the driving segment containing the half-axle vibration signal is relatively complex and some of the information is irrelevant to bad road identification, the present application can extract the half-axle vibration feature principal component based on the driving segment containing the half-axle vibration signal, so as to obtain the half-axle vibration signal clustering cluster based on the half-axle vibration feature principal component.

[0057] For example, the relevant half-axle vibration characteristics can be calculated from the driving segment containing the half-axle vibration signal, and then the principal components of the half-axle vibration signal can be extracted using but not limited to the principal component analysis method, and then the principal components of the half-axle vibration characteristics can be processed using but not limited to the SOM neural network and K-means clustering method, thereby obtaining the clustering clusters of the half-axle vibration signals of the bad road.

[0058] The embodiment of the present application can extract the main components of the semi-shaft vibration characteristics based on the form fragment containing the semi-shaft vibration signal and then obtain the clustering cluster of the semi-shaft vibration signal. By extracting useful information (useful components) in the semi-shaft vibration signal, redundant data can be screened out, the data processing cost can be reduced, and the data processing efficiency can be improved.

[0059] Optionally, in one embodiment of the present application, the principal components of the semi-axle vibration characteristics are extracted according to the driving segment, including: using the driving segment to calculate the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency of the semi-axle vibration signal and the average vehicle speed and average acceleration of the driving segment; extracting the principal components of the semi-axle vibration characteristics based on the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency and the average vehicle speed and average acceleration of the driving segment.

[0060] Based on the relevant descriptions of other embodiments, it can be understood that the present application can extract the main components of the semi-axle vibration characteristics based on the driving segment containing the semi-axle vibration signal. Specifically, the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency and the average vehicle speed and acceleration value of the driving segment can be calculated using the driving segment containing the semi-axle vibration signal, and these 8 parameters are used as the semi-axle vibration characteristics of the driving segment.

[0061] Then, the embodiment of the present application can extract the principal components of the semi-axle vibration characteristics based on this information. For example, it is possible but not limited to taking the semi-axle vibration characteristics of all driving segments as input, using the principal component analysis method to calculate all the principal components and cumulative contributions of the semi-axle vibration characteristics, while retaining the main features, eliminating redundant information and noise, mapping the high-dimensional data to a low-dimensional space, and then extracting the first few principal components with a cumulative contribution exceeding 85% as the principal components of the semi-axle vibration characteristics. Table 1 is a table of calculation results of all the principal components and cumulative contributions of the semi-axle vibration characteristics of an embodiment of the present application, which can be expressed as follows:

[0062] Table 1

[0063] Principal component number Eigenvalue Cumulative contribution rate (%) 1 2.86 35.80 2 2.12 62.28 3 1.32 78.75 4 0.99 91.12 5 0.54 97.90 6 0.10 99.10 7 0.06 99.82 8 0.01 100.00

[0064] According to Table 1, the first four principal components with cumulative contributions exceeding 85% can be extracted as the semi-axis vibration characteristic principal components.

[0065] It should be noted that the selection of specific semi-axis vibration characteristics and the main components of semi-axis vibration characteristics can be selected or adjusted by professional and technical personnel in this field according to actual conditions. The embodiments of this application are only used for illustrative purposes and no specific limitations are imposed.

[0066] The embodiment of the present application can utilize the driving segment containing the half-axle vibration signal to extract the half-axle vibration characteristics, and then extract the main components of the half-axle vibration characteristics, which can be used as the input of the subsequent clustering analysis to prepare information for the subsequent bad road identification.

[0067] Optionally, in one embodiment of the present application, a clustering cluster of half-axle vibration signals is obtained based on the principal components of half-axle vibration characteristics, including: using a target neural network to perform an initial clustering analysis on the principal components of half-axle vibration characteristics to obtain a target neural network clustering result; based on the target neural network clustering result, mapping the driving segment to a competition layer node of the target neural network to obtain a vibration energy average value and a vibration energy standard deviation of the half-axle vibration signal of the competition layer node; based on the vibration energy average value and the vibration energy standard deviation, obtaining a clustering cluster of half-axle vibration signals.

[0068] In other embodiments, after obtaining the principal components of the semi-shaft vibration characteristics, the present application can also perform initial clustering on the principal components of the semi-shaft vibration characteristics, classify the semi-shaft signals with similar vibration characteristics into the same category, and obtain semi-shaft vibration signal clusters, thereby helping to quickly identify semi-shaft vibration signals in different states.

[0069] Specifically, the embodiment of the present application can first use the target neural network to perform an initial cluster analysis on the principal components of the semi-axis vibration characteristics to obtain the target neural network clustering results. For example, using the principal components of the semi-axis vibration characteristics as input, using the SOM neural network with a competition layer network node number of 8×8, a preliminary cluster analysis is performed to obtain the SOM neural network clustering results.

[0070] Then, based on the target neural network clustering result, the driving segments containing the half-axle vibration signal are mapped to the competition layer nodes of the target neural network to obtain the vibration energy average and vibration energy standard deviation of the half-axle vibration signal of the competition layer node. For example, according to the SOM neural network clustering result, the driving segments containing the half-axle vibration signal are mapped to the competition layer nodes of the SOM neural network, and the vibration energy average and vibration energy standard deviation of the half-axle vibration signal on each node are calculated.

[0071] Finally, based on the average vibration energy and standard deviation of vibration energy, the semi-axle vibration signal clusters are obtained. For example, taking the average vibration energy and standard deviation of all nodes of the SOM neural network as input, the K-means clustering method is used to cluster all nodes of the SOM neural network into four clusters, and the cluster with the largest average vibration energy is selected as the semi-axle vibration signal cluster of the bad road.

[0072] Figure 3 This is a schematic diagram of clustering results of an embodiment of the present application. Figure 3 As shown in FIG. 1 , the embodiment of the present application shows the clustering results of clustering using the SOM neural network and the K-means clustering method with the distribution structure of the competition layer network nodes of the SOM neural network. Since the number of competition layer network nodes of the SOM neural network is 8×8, Figure 3 64 nodes are given in the figure, and each square represents a competitive layer network node of a SOM neural network. Based on this, the 64 competitive layer network nodes of the SOM neural network are clustered into 4 types of clusters using the K-means clustering method. Table 2 is a table of calculation results of the vibration energy average value and vibration energy standard deviation of each type of cluster in an embodiment of the present application, which can be expressed as follows:

[0073] Table 2

[0074] Cluster number Average vibration energy Vibration Energy Standard Deviation 1 19.55 6.16 2 8.25 2.60 3 3.02 1.29 4 0.76 0.51

[0075] As shown in Table 2, the cluster with the largest average vibration energy among the four clusters can be selected as the cluster of the semi-axle vibration signal of the bad road.

[0076] The embodiment of the present application can obtain the clustering clusters of the half-shaft vibration signals based on the principal components of the half-shaft vibration characteristics, using the target neural network and a certain clustering method, thereby obtaining the differences in vibration characteristics under roads with different degrees of damage. Furthermore, the vibration characteristics of the half-shaft under different fault conditions can be identified by analyzing the clustering clusters, thereby providing strong support for bad road detection.

[0077] Step S103, determining the bad road proportion result of the entire road network of the target city according to the clustering clusters of the half-axle vibration signals and the current longitude and latitude information of the vehicle.

[0078] As a possible implementation method, when a vehicle passes through a certain road surface, if the half-axle vibration generated at the half-axle belongs to the half-axle vibration signal cluster of a bad road, the embodiment of the present application can consider the road surface at that location to be a bad road.

[0079] When determining the bad road proportion result of the entire road network of the target city, the embodiment of the present application can, but is not limited to, take into account the geographic location information of the vehicle that produces bad road half-axle vibrations based on the results of cluster analysis of the half-axle vibration signals, so as to obtain a more accurate and comprehensive proportion result.

[0080] The following is a further explanation of this process.

[0081] Optionally, in one embodiment of the present application, the bad road proportion result of the entire road network of the target city is determined based on the clustering clusters of the semi-axle vibration signal and the current longitude and latitude information of the vehicle, including: locating the bad road position based on the clustering clusters of the semi-axle vibration signal and the longitude and latitude information of the vehicle; determining the bad road position distribution result of the entire road network of the target city based on the bad road position; and generating the proportion result based on the bad road position distribution result.

[0082] In the actual implementation process, the present application can determine the bad road location distribution of the entire road network of the target city based on the clustering of the semi-axle vibration signals of the bad roads and the longitude and latitude information that generates the signals, and then determine the proportion of the bad roads.

[0083] For example, after obtaining the driving segments containing half-axle vibration signals of the entire road network of the target city and obtaining the clustering clusters of half-axle vibration signals of bad roads, the present application can mark the driving segments corresponding to the half-axle vibration signals belonging to the clustering clusters of half-axle vibration signals of bad roads as bad roads.

[0084] Furthermore, in the entire road network of the target city, the driving segments marked as bad roads are located according to the latitude and longitude information to obtain the bad road location distribution results in the entire road network of the target city. Finally, the bad road proportion in the entire road network of the target city is calculated based on the bad road location distribution results.

[0085] Figure 4 This is a schematic diagram of the bad road location distribution result of an embodiment of the present application. Figure 4 As shown, the bad road locations of some actual driving sections and some detected sections of the street are displayed. Among them, the yellow solid line indicates the sections and detected sections that the vehicle actually traveled, and the red dotted line indicates the bad road location. This application identified two bad roads in some actual driving sections and some detected sections. Through the feedback of on-site real-time photos, it was found that the two determined bad road locations had bad road problems such as cracks and potholes, which effectively verified the accurate identification of bad roads in the road traffic system by this application.

[0086] Then, by obtaining the actual road driving data and half-axle vibration signals of vehicles in the entire road network of the city, all driving segments marked as bad roads can be located according to the longitude and latitude information. Through the positions of bad roads in the entire road network of the city, the proportion of bad roads in the entire road network of the city is calculated, which is approximately 17.8%, thereby realizing the positioning of bad roads and acquisition of the proportion of bad roads in the entire road network of the target city.

[0087] The embodiments of the present application can locate the bad road position according to the clustering of the half-axle vibration signal and the latitude and longitude information of the vehicle, so as to obtain the bad road position distribution results and bad road proportion results of the entire road network in the target city, reduce the implementation cost of bad road positioning and proportion acquisition in the entire road network, improve the efficiency of bad road identification, and at the same time help to use the bad road position for road surface maintenance, which greatly improves the practicality and scope of application of the present application.

[0088] The present application is described in detail below with reference to a specific embodiment.

[0089] Figure 5 This is a flow chart of a method for determining the bad road ratio of the entire road network based on a vehicle half-axle vibration signal according to an embodiment of the present application. Figure 5 As shown:

[0090] Step S501 , extracting the driving segment containing the half-axle vibration signal by using the segment cutting method and the Butterworth filter.

[0091] Step S502, calculating the semi-axle vibration characteristics of the driving segment, and extracting the principal components of the semi-axle vibration characteristics by using the principal component analysis method.

[0092] Step S503, using the SOM neural network and K-means clustering method to obtain the clustering clusters of the half-axle vibration signals of the bad road.

[0093] Step S504, determining the bad road location distribution and proportion of the entire road network of the target city based on the semi-axle vibration signal clusters and longitude and latitude information of the bad roads.

[0094] According to the method for determining the proportion of bad roads in the entire road network based on semi-axle vibration proposed in the embodiment of the present application, the position distribution result and proportion result of bad roads in the entire road network can be determined by the semi-axle vibration signal in the vehicle driving data. By extracting the driving segment containing the semi-axle vibration signal, the main component of the semi-axle vibration feature, and other information, the redundant data is effectively screened out while improving the accuracy of the results obtained in the embodiment of the present application. Clustering the main component of the semi-axle vibration feature into a cluster of semi-axle vibration signals effectively reduces the cost and time of bad road identification, improves the efficiency of bad road identification, and obtains the proportion result while also including the position distribution result, which is helpful for repairing bad roads and other operations, and has high practicality and scope of application. Therefore, the problems of the high cost of manual or model training in the methods in the related art, or the low efficiency of identification and positioning, the high time and energy consumption, and the difficulty in achieving the demand for determining the proportion of bad roads in the entire road network, and how to achieve the positioning and proportion acquisition of bad roads in the entire road network with lower data costs and more efficient methods are solved.

[0095] Next, a device for determining the bad road proportion of the entire road network based on semi-axle vibration proposed in an embodiment of the present application will be described with reference to the accompanying drawings.

[0096] Figure 6 It is a structural schematic diagram of a device for determining the bad road proportion of the entire road network based on semi-axle vibration according to an embodiment of the present application.

[0097] like Figure 6 As shown, the device 10 for determining the bad road proportion of the entire road network based on semi-axle vibration includes: an extraction module 100, an acquisition module 200 and a determination module 300.

[0098] The extraction module 100 is used to obtain the actual road driving data and the half-axle vibration signal of the vehicle in the entire road network of the target city, and extract the driving segment containing the half-axle vibration signal according to the actual road driving data and the half-axle vibration signal;

[0099] An acquisition module 200 is used to extract the main components of the semi-axle vibration characteristics according to the driving segment, so as to obtain the clustering clusters of the semi-axle vibration signals based on the main components of the semi-axle vibration characteristics;

[0100] The determination module 300 is used to determine the bad road ratio result of the entire road network of the target city according to the clustering clusters of the half-axle vibration signal and the current longitude and latitude information of the vehicle.

[0101] Optionally, in one embodiment of the present application, the extraction module 100 includes: a cutting unit, a first processing unit and a second processing unit.

[0102] The cutting unit is used to cut the actual road driving data to obtain the initial driving segment;

[0103] A first processing unit is used to obtain a corresponding half-axle vibration signal according to the start and end time of the initial driving segment, and perform low-pass filtering on the corresponding half-axle vibration signal to obtain a half-axle vibration signal that meets a preset processing condition;

[0104] The second processing unit is used to match and combine the half-axle vibration signal with the initial driving segment to obtain the driving segment.

[0105] Optionally, in one embodiment of the present application, the acquisition module 200 includes: a calculation unit and an extraction unit.

[0106] The calculation unit is used to calculate the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency of the semi-axle vibration signal and the average vehicle speed and average acceleration of the driving segment by using the driving segment;

[0107] The extraction unit is used to extract the main components of the semi-axle vibration characteristics based on the variance, the root mean square value, the peak factor, the kurtosis factor, the center of gravity frequency, the root mean square frequency, and the average vehicle speed and acceleration of the driving segment.

[0108] Optionally, in one embodiment of the present application, the acquisition module 200 includes: a clustering unit, a mapping unit and an acquisition unit.

[0109] The clustering unit is used to perform initial clustering analysis on the principal components of the semi-axle vibration characteristics using the target neural network to obtain the target neural network clustering results;

[0110] A mapping unit, used for mapping the driving segment to the competition layer node of the target neural network based on the target neural network clustering result, so as to obtain the vibration energy average value and vibration energy standard deviation of the semi-axle vibration signal of the competition layer node;

[0111] The acquisition unit is used to obtain the semi-axis vibration signal clustering clusters based on the vibration energy average value and the vibration energy standard deviation.

[0112] Optionally, in one embodiment of the present application, the determination module 300 includes: a positioning unit, a determination unit and a generation unit.

[0113] The positioning unit is used to locate the bad road position according to the clustering of the semi-axle vibration signal and the latitude and longitude information of the vehicle;

[0114] A determination unit, used to determine the bad road location distribution result of the entire road network of the target city according to the bad road location;

[0115] The generating unit is used to generate a weight result according to the bad road position distribution result.

[0116] It should be noted that the aforementioned explanation of the embodiment of the method for determining the bad road proportion of the entire road network based on semi-axle vibration is also applicable to the device for determining the bad road proportion of the entire road network based on semi-axle vibration of this embodiment, and will not be repeated here.

[0117] According to the device for determining the proportion of bad roads in the whole road network based on semi-axle vibration proposed in the embodiment of the present application, the position distribution result and proportion result of bad roads in the whole road network can be determined by the semi-axle vibration signal in the vehicle driving data. By extracting the driving segment containing the semi-axle vibration signal, the main component of the semi-axle vibration feature, and other information, the redundant data is effectively screened out while improving the accuracy of the results obtained in the embodiment of the present application. Clustering the main component of the semi-axle vibration feature into a cluster of semi-axle vibration signals effectively reduces the cost and time of bad road identification, improves the efficiency of bad road identification, and obtains the proportion result while also including the position distribution result, which is helpful for repairing bad roads, etc., and has high practicality and scope of application. Therefore, the problems of the high cost of manual or model training in the related technology, or the low efficiency of identification and positioning, the high time and energy consumption, and the difficulty in realizing the determination of the proportion of bad roads in the whole road network, and how to realize the positioning and proportion acquisition of bad roads in the whole road network with lower data cost and more efficient way are solved.

[0118] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0119] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0120] When the processor 702 executes the program, the method for determining the bad road proportion of the entire road network based on semi-axle vibration provided in the above embodiment is implemented.

[0121] Furthermore, the electronic device further comprises:

[0122] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0123] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0124] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0125] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0126] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0127] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0128] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above method for determining the bad road proportion of the entire road network based on semi-axle vibration.

[0129] An embodiment of the present application also provides a computer program product, including a computer program, which can run computer instructions. When the computer instructions are executed by a processor, the method for determining the bad road proportion of the entire road network based on semi-axle vibration provided in the embodiment of the present application is implemented.

[0130] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0131] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0132] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0133] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0134] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0135] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0137] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining the bad road ratio of the entire road network based on semi-axle vibration, characterized in that: The following steps are involved: Acquire actual road driving data and half-axle vibration signals of vehicles on the entire road network of the target city, and extract driving segments containing the half-axle vibration signals according to the actual road driving data and the half-axle vibration signals; Extracting the main components of the semi-axle vibration characteristics according to the driving segment, so as to obtain the clustering clusters of the semi-axle vibration signals based on the main components of the semi-axle vibration characteristics; The bad road proportion result of the entire road network of the target city is determined according to the clustering clusters of the semi-axle vibration signals and the current longitude and latitude information of the vehicle.

2. The method according to claim 1, characterized in that The step of extracting a driving segment containing the half-axle vibration signal according to the actual road driving data and the half-axle vibration signal comprises: Cutting the actual road driving data to obtain initial driving segments; Acquire a corresponding half-axle vibration signal according to the start and end time of the initial driving segment, and perform low-pass filtering on the corresponding half-axle vibration signal to obtain the half-axle vibration signal that meets a preset processing condition; The half-axle vibration signal is matched and combined with the initial running segment to obtain the running segment.

3. The method according to claim 1, characterized in that The extracting the main component of the half-axle vibration characteristics according to the driving segment comprises: Calculating the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency of the semi-axle vibration signal and the average vehicle speed and average acceleration of the driving segment by using the driving segment; The main components of the semi-axle vibration characteristics are extracted based on the variance, root mean square value, peak factor, kurtosis factor, center of gravity frequency, root mean square frequency and the average vehicle speed and acceleration of the driving segment.

4. The method according to claim 1, characterized in that The step of obtaining a cluster of semi-axle vibration signals based on the principal components of the semi-axle vibration characteristics comprises: Using a target neural network to perform an initial cluster analysis on the principal components of the semi-axle vibration characteristics, and obtaining a target neural network clustering result; Based on the target neural network clustering result, mapping the driving segment to the competition layer node of the target neural network to obtain the vibration energy average value and vibration energy standard deviation of the semi-axle vibration signal of the competition layer node; The semi-axis vibration signal clustering cluster is obtained based on the vibration energy average value and the vibration energy standard deviation.

5. The method according to claim 1, characterized in that The determining of the bad road proportion result of the entire road network of the target city according to the clustering of the semi-axle vibration signal and the current latitude and longitude information of the vehicle includes: Locating a bad road position according to the clustering of the half-axle vibration signal and the latitude and longitude information of the vehicle; Determine the bad road location distribution result of the entire road network of the target city according to the bad road location; The weight result is generated according to the bad road position distribution result.

6. A device for determining the bad road ratio of the entire road network based on semi-axle vibration, characterized in that: include: An extraction module, used to obtain actual road driving data and half-axle vibration signals of vehicles in the entire road network of the target city, and extract a driving segment containing the half-axle vibration signal according to the actual road driving data and the half-axle vibration signal; An acquisition module, used for extracting the main components of the semi-axle vibration characteristics according to the driving segment, so as to obtain the clustering clusters of the semi-axle vibration signals based on the main components of the semi-axle vibration characteristics; A determination module is used to determine the bad road proportion result of the entire road network of the target city according to the clustering clusters of the semi-axle vibration signals and the current longitude and latitude information of the vehicle.

7. The device according to claim 6, characterized in that The extraction module comprises: A cutting unit, used for cutting the actual road driving data to obtain an initial driving segment; A first processing unit, configured to obtain a corresponding half-axle vibration signal according to the start and end time of the initial driving segment, and perform low-pass filtering on the corresponding half-axle vibration signal to obtain the half-axle vibration signal that meets a preset processing condition; The second processing unit is used to match and combine the half-axle vibration signal with the initial driving segment to obtain the driving segment.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the bad road proportion of the entire road network based on semi-axle vibration as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for determining the bad road proportion of the entire road network based on semi-axle vibration as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed, it is used to implement the method for determining the bad road proportion of the entire road network based on semi-axle vibration as described in any one of claims 1-5.

Images