Mobile road surface ponding monitoring data analysis and processing system

Abstract

The invention relates to the technical field of data processing, in particular to a mobile pavement ponding monitoring data analysis and processing system, which comprises a data acquisition module used for acquiring a pavement ponding depth data sequence within a preset time period; the data analysis module is used for acquiring the interference degree of each datum in the pavement ponding depth data sequence; the filtering processing module is used for acquiring the self-adaptive weight of corresponding data according to the interference degree of each piece of data in any sliding window aiming at any sliding window when the sliding windows are used for carrying out sliding mean filtering on the road surface ponding depth data sequence, and carrying out mean filtering on all the data in any sliding window to obtain the self-adaptive weight of the data in any sliding window; obtaining a weighted mean value; and the data monitoring module is used for forming the weighted mean values of all the sliding windows into a target filtering data sequence, so that the denoising effect of filtering the pavement ponding depth data is enhanced, and the accuracy of subsequent ponding early warning based on the target filtering data sequence is improved.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a mobile road surface waterlogging monitoring data analysis and processing system. Background Art

[0002] In recent years, heavy rainfall has occurred frequently in summer (especially during the flood season), and the low terrain, rising river water levels, and imperfect urban drainage systems have led to frequent urban waterlogging, especially in low-lying areas, tunnels, overpasses, underground tracks, underground garages, underground shopping malls, etc. In order to avoid urban waterlogging and reduce casualties and economic losses, it is necessary to fully understand the urban waterlogging situation, conduct real-time monitoring of river water levels, tunnel bridges, low-lying road sections, etc., and establish an urban waterlogging early warning system.

[0003] In the prior art, when conducting mobile real-time monitoring of road waterlogging, the depth of road waterlogging is measured by installing sensors on a mobile vehicle, and the monitored road waterlogging depth data is transmitted in real time to a cloud server or a local data processing center. The collected road waterlogging depth data is then analyzed, and a waterlogging warning is generated based on the data analysis results. When the water level or rainfall exceeds the preset value, an alarm is automatically issued to notify relevant departments in advance to take countermeasures.

[0004] Since the monitored road waterlogging depth data is easily affected by the sensor's own equipment factors (such as the sensor itself is subject to electromagnetic interference, etc.) or external environmental factors (such as higher wind speeds will cause the sensor to shake to varying degrees, which may interfere with the sensor's measurement, and floating objects in the accumulated water will change the spectral reflection characteristics of the water body, causing changes in the performance of the water body in the remote sensing image, etc.), the collected road waterlogging depth data is inaccurate. Therefore, the collected road waterlogging depth data is subjected to sliding mean filtering. Specifically, the data mean in each sliding window is calculated as the denoised data after the corresponding sliding window filtering process. However, if the data mean of the sliding window is directly used as the denoised data after the corresponding filtering process, the denoising effect of the abnormal data in the sliding window will be reduced, thereby affecting the subsequent analysis results of the denoised data and the accuracy of the waterlogging warning.

[0005] Therefore, how to enhance the denoising effect of filtering the road water depth data to improve the accuracy of subsequent waterlogging warnings has become an urgent problem to be solved. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a mobile road surface waterlogging monitoring data analysis and processing system to solve the problem of how to enhance the denoising effect of filtering road surface waterlogging depth data to improve the accuracy of subsequent waterlogging warnings.

[0007] The present invention provides a mobile road surface water monitoring data analysis and processing system, which includes the following modules: A data acquisition module, used to obtain a road surface water depth data sequence within a preset time period; A data analysis module, used to obtain the interference degree of each data in the road surface water depth data sequence according to the position relationship of each data in the road surface water depth data sequence and the data difference between each data and its adjacent data; A filtering processing module, used for, in the process of performing sliding mean filtering on the road surface water depth data sequence using a sliding window of a preset size, obtaining adaptive weights of corresponding data for any sliding window according to the interference degree of each data in the any sliding window, and performing mean filtering on all data in the any sliding window according to the adaptive weight of each data in the any sliding window to obtain a corresponding weighted mean; The data monitoring module is used to form a target filtering data sequence with weighted means corresponding to all sliding windows, and to perform real-time monitoring and early warning of road surface waterlogging according to the target filtering data sequence.

[0008] Preferably, the data analysis module obtains the interference degree of each data in the road surface water depth data sequence according to the positional relationship of each data in the road surface water depth data sequence and the data difference between each data and its adjacent data, including: Respectively mark each data between the nth data to the N-n+1th data in the road surface water depth data sequence as target data in the road surface water depth data sequence, wherein N is the number of elements in the road surface water depth data sequence; For any target data, in the road surface water depth data sequence, a preset number of elements on both sides of the any target data are respectively obtained, and the elements and the any target data form a target data sequence, and the dissimilarity degree of the any target data is obtained according to the element differences in the target data sequence; According to adjacent data of the target data sequence in the road surface water depth data sequence, obtaining the local mutation degree of any target data; Performing a weighted summation on the non-similarity degree and the local mutation degree to obtain the interference degree of any target data; According to the interference degree of each target data, the interference degree of each non-target data in the road surface water depth data sequence is respectively obtained.

[0009] Preferably, the data analysis module obtains the degree of dissimilarity of any target data according to the element differences in the target data sequence, including: Mark each element in the target data sequence except any one of the target data as remaining data, obtain the absolute value of the difference between any one of the target data and each of the remaining data, obtain the average absolute value of the difference, use the average absolute value of the difference as a variable of the hyperbolic tangent function, and obtain the corresponding first hyperbolic tangent value; Obtaining the sum of the elements of the target data sequence, recorded as the first data sum, and respectively calculating the ratio of each element in the target data sequence to the first data sum to form a first ratio sequence; Obtain the mean of all remaining data in the target data sequence, use the mean as reference data for any target data, form a reference data sequence with each remaining data and the reference data, obtain the sum of elements of the reference data sequence, record it as the second data sum, calculate the ratio of each element in the reference data sequence to the second data sum, and form a second ratio sequence; Obtaining a cross entropy between the first ratio sequence and the second ratio sequence, and using the cross entropy as a variable of a hyperbolic tangent function to obtain a corresponding second hyperbolic tangent value; The average of the first hyperbolic tangent value and the second hyperbolic tangent value is used as the degree of dissimilarity of any target data.

[0010] Preferably, the data analysis module obtains the local mutation degree of any target data according to the adjacent data of the target data sequence in the road surface water depth data sequence, including: In the road waterlogging depth data sequence, a preset first number of elements before the target data sequence are obtained to form a first data sequence, and a first data change curve of the first data sequence is constructed in a two-dimensional plane, wherein the horizontal axis of the two-dimensional plane is time and the vertical axis is the road waterlogging depth; the preset first number of elements after the target data sequence are obtained to form a second data sequence, and a second data change curve of the second data sequence is constructed in the two-dimensional plane; the Spearman correlation coefficient of the first data change curve and the second data change curve is obtained, and the addition result of the Spearman correlation coefficient and a constant 1 is obtained, and the inverse of the addition result is normalized to obtain a first normalized result; Obtaining the mean of the elements in the road surface water depth data sequence except the elements in the target data sequence, recorded as a first mean, obtaining the mean of the elements in the target data sequence, recorded as a second mean, obtaining a first difference absolute value between the first mean and the second mean, and normalizing the first difference absolute value to obtain a second normalized result; The average of the first normalization result and the second normalization result is used as the local mutation degree of any target data.

[0011] Preferably, the data analysis module obtains the interference degree of each non-target data in the road surface water depth data sequence according to the interference degree of each target data, including: According to the interference degrees of a preset target number of continuous target data including the first target data in the road surface water depth data sequence, a minimum interference degree is obtained, and the minimum interference degree is used as the interference degree of each data before the nth data in the road surface water depth data sequence; According to the interference levels of the preset target number of continuous target data including the last target data in the road waterlogging depth data sequence, the minimum interference level is obtained, and the minimum interference level is used as the interference level of each data after the N-n+1th data in the road waterlogging depth data sequence.

[0012] Preferably, the filtering processing module obtains the adaptive weight of the corresponding data according to the interference degree of each data in any sliding window, including: According to the interference degree of each data in any sliding window, the total interference degree is obtained, the ratios of the total interference degree to the interference degree of each data are obtained, the total ratios are obtained, and the proportions between each ratio and the total ratios are obtained as the adaptive weights of the corresponding data.

[0013] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention provides a mobile road waterlogging monitoring data analysis and processing system, comprising a data acquisition module for acquiring a road waterlogging depth data sequence within a preset time period; a data acquisition module for acquiring a road waterlogging depth data sequence within a preset time period; a data analysis module for respectively acquiring the interference degree of each data in the road waterlogging depth data sequence according to the positional relationship of each data in the road waterlogging depth data sequence and the data difference between each data and its adjacent data; a filtering processing module for, in the process of performing sliding mean filtering on the road waterlogging depth data sequence using a sliding window of a preset size, for any sliding window, respectively acquiring the adaptive weight of the corresponding data according to the interference degree of each data in the any sliding window, performing mean filtering on all the data in the any sliding window according to the adaptive weight of each data in the any sliding window, and obtaining the corresponding weighted mean; a data monitoring module for forming a target filtering data sequence with the weighted means corresponding to all sliding windows, and performing real-time monitoring and early warning of road waterlogging according to the target filtering data sequence. Among them, when the road waterlogging depth data sequence is processed by sliding mean filtering, the adaptive weight of the corresponding data in each sliding window is obtained according to the interference degree of each data in each sliding window. The greater the interference degree, the smaller the adaptive weight of the corresponding data. Then all the data in each sliding window are mean filtered to obtain the weighted mean corresponding to each sliding window to form a target filtered data sequence, thereby eliminating the reduction of the denoising effect of the data in the sliding window due to the use of the data mean in the sliding window, enhancing the denoising effect of the filtering processing of the road waterlogging depth data, and improving the accuracy of the subsequent waterlogging warning based on the target filtered data sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0015] Figure 1 It is a structural block diagram of a mobile road surface waterlogging monitoring data analysis and processing system provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0016] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, but should not be understood as limiting the present disclosure.

[0017] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0018] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0019] See also Figure 1 , is a structural block diagram of a mobile road surface water monitoring data analysis and processing system provided in Embodiment 1 of the present invention, such as Figure 1 As shown, the system may include: The data acquisition module 11 is used to obtain a road surface water depth data sequence within a preset time period.

[0020] By installing sensors (such as mobile pavement condition monitors) on mobile monitoring vehicles, the depth of water on the road surface can be quickly and real-time monitored using the mobile pavement condition monitors while the mobile monitoring vehicles are driving, and a data series of road surface water depth within 2 hours of monitoring can be collected.

[0021] It should be noted that the monitoring time period set in the embodiment of the present invention is 2 hours, which is not limited and can be set according to specific real-time scenarios.

[0022] The data analysis module 12 is used to obtain the interference degree of each data in the road surface water depth data sequence according to the position relationship of each data in the road surface water depth data sequence and the data difference between each data and its adjacent data.

[0023] Taking into account that the road surface water depth data sequence may be subject to different degrees of interference during the collection process, including environmental factors, sensor factors, etc., therefore, in the prior art, the collected road surface water depth data sequence is usually filtered using a sliding mean filtering technique to obtain a denoised road surface water depth data sequence. However, due to the influence of the sensor's own equipment factors or external environmental factors, the degree of interference of each collected road surface water depth data is different. If the data mean in the sliding window is directly used as the denoised data after filtering, the denoising effect on the abnormal data in the sliding window is reduced, thereby affecting the denoising effect on the road surface water depth data sequence.

[0024] Therefore, in order to solve the above problems, before performing sliding mean filtering on the road surface water depth data sequence, the embodiment of the present invention first obtains the interference degree of each data in the road surface water depth data sequence, so as to assign an adaptive weight to each data according to the interference degree during subsequent sliding mean filtering, so as to improve the filtering effect of the sliding mean filtering.

[0025] For any data in the road waterlogging depth data sequence, when it is interfered by sensors and environmental factors, it manifests as: the similarity between the data and the adjacent data is low or the local mutation of the neighborhood where the data is located is high, wherein the degree of similarity between the data and the adjacent data reflects the degree of correlation between the data and the adjacent data. The higher the similarity, the higher the correlation between the data and the adjacent data, and the less interference. Because the similarity between the data and the adjacent data does not necessarily represent whether the neighborhood where the data is located has mutation, it is possible that the data has a high degree of similarity with the adjacent data, but the local mutation of the neighborhood where the data is located is large. This is also the case where the waterlogging data is interfered with. Therefore, it is necessary to comprehensively analyze the degree of noise interference of each data in the road waterlogging depth data sequence.

[0026] The method for obtaining the noise interference degree of each data in the road surface water depth data sequence is as follows: (1) Each data between the nth data to the (N-n+1th) data in the road surface water depth data sequence is marked as target data in the road surface water depth data sequence, where N is the number of elements in the road surface water depth data sequence.

[0027] In one implementation, n=6 is set, and the 6th to N-5th data in the road surface water depth data sequence are marked as target data in the road surface water depth data sequence.

[0028] (2) For any target data, in the road surface water depth data sequence, a preset number of elements on both sides of the any target data are respectively obtained, and the elements are combined with the any target data to form a target data sequence, and the degree of dissimilarity of the any target data is obtained according to the element differences in the target data sequence.

[0029] Specifically, each element in the target data sequence except any one of the target data is marked as remaining data, and the absolute value of the difference between any one of the target data and each of the remaining data is obtained to obtain an average absolute value of the difference, and the average absolute value of the difference is used as a variable of the hyperbolic tangent function to obtain a corresponding first hyperbolic tangent value; Obtaining the sum of the elements of the target data sequence, recorded as the first data sum, and respectively calculating the ratio of each element in the target data sequence to the first data sum to form a first ratio sequence; Obtain the mean of all remaining data in the target data sequence, use the mean as reference data for any target data, form a reference data sequence with each remaining data and the reference data, obtain the sum of elements of the reference data sequence, record it as the second data sum, calculate the ratio of each element in the reference data sequence to the second data sum, and form a second ratio sequence; Obtaining a cross entropy between the first ratio sequence and the second ratio sequence, and using the cross entropy as a variable of a hyperbolic tangent function to obtain a corresponding second hyperbolic tangent value; The average of the first hyperbolic tangent value and the second hyperbolic tangent value is used as the degree of dissimilarity of any target data.

[0030] In one embodiment, considering that the higher the correlation degree of adjacent data in a local area, that is, the greater the similarity, if the similarity between a certain data and its adjacent data is lower, that is, the correlation degree between the data and its adjacent data is lower, it indicates that the data is more likely to be interfered by noise. Therefore, the non-similarity degree of the data is obtained to indicate the possibility that the data is interfered by noise.

[0031] Therefore, taking the i-th target data as an example, the preset number is set to 2, and there is no limit on this. In the road surface water depth data sequence, the 2 consecutive elements adjacent to the left and the 2 consecutive elements adjacent to the right of the i-th target data are respectively obtained, and they are combined with the i-th target data to form a target data sequence. Each element in the target data sequence except the i-th target data is marked as the remaining data, and the absolute value of the difference between the i-th target data and each of the remaining data is obtained to obtain the average absolute value of the difference.

[0032] The proportion of each element in the target data sequence in all elements is obtained respectively to form a first ratio sequence, the mean of all remaining data is obtained, the mean is used as the reference data of the i-th target data, the reference data and all remaining data are combined into a reference data sequence, the proportion of each element in the reference data sequence in all elements is obtained respectively to form a second ratio sequence, and the cross entropy of the first ratio sequence and the second ratio sequence is calculated.

[0033] According to the average absolute value of the difference and the cross entropy, the degree of dissimilarity of the i-th target data is obtained, and its expression is: in, Indicates the degree of dissimilarity of the i-th target data, represents the i-th target data, represents the hth remaining data in the target data sequence, H represents the total number of remaining data in the target data sequence, p(d) represents the dth proportion in the first ratio sequence, q(d) represents the dth proportion in the second ratio sequence, lg() represents the logarithmic function with a constant as the base 10, tanh() represents the hyperbolic tangent function, and || represents the absolute value sign.

[0034] It should be noted that The larger the value of , the greater the difference between the i-th target data and its adjacent elements, that is, the lower the correlation between the i-th target data and its adjacent elements, indicating that the i-th target data is more likely to be abnormal data, that is, the greater the possibility of being interfered by noise, and the greater the degree of non-similarity of the corresponding i-th target data; The larger the value of , the greater the difference between the target data sequence and the reference data sequence, that is, the greater the difference between the ith target data and its adjacent elements, indicating that the ith target data is more likely to be abnormal data, that is, the greater the possibility of being interfered by noise, and the greater the degree of non-similarity of the corresponding ith target data.

[0035] (3) Obtaining the degree of local mutation of any target data according to adjacent data of the target data sequence in the road surface water depth data sequence.

[0036] Specifically, in the road surface water depth data sequence, a preset first number of elements before the target data sequence are obtained to form a first data sequence, and a first data change curve of the first data sequence is constructed in a two-dimensional plane, wherein the horizontal axis of the two-dimensional plane is time, and the vertical axis is the depth of road surface water, and the preset first number of elements after the target data sequence are obtained to form a second data sequence, and a second data change curve of the second data sequence is constructed in the two-dimensional plane, and the Spearman correlation coefficient of the first data change curve and the second data change curve is obtained, and the addition result of the Spearman correlation coefficient and a constant 1 is obtained, and the inverse of the addition result is normalized to obtain a first normalized result; Obtaining the mean of the elements in the road surface water depth data sequence except the elements in the target data sequence, recorded as a first mean, obtaining the mean of the elements in the target data sequence, recorded as a second mean, obtaining a first difference absolute value between the first mean and the second mean, and normalizing the first difference absolute value to obtain a second normalized result; The average of the first normalization result and the second normalization result is used as the local mutation degree of any target data.

[0037] In one embodiment, after obtaining the degree of dissimilarity, considering that within the local neighborhood to which the current data belongs, if the degree of correlation between the current data and its adjacent data is greater, it does not necessarily mean that the current data is less disturbed by noise, but it may also be due to the fact that all data within the local neighborhood to which the current data belongs are disturbed by noise and mutate, resulting in a greater degree of correlation between the current data and its adjacent data, that is, the data difference between the current data and its adjacent data is relatively small. In order to further prove whether the current data is disturbed by noise, the local area where the current data is located is taken as a whole, and according to the difference between the data on both sides of the local area where the current data is located, if the difference between the data on both sides of the local area is greater, and the overall data in the local area is significantly different from the remaining data, it means that the overall local area where the current data is located is more likely to be disturbed by noise, thereby further indicating that the current data is more likely to be noise data. Therefore, by obtaining the local mutation degree of the local area where the current data is located as the local mutation degree of the current data, it is further proved whether the current data is disturbed by noise.

[0038] Therefore, taking the i-th target data as an example, in the road waterlogging depth data sequence, the target data sequence corresponding to the i-th target data is obtained, and based on the value of the above n and the value of the preset number, the preset first number is set to 3, wherein the value of the preset first number is greater than 2 and less than or equal to 3, and the three elements before the target data sequence are obtained to form a first data sequence, and in a two-dimensional plane, a first data change curve of the first data sequence is constructed, wherein the horizontal axis of the two-dimensional plane represents time, and the vertical axis represents the depth of road waterlogging, and the three elements after the target data sequence are obtained to form a second data sequence, and in the two-dimensional plane, a second data change curve of the second data sequence is constructed, and the Spearman correlation coefficient of the first fitting curve and the second fitting curve is obtained, wherein the Spearman correlation coefficient belongs to the prior art and will not be repeated here.

[0039] Obtain the mean of the elements in the road surface water depth data sequence except the elements in the target data sequence, recorded as the first mean, obtain the mean of the elements in the target data sequence, recorded as the second mean, and obtain the local mutation degree of the i-th target data according to the Spearman correlation coefficient, the first mean and the second mean. The expression is: in, Indicates the degree of local mutation of the i-th target data, represents the first data variation curve, represents the second data variation curve, represents the Spearman correlation coefficient, D represents the target data sequence, represents the jth data in the target data sequence, represents the kth data in the road water depth data sequence except the target data sequence, N represents the number of elements in the road water depth data sequence, R represents the number of elements in the target data sequence, | | represents the absolute value sign, norm() represents the normalization function, and 1 represents a constant.

[0040] It should be noted that The smaller the value is, the lower the correlation between the first data change curve and the second data change curve is, that is, the more inconsistent the change degree of the data on both sides of the target data sequence is, indicating that the target data sequence corresponding to the i-th target data is more likely to be interfered by noise, that is, the greater the possibility that the i-th target data is abnormal data, and the greater the degree of local mutation corresponding to the i-th target data; represents the mean of the target data sequence, represents the mean of all elements in the road surface water depth data sequence except the elements in the target data sequence, The larger the value of , the greater the difference between the mean of the local neighborhood where the ith target data is located and the mean of the rest of the data, indicating that the data in the local neighborhood where the ith target data is located is more discrete than the rest of the data, that is, the greater the overall fluctuation of the local neighborhood where the ith target data is located, the greater the possibility of being disturbed by noise, that is, the greater the possibility that the ith target data is abnormal data, and the greater the local mutation degree of the corresponding ith target data.

[0041] (4) Taking a weighted sum of the non-similarity degree and the local mutation degree, the interference degree of any target data is obtained.

[0042] In one embodiment, after obtaining the non-similarity degree and local mutation degree of the target data, it is considered that the higher the non-similarity degree and the greater the local mutation degree of the target data, the greater the possibility that the target data is interfered by noise, and the corresponding interference degree is greater. Conversely, the lower the non-similarity degree and the smaller the local mutation degree, the smaller the possibility that the target data is interfered by noise, and the corresponding interference degree is smaller.

[0043] Therefore, taking the i-th target data as an example, according to the non-similarity and local mutation degree of the i-th target data, the interference degree of the i-th target data is obtained, and its expression is: in, represents the interference degree of the i-th target data, Indicates the degree of dissimilarity of the i-th target data, Indicates the degree of local mutation of the i-th target data, The weight representing the degree of dissimilarity, The weight representing the degree of local mutation.

[0044] Preferably, the weights of the non-similarity degree and the local mutation degree set in the embodiment of the present invention are empirical values, that is, There is no restriction on this, and it can be set according to the specific implementation scenario.

[0045] It should be noted that The larger the value of , the smaller the correlation between the i-th target data and its adjacent data, indicating that the i-th target data is more likely to be abnormal data, that is, the greater the possibility of being interfered by noise, and the greater the interference degree of the i-th target data; The larger the value of , the greater the overall fluctuation of the local neighborhood where the ith target data is located, indicating that the local neighborhood where the ith target data is located is more likely to be disturbed by noise as a whole, that is, the greater the possibility that the ith target data is abnormal data, and the greater the degree of interference of the corresponding ith target data.

[0046] According to the above method for obtaining the interference degree of the i-th target data, the interference degree of each target data is obtained respectively.

[0047] (5) According to the interference degree of each target data, respectively obtain the interference degree of each non-target data in the road surface water depth data sequence.

[0048] Specifically, according to the interference degrees of a preset target number of continuous target data including the first target data in the road surface water depth data sequence, a minimum interference degree is obtained, and the minimum interference degree is used as the interference degree of each data before the nth data in the road surface water depth data sequence; According to the interference levels of the preset target number of continuous target data including the last target data in the road waterlogging depth data sequence, the minimum interference level is obtained, and the minimum interference level is used as the interference level of each data after the N-n+1th data in the road waterlogging depth data sequence.

[0049] In one embodiment, considering that a large number of road waterlogging depth data are actually monitored, the 5 data before the 6th data and the 5 data after the N-5th data in the road waterlogging depth data sequence have little impact on the overall data, and the 5 data before the 6th data have a high degree of correlation with the local data adjacent to its right, and the 5 data after the N-5th data have a high degree of correlation with the local data adjacent to its left.

[0050] Therefore, the preset target number is set to 5, with no restriction on this. The interference degrees of the nth data to the n+4th data in the road waterlogging depth data sequence (that is, the interference degrees of the 6th data to the 10th data in the road waterlogging depth data sequence) are obtained respectively, and the minimum interference degree is obtained. The minimum interference degree is used as the interference degree of the 1st data to the 5th data in the road waterlogging depth data sequence.

[0051] The interference degrees of the N-n+1th data to the Nn-3th data in the road waterlogging depth data sequence (i.e., the interference degrees of the N-5th data to the N-9th data in the road waterlogging depth data sequence) are respectively obtained to obtain the minimum interference degree, and the minimum interference degree is used as the interference degree of the N-4th data to the Nth data in the road waterlogging depth data sequence.

[0052] At this point, the interference degree of each data in the road surface water depth data sequence is obtained.

[0053] The filtering processing module 13 is used to obtain the adaptive weights of the corresponding data in any sliding window according to the interference degree of each data in any sliding window during the process of performing sliding mean filtering on the road surface water depth data sequence using a sliding window of a preset size, and perform mean filtering on all the data in any sliding window according to the adaptive weight of each data in any sliding window to obtain the corresponding weighted mean.

[0054] After obtaining the interference degree of each data in the road surface water depth data sequence, the sliding mean filtering process of the road surface water depth data sequence is optimized based on the interference degree of each data in the road surface water depth data sequence to enhance the overall denoising effect of the sliding mean filtering of the road surface water depth data sequence. Therefore, in the process of sliding mean filtering the road surface water depth data sequence using a sliding window of a preset size, the preset size is first set to 10, without any restriction, and then, for any sliding window, according to the interference degree of each data in any sliding window, the adaptive weights of the corresponding data are respectively obtained.

[0055] Taking into account the different interference levels of each data in the sliding window, if a certain data in the sliding window is subject to greater noise interference, it indicates that the data is more affected by abnormal interference. If the data is given the same weight as the normal data in the sliding window, the denoising effect of the data will be reduced. Therefore, in an embodiment of the present invention, a smaller weight is given to data with a large degree of interference, thereby improving the filtering effect of the sliding window, thereby weakening the impact of noise interference when the road surface water depth data sequence is subjected to sliding mean filtering.

[0056] According to the interference degree of each data in any sliding window, the adaptive weight of the corresponding data is obtained respectively, including: According to the interference degree of each data in any sliding window, the total interference degree is obtained, the ratios of the total interference degree to the interference degree of each data are obtained, the total ratios are obtained, and the proportions between each ratio and the total ratios are obtained as the adaptive weights of the corresponding data.

[0057] In one embodiment, taking the i-th data in the k-th sliding window as an example, according to the interference degree of the i-th data in the k-th sliding window, the adaptive weight corresponding to the i-th data in the k-th sliding window is obtained, and its expression is: in, represents the adaptive weight corresponding to the i-th data in the k-th sliding window, represents the interference degree of the i-th data in the k-th sliding window, It represents the ratio between the sum of the interference levels of all data in the k-th sliding window and the interference level of the i-th data.

[0058] According to the above method for obtaining the adaptive weight corresponding to the i-th data in the k-th sliding window, the adaptive weight corresponding to each data in the k-th sliding window is obtained respectively. According to the adaptive weight corresponding to each data in the k-th sliding window, after obtaining the adaptive weight corresponding to each data in the k-th sliding window, the k-th sliding window is subjected to weighted mean filtering based on the adaptive weight to obtain the corresponding average value, which is recorded as the weighted mean. The calculation expression of the weighted mean is: in, represents the weighted mean corresponding to the kth sliding window, M represents the number of elements in the kth sliding window, represents the adaptive weight corresponding to the jth data in the kth sliding window, Represents the j-th data in the k-th sliding window.

[0059] The data monitoring module 14 is used to form a target filtering data sequence from the weighted mean values ​​corresponding to all sliding windows, and to perform real-time monitoring and early warning of road surface waterlogging according to the target filtering data sequence.

[0060] According to the above method of obtaining the weighted mean corresponding to the kth sliding window, the weighted mean corresponding to each sliding window in the sliding mean filtering process of the road waterlogging depth data sequence is obtained respectively, and all weighted means are combined into a target filtering data sequence. At this time, the sliding mean filtering process of the road waterlogging depth data sequence is completed. Afterwards, the target filtering data sequence is analyzed, and a visualization report is generated according to the analysis results, high-risk areas are identified, and waterlogging warning information is generated, etc., so that subsequent waterlogging warnings are more accurate and efficient. For example, the abnormal threshold of waterlogging is set to 15cm, and there is no restriction on this. For any weighted mean in the target filtering data sequence, if the weighted mean exceeds the abnormal threshold of waterlogging, a waterlogging warning is automatically triggered to remind the staff to take corresponding measures.

[0061] It should be noted that the focus of the present invention is on how to optimize the sliding mean filtering processing of the road waterlogging depth data sequence, and real-time monitoring and early warning of road waterlogging based on the filtered road waterlogging depth data sequence (i.e., the target filtered data sequence) belongs to the existing technology and will not be described in detail here.

[0062] In summary, the present invention provides a mobile road waterlogging monitoring data analysis and processing system, including a data acquisition module, used to obtain a road waterlogging depth data sequence within a preset time period; a data acquisition module, used to obtain a road waterlogging depth data sequence within a preset time period; a data analysis module, used to obtain the interference degree of each data in the road waterlogging depth data sequence according to the positional relationship of each data in the road waterlogging depth data sequence and the data difference between each data and its adjacent data; a filtering processing module, used to, in the process of performing sliding mean filtering on the road waterlogging depth data sequence using a sliding window of a preset size, for any sliding window, according to the interference degree of each data in the any sliding window, respectively obtain the adaptive weight of the corresponding data, and according to the adaptive weight of each data in the any sliding window, perform mean filtering on all the data in the any sliding window to obtain the corresponding weighted mean; a data monitoring module, used to form a target filtering data sequence with the weighted means corresponding to all sliding windows, and perform real-time monitoring and early warning of road waterlogging according to the target filtering data sequence. Among them, when the road waterlogging depth data sequence is processed by sliding mean filtering, the adaptive weight of the corresponding data in each sliding window is obtained according to the interference degree of each data in each sliding window. The greater the interference degree, the smaller the adaptive weight of the corresponding data. Then all the data in each sliding window are mean filtered to obtain the weighted mean corresponding to each sliding window to form a target filtered data sequence, thereby eliminating the reduction of the denoising effect of the data in the sliding window due to the use of the data mean in the sliding window, enhancing the denoising effect of the filtering processing of the road waterlogging depth data, and improving the accuracy of the subsequent waterlogging warning based on the target filtered data sequence.

[0063] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A mobile road surface water monitoring data analysis and processing system, characterized in that: The system comprises: A data acquisition module, used to obtain a road surface water depth data sequence within a preset time period; A data analysis module, used to obtain the interference degree of each data in the road surface water depth data sequence according to the position relationship of each data in the road surface water depth data sequence and the data difference between each data and its adjacent data; A filtering processing module, used for, in the process of performing sliding mean filtering on the road surface water depth data sequence using a sliding window of a preset size, obtaining adaptive weights of corresponding data for any sliding window according to the interference degree of each data in the any sliding window, and performing mean filtering on all data in the any sliding window according to the adaptive weight of each data in the any sliding window to obtain a corresponding weighted mean; The data monitoring module is used to form a target filtering data sequence with weighted means corresponding to all sliding windows, and to perform real-time monitoring and early warning of road surface waterlogging according to the target filtering data sequence.

2. A mobile road surface waterlogging monitoring data analysis and processing system according to claim 1, characterized in that: The data analysis module obtains the interference degree of each data in the road surface water depth data sequence according to the position relationship of each data in the road surface water depth data sequence and the data difference between each data and its adjacent data, including: Respectively mark each data between the nth data to the N-n+1th data in the road surface water depth data sequence as target data in the road surface water depth data sequence, wherein N is the number of elements in the road surface water depth data sequence; For any target data, in the road surface water depth data sequence, a preset number of elements on both sides of the any target data are respectively obtained, and the elements and the any target data form a target data sequence, and the dissimilarity degree of the any target data is obtained according to the element differences in the target data sequence; According to adjacent data of the target data sequence in the road surface water depth data sequence, obtaining the local mutation degree of any target data; Performing a weighted summation on the non-similarity degree and the local mutation degree to obtain the interference degree of any target data; According to the interference degree of each target data, the interference degree of each non-target data in the road surface water depth data sequence is respectively obtained.

3. A mobile road surface water monitoring data analysis and processing system according to claim 2, characterized in that: The data analysis module obtains the degree of dissimilarity of any target data according to the element differences in the target data sequence, including: Mark each element in the target data sequence except any one of the target data as remaining data, obtain the absolute value of the difference between any one of the target data and each of the remaining data, obtain the average absolute value of the difference, use the average absolute value of the difference as a variable of the hyperbolic tangent function, and obtain the corresponding first hyperbolic tangent value; Obtaining the sum of the elements of the target data sequence, recorded as the first data sum, and respectively calculating the ratio of each element in the target data sequence to the first data sum to form a first ratio sequence; Obtain the mean of all remaining data in the target data sequence, use the mean as reference data for any target data, form a reference data sequence with each remaining data and the reference data, obtain the sum of elements of the reference data sequence, record it as the second data sum, calculate the ratio of each element in the reference data sequence to the second data sum, and form a second ratio sequence; Obtaining a cross entropy between the first ratio sequence and the second ratio sequence, and using the cross entropy as a variable of a hyperbolic tangent function to obtain a corresponding second hyperbolic tangent value; The average of the first hyperbolic tangent value and the second hyperbolic tangent value is used as the degree of dissimilarity of any target data.

4. A mobile road surface waterlogging monitoring data analysis and processing system according to claim 2, characterized in that: The data analysis module obtains the local mutation degree of any target data according to the adjacent data of the target data sequence in the road surface water depth data sequence, including: In the road waterlogging depth data sequence, a preset first number of elements before the target data sequence are obtained to form a first data sequence, and a first data change curve of the first data sequence is constructed in a two-dimensional plane, wherein the horizontal axis of the two-dimensional plane is time and the vertical axis is the road waterlogging depth; the preset first number of elements after the target data sequence are obtained to form a second data sequence, and a second data change curve of the second data sequence is constructed in the two-dimensional plane; the Spearman correlation coefficient of the first data change curve and the second data change curve is obtained, and the addition result of the Spearman correlation coefficient and a constant 1 is obtained, and the inverse of the addition result is normalized to obtain a first normalized result; Obtaining the mean of the elements in the road surface water depth data sequence except the elements in the target data sequence, recorded as a first mean, obtaining the mean of the elements in the target data sequence, recorded as a second mean, obtaining a first difference absolute value between the first mean and the second mean, and normalizing the first difference absolute value to obtain a second normalized result; The average of the first normalization result and the second normalization result is used as the local mutation degree of any target data.

5. A mobile road surface waterlogging monitoring data analysis and processing system according to claim 2, characterized in that: The data analysis module obtains the interference degree of each non-target data in the road surface water depth data sequence according to the interference degree of each target data, including: According to the interference degrees of a preset target number of continuous target data including the first target data in the road surface water depth data sequence, a minimum interference degree is obtained, and the minimum interference degree is used as the interference degree of each data before the nth data in the road surface water depth data sequence; According to the interference levels of the preset target number of continuous target data including the last target data in the road waterlogging depth data sequence, the minimum interference level is obtained, and the minimum interference level is used as the interference level of each data after the N-n+1th data in the road waterlogging depth data sequence.

6. A mobile road surface water monitoring data analysis and processing system according to claim 1, characterized in that: The filtering processing module obtains the adaptive weight of the corresponding data according to the interference degree of each data in any sliding window, including: According to the interference degree of each data in any sliding window, the total interference degree is obtained, the ratios of the total interference degree to the interference degree of each data are obtained, the total ratio is obtained, and the ratio between each ratio and the total ratio is obtained as the adaptive weight of the corresponding data.

Images