Power transmission line engineering index mutual influence prediction method based on multi-dimensional data analysis

Abstract

The invention relates to the technical field of power index prediction, in particular to a power transmission line engineering index mutual influence prediction method based on multi-dimensional data analysis. The method comprises the following steps: firstly, obtaining a time sequence of state parameters of each tower under each index and a current state vector of each tower; and then obtaining the index importance of each index, the state fluctuation coefficient of each tower and the state influence weight of each index of each tower, and then obtaining the final state influence weight of each index of each tower at the current moment, thereby obtaining the prediction state vector of each tower in combination with the current state vector. According to the method, change correlation and historical fluctuation of state parameters under pole tower multi-dimensional indexes are analyzed, and the attention weight of each index of each pole tower is evaluated, so that the input of a Kalman filtering algorithm is adjusted, the algorithm captures index characteristics which have great influence on the pole tower state change, and the pole tower state change is accurately determined. And thus, the prediction accuracy of the state of each tower in the power transmission line project is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power index prediction, and in particular to a method for predicting mutual influence of transmission line engineering indexes based on multidimensional data analysis. Background Art

[0002] In modern power systems, transmission lines are important channels for transmitting electricity from power plants to users, and poles and towers are important supporting structures for erecting transmission lines, which will directly affect the reliability and stability of transmission line projects. However, factors such as changeable meteorological environments and complex terrain conditions will threaten the performance and safety of transmission line projects. Therefore, safety monitoring and risk prediction of transmission line projects are crucial.

[0003] In the process of safety monitoring and risk prediction of transmission line projects, the current state of towers and transmission lines is evaluated by monitoring and analyzing the state parameters under multi-dimensional indicators in the transmission line project, and the current state is input into the Kalman filter to predict the future state; however, there may be certain correlation changes between the state parameters of the multi-dimensional indicators in the transmission line project, and each dimensional indicator has a different degree of influence on the state of the transmission line project. Directly using the Kalman filter will affect the prediction accuracy of the future state of the transmission line project. Summary of the invention

[0004] In order to solve the technical problem that the existing technology has poor prediction accuracy for the future state of the transmission line project, the purpose of the present invention is to provide a method for predicting the mutual influence of transmission line project indicators based on multidimensional data analysis. The technical solution adopted is as follows:

[0005] At the current moment, obtain the time series of state parameters of each tower under each indicator in the transmission line project within a preset historical period, and the current state vector of each tower; the current state vector includes the state parameters under each indicator;

[0006] According to the change correlation between different indicators of different towers, the indicator importance of each indicator is obtained; according to the fluctuation change of the time series of each tower under each indicator, relative to the deviation of the fluctuation change of the time series of other towers under each indicator in the local geographical area, the state fluctuation coefficient of each tower is obtained;

[0007] According to the fluctuation change of the state parameter in the time series under each indicator of each tower, combined with the state fluctuation coefficient of each tower and the indicator importance of each indicator, the state influence weight of each indicator of each tower is obtained; at the current moment, according to the state influence weight of each indicator of each tower, and the deviation of the state parameter of each tower relative to the state parameter of all towers under the same indicator, the final state influence weight of each indicator of each tower is obtained;

[0008] According to the final state influence weight and the current state vector, the predicted state vector of each tower at the next acquisition moment is obtained.

[0009] Furthermore, the method for obtaining the indicator importance includes:

[0010] The state vector of each tower at each acquisition time is obtained, and the state transfer matrix of each tower is obtained based on the Kalman filter and the state vectors at all adjacent acquisition times; the indicator importance of each indicator is obtained by combining the matrix elements in the state transfer matrix of all towers.

[0011] Furthermore, the method of obtaining the indicator importance of each indicator by integrating the matrix elements in the state transfer matrix of all towers includes:

[0012] Each row and each column in the state transfer matrix corresponds to an indicator; the sum of all elements in each row of the state transfer matrix is ​​used as the first dependent reference value under the corresponding indicator, and the sum of all elements in each column of the state transfer matrix is ​​used as the second dependent reference value under the corresponding indicator;

[0013] Under each indicator, the sum of the products of the first dependence reference value and the second dependence reference value of all towers is taken as a first parameter, the product of the sum of the first dependence reference values ​​of all towers and the sum of the first dependence reference values ​​of all towers is taken as a second parameter, the sum of the squares of the second dependence reference values ​​of all towers is taken as a third parameter, and the sum squares of the second dependence reference values ​​of all towers is taken as a fourth parameter;

[0014] The difference between the first parameter and the second parameter is used as a numerator, the difference between the third parameter and the fourth parameter is used as a denominator, and the fractional ratio is used as the indicator importance of each indicator.

[0015] Furthermore, the method for obtaining the state fluctuation coefficient includes:

[0016] According to the fluctuation change of the state parameter in the time series of each tower under each indicator, the fluctuation evaluation parameter of each indicator of each tower is obtained; the overall fluctuation parameter of each tower is obtained by integrating the fluctuation evaluation parameters of all indicators of each tower;

[0017] Based on the connection conditions of the pole towers in the transmission line project, a pole tower sorting sequence in the transmission line project is obtained; a fluctuation sequence is constructed according to the overall fluctuation parameter of each pole tower, wherein the fluctuation sequence has the same sequence order as the pole tower sorting sequence; and according to the change of the fluctuation sequence, the pole tower sorting sequence is divided to obtain all pole tower subsequences;

[0018] According to the overall fluctuation parameter of each tower, the state fluctuation coefficient of each tower is obtained relative to the degree of deviation of the overall fluctuation parameter of all towers in the tower subsequence to which each tower belongs; the degree of deviation is positively correlated with the state fluctuation coefficient.

[0019] Furthermore, the method for obtaining the fluctuation evaluation parameter includes:

[0020] According to the local fluctuation similarity of the time series of each tower under each indicator, the time series is segmented to obtain all sequence sub-segments;

[0021] According to the total number of the sequence sub-segments and the sequence length of the last sequence sub-segment in time series, the fluctuation evaluation parameter of each indicator of each tower is obtained; the sequence length is negatively correlated with the fluctuation evaluation parameter, and the total number is positively correlated with the fluctuation evaluation parameter.

[0022] Furthermore, the method for obtaining the tower subsequence includes:

[0023] Obtain a first-order difference sequence of the fluctuation sequence. If two adjacent sequence elements in the first-order difference sequence have different numbers, use the largest number among the numbers corresponding to the two adjacent sequence elements as the segmentation number.

[0024] The sequence element corresponding to the segmentation sequence number in the tower sorting sequence is used as the sequence right endpoint of each tower subsequence, and the next sequence element adjacent to the right endpoint of each sequence is used as the sequence left endpoint of the next tower subsequence;

[0025] A tower sequence subsegment is obtained based on the sequence right endpoint and the sequence left endpoint of each tower subsequence.

[0026] Furthermore, the method for obtaining the state influence weight includes:

[0027] The state fluctuation coefficient of each tower is multiplied by the indicator importance of each indicator, and the product is used as the first weight parameter; the fluctuation evaluation parameter of each indicator of each tower is normalized, and the normalized result is used as the second weight parameter; the product of the first weight parameter and the second weight parameter is used as the state influence weight of the corresponding indicator of the corresponding tower.

[0028] Furthermore, the method for obtaining the final state influence weight includes:

[0029] Under the same indicator, the fluctuation weight of each indicator of each tower is obtained according to the deviation of the state parameter of each tower relative to the average level of the state parameter of all towers; the corresponding state influence weight is weighted by using the fluctuation weight, and the weighted result is used as the final state influence weight of each indicator of each tower.

[0030] Furthermore, the method for obtaining the predicted state vector includes:

[0031] The current state vector of the corresponding tower is weighted by using the final state influence weight, the weighted result is used as the input of the Kalman filter, and the predicted state vector of the next acquisition moment of the corresponding tower is output.

[0032] Furthermore, the indicators include at least load, tension ratio, height, gear spacing, weight, and dancing amplitude.

[0033] The present invention has the following beneficial effects:

[0034] The present invention obtains, at the current moment, the time series of state parameters of each tower under each indicator in the transmission line project within a preset historical period, and the current state vector of each tower, to provide a data basis for subsequent analysis of fluctuation association and prediction; obtains the indicator importance of each indicator according to the change association between different indicators of different towers; the indicator importance reflects the influence of the indicator on the state change of the transmission line project to a certain extent, so as to facilitate the subsequent determination of the attention paid to each indicator in the current state vector; obtains the state fluctuation coefficient of each tower according to the fluctuation change of the time series of each tower under each indicator and the deviation of the fluctuation change of the time series of other towers in the local geographical area under each indicator, the state fluctuation coefficient reflects the state stability of each tower, and prepares for the consideration weight of each indicator of each tower in the subsequent evaluation; The fluctuation change of state parameters in the time series under various indicators, combined with the state fluctuation coefficient of each tower and the indicator importance of each indicator, obtains the state influence weight of each indicator of each tower; at the current moment, according to the state influence weight of each indicator of each tower, and the deviation of the state parameter of each tower relative to the state parameter of all towers under the same indicator, obtains the final state influence weight of each indicator of each tower; the state influence weight reflects the attention weight of each indicator of each tower, so as to be able to capture the state change migration of the tower in time; the final state influence weight combines the state deviation degree of the tower at the current moment, and more accurately evaluates the attention degree of the state parameter of each indicator of each tower, so as to improve the state prediction accuracy; according to the final state influence weight and the current state vector, obtains the predicted state vector of each tower at the next acquisition moment. The present invention analyzes the change correlation and historical fluctuation of the state parameters under the multi-dimensional indicators of the tower, evaluates the attention weight of each indicator of each tower, thereby adjusting the input of the Kalman filter algorithm, so that the algorithm captures the indicator characteristics that have a great impact on the state change of the tower, and thus improves the prediction accuracy of the state of each tower in the transmission line project. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 work.

[0036] Figure 1 A flowchart of a method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis provided by one embodiment of the present invention;

[0037] Figure 2A schematic diagram of an indicator dependency table provided by an embodiment of the present invention;

[0038] Figure 3 A flow chart of a method for obtaining a state fluctuation coefficient provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a method for predicting the mutual influence of transmission line engineering indicators based on multidimensional data analysis proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0041] The following is a detailed description of a method for predicting mutual influence of transmission line engineering indicators based on multi-dimensional data analysis provided by the present invention in conjunction with the accompanying drawings.

[0042] See also Figure 1 , which shows a flow chart of a method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis provided by an embodiment of the present invention, specifically comprising:

[0043] Step S1, at the current moment, obtain the time series of state parameters of each tower under each indicator in the transmission line project within a preset historical period, and the current state vector of each tower; the current state vector includes the state parameters under each indicator.

[0044] In one embodiment of the present invention, various sensors are set to collect state parameters of each tower under corresponding indicators at all collection moments within a preset historical period, and then all state parameters of each tower under each indicator are sorted according to the collection time sequence to construct a time series; wherein the preset historical period is set to a historical week at the current moment, and the collection frequency is once per minute, which can also be set by the implementer according to actual needs; and at the same time, the current state vector of each tower is obtained at the current moment, wherein the current state vector is a multidimensional vector containing the state parameters of each tower under multidimensional indicators at the current moment.

[0045] It should be noted that all state parameters need to be standardized before constructing the time series to eliminate the dimension for subsequent analysis and application.

[0046] In one embodiment of the present invention, the indicators include at least load, tension ratio, height, span, weight, and swing amplitude; wherein, the load is calculated by installing a strain gauge on the pole tower to measure the strain information of the pole tower in real time; a tension sensor is installed on the transmission cable between the pole tower and the next adjacent pole tower to measure the cable tension in real time, thereby obtaining the tension ratio; a laser rangefinder is used to obtain the height of each pole tower and the span between two adjacent pole towers; a gravity sensor installed on the base of the pole tower and other parts is used to collect the weight of the pole tower; an acceleration sensor is used to monitor the swing amplitude of the pole tower in real time; it should be noted that the collection of the state parameters of the above indicators are all existing technologies well known to those skilled in the art, which will not be described in detail here; in other embodiments, the implementer may also set other types or quantities of indicators, which may be indicators related to the structural stability of the pole tower, such as vibration, inclination, etc., or indicators related to the foundation around the pole tower, such as soil bearing capacity or density, which will not be described in detail here.

[0047] Step S2, according to the change correlation between different indicators of different towers, the indicator importance of each indicator is obtained; according to the fluctuation change of the time series of each tower under each indicator, relative to the deviation of the fluctuation change of the time series of other towers in the local geographical area under each indicator, the state fluctuation coefficient of each tower is obtained.

[0048] Taking into account the influence of certain correlation changes between different indicators, for example, the greater the load, the greater the swing amplitude may be; the importance of each indicator can be evaluated by comprehensively analyzing the change correlation between different indicators of different towers; the importance of indicators reflects the impact of the change of each indicator on the change of other indicators, and indirectly reflects the impact on the state change of the transmission line project.

[0049] Preferably, in one embodiment of the present invention, considering that the state transfer matrix in the Kalman filter can be used to describe how the system state changes over time, and each element in the state transfer matrix reflects the relationship between different state variables and how they affect the evolution of the system, the correlation changes between different indicators can be analyzed and evaluated based on the state transfer matrix, so as to obtain the indicator importance of each indicator; based on this, the method for obtaining the indicator importance includes:

[0050] The state vector of each tower at each acquisition time is obtained, and the state transfer matrix of each tower is obtained based on the Kalman filter and the state vectors at all adjacent acquisition times; the matrix elements in the state transfer matrices of all towers are combined to obtain the indicator importance of each indicator.

[0051] It should be noted that the method for obtaining the state vector of each tower at each acquisition time is consistent with the method for obtaining the current state vector; it is known that obtaining the state transfer matrix of the Kalman filter from the state vectors at adjacent acquisition times is an existing technology well known to those skilled in the art and will not be repeated here.

[0052] Among them, in a preferred embodiment of the present invention, considering that if the state vector is an n-dimensional vector, the size of the state transfer matrix is ​​n×n, wherein each matrix element such as Aij represents the influence of the j-th state vector on the i-th state vector in the time step; and considering that the state vector is composed of state parameters under multi-dimensional indicators, the state transfer matrix can be regarded as an indicator dependency table between different indicators corresponding to each tower, and each row and each column in the indicator dependency table can be regarded as an indicator corresponding dimension, and each value therein reflects the correlation degree between the state parameter under each indicator and the state parameter under another indicator; therefore, the method of obtaining the indicator importance of each indicator by synthesizing the matrix elements in the state transfer matrix of all towers includes:

[0053] Each row and each column in the state transfer matrix corresponds to an indicator; the sum of all elements in each row of the state transfer matrix is ​​used as the first dependent reference value under the corresponding indicator, and the sum of all elements in each column of the state transfer matrix is ​​used as the second dependent reference value under the corresponding indicator;

[0054] Under each index, the sum of the products of the first dependent reference values ​​and the second dependent reference values ​​of all towers is taken as the first parameter, the product of the sum of the first dependent reference values ​​of all towers and the sum of the first dependent reference values ​​of all towers is taken as the second parameter, the sum of the squares of the second dependent reference values ​​of all towers is taken as the third parameter, and the sum of the squares of the second dependent reference values ​​of all towers is taken as the fourth parameter;

[0055] The difference between the first and second parameters was taken as the numerator, the difference between the third and fourth parameters was taken as the denominator, and the ratio of the fractions was taken as the indicator importance of each indicator.

[0056] As an example, please participate Figure 2 , which shows a schematic diagram of an indicator dependency table provided by an embodiment of the present invention, in which each row and each column in the indicator dependency table corresponds to an indicator dimension; the state transfer matrix, i.e., the sum of all elements in each row in the indicator dependency table, is used as the first dependency reference value under the corresponding indicator, and similarly, the state transfer matrix, i.e., the sum of all elements in each column in the indicator dependency table, is used as the second dependency reference value under the corresponding indicator; the first dependency reference value and the second dependency reference value evaluate the impact of the change of each indicator on the change of another indicator from the perspective of row and column respectively; then, the indicator importance of each indicator is obtained;

[0057] The calculation formula of indicator importance is: Where i is the index number; a is the tower number; A is the total number of towers in the transmission line; Z i is the indicator importance of the i-th indicator; X a,i is the first dependent reference value of the ith index of the ath tower; Y a,i is the second dependent reference value of the ith index of the ath tower; is the first parameter; is the second parameter; is the third parameter; is the fourth parameter; || is the absolute value symbol.

[0058] In the calculation formula of the indicator importance, the denominator integrates the absolute value of the sum of the squares of the second dependent reference values ​​of all towers under each indicator and the difference between the sum of the squares, which indirectly reflects that the second dependent reference values ​​between different towers under this indicator are more discrete, and the impact of this indicator on the changes of other indicators is more dispersed, and its importance may be lower; the numerator integrates the combination operation between the first dependent reference value and the second dependent reference value of all towers under each indicator, and refers to the numerator in the calculation formula of the correlation coefficient in the prior art to evaluate the importance of each indicator. The larger the difference, the more likely it is that the change of this indicator may significantly affect the data performance of other indicators.

[0059] It should be noted that the possibility that the second dependent reference values ​​of different towers under each indicator are equal and 0 is extremely low, so the case where the denominator is zero is ignored; when there is an extreme case where the denominator is 0, the implementer can set the denominator to a very small non-zero positive parameter such as 0.01 to make the fraction meaningful without affecting the value of the fraction.

[0060] In another embodiment of the present invention, the implementer may also obtain the correlation coefficient between every two time series, such as the Pearson correlation coefficient, between the time series of all indicators of each tower, to evaluate the change correlation between different indicators in each tower; then, between every two indicators, the average of the Pearson correlation coefficients between the corresponding time series of all towers is used as the correlation change coefficient between the two indicators; taking any indicator as the target indicator, accumulating the correlation change coefficients between the target indicator and the remaining indicators and performing linear normalization, the indicator importance of the target indicator can be obtained, and then the indicator importance of each indicator can be obtained.

[0061] It should be noted that the Pearson correlation coefficient and linear normalization are both existing technologies well known to those skilled in the art and will not be described in detail here; in other embodiments, the implementer may also use other correlation coefficients and normalization methods.

[0062] Considering that the fluctuation of the time series of each tower under each indicator reflects the state of each tower, if the state parameter fluctuation of the tower under the indicator is more drastic, it is more likely to cause the stable state of the tower to change, thus causing safety risks. Therefore, when predicting the future tower state based on the current tower state, more attention should be paid to the change of the state parameter of the indicator; therefore, the embodiment of the present invention further obtains the state fluctuation coefficient of each tower according to the fluctuation of the time series of each tower under each indicator and the deviation of the fluctuation of the time series of other towers under each indicator in the local geographical area. The state fluctuation coefficient reflects the stability of the state of each tower, and prepares for the consideration weight of each indicator of each tower in the subsequent evaluation.

[0063] Preferably, in one embodiment of the present invention, the method for obtaining the state fluctuation coefficient includes:

[0064] See also Figure 3 , which shows a flow chart of a method for obtaining a state fluctuation coefficient provided by an embodiment of the present invention, specifically comprising:

[0065] Step S201, obtaining the fluctuation evaluation parameter of each indicator of each tower according to the fluctuation change of the state parameter in the time series of each tower under each indicator; and obtaining the overall fluctuation parameter of each tower by integrating the fluctuation evaluation parameters of all indicators of each tower.

[0066] Considering that the greater the fluctuation degree of the state parameters of each tower in the time series under each indicator, the greater the impact on the change of the stable state of the tower; if the state parameters under all indicators of the tower fluctuate greatly, it means that the possibility of the tower state change is greater; based on this, the present invention first comprehensively considers the fluctuation of the time series under all indicators of each tower to obtain the overall fluctuation parameters of each tower.

[0067] The overall fluctuation parameter reflects the degree of fluctuation of each indicator of the tower within the preset historical period at the current moment, and indirectly reflects the possibility of state change of each tower, preparing for the subsequent analysis of the state impact weight of each indicator of each tower.

[0068] In a preferred embodiment of the present invention, considering that the fluctuation change of each time series is not an instantaneous mutation, but has a certain transition change over time, the time series can be segmented according to the local fluctuation of the time series. The more segments there are, the faster the fluctuation change is. Considering that the longer the length of a local segment closest to the current moment is, the more stable the state of the time series near the current moment may be. Based on this, the method for obtaining the fluctuation evaluation parameter includes:

[0069] According to the local fluctuation similarity of the time series of each tower under each indicator, the time series is segmented to obtain all sequence sub-segments;

[0070] According to the total number of sequence sub-segments and the sequence length of the last sequence sub-segment in time series, the fluctuation evaluation parameters of each indicator of each tower are obtained; the sequence length is negatively correlated with the fluctuation evaluation parameter, and the total number is positively correlated with the fluctuation evaluation parameter.

[0071] As an example, the time series of each tower under each indicator is first-order differencing to obtain the differential time series. If the differential time series is curve fitted, all extreme points in the curve are obtained, and the extreme points are used as mutation points of fluctuation changes. The horizontal axis serial number of the extreme points in the curve is increased by 1 as the sequence segmentation point in the time series, wherein the sequence segmentation point is the starting point of each sequence sub-segment, and the previous adjacent sequence element of the sequence segmentation point is the end point of the previous sequence sub-segment; all sequence sub-segments are determined based on the starting point and end point of the sequence sub-segments.

[0072] In another example, the time series of each tower under each indicator is clustered, such as using a hierarchical clustering algorithm to obtain all clusters, and the state parameters in the same cluster are assigned the same sign, and the state parameters between different clusters have different signs; in the time series, if the signs of two adjacent state parameters are different, it can be determined that they belong to different sequence sub-segments, thereby obtaining all sequence sub-segments.

[0073] It should be noted that first-order difference and hierarchical clustering are both existing technologies well known to those skilled in the art and will not be described in detail here. In other examples, implementers may also use slope to evaluate the changing trend or calculate the variance of the state parameters in each sliding window based on a sliding window. When the variance in the sliding window is the smallest, it indicates that it has a similar fluctuation trend, and it is determined to be a sequence sub-segment, and then all sequence sub-segments are obtained. These are all commonly used technical means and will not be described in detail here.

[0074] Then, the sequence length of the sequence subsegment closest to the current moment, that is, the last sequence subsegment on the instant sequence, is used as the denominator, the total number of sequence subsegments is used as the numerator, and the fraction ratio is used as the fluctuation evaluation parameter of the corresponding indicator of the corresponding tower; then, the fluctuation evaluation parameters of all indicators of each tower are accumulated to obtain the overall fluctuation parameter of each tower.

[0075] It should be noted that the total number of sequence sub-segments and the sequence length of the last sequence sub-segment in time cannot be 0, so the fractional result is not 0 and is always meaningful; in other examples, the implementer may also use other basic mathematical operations or related mapping methods to combine the sequence length and the total number of sequence sub-segments, which will not be elaborated here.

[0076] Step S202, based on the connection status of the towers in the transmission line project, obtain the tower sorting sequence in the transmission line project; construct a fluctuation sequence according to the overall fluctuation parameter of each tower, the fluctuation sequence has the same sequence order as the tower sorting sequence; divide the tower sorting sequence according to the change of the fluctuation sequence, and obtain all tower subsequences.

[0077] Considering that the pole towers in the transmission line are usually arranged in sequence and then connected by the transmission line, an embodiment of the present invention first takes the first pole tower at either end of the transmission line as the starting point, sequentially sorts each pole tower to obtain the corresponding number, thereby obtaining a pole tower sorting sequence; then takes the overall fluctuation parameter of each pole tower as a sequence element, and constructs a fluctuation sequence in the order of the pole tower sorting sequence; further, based on the change of the fluctuation sequence, the towers with similar state changes and close geographical locations are divided into a section, and all pole tower subsequences are obtained, so as to subsequently evaluate the state deviation of each pole tower relative to other towers.

[0078] In a preferred embodiment of the present invention, a method for obtaining a tower subsequence includes:

[0079] Get the first-order difference sequence of the fluctuation sequence. If two adjacent sequence elements in the first-order difference sequence have different numbers, the largest number between the numbers of the two adjacent sequence elements is used as the splitting number.

[0080] The sequence element corresponding to the segmentation number in the tower sorting sequence is used as the right endpoint of each tower subsequence, and the next sequence element adjacent to the right endpoint of each sequence is used as the left endpoint of the next tower subsequence;

[0081] A tower sequence subsegment is obtained based on a sequence right endpoint and a sequence left endpoint of each tower subsequence.

[0082] To help understand the process of obtaining tower subsequences, as an example, assume that the tower sorting sequence is {A, B, C, D, E, F, G}, and the corresponding fluctuation sequence is {1, 2, 3, 2, 4, 5, 4}, then the first-order difference sequence of the fluctuation sequence is {1, 1, -1, 2, 1, -1}, then all tower subsequences obtained are {A, B, C}, {D, E, F}, {G}.

[0083] Step S203, obtaining the state fluctuation coefficient of each tower according to the deviation degree of the overall fluctuation parameter of each tower relative to the overall fluctuation parameters of all towers in the tower subsequence to which each tower belongs; the deviation degree is positively correlated with the state fluctuation coefficient.

[0084] Considering that if the overall fluctuation parameter of each tower reflects its state change, if its state change is relatively close and the state changes of all towers in the adjacent section with relatively similar state changes are still relatively deviated, that is, there is a certain deviation in the state changes of all towers in the tower sequence to which it belongs, then it means that the state fluctuation coefficient of the tower is more likely to deviate abnormally, and its state fluctuation coefficient is larger.

[0085] As an example, the calculation formula for the state fluctuation coefficient is: Among them, i is the index number; a is the tower number; B a is the fluctuation coefficient of the fluctuation state of the a-th tower; I is the total number of indicators; W a,i is the fluctuation evaluation parameter of the ith index of the ath tower; is the overall fluctuation parameter of the a-th tower; c is the sequence number of the tower in the tower subsequence to which the a-th tower belongs, and c can be a; C a is the total number of towers in the tower subsequence to which the a-th tower belongs; || is the absolute value symbol.

[0086] In the calculation formula of the state fluctuation coefficient, It reflects the average level of the overall fluctuation parameters of all towers in the tower subsequence to which the a-th tower belongs, and provides a reference for evaluating the deviation of the overall fluctuation parameters of each tower. The numerator reflects the degree of deviation of the overall fluctuation parameters of each tower from the average level. The smaller the average level corresponding to the denominator, the more stable the state of the adjacent tower. If the degree of deviation is greater, the state fluctuation coefficient of the tower is relatively larger.

[0087] It should be noted that, since the fluctuation evaluation parameter of each tower under each indicator is not 0, the overall fluctuation parameter of each tower is not 0, and when it is used as the denominator, the fraction is always meaningful.

[0088] Step S3, according to the fluctuation change of the state parameter in the time series under each indicator of each tower, combined with the state fluctuation coefficient of each tower and the indicator importance of each indicator, obtain the state influence weight of each indicator of each tower; at the current moment, according to the state influence weight of each indicator of each tower, and the deviation of the state parameter of each tower relative to the state parameters of all towers under the same indicator, obtain the final state influence weight of each indicator of each tower.

[0089] Taking into account that the more drastic the fluctuation of the state parameters in the time series under each indicator of each tower, the greater the state fluctuation coefficient of each tower and the indicator importance of each indicator are, which means that the influence on the change of the stable state of the tower is greater; therefore, the embodiment of the present invention obtains the state influence weight of each indicator of each tower based on this, and the greater the state influence weight is, the more attention should be paid to the state parameter change of the tower under the indicator when predicting the state change of the tower in the subsequent time, that is, the corresponding indicator of the tower has a higher attention weight, so as to timely capture the state change migration of the tower, thereby improving the accuracy of the tower state prediction.

[0090] Preferably, in one embodiment of the present invention, the method for obtaining the state influence weight includes:

[0091] Multiply the state fluctuation coefficient of each tower by the indicator importance of each indicator, and use the product as the first weight parameter; normalize the fluctuation evaluation parameter of each indicator of each tower, and use the normalized result as the second weight parameter; and use the product of the first weight parameter and the second weight parameter as the state influence weight of the corresponding indicator of the corresponding tower.

[0092] As an example, the calculation formula for the state influence weight is: Q a,i =Z i ×B a ×norm(W a,i ), where i is the index number; a is the tower number; Q a,i is the state influence weight of the i-th indicator of the a-th tower; Zi is the indicator importance of the i-th indicator; B a is the fluctuation coefficient of the a-th tower; W a,i is the fluctuation evaluation parameter of the ith index of the ath tower; norm() is the linear normalization function; Z i ×B a is the first weight parameter; norm(W a,i ) is the second weight parameter.

[0093] In this example, the importance of the parameters and indicators reflecting the state fluctuations of each tower are multiplied and combined to obtain the state influence weight; the more important the indicator, the greater the state influence weight, and the higher the subsequent attention; the more drastic the state fluctuations of the tower, the greater the state influence weight, and the higher the subsequent attention; in other examples, implementers can also use basic mathematical operations such as addition or weighted summation or related mapping methods to combine the three, or use other normalization methods, which will not be repeated here.

[0094] Considering that the state parameters of each tower at the current moment are also crucial to the subsequent state prediction, and the changes in the tower states of adjacent time series often have certain similarities; the degree of attention paid to the towers with more violent fluctuations at the current moment should also be greater; therefore, at the current moment, the embodiment of the present invention, based on the state influence weight of each indicator of each tower, combines and analyzes the deviation of the state parameters of each tower relative to the state parameters of all towers under the same indicator, to obtain the final state influence weight of each indicator of each tower; the final state influence weight combines the state deviation degree of the tower at the current moment, and more accurately evaluates the attention paid to the state parameters of each indicator of each tower, so as to improve the accuracy of state prediction.

[0095] Preferably, in one embodiment of the present invention, the method for obtaining the final state influence weight includes:

[0096] Under the same indicators, the fluctuation weight of each indicator of each tower is obtained according to the deviation of the state parameter of each tower relative to the average level of the state parameters of all towers; the corresponding state impact weight is weighted by using the fluctuation weight, and the weighted result is used as the final state impact weight of each indicator of each tower.

[0097] As an example, the final state impact weight is calculated as: Among them, i is the index number; a is the tower number; Q′ a,i is the final state impact weight of the ith indicator of the ath tower; Q a,i is the state influence weight of the i-th indicator of the a-th tower; G a,i is the state parameter of the i-th indicator of the a-th tower at the current moment; is the mean value of the state parameters of all towers under the i-th index at the current moment; || is the absolute value symbol; is the fluctuation weight of the ith indicator of the ath tower; NORM[] is the standard normalization function.

[0098] In the calculation formula of the final state impact weight, It reflects the deviation of the state parameter of the ath tower relative to the average level of the state parameters of all towers under the same indicator; the larger the deviation, the larger the fluctuation weight, and the greater the need for subsequent attention; the relative fluctuation weight is then multiplied by the state influence weight to obtain the final state influence weight; in this example, the sum of the weighted results corresponding to all indicators in each tower is taken as the denominator, and the weighted result under each indicator is taken as the numerator, and normalized in the form of a ratio, so that the sum of the final state influence weights under all indicators of each tower is 1.

[0099] At this point, the final state influence weight of each indicator of each tower at the current moment, that is, the attention paid to the state parameter of each indicator of each tower, is obtained, so as to improve the accuracy of state prediction later.

[0100] Step S4, obtaining the predicted state vector of each tower at the next acquisition moment according to the final state influence weight and the current state vector.

[0101] At the current moment, after obtaining the final state influence weight of each indicator of each tower and the current state vector of each tower, the state of each tower at the next acquisition moment can be predicted.

[0102] Preferably, in one embodiment of the present invention, considering that the Kalman filter is a recursive algorithm for estimating the state of a dynamic system, and can be used for prediction and state estimation of time series data, the current state vector of the corresponding tower can be weighted by using the final state influence weight, and the attention paid to each indicator can be adjusted, so that the Kalman filter can more accurately capture the state changes of the system, thereby improving the accuracy of the output prediction results; based on this, the method for obtaining the predicted state vector includes:

[0103] The final state influence weight is used to weight the current state vector of the corresponding tower, and the weighted result is used as the input of the Kalman filter to output the predicted state vector of the corresponding tower at the next acquisition moment.

[0104] It should be noted that the acquisition of weighted results and the application of Kalman filter are already existing technologies well known to those skilled in the art and will not be described in detail here.

[0105] At this point, the predicted state vector of each tower at the next acquisition moment is obtained. Implementers can use the predicted state vector to evaluate the safety risks of the transmission line project, such as whether the load exceeds the preset load limit, and thus take optimization measures to reduce safety hazards.

[0106] In summary, the present invention first obtains the time series of state parameters of each tower under each indicator and the current state vector of each tower; then, according to the change correlation between different indicators of different towers, the indicator importance of each indicator is obtained; further analysis is performed to obtain the state fluctuation coefficient of each tower, thereby obtaining the state influence weight of each indicator of each tower; then, at the current moment, the final state influence weight of each indicator of each tower is obtained, thereby combining the current state vector to obtain the predicted state vector of each tower at the next acquisition moment. The present invention analyzes the change correlation and historical fluctuation of the state parameters under the multi-dimensional indicators of the tower, evaluates the attention weight of each indicator of each tower, and adjusts the input of the Kalman filter algorithm, so that the algorithm captures the indicator features that have a great impact on the change of the tower state, thereby improving the prediction accuracy of the state of each tower in the transmission line project.

[0107] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting the mutual influence of transmission line engineering indicators based on multidimensional data analysis, characterized in that: The method comprises: At the current moment, obtain the time series of state parameters of each tower under each indicator in the transmission line project within a preset historical period, and the current state vector of each tower; the current state vector includes the state parameters under each indicator; According to the change correlation between different indicators of different towers, the indicator importance of each indicator is obtained; according to the fluctuation change of the time series of each tower under each indicator, relative to the deviation of the fluctuation change of the time series of other towers under each indicator in the local geographical area, the state fluctuation coefficient of each tower is obtained; According to the fluctuation change of the state parameter in the time series under each indicator of each tower, combined with the state fluctuation coefficient of each tower and the indicator importance of each indicator, the state influence weight of each indicator of each tower is obtained; at the current moment, according to the state influence weight of each indicator of each tower, and the deviation of the state parameter of each tower relative to the state parameter of all towers under the same indicator, the final state influence weight of each indicator of each tower is obtained; According to the final state influence weight and the current state vector, the predicted state vector of each tower at the next acquisition moment is obtained.

2. A method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 1, characterized in that: The method for obtaining the importance of the indicator includes: The state vector of each tower at each acquisition time is obtained, and the state transfer matrix of each tower is obtained based on the Kalman filter and the state vectors at all adjacent acquisition times; the indicator importance of each indicator is obtained by combining the matrix elements in the state transfer matrix of all towers.

3. A method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 2, characterized in that: The method of obtaining the index importance of each index by integrating the matrix elements in the state transfer matrix of all towers includes: Each row and each column in the state transfer matrix corresponds to an indicator; the sum of all elements in each row of the state transfer matrix is ​​used as the first dependent reference value under the corresponding indicator, and the sum of all elements in each column of the state transfer matrix is ​​used as the second dependent reference value under the corresponding indicator; Under each indicator, the sum of the products of the first dependence reference value and the second dependence reference value of all towers is taken as a first parameter, the product of the sum of the first dependence reference values ​​of all towers and the sum of the first dependence reference values ​​of all towers is taken as a second parameter, the sum of the squares of the second dependence reference values ​​of all towers is taken as a third parameter, and the sum squares of the second dependence reference values ​​of all towers is taken as a fourth parameter; The difference between the first parameter and the second parameter is used as a numerator, the difference between the third parameter and the fourth parameter is used as a denominator, and the fractional ratio is used as the indicator importance of each indicator.

4. The method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 1 is characterized in that: The method for obtaining the state fluctuation coefficient includes: According to the fluctuation change of the state parameter in the time series of each tower under each indicator, the fluctuation evaluation parameter of each indicator of each tower is obtained; the overall fluctuation parameter of each tower is obtained by integrating the fluctuation evaluation parameters of all indicators of each tower; Based on the connection conditions of the pole towers in the transmission line project, a pole tower sorting sequence in the transmission line project is obtained; a fluctuation sequence is constructed according to the overall fluctuation parameter of each pole tower, wherein the fluctuation sequence has the same sequence order as the pole tower sorting sequence; and according to the change of the fluctuation sequence, the pole tower sorting sequence is divided to obtain all pole tower subsequences; According to the overall fluctuation parameter of each tower, the state fluctuation coefficient of each tower is obtained relative to the degree of deviation of the overall fluctuation parameter of all towers in the tower subsequence to which each tower belongs; the degree of deviation is positively correlated with the state fluctuation coefficient.

5. A method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 4, characterized in that: The method for obtaining the fluctuation evaluation parameter includes: According to the local fluctuation similarity of the time series of each tower under each indicator, the time series is segmented to obtain all sequence sub-segments; According to the total number of the sequence sub-segments and the sequence length of the last sequence sub-segment in time series, the fluctuation evaluation parameter of each indicator of each tower is obtained; the sequence length is negatively correlated with the fluctuation evaluation parameter, and the total number is positively correlated with the fluctuation evaluation parameter.

6. A method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 4, characterized in that: The method for obtaining the tower subsequence comprises: Obtain a first-order difference sequence of the fluctuation sequence. If two adjacent sequence elements in the first-order difference sequence have different numbers, use the largest number among the numbers corresponding to the two adjacent sequence elements as the segmentation number. The sequence element corresponding to the segmentation sequence number in the tower sorting sequence is used as the sequence right endpoint of each tower subsequence, and the next sequence element adjacent to the right endpoint of each sequence is used as the sequence left endpoint of the next tower subsequence; A tower sequence subsegment is obtained based on the sequence right endpoint and the sequence left endpoint of each tower subsequence.

7. The method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 4 is characterized in that: The method for obtaining the state influence weight includes: The state fluctuation coefficient of each tower is multiplied by the indicator importance of each indicator, and the product is used as the first weight parameter; the fluctuation evaluation parameter of each indicator of each tower is normalized, and the normalized result is used as the second weight parameter; the product of the first weight parameter and the second weight parameter is used as the state influence weight of the corresponding indicator of the corresponding tower.

8. The method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 1, characterized in that: The method for obtaining the final state influence weight includes: Under the same indicator, the fluctuation weight of each indicator of each tower is obtained according to the deviation of the state parameter of each tower relative to the average level of the state parameter of all towers; the corresponding state influence weight is weighted by using the fluctuation weight, and the weighted result is used as the final state influence weight of each indicator of each tower.

9. The method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 1, characterized in that: The method for obtaining the predicted state vector includes: The current state vector of the corresponding tower is weighted by using the final state influence weight, the weighted result is used as the input of the Kalman filter, and the predicted state vector of the next acquisition moment of the corresponding tower is output.

10. The method for predicting mutual influence of transmission line engineering indicators based on multidimensional data analysis according to claim 1, characterized in that: The indicators include at least load, tension ratio, height, gear spacing, weight, and dancing amplitude.

Images