Pipe jacking post-construction state detection method and system

Abstract

The invention provides a pipe jacking post-construction state detection method and system, and the method comprises the steps: carrying out the data preprocessing of the pipe jacking post-construction state detection data, so as to obtain the processing data; key influence factors are determined, and a key data set is extracted from the processing data based on the key influence factors; performing combined de-noising processing on data in the key data set to obtain a de-noised data set; performing clustering processing on the de-noised data set by using an improved clustering algorithm to obtain a clustered data set; according to the method, effective data can be effectively extracted from the mixed data, white noise, colored noise and the like in the data can be removed, the clustering speed can be greatly increased, the feature dimension can be greatly reduced, and the final pipe jacking post-construction state is determined on the basis of the influence weight and the clustering data set. The quality and effectiveness of data are improved, and finally the accuracy and effectiveness of safety state recognition are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of pipe jacking status detection, and in particular relates to a method and system for detecting the status of a pipe jacking after operation. Background Art

[0002] Pipe jacking is a trenchless construction method, a technique for burying pipes with minimal or no excavation. Pipe jacking involves using the jacking force generated by jacking equipment within a working pit to overcome friction between the pipe and the surrounding soil, pushing the pipe into the soil according to the designed slope and removing the soil. After one section of pipe is pushed into the soil, the second section is lowered and pushed forward. The principle is to use the thrust of the main jacking cylinder and the thrust of the pipe and relay rooms to push the tool pipe or tunnel boring machine from the working pit through the soil and into the receiving pit, where it is hoisted. The pipeline is then buried between the two pits, following the tool pipe or tunnel boring machine.

[0003] To ensure safety, it is usually necessary to install several sensors around and on the pipeline to detect the post-pipe jacking status detection data in real time through the sensors. The purpose of the detection is usually to ensure the safety of the pipeline. Under the influence of the external environment (external pressure, soil environment, weather), the pipeline is prone to deformation, cracking, leakage, serious material deterioration, etc. The existing technology obtains post-pipe jacking detection data and performs safety classification based on the detection data. However, in actual situations, there is a lot of noise in the detection data and some data that has little impact on the pipe jacking status. If the safety classification is directly based on the detection data, it is easy to have inaccurate safety classification, which in turn poses a major safety hazard. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for detecting the status of pipe jacking after operation, which are used to solve the technical problems in the prior art.

[0005] In one aspect, the present invention provides the following technical solution: a method for detecting the status of a pipe jacking after work, comprising: Acquiring post-pipe jacking status detection data, and performing data preprocessing on the post-pipe jacking status detection data to obtain processed data; Determining key influencing factors using a hierarchical analysis method, and extracting key data sets from the processed data based on the key influencing factors; Performing combined denoising processing on the data in the key data set to obtain a denoised data set; Performing clustering processing on the denoised data set using an improved clustering algorithm to obtain a clustered data set; Each of the key influencing factors is combined and weighted to obtain an influence weight, and a final post-pipe jacking status is determined based on the influence weight and the clustering data set.

[0006] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present invention first obtains the post-pipe jacking worker status detection data, and performs data preprocessing on the post-pipe jacking worker status detection data to obtain processed data; then adopts the hierarchical analysis method to determine the key influencing factors, and extracts the key data set from the processed data based on the key influencing factors; then performs combined denoising processing on the data in the key data set to obtain a denoised data set; then uses the improved clustering algorithm to perform clustering processing on the denoised data set to obtain a clustered data set; finally, each key influencing factor is combined and weighted to obtain an influence weight, and the final post-pipe jacking worker status is determined based on the influence weight and the clustered data set. The present invention performs combined denoising on the data, which can effectively extract valid data from the mixed data and remove white noise, colored noise, etc. in the data, and then performs clustering processing, which can greatly improve the clustering speed and reduce the feature dimension to improve the quality and effectiveness of the data, and then determines the final post-pipe jacking worker status through the influence weight, thereby improving the accuracy and effectiveness of safety status identification.

[0007] Preferably, the step of performing combined denoising processing on the data in the key data set to obtain a denoised data set includes: Decomposing the data in the key data set to obtain a plurality of IMF components and trend items, and arranging the plurality of IMF components in descending order to obtain a first IMF component set; Calculate the noise judgment value of each IMF component in the first IMF component set : ; Where, represents the number of IMF components in the first IMF component set, Indicates the first IMF component concentration IMF components; Determine the noise judgment value , storing the IMF components before the target arrangement position in a second IMF component set, determining the number of zero crossings of all IMF components in the first IMF component set, storing the IMF components whose number of zero crossings is less than a preset number in a third IMF component set, and storing the remaining IMF components in the first IMF component set except the second IMF component set and the third IMF component set in a fourth IMF component set; Denoising and power conversion are performed on the second IMF component set and the third IMF component set respectively to obtain a first denoised IMF component set and a second denoised IMF component set, and a denoised data set is determined based on the first denoised IMF component set and the second denoised IMF component set.

[0008] Preferably, the step of performing denoising and power conversion processing on the second IMF component set and the third IMF component set respectively to obtain a first denoised IMF component set and a second denoised IMF component set, and determining a denoised data set based on the first denoised IMF component set and the second denoised IMF component set includes: performing wavelet threshold denoising on the second IMF component set to obtain a first denoised IMF component set; Determining a power spectrum of the third IMF component set, and determining a power spectrum matrix based on the power spectrum; The power spectrum matrix is normalized to obtain a standard matrix, the eigenvector of the standard matrix is extracted, and the principal component sequence is determined based on the eigenvector and the standard matrix. : ; Where, is a standard matrix, is the eigenvector; Arrange the principal components in the principal component sequence in descending order according to their contribution, and extract the first several principal components after descending order to obtain the target principal component, and determine the reconstructed power spectrum based on the target principal component : ; ; Where, Indicates the target principal components, express The corresponding eigenvector, represents the intermediate reconstructed power spectrum, Respectively Middle Rank Elements of the column, To reconstruct the adjustment factor, is the first Mean of column elements; The reconstructed power spectrum Perform phase addition and inverse Fourier transform to obtain the second denoised IMF component set :

[0009] ; Where, represents the second denoised IMF component set Middle IMF components, is the inverse Fourier transform, is an imaginary number, Indicates the corresponding frequency phase; The first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term are reconstructed to obtain a denoised data set.

[0010] Preferably, the step of clustering the denoised data set using an improved clustering algorithm to obtain a clustered data set includes: Determine an intermediate data point in the denoised data set, and perform clustering with the intermediate data point as a cluster center to obtain a first cluster; If the number of data in the first cluster is less than a preset number, the positive data in the denoised data set is stored in a positive sample data set, and the negative data is stored in a negative sample data set; Determine a first mean in the positive sample data set and a second mean in the negative sample data set, and calculate an absolute value of a difference between the first mean and the second mean; Clustering is performed based on the absolute values of the differences and a clustered data set is output.

[0011] Preferably, the step of clustering based on the absolute value of the difference and outputting the cluster data set includes: If the absolute value of the difference is less than a preset value, clustering is performed using the data corresponding to the first mean or the second mean as the cluster center to obtain a second cluster; If the number of data in the second cluster is less than a preset number, then arbitrarily select a point in the denoised data set as a reference point, determine a data range with the reference point as the center and a preset distance as the radius, and if the number of data points within the data range is greater than a preset density threshold, then use the reference point as a sample point, determine the center of the sample point, and perform clustering with the center of the sample point as the cluster center, calculate the Euclidean distance between the sample point and the remaining data points in the denoised data set, and classify the data points with a Euclidean distance less than the preset distance into the class corresponding to the sample point, so as to obtain a clustered data set; If the absolute value of the difference is not less than a preset value, clustering is performed using the data corresponding to the first mean and the data corresponding to the second mean as cluster centers to obtain a third cluster and a fourth cluster; If the number of data in the third cluster is less than a preset number and the number of data in the fourth cluster is less than a preset number, then any point in the denoised data set is selected as a reference point, and the data range is determined with the reference point as the center and the preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point, the center of the sample point is determined, and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised data set is calculated, and the data points with a Euclidean distance less than the preset distance are classified into the class corresponding to the sample point to obtain a clustered data set.

[0012] Preferably, the step of combining and weighting the key influencing factors to obtain influence weights, and determining the final post-pipe jacking status based on the influence weights and the clustering data set includes: Select the lowest impact factor from the key impact factors and calculate the lowest impact factor The first level of impact and other key influencing factors The second level of impact : ; ; Where, For the evaluation section, For the The key influencing factors are The indicator value on the evaluation segment, The lowest influencing factor is The indicator value on each evaluation segment; Based on the first impact And the second level of impact Calculate the first weight : ; ; Where, is the important value of the indicator; Construct an original evaluation matrix and determine the index weight value based on the original evaluation matrix : ; Where, is the first Rank Elements of the column; Based on the weighting value of the index Determine the second weight : ; Preliminarily combine the first weight and the second weight to obtain a combined weight : ; Where, Represent the first and second combination parameters respectively, Respectively represent the weight set consisting of the first weight and the second weight; Determine the objective function: ; Solve the objective function to obtain the updated first combination parameter , Update the second combination parameters ; Based on the update of the first combination parameter , the updating of the second combination parameter Determine impact weight : ; Construct an initial indicator evaluation matrix based on the initial indicator evaluation matrix and the impact weight Determine the final status after pipe jacking.

[0013] Preferably, the initial indicator evaluation matrix is constructed based on the initial indicator evaluation matrix and the influence weights The steps to determine the final post-pipe jacking status include: Determine the security classification level and the classification standard of each security classification level, and determine the classification matrix based on the security classification level and the classification standard ,in, The number of security classification levels; Constructing the initial indicator evaluation matrix , in the grading matrix Extract the The row vector corresponding to the key influencing factors, if the elements in the row vector are in a decreasing relationship, then when hour, ,when hour, ,when hour, , if the elements in the row vector are in increasing relationship, then when hour, ,when hour, ,when hour, ,in, For the clustering data set The key influencing factors are The data value on the evaluation segment, is the first Rank Elements of the column, The first Rank Elements of the column; Based on the impact weight With the initial indicator evaluation matrix Determine the final matrix : ; Where, The final matrix Rank Elements of the column, Indicates the The impact weight corresponding to each key influencing factor; The safety status evaluation function is determined based on the final matrix. If the installation status evaluation function is satisfied, the final post-pipelining status is There are safety classification levels, among which the safety status evaluation function is: ; Where, Indicates the final matrix row vectors, is the evaluation threshold.

[0014] In a second aspect, the present invention provides the following technical solution: a post-pipe jacking status detection system, the system comprising: A preprocessing module is used to obtain the post-pipe jacking state detection data and perform data preprocessing on the post-pipe jacking state detection data to obtain processed data; An extraction module, configured to determine key influencing factors using a hierarchical analysis method, and extract a key data set from the processed data based on the key influencing factors; A denoising module, configured to perform combined denoising processing on the data in the key data set to obtain a denoised data set; A clustering module, configured to perform clustering processing on the denoised data set using an improved clustering algorithm to obtain a clustered data set; The state module is used to combine and weight each of the key influencing factors to obtain an influence weight, and determine the final post-pipe jacking state based on the influence weight and the clustering data set.

[0015] In a third aspect, the present invention provides the following technical solution: a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned post-pipe jacking status detection method when executing the computer program.

[0016] In a fourth aspect, the present invention provides the following technical solution: a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned post-pipe jacking status detection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0018] Figure 1 Flowchart of the post-pipe jacking status detection method provided in the first embodiment of the present invention; Figure 2 This is a structural block diagram of a post-pipe jacking status detection system provided in the second embodiment of the present invention; Figure 3 A schematic diagram of the hardware structure of a computer provided in another embodiment of the present invention.

[0019] The embodiments of the present invention will be further described below with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0021] Example 1 In the first embodiment of the present invention, Figure 1 As shown, a method for detecting the status of a pipe jacking after operation includes: S1. Acquire post-pipe jacking status detection data, and perform data preprocessing on the post-pipe jacking status detection data to obtain processed data; Specifically, the post-pipe jacking status detection data here can be obtained through several sensors installed at corresponding positions, and the preprocessing process here is a processing method commonly used in the existing technology, such as data normalization, standardization, smoothing processing, etc.

[0022] S2. using the analytic hierarchy process to determine key influencing factors, and extracting a key data set from the processed data based on the key influencing factors; Specifically, the hierarchical analysis method here is a commonly used method in the prior art, so it will not be described in detail here. The hierarchical analysis method can be used to determine several key influencing factors that have a relatively high impact on the post-pipe jacking status. Then, the corresponding data can be extracted from the original processed data based on the extracted key influencing factors to obtain the key data set.

[0023] S3, performing combined denoising processing on the data in the key data set to obtain a denoised data set; Wherein, the step S3 includes: S31. Decomposing the data in the key data set to obtain a plurality of IMF components and trend items, and arranging the plurality of IMF components in descending order to obtain a first IMF component set; Specifically, the algorithm used for decomposition here is the CEEMD algorithm, and then the first IMF component set can be obtained by sorting in descending order according to the frequency of each component.

[0024] S32, calculating the noise judgment value of each IMF component in the first IMF component set : ; Where, represents the number of IMF components in the first IMF component set, Indicates the first IMF component concentration IMF components.

[0025] S33, determine the noise judgment value , storing the IMF components before the target arrangement position in a second IMF component set, determining the number of zero crossings of all IMF components in the first IMF component set, storing the IMF components whose number of zero crossings is less than a preset number in a third IMF component set, and storing the remaining IMF components in the first IMF component set except the second IMF component set and the third IMF component set in a fourth IMF component set; Specifically, the noise judgment value The IMF component corresponding to the minimum value of is specifically the dividing point between the high-frequency component and the effective component. The high-frequency component, i.e., the second IMF component set, can be extracted through the dividing point. Since white noise usually exists in the high-frequency component, it is necessary to denoise the high-frequency component. As for the number of zero crossings, since the high-frequency component fluctuates greatly, the effective component fluctuates moderately, and the low-frequency component fluctuates less, the low-frequency component can be extracted by setting a preset number of times, i.e., the third IMF component set is obtained. Since colored noise usually exists in the low-frequency component, it is necessary to perform corresponding processing on the low-frequency component. For the first IMF component set, the noisy components have been extracted separately, and the remaining components are components without noise or with very small noise. They can be directly used as effective components without processing and can directly participate in the subsequent reconstruction process.

[0026] S34, performing denoising and power conversion processing on the second IMF component set and the third IMF component set respectively to obtain a first denoised IMF component set and a second denoised IMF component set, and determining a denoised data set based on the first denoised IMF component set and the second denoised IMF component set; Wherein, the step S34 includes: S341, performing wavelet threshold denoising on the second IMF component set to obtain a first denoised IMF component set; Specifically, the wavelet threshold denoising here is a commonly used method in the prior art, and thus will not be described in detail.

[0027] S342: Determine a power spectrum of the third IMF component set, and determine a power spectrum matrix based on the power spectrum.

[0028] S343, normalize the power spectrum matrix to obtain a standard matrix, extract the eigenvector of the standard matrix, and determine the principal component sequence based on the eigenvector and the standard matrix. : ; Where, is a standard matrix, is the eigenvector; Specifically, the purpose of normalization here is to prevent a power spectrum with too large a value from becoming the main component in the subsequent principal component analysis, thereby ignoring other principal components, and to obtain the eigenvalue and then the eigenvector corresponding to the eigenvalue.

[0029] S344, arranging the principal components in the principal component sequence in descending order according to their contribution, and extracting the first several principal components after the descending order to obtain the target principal component, and determining the reconstructed power spectrum based on the target principal component : ; ; Where, Indicates the target principal components, express The corresponding eigenvector, represents the intermediate reconstructed power spectrum, Respectively Middle Rank Elements of the column, To reconstruct the adjustment factor, is the first Mean of column elements; Specifically, the contribution here refers to the proportion of a single principal component in the entire principal component sequence, and here it is necessary to eliminate the principal component with a smaller proportion, that is, a lower contribution, and the reconstruction adjustment factor here is specifically The standard deviation of each element in the matrix. At the same time, in the above formula, after the intermediate reconstructed power spectrum is determined, it needs to be inversely normalized.

[0030] S345, reconstructing the power spectrum Perform phase addition and inverse Fourier transform to obtain the second denoised IMF component set :

[0031] ; Where, represents the second denoised IMF component set Middle IMF components, is the inverse Fourier transform, is an imaginary number, Indicates the corresponding frequency phase; Specifically, after the above steps, the noise in the second IMF component set and the third IMF component set can be removed, and then they can be reconstructed with the fourth IMF component set and the trend term.

[0032] S346: Reconstruct the first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term to obtain a denoised data set.

[0033] S4. performing clustering processing on the denoised data set using an improved clustering algorithm to obtain a clustered data set; Wherein, the step S4 includes: S41, determining an intermediate data point in the denoised data set, and performing clustering with the intermediate data point as a cluster center to obtain a first cluster; Specifically, the middle data point here is specifically the data point corresponding to the median in the denoised data set, and the clustering here adopts the clustering method described in the following S442 and S444.

[0034] S42: If the number of data in the first cluster is less than a preset number, the positive data in the denoised data set is stored in a positive sample data set, and the negative data is stored in a negative sample data set; Specifically, if the amount of data in the first cluster is not less than a preset amount, the data in the first cluster may be directly used as the cluster data set.

[0035] S43: Determine a first mean value in the positive sample data set and a second mean value in the negative sample data set, and calculate an absolute value of a difference between the first mean value and the second mean value.

[0036] S44, performing clustering based on the absolute value of the difference and outputting a clustering data set; Wherein, the step S44 includes: S441: If the absolute value of the difference is smaller than a preset value, clustering is performed using the data corresponding to the first mean or the second mean as a cluster center to obtain a second cluster.

[0037] S442: If the number of data points in the second cluster is less than a preset number, randomly select a point in the denoised data set as a reference point, determine a data range with the reference point as the center and a preset distance as the radius, and if the number of data points within the data range is greater than a preset density threshold, use the reference point as a sample point, determine the center of the sample point, and perform clustering with the center of the sample point as the cluster center. Calculate the Euclidean distance between the sample point and the remaining data points in the denoised data set, and assign data points with a Euclidean distance less than the preset distance to the class corresponding to the sample point, so as to obtain a clustered data set. Specifically, if the amount of data in the second cluster is not less than a preset amount, the data in the second cluster can be directly used as the cluster data set.

[0038] S443: If the absolute value of the difference is not less than a preset value, clustering is performed using the data corresponding to the first mean and the data corresponding to the second mean as cluster centers to obtain a third cluster and a fourth cluster.

[0039] S444. If the number of data points in the third cluster is less than a preset number and the number of data points in the fourth cluster is less than a preset number, then arbitrarily select a point in the denoised data set as a reference point, determine a data range with the reference point as the center and a preset distance as the radius, and if the number of data points within the data range is greater than a preset density threshold, then use the reference point as a sample point, determine the center of the sample point, and perform clustering with the center of the sample point as the cluster center, calculate the Euclidean distance between the sample point and the remaining data points in the denoised data set, and classify the data points with a Euclidean distance less than the preset distance into the class corresponding to the sample point, so as to obtain a clustered data set; Specifically, if the amount of data in the third cluster is not less than a preset amount or the amount of data in the fourth cluster is not less than a preset amount, the data in the third cluster and the fourth cluster can be directly used as the cluster data set; At the same time, through the above steps, by judging the data scale in the cluster and selecting different cluster centers, the number of sample point judgments can be greatly reduced. At the same time, the time responsibility of clustering can be greatly reduced, and the clustering effect can be improved. It is suitable for the clustering process of large sample data.

[0040] S5. Combining and weighting the key influencing factors to obtain an influence weight, and determining a final post-pipe jacking status based on the influence weight and the clustering data set.

[0041] Wherein, the step S5 includes: S51, selecting the lowest influencing factor from the key influencing factors, and calculating the lowest influencing factor The first level of impact and other key influencing factors The second level of impact : ; ; Where, For the evaluation section, For the The key influencing factors are The indicator value on the evaluation segment, The lowest influencing factor is The indicator value on each evaluation segment; Specifically, the minimum influencing factor here is specifically screened by experts based on their own experience and knowledge to find an influencing factor with the least influence, that is, the minimum influencing factor is obtained, and the evaluation section here specifically refers to the category of the state after the jacking work, such as leakage, cracking, deformation, etc., and the index value here can be obtained based on the expert evaluation.

[0042] S52: Based on the first impact level And the second level of impact Calculate the first weight : ; ; Where, It is the important value of the indicator.

[0043] S53: Construct an original evaluation matrix and determine the index weight value based on the original evaluation matrix. : ; Where, is the first Rank Elements of the column; Specifically, the original evaluation matrix here can be obtained by scoring the questionnaire.

[0044] S54, based on the index proportion value Determine the second weight : .

[0045] S55: Preliminarily combine the first weight and the second weight to obtain a combined weight. : ; Where, Represent the first and second combination parameters respectively, Respectively represent the weight set consisting of the first weight and the second weight; Specifically, the combination parameter here is a variable.

[0046] S56. Determine the objective function: .

[0047] S57, solving the objective function to obtain the updated first combination parameter , Update the second combination parameters ; Specifically, the solution here can be obtained by differentiating the objective function, then determining the linear differential equation system that optimizes the first-order derivative conditions, and then solving the equation system.

[0048] S58: Update the first combination parameter based on the , the updating of the second combination parameter Determine impact weight : ; Specifically, after obtaining the updated first combination parameter , Update the second combination parameters Afterwards, in order to achieve the balance of weights, the parameters need to be normalized to improve the rationality of the weights.

[0049] S59, constructing an initial indicator evaluation matrix, based on the initial indicator evaluation matrix and the impact weight Determine the final status after pipe jacking.

[0050] Wherein, the step S59 includes: S591: Determine security classification levels and classification standards for each security classification level, and determine a classification matrix based on the security classification levels and the classification standards. ,in, The number of security classification levels; Specifically, in the actual grading process, it can be divided into 5 levels, namely very safe, safe, basically safe, less safe, and unsafe. The corresponding states are no damage, slight damage, general damage, more serious damage, and severe damage. By determining the grading standards for each safety grade, the corresponding grading standard matrix can be obtained.

[0051] S592. Constructing the initial indicator evaluation matrix , in the grading matrix Extract the The row vector corresponding to the key influencing factors, if the elements in the row vector are in a decreasing relationship, then when hour, ,when hour, ,when hour, , if the elements in the row vector are in increasing relationship, then when hour, ,when hour, ,when hour, ,in, For the clustering data set The key influencing factors are The data value on the evaluation segment, is the first Rank Elements of the column, The first Rank Elements of the column; Specifically, by judging the increasing and decreasing relationship of row elements, it can be determined whether the corresponding grading index is as large as possible or as small as possible, and then the value of the element in the initial index evaluation matrix can be determined, and when hour, , assuming s is 2, then when hour, , the rest of the elements are 0, when hour, , assuming s is 2, then when hour, , the rest of the elements are 0. Similarly, the rest of the elements can be obtained in the same way, that is, according to The value of is between two adjacent elements in the row vector, thereby determining the value of the element in the initial index evaluation matrix at the corresponding position.

[0052] S593, based on the influence weight With the initial indicator evaluation matrix Determine the final matrix : ; Where, The final matrix Rank Elements of the column, Indicates the The impact weights corresponding to the key influencing factors.

[0053] S594: Determine the safety status evaluation function based on the final matrix. If the installation status evaluation function is satisfied, the final post-pipe jacking state is There are safety classification levels, among which the safety status evaluation function is: ; Where, Indicates the final matrix row vectors, is the evaluation threshold; Specifically, the evaluation threshold here is 0.5.

[0054] The method for detecting the post-pipe jacking worker status provided in the first embodiment of the present invention first obtains the post-pipe jacking worker status detection data, performs data preprocessing on the post-pipe jacking worker status detection data to obtain processed data; then adopts the hierarchical analysis method to determine the key influencing factors, and extracts the key data set from the processed data based on the key influencing factors; then performs combined denoising processing on the data in the key data set to obtain a denoised data set; then uses the improved clustering algorithm to cluster the denoised data set to obtain a clustered data set; finally, combines and weights each key influencing factor to obtain an influence weight, and determines the final post-pipe jacking worker status based on the influence weight and the clustered data set. The present invention performs combined denoising on the data, which can effectively extract valid data from the mixed data and remove white noise, colored noise, etc. in the data, and then performs clustering processing, which can greatly improve the clustering speed and reduce the feature dimension to improve the quality and effectiveness of the data, and then determines the final post-pipe jacking worker status through the influence weight, thereby improving the accuracy and effectiveness of safety status identification.

[0055] Example 2 like Figure 2 As shown, in a second embodiment of the present invention, a post-pipe jacking status detection system is provided, the system comprising: Preprocessing module 1 is used to obtain the post-pipe jacking state detection data and perform data preprocessing on the post-pipe jacking state detection data to obtain processed data; Extraction module 2, for determining key influencing factors using a hierarchical analysis method, and extracting a key data set from the processed data based on the key influencing factors; Denoising module 3, used for performing combined denoising processing on the data in the key data set to obtain a denoised data set; A clustering module 4 is configured to perform clustering processing on the denoised data set using an improved clustering algorithm to obtain a clustered data set; A state module 5 is configured to combine and weight each of the key influencing factors to obtain an influence weight, and determine a final post-pipe jacking state based on the influence weight and the clustering data set; The denoising module 3 includes: a decomposition submodule, configured to decompose the data in the key data set to obtain a plurality of IMF components and trend items, and arrange the plurality of IMF components in descending order to obtain a first IMF component set; A noise submodule is used to calculate the noise judgment value of each IMF component in the first IMF component set : ; Where, represents the number of IMF components in the first IMF component set, Indicates the first IMF component concentration IMF components; Arrangement submodule, used to determine the noise judgment value , storing the IMF components before the target arrangement position in a second IMF component set, determining the number of zero crossings of all IMF components in the first IMF component set, storing the IMF components whose number of zero crossings is less than a preset number in a third IMF component set, and storing the remaining IMF components in the first IMF component set except the second IMF component set and the third IMF component set in a fourth IMF component set; a denoising submodule, configured to perform denoising and power conversion processing on the second IMF component set and the third IMF component set, respectively, to obtain a first denoised IMF component set and a second denoised IMF component set, and determine a denoised data set based on the first denoised IMF component set and the second denoised IMF component set.

[0056] The denoising submodule includes: a denoising unit, configured to perform wavelet threshold denoising on the second IMF component set to obtain a first denoised IMF component set; a power spectrum unit, configured to determine a power spectrum of the third IMF component set, and determine a power spectrum matrix based on the power spectrum; A standardization unit is used to standardize the power spectrum matrix to obtain a standard matrix, extract the eigenvector of the standard matrix, and determine the principal component sequence based on the eigenvector and the standard matrix. : ; Where, is a standard matrix, is the eigenvector; The principal component unit is used to sort the principal components in the principal component sequence in descending order according to their contribution, and extract the first several principal components after descending order to obtain the target principal component, and determine the reconstructed power spectrum based on the target principal component : ; ; Where, Indicates the target principal components, express The corresponding eigenvector, represents the intermediate reconstructed power spectrum, Respectively Middle Rank Elements of the column, To reconstruct the adjustment factor, is the first Mean of column elements; A phase unit for reconstructing the power spectrum Perform phase addition and inverse Fourier transform to obtain the second denoised IMF component set :

[0057] ; Where, represents the second denoised IMF component set Middle IMF components, is the inverse Fourier transform, is an imaginary number, Indicates the corresponding frequency phase; A reconstruction unit is configured to reconstruct the first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term to obtain a denoised data set.

[0058] The clustering module 4 includes: A first clustering submodule, configured to determine an intermediate data point in the denoised data set, and perform clustering with the intermediate data point as a cluster center to obtain a first cluster; a data partitioning submodule, configured to store the positive data in the denoised data set into a positive sample data set and the negative data into a negative sample data set if the amount of data in the first cluster is less than a preset amount; an absolute value submodule, configured to determine a first mean value in the positive sample data set and a second mean value in the negative sample data set, and calculate an absolute value of a difference between the first mean value and the second mean value; The second clustering submodule is configured to perform clustering based on the absolute value of the difference and output a clustered data set.

[0059] The second clustering submodule includes: a first clustering unit, configured to perform clustering using the data corresponding to the first mean or the second mean as a cluster center to obtain a second cluster if the absolute value of the difference is less than a preset value; a second clustering unit, configured to, if the number of data points in the second cluster is less than a preset number, select any point in the denoised data set as a reference point, determine a data range with the reference point as the center and a preset distance as the radius, and if the number of data points within the data range is greater than a preset density threshold, use the reference point as a sample point, determine the center of the sample point, and perform clustering with the center of the sample point as the cluster center, calculate the Euclidean distance between the sample point and the remaining data points in the denoised data set, and classify the data points with a Euclidean distance less than the preset distance into the class corresponding to the sample point, so as to obtain a clustered data set; A third clustering unit is configured to perform clustering using the data corresponding to the first mean and the data corresponding to the second mean as cluster centers to obtain a third cluster and a fourth cluster if the absolute value of the difference is not less than a preset value; The fourth clustering unit is used to, if the number of data in the third cluster is less than a preset number and the number of data in the fourth cluster is less than a preset number, select any point in the denoised data set as a reference point, determine the data range with the reference point as the center and the preset distance as the radius, if the number of data points in the data range is greater than a preset density threshold, use the reference point as a sample point, determine the center of the sample point and cluster with the center of the sample point as the cluster center, calculate the Euclidean distance between the sample point and the remaining data points in the denoised data set, and classify the data points with a Euclidean distance less than the preset distance into the class corresponding to the sample point to obtain a clustered data set.

[0060] The state module 5 includes: The influence degree submodule is used to select the lowest influence factor from the key influence factors and calculate the lowest influence factor The first level of impact and other key influencing factors The second level of impact : ; ; Where, For the evaluation section, For the The key influencing factors are The indicator value on the evaluation segment, The lowest influencing factor is The indicator value on each evaluation segment; A first weight submodule is used to And the second level of impact Calculate the first weight : ; ; Where, is the important value of the indicator; The weight submodule is used to construct the original evaluation matrix and determine the weight value of the indicator based on the original evaluation matrix : ; Where, is the first Rank Elements of the column; The second weight submodule is used to calculate the weight of the indicator based on the weight of the indicator. Determine the second weight : ; A combination submodule, configured to preliminarily combine the first weight and the second weight to obtain a combined weight : ; Where, Represent the first and second combination parameters respectively, Respectively represent the weight set consisting of the first weight and the second weight; Function submodule, used to determine the target function: ; The solution submodule is used to solve the objective function to obtain the updated first combination parameter , Update the second combination parameters ; An influence weight submodule, configured to update the first combination parameter based on the , the updating of the second combination parameter Determine impact weight : ; The state output submodule is used to construct an initial indicator evaluation matrix based on the initial indicator evaluation matrix and the influence weight Determine the final status after pipe jacking.

[0061] The state output submodule includes: A grading unit is configured to determine a security grading level and a grading standard for each of the security grading levels, and to determine a grading matrix based on the security grading levels and the grading standards. ,in, The number of security classification levels; Construction unit, used to construct the initial indicator evaluation matrix , in the grading matrix Extract the The row vector corresponding to the key influencing factors, if the elements in the row vector are in a decreasing relationship, then when hour, ,when hour, ,when hour, , if the elements in the row vector are in increasing relationship, then when hour, ,when hour, ,when hour, ,in, For the clustering data set The key influencing factors are The data value on the evaluation segment, is the first Rank Elements of the column, The first Rank Elements of the column; Matrix unit for weighting based on the influence With the initial indicator evaluation matrix Determine the final matrix : ; Where, The final matrix Rank Elements of the column, Indicates the The impact weight corresponding to each key influencing factor; The evaluation output unit is used to determine the safety status evaluation function based on the final matrix. If the installation status evaluation function is satisfied, the final post-pipelining status is There are safety classification levels, among which the safety status evaluation function is: ; Where, Indicates the final matrix row vectors, is the evaluation threshold.

[0062] In other embodiments of the present invention, the embodiments of the present invention provide the following technical solutions: a computer comprising a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101; the processor 101 implements the post-pipe jacking status detection method as described above when executing the computer program.

[0063] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present invention.

[0064] Memory 102 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 102 may include removable or non-removable (or fixed) media. Where appropriate, memory 102 may be internal or external to the data processing device. In certain embodiments, memory 102 is non-volatile memory. In certain embodiments, memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0065] The memory 102 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101 .

[0066] The processor 101 implements the above-mentioned post-pipe jacking status detection method by reading and executing the computer program instructions stored in the memory 102.

[0067] In some embodiments, the computer may further include a communication interface 103 and a bus 100. Figure 3 As shown, the processor 101 , the memory 102 , and the communication interface 103 are connected via a bus 100 and communicate with each other.

[0068] The communication interface 103 is used to implement communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also implement data communication with other components such as external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0069] Bus 100 includes hardware, software, or both, and couples components of a computer device to each other. Bus 100 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Bus 100 may include one or more buses, where appropriate. Although embodiments of the present invention describe and illustrate a particular bus, the present invention contemplates any suitable bus or interconnect.

[0070] The computer can execute the pipe jacking worker status detection method of the present invention based on the acquired pipe jacking worker status detection system, thereby realizing the pipe jacking worker status detection.

[0071] In some further embodiments of the present invention, in combination with the above-mentioned method for detecting the status of pipe jacking workers after the operation, the embodiments of the present invention provide the following technical solutions: a storage medium having a computer program stored thereon, and the computer program implements the above-mentioned method for detecting the status of pipe jacking workers after the operation when the computer program is executed by the processor.

[0072] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0073] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0074] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0075] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0076] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A method for detecting the status of a pipe jacking after operation, characterized in that: include: Acquiring post-pipe jacking status detection data, and performing data preprocessing on the post-pipe jacking status detection data to obtain processed data; Determining key influencing factors using a hierarchical analysis method, and extracting key data sets from the processed data based on the key influencing factors; Performing combined denoising processing on the data in the key data set to obtain a denoised data set; Performing clustering processing on the denoised data set using an improved clustering algorithm to obtain a clustered data set; Each of the key influencing factors is combined and weighted to obtain an influence weight, and a final post-pipe jacking status is determined based on the influence weight and the clustering data set.

2. The post-pipe jacking status detection method according to claim 1, characterized in that: The step of performing combined denoising processing on the data in the key data set to obtain a denoised data set includes: Decomposing the data in the key data set to obtain a plurality of IMF components and trend items, and arranging the plurality of IMF components in descending order to obtain a first IMF component set; Calculate the noise judgment value of each IMF component in the first IMF component set : ； Where, represents the number of IMF components in the first IMF component set, Indicates the first IMF component concentration IMF components; Determine the noise judgment value , storing the IMF components before the target arrangement position in a second IMF component set, determining the number of zero crossings of all IMF components in the first IMF component set, storing the IMF components whose number of zero crossings is less than a preset number in a third IMF component set, and storing the remaining IMF components in the first IMF component set except the second IMF component set and the third IMF component set in a fourth IMF component set; Denoising and power conversion are performed on the second IMF component set and the third IMF component set respectively to obtain a first denoised IMF component set and a second denoised IMF component set, and a denoised data set is determined based on the first denoised IMF component set and the second denoised IMF component set.

3. The post-pipe jacking status detection method according to claim 2, characterized in that: The steps of performing denoising and power conversion processing on the second IMF component set and the third IMF component set respectively to obtain a first denoised IMF component set and a second denoised IMF component set, and determining a denoised data set based on the first denoised IMF component set and the second denoised IMF component set include: performing wavelet threshold denoising on the second IMF component set to obtain a first denoised IMF component set; Determining a power spectrum of the third IMF component set, and determining a power spectrum matrix based on the power spectrum; The power spectrum matrix is normalized to obtain a standard matrix, the eigenvector of the standard matrix is extracted, and the principal component sequence is determined based on the eigenvector and the standard matrix. : ； Where, is a standard matrix, is the eigenvector; Arrange the principal components in the principal component sequence in descending order according to their contribution, and extract the first several principal components after descending order to obtain the target principal component, and determine the reconstructed power spectrum based on the target principal component : ； ； Where, Indicates the target principal components, express The corresponding eigenvector, represents the intermediate reconstructed power spectrum, Respectively Middle Rank Elements of the column, To reconstruct the adjustment factor, is the first Mean of column elements; The reconstructed power spectrum Perform phase addition and inverse Fourier transform to obtain the second denoised IMF component set : ； Where, represents the second denoised IMF component set Middle IMF components, is the inverse Fourier transform, is an imaginary number, Indicates the corresponding frequency phase; The first denoised IMF component set, the second denoised IMF component set, the fourth IMF component set, and the trend term are reconstructed to obtain a denoised data set.

4. The post-pipe jacking status detection method according to claim 1, characterized in that: The step of clustering the denoised data set using an improved clustering algorithm to obtain a clustered data set includes: Determine an intermediate data point in the denoised data set, and perform clustering with the intermediate data point as a cluster center to obtain a first cluster; If the number of data in the first cluster is less than a preset number, the positive data in the denoised data set is stored in a positive sample data set, and the negative data is stored in a negative sample data set; Determine a first mean in the positive sample data set and a second mean in the negative sample data set, and calculate an absolute value of a difference between the first mean and the second mean; Clustering is performed based on the absolute values of the differences and a clustered data set is output.

5. The post-pipe jacking status detection method according to claim 4 is characterized in that: The step of clustering based on the absolute value of the difference and outputting the clustering data set includes: If the absolute value of the difference is less than a preset value, clustering is performed using the data corresponding to the first mean or the second mean as the cluster center to obtain a second cluster; If the number of data in the second cluster is less than a preset number, then any point in the denoised data set is selected as a reference point, and a data range is determined with the reference point as the center and a preset distance as the radius. If the number of data points in the data range is greater than a preset density threshold, then the reference point is used as a sample point, the center of the sample point is determined, and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised data set is calculated, and the data points with a Euclidean distance less than the preset distance are classified into the class corresponding to the sample point to obtain a clustered data set; If the absolute value of the difference is not less than a preset value, clustering is performed using the data corresponding to the first mean and the data corresponding to the second mean as cluster centers to obtain a third cluster and a fourth cluster; If the number of data in the third cluster is less than a preset number and the number of data in the fourth cluster is less than a preset number, then any point in the denoised data set is selected as a reference point, and the data range is determined with the reference point as the center and the preset distance as the radius. If the number of data points within the data range is greater than a preset density threshold, then the reference point is used as a sample point, the center of the sample point is determined, and clustering is performed with the center of the sample point as the cluster center. The Euclidean distance between the sample point and the remaining data points in the denoised data set is calculated, and the data points with a Euclidean distance less than the preset distance are classified into the class corresponding to the sample point to obtain a clustered data set.

6. The post-pipe jacking status detection method according to claim 1, characterized in that: The step of combining and weighting the key influencing factors to obtain an influence weight, and determining the final post-pipe jacking status based on the influence weight and the clustering data set includes: Select the lowest impact factor from the key impact factors and calculate the lowest impact factor The first level of impact and other key influencing factors The second level of impact : ； ； Where, For the evaluation section, For the The key influencing factors are The indicator value on the evaluation segment, The lowest influencing factor is The indicator value on each evaluation segment; Based on the first impact And the second level of impact Calculate the first weight : ； ； Where, is the important value of the indicator; Construct an original evaluation matrix and determine the index weight value based on the original evaluation matrix : ； Where, is the first Rank Elements of the column; Based on the weighting value of the index Determine the second weight : ； Preliminarily combine the first weight and the second weight to obtain a combined weight : ； Where, Represent the first and second combination parameters respectively, Respectively represent the weight set consisting of the first weight and the second weight; Determine the objective function: ； Solve the objective function to obtain the updated first combination parameter , Update the second combination parameters ; Based on the update of the first combination parameter , the updating of the second combination parameter Determine impact weight : ； Construct an initial indicator evaluation matrix based on the initial indicator evaluation matrix and the impact weight Determine the final status after pipe jacking.

7. The post-pipe jacking status detection method according to claim 6, characterized in that: The initial indicator evaluation matrix is constructed based on the initial indicator evaluation matrix and the influence weight The steps to determine the final post-pipe jacking status include: Determine the security classification level and the classification standard of each security classification level, and determine the classification matrix based on the security classification level and the classification standard ,in, The number of security classification levels; Constructing the initial indicator evaluation matrix , in the grading matrix Extract the The row vector corresponding to the key influencing factors, if the elements in the row vector are in a decreasing relationship, then when hour, ,when hour, ,when hour, , if the elements in the row vector are in increasing relationship, then when hour, ,when hour, ,when hour, ,in, For the clustering data set The key influencing factors are The data value on the evaluation segment, is the first Rank Elements of the column, The first Rank Elements of the column; Based on the impact weight With the initial indicator evaluation matrix Determine the final matrix : ； Where, The final matrix Rank Elements of the column, Indicates the The impact weight corresponding to each key influencing factor; The safety status evaluation function is determined based on the final matrix. If the installation status evaluation function is satisfied, the final post-pipelining status is There are safety classification levels, among which the safety status evaluation function is: ； Where, Indicates the final matrix row vectors, is the evaluation threshold.

8. A post-pipe jacking status detection system, characterized in that: The system comprises: A preprocessing module is used to obtain the post-pipe jacking state detection data and perform data preprocessing on the post-pipe jacking state detection data to obtain processed data; An extraction module, configured to determine key influencing factors using a hierarchical analysis method, and extract a key data set from the processed data based on the key influencing factors; A denoising module, configured to perform combined denoising processing on the data in the key data set to obtain a denoised data set; A clustering module, configured to perform clustering processing on the denoised data set using an improved clustering algorithm to obtain a clustered data set; The state module is used to combine and weight each of the key influencing factors to obtain an influence weight, and determine the final post-pipe jacking state based on the influence weight and the clustering data set.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the post-pipe jacking status detection method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the method for detecting the post-pipe jacking status according to any one of claims 1 to 7 is implemented.

Images