Data processing method and device for eliminating interference factors for pipeline thermal displacement

Abstract

The invention provides a data processing method and device for eliminating interference factors for pipeline thermal displacement. The method comprises the steps that the thermal displacement distance of a target pipeline in a thermal power plant is acquired; in response to the acquisition of the thermal displacement distance, acquiring position information and environment information of the target pipeline at a plurality of data acquisition moments, and forming a sample information set by using the data acquisition moments, the position information and the environment information; constructing a covariance matrix and a correlation matrix based on the sample information set; determining a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and determining a second eigenvalue sequence and a second eigenvector set based on the correlation matrix; and determining an interference source and a non-interference source in the environmental information based on the first feature value sequence, the first feature vector set, the second feature value sequence and the second feature vector set. According to the technical scheme, the reason of sudden change of the depth value can be quickly positioned, and the operation safety of the thermal power plant is improved.

Description

[Technical field]

[0001] The present application relates to the technical field of safety control of thermal power plants, and in particular to a data processing method and device for eliminating interference factors for thermal displacement of pipelines. [Background technology]

[0002] High-temperature pipelines are the core components of thermal power units in thermal power plants, and the status monitoring of high-temperature pipelines is an important part of the safety monitoring work of the entire thermal power plant. Once the status of high-temperature pipelines is abnormal, such as displacement, sinking, or displacement deviating from the design value, the unit may need to be shut down for inspection and reconstruction, or even worse, a pipeline explosion and leakage accident may occur.

[0003] In this regard, the safety level of the high-temperature pipeline can be judged by monitoring its displacement. On this basis, relevant technologies propose to use a depth camera to realize non-contact three-dimensional displacement measurement of the high-temperature pipeline.

[0004] However, the depth values ​​measured by the depth camera occasionally have data mutation problems, which may be caused by various environmental interference factors such as lighting. However, due to the diversity of environmental interference factors, it is difficult to effectively determine which specific environmental interference factor is involved in the mutation in related technologies.

[0005] Therefore, for depth cameras that monitor thermal displacement of pipelines, how to eliminate interference factors for sudden changes in depth values ​​has become a technical problem that needs to be solved urgently. [Summary of the invention]

[0006] The embodiments of the present application provide a data processing method and device for eliminating interference factors for pipeline thermal displacement, aiming to solve the technical problem in the related art that it is difficult to determine the environmental interference factors of the sudden change in the depth value of the depth camera that monitors the thermal displacement of the pipeline.

[0007] In a first aspect, an embodiment of the present application provides a data processing method for eliminating interference factors for pipeline thermal displacement, comprising:

[0008] Obtain the thermal displacement distance of the target pipeline in the thermal power plant;

[0009] In response to the acquisition of the thermal displacement distance, the position information and the environmental information of the target pipeline at a plurality of data acquisition moments are acquired, and a sample information set is formed by the data acquisition moments, the position information and the environmental information;

[0010] Based on the sample information set, construct a covariance matrix and a correlation matrix, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set;

[0011] Determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix;

[0012] Based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set, interference sources and non-interference sources are determined in the environmental information.

[0013] In one embodiment of the present application, optionally, obtaining the thermal displacement distance of a target pipeline in a thermal power plant includes:

[0014] Collecting the location information of the target pipeline at specified time intervals;

[0015] Based on the difference between the current position information and the previous position information, the thermal displacement distance of the target pipeline is determined, wherein:

[0016] If the thermal displacement distance is greater than or equal to the preset safety distance, it is determined that thermal displacement occurs in the target pipeline, and the step of obtaining the position information and environmental information of the target pipeline at multiple data collection moments is entered.

[0017] In one embodiment of the present application, optionally, constructing a covariance matrix based on the sample information set includes:

[0018] According to a preset information type arrangement order, the sample information set is converted into an initial matrix, wherein any row of the initial matrix includes the data collection time of the target pipeline and the location information and environmental information collected at the data collection time, and any column of the initial matrix is ​​information of any information type among the data collection time, the location information and the environmental information;

[0019] determining the covariance of each two of the information types;

[0020] Based on the covariance, the covariance matrix is ​​constructed.

[0021] In one embodiment of the present application, optionally, constructing a correlation matrix based on the sample information set includes:

[0022] For each information type possessed by the sample information set, determining a standard deviation of the information type based on a column element corresponding to the information type in the initial matrix;

[0023] determining the correlation between each two information types based on the covariance and respective standard deviations of each two information types;

[0024] Based on the correlation, the correlation matrix is ​​constructed, wherein the element in the i-th row and j-th column of the correlation matrix is ​​the correlation between the information under the i-th information type and the information under the j-th information type in the sample information set.

[0025] In one embodiment of the present application, optionally, determining interference sources and non-interference sources in the environmental information based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set, includes:

[0026] A third eigenvalue is selected from the first eigenvalue sequence, and a target eigenvector corresponding to the third eigenvalue is intercepted from the first eigenvector set.

[0027] The third eigenvalue is greater than or equal to a preset correlation threshold, or the third eigenvalue is in a predetermined position when the first eigenvalue sequence is arranged from large to small; and

[0028] A fourth eigenvalue is selected from the second eigenvalue sequence, and a target eigenvector corresponding to the fourth eigenvalue is intercepted from the second eigenvector set.

[0029] wherein the fourth eigenvalue is non-zero;

[0030] A principal component analysis process is performed on all the intercepted target feature vectors to determine interference sources and non-interference sources in the environmental information.

[0031] In one embodiment of the present application, optionally, performing principal component analysis on all the intercepted target feature vectors includes:

[0032] For each set of the target feature vectors, a target scalar is determined in the target feature vectors,

[0033] Wherein, the target scalar is in the top specified position when all scalars of the target feature vector are arranged from large to small, or the target scalar is greater than or equal to a preset scalar threshold, or the difference between the target scalar and the scalar average value of the target feature vector is greater than a preset scalar difference;

[0034] Environmental information is screened from the information type corresponding to the target scalar as an interference source, and other environmental information other than the interference source is determined as a non-interference source.

[0035] In one embodiment of the present application, optionally, after determining the first eigenvalue sequence and the first eigenvector set and determining the second eigenvalue sequence and the second eigenvector set, the method further includes:

[0036] The first feature vector set and the second feature vector set are normalized.

[0037] In a second aspect, an embodiment of the present application provides a data processing device for eliminating interference factors for pipeline thermal displacement, comprising:

[0038] A thermal displacement distance acquisition unit is used to acquire the thermal displacement distance of a target pipeline in a thermal power plant;

[0039] an information acquisition unit, configured to acquire the position information and environmental information of the target pipeline at a plurality of data acquisition moments in response to the acquisition of the thermal displacement distance, and to form a sample information set with the data acquisition moments, the position information and the environmental information;

[0040] A matrix construction unit, configured to construct a covariance matrix and a correlation matrix based on the sample information set, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set;

[0041] an eigenvalue and vector calculation unit, configured to determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and to determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix;

[0042] An interference judgment unit is used to determine interference sources and non-interference sources in the environmental information based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set.

[0043] In one embodiment of the present application, optionally, the thermal displacement distance acquisition unit is used to: collect the position information of the target pipeline at specified time intervals; determine the thermal displacement distance of the target pipeline based on the difference between the current position information and the adjacent previous position information, wherein if the thermal displacement distance is greater than or equal to a preset safety distance, it is determined that thermal displacement has occurred in the target pipeline, and the step of obtaining the position information and environmental information of the target pipeline at multiple data collection moments is entered.

[0044] In one embodiment of the present application, optionally, the matrix construction unit includes:

[0045] An initial matrix construction unit is used to convert the sample information set into an initial matrix according to a preset information type arrangement order, wherein any row of the initial matrix includes the data collection time of the target pipeline and the location information and environmental information collected at the data collection time, and any column of the initial matrix is ​​information of any information type among the data collection time, the location information and the environmental information;

[0046] a covariance calculation unit, used to determine the covariance of each two information types;

[0047] A covariance matrix construction unit is used to construct the covariance matrix based on the covariance.

[0048] In one embodiment of the present application, optionally, the matrix construction unit includes:

[0049] a standard deviation calculation unit, configured to determine, for each information type possessed by the sample information set, a standard deviation of the information type based on a column element corresponding to the information type in the initial matrix;

[0050] a correlation calculation unit, configured to determine the correlation between each two information types based on the covariance and respective standard deviations of each two information types;

[0051] A correlation difference matrix construction unit is used to construct the correlation matrix based on the correlation, wherein the element in the i-th row and j-th column of the correlation matrix is ​​the correlation between the information under the i-th information type in the sample information set and the information under the j-th information type.

[0052] In one embodiment of the present application, optionally, the interference determination unit includes:

[0053] A first processing unit is used to screen a third eigenvalue in the first eigenvalue sequence, and to intercept a target eigenvector corresponding to the third eigenvalue in the first eigenvector set, wherein the third eigenvalue is greater than or equal to a preset correlation threshold, or the third eigenvalue is in a predetermined position when the first eigenvalue sequence is arranged from large to small;

[0054] A second processing unit is used to screen a fourth eigenvalue in the second eigenvalue sequence, and to intercept a target eigenvector corresponding to the fourth eigenvalue in the second eigenvector set, wherein the fourth eigenvalue is non-zero;

[0055] The principal component analysis unit is used to perform principal component analysis on all the intercepted target feature vectors to determine the interference sources and non-interference sources in the environmental information.

[0056] In one embodiment of the present application, optionally, the principal component analysis unit is used to: for each group of the target feature vectors, determine a target scalar in the target feature vector, wherein the target scalar is in the front specified position when all scalars of the target feature vector are arranged from large to small, or the target scalar is greater than or equal to a preset scalar threshold, or the difference between the target scalar and the scalar average value of the target feature vector is greater than a preset scalar difference; filter environmental information from the information type corresponding to the target scalar as an interference source, and determine other environmental information other than the interference source as non-interference sources.

[0057] In one embodiment of the present application, optionally, the device further includes:

[0058] A normalization processing unit is used to perform normalization processing on the first eigenvalue set and the second eigenvector set after determining the first eigenvalue sequence and the first eigenvector set and determining the second eigenvalue sequence and the second eigenvector set.

[0059] In a third aspect, an embodiment of the present application provides a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are configured to enable the processor to execute the method described in the first aspect above.

[0060] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the method described in the first aspect above.

[0061] The above technical solution aims at the technical problem that it is difficult to determine the environmental interference factors of the depth value mutation of the depth camera that monitors the thermal displacement of the pipeline in the related technology. The location information and environmental information of multiple data collection moments are automatically processed into a correlation matrix and a covariance matrix, and the two matrices are used for automatic principal component analysis, so as to determine the interference factors that have the main contribution to the depth value mutation of the depth camera among the environmental factors that affect the thermal displacement of the high-temperature pipeline, and exclude irrelevant interference factors. In this way, the cause of the depth value mutation can be quickly located, which facilitates the timely adoption of safety control measures for environmental factors, avoids high-temperature pipeline accidents caused by environmental factors, and improves the safety of thermal power plant operation.

Brief Description of the Drawings

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A flow chart of a data processing method for eliminating interference factors for pipeline thermal displacement according to an embodiment of the present application is shown;

[0064] Figure 2 A block diagram of a computer device according to an embodiment of the present application is shown;

[0065] Figure 3 A block diagram of a computer device according to another embodiment of the present application is shown. [Specific implementation method]

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Figure 1 A flow chart of a data processing method for eliminating interference factors for pipeline thermal displacement according to an embodiment of the present application is shown.

[0068] like Figure 1 As shown, according to an embodiment of the present application, a data processing method for eliminating interference factors for pipeline thermal displacement includes:

[0069] Step 102, obtaining the thermal displacement distance of the target pipeline in the thermal power plant.

[0070] The target pipeline in a thermal power plant will be displaced under the action of high temperature, and the position deviation caused by this displacement is the thermal displacement distance.

[0071] In a possible design, the position information of the target pipeline can be collected at specified time intervals, and the thermal displacement distance of the target pipeline can be determined based on the difference between the current position information and the adjacent previous position information, wherein if the thermal displacement distance is greater than or equal to a preset safety distance, it is determined that thermal displacement has occurred in the target pipeline.

[0072] Optionally, the position information includes a depth value, and a depth camera is used to monitor the position of the target pipeline, and the thermal displacement distance of the target pipeline is determined by monitoring changes in the depth value obtained by the depth camera.

[0073] Step 104, in response to the acquisition of the thermal displacement distance, the position information and environmental information of the target pipeline at multiple data acquisition moments are acquired, and a sample information set is formed by the data acquisition moments, the position information and the environmental information.

[0074] The position information at the multiple data collection moments is different, and the position information at the multiple data collection moments reflects the thermal displacement of the target pipeline over time. Optionally, the position information includes the coordinates of a designated point of the target pipeline in a three-dimensional coordinate system.

[0075] The environmental information collected at a single data collection moment includes information in multiple dimensions, such as temperature, humidity, and light. Of course, the environmental information can also include any other environmental information other than temperature, humidity, and light that may interfere with the depth camera and cause a sudden change in depth value. Therefore, the environmental information at multiple data collection moments reflects the changes in the environment in which the target pipeline is located when thermal displacement occurs over time.

[0076] Therefore, the sample information set composed of the data collection time, the location information and the environmental information reflects, to a certain extent, how the location information of the target pipeline changes over time under the interference of some environmental information in the multi-dimensional environmental information. At the same time, a depth value can be obtained by monitoring the position of the target pipeline with a depth camera. The depth value monitored by the depth camera may mutate under the influence of environmental interference information. Analysis shows that the environmental interference information that contributes to the sudden change in the depth value of the depth camera is the aforementioned partial environmental information that interferes with the location information of the target pipeline. In other words, based on how the location information of the target pipeline reflected by the sample information set changes over time under the interference of some environmental information, it is possible to analyze what the specific part of the environmental information is. In other words, it is possible to determine what the environmental interference information that contributes to the sudden change in the depth value of the depth camera is.

[0077] Step 106, constructing a covariance matrix and a correlation matrix based on the sample information set, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set.

[0078] The specific method of constructing the covariance matrix is ​​as follows.

[0079] Firstly, the sample information set is converted into an initial matrix according to a preset information type arrangement order.

[0080] It can be understood that any row of the initial matrix includes the data collection time of the target pipeline and the location information and environmental information collected at the data collection time, and any column of the initial matrix is ​​information of any information type among the data collection time, the location information and the environmental information. For example, according to the data collection time, the x, y, z coordinate values ​​of the specified point on the target pipeline, and the order of multiple information types such as temperature, humidity and light, the initial matrix is ​​constructed as follows:

[0081] 2023-04-01 10:00:00, 100, 200, 10, 25.0, 50.0, 500.0,

[0082] 2023-04-01 10:01:00, 150, 250, 15, 30.0, 40.0, 600.0,

[0083] 2023-04-01 10:02:00, 200, 300, 20, 28.0, 60.0, 700.0.

[0084] Next, the covariance of each two information types is determined, and then based on the covariance, the covariance matrix is ​​constructed.

[0085] The covariance matrix is ​​an n*n matrix, where n is the number of information types. In the above example, the covariance matrix is ​​a 7*7 matrix. ij is the covariance between the i-th information type and the j-th information type, and is calculated as follows:

[0086]

[0087] Among them, x ki is the value corresponding to the i-th information type at the k-th data collection moment, is the mean of the i-th information type, and m is the number of observation samples, that is, the number of data collection moments.

[0088] At this point, based on the initial matrix in the previous example, the covariance matrix is ​​constructed as follows:

[0089]

[0090] The specific method of constructing the covariance matrix is ​​as follows.

[0091] First, for each information type possessed by the sample information set, the standard deviation of the information type is determined based on the column elements corresponding to the information type in the initial matrix; and the correlation between each two information types is determined based on the covariance and respective standard deviations of each two information types.

[0092] The correlation matrix is ​​also an n*n matrix. In the above example, the correlation matrix is ​​a 7*7 matrix. ij is the correlation coefficient between the i-th information type and the j-th information type, and is calculated as follows:

[0093]

[0094] Cij That is, the covariance between the i-th information type and the j-th information type, σ i and σ j are the standard deviations of the i-th information type and the j-th information type, and the correlation R ij The value range is between -1 and 1, indicating the strength and direction of the linear relationship between variables.

[0095] Next, based on the correlation, the correlation matrix is ​​constructed, wherein the element in the i-th row and j-th column of the correlation matrix is ​​the correlation between the information under the i-th information type and the information under the j-th information type in the sample information set.

[0096] At this point, based on the information in the previous example, the covariance matrix is ​​constructed as follows:

[0097]

[0098] Step 108: Determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix.

[0099] Based on the covariance matrix, the first eigenvalue sequence of the covariance matrix is ​​calculated as follows:

[0100] [5000, -500, -250, -50, 50, 10000, 9000].

[0101] Based on the covariance matrix, the first eigenvector set of the covariance matrix is ​​calculated as follows:

[0102] [[1.00000000e-04, -5.00000000e-01, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 1.00000000e+00, -2.50000000e-01];

[0103] [1.00000000e-04, 5.00000000e-01, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 1.00000000e+00, -2.50000000e-01];

[0104] [0.00000000e+00, 0.00000000e+00, 1.00000000e+00, 0.00000000e+00, -1.00000000e+00, 0.00000000e+00, 0.00000000e+00];

[0105] [0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 1.00000000e+00, -1.00000000e+00, 0.00000000e+00, 0.00000000e+00];

[0106] [0.00000000e+00, 0.00000000e+00, 1.00000000e+00, 0.00000000e+00, 0.00000000e+00, -1.00000000e+00, 0.00000000e+00];

[0107] [0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 1.00000000e+00];

[0108] [0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 1.00000000e+00, 1.00000000e+00]].

[0109] Based on the correlation matrix, the second eigenvalue sequence of the correlation matrix is ​​calculated as follows:

[0110] [1, 0, 0, 0, 0, 1, 1].

[0111] Based on the correlation matrix, the second eigenvector set of the correlation matrix is ​​calculated as follows:

[0112] [[0.57735027, -0.57735027, 0.57735027, -0.57735027, 0.57735027, -0.57735027, -0.57735027];

[0113] [-0.57735027, 0.57735027, -0.57735027, 0.57735027, -0.57735027, 0.57735027, 0.57735027];

[0114] [0.40824829, 0.40824829, 0.40824829, 0.40824829, -0.40824829, -0.40824829, -0.40824829];

[0115] [0.40824829, -0.40824829, -0.40824829, 0.40824829, 0.40824829, -0.40824829, 0.40824829];

[0116] [0.40824829, 0.40824829, -0.40824829, -0.40824829, 0.40824829, -0.40824829, 0.40824829, 0.40824829];

[0117] [0, -0, 0, 0, 0, 1, 0];

[0118] [0, 0, 0, 0, 0, 1,]].

[0119] Step 110: Determine interference sources and non-interference sources in the environmental information based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set.

[0120] The first eigenvalue sequence reflects the difference in the degree of change of the variables under different information types. Each vector of the first eigenvector set corresponds to an eigenvalue in the first eigenvalue sequence, representing the contribution of different information types to interference under the information type corresponding to the eigenvalue. The second eigenvalue sequence reflects whether different information types are related to interference, 1 represents related, and 0 represents unrelated. Each vector of the second eigenvector set corresponds to an eigenvalue in the second eigenvalue sequence, representing the correlation between different information types and interference under the information type corresponding to the eigenvalue.

[0121] In one possible design, a specific method for determining interference sources and non-interference sources in the environmental information in step 110 is as follows.

[0122] First, the third eigenvalue is screened in the first eigenvalue sequence, and the target eigenvector corresponding to the third eigenvalue is intercepted in the first eigenvector set.

[0123] Among them, the third eigenvalue is greater than or equal to a preset relevant threshold, or the third eigenvalue is in a predetermined ranking when the first eigenvalue sequence is arranged from large to small, and the preset relevant threshold refers to the lowest eigenvalue when the variable under the information type contributes to the interference. Similarly, the predetermined ranking refers to the ranking of the eigenvalue when the variable under the information type contributes to the interference.

[0124] In this way, the third eigenvalue is the eigenvalue of the variable that effectively contributes to the interference, and the target eigenvector corresponding to the third eigenvalue reflects the contribution level of the variable to the interference in different dimensions.

[0125] At the same time, the fourth eigenvalue is screened in the second eigenvalue sequence, and the target eigenvector corresponding to the fourth eigenvalue is intercepted in the second eigenvector set.

[0126] Among them, the fourth eigenvalue is non-zero, which means that the variable under the information type corresponding to the fourth eigenvalue is related to the interference, and the target eigenvector corresponding to the fourth eigenvalue represents the degree of correlation between the variable that effectively contributes to the interference and the interference.

[0127] At this point, principal component analysis is performed on all the intercepted target feature vectors to determine interference sources and non-interference sources in the environmental information.

[0128] Specifically, for each group of the target feature vectors, a target scalar is determined in the target feature vector.

[0129] In one possible design, the target scalar is in a top specified position when all scalars of the target feature vector are arranged from large to small.

[0130] In another possible design, the target scalar is greater than or equal to a preset scalar threshold.

[0131] In yet another possible design, a difference between the target scalar and a scalar average value of the target feature vector is greater than a preset scalar difference.

[0132] That is to say, a target scalar that is larger, larger enough, or larger than the average level of the scalars corresponding to each information type (ie, each variable) of the target feature vector is selected. The target scalar represents that the information type to which it belongs has a greater impact on the depth value mutation of the depth camera.

[0133] So far, environmental information is screened from the information type corresponding to the target scalar as an interference source, and other environmental information other than the interference source is determined as a non-interference source.

[0134] The above technical solution automatically processes the location information and environmental information at multiple data collection moments into a correlation matrix and a covariance matrix, and performs automated principal component analysis through these two matrices, thereby determining the interference factors that have the main contribution to the depth value mutation of the depth camera among the environmental factors that affect the thermal displacement of the high-temperature pipeline, and eliminating irrelevant interference factors. In this way, the cause of the depth value mutation can be quickly located, which facilitates timely implementation of safety control measures for environmental factors, avoids high-temperature pipeline accidents caused by environmental factors, and improves the safety of thermal power plant operation.

[0135] The embodiment of the present application provides a data processing device for eliminating interference factors for pipeline thermal displacement, including:

[0136] A thermal displacement distance acquisition unit is used to acquire the thermal displacement distance of a target pipeline in a thermal power plant;

[0137] an information acquisition unit, configured to acquire the position information and environmental information of the target pipeline at a plurality of data acquisition moments in response to the acquisition of the thermal displacement distance, and to form a sample information set with the data acquisition moments, the position information and the environmental information;

[0138] A matrix construction unit, configured to construct a covariance matrix and a correlation matrix based on the sample information set, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set;

[0139] an eigenvalue and vector calculation unit, configured to determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and to determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix;

[0140] An interference judgment unit is used to determine interference sources and non-interference sources in the environmental information based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set.

[0141] In one embodiment of the present application, optionally, the thermal displacement distance acquisition unit is used to: collect the position information of the target pipeline at specified time intervals; determine the thermal displacement distance of the target pipeline based on the difference between the current position information and the adjacent previous position information, wherein if the thermal displacement distance is greater than or equal to a preset safety distance, it is determined that thermal displacement has occurred in the target pipeline, and the step of obtaining the position information and environmental information of the target pipeline at multiple data collection moments is entered.

[0142] In one embodiment of the present application, optionally, the matrix construction unit includes:

[0143] An initial matrix construction unit is used to convert the sample information set into an initial matrix according to a preset information type arrangement order, wherein any row of the initial matrix includes the data collection time of the target pipeline and the location information and environmental information collected at the data collection time, and any column of the initial matrix is ​​information of any information type among the data collection time, the location information and the environmental information;

[0144] a covariance calculation unit, used to determine the covariance of each two information types;

[0145] A covariance matrix construction unit is used to construct the covariance matrix based on the covariance.

[0146] In one embodiment of the present application, optionally, the matrix construction unit includes:

[0147] a standard deviation calculation unit, configured to determine, for each information type possessed by the sample information set, a standard deviation of the information type based on a column element corresponding to the information type in the initial matrix;

[0148] a correlation calculation unit, configured to determine the correlation between each two information types based on the covariance and respective standard deviations of each two information types;

[0149] A correlation difference matrix construction unit is used to construct the correlation matrix based on the correlation, wherein the element in the i-th row and j-th column of the correlation matrix is ​​the correlation between the information under the i-th information type in the sample information set and the information under the j-th information type.

[0150] In one embodiment of the present application, optionally, the interference determination unit includes:

[0151] A first processing unit is used to screen a third eigenvalue in the first eigenvalue sequence, and to intercept a target eigenvector corresponding to the third eigenvalue in the first eigenvector set, wherein the third eigenvalue is greater than or equal to a preset correlation threshold, or the third eigenvalue is in a predetermined position when the first eigenvalue sequence is arranged from large to small;

[0152] A second processing unit is used to screen a fourth eigenvalue in the second eigenvalue sequence, and to intercept a target eigenvector corresponding to the fourth eigenvalue in the second eigenvector set, wherein the fourth eigenvalue is non-zero;

[0153] The principal component analysis unit is used to perform principal component analysis on all the intercepted target feature vectors to determine the interference sources and non-interference sources in the environmental information.

[0154] In one embodiment of the present application, optionally, the principal component analysis unit is used to: for each group of the target feature vectors, determine a target scalar in the target feature vector, wherein the target scalar is in the front specified position when all scalars of the target feature vector are arranged from large to small, or the target scalar is greater than or equal to a preset scalar threshold, or the difference between the target scalar and the scalar average value of the target feature vector is greater than a preset scalar difference; filter environmental information from the information type corresponding to the target scalar as an interference source, and determine other environmental information other than the interference source as non-interference sources.

[0155] In one embodiment of the present application, optionally, the device further includes:

[0156] A normalization processing unit is used to perform normalization processing on the first eigenvalue set and the second eigenvector set after determining the first eigenvalue sequence and the first eigenvector set and determining the second eigenvalue sequence and the second eigenvector set.

[0157] The device uses any one of the solutions described in the above embodiments, and therefore has all the above technical effects, which will not be repeated here.

[0158] In addition, in one embodiment, the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 2 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the method described in any of the above embodiments can be implemented.

[0159] In one embodiment, the present application further provides a computer device, which may be a client, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, the method described in any of the above embodiments can be implemented.

[0160] Any of the above-mentioned computer devices in the embodiments of the present application may exist in various forms, including but not limited to:

[0161] (1) Mobile communication devices: These devices are characterized by their mobile communication functions and their main purpose is to provide voice and data communications. These terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

[0162] (2) Ultra-mobile personal computer devices: These devices fall into the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, such as iPad.

[0163] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys, wearable devices, and portable car navigation devices.

[0164] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0165] (5) Other electronic devices with data interaction functions.

[0166] In addition, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to perform the following steps:

[0167] Obtain the thermal displacement distance of the target pipeline in the thermal power plant;

[0168] In response to the acquisition of the thermal displacement distance, the position information and the environmental information of the target pipeline at a plurality of data acquisition moments are acquired, and a sample information set is formed by the data acquisition moments, the position information and the environmental information;

[0169] Based on the sample information set, construct a covariance matrix and a correlation matrix, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set;

[0170] Determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix;

[0171] Based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set, interference sources and non-interference sources are determined in the environmental information.

[0172] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description in the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0173] The above describes the technical solution of the present application in detail in combination with the accompanying drawings. Through the technical solution of the present application, the location information and environmental information at multiple data collection times are automatically processed into a correlation matrix and a covariance matrix, and the two matrices are used to perform automated principal component analysis, thereby determining the interference factors that have a major contribution to the depth value mutation of the depth camera among the environmental factors that affect the thermal displacement of the high-temperature pipeline, and excluding irrelevant interference factors. In this way, the cause of the depth value mutation can be quickly located, which facilitates timely safety control measures for environmental factors, avoids high-temperature pipeline accidents caused by environmental factors, and improves the safety of thermal power plant operation.

[0174] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0175] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0176] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0177] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0178] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0179] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A data processing method for eliminating interference factors for pipeline thermal displacement, characterized in that: include: Obtain the thermal displacement distance of the target pipeline in the thermal power plant; In response to the acquisition of the thermal displacement distance, the position information and the environmental information of the target pipeline at a plurality of data acquisition moments are acquired, and a sample information set is formed by the data acquisition moments, the position information and the environmental information; Based on the sample information set, construct a covariance matrix and a correlation matrix, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set; Determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix; Based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set, interference sources and non-interference sources are determined in the environmental information.

2. The method according to claim 1, characterized in that: The step of obtaining the thermal displacement distance of a target pipeline in a thermal power plant includes: Collecting the location information of the target pipeline at specified time intervals; Based on the difference between the current position information and the previous position information, the thermal displacement distance of the target pipeline is determined, wherein: If the thermal displacement distance is greater than or equal to the preset safety distance, it is determined that thermal displacement occurs in the target pipeline, and the step of obtaining the position information and environmental information of the target pipeline at multiple data collection moments is entered.

3. The method according to claim 1, characterized in that The constructing a covariance matrix based on the sample information set includes: According to a preset information type arrangement order, the sample information set is converted into an initial matrix, wherein any row of the initial matrix includes the data collection time of the target pipeline and the location information and environmental information collected at the data collection time, and any column of the initial matrix is ​​information of any information type among the data collection time, the location information and the environmental information; determining the covariance of each two of the information types; Based on the covariance, the covariance matrix is ​​constructed.

4. The method according to claim 3, characterized in that The constructing a correlation matrix based on the sample information set includes: For each information type possessed by the sample information set, determining a standard deviation of the information type based on a column element corresponding to the information type in the initial matrix; determining the correlation between each two information types based on the covariance and respective standard deviations of each two information types; Based on the correlation, the correlation matrix is ​​constructed, wherein the element in the i-th row and j-th column of the correlation matrix is ​​the correlation between the information under the i-th information type and the information under the j-th information type in the sample information set.

5. The method according to any one of claims 1 to 4, characterized in that The determining, in the environment information, interference sources and non-interference sources based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set, includes: A third eigenvalue is selected from the first eigenvalue sequence, and a target eigenvector corresponding to the third eigenvalue is intercepted from the first eigenvector set. The third eigenvalue is greater than or equal to a preset correlation threshold, or the third eigenvalue is in a predetermined position when the first eigenvalue sequence is arranged from large to small; and A fourth eigenvalue is selected from the second eigenvalue sequence, and a target eigenvector corresponding to the fourth eigenvalue is intercepted from the second eigenvector set. wherein the fourth eigenvalue is non-zero; A principal component analysis process is performed on all the intercepted target feature vectors to determine interference sources and non-interference sources in the environmental information.

6. The method according to claim 5, characterized in that The principal component analysis process is performed on all the intercepted target feature vectors, including: For each set of the target feature vectors, a target scalar is determined in the target feature vectors, Wherein, the target scalar is in the top specified position when all scalars of the target feature vector are arranged from large to small, or the target scalar is greater than or equal to a preset scalar threshold, or the difference between the target scalar and the scalar average value of the target feature vector is greater than a preset scalar difference; Environmental information is screened from the information type corresponding to the target scalar as an interference source, and other environmental information other than the interference source is determined as a non-interference source.

7. The method according to claim 5, characterized in that After the first eigenvalue sequence and the first eigenvector set are determined and the second eigenvalue sequence and the second eigenvector set are determined, the method further includes: The first feature vector set and the second feature vector set are normalized.

8. A data processing device for eliminating interference factors for pipeline thermal displacement, characterized in that: include: A thermal displacement distance acquisition unit is used to acquire the thermal displacement distance of a target pipeline in a thermal power plant; an information acquisition unit, configured to acquire the position information and environmental information of the target pipeline at a plurality of data acquisition moments in response to the acquisition of the thermal displacement distance, and to form a sample information set with the data acquisition moments, the position information and the environmental information; A matrix construction unit, configured to construct a covariance matrix and a correlation matrix based on the sample information set, wherein the covariance matrix is ​​used to reflect the overlapping influence of each information in the sample information set on the thermal displacement distance, and the correlation matrix is ​​used to reflect the correlation between each information in the sample information set; an eigenvalue and vector calculation unit, configured to determine a first eigenvalue sequence and a first eigenvector set based on the covariance matrix, and to determine a second eigenvalue sequence and a second eigenvector set based on the correlation matrix; An interference judgment unit is used to determine interference sources and non-interference sources in the environmental information based on the first eigenvalue sequence and the first eigenvector set, and the second eigenvalue sequence and the second eigenvector set.

9. A computer device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are configured to enable the processor to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are configured to execute the method according to any one of claims 1 to 7.

Images