CN-122023748-A - Submarine pipeline multi-parameter monitoring data fusion visualization method and system based on Internet of things

CN122023748ACN 122023748 ACN122023748 ACN 122023748ACN-122023748-A

Abstract

The invention discloses a submarine pipeline multi-parameter monitoring data fusion visualization method and a submarine pipeline multi-parameter monitoring data fusion visualization system based on the Internet of things, and relates to the technical field of submarine pipeline monitoring data processing and visualization, wherein the method comprises the following steps of S1, generating a reference deviation graph, a sensing response uniformity correction graph, a first monitoring parameter channel gain and a second monitoring parameter channel gain based on a reference zero value graph and a standard calibration graph; S2, acquiring four original monitoring data graphs under the conditions of a first monitoring dimension and a second monitoring dimension respectively at a first Internet of things acquisition node and a second Internet of things acquisition node, and correcting the four original monitoring data graphs. The invention establishes a monitoring calibration base line through a reference deviation graph and a sensing response uniformity correction graph.

Inventors

ZHANG CHAO
ZHANG BOWEN
DONG YANNAN
XING RONGRONG
LIU JIMIN
LI XUESHEN
LI RUIFENG
ZHANG CHONG
DOU HAIPENG
XUE YANG

Assignees

天津大学
秦皇岛华勘地质工程有限公司

Dates

Publication Date: 20260512
Application Date: 20260319

Claims (10)

1. The submarine pipeline multi-parameter monitoring data fusion visualization method based on the Internet of things is characterized by comprising the following steps of: s1, generating a reference deviation graph, a sensing response uniformity correction graph, a first monitoring parameter channel gain and a second monitoring parameter channel gain based on a reference zero value graph and a standard calibration graph; s2, acquiring four original monitoring data graphs under the conditions of a first monitoring dimension and a second monitoring dimension respectively at a first Internet of things acquisition node and a second Internet of things acquisition node, and correcting the four original monitoring data graphs; s3, carrying out uniform processing on the corrected four original monitoring data graphs to obtain four uniform monitoring graphs, and calculating a common mode item according to the pixel intensities of the four uniform monitoring graphs; S4, calculating a difference term according to pixel intensities of a first monitoring dimension and a second monitoring dimension of the four unified monitoring graphs, and carrying out normalization processing on the difference term based on a common mode term to obtain a multi-node multi-dimensional monitoring difference index graph; s5, generating a saturated data mask based on the four unified monitoring graphs, and performing confidence calculation and robust smoothing on the multi-node multi-dimensional monitoring differential index graph based on the saturated data mask to obtain a confidence graph and a robust multi-node multi-dimensional monitoring differential index graph; S6, carrying out threshold screening and morphological purification treatment on the confidence map to obtain an effective data mask, and carrying out statistical calculation on the robust multi-node multi-dimensional monitoring differential index map based on the effective data mask to obtain a statistic set; And S7, packaging the robust multi-node multi-dimensional monitoring differential index graph, the confidence graph, the effective data mask and the statistic set to obtain a monitoring sample data packet, and completing fusion visual presentation of multi-parameter monitoring data of the submarine pipeline based on the monitoring sample data packet.
2. The method for visualizing multi-parameter monitoring data fusion of a subsea pipeline based on the internet of things according to claim 1, wherein generating a reference deviation map, a sensing response uniformity correction map, a first monitoring parameter channel gain and a second monitoring parameter channel gain based on a reference zero value map and a standard calibration map, comprises: carrying out multi-frame average noise reduction on the reference zero value graph to obtain a reference deviation graph; subtracting a reference deviation graph from the standard calibration graph, calculating the average value of the pixel intensity of the subtracted standard calibration graph in the standard calibration effective area, and carrying out normalization processing to obtain a sensing response uniformity correction graph; Respectively carrying out reference deviation deduction and sensing response uniformity correction on the standard calibration graph of the first monitoring dimension and the standard calibration graph of the second monitoring dimension under the first Internet of things acquisition node to obtain a corrected standard calibration graph; And averaging the corrected standard calibration graph in a standard calibration effective area to obtain a first monitoring parameter channel gain and a second monitoring parameter channel gain.
3. The method for fusing and visualizing the multi-parameter monitoring data of the subsea pipeline based on the internet of things according to claim 1, wherein the four original monitoring data graphs are obtained under the conditions of the first monitoring dimension and the second monitoring dimension respectively at the first internet of things acquisition node and the second internet of things acquisition node, and the four original monitoring data graphs are corrected, and the method comprises the following steps: performing parameter curing on the combination of the first monitoring dimension, the second monitoring dimension, the first Internet of things acquisition node and the second Internet of things acquisition node, and recording the acquisition time and the signal gain of the monitoring dimension to obtain a metadata group containing the monitoring dimension, the acquisition node, the acquisition time and the signal gain; Under the condition of triggering the monitoring gesture of the same pipeline, four original monitoring data graphs corresponding to a first monitoring dimension and a first Internet of things acquisition node, a first monitoring dimension and a second Internet of things acquisition node, a second monitoring dimension and the first Internet of things acquisition node and a second monitoring dimension and the second Internet of things acquisition node are obtained based on the metadata set; And respectively carrying out reference deviation deduction and sensing response uniformity correction on the four original monitoring data graphs, and carrying out channel gain consistency by adopting a first monitoring parameter channel gain and a second monitoring parameter channel gain to obtain a corrected four-channel monitoring data stack.
4. The method for fusing and visualizing the multi-parameter monitoring data of the submarine pipeline based on the internet of things according to claim 1, wherein the method for fusing and visualizing the corrected four original monitoring data patterns to obtain four unified monitoring patterns and calculating the common mode item according to the pixel intensities of the four unified monitoring patterns comprises the following steps: Dividing the corrected four-channel monitoring data stack by the acquisition time and the signal gain respectively to obtain four unified monitoring graphs, and adding the pixel intensities of the same pixel position of the four unified monitoring graphs and multiplying the pixel intensities by one half to obtain a common mode term.
5. The method for fusing and visualizing the multi-parameter monitoring data of the subsea pipeline based on the internet of things according to claim 1, wherein the method for computing the differential term according to the pixel intensities of the first monitoring dimension and the second monitoring dimension of the four unified monitoring graphs and normalizing the differential term based on the common mode term to obtain the multi-node multi-dimensional monitoring differential index graph comprises the following steps: carrying out pixel intensity subtraction on the first monitoring dimension unification monitoring graph and the second monitoring dimension unification monitoring graph of the first Internet of things acquisition node to obtain a first acquisition node multidimensional difference item; Carrying out pixel intensity subtraction on the first monitoring dimension unification monitoring graph and the second monitoring dimension unification monitoring graph of the second networking acquisition node to obtain a second acquisition node multidimensional difference term; Subtracting the multi-dimensional difference term of the second acquisition node from the multi-dimensional difference term of the first acquisition node to obtain a difference term, and dividing the difference term by the sum of the common mode term and the tiny positive number to obtain a multi-node multi-dimensional monitoring difference index diagram.
6. The method for visualizing the multi-parameter monitoring data fusion of the submarine pipeline based on the internet of things according to claim 1, wherein generating a saturated data mask based on the four unified monitoring graphs, and performing confidence calculation and robust smoothing on the multi-node multi-dimensional monitoring differential index graph based on the saturated data mask to obtain a confidence graph and a robust multi-node multi-dimensional monitoring differential index graph, comprises: Comparing the pixel intensities of the same pixel position of the four unified monitoring graphs, comparing the maximum value of the pixel intensities with a saturation threshold, marking the pixel position as a saturation data point if the maximum value is larger than or equal to the saturation threshold, otherwise marking the pixel position as an unsaturated data point to generate a saturation data mask; Calculating the median absolute deviation of the multi-node multi-dimensional monitoring differential index map in the neighborhood of the preset size of the unsaturated data point, and carrying out coefficient conversion to obtain local noise estimation; Dividing the absolute value of the difference term by the sum of the local noise estimation and the tiny positive number to obtain a confidence map; And carrying out median filtering treatment on the multi-node multi-dimensional monitoring differential index map under the constraint of the saturated data mask to obtain the robust multi-node multi-dimensional monitoring differential index map.
7. The method for visualizing multi-parameter monitoring data fusion of a subsea pipeline based on the internet of things according to claim 1, wherein the performing the threshold screening and morphological purification processing on the confidence map to obtain an effective data mask, and performing the statistical calculation on the robust multi-node multi-dimensional monitoring differential index map based on the effective data mask to obtain a statistic set comprises: And respectively carrying out mean value calculation, standard deviation calculation and quantile calculation of preset percentiles on the robust multi-node multi-dimensional monitoring differential index map in a pixel set of the effective data mask, and forming a statistic set by the obtained mean value, standard deviation and the quantiles of each preset percentile.
8. The method for fusing and visualizing the multi-parameter monitoring data of the submarine pipeline based on the internet of things according to claim 1, wherein the method for fusing and visualizing the multi-parameter monitoring data of the submarine pipeline based on the monitoring sample data packet is completed, and comprises the following steps: performing layer fusion on the robust multi-node multi-dimensional monitoring differential index graph, the confidence graph and the effective data mask in the monitoring sample data packet to generate a multi-dimensional fusion monitoring base graph; visual labeling is carried out on numerical indexes in the statistic set, and superposition is carried out on the numerical indexes and the multi-dimensional fusion monitoring base map; Registering the superimposed fusion monitoring graph with the spatial position of the submarine pipeline based on geographic information data of the submarine pipeline of the Internet of things to generate a three-dimensional/two-dimensional submarine pipeline multi-parameter monitoring data visualization map; And carrying out dynamic updating and interactive design on the visual map, and supporting multi-view viewing of monitoring data, highlighting of abnormal data and backtracking comparison of historical data.
9. The submarine pipeline multi-parameter monitoring data fusion visualization system based on the Internet of things is characterized by comprising a baseline calibration module, a baseline calibration module and a baseline calibration module, wherein the baseline calibration module is used for generating a baseline deviation graph, a sensing response uniformity correction graph, a first monitoring parameter channel gain and a second monitoring parameter channel gain based on a baseline zero value graph and a standard calibration graph; The node acquisition and correction module is used for acquiring four original monitoring data graphs under the conditions of a first monitoring dimension and a second monitoring dimension respectively at a first Internet of things acquisition node and a second Internet of things acquisition node, and correcting the four original monitoring data graphs; The unification module is used for performing unification processing on the corrected four original monitoring data graphs to obtain four unification monitoring graphs, and calculating a common mode item according to the pixel intensities of the four unification monitoring graphs; The differential normalization module is used for calculating differential terms according to pixel intensities of a first monitoring dimension and a second monitoring dimension of the four unified monitoring graphs, and performing normalization processing on the differential terms based on common mode terms to obtain a multi-node multi-dimensional monitoring differential index graph; The confidence robustness module is used for generating a saturated data mask based on the four consistent monitoring graphs, and carrying out confidence calculation and robust smoothing on the multi-node multi-dimensional monitoring differential index graph based on the saturated data mask to obtain a confidence graph and a robust multi-node multi-dimensional monitoring differential index graph; The effective domain statistics module is used for carrying out threshold screening and morphological purification treatment on the confidence map to obtain an effective data mask, and carrying out statistics calculation on the robust multi-node multi-dimensional monitoring differential index map based on the effective data mask to obtain a statistic set; The data packaging module is used for packaging the robust multi-node multi-dimensional monitoring differential index graph, the confidence graph, the effective data mask and the statistic set to obtain a monitoring sample data packet; and the fusion visualization module is used for completing fusion visualization presentation of the multi-parameter monitoring data of the submarine pipeline based on the monitoring sample data packet.
10. The internet of things-based subsea pipeline multi-parameter monitoring data fusion visualization system of claim 9, wherein the fusion visualization module comprises: The system comprises a layer fusion unit, an index labeling unit, a multi-dimensional fusion monitoring base graph and a multi-dimensional fusion monitoring base graph, wherein the layer fusion unit is used for carrying out layer fusion on a robust multi-node multi-dimensional monitoring differential index graph, a confidence graph and an effective data mask in a monitoring sample data packet to generate the multi-dimensional fusion monitoring base graph; The spatial registration unit is used for registering the superimposed fusion monitoring graph and the spatial position of the submarine pipeline based on the geographic information data of the submarine pipeline of the Internet of things to generate a three-dimensional/two-dimensional submarine pipeline multi-parameter monitoring data visualization map; and the interaction updating unit is used for dynamically updating and interactively designing the visual map and supporting multi-view viewing of the monitoring data, highlighting of the abnormal data and backtracking comparison of the historical data.

Description

Submarine pipeline multi-parameter monitoring data fusion visualization method and system based on Internet of things Technical Field The invention relates to the technical field of submarine pipeline monitoring data processing and visualization, in particular to a submarine pipeline multi-parameter monitoring data fusion visualization method based on the Internet of things. Background In the multi-parameter on-line monitoring and data processing of the submarine pipeline under the architecture of the Internet of things, the submarine pipeline is in a complex marine environment, various interference factors such as sea water flow speed change, temperature gradient, salinity fluctuation, submarine topography disturbance and the like exist, the acquisition nodes of the Internet of things are distributed in different sections of the pipeline, the problems of installation attitude deviation, signal transmission delay, aging of a sensing unit and the like exist, and the monitored multidimensional parameters such as pressure, temperature, strain, corrosion and the like have the characteristics of dimensional difference and different data fluctuation characteristics. The monitoring system mainly adopts multi-node Internet of things to collect and multi-dimensional parameter monitoring configuration so as to acquire multi-source monitoring data sensitive to the running state of a submarine pipeline, however, the factors such as sensor unit reference drift, uneven response among nodes, signal transmission noise, random interference of marine environment, scale mismatch of different monitoring dimension data and the like exist at the same time on the ocean scene, and the factors act together on a plurality of collecting nodes and various monitoring dimensions, so that four paths of monitoring data of the same monitoring position show similar integral fluctuation with the marine environment along with time, and challenges are brought to stable extraction of effective data related to the running state of the pipeline and comparability of cross-node and cross-batch monitoring data. In the prior art, single-node single-dimensional data calibration or simple multi-data average value fusion is adopted, or data normalization processing is carried out only in a single monitoring dimension, and a scheme for reducing environmental interference through global numerical scaling is also adopted. The method is effective in compensating the reference drift of a single sensing unit, but when the signal additional interference caused by marine environment, the integral gain drift of the sensing unit and the monitoring data fluctuation caused by the attitude change of the acquisition node are faced, the pipeline running state change and the environment and equipment change are difficult to distinguish, the incomparable monitoring data batch and the abnormal judgment threshold value are easy to be unstable, the processing chain for unifying the complementary information of a plurality of acquisition nodes and various monitoring dimensions to the same monitoring position is lacking, the saturated data elimination and the local noise evaluation are lacking, the data-level confidence and the sample-level statistics are not output generally, the monitoring result is sensitive to noise and saturated data points, the dependence on the set parameters is strong, the traceability is insufficient, and the requirements of the submarine pipeline safety monitoring on the data stability, the consistency and the visual intuitiveness are difficult to be met. Disclosure of Invention The invention aims to solve the defects that in the prior art, under the factors of marine environment interference, change of the attitude of a collection node, drift of the gain of a sensing unit and the like, comparable monitoring data level indexes are difficult to obtain stably and high-efficiency fusion visualization cannot be realized. In order to solve the problems existing in the prior art, the invention adopts the following technical scheme: the submarine pipeline multi-parameter monitoring data fusion visualization method based on the Internet of things comprises the following steps: s1, generating a reference deviation graph, a sensing response uniformity correction graph, a first monitoring parameter channel gain and a second monitoring parameter channel gain based on a reference zero value graph and a standard calibration graph; s2, acquiring four original monitoring data graphs under the conditions of a first monitoring dimension and a second monitoring dimension respectively at a first Internet of things acquisition node and a second Internet of things acquisition node, and correcting the four original monitoring data graphs; s3, carrying out uniform processing on the corrected four original monitoring data graphs to obtain four uniform monitoring graphs, and calculating a common mode item according to the pixel intensities of the four uniform monitoring gra