Method for establishing digital twin system for full life cycle tracking of buried pipelines based on RFID

Abstract

The present invention discloses a method for establishing a digital twin system for tracking the entire life cycle of a buried pipeline based on RFID, comprising the following steps: S1, preparing RFID tags and a reader / writer; S2, installing RFID tags at equal intervals on the buried pipeline, and periodically using the reader / writer to perform reading operations to obtain RFID tag information; S3, establishing a digital twin model of the buried pipeline according to the RFID tag information obtained in step S2; S4, monitoring and simulating the health status and geographical location of the buried pipeline through the digital twin model of the buried pipeline, generating a one-to-one corresponding digital twin model of the buried pipeline using the initial pipeline information and the special RFID tag, using the reader / writer module to transfer the special RFID tag monitoring information to the digital twin model to update the digital twin model of the buried pipeline, and monitoring and simulating the health status and geographical location of the buried pipeline in real time through the digital twin model, thereby realizing the information management of the entire life cycle of the buried pipeline.

Description

Technical Field

[0001] The present invention relates to the technical field of civil engineering intelligent management applications, and in particular to a method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID. Background Art

[0002] With the rapid development of the world economy, infrastructure around the world is developing rapidly, and the number of buried pipelines is inevitably increasing year by year, thus forming a complex and huge underground pipeline network map. However, the informationization of key data such as the buried depth, purpose, laying date, inspection and maintenance records of key positions of buried pipes is relatively low, and the existing data cannot be associated with the actual object in the "Internet of Things". At the same time, due to construction errors, soil layer movement and other reasons, the position information of key parts such as welds and pipe angles of the pipeline itself does not match the actual position, which makes it difficult to accurately locate during construction, causing great trouble for pipeline inspection and excavation operations. Buried pipelines will be eroded, corroded, high temperature, and damaged by non-natural factors under long-term service. Therefore, the construction of an RFID buried pipeline full life cycle tracking digital twin system can realize the information management of the entire life cycle of buried pipelines, which is an important technical guarantee for monitoring and managing the health status of buried pipelines. Summary of the invention

[0003] In response to the above problems, the present invention provides an RFID-based digital twin system for tracking the entire life cycle of buried pipelines. By combining RFID with digital twins, the information management of the entire life cycle of buried pipelines can be realized, which facilitates the operation and maintenance of buried pipelines.

[0004] The technical solution of the present invention is:

[0005] The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID includes the following steps:

[0006] S1. Prepare RFID tags and readers;

[0007] S2, installing RFID tags on the buried pipeline at equal intervals, and periodically using a reader to read and obtain RFID tag information;

[0008] S3. Establishing a digital twin model of the buried pipeline according to the RFID tag information obtained in step S2;

[0009] S4. Monitor and simulate the health status and geographical location of buried pipelines through the digital twin model of buried pipelines.

[0010] Preferably, in step S1, the RFID tag has a built-in temperature sensor, an acoustic wave sensor, a flow sensor, a pressure sensor, and a positioning sensor.

[0011] Preferably, in step S3, the method for establishing the buried pipeline twin model is as follows:

[0012] 1) Map the RFID tag information in the 3D modeling space to generate identity information feature points that carry the identity information of the buried pipeline and the installation sequence of the pipeline tags, and record the corresponding size and specification feature information of each buried pipeline;

[0013] 2) constructing a 3D model of each pipeline size based on the size specification feature information of each underground pipeline obtained in step 1);

[0014] 3) Classifying the identity information feature points obtained in step 1) according to different branches of the buried pipeline, connecting the identity information feature points of the buried pipelines in the same branch in sequence, and establishing a three-dimensional linear network of the buried pipeline;

[0015] 4) Correcting the three-dimensional line network of buried pipelines established in step 3);

[0016] 5) Determine the positioning points and positioning data of each line in the three-dimensional linear network of the buried pipeline corrected in step 4) through feature extraction algorithm recognition and Hough detection;

[0017] 6) Fitting the 3D model of each pipeline size obtained in step 2) with the positioning data obtained in step 5) to obtain a theoretical buried pipeline 3D model;

[0018] 7) Obtain the actual 3D model and BIM model through the theoretical buried pipeline 3D model obtained in step 6);

[0019] 8) Combine the 3D model with the BIM model data to obtain a neural network physical simulation model.

[0020] Preferably, the feature extraction algorithm in step 5) is used to quickly create feature vectors for key points in the image, and these feature vectors are used to identify objects in the three-dimensional linear network of buried pipelines.

[0021] The Hough detection in step 5) utilizes the Hough transformation to apply the transformation between two coordinate spaces, and maps a curve or straight line in one space to a point in another coordinate space to form a peak, thereby converting the problem of detecting arbitrary shapes into a statistical peak problem.

[0022] Preferably, the recognition result in step 5) is saved in a corresponding file, and each file saves specific identity feature information of different positioning points and positioning point coordinate information, thereby constituting positioning data of the positioning points.

[0023] Preferably, in step S4, the method for using the buried pipeline twin model is as follows:

[0024] a) Establish RFID tag monitoring database, neural network physical simulation database, RFID tag monitoring sound wave database, pipeline failure cause and damage location database in the neural network physical simulation model;

[0025] b) Determine pipeline vibration type, predict pipeline erosion speed and location, and predict stress damage location based on the collected tag data;

[0026] c) Predict the remaining life of the pipeline based on the pipeline vibration type, pipeline erosion speed and location, and stress damage location obtained in step b).

[0027] Preferably, in step b), the data of determining pipeline vibration type, predicting pipeline erosion speed and location, and predicting stress damage location are fed back to the neural network physical simulation model for enhanced training.

[0028] Preferably, the reader / writer is a mobile reader / writer or a fixed reader / writer.

[0029] Preferably, the RFID-based buried pipeline full life cycle tracking digital twin system also includes an information integration visualization platform, which is connected to the reader / writer.

[0030] Preferably, the RFID-based buried pipeline full life cycle tracking digital twin system also includes an early warning module, which is used to alarm when an abnormality occurs in the buried pipeline.

[0031] The early warning module will retrieve the digital twin prediction data and the special RFID tag measured data at the threshold S set at the initial risk level. max , Y max Make comparisons, determine the risk level and take subsequent actions.

[0032] The beneficial effects of the present invention are:

[0033] Special RFID tags are pre-buried or installed in the corresponding positions of the buried pipelines to be tested. Special RFID electronic tags are used to "identify" the buried pipelines. By detecting the special RFID tag signals through mobile and fixed readers and writers, the objects being searched can be efficiently and accurately located without excavation. The buried depth, GPS coordinates, purpose, laying date, inspection dynamics, inspection records, maintenance records, etc. of the identified objects can be integrated, standardized, intelligent, and information-based. A one-to-one digital twin model of the buried pipeline is generated using the initial pipeline information and special RFID tags. The reader-writer module is used to pass the special RFID tag monitoring information to the digital twin model to update the digital twin model of the buried pipeline. The digital twin model is used to monitor and simulate the health status and geographical location of the buried pipeline in real time, thereby realizing the information management of the entire life cycle of the buried pipeline. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flow chart of a method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to an embodiment of the present invention;

[0035] Figure 2 It is a structural block diagram of the buried pipeline digital twin model system according to an embodiment of the present invention;

[0036] Figure 3 The buried pipeline digital twin module data processing method described in the embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram of the installation position of the special RFID tag for buried pipelines according to an embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of a buried pipeline real-time transmission monitoring buried pipeline according to an embodiment of the present invention;

[0039] Figure 6 This is a flow chart of the early warning module of the buried pipeline digital twin module described in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1-Figure 6 The present invention provides a technical solution: a method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID, comprising the following steps:

[0042] S1. Prepare RFID tags and readers;

[0043] This RFID tag is a special tag, which is integrated with multiple sensors such as temperature sensor, acoustic wave sensor, flow sensor, pressure sensor, positioning sensor, etc. according to demand. It has the characteristics of strong metal resistance and corrosion resistance, signal penetration of soil layer, compact size, and a unique identity number that can be recognized by the reader. At the same time, the information stored and collected by the sensor can be transmitted to the reader module. The reader includes different types of readers, such as mobile readers and fixed readers. The fixed reader is installed within the readable and writable information range of the RFID tag, and relies on the reader to carry its own power supply or connect to the surrounding environment to connect to the power supply for periodic operation.

[0044] S2. Install RFID tags on the buried pipeline at equal distances. Key locations can also be installed independently. Periodically use a reader to read and obtain RFID tag information.

[0045] RFID tags are installed at equal intervals on buried pipelines and are also installed in key locations of buried pipelines, such as welds, pipe corners, locations with harsh working environments, where multiple layers of pipelines cross and overlap, and locations where ground operations are frequent.

[0046] S3. Establish a digital twin model of the buried pipeline based on the RFID tag information obtained in step S2, as follows;

[0047] 1) Map the RFID tag information in the 3D modeling space to generate identity information feature points that carry the identity information of the buried pipeline and the installation sequence of the pipeline tags, and record the corresponding size and specification feature information of each buried pipeline;

[0048] 2) constructing a 3D model of each pipeline size based on the size specification feature information of each underground pipeline obtained in step 1);

[0049] 3) Classifying the identity information feature points obtained in step 1) according to different branches of the buried pipeline, connecting the identity information feature points of the buried pipelines in the same branch in sequence, and establishing a three-dimensional linear network of the buried pipeline;

[0050] 4) Correcting the three-dimensional network of buried pipelines established in step 3);

[0051] 5) Determine the positioning points and positioning data of each line in the three-dimensional linear network of the buried pipeline corrected in step 4) through feature extraction algorithm recognition and Hough detection;

[0052] The feature extraction algorithm is used to quickly create feature vectors for key points in the image. These feature vectors are used to identify objects in the three-dimensional linear network of buried pipelines. Hough detection uses the Hough change to apply the change between two coordinate spaces to map a curve or straight line in one space to a point in another coordinate space to form a peak, thereby transforming the problem of detecting arbitrary shapes into a statistical peak problem. 5) The recognition results are saved in the corresponding files, and each file saves the specific identity feature information of different positioning points and the coordinate information of the positioning points, thereby forming the positioning data of the positioning points;

[0053] 6) Fitting the 3D model of each pipeline size obtained in step 2) with the positioning data obtained in step 5) to obtain a theoretical buried pipeline 3D model;

[0054] 7) Obtain the actual 3D model and BIM model through the theoretical buried pipeline 3D model obtained in step 6);

[0055] Manual optimization and adjustment before generating 3D models and BIM models: The theoretical buried pipeline 3D model initially generated by manual optimization and adjustment can prevent errors in the subsequent neural network physical simulation model;

[0056] 8) Combine the 3D model with the BIM model data to obtain a neural network physical simulation model.

[0057] The actual data stored in the RFID tag carries the corresponding generation timestamp and sensor identifier. Here, the monitoring data corresponding to the acquired RFID tag is obtained with the timestamp as the vertical column value and the monitoring data as the horizontal column value to obtain the monitoring record corresponding to the storage time, and judge whether the classified RFID tag monitoring data exceeds the bearing range of the buried pipeline, such as whether it exceeds the maximum allowable stress, maximum flow, maximum temperature, etc. of the pipeline. The monitoring data that does not exceed the bearing range of the buried pipeline is sent to the neural network physical simulation model for simulation.

[0058] S4. Monitor and simulate the health status and geographical location of the buried pipeline through the buried pipeline digital twin model, as follows;

[0059] a) Establish RFID tag monitoring database, neural network physical simulation database, RFID tag monitoring sound wave database, pipeline failure cause and damage location database in the neural network physical simulation model;

[0060] b) Determine pipeline vibration type, predict pipeline erosion speed and location, and predict stress damage location based on the collected tag data;

[0061] Here, the pipeline vibration type is determined, the pipeline erosion speed and location are predicted, and the data on the stress damage location are predicted, which can be fed back to the neural network physical simulation model for enhanced training;

[0062] The data monitored by special RFID tags in multiple databases and the simulation data obtained by physical simulation of neural networks are trained by Gaussian process regression to build a model of buried pipeline erosion location and erosion rate to predict the erosion rate and erosion location. At the same time, the maximum corrosion depth of buried pipelines is predicted by combining the GEV distribution function with the simulation model, where:

[0063] In the neural network physical simulation model, if the buried pipeline with a length of Y is extracted into y segments, each with a length of 1, then y corrosion depths x can be obtained. i , taking the logarithm of the GEV distribution function, we get:

[0064]

[0065] Will With x iThe fitting is a negative linear relationship, through the regression period E （A） To predict the maximum corrosion depth of buried pipelines:

[0066]

[0067]

[0068]

[0069]

[0070] Get the maximum corrosion depth . G(x i ) is the maximum corrosion depth not exceeding x i The probability of is a positional parameter, is the first shape parameter, is the scale parameter, x i is the corrosion depth, is the second shape parameter.

[0071] c) Predict the remaining life of the pipeline based on the pipeline vibration type, pipeline erosion speed and location, and stress damage location obtained in step b).

[0072] The remaining service life of buried pipelines is calculated by using the Paris formula and the corrosion margin prediction method based on the reliability model. The genetic algorithm is used to optimize the extreme learning machine method to train the buried pipeline erosion rate prediction model and multiple groups of data in the database, and the buried pipeline erosion and maximum corrosion depth life prediction model is obtained to predict the remaining service life of the pipeline.

[0073] The system also includes an information comprehensive visualization platform, which is connected to the reader / writer through 5G, WiFi, Bluetooth and other communication technologies.

[0074] like Figure 6 As shown in the figure, the system also includes an early warning module. The sound wave signal detected by the RFID tag is analyzed, and the control rules described by fuzzy mathematical language are used to manipulate the control mode of the identification system to determine whether the buried pipeline is in an abnormal state (such as oil theft, impact, position change, etc.), and send a signal to the early warning module in an abnormal state. After receiving the signal from the early warning module, the maintenance staff arrives at the site to inspect the pipeline. After the inspection, the inspection content and inspection location information are modified and supplemented through the handheld terminal reader or information comprehensive visualization platform.

[0075] The early warning module will retrieve the digital twin prediction data and the special RFID tag measured data at the threshold S set at the initial risk level. max , Y maxCompare, determine the risk level and carry out subsequent processing. The actual detection value S of a certain type of sensor i <S max , the early warning module determines that the pipeline is safe at this time and no early warning is required. Otherwise, S i ≥S max The early warning module sends out an audible and visual warning, and the management personnel determine and assign relevant maintenance personnel to rush to the site for manual maintenance. After arriving at the site, the personnel will determine whether they can handle the risk on their own. If not, they will feedback to the management personnel to send additional maintenance personnel. Otherwise, after successful handling, the risk warning will be lifted and the maintenance information will be uploaded and updated. The initial risk level threshold of the digital twin prediction data is divided into Y max1 <Y max2 <Y max3 Three levels, Y i <Y max1 When the pipeline is judged to be safe, no warning is required. max1 <Y i <Y max2 When the warning module issues a first-level warning, Y max2 <Y i <Y max3 When the warning module issues a second-level warning, Y i ≥Y max3 When the warning module issues a third-level warning, the buried pipeline digital twin system uses sound waves to determine the pipeline vibration type. If there is a safety risk, a third-level warning will be issued. If there is no safety risk, no warning will be issued.

[0076] The first-level warning reminds the managers of buried pipelines that there are certain risks and hidden dangers in the pipeline-related locations and they need to pay more attention to observation. The second-level warning reminds the managers that the safety hazards in the pipeline-related locations are continuously escalating and they need to be prepared for emergencies at all times. The third-level warning warns the managers that the pipeline-related locations are about to or have already had risks and hidden dangers and they need to immediately arrange maintenance staff to conduct inspections. After the first, second, and third-level warnings are issued, the buried pipeline digital twin system locates through the three-dimensional coordinates of the simulation model and makes corresponding marks on the model for management. At the same time, the three-dimensional coordinates of the digital twin system simulation model are compared with the pipeline coordinates preset when designing and installing the buried pipeline to determine whether the geographical location of the buried pipeline is offset. Through the 3D and BIM models of the buried pipelines in the digital twin system, artificial intelligence or big data analysis technology is used to intelligently plan and analyze the future layout of buried pipelines.

[0077] The basic parameters of the neural network physical simulation model in the digital twin are updated in real time as the RFID tag monitoring data changes.

[0078] The above is only a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art shall not deviate from the spirit and scope of the present invention, and shall be within the scope of protection of the claims attached to the present invention.

Claims

1. A method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID, characterized in that: The steps include: S1. Prepare RFID tags and readers; S2, installing RFID tags at equal intervals on the buried pipeline and also at key locations of the buried pipeline, and periodically using a reader to perform reading operations to obtain RFID tag information; S3. Establishing a digital twin model of the buried pipeline according to the RFID tag information obtained in step S2; S4. Monitor and simulate the health status and geographical location of buried pipelines through the digital twin model of buried pipelines; In step S3, the method for establishing the buried pipeline twin model is as follows: 1) Map the RFID tag information in the 3D modeling space to generate identity information feature points that carry the identity information of the buried pipeline and the installation sequence of the pipeline tags, and record the corresponding size and specification feature information of each buried pipeline; 2) constructing a 3D model of each pipeline size based on the size specification feature information of each underground pipeline obtained in step 1); 3) Classifying the identity information feature points obtained in step 1) according to different branches of the buried pipeline, connecting the identity information feature points of the buried pipelines in the same branch in sequence, and establishing a three-dimensional linear network of the buried pipeline; 4) Correcting the three-dimensional network of buried pipelines established in step 3); 5) Determine the positioning points and positioning data of each line in the three-dimensional linear network of the buried pipeline corrected in step 4) through feature extraction algorithm recognition and Hough detection; 6) Fitting the 3D model of each pipeline size obtained in step 2) with the positioning data obtained in step 5) to obtain a theoretical buried pipeline 3D model; 7) Obtain the actual 3D model and BIM model through the theoretical buried pipeline 3D model obtained in step 6); 8) Combine the 3D model with the BIM model data to obtain a neural network physical simulation model; The feature extraction algorithm in step 5) is used to quickly create feature vectors for key points in the image, and these feature vectors are used to identify objects in the three-dimensional linear network of buried pipelines; The Hough detection in step 5) utilizes the Hough transformation to apply the transformation between two coordinate spaces, and maps a curve or straight line in one space to a point in another coordinate space to form a peak value, thereby transforming the problem of detecting arbitrary shapes into a statistical peak problem; In step S4, the method for using the buried pipeline twin model is as follows: a) Establish RFID tag monitoring database, neural network physical simulation database, RFID tag monitoring sound wave database, pipeline failure cause and damage location database in the neural network physical simulation model; b) Determine pipeline vibration type, predict pipeline erosion speed and location, and predict stress damage location based on the collected tag data; c) Predict the remaining life of the pipeline based on the pipeline vibration type, pipeline erosion speed and location, and stress damage location obtained in step b).

2. The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to claim 1 is characterized in that: In the step S1, the RFID tag has a built-in temperature sensor, an acoustic wave sensor, a flow sensor, a pressure sensor, and a positioning sensor.

3. The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to claim 1 is characterized in that: The recognition result in step 5) is saved in a corresponding file, and each file saves the specific identity feature information of different positioning points and the coordinate information of the positioning points, thereby constituting the positioning data of the positioning points.

4. The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to claim 1 is characterized in that: In the step b), the data of determining the pipeline vibration type, predicting the pipeline erosion speed and location, and predicting the stress damage location can be fed back to the neural network physical simulation model for enhanced training.

5. The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to claim 1 is characterized in that: The reader / writer is a mobile reader / writer or a fixed reader / writer.

6. The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to claim 1 is characterized in that: The RFID-based buried pipeline full life cycle tracking digital twin system also includes an information comprehensive visualization platform, which is connected to the reader / writer.

7. The method for establishing a digital twin system for tracking the entire life cycle of buried pipelines based on RFID according to claim 1 is characterized in that: The RFID-based buried pipeline full life cycle tracking digital twin system also includes an early warning module, which is used to alarm when an abnormality occurs in the buried pipeline; The early warning module will retrieve the digital twin prediction data and the special RFID tag measured data at the threshold S set at the initial risk level. max , Y max Make comparisons, determine the risk level and take subsequent actions.

Images