Booster station state early warning research and application method based on data twinning

Abstract

The invention relates to the technical field of booster station equipment, and discloses a booster station state early warning research and application method based on data twinning. S10, acquiring real scene field data of the booster station, and performing real scene data acquisition on the field of the booster station by using professional data acquisition equipment; s20, constructing a three-dimensional model of the booster station, and constructing a digital twinborn model of the booster station after performing automatic splicing and smoothing processing on point cloud data by using professional three-dimensional modeling processing software; and S30, data acquisition: acquiring operation data of the booster station, including equipment part, meter and spectral data. The state management and control capability of booster station equipment is improved, and on the basis of a digital twin technology, interaction, comprehensive evaluation and active early warning of equipment information are realized, so that heavy daily operation and maintenance tasks of maintenance personnel are reduced, and the intelligent and digital operation and maintenance management and control level of the booster station is systematically improved.

Description

Technical Field

[0001] The present invention relates to the technical field of booster station equipment, and specifically to a method for researching and applying status early warning of a booster station based on data twins. Background Art

[0002] In modern power systems, booster stations play a key role as important nodes in power transmission and distribution. However, traditional booster station monitoring methods often face challenges such as insufficient monitoring capabilities, low prediction accuracy, and insufficient real-time identification of potential faults.

[0003] In response to the country's call for "carbon neutrality", the scale of hydropower generation will be further expanded in the future. In the process of ensuring the safe and smooth operation of hydropower generation, the status assessment and fault warning of booster station equipment are crucial. It is an important basis for ensuring its smooth and safe grid connection. However, the existing booster station status monitoring and early warning methods are usually based on traditional physical sensors and manual inspections. These methods are not only inefficient, but also difficult to accurately predict equipment failures and abnormalities.

[0004] Therefore, developing a method for researching and applying status warning of substations based on data twins will help improve the efficiency and accuracy of equipment monitoring and warning. Summary of the invention

[0005] In response to the shortcomings of the prior art, the present invention provides a method for research and application of booster station status early warning based on data twins, which solves the problem that the existing booster station status monitoring and early warning are based on physical sensors and manual inspections, resulting in low efficiency and difficulty in accurately predicting equipment failures and abnormalities.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for research and application of booster station status warning based on data twins, comprising the following steps;

[0007] S10, obtaining the real scene data of the booster station, and using professional data acquisition equipment to collect real scene data of the booster station;

[0008] S20. Build a 3D model of the booster station. Use professional 3D modeling processing software to automatically stitch point cloud data and build a digital twin model of the booster station after smoothing.

[0009] S30, data collection, collecting the operation data of the booster station, including equipment components, meters, and spectrum data;

[0010] S40, data preprocessing, preprocessing the collected data, including cleaning, filtering, and normalizing the collected data to eliminate noise and outliers and improve the accuracy and reliability of the data;

[0011] S50, early warning analysis, in which the digital twin booster station early warning system automatically and intelligently analyzes the real-time collected data, predicts abnormal status and potential failures of the booster station by comparing the data twin model with the actual operation data, and generates early warning signals;

[0012] S60, fault diagnosis: the system diagnoses the fault type and location of the booster station based on early warning analysis and actual operation data, including temperature alarm, personnel alarm, deformation alarm, and spectral data alarm, and generates a fault report;

[0013] S70: Visual presentation: the warning signals and fault reports generated in the digital twin booster station warning system are output in a visual manner.

[0014] Preferably, in S10, laser scanners and camera devices are used to collect real-time data of the booster station. These devices generate a large amount of point cloud data, which reflects the geometric shape and external features of the booster station.

[0015] Preferably, in S20, professional 3D modeling software is used to process the point cloud obtained from real-scene data collection, perform splicing and smoothing, and finally construct a digital twin model.

[0016] Preferably, in S30, data on the operation of the booster station is collected by using sensors and monitoring equipment.

[0017] Preferably, in S40, the collected data is cleaned, filtered, and normalized to remove outliers and noise.

[0018] Preferably, in S50, a machine learning or deep learning algorithm is used to compare the real-time collected data with the digital twin model to predict potential abnormal conditions and faults.

[0019] Preferably, in S60, the warning analysis and actual operation data are combined and a professional diagnosis algorithm is used to determine the type and location of the fault.

[0020] Preferably, in S70, a chart or a graphical interface visualization tool is used to present the generated warning signal and fault report.

[0021] The present invention provides a method for research and application of booster station status warning based on data twins. It has the following beneficial effects:

[0022] 1. The present invention improves the status control capability of the substation equipment and realizes the interaction, comprehensive evaluation and active early warning of equipment information based on digital twin technology, thereby reducing the heavy daily operation and inspection tasks of maintenance personnel and systematically improving the intelligent and digital operation and maintenance control level of the substation.

[0023] 2. The present invention aims to realize the intelligent operation and maintenance of booster station equipment based on digital twins, improve the state control capability of booster station equipment, and realize information interaction, comprehensive evaluation and active early warning of booster station equipment through digital twin technology, thereby improving the operation and maintenance control level of booster stations. At the same time, with the openness and scalability of the digital twin platform, cables, overhead lines and other equipment can be included in it in the future, and a digital power grid can be built together with the booster station to realize the digital twin of the entire power grid and provide a demonstration sample for the construction of digital twin cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only 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.

[0026] Example:

[0027] Please see attached Figure 1 , an embodiment of the present invention provides a method for research and application of booster station status warning based on data twin, comprising the following steps;

[0028] S10, obtaining the real scene data of the booster station, and using professional data acquisition equipment to collect real scene data of the booster station;

[0029] S20. Build a 3D model of the booster station. Use professional 3D modeling processing software to automatically stitch point cloud data and build a digital twin model of the booster station after smoothing.

[0030] S30, data collection, collecting the operation data of the booster station, including equipment components, meters, and spectrum data;

[0031] S40, data preprocessing, preprocessing the collected data, including cleaning, filtering, and normalizing the collected data to eliminate noise and outliers and improve the accuracy and reliability of the data;

[0032] S50, early warning analysis, in which the digital twin booster station early warning system automatically and intelligently analyzes the real-time collected data, predicts abnormal status and potential failures of the booster station by comparing the data twin model with the actual operation data, and generates early warning signals;

[0033] S60, fault diagnosis: the system diagnoses the fault type and location of the booster station based on early warning analysis and actual operation data, including temperature alarm, personnel alarm, deformation alarm, and spectral data alarm, and generates a fault report;

[0034] S70: Visual presentation: the warning signals and fault reports generated in the digital twin booster station warning system are output in a visual manner.

[0035] Starting from real-life data collection and 3D model construction, to the collection and preprocessing of operating data, to early warning analysis and fault diagnosis, and finally presenting the results to users through a visual interface, this workflow can monitor the operating status of the substation in real time, quickly discover abnormal conditions and potential faults, and provide accurate fault diagnosis reports to help users take timely measures to ensure the safe operation of the substation.

[0036] S10 uses laser scanners and camera equipment to collect real-time data of the booster station. These devices generate a large amount of point cloud data that reflects the geometric shape and external features of the booster station.

[0037] The laser scanner creates a point cloud by emitting a laser beam and measuring the time it takes for the laser to return to calculate the distance to the surface of the object, while the camera captures the appearance of the object. This data is used to build a digital twin model of the booster station, generating a high-precision, high-resolution digital twin model of the real-world booster station that reflects its geometry and external features.

[0038] S20 uses professional 3D modeling software to process the point cloud obtained from real-life data collection, perform splicing and smoothing, and finally build a digital twin model.

[0039] The 3D modeling software uses mathematical algorithms to process point clouds, including point cloud registration, stitching and smoothing. It can automatically convert point clouds into geometric models and generate geometrically accurate digital twin models as virtual copies of the booster station for subsequent analysis and simulation.

[0040] In S30, data on the operation of the booster station is collected by using sensors and monitoring equipment.

[0041] The sensors measure physical quantities and convert them into electrical signals, which are recorded to form real-time monitoring data, and obtain real-time data of various parameters during the operation of the booster station to monitor the status and performance of the equipment.

[0042] In S40, the collected data is cleaned, filtered, and normalized to remove outliers and noise.

[0043] Cleaning improves data quality by eliminating erroneous or abnormal data, filtering removes high-frequency noise through algorithms, and normalization ensures that different types of data are on the same scale, allowing for more effective analysis, improving data quality, and ensuring the accuracy and reliability of subsequent analysis and modeling processes.

[0044] S50 uses machine learning or deep learning algorithms to compare real-time collected data with the digital twin model to predict potential abnormal conditions and failures;

[0045] The mathematical formula of the early warning analysis algorithm is;

[0046] Machine Learning Models:

[0047] [Y=f(X;θ)]

[0048] Among them, (θ) represents the parameters of the model;

[0049] Deep Learning Models:

[0050] [Y=g(W2·h(W1·X+b1)+b2)]

[0051] Among them, (w1) and (w2) are weight matrices, (b1) and (b2) are bias vectors, (h) is the activation function, and (g) is the output function.

[0052] Algorithms learn the relationship between the digital twin model and actual operating data in order to detect patterns that deviate from normal operation, providing real-time anomaly detection and early warning to help prevent equipment failures and optimize operations.

[0053] S60 combines early warning analysis with actual operating data and uses professional diagnostic algorithms to determine the type and location of the fault;

[0054] The mathematical formula of the fault diagnosis algorithm is;

[0055] Rule-based troubleshooting:

[0056] If X1>threshold and X2 <threshold,then Fault A]

[0057] Among them, (X1) and (X2) are specific features of the monitoring data, and (threshold) is the threshold;

[0058] Model-based fault diagnosis:

[0059] [Y=W·X+b]

[0060] Where (W) is the weight vector, (b) is the bias, and (Y) is the failure probability score.

[0061] The fault diagnosis algorithm matches the predicted anomalies with the actual faults based on known patterns and rules, providing accurate fault diagnosis results to help operation and maintenance personnel quickly locate and solve problems.

[0062] S70 uses charts and graphical interface visualization tools to present the generated warning signals and fault reports.

[0063] Visualization makes complex data easier to understand. Charts and interfaces display predictive information and fault reports in an intuitive way, helping operation and maintenance personnel to quickly understand the system status, take necessary actions, and improve operation and maintenance efficiency.

[0064] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for research and application of booster station status warning based on data twin, characterized in that: The steps include: S10, obtaining the real scene data of the booster station, and using professional data acquisition equipment to collect real scene data of the booster station; S20. Build a 3D model of the booster station. Use professional 3D modeling processing software to automatically stitch point cloud data and build a digital twin model of the booster station after smoothing. S30, data collection, collecting the operation data of the booster station, including equipment components, meters, and spectrum data; S40, data preprocessing, preprocessing the collected data, including cleaning, filtering, and normalizing the collected data to eliminate noise and outliers and improve the accuracy and reliability of the data; S50, early warning analysis, in which the digital twin booster station early warning system automatically and intelligently analyzes the real-time collected data, predicts abnormal status and potential failures of the booster station by comparing the data twin model with the actual operation data, and generates early warning signals; S60, fault diagnosis: the system diagnoses the fault type and location of the booster station and generates a fault report based on early warning analysis and actual operation data, including temperature alarms, personnel alarms, deformation alarms, and spectral data alarms; S70: Visual presentation: the warning signals and fault reports generated in the digital twin booster station warning system are output in a visual manner.

2. According to claim 1, a method for research and application of booster station status early warning based on data twins is characterized in that: The S10 uses laser scanners and camera devices to collect real-time data on the booster station. These devices generate a large amount of point cloud data, which reflects the geometric shape and external features of the booster station.

3. According to claim 1, a method for research and application of booster station status early warning based on data twins is characterized in that: The S20 uses professional 3D modeling software to process the point cloud obtained from real-scene data collection, perform splicing and smoothing, and finally build a digital twin model.

4. According to claim 1, a method for research and application of booster station status early warning based on data twins is characterized in that: In the S30, the data of the booster station during operation is collected by using sensors and monitoring equipment.

5. According to claim 1, a method for research and application of booster station status early warning based on data twins is characterized in that: In S40, the collected data is cleaned, filtered, and normalized to remove outliers and noise.

6. According to claim 1, a method for research and application of booster station status early warning based on data twins is characterized in that: In S50, a machine learning or deep learning algorithm is used to compare the real-time collected data with the digital twin model to predict potential abnormal conditions and failures.

7. The method for research and application of booster station status early warning based on data twin according to claim 1 is characterized in that: The S60 combines the early warning analysis with the actual operation data and uses a professional diagnostic algorithm to determine the type and location of the fault.

8. The method for research and application of booster station status early warning based on data twin according to claim 1 is characterized in that: In the S70 , a chart or a graphical interface visualization tool is used to present the generated warning signal and fault report.

Images