CN119646673A - Digital twin system for real-time monitoring of power tower status and common fault identification - Google Patents
Digital twin system for real-time monitoring of power tower status and common fault identification Download PDFInfo
- Publication number
- CN119646673A CN119646673A CN202411427268.3A CN202411427268A CN119646673A CN 119646673 A CN119646673 A CN 119646673A CN 202411427268 A CN202411427268 A CN 202411427268A CN 119646673 A CN119646673 A CN 119646673A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- maintenance
- module
- digital twin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明提出了一种基于数字孪生技术的电力杆塔状态实时监测与通病识别系统。该系统通过构建高精度的数字孪生模型模块，集成了传感器网络模块以实时采集杆塔关键数据。数据处理中心模块利用先进的时钟同步技术确保数据精度，配合通病识别系统模块和健康状态评估模块，采用有限元分析和Paris定律，对杆塔的健康状况进行精确评估。系统还包括一个智能化的维护决策支持模块，提供科学的维护策略。此外，数据可视化平台模块和用户交互界面模块增强了用户体验，使得系统不仅限于监测与评估，还实现了维护决策的优化和用户交互的个性化。整体系统设计注重实时性、精确性和智能化，旨在提升电力杆塔的运维效率和安全性。
The present invention proposes a real-time monitoring and common fault identification system for power tower status based on digital twin technology. The system integrates a sensor network module to collect key tower data in real time by constructing a high-precision digital twin model module. The data processing center module uses advanced clock synchronization technology to ensure data accuracy, and cooperates with the common fault identification system module and the health status assessment module to accurately assess the health status of the tower using finite element analysis and Paris's law. The system also includes an intelligent maintenance decision support module to provide scientific maintenance strategies. In addition, the data visualization platform module and the user interaction interface module enhance the user experience, so that the system is not limited to monitoring and evaluation, but also realizes the optimization of maintenance decisions and the personalization of user interactions. The overall system design focuses on real-time, accuracy and intelligence, aiming to improve the operation and maintenance efficiency and safety of power towers.
Description
Technical Field
The invention relates to the technical field of power system monitoring, in particular to a power tower state real-time monitoring and common fault identification system based on a digital twin technology.
Background
The stability of the power tower, which is an important component of the power transmission line, is directly related to the reliability and safety of the power grid. The traditional power tower monitoring method mainly depends on manual inspection, and has various limitations such as long monitoring period, incapability of real-time response, high labor intensity, low efficiency and the like. With the development of sensing technology and information technology, some automatic monitoring solutions appear, but the problems of low monitoring precision, limited fault identification capability, insufficient intelligence of maintenance decision and the like often exist in the solutions.
Disclosure of Invention
In order to solve the problems, the system for monitoring the states of the power towers in real time and identifying the common diseases based on the digital twin technology is characterized in that a high-precision digital twin model is created for each power tower, and the model can accurately reflect the physical characteristics, the environmental conditions and the running states of the towers. The system is capable of receiving and integrating data from tower sensors in real time, including but not limited to stress, displacement, vibration, ambient temperature and humidity, and the like. A set of algorithms is developed for analyzing real-time data and automatically identifying common problems of towers, such as corrosion, cracks, foundation instability, and the like. Based on the results of the universal identification, the system can evaluate the health status of the towers and predict potential failure risks. The system provides intelligent maintenance decision support including maintenance time, required materials, personnel scheduling, etc.
In order to achieve the above purpose, the application adopts the following technical scheme:
a power tower digital twinning system comprising:
-a high-precision digital twin model module for receiving design parameters, material properties, construction records and historical maintenance data of the tower, constructing a digital twin model comprising a geometric model and physical properties;
The sensor network module is used for deploying sensors according to the position information of key monitoring points in the digital twin model, acquiring stress, displacement and vibration data of the tower in real time and generating a sensor data set;
-a data processing center module for receiving the sensor dataset, performing data synchronization, preprocessing and anomaly detection, outputting a preprocessed dataset;
-a common-fault recognition system module for receiving the preprocessed data set and the digital twin model, performing feature extraction, model training and fault recognition, and outputting a fault state set;
-a health status assessment module for receiving a set of fault status and a digital twinning model, performing a fault severity analysis and risk prediction, outputting a health index;
-a maintenance decision support module for receiving the health index and the digital twinning model, determining a maintenance priority and optimizing resource allocation, generating a maintenance plan.
The high-precision digital twin model module comprises:
-an environment simulation unit for simulating the mechanism of influence of environmental factors such as wind, temperature, humidity etc. on the tower;
-a real-time updating unit for synchronously updating the digital twin model by wireless or wired communication means to reflect the real-time status of the tower.
The sensor network module includes:
-an adaptive algorithm unit for adjusting the sensor position based on real-time feedback to enhance the accuracy of the sensor dataset;
-a data synchronization algorithm unit for handling communication delays or data loss, ensuring a spatiotemporal consistency of the sensor dataset.
The data processing center module includes:
-a data preprocessing unit for processing the sensor dataset using a low pass filter, wavelet transform, Z-score or Min-Max normalization method;
-an outlier detection unit for automatically identifying and rejecting outlier data points in the preprocessed dataset based on an isolated forest or One-Class SVM algorithm.
The universal disease recognition system module comprises:
-a feature extraction unit for extracting key features from the preprocessed dataset based on PCA and ICA techniques;
-a model training unit for fault pattern recognition using SVM, random forest, GBM and deep neural network algorithms, generating a set of fault states.
The health status assessment module includes:
-a fault severity analysis unit for quantifying a stress increase caused by a fault state concentrating crack or notch using a stress concentrating coefficient;
-a risk prediction unit for predicting the probability of a failure state transition using markov chain analysis, determining the remaining useful life of the tower.
The maintenance decision support module comprises:
-a maintenance priority determination unit based on the risk matrix for determining a maintenance priority in combination with the health index, the tower importance and the maintenance resource availability;
-a time-cost optimization unit for balancing the time and cost of task completion in the maintenance plan.
The system further includes a data visualization platform module, the data visualization platform module comprising:
-an interactive three-dimensional visualization unit for allowing a user to observe the digital twin model from different angles and scales;
-a custom data report generating unit for generating a report from the set of fault conditions, the health index and the maintenance plan.
The system further includes a user interaction interface module, the user interaction interface module comprising:
-a personalized recommendation unit for recommending maintenance policies in a maintenance plan according to historical selections and preferences of the user;
-a maintenance log tracking unit for recording maintenance activities and results and updating the digital twin model.
The system further comprises:
-a high performance computing cluster unit for processing the preprocessed data set using a MapReduce parallel processing technique;
-a real-time stream processing unit for processing a sensor data stream of the sensor data set.
Through the technical scheme, the digital twin technology-based power tower state real-time monitoring and universal fault identification system is provided. The system utilizes a high-precision digital twin model, real-time data integration, a common-fault recognition algorithm, health state assessment and maintenance decision support technology to realize accurate monitoring and maintenance of the state of the power tower.
Drawings
In order to make the embodiments, technical solutions and technical advantages of the present application more clear, the following drawings provide non-limiting views of the present application:
fig. 1 shows a schematic diagram of the overall architecture of a power tower digital twin system.
FIG. 2 shows a flow chart for the construction of a high-precision digital twin model.
Fig. 3 shows a schematic diagram of the operation of the environmental simulation unit.
Fig. 4 shows a flow chart of real-time data acquisition and synchronization.
FIG. 5 illustrates a flow chart of data preprocessing and outlier detection for a data processing center.
Fig. 6 shows a workflow diagram of a common fault recognition algorithm.
Fig. 7 illustrates an evaluation flow chart of the health status evaluation module.
Fig. 8 illustrates a decision flow diagram of a maintenance decision support module.
Detailed Description
For an exhaustive description of the embodiments, technical solutions and technical advantages of the present application, a detailed and complete description is provided below with reference to the accompanying drawings. It should be clear that the described embodiments represent only a part of the application scenarios of the application, not all possibilities. Other possible embodiments will be apparent to those skilled in the art from consideration of the specification without undue burden of the application, as such embodiments are within the scope of the application.
1. Construction of high-precision digital twin model
The construction of the high-precision digital twin model is a key step for realizing the innovation target of the power tower state real-time monitoring and universal fault recognition system. The construction flow, technical details and fusion and embodiment of the digital twin model in the actual application scene are described in detail in the section.
The first step in constructing a high-precision digital twin model is to collect the design parameters, material properties, construction records and historical maintenance data of the power tower comprehensively. These data provide basic information to the model including, but not limited to, tower size, material grade, force characteristics, and historical repair and failure records. After data collection, preprocessing is performed to ensure consistency and accuracy of the data, including data cleaning, format unification and outlier rejection.
And (3) adopting professional three-dimensional modeling software to build a geometric model of the vertical tower according to the collected data. This process is careful to each component of the tower, such as the base, pole, cross arm, insulator, wire, etc., and the connection relationship between them. And creating a 1:1 ratio three-dimensional model by using SolidWorks or Autodesk 3ds Max and other software, and ensuring that the geometric dimension and the relative position of each part are consistent with those of the solid tower.
Physical properties such as density, elastic modulus, poisson's ratio, yield strength, etc. are imparted to each component on the basis of the geometric model. These properties are based on material science and engineering principles, and can be obtained through material mechanics testing or set according to material standards and specifications. For example, for concrete towers, their modulus of elasticity E and Poisson's ratio v are determined based on material grade and used for subsequent stress analysis.
The environment simulation unit simulates the influence of the tower in the actual environment, such as wind power, temperature, humidity and the like. Through environmental simulation software or algorithms, these environmental factors are incorporated into the model to reflect the stress state and performance changes of the tower under different environmental conditions. For example, temperature variations may affect material properties, while wind forces act directly on the tower to create bending moments and vibrations.
The wind load can be calculated by the following formula:
Fw＝0.5·ρ·A·Cd·V2
Wherein Fw is wind load, ρ is air density, A is windward area, cd is drag coefficient, and V is wind speed.
The real-time updating unit is a key component of the digital twin model. By disposing high-precision sensors such as strain gauges, displacement sensors, vibration sensors and the like on the towers, stress, displacement and vibration data of the towers are acquired in real time. The data are transmitted to a data processing center in a wireless or wired communication mode and are synchronously updated with the digital twin model, so that the model is ensured to reflect the real-time state of the tower.
In order to ensure accuracy of the digital twin model, model verification and calibration is required. And (3) evaluating the accuracy of the model by comparing the model prediction with actual measurement data, and carrying out necessary adjustment. For example, if the model predicted stress distribution is found to deviate from the actual measurement, calibration may be performed by adjusting material properties or boundary conditions.
To further enhance the accuracy of the digital twin model, the present invention integrates Finite Element Analysis (FEA). By discretizing the three-dimensional model of the tower into a limited number of elements and nodes, detailed analysis of the stress, strain, and displacement of the tower under various loads can be performed. The general formula of the finite element model is as follows:
K·U=F
where K is the stiffness matrix, U is the node displacement vector, and F is the node load vector. The stiffness matrix of each element can be calculated from the elastic modulus E and the geometric properties of the material.
The digital twin model simulates various physical field influences such as thermal expansion, electric corrosion and the like, which are suffered by the power tower in actual operation through multi-physical field coupling analysis. For example, thermal expansion may be expressed as:
ΔL=α·L0·ΔT
Where Δl is the change in length, α is the coefficient of thermal expansion, L 0 is the initial length, and Δt is the change in temperature.
Through the steps, a digital twin model with high precision and dynamic updating is constructed, and a foundation is laid for subsequent state monitoring and common disease identification.
2. Real-time data integration
The real-time data integration system is realized based on the sensor network module and the data processing center module. The two modules work cooperatively to ensure the high efficiency and accuracy of the whole process from data acquisition to processing.
The sensor network module is the core of real-time data acquisition and is responsible for generating a sensor data set. The method is specifically realized as follows:
and according to the position information of the key monitoring points in the digital twin model, the system adopts an optimization algorithm to determine the optimal layout of the sensor. For example, strain gauges are preferentially deployed in the region of expected maximum bending moment, and vibration sensors are mounted on top of the tower, which is susceptible to wind vibrations. By genetic algorithms or particle swarm optimization algorithms, we can find the most cost effective sensor deployment solution.
To address the specific environmental and structural characteristics of the pole, the adaptive algorithm unit adjusts the sensor position based on real-time feedback to enhance the accuracy of the sensor dataset. For example, if an anomaly in stress data of a region is detected, the system automatically adjusts parameters of the proximity sensor or increases the sensor to enhance the accuracy of the data of the region.
To ensure the spatio-temporal consistency of the sensor data sets, the data synchronization algorithm employs high precision clock synchronization techniques, such as Network Time Protocol (NTP), to ensure that all sensor data is collected under a uniform time reference. Furthermore, we have developed a data synchronization algorithm based on a time window to handle possible communication delays or data loss.
The improved PTP (Precision Time Protocol) is adopted to ensure the nanosecond time synchronization precision. In addition, a spatial calibration algorithm is introduced to ensure that the spatial position errors of different sensors are within an acceptable range, and the formula is as follows:
Wherein Δx, Δy, Δz represent the positioning errors of the sensor on three coordinate axes, respectively.
With the consideration that towers are often located in outdoor environments where wiring is difficult, the system employs wireless communication technology to transmit sensor data. According to the data volume, transmission distance and energy consumption requirements, a proper communication mode is selected, such as a cellular network, wi-Fi, loRa and the like. The data is compressed and encrypted before transmission to reduce bandwidth requirements and ensure data security. The system also develops an adaptive transmission power control algorithm based on channel quality to maximize transmission efficiency and reduce power consumption. The transmission power PP is dynamically adjusted according to Channel State Information (CSI), as follows:
P=min(Pmax,k·CSI)
Where P max is the maximum transmission power and k is a proportionality constant determined according to energy consumption and coverage.
The data processing center module is responsible for receiving the sensor data set, carrying out data synchronization, preprocessing and abnormality detection, and outputting the preprocessed data set. The method is specifically realized as follows:
The data preprocessing unit employs a series of algorithms to improve data quality, including removing high frequency noise using a low pass filter, denoising signals using wavelet transform, and normalizing data using a Z-score or Min-Max normalization method. These algorithms can automatically adjust parameters to accommodate different data characteristics and environmental changes. For example, the Z-score normalization formula is as follows:
z=(x-μ)/σ
Where x is the raw data point, μ is the mean of the dataset and σ is the standard deviation.
The abnormal value detection unit automatically identifies and eliminates abnormal data points in the preprocessed data set based on methods such as isolation forests or One-Class SVM, and the like, so that the data quality is improved. The decision function can be expressed as:
f(x)=w·x+b
where w and b are model parameters, x is a data point, and the value of f (x) is used to determine if the data point is abnormal.
Data fusion is the integration of data from different sensors into a unified reference frame. The system adopts a fusion algorithm based on a Kalman filter, and can estimate and update the state of the tower in real time while considering the uncertainty and the relevance of different sensors.
To process large-scale real-time data streams, the system employs a real-time stream processing framework, such as APACHE KAFKA and Apache Storm. The techniques enable efficient processing and analysis of sensor data streams of a sensor dataset, ensuring real-time and reliability of data processing.
Through the steps, the system can effectively collect, transmit and process the real-time state data of the power tower, and provide high-quality data support for subsequent common-fault identification and health state evaluation. 3. Data processing center module and common fault recognition system module
The data processing center module is responsible for receiving the original data sensor data set transmitted by the sensor network module, carrying out data synchronization, preprocessing and anomaly detection, and finally outputting the preprocessed data set. The module comprises the following main units:
1) A data preprocessing unit:
-removing high frequency noise with a low pass filter.
-Signal denoising using a wavelet transform, the wavelet transform formula being as follows:
Where a is the scale parameter, b is the translation parameter, and ψ is the wavelet function.
-Normalizing the data using a Z-score or Min-Max normalization method.
2) An abnormal value detection unit:
-identifying outlier data points based on an isolated Forest (Isolation Forest) algorithm.
-Anomaly detection using One-Class SVM algorithm, with an optimized objective function:
s.t.(wTφ(xi))≥p-ξi,ξi≥0
where w is a weight vector, φ (x) is a kernel function that maps data to a high-dimensional feature space, ζ i is a relaxation variable, ρ is a decision threshold, and l is the total number of data points.
The universal disease recognition system module receives the preprocessed data set and the digital twin model to perform feature extraction, model training and fault recognition, and outputs a fault state set. The module comprises the following main units:
1) Feature extraction unit:
-extracting key features based on Principal Component Analysis (PCA) techniques;
C=(1/n)∑(Xi-μ)(Xi-μ)^T
[U,S,V]=SVD(C)
Y=U^T·X
Wherein C is covariance matrix, U is eigenvector matrix, S is singular value matrix, Y is feature after dimension reduction.
-Separating the independent signal sources using Independent Component Analysis (ICA) technology:
max J(y)=H(y)-I(s,y)
wherein H (y) is the output entropy, and I (s, y) is the mutual information.
2) Model training unit:
-Support Vector Machine (SVM) algorithm:
min(1/2)||w||^2+C∑ξi
s.t.yi(w·xi+b)≥1-ξi,ξi≥0
Wherein w is a weight vector, b is a bias term, C is a penalty parameter, and xi is a relaxation variable
-Random forest algorithm, namely constructing a plurality of decision trees and classifying by adopting a voting mechanism.
-Gradient hoist (GBM) algorithm, optimizing the loss function by iteration.
F(x)=∑γm·h(x;am)
Wherein γm is the step size, and h (x; am) is the base learner.
Deep neural network, training using a back propagation algorithm with a multi-layer perceptron structure.
3) A fault identification unit:
-combining the outputs of the plurality of models, employing an ensemble learning method to improve recognition accuracy.
-Updating the fault state set in real time, containing information of fault type, location and severity.
Through the cooperative work of the modules, the system can effectively identify various common diseases of the power tower and provide reliable basis for subsequent health state evaluation and maintenance decision.
4. Health status evaluation module
The health state evaluation module is responsible for receiving the fault state set and the digital twin model, analyzing the fault severity and predicting the risk, and finally outputting the health index. The module comprises the following main units:
1) Fault severity analysis unit using stress concentration coefficients (Stress Concentration Factor, SCF) to quantify crack or notch induced stress increase:
Where σ max is the maximum stress and σ nom is the nominal stress.
Finite Element Analysis (FEA) was used to simulate the effect of faults on structural integrity of towers:
Where σ fea is the stress modeled by FEA, N is the force, and A is the effective cross-sectional area of the tower. A Markov chain model is adopted to predict the transition probability of the fault state:
Where P ij is the probability of transitioning from state i to state j, and T ij is the number of transitions from i to j in the state transition matrix.
The time of failure occurrence is analyzed by adopting a Cox proportion risk model:
h(t)=h0(t)exp(βX)
Where h (t) is the risk function at time t, h 0 (t) is the reference risk function, β is the risk coefficient, and X is the influencing factor vector.
Prediction of remaining useful life (REMAINING USEFUL LIFE, RUL) may employ a physical-based degradation model or a data-driven approach, such as the Kaplan-Meier estimator:
Wherein, Is the probability of existence at time t, N i is the number of units that failed at time i, and N i is the total number of units at risk at start time i.
The health index calculation comprehensively considers the structural integrity of the tower, historical maintenance records and real-time monitoring data. Calculating the health index of the tower by a weighted synthesis method:
HI=w1·S1+w2·SH+w3·SM
Where HI is health index, S I、SH and S M are normalized scores for structural integrity, historical maintenance and real-time monitoring, respectively, and w 1、w2 and w 3 are the corresponding weights.
5. Maintenance decision support module
And the maintenance decision support module receives the health index and the digital twin model, determines maintenance priority and optimizes resource allocation, and finally generates a maintenance plan. The module comprises the following main units:
1) A maintenance priority determination unit based on the risk matrix:
-constructing a risk matrix with the probability of occurrence of a fault on the horizontal axis and the severity of the consequences of the fault on the vertical axis.
-Determining maintenance priority for each tower in combination with health index, tower importance and maintenance resource availability.
2) Time-cost optimization unit:
-building a multi-objective optimization model:
minf 1(x)＝∑ici·xi (total maintenance cost)
Minf 2(x)＝max(ti·xi) (maximum completion time)
Where c i is the cost of maintenance task i, t i is the completion time of maintenance task i, and x i is the decision variable.
3) A resource scheduling unit:
-resource allocation based on Constraint Satisfaction Problem (CSP) model:
V= { V1, V2,..vn } (variable set)
D= { D1, D2, & gt, dn } (value range set)
C= { C1, C2,..cm } (constraint set)
Solving the CSP using a backtracking search algorithm, resulting in a resource allocation scheme that satisfies all constraints
4) Maintenance plan generation unit:
Comprehensive consideration of maintenance priority, time-cost optimization results and resource allocation schemes
-Generating a detailed maintenance plan comprising information of maintenance task list, execution time, required resources etc
Through the cooperative work of the modules, the system can carry out scientific maintenance decision based on the health state of the pole tower, and preventive maintenance of the power pole tower and efficient utilization of resources are realized.
6. Data visualization platform module, user interaction interface module, high performance computing and real-time data processing capabilities
The data visualization platform module aims at visually and efficiently displaying various data and analysis results generated by the system. The module mainly comprises the following units:
1) Interactive three-dimensional visualization unit:
the unit adopts the WebGL technology to realize the 3D rendering based on the browser. The specific implementation steps are as follows:
a. creating scenes, cameras and renderers, setting appropriate viewing angles and lighting conditions.
B. And constructing a three-dimensional model of the tower according to the digital twin model, wherein the three-dimensional model comprises geometric shapes and material properties.
C. interactive control of the model is realized, and the user is allowed to perform rotation, zooming and translation operations.
D. Using color coding to display stress distribution of each part of the tower, the mapping relationship between the stress value sigma and the color can be expressed as follows:
color=f(σ)={
red, if sigma > sigma max
Yellow, if sigma threshold < sigma max
Green, if sigma is less than or equal to sigma threshold
}
Wherein σmax is the maximum allowable stress of the material, and σthreshold is the early warning threshold.
2) Custom data report generation unit:
the unit creates an interactive data visualization chart and generates a comprehensive report. The specific implementation is as follows:
a. Health trend graph, which is to predict future health index trend by using time sequence analysis method such as index smoothing method.
The predictive formula is H (t+1) =α×h (t) + (1- α) ×h' (t)
Where H (t) is the actual health index at time t, H' (t) is the predicted value at time t, and α is the smoothing coefficient.
B. and maintaining the Gantt chart, namely generating a task time axis according to a maintenance plan and expressing task priorities by using different colors.
C. And (3) a fault distribution diagram, namely, using a thermodynamic diagram to display the fault frequency of each part of the tower, and indicating the probability of fault occurrence by the shade of the color.
The user interaction interface module provides an intuitive and friendly operating environment for system operators. The module mainly comprises the following units:
1) Personalized recommendation unit:
The unit recommends maintenance strategies for users by using collaborative filtering algorithms and reinforcement learning methods. The specific implementation is as follows:
a. And a collaborative filtering algorithm, namely calculating the similarity among users based on the user-item matrix, and predicting the interest degree of the users on unscored items.
The similarity calculation adopts cosine similarity: sim (a, B) =cos (θ) = (a.b)/(|a|||b|) wherein, a and B represent scoring vectors for users a and B, respectively.
B. and (3) a reinforcement learning algorithm, namely optimizing a recommendation strategy by using a Q-learning method, wherein a Q value updating formula is as follows:
Q(s,a)←Q(s,a)+α[r+γmax Q(s',a')-Q(s,a)]
where s is the current state, a is the selected action, r is the instant prize, γ is the discount factor, and α is the learning rate.
2) Maintenance log tracking unit:
The present unit employs blockchain techniques to ensure that the maintenance record is not tamperable. The specific implementation is as follows:
a. The block structure comprises an index, a time stamp, data, a hash value of a previous block and a hash value of a current block.
B. hash calculation, namely ensuring data integrity by using an SHA-256 algorithm.
C. and the consensus mechanism adopts a workload proof (PoW) mechanism, and the difficulty value is dynamically adjusted so as to ensure the stability of the block generation speed.
In order to process large amounts of sensor data and support complex analytical models, the system further comprises the following functions:
1) High performance computing cluster unit:
The unit adopts a distributed computing framework to realize large-scale data processing. The main characteristics include:
a. And data partitioning, namely uniformly distributing data to cluster nodes by using a consistent hash algorithm.
B. and (3) parallel calculation, namely adopting a MapReduce model, processing single data points by a Map function, and aggregating processing results by a Reduce function.
C. And the fault-tolerant mechanism is used for realizing data replication and task rescheduling and ensuring the reliability of the system.
2) Real-time stream processing unit:
the unit processes the sensor data stream of the sensor data set, and is mainly characterized by comprising:
a. sliding window model data grouping and processing is performed using a time window W and a sliding step S.
B. abnormality detection, namely identifying abnormal values in real time by adopting a Z-score method, wherein Z= (x-mu)/sigma
Where x is the observed value, μ is the historical average, and σ is the standard deviation.
C. Real-time aggregation, the aggregation statistics of large-scale data streams are calculated using an approximation algorithm (e.g., hyperLogLog).
Through the cooperative work of the modules and the functions, the system can efficiently process and analyze a large amount of real-time data, and provides powerful support for the state monitoring and maintenance decision of the power tower.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411427268.3A CN119646673A (en) | 2024-10-12 | 2024-10-12 | Digital twin system for real-time monitoring of power tower status and common fault identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411427268.3A CN119646673A (en) | 2024-10-12 | 2024-10-12 | Digital twin system for real-time monitoring of power tower status and common fault identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119646673A true CN119646673A (en) | 2025-03-18 |
Family
ID=94953098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411427268.3A Pending CN119646673A (en) | 2024-10-12 | 2024-10-12 | Digital twin system for real-time monitoring of power tower status and common fault identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119646673A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119848478A (en) * | 2025-03-21 | 2025-04-18 | 南京纳恩自动化科技有限公司 | Power equipment state evaluation method and system based on machine learning |
| CN120338757A (en) * | 2025-04-02 | 2025-07-18 | 中国计量科学研究院 | Intelligent storage equipment health status assessment and predictive maintenance method and system |
| CN120509754A (en) * | 2025-04-29 | 2025-08-19 | 天津国能盘山发电有限责任公司 | Maintenance decision system and method based on big data driving |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117972981A (en) * | 2023-12-15 | 2024-05-03 | 国网山东省电力公司泰安供电公司 | Shared transmission tower fault detection method, device and equipment based on digital twin |
| CN117994728A (en) * | 2024-02-21 | 2024-05-07 | 北京中瀚润淇科技有限公司 | Intelligent operation and maintenance management system for high-speed trains based on digital twins |
| CN118154119A (en) * | 2024-03-08 | 2024-06-07 | 广东粤海珠三角供水有限公司 | Hydraulic engineering full life cycle intelligent management system based on digital twin |
| CN118172040A (en) * | 2024-03-12 | 2024-06-11 | 国网安徽省电力有限公司宣城供电公司 | A digital twin substation intelligent operation and maintenance system and method |
| CN118428067A (en) * | 2024-04-28 | 2024-08-02 | 苏州途睿思信息科技有限公司 | Power transmission and transformation tower fault detection method and system based on digital twin technology |
-
2024
- 2024-10-12 CN CN202411427268.3A patent/CN119646673A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117972981A (en) * | 2023-12-15 | 2024-05-03 | 国网山东省电力公司泰安供电公司 | Shared transmission tower fault detection method, device and equipment based on digital twin |
| CN117994728A (en) * | 2024-02-21 | 2024-05-07 | 北京中瀚润淇科技有限公司 | Intelligent operation and maintenance management system for high-speed trains based on digital twins |
| CN118154119A (en) * | 2024-03-08 | 2024-06-07 | 广东粤海珠三角供水有限公司 | Hydraulic engineering full life cycle intelligent management system based on digital twin |
| CN118172040A (en) * | 2024-03-12 | 2024-06-11 | 国网安徽省电力有限公司宣城供电公司 | A digital twin substation intelligent operation and maintenance system and method |
| CN118428067A (en) * | 2024-04-28 | 2024-08-02 | 苏州途睿思信息科技有限公司 | Power transmission and transformation tower fault detection method and system based on digital twin technology |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119848478A (en) * | 2025-03-21 | 2025-04-18 | 南京纳恩自动化科技有限公司 | Power equipment state evaluation method and system based on machine learning |
| CN120338757A (en) * | 2025-04-02 | 2025-07-18 | 中国计量科学研究院 | Intelligent storage equipment health status assessment and predictive maintenance method and system |
| CN120509754A (en) * | 2025-04-29 | 2025-08-19 | 天津国能盘山发电有限责任公司 | Maintenance decision system and method based on big data driving |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119646673A (en) | Digital twin system for real-time monitoring of power tower status and common fault identification | |
| CN118731179A (en) | A three-dimensional damage identification method for bridge structures | |
| CN116129366A (en) | Digital twinning-based park monitoring method and related device | |
| CN118688575A (en) | An automated defect identification method for distribution network fault handling | |
| CN119337290B (en) | A housing safety detection method and system | |
| JP2013186899A (en) | Method and system for monitoring structure | |
| CN117828883B (en) | GIS-based power transmission line tension paying-off simulation system | |
| CN118627407B (en) | Waterlogging model creation method and system applied to urban water management | |
| CN118898205A (en) | A device fault detection method and system based on digital twin | |
| CN120653941B (en) | Data analysis methods for digital management of engineering consulting | |
| CN120356316A (en) | Multi-mode early warning method and system for slope geological disasters | |
| CN120355225A (en) | Construction site safety risk intelligent early warning system and method based on BIM and big data analysis | |
| US20200160208A1 (en) | Model sharing among edge devices | |
| CN118840485A (en) | Three-dimensional model construction method and system for curtain wall unit plates | |
| CN118550573B (en) | IT operation and maintenance management method and IT operation and maintenance management device | |
| CN119249212A (en) | A data change trend prediction method for a big data analysis platform | |
| CN120745906A (en) | Intelligent monitoring method and system for construction progress of building decoration curtain wall | |
| CN119091069A (en) | A three-dimensional geographic target construction and analysis system based on neural network model | |
| CN119845344A (en) | Marine booster station steel structure safety monitoring method and system based on artificial intelligence | |
| CN120655248B (en) | A continuous casting quality control method based on a metacognitive coordination architecture intelligent agent cluster | |
| CN120541926A (en) | A BIM-based intelligent management method and system for building structures | |
| CN120655118A (en) | Engineering construction digital management system and method based on data portrait | |
| CN119416136A (en) | Irrigation area measurement and control integrated gate health monitoring method and system | |
| CN117131581B (en) | Digital twin urban road construction system and method | |
| CN119557622A (en) | A fault identification method, system, device and medium for non-stop operation of distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |