An electric power fitting vibration fatigue monitoring and early warning method and system based on an internet of things

Abstract

The application discloses a kind of power fittings vibration fatigue monitoring and early warning method and system based on Internet of Things, first acquire the vibration data of power fittings, the dynamic topology network of power fittings is constructed, after the vibration fatigue assessment of single power fittings is carried out, it is reflected in the dynamic topology network, by the analysis of group vibration fatigue, the vibration fatigue assessment result of single power fittings is adjusted, until reach the maximum iteration number or fitness no longer improves, output final adjustment result and the vibration fatigue assessment result of power fittings.This scheme constructs transmission line dynamic topology network, accurately obtains the vibration data of single node, and innovatively introduces power consumption baseline dynamic adjustment and spatial correlation analysis method, can real-time, self-adaptingly assess the real fatigue state of power fittings in transmission line and concentrated abnormal area.

Description

Technical Field

[0001] This invention belongs to the field of power fatigue monitoring, specifically a method and system for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things. Background Technology

[0002] Power fittings in transmission lines are subject to long-term vibration fatigue due to wind vibration and line loads. Traditional methods often rely on independent assessment using single-point sensors, which struggles to effectively identify concentrated anomalies caused by line characteristics and lacks adaptive analysis and response to changes in transmission line power consumption characteristics. Therefore, how to accurately locate and adaptively identify vibration fatigue anomalies in power fittings based on monitoring data from a single sensor node, through swarm intelligence analysis and line power consumption characteristics, has become a pressing technical challenge for the power industry. Summary of the Invention

[0003] To address the aforementioned problems, the present invention aims to provide a method and system for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things.

[0004] The specific technical solution for achieving the objective of this invention is as follows:

[0005] A method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things includes the following steps:

[0006] Step 1: Obtain vibration data of power fittings;

[0007] Step 2: Construct a dynamic topology network for power fittings;

[0008] Step 3: After conducting a vibration fatigue assessment on an individual power fitting, the results are reflected in the dynamic topology network. By analyzing the vibration fatigue of the group, the vibration fatigue assessment results of the individual power fitting are adjusted.

[0009] Step 4: Repeat steps 1 to 3 until the maximum number of iterations is reached or the fitness no longer improves. Output the final adjustment results and the vibration fatigue assessment results of the power fittings.

[0010] An Internet of Things (IoT) based vibration fatigue monitoring and early warning system for power fittings includes the following modules:

[0011] Data acquisition module: used to acquire vibration data of power fittings;

[0012] Dynamic Topology Network Building Module: Used to build dynamic topology networks for power fittings;

[0013] Evaluation and Adjustment Module: This module is used to evaluate the vibration fatigue of individual power fittings and reflect the results in the dynamic topology network. By analyzing the vibration fatigue of the group, it adjusts the vibration fatigue evaluation results of individual power fittings.

[0014] Output module: Outputs the final adjustment results and the vibration fatigue assessment results of the power fittings.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0016] The present invention provides an IoT-based method for monitoring and early warning of vibration fatigue of power fittings. By constructing a dynamic topology network of transmission lines, it can accurately acquire vibration data of individual nodes and innovatively introduce dynamic adjustment of power consumption baseline and spatial correlation analysis method, which can evaluate the real fatigue state and concentrated abnormal areas of power fittings in transmission lines in real time and adaptively.

[0017] This solution utilizes a neural network model to quickly and accurately predict the fatigue level of various hardware components, avoiding the errors inherent in traditional fixed parameters. Ultimately, through visualization and real-time alarm strategies, it significantly improves the operational safety of transmission lines, reduces maintenance costs, and ensures the reliable operation of power facilities.

[0018] The present invention will be further described below with reference to specific embodiments. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the process for the Internet of Things-based vibration fatigue monitoring and early warning method for power fittings according to the present invention.

[0020] Figure 2 This is a schematic diagram of power fittings in an embodiment of the present invention. Detailed Implementation

[0021] Example

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0024] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0025] Combination Figure 1 A method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things includes the following steps:

[0026] Step 1: Obtain vibration data of power fittings;

[0027] When acquiring vibration data of power fittings, vibration sensors are placed on the surface of the power fittings or transmission lines. When the fittings vibrate due to wind, line load, or other external forces, the vibration sensors output the vibration data of the power fittings.

[0028] The vibration data of the power fittings includes vibration acceleration data, vibration displacement data, and vibration spectrum data.

[0029] This method does not restrict the equipment used; equipment can be selected manually based on power requirements. The analysis process described later is then performed based on the acquired vibration signals.

[0030] First, the vibration sensor in this solution is installed on the surface of power fittings or transmission lines. When the fittings vibrate due to wind, line load, or other external forces, the sensor converts the mechanical motion of this vibration into an electrical signal output.

[0031] Sensing devices such as piezoelectric sensors:

[0032] Principle: When the sensor is subjected to vibration, the internal piezoelectric crystal generates charge, which is converted into a voltage signal output.

[0033] Advantages: High sensitivity and fast high-frequency response, suitable for high-frequency vibration detection.

[0034] Resistance strain gauge sensor:

[0035] Principle: Strain gauges are attached to the surface of the fittings. Vibration produces minute deformations, causing changes in resistance, which in turn outputs a voltage signal.

[0036] Advantages: Good low-frequency response, suitable for low-frequency or low-to-medium frequency vibration.

[0037] MEMS accelerometer:

[0038] Principle: Based on microelectromechanical systems (MEMS), the acceleration of vibration is sensed through a micro-mechanical structure and converted into an electrical signal.

[0039] Advantages: Small size, low power consumption, easy integration, suitable for IoT applications.

[0040] Fiber optic vibration sensor:

[0041] Principle: Based on fiber optic interferometry or Brillouin scattering technology, the phase or frequency change of the optical signal is detected to measure the vibration displacement or amplitude.

[0042] Advantages: Strong resistance to electromagnetic interference, suitable for power environments.

[0043] Vibration sensors typically acquire the following types of data:

[0044] Vibration acceleration data:

[0045] The most commonly used data type is usually expressed in g (gravitational acceleration) or m / s². 2 express;

[0046] It can be directly used to calculate vibration intensity and frequency, and to assess the health status of equipment.

[0047] Vibration velocity data:

[0048] Expressed in mm / s or cm / s, it is suitable for vibration analysis in the mid-frequency range;

[0049] It is commonly used for fatigue analysis, life prediction, and condition assessment.

[0050] Vibration displacement data:

[0051] It is usually expressed in μm or mm and is suitable for vibration measurement in the low frequency range;

[0052] Used to evaluate amplitude and the physical motion trajectory of a structure.

[0053] Vibration spectrum data:

[0054] The original vibration data is processed by FFT (Fast Fourier Transform) to obtain frequency spectrum information;

[0055] Used to identify the dominant and potential anomalous frequencies of vibration, and to pinpoint possible problems.

[0056] Step 2: Construct a dynamic topology network for power fittings, where a single node in the network contains multiple power fittings, and each power fitting is represented by superimposing different states on the node.

[0057] Specifically, the location of each power fitting is taken as a node, and the connection between different nodes is constructed by connecting the power transmission lines;

[0058] When multiple nodes exist at the same location, the relationships between these nodes are analyzed:

[0059] If multiple nodes operate on different transmission lines, they should be accounted for separately as different nodes.

[0060] If a node can function on multiple transmission lines simultaneously, it is accounted for separately as a special node. For example, in some embodiments, a power fitting may function at the intersection of multiple lines.

[0061] If multiple nodes operate on the same transmission line, then the multiple nodes at the same location are merged into a single node with superimposed different states, represented as: J i ={j i,1 j i,2 , ..., j i,n}, where j i,n This represents the nth state of the i-th node, where each state represents the vibration data of a power fitting.

[0062] The connections between nodes are represented by lines.

[0063] It should be noted that, generally speaking, a node of a transmission line usually contains multiple power fittings, rather than just a single one. This is determined by the structural characteristics and functional requirements of the transmission line node itself.

[0064] The specific reasons are as follows:

[0065] Structural complexity: Nodes in transmission lines (such as tower connections, insulator string connections, and conductor connections) often require different types of fittings to achieve combined connections of multiple conductors, insulators, and components. For example, a single tower node typically includes multiple fittings such as suspension clamps, tension clamps, vibration dampers, spacers, and insulator connectors.

[0066] Functional versatility: Power fittings do not have only one function, but need to be configured with multiple fittings with different functions to work together, depending on different uses (such as connection, suspension, protection, vibration damping, etc.).

[0067] Safety and reliability requirements: To ensure line reliability, nodes often use multiple fittings to share stress and vibration loads, in order to reduce the safety risks caused by fatigue or damage of a single fitting.

[0068] For example:

[0069] A single node (metal tower node) typically contains the following hardware: multiple suspension clamps, multiple tension clamps, several vibration damping hardware (such as vibration dampers), multiple spacers or dampers, and multiple connecting hardware (such as connecting plates, cleats, and pins). Therefore, in practical applications, especially at critical connection nodes in transmission lines, it is usually a combination structure of multiple electrical hardware, rather than a single electrical hardware. For example... Figure 2 As shown, a node includes composite insulators, ball-head hanging rings, U-shaped hanging rings, extension rings, right-angle hanging plates, and extension rings.

[0070] Step 3: After performing vibration fatigue assessment on individual power fittings, the results are reflected in the dynamic topology network. Through analysis of the group vibration fatigue, the vibration fatigue assessment results of individual power fittings are adjusted.

[0071] Step 3-1: Based on the power consumption of each transmission line, set the power consumption baseline for each node:

[0072] The power consumption baseline of each node is used to represent the workload of that node from the last replacement of the power fittings to the current moment:

[0073]

[0074] Where U represents the time interval from the last replacement of the power fitting at the node to the current time; Q_U represents the calculated power consumption baseline of the node within time U; and I_U represents the power consumption baseline of the node within time U. u f(I) represents the current intensity of the transmission line. u ) represents the transmission line coefficient.

[0075] Step 3-2: Construct a vibration fatigue assessment model for power fittings and perform vibration fatigue assessment on individual power fittings:

[0076] The vibration fatigue assessment includes setting a power consumption baseline for each node based on the power consumption of each transmission line, representing the working intensity of each node from the last replacement of power fittings to the current time. The vibration fatigue assessment model is constructed using a deep feedforward neural network and trained using a dataset.

[0077] The vibration fatigue of each power fitting is evaluated using a pre-trained neural network. The input of the vibration fatigue evaluation model is the cumulative fatigue level of the transmission line when the power fitting was last replaced, the power baseline, and the model of the power fitting; the output is the fatigue level of the node at the current moment.

[0078] The fatigue level includes the durability of the power fittings; a fatigue threshold is preset for each model of power fittings. If the fatigue level of the power fittings exceeds the corresponding threshold at the current moment, it is determined that the power fittings need to be replaced.

[0079] It is worth mentioning that the system accurately measures the actual working load of power fittings, avoiding misjudgments caused by traditional assessment methods that rely solely on fixed vibration intensity. Secondly, by introducing time integration, it enables full lifecycle tracking of the actual usage process. Thirdly, by combining a neural network model with the power consumption baseline as input, it dynamically and adaptively predicts the vibration fatigue state, thereby achieving accurate early warning and maintenance. Finally, it effectively improves the reliability of transmission lines, reduces maintenance costs, and prevents accidents.

[0080] In this embodiment, a deep feedforward neural network is used for prediction. The model is easy to train, highly stable, and suitable for rapid implementation and deployment; it can quickly evaluate and provide reliable fatigue prediction values, facilitating calculations in subsequent iterative processes.

[0081] In an alternative embodiment, the neural network may also be a Transformer attention mechanism network, a Long Short-Term Memory (LSTM) network, or a Gated Recurrent Unit (GRU) network.

[0082] Step 3-3: Based on the vibration fatigue assessment results of individual power fittings, adjust the power supply baseline of the transmission line:

[0083] Based on the fatigue value of electrical fittings on a single transmission line in the dynamic topology network, if the number of electrical fittings exceeding the set fatigue value on a single transmission line exceeds a preset proportion, the power consumption baseline of that transmission line will be adjusted.

[0084] The power consumption baseline of each node in the transmission line R is adjusted by a step size. If the selected transmission line R is a trunk line, the power consumption baseline of each node in each branch of the transmission line R is adjusted proportionally according to the power consumption ratio. If the selected transmission line R is a branch line, the trunk line to which the transmission line R belongs is adjusted by the same amount.

[0085] Assess the suitability of the adjusted power fittings. If the suitability is improved after adjustment, retain the adjustment results.

[0086] More specifically, the adjusted fitness is as follows:

[0087] Let the power fitting that exceeds the set fatigue value be power fitting 1;

[0088] After adjusting the power supply baseline of the transmission line, the fatigue values ​​of the power fittings 1 that have changed in fatigue value are summed and averaged to obtain parameter 1;

[0089] The spatial correlation of power fitting 1 is calculated. If any two power fittings 1 belong to the same branch or trunk, the count is 0; if any two power fittings 1 belong to the same branch and trunk, the count is 0; if any two power fittings 1 belong to different branches, the count is 1. The spatial correlation is counted and accumulated for any two power fittings 1 to obtain the spatial correlation parameter 2.

[0090] The fitness evaluation process is as follows:

[0091] The parameters 1 and 2 are calculated. When the decrease in parameter 1 is greater than K and parameter 2 is greater than the change in parameter 2 minus H (the change in parameter 2 can be greater than 0 or equal to 0, but cannot be less than -H), the fitness is judged to be improved. Here, H represents the adjustment threshold of parameter 2 and K represents the judgment threshold of parameter 1.

[0092] "Parameter 1" (average fatigue level) reflects the change in fatigue state before and after line adjustment, quantitatively assessing the actual impact of line power baseline adjustment on the fatigue of power fittings. The degree of fatigue change clarifies the adaptive adjustment effect of power load. Simultaneously, "Parameter 2" (spatial correlation index) is introduced to determine whether there are spatial clustering characteristics in concentrated anomalies of fatigue changes, paying particular attention to the correlation between anomalies between different branches. When fatigue anomalies cross different branches, it indicates that there may be structural or load distribution problems in the overall line, requiring further analysis and adjustment. Therefore, the combination of "Parameter 1" and "Parameter 2" comprehensively reflects the effectiveness of the adjustment scheme, optimizing the overall fatigue state of power fittings and identifying concentrated anomaly areas, thereby improving the accuracy and intelligence of the safe and stable operation of the power grid.

[0093] Step 4: Repeat steps 1 to 3 until the maximum number of iterations is reached or the fitness no longer improves. Output the final adjustment results and the vibration fatigue assessment results of the power fittings.

[0094] When outputting the final adjustment results and the vibration fatigue assessment results of the power fittings, upper and lower limits are set for the adjustment amount of each transmission line branch or trunk.

[0095] If the adjustment amount of a certain transmission line branch or trunk exceeds the corresponding upper or lower limit, it is judged as a line abnormality and the line is marked in the dynamic topology network.

[0096] After the adjustments are completed, historical data is incorporated. Based on the updated historical data, a preset function f(I) is applied to each node on each line. uAdjustments are made to adapt to new historical data, ensuring that the power consumption baseline of the node more closely matches the actual operating conditions. Data feedback after each adjustment enables adaptive dynamic optimization, thereby improving the accuracy and adaptability of node vibration fatigue prediction. This allows subsequent assessments to automatically adapt to changes in line load, environmental conditions, and hardware aging, achieving more accurate, reliable, and long-term effective fatigue monitoring and early warning.

[0097] It's important to understand that if a node is operating on multiple lines simultaneously, the power baseline of that node is determined by the Q value on each line. U We obtain the summation.

[0098] This step introduces the average fatigue value (parameter 1) and spatial correlation (parameter 2) to jointly construct an fitness assessment mechanism, which can accurately evaluate the optimization effect of line adjustment on fatigue state, ensuring the scientific nature and effectiveness of the adjustment. Simultaneously, an iterative mechanism is designed to ensure the adaptive selection of the optimal strategy, and upper and lower limit constraints are introduced to identify abnormal line states, thereby achieving intelligent and efficient centralized vibration fatigue anomaly identification and early warning intervention, improving the safety and reliability of power facility operation.

[0099] When outputting the final adjustment results, the electrical fittings that need to be replaced are determined based on the final vibration fatigue assessment results.

[0100] In this embodiment, the fatigue of each power fitting is evaluated based on the adjusted power consumption baseline, and the power fittings that need to be replaced are output.

[0101] The actual output is the prediction result of the last time the power baseline was adjusted using the neural network.

[0102] Within the nodes, electrical fittings that need to be replaced are marked; the markings on the marked nodes and lines are visualized, and alarm information is generated based on the marking information to issue early warning reminders to operators.

[0103] In the visualization interface of the dynamic topology network, the abnormal status of nodes and lines is displayed intuitively using different colors or special markers (e.g., red indicates abnormal nodes, green indicates normal nodes). When a marked node or line appears, alarm information is automatically generated, including but not limited to detailed information such as the abnormal node number, the line it belongs to, the current fatigue value, and whether the threshold has been exceeded. The generated alarm information is sent to the power operation and maintenance system platform in real time via IoT communication technology, and sound, vibration, pop-up window, or message push reminders are sent to the corresponding maintenance personnel's terminals. Finally, the handling status and log of this alarm are recorded for subsequent operation and maintenance analysis.

[0104] In addition, the present invention also provides an Internet of Things-based vibration fatigue monitoring and early warning system for power fittings, comprising the following modules:

[0105] Data acquisition module: used to acquire vibration data of power fittings;

[0106] Dynamic Topology Network Building Module: Used to build dynamic topology networks for power fittings;

[0107] Evaluation and Adjustment Module: This module is used to evaluate the vibration fatigue of individual power fittings and reflect the results in the dynamic topology network. By analyzing the vibration fatigue of the group, it adjusts the vibration fatigue evaluation results of individual power fittings.

[0108] Output module: Outputs the final adjustment results and the vibration fatigue assessment results of the power fittings.

[0109] The embodiments described above are merely one implementation method of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things, characterized in that, Includes the following steps: Step 1: Obtain vibration data of power fittings; Step 2: Construct the dynamic topology network of power fittings: The location of each power fitting is taken as a node, and the connection between different nodes is constructed by connecting the power transmission lines; When multiple nodes exist at the same location, the relationships between these nodes are analyzed: If multiple nodes operate on different transmission lines, they should be accounted for separately as different nodes. If a node can function on multiple transmission lines simultaneously, it is accounted for separately as a special node. If multiple nodes are operating on the same transmission line, then the multiple nodes at the same location are merged into a single node with superimposed different states, represented as follows: ,in, This represents the nth state of the i-th node, where each state represents the vibration data of a power fitting. Step 3: After performing vibration fatigue assessment on individual power fittings, the results are reflected in the dynamic topology network. Through analysis of the group vibration fatigue, the vibration fatigue assessment results of individual power fittings are adjusted. Step 3-1: Based on the power consumption of each transmission line, set the power consumption baseline for each node; Step 3-2: Construct a vibration fatigue assessment model for power fittings and conduct vibration fatigue assessment on individual power fittings; Step 3-3: Based on the vibration fatigue assessment results of individual power fittings, adjust the power supply baseline of the transmission line; Step 4: Repeat steps 1 to 3 until the maximum number of iterations is reached or the fitness no longer improves. Output the final adjustment results and the vibration fatigue assessment results of the power fittings. The fitness specifically refers to: Let the power fitting that exceeds the set fatigue value be power fitting 1; After adjusting the power supply baseline of the transmission line, the fatigue values ​​of the power fittings 1 that have changed in fatigue value are summed and averaged to obtain parameter 1; The spatial correlation of power fitting 1 is calculated. If any two power fittings 1 belong to the same branch or trunk, the count is 0; if any two power fittings 1 belong to the same branch and trunk, the count is 0; if any two power fittings 1 belong to different branches, the count is 1. The spatial correlation is counted and accumulated for any two power fittings 1 to obtain the spatial correlation parameter 2. The fitness evaluation process is as follows: The parameters 1 and 2 are calculated. When the decrease in parameter 1 is greater than K and parameter 2 is greater than the difference between parameter 2 and H before adjustment, the fitness is judged to be improved. Here, H represents the adjustment threshold of parameter 2 and K represents the judgment threshold of parameter 1.

2. The method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things according to claim 1, characterized in that, When obtaining vibration data of power fittings in step 1, a vibration sensor is placed on the surface of the power fittings or transmission lines. When the fittings vibrate due to wind, line load or other external forces, the vibration sensor outputs the vibration data of the power fittings. The vibration data of the power fittings includes vibration acceleration data, vibration displacement data, and vibration spectrum data.

3. The method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things according to claim 1, characterized in that, The power consumption baseline of each node in step 3-1 is used to represent the workload of that node from the last replacement of the power fittings to the current moment: ； Where U represents the time interval from the last replacement of the power fittings at the node to the current time; Q_U represents the calculated power consumption baseline of the node within the time interval U. This indicates the current intensity in the transmission line. This represents the transmission line coefficient.

4. The method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things according to claim 1, characterized in that, The vibration fatigue assessment model in step 3-2 is constructed using a deep feedforward neural network and trained using a dataset. The inputs to the vibration fatigue assessment model are the cumulative fatigue level of the transmission line when the power fittings were last replaced, the power supply baseline, and the power fitting model. The output is the fatigue level of the node at the current moment.

5. The method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things according to claim 1, characterized in that, In step 3-3, based on the vibration fatigue assessment results of individual power fittings, the power supply baseline of the transmission line is adjusted, specifically as follows: Based on the fatigue value of electrical fittings on a single transmission line in the dynamic topology network, if the number of electrical fittings exceeding the set fatigue value on a single transmission line exceeds a preset proportion, the power consumption baseline of that transmission line will be adjusted. The power consumption baseline of each node in the transmission line R is adjusted by a step size. If the selected transmission line R is a trunk line, the power consumption baseline of each node in each branch of the transmission line R is adjusted proportionally according to the power consumption ratio. If the selected transmission line R is a branch line, the trunk line to which the transmission line R belongs is adjusted by the same amount. Evaluate the adjusted fitness; if the adjusted fitness improves, retain the adjustment result.

6. The method for monitoring and early warning of vibration fatigue in power fittings based on the Internet of Things according to claim 5, characterized in that, In step 4, when outputting the final adjustment result and the vibration fatigue assessment result of the power fittings, upper and lower limits are set for the adjustment amount of each power transmission line branch or trunk. If the adjustment amount of a certain transmission line branch or trunk exceeds the corresponding upper or lower limit, it is judged as a line abnormality and the line is marked in the dynamic topology network. When outputting the final adjustment results, the electrical fittings that need to be replaced are determined based on the final vibration fatigue assessment results.

7. A vibration fatigue monitoring and early warning system for power fittings based on the Internet of Things, characterized in that, Includes the following modules: Data acquisition module: used to acquire vibration data of power fittings; Dynamic Topology Network Building Module: Used to build dynamic topology networks for power fittings. The location of each power fitting is taken as a node, and the connection between different nodes is constructed by connecting the power transmission lines; When multiple nodes exist at the same location, the relationships between these nodes are analyzed: If multiple nodes operate on different transmission lines, they should be accounted for separately as different nodes. If a node can function on multiple transmission lines simultaneously, it is accounted for separately as a special node. If multiple nodes are operating on the same transmission line, then the multiple nodes at the same location are merged into a single node with superimposed different states, represented as follows: ,in, This represents the nth state of the i-th node, where each state represents the vibration data of a power fitting. The evaluation and adjustment module is used to evaluate the vibration fatigue of individual power fittings and reflect this evaluation in the dynamic topology network. Through analysis of the overall vibration fatigue, it adjusts the vibration fatigue evaluation results of individual power fittings, including: Based on the power consumption of each transmission line, set the power consumption baseline for each node; A vibration fatigue assessment model for power fittings is constructed to conduct vibration fatigue assessment on individual power fittings. Based on the vibration fatigue assessment results of individual power fittings, the power supply baseline of the transmission line is adjusted; Output module: Used to output the final adjustment results and vibration fatigue assessment results of power fittings when the number of evaluations and adjustments reaches the maximum number of iterations or the fitness no longer improves; The fitness specifically refers to: Let the power fitting that exceeds the set fatigue value be power fitting 1; After adjusting the power supply baseline of the transmission line, the fatigue values ​​of the power fittings 1 that have changed in fatigue value are summed and averaged to obtain parameter 1; The spatial correlation of power fitting 1 is calculated. If any two power fittings 1 belong to the same branch or trunk, the count is 0; if any two power fittings 1 belong to the same branch and trunk, the count is 0; if any two power fittings 1 belong to different branches, the count is 1. The spatial correlation is counted and accumulated for any two power fittings 1 to obtain the spatial correlation parameter 2. The fitness evaluation process is as follows: The parameters 1 and 2 are calculated. When the decrease in parameter 1 is greater than K and parameter 2 is greater than the difference between parameter 2 and H before adjustment, the fitness is judged to be improved. Here, H represents the adjustment threshold of parameter 2 and K represents the judgment threshold of parameter 1.

Images