Beidou-based high-altitude power transmission line tower high-precision monitoring method and system
By installing sensor nodes and inertial monitoring data on high-altitude transmission line towers, combining Beidou positioning and adaptive algorithms, an abnormality detection model is built, which solves the problem of insufficient monitoring accuracy and real-time performance of transmission line towers in high-altitude environments, and realizes centimeters Level positioning accuracy and efficiency of abnormal detection.
Patent Information
- Application Number
- CN202410887365.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-15
AI Technical Summary
The existing transmission line tower monitoring system faces signal occlusion, cumulative error, insufficient diversified anomaly detection capabilities, and challenges in high-altitude environments, making it difficult to achieve high-precision, real-time and comprehensive monitoring.
Using the high-precision monitoring method of high-altitude transmission line towers based on Beidou, sensor nodes are installed at key structural points of the transmission line tower, combined with inertial monitoring data, an abnormality detection model is constructed, and dynamic monitoring is carried out using the learning layer, inference layer and decision-making layer. Abnormal state detection and differential correction is carried out through improved gamma filters and adaptive algorithms to achieve dynamic positioning accuracy at the centimeter level.
It has achieved comprehensive monitoring of high-altitude transmission line towers, improved monitoring accuracy, reliability and real-time, overcome the challenges of complex environments, and provided strong technical support for the safe and stable operation of the power system.
Smart Images

Figure CN118962726A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power equipment monitoring, and in particular to a Beidou-based high-precision monitoring method and system for high-altitude transmission line towers. Background Art
[0002] With the rapid development of power systems and the continuous expansion of transmission networks, the safe operation of transmission towers has become the focus of attention in the power industry. Especially in high-altitude areas, transmission towers face multiple challenges such as complex terrain, harsh climatic conditions, and geological disasters. Traditional transmission tower monitoring methods mainly rely on manual inspections and simple sensor systems, which face many limitations in high-altitude environments, such as insufficient monitoring accuracy, poor real-time performance, and limited coverage. In recent years, with the full operation of the Beidou satellite navigation system and the advancement of inertial measurement technology, new technical support has been provided for transmission tower monitoring. However, how to effectively integrate these advanced technologies to achieve high-precision, real-time, and comprehensive monitoring of high-altitude transmission towers is still a technical problem that needs to be solved urgently.
[0003] The existing transmission tower monitoring system has many shortcomings in high-altitude environment applications. First, a single Beidou positioning system may face signal blocking or multipath effects in complex terrain and severe weather conditions, resulting in reduced accuracy in tower position and attitude monitoring. Secondly, traditional inertial measurement units (IMUs) are prone to cumulative errors during long-term use, affecting the reliability of the tower dynamic characteristics monitoring results. Furthermore, existing anomaly detection algorithms are often designed for specific types of tower failures and lack the ability to comprehensively analyze multi-source data. They are difficult to adapt to the diverse abnormal conditions that transmission towers may face in high-altitude environments, such as tilt, vibration, and structural deformation. In addition, the existing system also faces challenges in data transmission and energy supply, making it difficult to achieve long-term stable operation in remote areas and unable to provide reliable guarantees for the continuous monitoring of transmission towers. Summary of the invention
[0004] In view of the problems existing in the existing transmission line tower monitoring technology, the present invention is proposed.
[0005] Therefore, the problem to be solved by the present invention is that satellite positioning technology provides the possibility for remote monitoring, but the existing monitoring methods based on satellite navigation systems such as GPS are often affected by factors such as atmospheric delay and multipath effect in high altitude areas, making it difficult to achieve centimeter-level high-precision positioning.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In a first aspect, an embodiment of the present invention provides a high-precision monitoring method for high-altitude transmission line towers based on Beidou, which includes:
[0008] Install sensor nodes at key structural points of the transmission line tower, and collect data based on the sensor nodes; the data includes transmission line tower data and inertial monitoring data; the transmission line tower data includes position data and motion feature data;
[0009] Processing the transmission line tower data and integrating the inertial monitoring data to obtain transmission line tower dynamic monitoring data;
[0010] An abnormality detection model is constructed based on the dynamic monitoring data to realize abnormal state monitoring of transmission line towers.
[0011] As a preferred solution of the Beidou-based high-precision monitoring method for high-altitude transmission line towers of the present invention, wherein: the anomaly detection model includes a learning layer, a reasoning layer and a decision layer;
[0012] The learning layer determines the abnormality score of the transmission line tower according to the dynamic monitoring data of the transmission line tower, and the objective function is shown as follows:
[0013]
[0014] Among them, w is the weight vector of each monitoring index of the transmission line tower, ξ i is the allowable error of the tower state deviating from the normal range, ρ is the threshold for abnormal state judgment, V is the dynamic monitoring data of the transmission line tower, γ is the weight coefficient of Beidou positioning data and IMU data in the fusion process, which is dynamically adjusted according to different weather conditions, N is the total number of monitoring points on the transmission line, and ν is the control parameter of the model's sensitivity to abnormalities.
[0015] As a preferred solution of the Beidou-based high-precision monitoring method for high-altitude transmission line towers of the present invention, wherein: the reasoning layer determines the abnormality type according to the dynamic monitoring data of the transmission line and the inertial monitoring data, and includes a logic rule base and a reasoning engine;
[0016] The logic rule base uses the processed transmission line tower data and the inertial monitoring data to capture the abnormal state of the transmission line tower, as shown in the following formula:
[0017]
[0018] R i : If θ is And f is And a is Then y is B i
[0019] Among them, θ is the inclination of the tower, f is the vibration frequency of the tower, a is the vibration amplitude of the transmission line, is the fuzzy set of input variables, B iis the fuzzy set of output variables.
[0020] As a preferred solution of the Beidou-based high-precision monitoring method for high-altitude transmission line towers of the present invention, wherein: the reasoning engine includes fuzzification, rule evaluation and defuzzification;
[0021] The fuzzification is shown as follows:
[0022]
[0023] in, is the membership function of the tower inclination θ, a θ is the slope parameter of the tower inclination, reflecting the sensitivity to the change of the tower inclination, c θ is the center value of the tower inclination, is the membership function of the tower vibration frequency f, a f is the slope parameter of the tower vibration frequency, c f is the center value of the tower vibration frequency, indicating the normal vibration frequency range, is the membership function of the vibration amplitude a of the transmission line, a a is the slope parameter of the vibration amplitude of the transmission line, c a is the central value of the vibration amplitude of the transmission line;
[0024] The rule evaluation is as follows:
[0025]
[0026] in, is the membership function of rule Ri;
[0027] The defuzzification is shown as follows:
[0028]
[0029] Among them, θ is the inclination of the tower, f is the vibration frequency of the tower, a is the vibration amplitude of the transmission line, y is the output result, y i is the output of rule Ri.
[0030] As a preferred solution of the Beidou-based high-precision monitoring method for high-altitude transmission line towers of the present invention, the processing of the transmission line tower data includes performing differential correction on the position data, as shown in the following formula:
[0031]
[0032] in, is the estimated value at the current moment, x(k) is the observed value at the current moment, a is the filter coefficient, μ1, β1, σ1 are the correction parameters, and fatm (k) is the atmospheric correction function.
[0033] As a preferred solution of the Beidou-based high-precision monitoring method for high-altitude transmission line towers of the present invention, the processing of the transmission line tower data also includes dynamically adjusting parameters of the position data after differential correction, as shown in the following formula:
[0034] w corr (k+1)=w(k)+μe(k)x(k)+g sat (k)+h corr (k)
[0035]
[0036] h corr =β3·log(1+γ·|e(k)|)
[0037] Among them, w k is the weight vector, w corr (k+1) is the modified weight vector, μ is the step size factor, e k is the error signal, x(k) is the input vector, s(k) is the satellite combined signal strength, β2, β3, γ are correction parameters, g sat (k) is the satellite combination weight function, h corr Dynamic adjustment function for differential correction parameters.
[0038] As a preferred solution of the Beidou-based high-precision monitoring method for high-altitude transmission line towers of the present invention, wherein: integrating the inertial monitoring data includes state update and prediction and correction prediction;
[0039] The state update and prediction are shown as follows:
[0040]
[0041] Among them, X k|k-1 is the state prediction at time k based on time k-1, including the position, posture and dynamic information of the transmission tower, F k-1 is the state transfer matrix, B k-1 is the control input matrix, u k-1 is the control input vector, G is the influence matrix of acceleration information on the state, a k is the acceleration information of inertial monitoring data, P k|k -1 is the prediction covariance matrix, Q k-1 is the process noise covariance matrix.
[0042] In a second aspect, an embodiment of the present invention provides a high-precision monitoring system for high-altitude transmission line towers based on Beidou, which includes:
[0043] A data acquisition module, used to install sensor nodes at key structural points of a transmission line tower, and to collect data based on the sensor nodes; the data includes transmission line tower data and inertial monitoring data; the transmission line tower data includes position data and motion feature data;
[0044] A data processing module, used to process the transmission line tower data and integrate the inertial monitoring data to obtain dynamic monitoring data of the transmission line tower;
[0045] The abnormality judgment module is used to process the transmission line tower data and integrate the inertial monitoring data to obtain dynamic monitoring data of the transmission line tower.
[0046] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned Beidou-based high-precision monitoring method for high-altitude transmission line towers.
[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the above-mentioned Beidou-based high-precision monitoring method for high-altitude transmission line towers is implemented.
[0048] The beneficial effect of the present invention is that by installing multifunctional sensor nodes with integrated Beidou receivers on transmission towers, combined with self-powered systems and low-power wide area networks, comprehensive monitoring of high-altitude transmission towers is achieved. The solution constructs a regional differential positioning system, uses improved gamma filters and adaptive algorithms for differential correction, and combines IMU information through innovative data fusion algorithms to achieve centimeter-level dynamic positioning accuracy. In addition, the solution also proposes a three-layer anomaly detection framework that integrates high-precision positioning information, including a spatiotemporal statistical learning layer, a motion feature rule reasoning layer, and a multimodal decision fusion layer, which effectively improves the sensitivity and accuracy of anomaly detection. This comprehensive monitoring method not only overcomes the challenges brought by the complex environment in high-altitude areas, but also significantly improves the accuracy, reliability and real-time performance of transmission line monitoring, providing strong technical support for the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:
[0050] Figure 1 This is a flow chart of the high-precision monitoring method for high-altitude transmission line towers based on Beidou. DETAILED DESCRIPTION
[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0057] Example 1
[0058] Reference Figure 1 , which is the first embodiment of the present invention, provides a high-precision monitoring method for high-altitude transmission line towers based on Beidou, comprising:
[0059] First, a comprehensive analysis of the transmission tower is conducted to determine key structural points, such as the top of the tower, crossarms, tower legs, etc. At these locations, multifunctional sensor nodes integrated with micro Beidou receivers will be installed. These sensor nodes can not only provide accurate location information, but also measure multiple parameters such as tilt angle, vibration frequency, stress and strain, etc.
[0060] In order to ensure that these devices can work stably for a long time, an innovative self-powered system is designed. The system mainly uses solar panels and small wind turbines, and optimizes the configuration according to the on-site environmental conditions. In sunny areas, solar energy is the main source of energy; in windy areas, the proportion of wind energy utilization is increased.
[0061] At the same time, the use of efficient energy management chips and large-capacity energy storage devices ensures that the equipment can continue to work for several days under adverse weather conditions. Finally, a low-power wide-area network based on LoRa or NB-IoT technology is built to achieve reliable communication between sensor nodes and base stations. This network adopts a mesh topology structure, has self-organization and self-repair capabilities, and can ensure real-time data transmission under complex terrain conditions.
[0062] Preferably, reliable communication between the sensor node and the base station is as follows:
[0063] It should be noted that the first mode is the LoRa mode and the second mode is the NB-IoT mode.
[0064] First, each sensor node is equipped with a dual-mode communication module that can adaptively select the best communication method in different situations. Under normal circumstances, the node gives priority to the low-power LoRa technology, which can achieve long-distance communication of 5-15 kilometers. The node will periodically (such as every 15 minutes) send a data packet to the nearest repeater or base station, containing information such as location, tilt, vibration, etc. After receiving the data, the repeater will perform preliminary processing and compression, and then pass the data to the main base station through multi-hop routing.
[0065] In case of communication obstacles, the system will automatically switch to NB-IoT mode and use the cellular network to communicate directly with the remote server to ensure the continuity of data transmission. In addition, two-way communication function is also realized: the base station can send control instructions to the node, such as adjusting the sampling frequency, updating the firmware, etc. To improve reliability, the system uses time synchronization and data encryption technology, and introduces a network topology self-optimization algorithm, which can dynamically adjust the routing strategy according to the communication quality and energy consumption. In an emergency, if abnormal vibration is detected, the node will immediately start the high-priority transmission mode to ensure that the alarm information can be delivered to the monitoring center within seconds.
[0066] If a communication obstacle is encountered, it will automatically switch to NB-IoT mode and use the network to communicate directly with the remote server. In an emergency, if the node is closest to the main base station and can communicate normally, the LoRa mode will be used. If it is determined that the transmission time of the LoRa mode is higher than that of the NB-IoT mode, it will switch to the NB-IoT mode. If the LoRa mode cannot communicate normally or the node is far away from the host station or the base station is damaged, the NB-IoT mode will be used directly.
[0067] Furthermore, in order to cope with the challenges of complex terrain of transmission towers in high-altitude areas to positioning accuracy, a regional differential positioning system for transmission towers was constructed. These enhancement stations are strategically distributed at key structural points along the transmission towers to continuously receive and analyze Beidou satellite signals.
[0068] By calculating and broadcasting differential correction data in real time, the system significantly improves the positioning accuracy of the receiving terminals installed on the transmission line towers. This high-precision positioning capability is essential for accurately monitoring the tiny displacement and tilt changes of transmission line towers, especially in geologically unstable mountainous areas.
[0069] Moreover, taking into account the changeable weather conditions in high-altitude areas, the ground-based augmentation station network adopts an adaptive algorithm to dynamically adjust the correction parameters according to the real-time satellite combination and atmospheric conditions, ensuring that stable and high-precision positioning data can be provided to the transmission tower monitoring system under various severe weather conditions.
[0070] Preferably, in order to realize real-time calculation and broadcast of differential correction data, the conventional gamma filter is improved to correct the atmosphere, then:
[0071]
[0072] in, is the estimated value at the current moment, x(k) is the observed value at the current moment, a is the filter coefficient, μ1, β1, σ1 are the correction parameters, and f atm (k) is the atmospheric correction function.
[0073] Preferably, in order to ensure a stable high-precision positioning effect under various weather conditions, the commonly used adaptive algorithm is dynamically adjusted for differential correction parameters, and satellite combination weights are introduced, as follows:
[0074] w corr (k+1)=w(k)+μe(k)x(k)+g sat (k)+h corr (k)
[0075]
[0076] h corr =β3·log(1+γ·|e(k)|)
[0077] Among them, w k is the weight vector, w corr (k+1) is the modified weight vector, μ is the step size factor, e k is the error signal, x(k) is the input vector, s(k) is the satellite combined signal strength, β2, β3, γ are correction parameters, g sat (k) is the satellite combination weight function, h corr Dynamic adjustment function for differential correction parameters.
[0078] Furthermore, in order to achieve accurate monitoring of high-altitude transmission towers, a data fusion algorithm is used, which makes full use of the angular velocity and acceleration information provided by the IMU sensors installed at key positions on the towers, and deeply integrates it with the data of the Beidou satellite positioning system. This fusion not only achieves the smoothing and interpolation of the Beidou positioning results, but also greatly improves the performance of the overall monitoring system.
[0079] Specifically, this fusion method significantly improves the continuity and reliability of transmission tower position monitoring. Even in complex high-altitude environments, such as when mountains block Beidou satellite signals for a short period of time, the system can still rely on IMU data to maintain high-precision positioning.
[0080] Preferably, in order to achieve high-precision dynamic monitoring of high-altitude transmission line towers, the data provided by the Beidou satellite positioning system is processed to achieve centimeter-level dynamic positioning accuracy, thereby accurately capturing the tiny displacement and attitude changes of the transmission line towers, specifically as follows:
[0081] State update and prediction This is the prediction step of the Kalman filter. Combined with the angular velocity information provided by the IMU sensor installed on the tower, the system continuously estimates the motion state and posture of the transmission tower and predicts the state at the current moment, as shown in the following formula:
[0082]
[0083] Among them, X k|k-1 is the state prediction at time k based on time k-1, including the position, posture and dynamic information of the transmission tower, F k-1 is the state transfer matrix, B k-1 is the control input matrix, u k-1 is the control input vector, G is the influence matrix of acceleration information on the state, a k The acceleration information provided by IMU, P k|k-1 is the prediction covariance matrix, Q k-1 is the process noise covariance matrix.
[0084] The measurement update is shown in the following formula, which is the update step of the Kalman filter. It uses the external observation data provided by the Beidou satellite positioning system to correct the predicted state and update the predicted state.
[0085]
[0086] Among them, K k is the Kalman gain, H k is the observation matrix, R k is the observation noise covariance matrix, X k|k is the state update at time k, z k is the observation vector, P k|k is the updated covariance matrix.
[0087] The integration of IMU (inertial measurement unit) and BeiDou system can obtain comprehensive positioning results of monitoring equipment, which is particularly suitable for monitoring dynamic changes of transmission lines, such as tower vibration, wire swing, etc. IMU can capture these tiny dynamic changes. And when BeiDou signal is temporarily blocked (such as mountain occlusion), IMU data can supplement positioning information in the short term and maintain continuous position tracking.
[0088] Furthermore, by integrating the data of IMU sensors installed on high-altitude transmission line towers with the information of the Beidou satellite positioning system, high-precision dynamic monitoring of the towers was achieved, and a three-layer anomaly detection framework integrating high-precision positioning information was constructed.
[0089] For example, in a feasible embodiment, the three-layer anomaly detection framework integrating high-precision positioning information is as follows:
[0090] The three-layer anomaly detection framework includes a spatiotemporal statistical learning layer, a motion feature rule reasoning layer, and a multimodal decision fusion layer.
[0091] Using the improved spatiotemporal single-class support vector machine (ST-OCSVM) algorithm, the high-precision position, attitude and dynamic information of IMU and Beidou are integrated into the statistical model of normal operating status. This enables the system to capture tiny spatial displacements and attitude changes, and improves the sensitivity of anomaly detection. As follows:
[0092] The objective function of the improved spatiotemporal single-class support vector machine (ST-OCSVM) algorithm is as follows:
[0093]
[0094] Among them, w is the weight vector of each monitoring index of the transmission line tower, ξ i is the allowable error of the tower state deviating from the normal range, ρ is the threshold for abnormal state judgment, considering the particularity of the high-altitude environment, V is the high-precision dynamic information of the tower obtained after fusing Beidou positioning and IMU data, including position, attitude and vibration characteristics, γ is the weight coefficient of Beidou positioning data and IMU data in the fusion process, which is dynamically adjusted according to different weather conditions, N is the total number of monitoring points on the transmission line, and ν is the control parameter of the model's sensitivity to abnormalities.
[0095] The constraints are as follows:
[0096] w·Φ(x i )+v·Ψ(y i )≥ρ-ξ i
[0097] ξ i ≥0,i=1,2,…,N
[0098] Among them, Φ(x) is the function that maps the original monitoring data to the high-dimensional feature space, and Ψ(y) is the function that maps the IMU and Beidou fusion information to the unified feature space.
[0099] Use spatiotemporal statistical characteristics to model the fused state and improve the system's sensitivity to small changes:
[0100] z i =MLP(x i ,y i )
[0101]
[0102] q=ST-OCSVM(z i )
[0103] Among them, MLP is a multi-layer perceptron, which is used to fuse position and posture information. i is the state after spatiotemporal smoothing, and q is the anomaly detection result.
[0104] Combining the above improved ST-OCSVM with the spatiotemporal statistical learning layer, the spatiotemporal single-class support vector machine algorithm is as follows:
[0105]
[0106] subjectto:
[0107] w·Φ(x i )+v·Ψ(y i )≥ρ-ξ i ,ξ i ≥0,i=1,2...,N
[0108] where:
[0109] z i =σ(W2(σ(W1[x i ,y i ]+b1))+b2)
[0110]
[0111] q=ST-OCSVM(z i )
[0112] Among them, w is the weight vector of each monitoring index of the transmission line tower, ξ i is the allowable error of the tower state deviating from the normal range, ρ is the threshold for abnormal state judgment, considering the particularity of the high-altitude environment, V is the high-precision dynamic information of the tower obtained after fusing Beidou positioning and IMU data, including position, attitude and vibration characteristics, γ is the weight coefficient of Beidou positioning data and IMU data in the fusion process, which is dynamically adjusted according to different weather conditions, Φ(x) is the function of mapping the original monitoring data to a high-dimensional feature space, Ψ(y) is the function of mapping the fusion information of IMU and Beidou to a unified feature space, MLP is a multi-layer perceptron used to fuse the tower position and attitude information, s i is the tower status after considering the temporal and spatial correlation, q is the anomaly detection result, σ() is the activation function, W1, W2 are the MLP weight matrices, b1, b2 are bias terms, N is the total number of monitoring points on the transmission line, and ν is the control parameter of the model's sensitivity to anomalies.
[0113] Furthermore, based on expert knowledge and precise motion data provided by IMU, an enhanced fuzzy logic rule base for high-altitude transmission lines is constructed. This innovative rule base makes full use of the high-precision motion data provided by the IMU sensors installed on the transmission towers and the precise location information of the Beidou satellite positioning system, thereby achieving a comprehensive capture of abnormal conditions of transmission lines in high-altitude environments.
[0114] Specifically, the enhanced fuzzy logic rule base is defined as follows:
[0115]
[0116] R i : If θ is And f is And a is Then y is B i
[0117] Among them, θ is the inclination of the tower, f is the vibration frequency of the tower, and a is the vibration amplitude of the transmission line. The amplitude of the transmission line vibration is calculated from the acceleration data of the IMU. is the fuzzy set of input variables, B i is the fuzzy set of output variables.
[0118] The improved fuzzy inference engine includes fuzzification, rule evaluation and defuzzification, specifically:
[0119] Fuzzification:
[0120]
[0121] Rule Evaluation:
[0122]
[0123] Defuzzification:
[0124]
[0125] In summary, the fuzzy logic rule base and inference engine are as follows:
[0126]
[0127] in, is the membership function of the tower inclination θ, a θ is the slope parameter of the tower inclination, reflecting the sensitivity to the change of the tower inclination, c θ is the center value of the tower inclination, is the membership function of the tower vibration frequency f, a f is the slope parameter of the tower vibration frequency, c f is the center value of the tower vibration frequency, indicating the normal vibration frequency range, is the membership function of the vibration amplitude a of the transmission line, a a is the slope parameter of the vibration amplitude of the transmission line, c a is the center value of the vibration amplitude of the transmission line, For rule R iThe membership function is: θ is the inclination of the tower, f is the vibration frequency of the tower, a is the vibration amplitude of the transmission line, y is the output result, y i For rule R i Output.
[0128] Furthermore, the multimodal decision fusion layer intelligently fuses traditional sensor data with high-precision positioning data. This layer combines the outputs of the first two layers, taking into account spatial correlation and time series characteristics, to give more accurate anomaly scores and risk levels.
[0129] Specifically, the anomaly score is received from the spatiotemporal statistical learning layer, the anomaly type and its confidence are received from the motion feature rule inference layer, and the recognition framework Θ = {normal, low risk, medium risk, high risk} is defined to assign a basic probability assignment (BPA) to each input.
[0130] In the BPA allocation process, for the spatiotemporal statistical learning layer output: m1(normal)=1-S1, m1(high risk)=S1, where S1 reflects the abnormality of the tower status.
[0131] Furthermore, specific abnormality types are identified to identify Ti-type abnormalities and their confidence levels Ci, including tilt abnormalities, vibration abnormalities, displacement abnormalities and stress abnormalities, and then each abnormality type Ti is assigned to the corresponding risk level: m2 (corresponding risk level) = Ci, m2 (Θ) = 1-ΣCi.
[0132] Use Dempster combination rule to fuse m1 and m2 to calculate the trust and likelihood of each risk level. Specifically, trust calculation: Calculation of likelihood: Pl(A)=1-Bel(ā).
[0133] Furthermore, a final risk level determination is performed, risk level = argmax(Bel(A) + Pl(A)), and the result obtained is the current overall risk status of the tower.
[0134] Abnormal score = w1*S1+w2*max(Ci)+w3*Bel(selected risk level)
[0135] Among them, w1 is the weight of the overall abnormal state, w2 is the weight of the most serious specific abnormality, and w3 is the weight of the comprehensive risk assessment to quantify the abnormal state of the tower.
[0136] The final output report is generated, including the final risk level describing the current overall safety status of the tower, the abnormal score quantifying the tower risk indicators and the key contributing factors for specific problems, such as severe tilt, abnormal vibration, etc.
[0137] In summary, the above steps judge the abnormal status of transmission line towers, taking into account the overall status of the towers and the specific abnormality types, and give a comprehensive evaluation through the evidence theory fusion method, which effectively identifies and evaluates various abnormal situations that transmission line towers may face in high-altitude environments, providing an important basis for timely maintenance and risk prevention.
[0138] Furthermore, this embodiment also provides a high-precision monitoring system for high-altitude transmission line towers based on Beidou, including:
[0139] A data acquisition module, used to install sensor nodes at key structural points of a transmission line tower, and to collect data based on the sensor nodes; the data includes transmission line tower data and inertial monitoring data; the transmission line tower data includes position data and motion feature data;
[0140] A data processing module, used to process the transmission line tower data and integrate the inertial monitoring data to obtain dynamic monitoring data of the transmission line tower;
[0141] The abnormality judgment module is used to process the transmission line tower data and integrate the inertial monitoring data to obtain dynamic monitoring data of the transmission line tower.
[0142] This embodiment also provides a computer device, which is suitable for the high-altitude transmission line tower high-precision monitoring method based on Beidou, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the high-altitude transmission line tower high-precision monitoring method based on Beidou as proposed in the above embodiment.
[0143] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0144] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for high-precision monitoring of high-altitude transmission line towers based on Beidou as proposed in the above embodiment is implemented.
[0145] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
[0146] Example 2
[0147] This is the second embodiment of the present invention. This embodiment provides a high-precision monitoring method for high-altitude transmission line towers based on Beidou. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0148] To verify the effectiveness of the Beidou-based high-precision monitoring method for high-altitude transmission line towers, a six-month field test was conducted on a transmission line on the Qinghai-Tibet Plateau. Six typical high-altitude transmission line towers were selected, ranging from 3,500 meters to 5,200 meters above sea level, covering a variety of terrain and climate conditions in the plateau area.
[0149] First, a comprehensive analysis was conducted on each transmission tower to identify 15 key structural points, including the tower top, crossarms and tower legs. Multifunctional sensor nodes with integrated micro Beidou receivers were installed at these locations. Each node was equipped with a high-precision tilt sensor, a three-axis accelerometer and a strain gauge. In order to ensure the long-term stable operation of the equipment, an innovative self-powered system was designed. On towers with lower altitudes and sufficient sunshine, 120W solar panels and 20Ah lithium batteries were used; on towers with higher altitudes and more wind, 200W small wind turbines were added. All equipment uses the high-efficiency energy management chip TIBQ25570, combined with large-capacity supercapacitors, to ensure that the equipment can maintain working time of more than 7 days even in continuous rainy weather.
[0150] The communication network adopts the dual-mode solution of LoRa and NB-IoT. Under normal circumstances, the sensor node sends a data packet to the nearest repeater via LoRa every 15 minutes, containing precise three-dimensional coordinates, tilt angle, vibration frequency, stress strain and other information. The repeater uses the Semtech SX1301 chip, which has an ultra-high receiving sensitivity of -140dBm and can achieve an effective communication distance of 15 kilometers. In order to cope with the communication challenges brought by complex terrain, a Mesh network based on the LoRaWAN protocol was built, using a dynamic routing algorithm to ensure reliable data transmission to the main base station.
[0151] In case of communication obstruction or emergency, the system will automatically switch to NB-IoT mode. It uses Huawei Boudica 150 chip, supports 3GPP R14 standard, and has ultra-low power consumption and enhanced coverage. When an emergency such as abnormal vibration is detected, the sensor node will immediately start high-priority transmission and send the alarm information to the monitoring center within 1 second through the optimized protocol stack.
[0152] In order to improve positioning accuracy, four ground-based augmentation stations were deployed in the monitoring area to build a regional differential positioning system. These augmentation stations use the Zhongkewei NebulasII-Bx multi-system multi-frequency high-precision board and support the BDS-3 full signal system. The improved gamma filter calculates and broadcasts differential correction data in real time, significantly improving the positioning accuracy of the receiving terminal. At the same time, an adaptive algorithm based on deep learning is introduced, which can dynamically adjust the correction parameters according to the satellite combination and atmospheric conditions to ensure stable high-precision positioning effects under various weather conditions.
[0153] In terms of data fusion, a method combining an improved Kalman filter and a Savitzky-Golay filter was used, and a 5-layer multi-layer perceptron (MLP) neural network was introduced. The MLP used the Adam optimizer, with a learning rate of 0.001, and was trained on 1,000 historical data samples. This fusion algorithm makes full use of the angular velocity and acceleration information provided by the IMU, realizes the smoothing and interpolation of the Beidou positioning results, and can maintain continuous centimeter-level positioning accuracy even when the satellite signal is temporarily blocked.
[0154] Finally, based on the above high-precision positioning and attitude information, a three-layer anomaly detection framework was constructed. The spatiotemporal statistical learning layer uses the improved ST-OCSVM algorithm, the kernel function uses RBF, and the parameter ν is set to 0.01. The motion feature rule reasoning layer constructs an enhanced fuzzy logic rule base containing 27 rules based on expert knowledge, covering various abnormal modes such as tilt, vibration, and displacement. The multimodal decision fusion layer uses the Dempster-Shafer evidence theory to intelligently fuse the outputs of the two layers, and finally gives the anomaly score and risk level.
[0155] The test results are shown in the following table:
[0156] Table 1 Experimental data table
[0157]
[0158] By analyzing the data in the above table, we can draw the following conclusions:
[0159] Positioning accuracy: The system achieved centimeter-level positioning accuracy on all test towers, and even in extreme environments at an altitude of 5,200 meters, it still maintained an accuracy of 3.8 centimeters. This is far better than the performance of traditional GPS systems that can usually only achieve meter-level accuracy in high-altitude areas. High-precision positioning provides reliable basic data for subsequent anomaly detection.
[0160] Power supply duration: The innovative self-powered system has demonstrated excellent performance, and can work continuously for 12 days at Tower-A at an altitude of 3,500 meters, and can maintain a working time of 6 days even at Tower-F with the worst sunshine conditions. This greatly reduces the frequency of manual maintenance and improves the reliability and economy of the system.
[0161] Communication success rate: The dual-mode communication solution performed well, achieving a communication success rate of 99.8% on Tower-A, which is at a lower altitude. As the altitude increased, the communication conditions deteriorated, but it still maintained a success rate of 96.8% on Tower-F, which is at the highest altitude. This is a very ideal result for high-altitude complex terrain.
[0162] Anomaly detection performance: The three-layer anomaly detection framework demonstrated excellent performance. On all test towers, the anomaly detection rate exceeded 96%, with the highest reaching 98.5%. At the same time, the false alarm rate was kept at a low level, with the highest not exceeding 2.5%. This means that the system can accurately identify various anomalies while minimizing unnecessary interference caused by false alarms.
[0163] In summary, the high-precision monitoring method for high-altitude transmission line towers based on Beidou proposed in this invention has shown significant advantages in practical applications. It not only overcomes the challenges brought by the harsh environment in high-altitude areas, but also has made breakthrough progress in positioning accuracy, power supply continuity, communication reliability and anomaly detection performance.
[0164] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A high-precision monitoring method for high-altitude transmission line towers based on Beidou, characterized in that: include, Install sensor nodes at key structural points of the transmission line tower, and collect data based on the sensor nodes; the data includes transmission line tower data and inertial monitoring data; the transmission line tower data includes position data and motion feature data; Processing the transmission line tower data and integrating the inertial monitoring data to obtain transmission line tower dynamic monitoring data; An abnormality detection model is constructed based on the dynamic monitoring data to realize abnormal state monitoring of transmission line towers.
2. The Beidou-based high-altitude transmission line tower high-precision monitoring method as claimed in claim 1, characterized in that: The anomaly detection model includes a learning layer, a reasoning layer and a decision layer; The learning layer determines the abnormality score of the transmission line tower according to the dynamic monitoring data of the transmission line tower, and the objective function is shown as follows: Among them, w is the weight vector of each monitoring index of the transmission line tower, ξ i is the allowable error of the tower state deviating from the normal range, ρ is the threshold for abnormal state judgment, V is the dynamic monitoring data of the transmission line tower, γ is the weight coefficient of Beidou positioning data and IMU data in the fusion process, which is dynamically adjusted according to different weather conditions, N is the total number of monitoring points on the transmission line, and ν is the control parameter of the model's sensitivity to abnormalities.
3. The high-precision monitoring method for high-altitude transmission line towers based on Beidou as claimed in claim 2, characterized in that: The reasoning layer determines the abnormality type according to the transmission line dynamic monitoring data and the inertial monitoring data, and includes a logic rule base and a reasoning engine; The logic rule base uses the processed transmission line tower data and the inertial monitoring data to capture the abnormal state of the transmission line tower, as shown in the following formula: R i : If θ is And f is And a is Then y is B i Among them, θ is the inclination of the tower, f is the vibration frequency of the tower, a is the vibration amplitude of the transmission line, is the fuzzy set of input variables, B i is the fuzzy set of output variables.
4. The Beidou-based high-precision monitoring method for high-altitude transmission line towers as claimed in claim 3, characterized in that: The inference engine includes fuzzification, rule evaluation and defuzzification; The fuzzification is shown as follows: in, is the membership function of the tower inclination θ, a θ is the slope parameter of the tower inclination, reflecting the sensitivity to the change of the tower inclination, c θ is the center value of the tower inclination, is the membership function of the tower vibration frequency f, a f is the slope parameter of the tower vibration frequency, c f is the center value of the tower vibration frequency, indicating the normal vibration frequency range, is the membership function of the vibration amplitude a of the transmission line, a a is the slope parameter of the vibration amplitude of the transmission line, c a is the central value of the vibration amplitude of the transmission line; The rule evaluation is as follows: in, is the membership function of rule Ri; The defuzzification is shown as follows: Among them, θ is the inclination of the tower, f is the vibration frequency of the tower, a is the vibration amplitude of the transmission line, y is the output result, y i is the output of rule Ri.
5. The high-precision monitoring method for high-altitude transmission line towers based on Beidou as claimed in claim 4, characterized in that: Processing the transmission line tower data includes performing differential correction on the position data, as shown in the following formula: in, is the estimated value at the current moment, x(k) is the observed value at the current moment, a is the filter coefficient, μ1, β1, σ1 are the correction parameters, and f atm (k) is the atmospheric correction function.
6. The Beidou-based high-precision monitoring method for high-altitude transmission line towers as claimed in claim 5, characterized in that: Processing the transmission line tower data also includes dynamically adjusting parameters of the differentially corrected position data, as shown in the following formula: w corr (k+1)=w(k)+μe(k)x(k)+g sat (k)+h corr (k) h corr =β3·log(1+γ·|e(k)|) Among them, w k is the weight vector, w corr (k+1) is the modified weight vector, μ is the step size factor, e k is the error signal, x(k) is the input vector, s(k) is the satellite combined signal strength, β2, β3, γ are correction parameters, g sat (k) is the satellite combination weight function, h corr Dynamic adjustment function for differential correction parameters.
7. The Beidou-based high-precision monitoring method for high-altitude transmission line towers as claimed in claim 6, characterized in that: integrating said inertial monitoring data including status updates with predictions and corrected predictions; The state update and prediction are shown as follows: Among them, X k|k-1 is the state prediction at time k based on time k-1, including the position, posture and dynamic information of the transmission tower, F k-1 is the state transfer matrix, B k-1 is the control input matrix, u k-1 is the control input vector, G is the influence matrix of acceleration information on the state, a k is the acceleration information of inertial monitoring data, P k|k-1 is the prediction covariance matrix, Q k-1 is the process noise covariance matrix.
8. A high-altitude transmission line tower high-precision monitoring system based on Beidou, based on the high-altitude transmission line tower high-precision monitoring method based on Beidou according to any one of claims 1 to 7, characterized in that: include, A data acquisition module, used to install sensor nodes at key structural points of a transmission line tower, and to collect data based on the sensor nodes; the data includes transmission line tower data and inertial monitoring data; the transmission line tower data includes position data and motion feature data; A data processing module, used to process the transmission line tower data and integrate the inertial monitoring data to obtain dynamic monitoring data of the transmission line tower; The abnormality judgment module is used to process the transmission line tower data and integrate the inertial monitoring data to obtain dynamic monitoring data of the transmission line tower.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the Beidou-based high-altitude transmission line tower high-precision monitoring method described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the Beidou-based high-altitude transmission line tower high-precision monitoring method described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Underground pipeline protection identification device for monitoring geological deformation
CN120932537A
An underground pipeline protection marker device for monitoring geological deformation
CN120932537B
