A slope cooperative monitoring and early warning method and system for distributed power equipment

Abstract

The application discloses a slope cooperative monitoring and early warning method and system of distributed power equipment, and relates to the technical field of safety monitoring. The method comprises the following steps: acquiring three-dimensional position coordinates of monitoring nodes arranged along a slope, calculating the distance between the nodes and arranging the nodes according to the cumulative distance in the ascending direction along the slope to form a monitoring node sequence; collecting monitoring data by each monitoring node and recording a time stamp; standardizing the monitoring data to generate dimensionless monitoring indexes, screening abnormal monitoring indexes exceeding a first preset threshold, analyzing the spatial distribution characteristics of the abnormal monitoring indexes to identify a spatial propagation mode or a single-point abnormal mode; if the abnormal monitoring indexes are of the spatial propagation mode and the time stamps are sequentially increased according to the node sequence, outputting a geological disaster early warning signal; and if the abnormal monitoring indexes are of the single-point abnormal mode and the time stamp interval of the abnormal nodes exceeds a second preset threshold, outputting an equipment fault signal. The application effectively distinguishes a real landslide event from an equipment fault by spatiotemporal cooperation, solves the problem of high false alarm rate of a traditional single-point and fixed threshold monitoring method, and significantly improves the early warning accuracy.

Description

Technical Field

[0001] This application relates to the field of safety monitoring technology, and in particular to a method and system for collaborative monitoring and early warning of slopes for distributed power equipment. Background Technology

[0002] To ensure the safety of power transmission towers and other electrical equipment built on mountain slopes, the industry practice is to deploy tilt and displacement monitoring sensors at critical locations such as the tower base or tower body to obtain monitoring parameters characterizing the physical state of the equipment. The conventional early warning process involves setting a fixed alarm threshold for each individual sensor; when the collected monitoring parameters exceed this threshold, an alarm signal is output.

[0003] However, despite the distributed deployment of monitoring sensors along the slope, this approach treats each monitoring point as an isolated information island, failing to leverage the spatial correlation between distributed nodes for collaborative judgment. This method cannot distinguish, as a whole, whether a single-point anomaly is caused by sensor malfunction or a continuous event propagating across multiple distributed nodes due to geological disasters. Therefore, the output alarm signal cannot clearly identify the source of the event, a problem that urgently needs to be addressed in current technology. Summary of the Invention

[0004] Therefore, this application provides a slope collaborative monitoring and early warning method and system for distributed power equipment, which can solve the problem that existing processing methods cannot distinguish between real physical propagation events and single-point equipment failures, resulting in false alarms due to the inability to trace the source.

[0005] To solve the above-mentioned technical problems, this application provides the following technical solution: In a first aspect, this application provides a method for collaborative monitoring and early warning of distributed power equipment on slopes, comprising: acquiring the three-dimensional position coordinates of monitoring nodes of distributed power equipment deployed along a slope; calculating the distance between monitoring nodes based on the position coordinates; arranging the monitoring nodes in distance order to form a monitoring node sequence; collecting monitoring data from each monitoring node in the monitoring node sequence and recording the collection timestamp; standardizing the monitoring data to generate dimensionless monitoring indicators; filtering abnormal monitoring indicators exceeding a first preset threshold from the dimensionless monitoring indicators; analyzing the spatial distribution characteristics of monitoring nodes exhibiting abnormal monitoring indicators and the temporal relationship between their collection timestamps to identify event patterns; the event patterns include spatial propagation patterns and single-point anomaly patterns; if the event pattern is identified as the spatial propagation pattern, a geological disaster early warning signal is output; if the event pattern is identified as the single-point anomaly pattern, an equipment fault signal is output.

[0006] Preferably, the spatial propagation mode is that the abnormal monitoring indicator appears at multiple consecutive adjacent monitoring nodes, and the single-point anomaly mode is that the abnormal monitoring indicator appears at a single monitoring node.

[0007] Preferably, the step of obtaining the three-dimensional position coordinates of the monitoring nodes of the distributed power equipment deployed along the slope, calculating the distance between the monitoring nodes based on the position coordinates, and arranging the monitoring nodes in order of distance to form a monitoring node sequence includes: obtaining the three-dimensional position coordinates of the monitoring nodes of the distributed power equipment deployed along the slope; establishing a local coordinate system of the slope with the transmission tower at the bottom of the slope as the origin, and converting the three-dimensional position coordinates into local coordinates under the local coordinate system of the slope; calculating the cumulative distance of each monitoring node along the upward direction of the slope based on the local coordinates, and arranging the monitoring nodes in order of cumulative distance from smallest to largest to form a monitoring node sequence.

[0008] Preferably, the step of standardizing the monitoring data to generate dimensionless monitoring indicators includes: calculating reference values ​​for each monitoring node within a preset time window based on the monitoring data; calculating the deviation between the monitoring data and the reference values; and normalizing the deviation using a preset standardization function to obtain the dimensionless monitoring indicators.

[0009] Preferably, the step of screening abnormal monitoring indicators that exceed a first preset threshold from the dimensionless monitoring indicators includes: marking the dimensionless monitoring indicators that exceed the first preset threshold as candidate abnormal indicators; if the candidate abnormal indicator exceeds the first preset threshold in multiple consecutive collection cycles, then the candidate abnormal indicator is determined as the abnormal monitoring indicator; otherwise, the candidate abnormal indicator is determined as a transient disturbance and is removed.

[0010] Preferably, the analysis of the spatial distribution characteristics of monitoring nodes exhibiting abnormal monitoring indicators and the temporal relationship between their collection timestamps to identify event patterns includes: obtaining the location numbers of the monitoring nodes exhibiting the abnormal monitoring indicators in the monitoring node sequence; sorting the monitoring nodes exhibiting the abnormal monitoring indicators according to the location numbers, calculating the location number interval between adjacent abnormal monitoring nodes; if all the location number intervals are less than a preset interval threshold, and the number of abnormal monitoring nodes exceeds a preset number threshold, then it is initially determined to be a spatial propagation pattern; if the location number interval is greater than or equal to the preset interval threshold, or the number of abnormal monitoring nodes does not exceed the preset number threshold, then it is initially determined to be a single-point abnormal pattern; extracting the collection timestamps of each monitoring node in the preliminary determination result, analyzing the temporal relationship, and completing the final identification of the event pattern.

[0011] Preferably, if the initial determination is the spatial propagation mode, the method further includes: obtaining the timestamps recorded by each monitoring node exhibiting the spatial continuity feature; calculating the time interval between the timestamps of adjacent monitoring nodes according to the position number order in the monitoring node sequence; if the time interval is positive along the increasing direction of the monitoring node sequence, then: determining whether the position numbers of each monitoring node exhibiting the abnormal monitoring indicator constitute a continuous sequence in the monitoring node sequence; if it constitutes the continuous sequence, then confirming it as the spatial propagation mode and outputting the geological disaster early warning signal; if it does not constitute the continuous sequence, then determining that the physical continuity of the spatial propagation mode is interrupted, re-determining it as a multi-point independent fault and outputting the equipment fault signal; if the time interval has a negative value, then re-determining it as the single-point abnormal mode.

[0012] Preferably, if the initial determination is the single-point anomaly mode, the method further includes: checking whether there are other monitoring nodes in the monitoring node sequence that exhibit the abnormal monitoring indicator; if there are no other monitoring nodes that exhibit the abnormal monitoring indicator, then confirming the single-point anomaly mode and outputting the equipment fault signal; if there are other monitoring nodes that exhibit the abnormal monitoring indicator, then calculating the timestamp interval of each monitoring node exhibiting the abnormal monitoring indicator.

[0013] Preferably, if the timestamp interval of the abnormal monitoring indicators of each monitoring node exceeds the second preset threshold, it is confirmed as the single-point abnormal mode and the equipment fault signal is output; if there is a pair of monitoring nodes whose timestamp interval does not exceed the second preset threshold, it is determined whether the pair of monitoring nodes is adjacent in the monitoring node sequence; if they are adjacent and the timestamps increase sequentially according to the monitoring node sequence, it is re-determined as the spatial propagation mode; otherwise, it is confirmed as a multi-point independent fault and the equipment fault signal is output.

[0014] Secondly, this application also provides a slope collaborative monitoring and early warning system for distributed power equipment, comprising: a data acquisition module, used to acquire the three-dimensional position coordinates of monitoring nodes of distributed power equipment deployed along the slope, calculate the cumulative distance of the monitoring nodes along the slope's upward direction based on the three-dimensional position coordinates, arrange the monitoring nodes in ascending order of the cumulative distance along the slope's upward direction to form an ordered sequence of monitoring nodes, and synchronously collect monitoring data through each monitoring node and record the collection timestamp corresponding to each monitoring data; a data processing module, used to standardize the monitoring data to generate dimensionless monitoring indicators, and filter abnormal monitoring indicators exceeding a first preset threshold from the dimensionless monitoring indicators; a pattern recognition module, used to analyze the spatial distribution characteristics of monitoring nodes exhibiting the abnormal monitoring indicators and the temporal relationship between their collection timestamps to identify event patterns, the event patterns including spatial propagation patterns and single-point anomaly patterns; and an early warning module, used to output a geological disaster early warning signal if the event pattern is identified as the spatial propagation pattern, and output an equipment fault signal if the event pattern is identified as the single-point anomaly pattern.

[0015] Beneficial effects of implementing this application This application provides a method and system for collaborative monitoring and early warning of slopes for distributed power equipment. By constructing distributed monitoring nodes into an ordered spatial sequence, it establishes an objective framework for analyzing the physical propagation process of abnormal events. Unlike isolated judgments of monitoring data from a single node, this application analyzes the spatiotemporal distribution patterns of abnormal indicators across multiple nodes to distinguish between geological disasters with physical propagation characteristics and equipment failures without propagation characteristics. After identifying events that initially conform to spatiotemporal propagation characteristics, the physical continuity of the abnormal node location sequence is further determined to identify pseudo-propagation phenomena formed by multiple independent, discontinuous equipment failures occurring coincidentally in time. The spatiotemporal correlation collaborative judgment logic established in this application fundamentally solves the problem that single-point threshold judgment cannot trace the cause of anomalies, thereby improving the accuracy of early warning results. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an overall flowchart of a slope collaborative monitoring and early warning method for distributed power equipment involved in this application; Figure 2This is a flowchart illustrating the analysis of spatial distribution characteristics of abnormal monitoring indicators and the identification of event patterns in a slope collaborative monitoring and early warning method for distributed power equipment, as described in this application. Figure 3 This is a schematic diagram of the overall structure of a slope collaborative monitoring and early warning system for distributed power equipment involved in this application; Figure 4 This is a computer device diagram of a slope collaborative monitoring and early warning method for distributed power equipment involved in this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] Distributed power equipment, such as transmission towers or poles erected along mountain slopes, is an important component of the power grid. Slope safety monitoring of distributed power equipment is typically achieved by installing various monitoring sensors on the equipment itself or the surrounding geological features. These sensors are used to collect physical parameters in real time that reflect the structural condition of the equipment or changes in the surrounding soil and rock.

[0020] Currently, early warning processing for slope safety monitoring is mainly based on independent analysis of data from individual monitoring points. One type is static threshold judgment, which presets a fixed safety threshold for the monitoring parameters (such as the tilt angle of a transmission tower or the absolute displacement of the tower base). When the data value collected by the sensor exceeds this safety threshold, it is judged as abnormal and an alarm is triggered. Another type considers the changes of monitoring parameters over time. By calculating the magnitude of the change in the value of the monitoring parameter at adjacent collection times, an alarm is triggered when this magnitude of change exceeds a set limit. This processing method responds faster to sudden events, but the judgment is still limited to the time dimension of a single monitoring point.

[0021] While the aforementioned processing methods can reflect equipment anomalies to some extent, their core logic is based on the analysis of data from isolated monitoring points. These methods treat multiple monitoring points distributed along the slope as independent entities, ignoring the physical processes of spatial propagation and evolution of geological disasters (such as landslides). Therefore, when sensors malfunction, there is strong environmental disturbance, or a real geological disaster occurs, these methods may all output the same, indiscriminate alarm signal, making it impossible to effectively distinguish the source of the event, resulting in false alarms and increasing unnecessary on-site verification costs and risks.

[0022] Based on the above, this application provides a method and system for collaborative monitoring and early warning of slopes for distributed power equipment. This application no longer treats distributed monitoring nodes as independent individuals, but first arranges them into an ordered sequence of monitoring nodes based on their physical location coordinates, using this as the basis for collaborative analysis. Subsequently, this application identifies the root cause of events by analyzing the spatial distribution characteristics and temporal evolution patterns of abnormal monitoring indicators on the monitoring node sequence. This application identifies and distinguishes between spatially propagating patterns that are continuously propagated and isolated single-point anomaly patterns. By imposing strict temporal logic constraints on these two patterns, it outputs early warning signals pointing to geological disasters or equipment failures, thereby effectively distinguishing between real physical propagation events and single-point equipment failures, solving the problem of false alarms caused by the inability to trace the source in existing technologies.

[0023] According to an embodiment of the present invention, a slope collaborative monitoring and early warning embodiment for distributed power equipment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer device with data processing capabilities, such as a computer or server. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] This embodiment provides a method for collaborative monitoring and early warning of slopes for distributed power equipment, which can be used with the aforementioned computer equipment. Figure 1 This is a flowchart of a question-answering task processing model training method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step 100: Obtain the three-dimensional location coordinates of the monitoring nodes of the distributed power equipment deployed along the slope, calculate the distance between the monitoring nodes based on the location coordinates, and arrange the monitoring nodes in order of distance to form a monitoring node sequence.

[0025] Step 110: Obtain the three-dimensional location coordinates of the monitoring nodes of the distributed power equipment deployed along the slope.

[0026] Specifically, the three-dimensional location coordinates include the longitude, latitude, and elevation values ​​of each monitoring node; the monitoring nodes are installed on the transmission tower foundation, guy wire anchor points, or the tower body itself.

[0027] Step 120: Establish a local coordinate system for the slope with the transmission tower at the bottom of the slope as the origin, and convert the three-dimensional position coordinates into local coordinates under the local coordinate system of the slope.

[0028] Specifically, the X-axis of the local coordinate system of the slope runs along the slope direction, the Y-axis is perpendicular to the slope surface and points upward, and the Z-axis runs along the slope dip. The three-dimensional position coordinates are converted into local coordinates through a coordinate rotation matrix.

[0029] Step 130: Calculate the cumulative distance of each monitoring node along the upward direction of the slope based on the local coordinates, and arrange the monitoring nodes in ascending order of cumulative distance to form a monitoring node sequence.

[0030] Specifically, the cumulative distance is the projected length of the straight-line distance from the monitoring node to the origin at the bottom of the slope on the slope surface. The first node in the monitoring node sequence is the bottom node of the slope, and the last node is the top node of the slope. The difference in the sequence number between adjacent nodes is 1.

[0031] Preferably, step 100 organizes the dispersed monitoring nodes into an ordered sequence by establishing a local coordinate system for the slope and calculating the cumulative distance. This provides a spatial basis for collecting monitoring data according to the monitoring node sequence in step 200 and identifying spatial propagation patterns in step 300. The serialization processing used in this application allows the spatial propagation characteristics of abnormal monitoring indicators to be directly determined through the adjacency relationship and timestamp order in the sequence, thus eliminating the need for overly complex spatial topology analysis.

[0032] Step 200: Collect monitoring data from each monitoring node in the monitoring node sequence and record the timestamp of the collection.

[0033] Specifically, step 200 includes steps 210 to 230: Step 210: Collect monitoring data through the sensors of each monitoring node in the monitoring node sequence according to the preset collection cycle.

[0034] It should be noted that the monitoring data includes tilt angle data, acceleration data, and displacement data. The tilt angle data is the tilt angle value of the transmission tower foundation or tower body collected by the tilt angle sensor. The acceleration data is the acceleration value of the monitoring point in three orthogonal directions collected by the triaxial acceleration sensor. The displacement data is the spatial coordinate value of the monitoring point collected by the positioning module.

[0035] The preset acquisition cycle is a configurable time interval based on actual monitoring needs. Setting the preset acquisition cycle requires balancing two considerations: firstly, the acquisition cycle needs to be short enough to ensure the complete process of slope deformation or equipment status changes is captured, avoiding the loss of crucial information due to excessively long sampling intervals; secondly, the acquisition cycle also needs to consider the energy consumption and data transmission load of the monitoring nodes, avoiding premature equipment failure or data redundancy due to overly frequent acquisition. In this embodiment, the preset acquisition cycle is set to 10 minutes, 30 minutes, or 60 minutes.

[0036] Step 220: Record the timestamp when collecting monitoring data at each monitoring node.

[0037] It should be noted that the timestamp is the time value recorded by the built-in clock of each monitoring node when collecting monitoring data. The built-in clock of each monitoring node is calibrated through a time synchronization signal, and the monitoring data, timestamp and monitoring node identifier are stored together.

[0038] Step 230: Preprocess the monitoring data, specifically by removing the portion of the monitoring data that exceeds the preset range and interpolating the missing portion of the monitoring data.

[0039] Specifically, tilt data, acceleration data, or displacement data that exceed the sensor's measurement range are discarded. For missing data of a single monitoring node in two consecutive acquisition cycles, interpolation is performed based on the monitoring data of adjacent acquisition cycles. The interpolated monitoring data is marked with a completion identifier. The pre-processed monitoring data is then used for standardization in step 300.

[0040] Preferably, step 200 records and calibrates the monitoring data of each monitoring node through timestamps, so that step 300 can accurately identify the temporal relationship between abnormal monitoring indicators in different monitoring nodes based on the monitoring data and timestamps.

[0041] Step 300: Standardize the monitoring data to generate dimensionless monitoring indicators, select abnormal monitoring indicators that exceed the first preset threshold from the dimensionless monitoring indicators, analyze the spatial distribution characteristics of the monitoring nodes that have abnormal monitoring indicators and the temporal relationship between their collection timestamps, and identify event patterns.

[0042] The event patterns include spatial propagation pattern and single-point anomaly pattern. Spatial propagation pattern involves multiple consecutive adjacent monitoring nodes exhibiting abnormal monitoring indicators, while single-point anomaly pattern involves a single monitoring node exhibiting abnormal monitoring indicators.

[0043] Furthermore, if the event pattern is identified as a spatial propagation pattern, a geological disaster early warning signal will be output. If the identified event pattern is a single point of failure, then a device fault signal is output.

[0044] Specifically, step 310: Standardize the monitoring data to generate dimensionless monitoring indicators, including steps 311 to 313: Step 311: Calculate the reference value of each monitoring node within the preset time window based on the monitoring data; Step 312: Calculate the deviation based on the monitoring data and the reference value; Step 313: Normalize the deviation using a preset standardization function based on the deviation, and calculate the dimensionless monitoring index.

[0045] It should be noted that step 311 requires establishing a stable numerical benchmark for each monitoring node to identify abnormal fluctuations. In slope monitoring engineering practice, monitoring data under normal conditions will exhibit periodic fluctuations due to environmental factors such as temperature changes and wind loads, but these fluctuations revolve around a relatively stable central value. The selection of the preset time window needs to balance two considerations: a window that is too short may include occasional disturbances, while a window that is too long may mask slow, real changes. According to the "Code for Seismic Design of Power Facilities" and related monitoring technical standards, the natural frequency of transmission tower structures is usually in the range of 0.5-3Hz, with a corresponding response time of several seconds to several minutes. However, the development cycle of geological processes such as slope creep is usually several days to several weeks. Based on this understanding, this embodiment sets the preset time window to 72 hours, which can cover the complete cycle of daily environmental disturbances while avoiding misjudging real geological changes as normal fluctuations.

[0046] For each monitoring node, all valid monitoring data from the past 72 hours are extracted from the database. The reference value for tilt angle data is calculated using a simple arithmetic mean: the ratio of the sum of all tilt angle measurements within 72 hours to the number of measurements is used as the reference value for tilt angle data. Due to the AC characteristics of acceleration signals, the reference value for acceleration data is calculated using the root mean square (RMS) value: the square of each value in the X-axis, Y-axis, and Z-axis acceleration sequences is calculated, summed, divided by the number of data points, and then the square root is taken. The reference value for displacement data is calculated by taking the arithmetic mean of the X, Y, and Z coordinates to form the three-dimensional coordinates of the reference position. During the calculation process, two types of data are automatically excluded: abnormal data marked when sensors malfunction, and data interpolated after communication interruptions, ensuring that the reference values ​​accurately reflect the normal baseline of the monitoring node.

[0047] Step 312 compares the current monitored value with the reference value to quantify the degree of deviation. The key to step 312 is establishing a comparable basis for different types of monitoring data. For tilt angle data, the absolute difference between the current measured value and the tilt angle reference value is calculated. Then, this difference is compared with the standard deviation of the tilt angle reference value within a 72-hour window to obtain the tilt angle deviation. The standard deviation reflects the dispersion of tilt angle data under normal conditions and can be used as a normalization factor to eliminate baseline fluctuations caused by differences in environmental conditions at different monitoring points. When the standard deviation of the tilt angle at a monitoring point is less than 0.01 degrees (this usually occurs at monitoring points with extremely stable environments), 0.01 degrees is used as the minimum standard deviation to avoid numerical instability in division operations.

[0048] Furthermore, because acceleration is a three-dimensional vector, the calculation of acceleration deviation is more complex. Specifically, it involves calculating the differences between the current X, Y, and Z-axis accelerations and their corresponding reference values, using these three differences as components of a three-dimensional difference vector, and calculating the Euclidean magnitude of the vector as the scalar acceleration deviation. Therefore, the acceleration deviation calculation in this application can capture acceleration anomalies in any direction without overlooking composite directional anomalies that might be ignored in single-axis analysis. Similarly, displacement deviation uses a similar approach, calculating the three-dimensional Euclidean distance between the current displacement coordinate and the reference displacement coordinate.

[0049] Step 313 converts various deviations into dimensionless monitoring indicators using a preset standardization function. Standardization is necessary because the dimension of tilt deviation is a dimensionless ratio, the dimension of acceleration deviation is m / s², and the dimension of displacement deviation is meters (m), making direct comparison impossible. The standardization function uses a variation of the Z-score method: ; The historical mean and historical standard deviation of the deviation are calculated based on the deviation sequence of the monitoring node over the past 30 days. The reason for defining the past 30 days in this application embodiment is due to the seasonality of slope monitoring, that is, to include enough samples to ensure statistical stability, and to avoid interference from long-term trends across seasons.

[0050] Preferably, the adjustment coefficients in this application reflect the differences in sensitivity at different monitoring locations. For example, the adjustment coefficient for the transmission tower foundation monitoring node can be set to 1.2, because the foundation is in direct contact with the soil and rock mass and is most sensitive to geological changes, requiring a higher weight. The adjustment coefficient for the tower body monitoring node can be set to 1.0 as a standard reference, because tower body monitoring can comprehensively reflect the overall structural condition. The adjustment coefficient for the guy wire anchor point monitoring node can be set to 0.8, because anchor points are usually located in relatively stable rock strata, and the intensity of abnormal signals is relatively weak. When the historical data for a monitoring node is less than 30 days (such as for newly installed monitoring points), the existing data is used to calculate the statistics, but a minimum of 7 days of data is required to ensure the minimum requirement of basic statistical validity.

[0051] This application, based on the 3σ principle, restricts dimensionless monitoring indicators to the [-5, 5] interval using a cutoff function. 99.7% of the data in a normal distribution fall within the mean ± 3σ range. Due to the diversity and complexity of the monitoring environment, this can be appropriately extended to ± 5σ, thus covering the vast majority of normal fluctuations while effectively identifying true anomalies.

[0052] Steps 311 to 313 successfully resolved the issue of unifying multi-source heterogeneous monitoring data in step 310. For example, an inclination sensor on a transmission tower foundation measured a 0.5-degree angle change, while an acceleration sensor detected an abnormal vibration of 0.02 m / s², and a displacement sensor detected a 2 mm displacement. In traditional fixed-threshold judgments, engineers need to set separate thresholds for angle, acceleration, and displacement, and these thresholds may need adjustment under different geological and meteorological conditions. However, after the standardization process in step 310, the three heterogeneous data points are converted into dimensionless monitoring indicators, such as 2.1, 1.8, and 2.3, respectively. These indicators can be compared and comprehensively judged within a unified framework, laying a solid foundation for anomaly screening and pattern recognition.

[0053] Step 320: Select abnormal monitoring indicators from the dimensionless monitoring indicators that exceed the first preset threshold, specifically including: Dimensionless monitoring indicators that exceed the first preset threshold are marked as candidate abnormal indicators; If a candidate abnormal indicator exceeds the first preset threshold in multiple consecutive collection cycles, the candidate abnormal indicator will be identified as an abnormal monitoring indicator. Otherwise, candidate abnormal indicators will be judged as transient disturbances and eliminated.

[0054] It should be noted that step 320 filters abnormal monitoring indicators from the dimensionless monitoring indicators generated in step 310. Various transient interference sources exist in the slope monitoring environment, such as electromagnetic pulses generated by lightning, ground vibrations when heavy vehicles pass by, and transient structural responses caused by sudden temperature changes. Analysis of monitoring data reveals that the duration of environmental disturbances typically ranges from several minutes to one hour, while the duration of actual geological activity or equipment failures far exceeds that of environmental disturbances. Traditional monitoring methods use a single threshold judgment; once a dimensionless monitoring indicator exceeds a preset value, an alarm is triggered, failing to distinguish between transient disturbances and continuous anomalies.

[0055] In this application, the setting of the first preset threshold needs to strike a balance between detection sensitivity and false alarm control. According to the technical requirements for structural monitoring in the "Code for Geological Investigation of Power Engineering" DL / T5010-2007, the structural response under normal operating conditions should be controlled within two standard deviations of the design reference value. Combining the Z-score standardization characteristics of the dimensionless monitoring index in step 310, this embodiment sets the first preset threshold to 2.5. The basis for selecting 2.5 includes: statistically, the probability of events exceeding 2.5 standard deviations is approximately 1.2%, which conforms to the low probability characteristics of abnormal events. For example, in a two-year monitoring experiment conducted by a domestic power grid company in the western Sichuan mountainous area, 172 out of 184 confirmed equipment anomalies and geological disasters had dimensionless monitoring indices exceeding 2.5, thus verifying the effectiveness of the first preset threshold.

[0056] In this embodiment, the screening process for anomaly monitoring indicators is divided into two stages: preliminary labeling and continuous verification. When the absolute value of the dimensionless monitoring indicator of a monitoring node exceeds a first preset threshold of 2.5, the dimensionless monitoring indicator is labeled as a candidate anomaly indicator. The candidate anomaly indicator is only a temporary state and needs to be determined whether it is a real anomaly through observation over multiple consecutive collection cycles.

[0057] For example, since precursor signals of geological disasters such as landslides typically last for more than 6 hours, and equipment malfunctions such as sensor drift can also generate abnormal signals lasting for several hours, while the impact of environmental interference such as lightning and mechanical shocks usually lasts for less than 30 minutes, the continuous observation period can be set to 3 acquisition cycles, corresponding to a 30-minute observation duration under a commonly used 10-minute acquisition interval in monitoring projects.

[0058] The continuity verification requires that candidate anomaly indicators remain above a first preset threshold for three consecutive data collection cycles. During the continuity verification process, dimensionless monitoring indicators are allowed to fluctuate within a range above the threshold. For example, a dimensionless monitoring indicator for the tilt angle of a certain monitoring node might be recorded as 2.8, 3.2, and 2.9 during the verification period. Although the value changes, it always exceeds 2.5, thus meeting the continuity requirement. Candidate anomaly indicators that pass the continuity verification are converted into anomaly monitoring indicators and entered into spatial distribution characteristic analysis; candidate anomaly indicators that fail the verification are marked as transient disturbances and removed from the analysis process.

[0059] When multiple dimensionsless monitoring indicators of the same monitoring node simultaneously exceed the first preset threshold, the verification time can be shortened. If two or more dimensionsless monitoring indicators of a certain monitoring node, such as tilt angle, acceleration, and displacement, simultaneously become candidate anomaly indicators, the continuous verification cycle is adjusted to two acquisition cycles. The rationale for shortening the verification time is that real anomaly events often affect multiple physical parameters simultaneously, and the simultaneous anomaly of multiple types of indicators increases the credibility of the signal's authenticity.

[0060] For example, six months of operational data from a 220kV transmission line slope monitoring project validated the screening effectiveness of step 320. During the project, 298 candidate anomaly indicators were generated. After continuous verification, 39 anomaly indicators were confirmed, and 259 candidate anomaly indicators were determined to be transient disturbances. On-site technicians verified the 39 anomaly indicators and found that 36 corresponded to actual changes in equipment status or geological conditions, achieving an accuracy rate of 92.3%. In contrast, the traditional single-threshold judgment method requires on-site verification for all 298 threshold-exceeding events, while only 36 are considered genuine anomalies, resulting in a false alarm rate as high as 87.9%. The continuous verification in step 320 reduced the on-site verification workload by 86.9%, saving maintenance personnel significant time and costs.

[0061] Step 330: Analyze the spatial distribution characteristics of monitoring nodes for anomaly monitoring indicators and the temporal relationship between their collection timestamps to identify event patterns, such as... Figure 2 As shown, it includes: Obtain the position number of the monitoring node that exhibits abnormal monitoring indicators in the monitoring node sequence; Specifically, in step 100, the monitoring nodes deployed along the slope are arranged in order of distance from bottom to top, forming an ordered sequence of monitoring nodes, each with a unique location number. When an abnormal monitoring indicator is detected at a certain monitoring node, the platform extracts the location number of the monitoring node in the monitoring node sequence and establishes a correspondence between the abnormal monitoring indicator and its spatial location.

[0062] After sorting the monitoring nodes with abnormal monitoring indicators in ascending order of their location numbers, the location number interval between adjacent abnormal monitoring nodes is calculated. Specifically, monitoring nodes exhibiting abnormal indicators are sorted by location number from smallest to largest, and then the difference in number between two adjacent abnormal monitoring nodes is calculated. The location number interval reflects the spatial distribution density and continuity of the abnormal monitoring indicators.

[0063] If the interval between all location numbers is less than the preset interval threshold, then it is determined that there is a spatial continuity feature. It should be explained that the preset interval threshold in this application embodiment is based on the actual deployment characteristics of the monitoring nodes. For example, in areas prone to landslides, monitoring nodes are deployed relatively densely, and under normal circumstances, the numbering difference between adjacent monitoring nodes is 1 or 2; in relatively stable areas, monitoring nodes are deployed relatively sparsely, and the numbering difference may be 3 or 4. The preset interval threshold is typically set to 3, allowing anomalies to skip a few monitoring nodes in a normal state during propagation, which conforms to the local unevenness of geological phenomenon propagation. The spatial continuity characteristic indicates that the anomaly monitoring indicators exhibit a relatively continuous distribution pattern along the monitoring node sequence, consistent with the basic law of physical phenomena propagating along spatial paths.

[0064] If spatial continuity is present and the number of abnormal monitoring nodes exceeds a preset threshold, it is initially determined to be a spatial propagation pattern. It should be explained that the preset quantity threshold in this application is used to prevent accidental local clustering from being misjudged as a real propagation phenomenon. Since abnormal monitoring indicators at a single or two adjacent locations may be due to local equipment problems or environmental interference, while abnormal monitoring indicators at multiple consecutive locations are more likely to reflect the real physical propagation process, the preset quantity threshold is usually set to 3, that is, at least 3 monitoring nodes are required to show abnormal monitoring indicators in order to constitute a spatial propagation pattern.

[0065] If there is no spatial continuity feature or the number of abnormal monitoring nodes does not exceed the preset threshold, it is initially determined to be a single-point abnormal mode. Extract the collection timestamps of each monitoring node from the preliminary judgment results, analyze the temporal relationship, and complete the final identification of the event pattern.

[0066] It should be noted that step 330 identifies the physical propagation characteristics of abnormal events by analyzing the spatial distribution patterns and temporal evolution of the abnormal monitoring indicators selected in step 320. Slope geological disasters such as landslides exhibit spatial propagation characteristics: the sliding surface begins to break down from a weak point and gradually expands along the slope; monitoring equipment will detect abnormal monitoring indicators sequentially according to their spatial location numbers. In contrast, equipment failures such as sensor drift and localized structural damage typically occur at single or a few isolated locations and do not possess the continuity of spatial propagation.

[0067] Furthermore, if the preliminary determination is that it is a spatial propagation mode, it also includes: Obtain the timestamps recorded by each monitoring node that exhibits spatial continuity. Calculate the time interval between timestamps of adjacent monitoring nodes based on the position number order in the monitoring node sequence; If the time intervals are all positive values ​​along the increasing direction of the monitoring node sequence, then: Determine whether the position numbers of the monitoring nodes that exhibit abnormal monitoring indicators form a continuous sequence in the monitoring node sequence; If a continuous sequence is formed, it is confirmed as a spatial propagation pattern and a geological disaster early warning signal is output. If a continuous sequence is not formed, the physical continuity of the spatial propagation mode is determined to be interrupted, and it is re-determined as a multi-point independent fault and a device fault signal is output. If the time interval has a negative value, it will be reclassified as a single point of failure.

[0068] It should be noted that for cases initially determined to be of a spatial propagation pattern, it is necessary to obtain the timestamps of each monitoring node when recording abnormal monitoring indicators. The physical propagation of geological disasters has a clear temporal sequence: the abnormal phenomenon starts from the initial point and gradually propagates to other locations along the spatial path. The time interval between the timestamps of adjacent monitoring nodes is calculated according to the position numbering order of the monitoring nodes in the monitoring node sequence.

[0069] A positive time interval indicates that the anomaly occurs sequentially in time according to spatial order, which conforms to the basic logic of physical propagation. A negative time interval indicates that the anomaly monitoring indicators appear later at the earlier monitoring nodes than at the later monitoring nodes, which violates the physical laws of propagation and usually indicates that the anomaly monitoring indicators originate from multiple independent fault points.

[0070] When the time intervals are all positive values ​​increasing along the monitoring node sequence, it is determined whether the position numbers of the monitoring nodes with abnormal monitoring indicators form a continuous sequence. A continuous sequence requires that there are no large jumps between the position numbers, reflecting the physical continuity of geological propagation. If a continuous sequence is formed, it is confirmed as a spatial propagation mode and a geological disaster early warning signal is output; if a continuous sequence is not formed, the propagation path is determined to be interrupted, and it is re-determined as a multi-point independent fault, and an equipment fault signal is output.

[0071] Furthermore, if the initial assessment indicates a single point of failure pattern, it also includes: Check if there are other monitoring nodes in the monitoring node sequence that exhibit abnormal monitoring indicators; If no other monitoring nodes exhibit abnormal monitoring indicators, the system is confirmed as a single-point abnormality mode and a device fault signal is output. If there are other monitoring nodes that exhibit abnormal monitoring indicators, then calculate the timestamp interval for the abnormal monitoring indicators of each monitoring node.

[0072] Furthermore, if the timestamp interval of abnormal monitoring indicators at each monitoring node exceeds the second preset threshold, it is confirmed as a single-point abnormal mode and a device fault signal is output. If there are monitoring node pairs whose timestamp interval does not exceed the second preset threshold, then determine whether the monitoring node pairs are adjacent in the monitoring node sequence. If the timestamps are adjacent and increase sequentially according to the monitoring node sequence, then the spatial propagation mode is re-determined; otherwise, it is confirmed as a multi-point independent fault and a device fault signal is output.

[0073] It should be noted that for cases initially determined to be a single-point anomaly pattern, it is necessary to check whether there are other monitoring nodes in the monitoring node sequence exhibiting abnormal monitoring indicators. If only a single monitoring node in the entire monitoring node sequence exhibits abnormal monitoring indicators, it is directly confirmed as a single-point anomaly pattern, and a device fault signal is output. If multiple abnormal monitoring nodes exist but do not possess spatial continuity, then temporal correlation analysis is required.

[0074] Calculate the timestamp interval for abnormal monitoring indicators at each monitoring node. The second preset threshold is typically set to 2 hours, based on the time pattern of equipment failure propagation: related equipment failures usually occur consecutively within a short period. If the timestamp interval of each monitoring node exceeds the second preset threshold, it indicates that the abnormal events are independent of each other in time, confirming a single-point anomaly mode and outputting an equipment failure signal.

[0075] If there are monitoring node pairs with timestamp intervals not exceeding the second preset threshold, it is determined whether the monitoring node pairs are adjacent in the monitoring node sequence. If they are adjacent and their timestamps increase sequentially according to the monitoring node sequence, it indicates the existence of a small-scale propagation phenomenon, and the pattern is reclassified as spatial propagation; otherwise, it is confirmed as a multi-point independent fault and a device fault signal is output.

[0076] Preferably, step 330 solves the problem that traditional monitoring cannot distinguish between geological disasters and equipment failures. Multi-level verification of spatial continuity, temporal propagation, and physical continuity enables accurate identification of the root causes of abnormal events, providing a reliable basis for determining event patterns to output corresponding early warning signals.

[0077] Furthermore, this application also includes the following after step 300: The number of geological disaster early warning signals and equipment failure signals output within a preset statistical period is counted. It should be noted that the preset statistical period is set according to the actual needs of transmission line operation and maintenance management. Since power operation and maintenance departments usually conduct equipment status assessments and maintenance plan formulations on a monthly basis, the preset statistical period is set to 30 days. In this embodiment of the application, at the end of each preset statistical period, the records of geological disaster early warning signals and equipment fault signals output in step 330 are extracted from the database, and the quantities of both are counted.

[0078] If the number of geological disaster early warning signals exceeds the first statistical threshold, then the first preset threshold will be adjusted. It should be explained that the embodiments of this application set the first statistical threshold based on the frequency of occurrence of slope geological disasters. In this embodiment, the first statistical threshold is set to 5. When the number of geological disaster early warning signals output within 30 days exceeds 5, it indicates that the early warning sensitivity is too high, and there is a possibility of misjudging equipment failure as a geological disaster. In this case, it is necessary to increase the first preset threshold, for example, from the original 2.5 to 2.8, to reduce the sensitivity of anomaly detection.

[0079] If the number of equipment fault signals exceeds the second statistical threshold, then the second preset threshold is adjusted.

[0080] It needs to be explained that the second statistical threshold is set based on the normal frequency of equipment failures. For example, under normal operation and maintenance, transmission line equipment typically experiences 8-12 abnormal events per month, including common issues such as sensor aging and communication module failures. Therefore, the second statistical threshold is set to 15. If the number of equipment failure signals output within 30 days exceeds 15, it indicates that the fault detection is too sensitive and may misjudge normal environmental fluctuations as equipment failures. In this case, the second preset threshold needs to be extended from the original 2 hours to 3 hours to reduce false alarms caused by overly strict time-related judgments.

[0081] In this embodiment, the adjustment of the first and second preset thresholds is gradual to avoid the impact of drastic parameter changes on monitoring stability. For example, the adjustment increment of the first preset threshold is set to 0.3, i.e., from 2.5 to 2.8, and then to 3.1; the adjustment increment of the second preset threshold is set to 1 hour, i.e., from 2 hours to 3 hours, and then to 4 hours. The adjusted first or second preset threshold takes effect in the next preset statistical period, and the counting of warning signals restarts.

[0082] The adjustment records of the first and second preset thresholds are saved in the parameter configuration table, including the adjustment time, reason for adjustment, and threshold values ​​before and after adjustment. Maintenance personnel can view the parameter adjustment history to understand the trajectory of changes in the monitored parameters, providing a reference for parameter optimization. When the number of warning signals remains within a reasonable range for multiple consecutive (e.g., 3) preset statistical periods, threshold adjustment is paused to maintain stable operation of the current parameters.

[0083] Preferably, the adjustment method of the first and second preset thresholds in this application solves the limitation that fixed thresholds cannot adapt to different environmental conditions (different slope geological conditions, climate environment, and equipment aging will affect the baseline level and fluctuation range of monitoring data). By statistically analyzing the output frequency of the early warning signal, the detection threshold is automatically adjusted, enabling this application to control the false alarm rate at a reasonable level while ensuring detection accuracy, thereby improving the practicality and reliability of the early warning method.

[0084] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0085] Based on the same inventive concept, this application also provides a slope collaborative monitoring and early warning system for distributed power equipment. The solution provided by this platform is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the slope collaborative monitoring and early warning system for distributed power equipment provided below can be found in the limitations of the slope collaborative monitoring and early warning method for distributed power equipment described above, and will not be repeated here.

[0086] In one exemplary embodiment, such as Figure 3 As shown, a slope collaborative monitoring and early warning system for distributed power equipment is provided, comprising: The data acquisition module is used to obtain the three-dimensional position coordinates of the monitoring nodes of the distributed power equipment deployed along the slope, calculate the cumulative distance of each monitoring node along the upward direction of the slope based on the three-dimensional position coordinates, arrange the monitoring nodes in ascending order of the cumulative distance along the upward direction of the slope to form an ordered sequence of monitoring nodes, and collect monitoring data synchronously through each monitoring node and record the collection timestamp corresponding to each monitoring data. The data processing module is used to standardize the monitoring data to generate dimensionless monitoring indicators, and to filter out abnormal monitoring indicators that exceed the first preset threshold from the dimensionless monitoring indicators. The pattern recognition module is used to analyze the spatial distribution characteristics of the abnormal monitoring indicators and the temporal relationship between their collection timestamps in order to identify event patterns, including spatial propagation patterns and single-point anomaly patterns. The early warning module is used to output a geological disaster early warning signal if the identified event pattern is a spatial propagation pattern, and to output a device fault signal if the identified event pattern is a single-point anomaly pattern.

[0087] Each module in the aforementioned distributed power equipment slope collaborative monitoring and early warning system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0088] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for collaborative monitoring and early warning of slopes in distributed power equipment. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0089] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0090] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0091] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0092] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0094] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0095] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0096] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. 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 application should be determined by the appended claims.

Claims

1. A method for collaborative monitoring and early warning of slopes for distributed power equipment, characterized in that, include: The three-dimensional location coordinates of the monitoring nodes of the distributed power equipment deployed along the slope are obtained, monitoring data is collected synchronously through each monitoring node, and the collection timestamp corresponding to each monitoring data is recorded. The monitoring data is standardized to generate dimensionless monitoring indicators. Abnormal monitoring indicators exceeding a first preset threshold are selected from the dimensionless monitoring indicators. The spatial distribution characteristics of the monitoring nodes with abnormal monitoring indicators and the temporal relationship between their collection timestamps are analyzed to identify event patterns. The event patterns include spatial propagation patterns and single-point anomaly patterns. If the event pattern is identified as the spatial propagation pattern, a geological disaster early warning signal is output. If the event pattern is identified as the single-point anomaly pattern, a device fault signal is output.

2. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 1, characterized in that, After obtaining the three-dimensional position coordinates of the monitoring nodes of the distributed power equipment deployed along the slope, the method further includes: calculating the cumulative distance of each monitoring node along the upward direction of the slope based on the three-dimensional position coordinates; arranging the monitoring nodes in ascending order of the cumulative distance along the upward direction of the slope to form an ordered sequence of monitoring nodes; and analyzing the spatial distribution characteristics based on the sequence of monitoring nodes.

3. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 2, characterized in that, The process of obtaining the three-dimensional location coordinates of the monitoring nodes of the distributed power equipment deployed along the slope, and calculating the spatial distance between each monitoring node based on the three-dimensional location coordinates, includes: Obtain the three-dimensional location coordinates of the monitoring nodes of distributed power equipment deployed along the slope, including longitude, latitude, and elevation. With the base of the transmission tower at the bottom of the slope as the origin, a local coordinate system for the slope is established with the X-axis along the slope direction, the Y-axis perpendicular to the slope surface and upward, and the Z-axis along the slope inclination. The three-dimensional position coordinates are then converted into local coordinates under the local coordinate system of the slope using a coordinate rotation matrix. The cumulative projected distance of each monitoring node along the slope's upward direction is calculated based on the local coordinates and used as the cumulative distance along the slope's upward direction.

4. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 1, characterized in that, The standardization process for generating dimensionless monitoring indicators from the monitoring data includes: Based on the monitoring data, the statistical reference value of each monitoring node within a preset time window is calculated. The statistical reference value is the arithmetic mean of the tilt angle data, the root mean square value of the acceleration data, or the three-dimensional coordinate average of the displacement data. Calculate the deviation between the monitoring data and the corresponding statistical reference value. The deviation is the ratio of the absolute difference of the tilt angle to the standard deviation, the Euclidean modulus of the three-dimensional difference vector of acceleration, or the Euclidean distance of the three-dimensional coordinates of displacement. The deviation is normalized by a preset standardization function to generate a dimensionless monitoring index.

5. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 1, characterized in that, The abnormal monitoring indicators that are filtered out exceeding the first preset threshold include: Dimensionless monitoring indicators whose absolute values ​​exceed the first preset threshold are marked as candidate abnormal indicators. If the candidate abnormal indicator continuously exceeds the first preset threshold within 2-3 consecutive collection cycles, it is determined as an abnormal monitoring indicator. If the candidate abnormal index exceeds the first preset threshold only in a single collection cycle, it is determined to be a transient disturbance and is removed.

6. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 2, characterized in that, The analysis of the spatial distribution characteristics of the monitoring nodes of the anomaly monitoring indicators and the temporal relationship between their collection timestamps to identify event patterns includes: Obtain the position number of the monitoring node that exhibits the abnormal monitoring indicator in the monitoring node sequence; After sorting the monitoring nodes that exhibit the abnormal monitoring indicators according to their location numbers, the location intervals between adjacent abnormal monitoring nodes are calculated to determine the spatial distribution characteristics. If all the location intervals are less than a preset interval threshold, and the number of abnormal monitoring nodes exceeds a preset number threshold, then it is initially determined to be a spatial propagation mode. If the location interval is greater than or equal to the preset interval threshold, or the number of abnormal monitoring nodes does not exceed the preset number threshold, it is initially determined to be a single-point abnormal mode. Extract the collection timestamps of each monitoring node from the preliminary judgment results, analyze the temporal relationship, and complete the final identification of the event pattern.

7. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 6, characterized in that, The process of extracting the collection timestamps of each monitoring node from the preliminary judgment results, analyzing the temporal relationships, and completing the final identification of event patterns includes: If the spatial propagation mode is initially determined, the time interval between the collection timestamps of adjacent monitoring nodes is calculated according to the position number of the monitoring node sequence; If all the time intervals are positive and the locations of the monitoring nodes of the abnormal monitoring indicators form a continuous sequence, then it is confirmed as a spatial propagation mode, and a geological disaster early warning signal is output. If all the time intervals are positive, but the location numbers do not form a continuous sequence, then the physical continuity of the spatial propagation pattern is determined to be interrupted, and it is re-determined as a multi-point independent fault. If a negative time interval exists, it will be reclassified as a single point of failure.

8. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 6, characterized in that, The process of extracting the collection timestamps of each monitoring node from the preliminary judgment results, analyzing the temporal relationships, and completing the final identification of event patterns includes: If it is initially determined to be the single-point anomaly pattern, traverse the monitoring node sequence and investigate other monitoring nodes that show the abnormal monitoring indicators; If no other abnormal monitoring nodes are found, it is confirmed as a single point of failure. If other abnormal monitoring nodes are found, the time interval between the collection timestamps of each abnormal monitoring node is calculated.

9. The slope collaborative monitoring and early warning method for distributed power equipment as described in claim 8, characterized in that: If the collection timestamp interval of all abnormal monitoring nodes exceeds the second preset threshold, it is confirmed as a single-point abnormal mode. If there is a pair of monitoring nodes whose timestamp interval does not exceed the second preset threshold, and the pair of monitoring nodes are adjacent in the monitoring node sequence and the timestamps increase sequentially, then it is re-determined as a spatial propagation mode. If the monitoring nodes are not adjacent, or the timestamps do not increase sequentially, then it is confirmed as a multi-point independent fault.

10. A slope collaborative monitoring and early warning system for distributed power equipment, characterized in that, The slope collaborative monitoring and early warning method for distributed power equipment as described in any one of claims 1 to 9 includes: The data acquisition module is used to acquire the three-dimensional position coordinates of the monitoring nodes of the distributed power equipment deployed along the slope, calculate the cumulative distance of each monitoring node along the upward direction of the slope based on the three-dimensional position coordinates, arrange the monitoring nodes in ascending order of the cumulative distance along the upward direction of the slope to form an ordered sequence of monitoring nodes, and collect monitoring data synchronously through each monitoring node and record the collection timestamp corresponding to each monitoring data. The data processing module is used to standardize the monitoring data to generate dimensionless monitoring indicators, and to filter out abnormal monitoring indicators that exceed a first preset threshold from the dimensionless monitoring indicators. The pattern recognition module is used to analyze the spatial distribution characteristics of the abnormal monitoring indicators and the temporal relationship between their collection timestamps in order to identify event patterns, including spatial propagation patterns and single-point anomaly patterns. The early warning module is used to output a geological disaster early warning signal if the event pattern is identified as the spatial propagation pattern, and to output a device fault signal if the event pattern is identified as the single-point anomaly pattern.

Images