Overhead line risk identification method and device

Abstract

The invention discloses an overhead line risk identification method and device. The method comprises the steps that multiple sets of sonar data corresponding to multiple vehicles in an area where an overhead line is located and collected in a target time period are acquired, and each set of sonar data at least comprises the frequency, the volume and the driving direction; clustering the multiple groups of sonar data according to the frequency to obtain sonar data sets corresponding to different vehicle types; for each group of sonar data in each sonar data set, determining a corresponding target speed according to a frequency-speed relationship, and determining a corresponding target distance according to a volume-distance relationship; and according to the driving direction, the target speed and the target distance in the sonar data, determining a comprehensive risk index of overhead line abnormity caused by the vehicle, and generating risk prompt information under the condition that the comprehensive risk index is greater than a preset risk threshold. The technical problems of low response efficiency and poor service quality caused by limitation of position and height information depending on a traditional identification method are solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent operation and maintenance technology, and specifically to a method and device for identifying risks of overhead lines. Background Art

[0002] Overhead lines are widely used in telecommunications infrastructure construction due to their rapid deployment and relatively low cost. However, this wiring method is not infallible and presents a unique set of challenges, especially in areas with busy roads or frequent vehicle traffic. Traditional monitoring methods often rely on manual recording and regular inspections of line locations and heights. This method is not only time-consuming and labor-intensive, but also difficult to respond to in real-time emergencies. For example, accidental collisions with large vehicles or unintentional scrapes by heavy machinery can damage optical cables, thereby affecting the continuity and stability of communication services.

[0003] In recent years, with the advancement of technology, more intelligent and automated methods have been adopted to identify risks associated with overhead lines. For example, some operators have introduced early warning systems based on location information and altitude changes, indirectly assessing potential risks by monitoring changes in the line's surrounding environment. While these technologies have improved the efficiency of risk warnings to a certain extent, they still have limitations, such as the inability to directly perceive real-time mobile threats and the potential for missing critical risk signals in complex and changing environments. Furthermore, urbanization, coupled with changes in ground elevation and the diversification of vehicle types, further exacerbate the safety risks of overhead optical cables. For example, road elevation renovation projects can lower the relative height of optical cables above the ground, making them more vulnerable to threats from passing vehicles. Furthermore, different types of vehicles (such as large trucks, excavators, and tractors) generate varying levels of vibration and impact at different speeds, creating new challenges for risk management of overhead lines.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a method and device for identifying risks of overhead lines, so as to at least solve the technical problem that the traditional identification method has limitations in relying on location and height information, resulting in low response efficiency and poor service quality.

[0006] According to one aspect of an embodiment of the present application, a method for identifying overhead line risks is provided, comprising: obtaining multiple sets of sonar data corresponding to multiple vehicles in an area where the overhead line is located, collected during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction; clustering the multiple sets of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types; for each sonar data set, determining a frequency-speed relationship and a volume-distance relationship preset for the vehicle type corresponding to the sonar data set; for each set of sonar data in the sonar data set, determining a target speed of the vehicle corresponding to the frequency in the sonar data based on the frequency-speed relationship, and determining a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on the volume-distance relationship; determining a comprehensive risk index for the vehicle causing overhead line abnormality based on the driving direction, target speed, and target distance in the sonar data, and generating risk warning information if the comprehensive risk index is greater than a preset risk threshold.

[0007] Optionally, obtaining multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located during a target time period includes: obtaining multiple sets of sonar data collected by multiple sonar induction loops distributed on the overhead line at multiple collection moments during the target time period, wherein each set of sonar data is used to reflect the driving status of a vehicle at the corresponding collection moment, and each set of sonar data also includes: the identification and position of the corresponding sonar induction loop, and the corresponding collection moment.

[0008] Optionally, multiple groups of sonar data are clustered according to frequency to obtain sonar data sets corresponding to different vehicle types, including: using a target clustering algorithm to cluster multiple frequencies in the multiple groups of sonar data to obtain multiple cluster clusters, wherein the target clustering algorithm includes one of the following: a hierarchical clustering algorithm, a density-based spatial clustering algorithm; for each cluster cluster, determining a target standard frequency that matches the center point of the cluster from multiple standard frequencies corresponding to multiple preset vehicle types, and combining the multiple groups of sonar data corresponding to the multiple frequencies in the cluster cluster into a sonar data set corresponding to the target vehicle type corresponding to the target standard frequency.

[0009] Optionally, the process of determining the frequency-speed relationship corresponding to each vehicle type includes: for each vehicle type, obtaining the frequencies corresponding to the vehicle type collected by the sonar induction loop when traveling at different speeds, wherein the frequency corresponding to the driving speed of 0 is used as the standard frequency corresponding to the vehicle type; determining the difference between each collected frequency and the standard frequency as the Doppler frequency shift; and performing linear fitting on multiple Doppler frequency shifts and corresponding driving speeds to obtain the frequency-speed relationship corresponding to the vehicle type.

[0010] Optionally, the process of determining the volume-distance relationship corresponding to each vehicle type includes: for each vehicle type, obtaining the volume corresponding to the vehicle type collected by the sonar induction loop when the vehicle is at different distances from the sonar induction loop during driving; performing linear fitting on multiple volumes and corresponding distances to obtain the volume-distance relationship corresponding to the vehicle type.

[0011] Optionally, a comprehensive risk index of the vehicle causing overhead line abnormality is determined based on the driving direction, target speed and target distance in the sonar data, including: determining a first risk index matching the target speed from a preset first risk index mapping table, wherein the first risk index mapping table stores a mapping relationship between multiple speed intervals and multiple risk indices; determining a second risk index matching the target distance from a preset second risk index mapping table, wherein the second risk index mapping table stores a mapping relationship between multiple distance intervals and multiple risk indices; determining the angle between the driving direction and the direction of the overhead line; and determining a comprehensive risk index based on the first risk index, the second risk index and the angle.

[0012] Optionally, determining the comprehensive risk index according to the first risk index, the second risk index, and the angle includes: determining the comprehensive risk index according to the following formula:

[0013] R=(1+k·cos 2 θ)·(w1·R1+w2·R2)

[0014] Where R is the comprehensive risk coefficient, R1 and R2 are the first risk index and the second risk index respectively, w1 and w2 are the preset weight coefficients respectively, θ is the angle, and k is the preset adjustment coefficient.

[0015] Optionally, when the comprehensive risk index is greater than a preset risk threshold, risk warning information is generated, including: when the comprehensive risk index is greater than the preset risk threshold, risk warning information is generated, wherein the risk warning information at least includes: the position of the sonar sensing ring that collects the sonar data corresponding to the comprehensive risk index, the corresponding collection time, the vehicle type corresponding to the sonar data set to which the sonar data corresponding to the comprehensive risk index belongs, the target speed of the vehicle, and the target distance between the vehicle and the overhead line.

[0016] According to another aspect of an embodiment of the present application, an overhead line risk identification device is further provided, comprising: an acquisition module for acquiring multiple sets of sonar data corresponding to multiple vehicles in an area where the overhead line is located, collected during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction; a clustering module for clustering the multiple sets of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types; a selection module for determining, for each sonar data set, a preset frequency-speed relationship and volume-distance relationship for the vehicle type corresponding to the sonar data set; a calculation module for determining, for each set of sonar data in the sonar data set, a target speed of the vehicle corresponding to the frequency in the sonar data based on the frequency-speed relationship, and a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on the volume-distance relationship; a risk determination module for determining a comprehensive risk index of a vehicle causing an overhead line abnormality based on the driving direction, target speed, and target distance in the sonar data, and generating risk warning information when the comprehensive risk index is greater than a preset risk threshold.

[0017] According to another aspect of an embodiment of the present application, a computer program product is further provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, the above-mentioned overhead line risk identification method is implemented.

[0018] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned overhead line risk identification method through the computer program.

[0019] In an embodiment of the present application, the frequency and volume data collected by the sonar induction loop, combined with the vehicle's driving direction, the mathematical relationship obtained through preliminary modeling and fitting and the preset mapping relationship can be used to accurately evaluate the risk factors of different vehicle types under different driving conditions. When the risk factor is greater than the preset threshold, it is determined that the relevant vehicle may pose a threat to the overhead line, so as to facilitate early warning and taking measures, thereby solving the technical problem that the traditional identification method relies on the limitations of position and height information, resulting in low response efficiency and poor service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 is a flow chart of an optional overhead line risk identification method according to an embodiment of the present application;

[0022] Figure 2 is a schematic structural diagram of an optional sonar induction loop deployment according to an embodiment of the present application;

[0023] Figure 3 is a schematic structural diagram of an optional overhead line risk identification device according to an embodiment of the present application;

[0024] Figure 4 It is a schematic structural diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0026] It should be noted that the terms "first", "second", etc. in the specification, claims, and drawings of the present application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0027] In order to better understand the embodiments of the present application, some nouns or terms that appear in the description of the embodiments of the present application are first translated and explained as follows:

[0028] Doppler shift is a physical phenomenon that describes the difference between the frequency of sound waves received by an observer and the actual frequency emitted by the source when there is relative motion between the source and the observer. This phenomenon is common in everyday life. For example, when an ambulance passes by, you hear the siren's pitch change; this is a manifestation of Doppler shift. When a moving object (such as a vehicle) approaches or moves away from the sonar sensing loop, the frequency of the sound waves changes. If the object approaches, the frequency of the sound waves increases; if it moves away, the frequency decreases. This frequency change is caused by the Doppler effect. By analyzing this change in the frequency of the received sound waves, a Doppler shift analyzer can calculate the object's speed. This is because the magnitude of the frequency change is directly related to the object's speed; the faster the object, the greater the frequency change.

[0029] Example 1

[0030] According to an embodiment of the present application, a method for identifying overhead line risks is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 1 FIG. 1 is a flow chart of a method for identifying overhead line risks according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0032] Step S102, obtaining multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located, collected during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction;

[0033] Step S104, clustering the multiple sets of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types;

[0034] Step S106 , for each sonar data set, determining a frequency-speed relationship and a volume-distance relationship preset for the vehicle type corresponding to the sonar data set;

[0035] Step S108, for each set of sonar data in the sonar data set, determining a target speed of the vehicle corresponding to the frequency in the sonar data based on the frequency-speed relationship, and determining a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on the volume-distance relationship;

[0036] Step S110, determining a comprehensive risk index of the vehicle causing an overhead line abnormality based on the driving direction, target speed, and target distance in the sonar data, and generating risk warning information when the comprehensive risk index is greater than a preset risk threshold.

[0037] The following describes the various steps of the overhead line risk identification method in conjunction with the specific implementation process.

[0038] Figure 2 A schematic diagram of a sonar induction loop deployment is shown. The sonar induction loops collect data, which is then transmitted to corresponding modules via induction information conveyors for processing. These sonar induction loops are not only spaced along the optical cable axis according to a specific mathematical relationship (e.g., linear relationship), but also provide 360-degree coverage around the overhead line to capture sonar signals from any direction. Each induction loop and its sub-sensing points are uniquely identified. For example, L01H01Z01 represents the first sub-sensing point Z01 of the first induction loop H01 on overhead line L01, and so on. This ensures data traceability and precise positioning.

[0039] As an optional implementation, obtaining multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located during a target time period can be achieved in the following way: obtaining multiple sets of sonar data collected by multiple sonar induction loops distributed on the overhead line at multiple collection moments during the target time period, wherein each set of sonar data is used to reflect the driving status of a vehicle at the corresponding collection moment, and each set of sonar data also includes: the identification and position of the corresponding sonar induction loop, and the corresponding collection moment.

[0040] During a targeted timeframe, such as peak hours, the sonar loop automatically collects sonar data from the surrounding environment. This data includes not only the sonar frequency, volume, and direction of travel generated by the vehicle, but also the loop's own identification (e.g., L01H01), its precise location coordinates on a map, and the data's acquisition timestamp. This continuous stream of digital data allows us to construct a three-dimensional data network encompassing time, space, and frequency for subsequent risk assessment.

[0041] It's important to note that each set of sonar data not only reflects a vehicle's driving status at the specific moment of collection, such as its speed, direction, and distance, but also allows analysis of the vehicle's trajectory and behavior patterns by comparing data collected by different induction loops as the same vehicle passes. This multi-dimensional data collection approach allows us to grasp the overall overview of vehicle activity in the area from a macro perspective, while also delving into details to identify individual high-risk situations, providing a solid foundation for risk assessment. Through in-depth analysis of the collected data, we can predict which vehicle behaviors may pose a threat to overhead lines, such as close passage of heavily loaded vehicles or crossing at unusually high speeds, allowing us to take preventative measures to ensure the safe operation of overhead lines.

[0042] As an optional implementation, clustering multiple groups of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types can be achieved in the following manner: using a target clustering algorithm to cluster multiple frequencies in the multiple groups of sonar data to obtain multiple cluster clusters, wherein the target clustering algorithm includes one of the following: a hierarchical clustering algorithm, a density-based spatial clustering algorithm; for each cluster cluster, determining a target standard frequency that matches the center point of the cluster from multiple standard frequencies corresponding to multiple preset vehicle types, and combining the multiple groups of sonar data corresponding to the multiple frequencies in the cluster cluster into a sonar data set corresponding to the target vehicle type corresponding to the target standard frequency.

[0043] The sonar induction loop continuously collects sonar signals within the target time period. The system records the frequency, volume, driving direction, and corresponding induction loop identification, location, and collection time of each set of sonar data.

[0044] All collected frequency values ​​can be clustered using a relevant clustering algorithm. The algorithm automatically groups similar frequency points into the same cluster based on the frequency characteristics of the sound emitted by the vehicle. Common clustering algorithms include, but are not limited to, hierarchical clustering algorithms and density-based spatial clustering algorithms. Hierarchical clustering algorithms construct a tree-like clustering structure by continuously merging the most similar clusters or splitting the most dissimilar objects. Density-based spatial clustering algorithms, on the other hand, build on the concept of density to automatically discover clusters of any shape, avoiding the limitation of pre-specified cluster numbers or shapes, making vehicle type identification more flexible and accurate.

[0045] For each generated cluster, we further compare it to a pre-set sonar database to find the standard frequency that best matches the cluster's center frequency. This database contains sonar frequency information for various vehicle types (such as trucks, tractors, buses, excavators, etc.) under different conditions. Through this matching process, the system can identify which type of vehicle the cluster's frequency corresponds to.

[0046] Once the matching between clusters and vehicle types is determined, multiple sets of sonar data belonging to the same vehicle type are aggregated to form sonar data sets for a specific vehicle type (the target vehicle type). These sets contain not only the sonar frequency data for a specific vehicle, but also other key information such as travel direction and timestamps, providing detailed data support for subsequent risk assessments.

[0047] Through the above steps, we can systematically identify and classify the types of vehicles around overhead lines, such as cars, trucks, motorcycles, etc. Each vehicle type has its own specific frequency characteristics. For example, trucks usually produce lower frequency sound waves due to their larger size and engine power. The frequency characteristics of cars are relatively high. This frequency-based vehicle type identification not only reduces the errors of manual classification, but also improves the recognition speed, allowing risk assessment to be carried out in real time. This application solves the problem of traditional methods that it is difficult to accurately distinguish different vehicle types and their impact on overhead lines. Through automated data processing, it realizes the refined management of overhead line risks.

[0048] As an optional implementation, the process of determining the frequency-speed relationship corresponding to each vehicle type includes: for each vehicle type, obtaining the frequencies corresponding to the vehicle type collected by the sonar induction loop when traveling at different speeds, wherein the frequency corresponding to the driving speed of 0 is used as the standard frequency corresponding to the vehicle type; determining the difference between each collected frequency and the standard frequency as the Doppler frequency shift; and performing linear fitting on multiple Doppler frequency shifts and corresponding driving speeds to obtain the frequency-speed relationship corresponding to the vehicle type.

[0049] For the sound frequency information collected by the sonar induction loop when different types of vehicles are traveling at different speeds during the target time period, we can regard the frequency when the vehicle is stationary as the standard frequency of that vehicle type. This is because the sound waves in the stationary state do not produce the Doppler effect, and the frequency at this time can be used as a comparison benchmark.

[0050] For each vehicle type, we take the difference between the sound frequency generated by the vehicle at different speeds and its standard frequency value. This difference is the Doppler shift Δf. The Doppler shift reflects the change in the sound frequency with the vehicle speed. It is one of the key factors in assessing potential risks. Table 1 shows the Doppler shift of some vehicle types at different driving speeds.

[0051] Table 1

[0052]

[0053] Next, the calculated Doppler frequency shift data is paired with the corresponding vehicle speed, and the linear regression method in statistics is used to fit the relationship model between the two.

[0054] Assume that the linear regression equation can be expressed as:

[0055] Δf=k·V+z

[0056] Where Δf represents the Doppler frequency shift, V represents the vehicle speed, and k and z are regression coefficients, which can be obtained by using methods such as the least squares method. If the relationship between frequency shift and speed is found to be not completely linear (such as an exponential or logarithmic relationship), we can introduce an intermediate variable t to convert the nonlinear relationship into a linear form and then perform a fitting analysis. For example, if the relationship is assumed to be:

[0057] Δf=a·e b·t

[0058] We can bt Take the natural logarithm and convert it to:

[0059] logΔf=b·t+loga

[0060] Finally, t=V or other appropriate intermediate variables are used to simplify the problem to a linear regression problem, which is easy to calculate and interpret.

[0061] Finally, based on the results of linear fitting, we can determine the frequency-speed relationship corresponding to different vehicle types. The calculation of Doppler shift and the establishment of frequency-speed relationship are the core of the technical solution of this application. It utilizes the Doppler effect in physics, that is, the frequency of sound waves will change due to the relative motion between the sound source and the observer. When the vehicle approaches or moves away from the sonar sensing loop, the frequency of the sound waves it emits will change, and this change is directly related to the speed of the vehicle. Through linear fitting, this solution can establish a mathematical model between frequency and speed, so that in practical applications, only the frequency needs to be measured to infer the vehicle's speed. This method not only improves the accuracy of speed measurement, but also avoids the need to install additional speed sensors, reducing system costs. This solution solves the problem of difficulty in accurately measuring vehicle speed in traditional methods, and provides more accurate speed information for overhead line risk assessment.

[0062] As an optional implementation, the process of determining the volume-distance relationship corresponding to each vehicle type includes: for each vehicle type, obtaining the corresponding volume of the vehicle type collected by the sonar induction loop when the vehicle is at different distances from the sonar induction loop during driving; and performing linear fitting on multiple volume levels and corresponding distances to obtain the volume-distance relationship corresponding to the vehicle type.

[0063] The above process mainly shows the process of determining the volume-distance relationship for each vehicle type. This process aims to quantify the trend of vehicle volume changes as its distance from the sonar induction loop changes, and then assess the risk level when the vehicle is close to the optical cable.

[0064] Using sonar induction loops, we collected volume data generated by dangerous vehicles (such as large trucks, tractors, etc.) at different distances.

[0065] Table 2 shows the volume data for different types of vehicles at different distances from the sonar loop. The data includes the vehicle type, the distance from the sonar loop (equivalent to the overhead line) (denoted as L), and the real-time volume at that distance (denoted as S). This data collection needs to cover a wide range of distances, from long to short, to ensure comprehensiveness and representativeness.

[0066] Table 2

[0067]

[0068] First, we create a scatter plot of the volume S for vehicle type a (e.g., a large truck) versus the distance L to visualize the relationship between the two. We anticipate that the volume will increase as the distance between the vehicle and the sonar loop decreases. If the raw data exhibits a nonlinear relationship (such as an exponential or logarithmic relationship), we employ an intermediate value conversion strategy similar to the one used for processing the relationship between frequency shift and rate. By introducing an intermediate variable t, we convert the nonlinear relationship into a linear one, facilitating subsequent analysis and processing.

[0069] Based on the collected volume-distance data pairs, we used the linear regression method in statistical analysis to fit the relationship model between volume and distance. This model can be expressed as:

[0070] S=m·L+n

[0071] Here, S represents volume, L represents distance, and m and n are regression coefficients, representing the slope and intercept of the relationship between volume and distance. Through fitting, we can intuitively see how volume changes with decreasing distance, providing a scientific basis for risk assessment.

[0072] Ultimately, based on the results of the fitting analysis, we determined a specific volume-distance relationship for each vehicle type. This relationship model not only helps us understand the specific relationship between vehicle volume and distance, but also serves as a tool for predicting future risks. For example, using real-time volume data, we can infer the relative position of a vehicle to the fiber optic cable and assess its potential threat to the cable.

[0073] The above process determines the volume-distance relationship based on acoustic principles and can quantify the distance between the vehicle and the overhead line. Different types of vehicles produce different volumes at different distances due to differences in factors such as engine power and body structure. Through linear fitting, the present application can establish a mathematical model between volume and distance, so that in practical applications, the relative distance between the vehicle and the overhead line can be calculated by simply measuring the volume. This method not only improves the accuracy of distance measurement, but also avoids the need to install additional distance sensors, reducing system complexity and cost. The present application solves the problem of traditional methods that are difficult to accurately measure the distance between the vehicle and the overhead line, and provides more accurate location information for overhead line risk assessment.

[0074] As an optional implementation, determining the comprehensive risk index of the vehicle causing overhead line abnormality based on the driving direction, target speed and target distance in the sonar data can be achieved in the following way: determining a first risk index matching the target speed from a preset first risk index mapping table, wherein the first risk index mapping table stores a mapping relationship between multiple speed intervals and multiple risk indices; determining a second risk index matching the target distance from a preset second risk index mapping table, wherein the second risk index mapping table stores a mapping relationship between multiple distance intervals and multiple risk indices; determining the angle between the driving direction and the direction of the overhead line; and determining a comprehensive risk index based on the first risk index, the second risk index and the angle.

[0075] The above process embodies a comprehensive assessment system for receiving the driving direction, target speed and target distance information extracted from the sonar data to determine the comprehensive risk index of the abnormal risk that the vehicle may cause to the overhead line.

[0076] First, the first risk index mapping table details the mapping relationships between multiple speed ranges and multiple risk indices. Based on the target speed, the first risk index mapping table is compared to determine the risk index (first risk index) that best matches the target speed. The mapping table is designed to account for the positive correlation between speed and risk: faster speeds are associated with higher risk to the route, and vice versa.

[0077] Next, the second risk index mapping table, similar to the first risk index mapping table, records the correspondence between multiple distance intervals and multiple risk indices. Using data collected by the sonar induction loop, we can calculate the real-time distance (target distance) between the hazardous vehicle and the overhead line. By consulting the second risk index mapping table, we find the risk index (second risk index) that matches the target distance. The mapping table is designed based on the principle that closer distances indicate higher risk, and closer distances indicate lower risk.

[0078] It should be noted that only when the volume is greater than a certain value will it be judged that the dangerous vehicle has the risk of affecting overhead lines and optical cables.

[0079]

[0080] Assume that for the dangerous vehicle a, when designing the second risk index mapping table, when the received volume value is less than the safe volume threshold S a0 When , it is considered that there is no risk, the risk index value is 0, and the received volume value is not less than the safe volume threshold S a0 When the volume of the dangerous vehicle a is determined to be S by matching the mapping relationship between the volume interval and the second risk index, a The corresponding risk index.

[0081] In addition to speed and distance, the vehicle's direction of travel is also a crucial factor in assessing overall risk. By analyzing the sonar loop signal, we can determine the angle between the vehicle's direction of travel and the direction of the overhead lines. This angular information helps more accurately assess the risk level of a vehicle approaching a fiber optic cable. Generally, when the vehicle is parallel to the line, the risk assessment warrants greater attention. However, when the vehicle's direction of travel is perpendicular or at a significant angle to the line, its direct impact on the line is less significant, and the risk assessment weighting can be adjusted appropriately.

[0082] After obtaining the first risk index, the second risk index and the angle between the driving direction and the overhead line, we use weighted average or other composite calculation methods to combine these three risk factors into a comprehensive risk index.

[0083] As an optional implementation, determining the comprehensive risk index based on the first risk index, the second risk index, and the angle can be achieved in the following manner: determining the comprehensive risk index based on the following formula:

[0084] R=(1+k·cos 2 θ)·(w1·R1+w2·R2)

[0085] Where R is the comprehensive risk coefficient, R1 and R2 are the first risk index and the second risk index respectively, w1 and w2 are the preset weight coefficients respectively, θ is the angle, and k is the preset adjustment coefficient.

[0086] When calculating the comprehensive risk index, we introduced the angle θ as an important parameter to evaluate the relative position between the vehicle's direction of travel and the overhead line. By adding (1+k·cos 2 θ), we can quantify the impact of direction change on risk assessment. When the vehicle is parallel to the line, cos 2When θ=1, the direction weight adjustment coefficient becomes 1+k, which reflects the risk sensitivity during parallel movement. As θ deviates from 0° or 180°, that is, the relative angle between the vehicle's moving direction and the optical cable increases, cos 2 The value of θ is gradually reduced until, when the vehicle is perpendicular to the line, cos 2 When θ = 0, the direction weight adjustment coefficient becomes 1, indicating that the impact of the direction factor on the risk is minimized, and only the basic risk assessment based on speed and distance is retained.

[0087] Introducing the consideration of the direction factor enables the risk assessment model to more comprehensively reflect the potential threat of mobile sources to overhead optical cables. In particular, when θ is around 0° or 180°, (1+k·cos 2 A higher value of θ helps highlight the increased risk associated with parallel movement, ensuring a more accurate assessment. Adjusting the coefficient k allows the operator to customize the impact of direction on the overall risk based on actual conditions and experience. A larger k value places greater emphasis on the importance of direction in risk assessment, making it suitable for direction-sensitive scenarios such as busy traffic sections or areas with dense fiber optic cables, ensuring the system can respond quickly to parallel approaching vehicles.

[0088] Because cos 2 The characteristics of θ and the existence of the adjustment coefficient k allow this risk weight adjustment mechanism to maintain flexibility under different mobile sources and overhead line patterns. Whether parallel movement, vertical crossing, or angular interspersed, the risk assessment focus can be automatically adjusted according to the specific scenario, improving the adaptability and robustness of the early warning system.

[0089] As an optional implementation, when the comprehensive risk index is greater than a preset risk threshold, risk warning information is generated. This can be achieved in the following way: when the comprehensive risk index is greater than the preset risk threshold, risk warning information is generated, wherein the risk warning information includes at least: the position of the sonar sensing ring that collects the sonar data corresponding to the comprehensive risk index, the corresponding collection time, the vehicle type corresponding to the sonar data set to which the sonar data corresponding to the comprehensive risk index belongs, the target speed of the vehicle, and the target distance between the vehicle and the overhead line.

[0090] The generation of risk warning information is a practical embodiment of the technical solution of this application. It ensures that when a vehicle poses a high risk to overhead lines, maintenance personnel can be notified immediately and necessary preventive measures can be taken, such as adjusting line protection strategies and notifying relevant departments to intervene. This immediate warning mechanism not only improves the efficiency of risk response, but also reduces the possibility of line damage, ensuring the stable operation of the power or communication network. In addition, the detailed content of the risk warning information, such as the location of the sonar sensing loop of the sonar data corresponding to the comprehensive risk index, the time of collection, the type of vehicle, the speed, the distance, etc., provides important data for subsequent accident analysis and risk assessment, which helps to optimize the line protection strategy and improve the overall safety of the system. This solution solves the problems of untimely warnings and incomplete information in traditional monitoring methods. Through the immediate generation of risk warning information, it achieves rapid response and effective management of overhead line risks.

[0091] Through the above steps, the frequency and volume data collected by the sonar induction loop, combined with the vehicle's driving direction, the mathematical relationship obtained through the preliminary modeling and fitting and the preset mapping relationship can be used to accurately evaluate the risk factors of different vehicle types under different driving conditions. When the risk factor is greater than the preset threshold, it is determined that the relevant vehicle may pose a threat to the overhead line, so as to facilitate early warning and take measures, thereby solving the technical problems of low response efficiency and poor service quality caused by the limitations of traditional identification methods that rely on position and height information.

[0092] Example 2

[0093] According to an embodiment of the present application, an overhead line risk identification device for implementing the overhead line risk identification method in Example 1 is also provided. Figure 3 As shown, the overhead line risk identification device at least includes: an acquisition module 31, a clustering module 32, a selection module 33, a calculation module 34 and a risk determination module 35, wherein:

[0094] The acquisition module 31 can acquire multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction;

[0095] The clustering module 32 can cluster multiple sets of sonar data according to frequency to obtain sonar data sets corresponding to different vehicle types;

[0096] The selection module 33 may determine, for each sonar data set, a frequency-speed relationship and a volume-distance relationship preset for the vehicle type corresponding to the sonar data set;

[0097] The calculation module 34 may determine, for each set of sonar data in the sonar data set, a target speed of the vehicle corresponding to the frequency in the sonar data based on a frequency-speed relationship, and determine a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on a volume-distance relationship;

[0098] The risk determination module 35 can determine the comprehensive risk index of the vehicle causing overhead line abnormality based on the driving direction, target speed and target distance in the sonar data, and generate risk warning information when the comprehensive risk index is greater than a preset risk threshold.

[0099] The functions of each module of the overhead line risk identification device are explained below in conjunction with a specific implementation process.

[0100] As an optional implementation, the acquisition module obtains multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located, which are collected during a target time period. This can be achieved in the following way: multiple sets of sonar data collected at multiple collection moments within the target time period by multiple sonar induction loops distributed on the overhead line are obtained, wherein each set of sonar data is used to reflect the driving status of a vehicle at the corresponding collection moment, and each set of sonar data also includes: the identification and position of the corresponding sonar induction loop, and the corresponding collection moment.

[0101] As an optional implementation, the clustering module clusters multiple groups of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types. This can be achieved by: using a target clustering algorithm to cluster multiple frequencies in the multiple groups of sonar data to obtain multiple cluster clusters, wherein the target clustering algorithm includes one of the following: a hierarchical clustering algorithm, a density-based spatial clustering algorithm; for each cluster cluster, determining a target standard frequency that matches the center point of the cluster from multiple standard frequencies corresponding to multiple preset vehicle types, and combining the multiple groups of sonar data corresponding to the multiple frequencies in the cluster cluster into a sonar data set corresponding to the target vehicle type corresponding to the target standard frequency.

[0102] As an optional implementation, the process of determining the frequency-speed relationship corresponding to each vehicle type includes: for each vehicle type, obtaining the frequencies corresponding to the vehicle type collected by the sonar induction loop when traveling at different speeds, wherein the frequency corresponding to the driving speed of 0 is used as the standard frequency corresponding to the vehicle type; determining the difference between each collected frequency and the standard frequency as the Doppler frequency shift; and performing linear fitting on multiple Doppler frequency shifts and corresponding driving speeds to obtain the frequency-speed relationship corresponding to the vehicle type.

[0103] As an optional implementation, the process of determining the volume-distance relationship corresponding to each vehicle type includes: for each vehicle type, obtaining the corresponding volume of the vehicle type collected by the sonar induction loop when the vehicle is at different distances from the sonar induction loop during driving; and performing linear fitting on multiple volume levels and corresponding distances to obtain the volume-distance relationship corresponding to the vehicle type.

[0104] As an optional implementation, determining the comprehensive risk index of the vehicle causing overhead line abnormality based on the driving direction, target speed and target distance in the sonar data can be achieved in the following way: the calculation module determines a first risk index matching the target speed from a preset first risk index mapping table, wherein the first risk index mapping table stores a mapping relationship between multiple speed intervals and multiple risk indices; determines a second risk index matching the target distance from a preset second risk index mapping table, wherein the second risk index mapping table stores a mapping relationship between multiple distance intervals and multiple risk indices; the risk determination module determines the angle between the driving direction and the direction of the overhead line; and determines the comprehensive risk index based on the first risk index, the second risk index and the angle.

[0105] As an optional implementation, the risk determination module determines the comprehensive risk index based on the first risk index, the second risk index, and the angle, which can be achieved by: determining the comprehensive risk index according to the following formula:

[0106] R=(1+k·cos 2 θ)·(w1·R1+w2·R2)

[0107] Where R is the comprehensive risk coefficient, R1 and R2 are the first risk index and the second risk index respectively, w1 and w2 are the preset weight coefficients respectively, θ is the angle, and k is the preset adjustment coefficient.

[0108] As an optional implementation, the risk determination module generates risk warning information when the comprehensive risk index is greater than a preset risk threshold. This can be achieved in the following way: when the comprehensive risk index is greater than the preset risk threshold, risk warning information is generated, wherein the risk warning information includes at least: the position of the sonar sensing ring that collects the sonar data corresponding to the comprehensive risk index, the corresponding collection time, the vehicle type corresponding to the sonar data set to which the sonar data corresponding to the comprehensive risk index belongs, the target speed of the vehicle, and the target distance between the vehicle and the overhead line.

[0109] It should be noted that each module in the overhead line risk identification device in the embodiment of the present application corresponds one-to-one to each implementation step of the overhead line risk identification method in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1 and will not be elaborated here.

[0110] Example 3

[0111] According to an embodiment of the present application, a computer program product is further provided. The computer program product includes a computer program, wherein when the computer program is executed by a processor, the overhead line risk identification method in Example 1 is implemented.

[0112] According to an embodiment of the present application, a non-volatile storage medium is further provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the overhead line risk identification method in Example 1 by running the computer program.

[0113] According to an embodiment of the present application, a processor is further provided, which is used to run a computer program, wherein the overhead line risk identification method in Example 1 is executed when the computer program is run.

[0114] According to an embodiment of the present application, an electronic device is further provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the overhead line risk identification method in Example 1 through the computer program.

[0115] Specifically, the computer program executes the following steps when it is run: obtaining multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located, collected during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction; clustering the multiple sets of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types; for each sonar data set, determining a frequency-speed relationship and a volume-distance relationship preset for the vehicle type corresponding to the sonar data set; for each set of sonar data in the sonar data set, determining a target speed of the vehicle corresponding to the frequency in the sonar data based on the frequency-speed relationship, and determining a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on the volume-distance relationship; determining a comprehensive risk index of the vehicle causing an abnormality in the overhead line based on the driving direction, target speed, and target distance in the sonar data, and generating risk warning information when the comprehensive risk index is greater than a preset risk threshold.

[0116] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 4The following is a hardware block diagram of an electronic device for implementing a method for identifying overhead line risks. Figure 4 As shown, the electronic device 40 may include one or more (402a, 402b, ..., 402n are shown in the figure) processors 402 (the processor 402 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 404 for storing data, and a transmission device 406 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components than shown, or with Figure 4 Different configurations shown.

[0117] It should be noted that the one or more processors 402 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single, independent processing module, or may be incorporated in whole or in part into any of the other components of the electronic device 40. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0118] Memory 404 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the overhead line risk identification method in the embodiments of the present application. Processor 402 executes the software programs and modules stored in memory 404 to perform various functional applications and data processing, thereby implementing the aforementioned application vulnerability detection method. Memory 404 can include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 404 may further include memory remotely located from processor 402, which can be connected to electronic device 40 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0119] Transmission device 406 is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the communications provider of electronic device 40. In one embodiment, transmission device 406 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 406 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0120] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 40 .

[0121] The serial numbers of the above embodiments are for description only and do not represent the advantages or disadvantages of the embodiments.

[0122] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0124] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0125] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0126] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0127] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for identifying overhead line risks, characterized in that: include: Acquire multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located, collected during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction; Clustering the multiple sets of sonar data according to frequency to obtain sonar data sets corresponding to different vehicle types; For each sonar data set, determining a frequency-speed relationship and a volume-distance relationship preset for the vehicle type corresponding to the sonar data set; For each set of sonar data in the sonar data set, determining a target speed of the vehicle corresponding to the frequency in the sonar data based on the frequency-speed relationship, and determining a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on the volume-distance relationship; A comprehensive risk index of the vehicle causing an overhead line abnormality is determined based on the driving direction, the target speed, and the target distance in the sonar data, and risk warning information is generated when the comprehensive risk index is greater than a preset risk threshold.

2. The method according to claim 1, characterized in that Acquire multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead lines are located during the target time period, including: Acquire multiple sets of sonar data collected by multiple sonar induction loops distributed on the overhead line at multiple collection times within the target time period, wherein each set of sonar data is used to reflect the driving status of a vehicle at the corresponding collection time, and each set of sonar data also includes: the identification and location of the corresponding sonar induction loop, and the corresponding collection time.

3. The method according to claim 1, characterized in that Clustering the multiple sets of sonar data based on frequency to obtain sonar data sets corresponding to different vehicle types, including: Clustering multiple frequencies in multiple groups of sonar data using a target clustering algorithm to obtain multiple clusters, wherein the target clustering algorithm includes one of the following: a hierarchical clustering algorithm and a density-based spatial clustering algorithm; For each cluster, a target standard frequency that matches the center point of the cluster is determined from multiple standard frequencies corresponding to multiple preset vehicle types, and multiple groups of sonar data corresponding to the multiple frequencies in the cluster are combined into a sonar data set corresponding to the target vehicle type corresponding to the target standard frequency.

4. The method according to claim 1, wherein The process of determining the frequency-speed relationship for each vehicle type includes: For each vehicle type, obtain the frequencies corresponding to the vehicle type when traveling at different speeds, as collected by the sonar induction loop, wherein the frequency corresponding to a traveling speed of 0 is used as the standard frequency corresponding to the vehicle type; Determine the difference between each collected frequency and the standard frequency as a Doppler shift; Linear fitting is performed on the multiple Doppler frequency shifts and the corresponding driving speeds to obtain a frequency-speed relationship corresponding to the vehicle type.

5. The method according to claim 1, characterized in that The process of determining the volume-distance relationship for each vehicle type includes: For each vehicle type, obtaining the volume of the vehicle of the vehicle type collected by the sonar induction loop when the vehicle is at different distances from the sonar induction loop during driving; A linear fit is performed on the multiple volumes and the corresponding distances to obtain a volume-distance relationship corresponding to the vehicle type.

6. The method according to claim 1, characterized in that Determining a comprehensive risk index of the vehicle causing an overhead line anomaly based on the driving direction, the target speed, and the target distance in the sonar data includes: determining a first risk index that matches the target speed from a preset first risk index mapping table, wherein the first risk index mapping table stores mapping relationships between a plurality of speed intervals and a plurality of risk indices; Determining a second risk index that matches the target distance from a preset second risk index mapping table, wherein the second risk index mapping table stores mapping relationships between multiple distance intervals and multiple risk indices; determining an angle between the direction of travel and the direction of the overhead line; The comprehensive risk index is determined based on the first risk index, the second risk index and the angle.

7. The method according to claim 6, characterized in that Determining the comprehensive risk index based on the first risk index, the second risk index, and the angle includes: The comprehensive risk index is determined according to the following formula: R=(1+k·cos 2 θ)·(w1·R1+w2·R2) In the formula, R is the comprehensive risk coefficient, R1 and R2 are the first risk index and the second risk index respectively, w1 and w2 are preset weight coefficients respectively, θ is the angle, and k is a preset adjustment coefficient.

8. The method according to claim 2, characterized in that When the comprehensive risk index is greater than the preset risk threshold, risk warning information is generated, including: When the comprehensive risk index is greater than a preset risk threshold, the risk warning information is generated, wherein the risk warning information at least includes: the position of the sonar sensing ring that collects the sonar data corresponding to the comprehensive risk index, the corresponding collection time, the vehicle type corresponding to the sonar data set to which the sonar data corresponding to the comprehensive risk index belongs, the target speed of the vehicle, and the target distance between the vehicle and the overhead line.

9. An overhead line risk identification device, characterized in that: include: An acquisition module is configured to acquire multiple sets of sonar data corresponding to multiple vehicles in the area where the overhead line is located, collected during a target time period, wherein each set of sonar data includes at least: frequency, volume, and driving direction; A clustering module, configured to cluster the multiple sets of sonar data according to frequency to obtain sonar data sets corresponding to different vehicle types; A selection module is configured to determine, for each sonar data set, a frequency-speed relationship and a volume-distance relationship preset for a vehicle type corresponding to the sonar data set; a calculation module configured to determine, for each set of sonar data in the sonar data set, a target speed of the vehicle corresponding to the frequency in the sonar data based on the frequency-speed relationship, and determine a target distance between the vehicle and the overhead line corresponding to the volume in the sonar data based on the volume-distance relationship; The risk determination module is used to determine the comprehensive risk index of the vehicle causing overhead line abnormality based on the driving direction, the target speed and the target distance in the sonar data, and generate risk warning information when the comprehensive risk index is greater than a preset risk threshold.

10. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the overhead line risk identification method according to any one of claims 1 to 8 is implemented.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the overhead line risk identification method according to any one of claims 1 to 8 through the computer program.

Images