Intelligent supervision system and method based on power line carrier communication

Abstract

The invention discloses an intelligent supervision system and method based on power line carrier communication, and belongs to the technical field of power supervision. The method comprises the following steps: calculating theoretical signal emission intensity under an ideal free space condition; introducing an environment correction coefficient, and correcting the theoretical signal emission intensity; potential monitoring points in the tunnel are clustered, selection of the monitoring points is optimized, and a monitoring point set is obtained; monitoring the signal emission intensity of the antenna in the tunnel, and comparing the signal emission intensity with the theoretical signal emission intensity to obtain an emission intensity difference set; defining a graph structure, determining a power line carrier communication coverage node corresponding to each monitoring point, and binding a transmission intensity difference value; calculating a threshold range of emission intensity differences associated with all nodes, and marking potential abnormal candidate nodes; node neighborhood connection characteristics are analyzed; and tracking the conduction direction of the abnormal difference along the transmission path of the power line carrier communication, judging abnormal nodes, and forming an abnormal node set of the power line carrier communication.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power supervision, and particularly relates to an intelligent supervision system and method based on power carrier communication. BACKGROUND

[0002] In a closed and narrow space such as a tunnel, power carrier communication is widely used for device state monitoring and data transmission due to the characteristics of no additional wiring and adaptation to complex environment. However, the environment in the tunnel is complex, and the antenna signal propagation is easily affected, resulting in communication quality fluctuation. At the same time, the power carrier communication network has many nodes and a complex topology, and the traditional supervision method is difficult to accurately capture signal abnormalities and locate fault nodes, which brings hidden dangers to the safety of tunnel operation.

[0003] The prior art often adopts uniform point distribution or experience point distribution method, without combining the antenna radiation characteristics and the tunnel structure for targeted optimization, resulting in monitoring redundancy in some areas and monitoring missing in key areas, and the real signal state cannot be fully reflected. The abnormality determination of the communication network node depends on manual investigation or simple threshold judgment, without combining the connection relationship between nodes and the signal conduction law, and it is difficult to quickly locate the core fault node and to distinguish between node faults and conduction abnormalities. The signal monitoring, network topology and node state are regarded as independent modules, and the correlation mechanism of multi-dimensional data is not established, and the system abnormality cannot be identified from a global perspective, and the overall and forward-looking of supervision is insufficient. SUMMARY

[0004] The purpose of the present application is to provide an intelligent supervision system and method based on power carrier communication to solve the problems in the prior art.

[0005] To achieve the above purpose, the present application provides the following technical scheme: In a first aspect, the present application provides an intelligent supervision method based on power carrier communication, comprising the following steps: Collecting the working parameters and environmental parameters of the antenna and calculating the antenna radiation power; based on the antenna radiation power, calculating the theoretical signal transmission intensity according to the inverse square law under ideal free space conditions; based on the influence of the geometric structure of the tunnel on signal propagation, introducing an environmental correction coefficient to correct the theoretical signal transmission intensity; Obtaining the antenna characteristics and tunnel characteristics, clustering the potential monitoring points in the tunnel, optimizing the selection of monitoring points, and obtaining a monitoring point set; based on the monitoring point set, monitoring the signal transmission intensity of the antenna in the tunnel, comparing with the theoretical signal transmission intensity, and obtaining a transmission intensity difference set; A graph structure is defined by taking each node in the power carrier communication network as a vertex of the graph and taking the communication connection relationship between the nodes as an edge of the graph; according to the physical positions of the monitoring point set, the power carrier communication coverage node corresponding to each monitoring point is determined, and the transmission intensity difference of the monitoring point is bound to the vertex attribute of the corresponding node; a threshold range of the transmission intensity difference associated with all nodes is calculated, and a potential abnormal candidate node is marked; In defining the graph structure, all functional nodes involved in the power carrier communication system in the tunnel are acquired, including the communication module of an antenna, a signal relay node, a data forwarding node, a control terminal node, etc., and each node is given a unique identifier for distinction. The actual communication links between the nodes are checked one by one to determine which nodes have a direct power carrier signal transmission relationship, the connection direction is recorded, and a node connection list is formed. Each node is corresponded to a vertex of the graph, and the communication connection relationship between the nodes is corresponded to an edge of the graph. For example, if node A and node B have a bidirectional communication, A and B are represented by two vertices in the graph, and a non-directed edge is used for connection; if it is unidirectional transmission, a directed edge is used to represent the transmission direction. An attribute describing the connection characteristics is added to each edge. The vertices and edges are combined according to the actual connection relationship to form an initial graph structure.

[0006] For the potential abnormal candidate node, the connection characteristics of the node neighborhood are analyzed; the conduction direction of the abnormal difference is tracked along the transmission path of the power carrier communication to determine the abnormal node; and all vertices determined to be abnormal are integrated to form a set of abnormal nodes of the power carrier communication.

[0007] In combination with the first aspect, in a first implementation manner of the first aspect of the present application, the theoretical signal transmission intensity is calculated based on the antenna radiation power under ideal free space conditions according to the inverse square law, including: The antenna radiation power represents the total energy radiated by the antenna to the space in an ideal state. The propagation environment is set to be ideal free space, specifically, there are no any obstacles, reflectors and electromagnetic interference, and the energy attenuation is only caused by space diffusion in the signal propagation process without other additional losses; the antenna is taken as a point radiation source, and the signals radiated by the antenna are uniformly propagated to the surrounding in the form of spherical waves; In ideal free space, the wave front of the spherical wave is a complete sphere, the energy is uniformly distributed on the sphere, and the propagation direction is not hindered and extends along a straight line in all directions; the total power radiated by the antenna is uniformly distributed on the sphere with the antenna as the sphere center and the propagation distance as the radius; the theoretical signal transmission intensity at a certain distance is specifically the proportion of the radiation power allocated to the sphere area corresponding to the distance; the target distance at which the theoretical signal transmission intensity needs to be calculated is determined, specifically the straight line distance from the antenna to the monitoring point; according to the inverse square law, the sphere area at the distance is proportional to the square of the distance; the signal energy per unit area at the distance is obtained by dividing the antenna radiation power by the sphere area, which is taken as the theoretical signal transmission intensity.

[0008] In combination with the first aspect, in a second implementation of the first aspect of the application, the influence of the tunnel-based geometric structure on signal propagation introduces an environmental correction coefficient to correct the theoretical signal emission intensity, including: The geometric structure of the tunnel includes the length, cross-sectional shape, diameter, degree of curvature, and whether there are branches of the tunnel; by analyzing historical data of similar tunnels, a correlation between geometric structure factors and signal attenuation degree is obtained, which reflects the loss of signal energy under different geometric structures; taking the signal propagation state under ideal free space conditions as the benchmark, the environmental correction coefficient is 1, representing no additional attenuation; according to the correlation, an adjustment rule for the environmental correction coefficient is developed, when there are geometric structure factors that cause signal attenuation, the environmental correction coefficient is less than 1, and the more severe the attenuation, the smaller the environmental correction coefficient; According to the geometric structure of the current tunnel, the corresponding environmental correction coefficient is calculated by comparing the geometric structure factors and the adjustment rule; the calculated environmental correction coefficient is used to multiply the theoretical signal emission intensity to correct it.

[0009] In combination with the first aspect, in a third implementation of the first aspect of the application, the antenna characteristics and tunnel characteristics are obtained, the potential monitoring points in the tunnel are clustered, the selection of monitoring points is optimized, and a monitoring point set is obtained, including: The antenna characteristics include radiation direction, coverage range, and signal strength distribution law, and the tunnel characteristics include length, width, curved segment position, and material; potential monitoring points are pre-set in the tunnel to cover all areas of the tunnel; according to the signal strength distribution law in the antenna characteristics, it is determined whether the signal characteristics at different potential monitoring points are similar, and the DBSCAN algorithm is used to classify potential monitoring points with similar signal characteristics into the same cluster, and the monitoring points in the same cluster have consistency in signal performance, representing the signal characteristics of the area; through clustering, the potential monitoring points are divided into several clusters; The goal of reinforcement learning is to select monitoring points from the clusters obtained by clustering, so that the monitoring points cover all key signal areas in the tunnel with the least number; the signal environment in the tunnel is regarded as the environment of reinforcement learning, each cluster is regarded as a selectable state, and the selection of a monitoring point in a cluster is regarded as an action; the reinforcement learning agent starts from the initial state and gradually selects monitoring points in different clusters; after each selection, rewards or punishments are given according to whether the coverage of the selected monitoring point is comprehensive and whether it can effectively reflect signal changes; through continuous trial and adjustment of the selection strategy, the agent gradually learns the optimal selection method, filters out a number of suitable and reasonably distributed monitoring points to form the monitoring point set.

[0010] In a fourth implementation form of the first aspect, the first aspect further includes that the signal transmission intensity difference set is obtained by comparing the signal transmission intensity of the antennas in the tunnel with the theoretical signal transmission intensity based on the set of monitoring points. The external signal monitoring devices are installed at each monitoring point in the tunnel based on the set of monitoring points, and the signal transmission intensity of the antennas at each monitoring point in the tunnel is monitored by starting the external monitoring devices. The theoretical signal transmission intensity corresponding to each monitoring point is retrieved, and the actual signal transmission intensity of each monitoring point is compared with the corresponding theoretical signal transmission intensity at each time point. For each time point, the actual signal transmission intensity of the monitoring point is subtracted from the theoretical signal transmission intensity to obtain the signal transmission intensity difference at the time point. The signal transmission intensity differences of all monitoring points at each time point are integrated and sorted according to the monitoring point position and time point to obtain the signal transmission intensity difference set.

[0011] In a fifth implementation form of the first aspect, the first aspect further includes that the power carrier communication coverage node corresponding to each monitoring point is determined according to the physical position of the set of monitoring points, and the signal transmission intensity difference of the monitoring point is bound to the vertex attribute of the corresponding node. The physical position of each monitoring point is compared with the coverage range of each node to determine which node the monitoring point belongs to. When the position of the monitoring point is within the coverage range of a node, and the node is the closest node with the most stable signal connection, the node is determined as the power carrier communication coverage node corresponding to the monitoring point. For a monitoring point in the overlapping area of the coverage ranges of multiple nodes, the node with the best signal transmission quality is selected as the power carrier communication coverage node through historical communication data. For each power carrier communication coverage node, the signal transmission intensity differences of all monitoring points corresponding to the node are collected and added to the vertex attribute of the node in the graph structure as a new attribute.

[0012] In a sixth implementation form of the first aspect, the first aspect further includes that the threshold range of the signal transmission intensity differences associated with all nodes is calculated, and the potential abnormal candidate node is marked. The signal transmission intensity differences associated with all nodes are extracted from the graph structure, and a threshold range is set based on the overall distribution characteristics of the signal transmission intensity differences. For each node, the signal transmission intensity differences of all monitoring points corresponding to the node are obtained, and whether each signal transmission intensity difference is within the threshold range is determined one by one. When part or all of the signal transmission intensity differences of a node are outside the threshold range, the node is marked as a potential abnormal candidate node.

[0013] In a seventh implementation form of the first aspect, the first aspect further includes that the node neighborhood connection characteristics of the potential abnormal candidate node are analyzed. Determine the neighborhood nodes of each potential abnormal candidate node, specifically all nodes directly connected to the potential abnormal candidate node through edges; query whether each neighborhood node is a potential abnormal candidate node, record the emission intensity difference value of the neighborhood node, and form a neighborhood node state list; Based on the neighborhood node state list, collect the connection attributes of the edges between the potential abnormal candidate node and the neighborhood nodes and the label information of the potential abnormal candidate node to obtain a data set; use the support and confidence indicators in the association rule mining method to analyze the association strength of the connection attributes and the label information in the data set, and when the support and confidence of a certain connection attribute and the label information are both higher than the set threshold, and the neighborhood node is in the communication transmission direction between the potential abnormal candidate node and the neighborhood node, it is determined that there is a strong matching relationship between the connection attribute and the neighborhood node.

[0014] In combination with the first aspect, in an eighth implementation manner of the first aspect of the present application, the transmission path along the power carrier communication, the conduction direction of the abnormal difference value, and the determination of the abnormal node include: Determine the main transmission path of data in the power carrier communication network, specifically the main node connection sequence from the signal source to the data terminal, record the node connection relationship of each branch path, and form a transmission path atlas; based on the transmission path atlas, for the nodes with a strong matching relationship, obtain their positions in the main transmission path; when the node is the starting node of a certain path, and its abnormal difference value appears earlier than the downstream nodes, and the abnormal difference value of the downstream nodes is consistent with that of the node, the node is determined as a potential starting point of abnormal conduction; start from the potential starting point, and sequentially check the abnormality of the downstream nodes along the transmission path; when the abnormal difference value of the downstream nodes gradually weakens with the increase of the distance from the starting point, and the abnormality of each node has a strong matching connection attribute with the previous node, it is confirmed that the abnormal difference value is conducted along the path, and the abnormal conduction path is recorded, including the conduction direction and the abnormal appearance order of each node; In the abnormal conduction path, when a node is the original source of the abnormal difference value, and the abnormal difference value amplitude of the node is the largest, the node is determined as a core abnormal node; wherein the condition for judging the original source is that the node has the earliest abnormal appearance time, and no upstream node conducts the abnormality to the node through a strong matching connection; in the downstream transmission path of the core abnormal node, the node that appears the abnormal difference value due to the strong matching connection with the core abnormal node or the previous abnormal node, and does not have an independent abnormal trigger factor itself, is determined as a derivative abnormal node; for the potential abnormal candidate node, when the connection attribute of the potential abnormal candidate node and the neighborhood node does not have a strong matching relationship, and no upstream node conducts the abnormality to the node in the transmission path, and the abnormal difference value of the potential abnormal candidate node is not associated with other nodes, the potential abnormal candidate node is determined as a self-fault node, and the abnormality of the potential abnormal candidate node is caused by the self hardware or local environmental problem, and is not related to the conduction.

[0015] In a second aspect, the application provides an intelligent monitoring system based on power carrier communication, comprising: The theoretical signal transmission intensity calculation module comprises an antenna radiation power calculation unit, a theoretical signal transmission intensity calculation unit and a theoretical signal transmission intensity correction unit; the antenna radiation power calculation unit collects the working parameters and environmental parameters of the antenna and calculates the antenna radiation power; the theoretical signal transmission intensity calculation unit calculates the theoretical signal transmission intensity under ideal free space conditions based on the antenna radiation power according to the inverse square law; and the theoretical signal transmission intensity correction unit corrects the theoretical signal transmission intensity based on the influence of the geometric structure of the tunnel on signal propagation by introducing an environmental correction coefficient. The transmission intensity difference calculation module comprises a monitoring point generation unit and a transmission intensity difference calculation unit; the monitoring point generation unit obtains the antenna features and the tunnel features, clusters the potential monitoring points in the tunnel, optimizes the selection of the monitoring points and obtains a monitoring point set; and the transmission intensity difference calculation unit monitors the signal transmission intensity of the antenna in the tunnel based on the monitoring point set, compares the signal transmission intensity with the theoretical signal transmission intensity and obtains a transmission intensity difference set. The potential anomaly marking module comprises a graph structure definition unit, a transmission intensity difference binding unit and a potential anomaly marking unit; the graph structure definition unit defines a graph structure by taking each node in the power carrier communication network as a vertex of the graph and taking the communication connection relationship between the nodes as an edge of the graph; the transmission intensity difference binding unit determines the power carrier communication coverage node corresponding to each monitoring point according to the physical location of the monitoring point set and binds the transmission intensity difference of the monitoring point to the vertex attribute of the corresponding node; and the potential anomaly marking unit calculates the threshold range of the transmission intensity difference associated with all nodes and marks the potential anomaly candidate nodes. The abnormal node set generation module comprises a neighborhood connection characteristic analysis unit, an abnormal node determination unit and an abnormal node set generation unit; the neighborhood connection characteristic analysis unit analyzes the neighborhood connection characteristics of the potential anomaly candidate nodes; the abnormal node determination unit traces the conduction direction of the abnormal difference along the transmission path of the power carrier communication and determines the abnormal nodes; and the abnormal node set generation unit integrates all the vertices determined to be abnormal to form an abnormal node set of the power carrier communication.

[0016] Compared with the prior art, the application has the following beneficial effects: 1. The application selects monitoring points through clustering and optimization algorithms, realizes on-demand point placement in combination with the antenna features and the tunnel structure, reduces redundancy while ensuring comprehensive signal coverage, reduces data collection costs and improves monitoring efficiency.

[0017] 2. This application analyzes the neighborhood connectivity characteristics of nodes based on graph structure analysis and combines signal transmission path tracing to identify the source of anomalies. It can quickly distinguish core abnormal nodes, derived abnormal nodes, and self-faulty nodes, achieving accurate fault location and shortening troubleshooting time.

[0018] 3. This application establishes a correlation mechanism between signal monitoring, network topology and node status, integrating scattered data into a global view, which can identify systemic anomaly risks, provide decision support for preventive maintenance of tunnel communication networks, and enhance the initiative and comprehensiveness of supervision. Attached Figure Description

[0019] Fig. 1 This is a schematic diagram illustrating the steps of an intelligent monitoring method based on power line carrier communication according to the present invention. Fig. 2 This is a system structure diagram of an intelligent monitoring system based on power line carrier communication according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Example: Figs. 1-2 As shown, the present invention provides a technical solution. like Fig. 1 As shown, this application provides an intelligent monitoring method based on power line carrier communication, including the following steps: Step S100: Collect the antenna's operating parameters and environmental parameters, and calculate the antenna's radiated power; based on the antenna's radiated power, under ideal free space conditions, calculate the theoretical signal transmission intensity according to the inverse square law; based on the influence of the tunnel's geometry on signal propagation, introduce an environmental correction coefficient to correct the theoretical signal transmission intensity; Specifically, antenna radiated power represents the total energy radiated into space by the antenna under ideal conditions. The propagation environment is set as ideal free space, specifically where there are no obstacles, reflectors, or electromagnetic interference. During signal propagation, energy attenuation only occurs due to spatial diffusion, with no other additional losses. The antenna is used as a point radiation source, and the radiated signal propagates uniformly in all directions in the form of a spherical wave. In ideal free space, the wavefront of a spherical wave is a complete sphere, with energy uniformly distributed on the surface and unimpeded propagation in all directions along a straight line. The total power radiated by the antenna is uniformly distributed on a sphere with the antenna as its center and the propagation distance as its radius. The theoretical signal transmission intensity at a certain distance is specifically the proportion of radiated power allocated to the spherical area corresponding to that distance. The target distance for calculating the theoretical signal transmission intensity is determined as the straight-line distance from the antenna to the monitoring point. According to the inverse square law, the spherical area at that distance is proportional to the square of the distance. Dividing the antenna radiated power by the spherical area yields the signal energy per unit area at that distance, which is taken as the theoretical signal transmission intensity.

[0022] Furthermore, the tunnel's geometry includes its length, cross-sectional shape, diameter, curvature, and whether it branches. By analyzing historical data from similar tunnels, the correlation between geometric factors and signal attenuation is obtained, reflecting the signal energy loss under different geometric structures. Using the signal propagation state under ideal free space conditions as a benchmark, the environmental correction coefficient is 1, representing no additional attenuation. Based on this correlation, an adjustment rule for the environmental correction coefficient is established: when geometric factors causing signal attenuation exist, the environmental correction coefficient is less than 1, and the more severe the attenuation, the smaller the environmental correction coefficient. Based on the current tunnel geometry, and in accordance with the established geometric factors and adjustment rules, the corresponding environmental correction coefficient is calculated. The calculated environmental correction coefficient is then multiplied by the theoretical signal transmission strength for correction.

[0023] In one specific embodiment, a circular tunnel with a length of 1000 meters and a cross-sectional diameter of 5 meters is selected, with two 90° bends (located at 300 meters and 700 meters respectively), and the tunnel wall is made of reinforced concrete; a certain type of directional antenna with an operating frequency of 500 kHz is used and deployed at the tunnel starting point (0 meters).

[0024] Antenna operating parameters: operating voltage 220V, operating current 0.5A, power conversion efficiency 90%, antenna inherent efficiency 85%.

[0025] Calculate the input power: 220V × 0.5A = 110W. After correction, the input power is 110W × 90% = 99W.

[0026] Environmental parameters collected: temperature 25℃, humidity 60% inside the tunnel, no strong electromagnetic interference, environmental efficiency correction factor 0.95, spatial attenuation influence factor 0.9 (because the antenna is 1 meter away from the tunnel wall, the material has little effect on signal attenuation).

[0027] Calculate the antenna radiated power: 99W × 85% × 0.95 × 0.9 ≈ 68.5W.

[0028] Select target monitoring points: respectively located at 100 meters (straight section), 350 meters (just after the first curved section), 800 meters (after the second curved section) of the tunnel, the straight distance antennas are 100 meters, 350 meters, 800 meters respectively.

[0029] 100 meters: the spherical area is 4π×(100m)²≈125664m², the theoretical signal transmission intensity = 68.5W÷125664m²≈0.000545W / m².

[0030] 350 meters: the spherical area is 4π×(350m)²≈1539380m², the theoretical signal transmission intensity = 68.5W÷1539380m²≈0.0000445W / m².

[0031] 800 meters: the spherical area is 4π×(800m)²≈8042477m², the theoretical signal transmission intensity = 68.5W÷8042477m²≈0.0000085W / m².

[0032] Straight section (100 meters): no bending, uniform cross section, small influence of geometric structure on signal attenuation, environment correction coefficient 0.9 (slight attenuation). The corrected signal intensity = 0.000545W / m²×0.9≈0.00049W / m².

[0033] Just after the curved section (350 meters): the bending causes signal diffraction loss, and the environment correction coefficient is 0.6. The corrected signal intensity = 0.0000445W / m²×0.6≈0.0000267W / m².

[0034] After the second curved section (800 meters): double bending + distance increase, serious attenuation, environment correction coefficient 0.3. The corrected signal intensity = 0.0000085W / m²×0.3≈0.00000255W / m².

[0035] Step S200: Obtain the antenna features and tunnel features, cluster the potential monitoring points in the tunnel, optimize the selection of monitoring points, and obtain a monitoring point set; based on the monitoring point set, monitor the signal transmission intensity of the antenna in the tunnel, compare it with the theoretical signal transmission intensity, and obtain a transmission intensity difference set; Specifically, the antenna characteristics are obtained, including radiation direction, coverage range and signal strength distribution law, and the tunnel characteristics are obtained, including the length, width, bending segment position and material of the tunnel; potential monitoring points are preset in the tunnel to cover each area of the tunnel; according to the signal strength distribution law in the antenna characteristics, it is judged whether the signal characteristics at different potential monitoring points are similar, the DBSCAN algorithm is used to classify the potential monitoring points with similar signal characteristics into the same cluster, and the monitoring points in the same cluster have consistency in signal performance, representing the signal characteristics of the area; through clustering, the potential monitoring points are divided into several clusters; The goal of reinforcement learning is to select monitoring points from the clusters obtained by clustering, so that the monitoring points cover all key signal areas in the tunnel with the least number; the signal environment in the tunnel is regarded as the environment of reinforcement learning, each cluster is regarded as a selectable state, and the selection of a monitoring point in a cluster is regarded as an action; the reinforcement learning agent starts from the initial state and gradually selects monitoring points in different clusters; after each selection, rewards or punishments are given according to whether the coverage of the selected monitoring point is comprehensive and whether it can effectively reflect the signal change; through continuous trial and adjustment of the selection strategy, the agent gradually learns the optimal selection method, filters out a number of suitable and reasonably distributed monitoring points to form a monitoring point set.

[0036] Further, based on the monitoring point set, corresponding external signal monitoring devices are installed at each monitoring point position in the tunnel; the external monitoring devices are started to monitor the antenna signal transmission intensity of each monitoring point in the tunnel; the theoretical signal transmission intensity corresponding to each monitoring point is retrieved and matched with the position of each monitoring point; the actual signal transmission intensity of each monitoring point is compared with the corresponding theoretical signal transmission intensity at each time point; for each time point, the actual signal intensity of the monitoring point is subtracted from the theoretical signal intensity to obtain the transmission intensity difference at that time; the transmission intensity differences of all monitoring points at each time point are integrated and sorted according to the monitoring point position and time point sequence to obtain a transmission intensity difference set.

[0037] In a specific embodiment, the antenna characteristics are obtained: the radiation direction is the tunnel extension direction (0°-180°), the coverage range is 0-1000 meters, and the signal strength decreases exponentially with the increase of distance (the straight section attenuates slower than the curved section). The tunnel characteristics are obtained: step S100 (1000-meter circular tunnel, 5-meter diameter, 90-degree bending segments at 300 meters and 700 meters, and reinforced concrete material). The potential monitoring points are obtained: one monitoring point is preset every 10 meters in the range of 0-1000 meters of the tunnel, a total of 101, numbered P0 (0 meters), P10 (10 meters), …, P1000 (1000 meters).

[0038] The signal strength attenuation trend and the degree of influence of the bending segment are used as similarity indicators. The clustering results are as follows: Cluster 1 (straight segment I): includes P0-P290 (0-290 meters), a total of 30 monitoring points, signal characteristics are slow attenuation (30% intensity decrease per 100 meters).

[0039] Cluster 2 (curved segment I periphery): includes P300-P390 (300-390 meters), a total of 10 monitoring points, signal characteristics are severe attenuation (15% intensity decrease per 10 meters).

[0040] Cluster 3 (straight segment II): includes P400-P690 (400-690 meters), a total of 30 monitoring points, signal characteristics are slow attenuation (35% intensity decrease per 100 meters).

[0041] Cluster 4 (curved segment II periphery): includes P700-P790 (700-790 meters), a total of 10 monitoring points, signal characteristics are severe attenuation (20% intensity decrease per 10 meters).

[0042] Cluster 5 (straight segment III): includes P800-P1000 (800-1000 meters), a total of 21 monitoring points, signal characteristics are slow attenuation (40% intensity decrease per 100 meters).

[0043] The goal of reinforcement learning is to cover the 5 clusters with ≤10 monitoring points and a signal anomaly capture rate ≥90%. The agent initially selects the center nodes of each cluster (such as P150, P350, etc.), and adjusts them through 5 rounds of iteration (remove redundant points and supplement key curved segment periphery points). The final monitoring point set is: P100 (cluster 1), P300 (cluster 2), P350 (cluster 2), P500 (cluster 3), P700 (cluster 4), P750 (cluster 4), P800 (cluster 5), P900 (cluster 5), a total of 8 points, covering all clusters and with higher curved segment periphery density.

[0044] Actual signal monitoring (selecting data at a certain time) is as follows: P100: 0.00048 W / m² (theoretical value 0.00049 W / m²), difference = -0.00001 W / m².

[0045] P300: 0.000020 W / m² (theoretical value 0.0000267 W / m²), difference = -0.0000067 W / m².

[0046] P350: 0.000025 W / m² (theoretical value 0.0000267 W / m²), difference = -0.0000017 W / m².

[0047] P500: 0.000018 W / m2(theoretical value 0.000020 W / m2, corrected by cluster 3), difference =-0.000002 W / m2.

[0048] P700: 0.0000015 W / m2(theoretical value 0.00000255 W / m2), difference =-0.00000105 W / m2.

[0049] P750: 0.0000012 W / m2(theoretical value 0.0000022 W / m2, corrected by cluster 4), difference =-0.000001 W / m2.

[0050] P800: 0.0000025 W / m2(theoretical value 0.00000255 W / m2), difference =-0.00000005 W / m2.

[0051] P900: 0.0000010 W / m2(theoretical value 0.0000012 W / m2, corrected by cluster 5), difference =-0.0000002 W / m2.

[0052] The set of emission intensity differences is arranged in the order of the monitoring points as [-0.00001, -0.0000067, -0.0000017, -0.000002, -0.00000105, -0.000001, -0.00000005, -0.0000002] (unit: W / m2), and the timestamp is unified as "T10:00:00".

[0053] Step S300: defining a graph structure with each node in the power carrier communication network as a vertex of the graph and the communication connection relationship between the nodes as an edge of the graph; determining a power carrier communication coverage node corresponding to each monitoring point according to the physical location of the monitoring point set, and binding the emission intensity difference of the monitoring point to the vertex attribute of the corresponding node; calculating a threshold range of the emission intensity difference associated with all nodes, and marking potential abnormal candidate nodes; Specifically, the physical location of each monitoring point is compared with the coverage range of each node to determine which node the monitoring point belongs to; when the location of the monitoring point is within the coverage range of a node and the node is the closest and most stable node in signal connection to the monitoring point, the node is determined as the power carrier communication coverage node corresponding to the monitoring point; for a monitoring point in the overlapping area of the coverage ranges of multiple nodes, the node with the best signal transmission quality is selected as the power carrier communication coverage node through historical communication data; for each power carrier communication coverage node, the emission intensity differences of all monitoring points corresponding to the node are collected and added as new attributes to the vertex attributes of the node in the graph structure.

[0054] Further, the difference in emission intensity associated with all nodes in the graph structure is extracted, and based on the overall distribution characteristics of the difference in emission intensity, a threshold range is set; for each node, the difference in emission intensity of all monitoring points corresponding to the node is obtained, and whether it is within the threshold range is judged one by one; when part or all of the difference values of a node exceed the threshold range, the node is marked as a potential abnormal candidate node.

[0055] In a specific embodiment, 5 power carrier communication nodes are deployed inside the tunnel, namely N1 (0-300 meters), N2 (300-500 meters), N3 (500-700 meters), N4 (700-900 meters), and N5 (900-1000 meters). The nodes are connected through power lines to form a one-way communication path N1→N2→N3→N4→N5 (the attributes of the edges are all "moderate stability", and the historical interruption frequency is <1 time / day). The 5 nodes are taken as vertices, and the communication connection between the nodes is taken as edges. The vertex attributes initially include coverage range and hardware model, and the edge attributes include transmission direction and stability.

[0056] N1 covers 0-300 meters, N2 covers 300-500 meters, N3 covers 500-700 meters, N4 covers 700-900 meters, and N5 covers 900-1000 meters. The matching results are as follows: P100 (100 meters)→N1, P300 (300 meters)→N2 (closer to N2, signal connection stability 92% higher than N1's 85%), P350 (350 meters)→N2, P500 (500 meters)→N3, P700 (700 meters)→N4, P750 (750 meters)→N4, P800 (800 meters)→N4, and P900 (900 meters)→N5.

[0057] N1 vertex attribute addition: coverage monitoring point difference set [P100: -0.00001 W / m²].

[0058] N2 vertex attribute addition: coverage monitoring point difference set [P300: -0.0000067 W / m², P350: -0.0000017 W / m²].

[0059] N3 vertex attribute addition: coverage monitoring point difference set [P500: -0.000002 W / m²].

[0060] N4 vertex attribute addition: coverage monitoring point difference set [P700: -0.00000105 W / m², P750: -0.000001 W / m², P800: -0.00000005 W / m²].

[0061] N5 vertex attribute addition: coverage monitoring point difference set [P900: -0.0000002 W / m²].

[0062] The emission intensity difference of all nodes ranges from -0.00001 W / m2 to -0.00000005 W / m2, with an average of -0.000003 W / m2 and small fluctuations. Based on the distribution characteristics, the threshold range is set to [-0.000008 W / m2, -0.00000001 W / m2] (including more than 95% of normal differences).

[0063] The node difference is judged: N1: difference -0.00001 W / m2, exceeds the lower limit (-0.000008 W / m2). N2: difference -0.0000067 W / m2, -0.0000017 W / m2, both within the range. N3: difference -0.000002 W / m2, within the range. N4: difference -0.00000105 W / m2, -0.000001 W / m2, -0.00000005 W / m2, all within the range. N5: difference -0.0000002 W / m2, within the range. The difference of N1 exceeds the threshold range, and is marked as a potential abnormal candidate node.

[0064] Step S400: For the potential abnormal candidate node, analyze the node neighborhood connection characteristics; along the transmission path of power carrier communication, track the conduction direction of abnormal difference, determine the abnormal node; integrate all vertices determined as abnormal, form the abnormal node set of power carrier communication.

[0065] Specifically, determine the neighborhood nodes of each potential abnormal candidate node, specifically all nodes directly connected to the potential abnormal candidate node through edges; query whether each neighborhood node is a potential abnormal candidate node, record the emission intensity difference of the neighborhood node, and form a neighborhood node state list; Based on the neighborhood node state list, collect the connection attributes of the edges between the potential abnormal candidate node and the neighborhood nodes and the labeled information of the potential abnormal candidate node to obtain a data set; use the support and confidence indexes in the association rule mining method to analyze the association strength of the connection attributes and the labeled information in the data set, when the support and confidence of a connection attribute and the labeled information are both higher than the set threshold, and the neighborhood node is in the communication transmission direction between the potential abnormal candidate node and the neighborhood node, it is determined that there is a strong matching relationship between the connection attribute and the neighborhood node.

[0066] Further, the main transmission path of data in the power carrier communication network is determined, specifically the main node connection sequence from the signal source to the data terminal, the node connection relationship of each branch path is recorded, and a transmission path map is formed; based on the transmission path map, the position of the node in the main transmission path is obtained for the node with a strong matching relationship; when the node is the starting node of a certain path, and the abnormal difference of the node appears earlier than the downstream node, and the abnormal difference of the downstream node is consistent with that of the node, the node is determined as a potential starting point of abnormal conduction; the abnormality of the downstream node is checked in sequence along the transmission path from the potential starting point; when the abnormal difference of the downstream node gradually weakens with the increase of the distance from the starting point, and the abnormality of each node has a strong matching connection attribute with the previous node, it is confirmed that the abnormal difference is conducted along the path, and the abnormal conduction path is recorded, including the conduction direction and the abnormal appearance order of each node. In the abnormal conduction path, when a node is the original source of the abnormal difference, and the abnormal difference amplitude of the node is the largest, the node is determined as a core abnormal node; wherein the condition for judging the original source is that the node has the earliest abnormal appearance time, and no upstream node conducts the abnormality to the node through a strong matching connection; in the downstream transmission path of the core abnormal node, the node that appears abnormal difference due to the strong matching connection with the core abnormal node or the previous abnormal node, and does not have an independent abnormal trigger factor itself, is determined as a derived abnormal node; for the potential abnormal candidate node, when the connection attribute of the node with the neighborhood node does not have a strong matching relationship, and no upstream node conducts the abnormality to the node in the transmission path, and the abnormal difference of the node has no association with other nodes, the node is determined as a self-fault node, and the abnormality of the node is caused by the hardware or local environmental problem of the node itself, and is irrelevant to the conduction.

[0067] In a specific embodiment, the potential abnormal candidate node is N1 (marked). The direct neighborhood node of N1 is N2 (only one edge of N1→N2 is connected). The emission intensity difference of N2 is -0.0000067 W / m² and -0.0000017 W / m² (both within the threshold range). The edge attribute of N1 and N2 is “moderate stability”, the historical interruption frequency is 0.5 times / day, and the transmission direction is unidirectional (N1 to N2). The data set of “moderate connection stability” and “abnormal node” is collected, the support degree is calculated to be 20% (lower than the set threshold of 30%), and the confidence degree is 60% (lower than the set threshold of 70%), so it is determined that the connection attribute of N1 and N2 and the abnormal node have no strong matching relationship.

[0068] The main transmission path is: N1→N2→N3→N4→N5. The abnormal difference of N1 is-0.00001W / m² (occurrence time T10:00:00), the abnormal difference of downstream node N2 is normal at T10:00:00, and there is no abnormality within 30 minutes after N2; the difference of N3, N4 and N5 is stable within the threshold range within the same time period, and there is no abnormal conduction trend with distance attenuation. No abnormal difference is found along the transmission path, and the abnormality of N1 is an isolated phenomenon.

[0069] The abnormal difference amplitude of N1 is the largest (-0.00001W / m²), but there is no node upstream of N1 (N1 is the starting point of the transmission path), and no abnormality is conducted to the downstream, which does not meet the condition of "initial source of abnormal conduction", so the core abnormal node is excluded. The downstream nodes N2-N5 have no abnormal difference, and have no strong matching connection attribute with N1, so there is no derived abnormal node. N1 has no strong matching connection attribute with the adjacent node N2, there is no upstream node conduction abnormality in the transmission path, its abnormal difference (-0.00001W / m²) has no association with other nodes (the difference of other nodes is within the threshold), and the inspection of N1 hardware log finds that there is a local circuit aging record (independent abnormal trigger factor), so N1 is determined as a self-fault node.

[0070] As shown in Fig. 2 The application provides an intelligent monitoring system based on power carrier communication, which comprises: The theoretical signal transmission intensity calculation module comprises an antenna radiation power calculation unit, a theoretical signal transmission intensity calculation unit and a theoretical signal transmission intensity correction unit; wherein the antenna radiation power calculation unit collects the working parameters and environmental parameters of the antenna and calculates the antenna radiation power; the theoretical signal transmission intensity calculation unit calculates the theoretical signal transmission intensity based on the antenna radiation power under ideal free space conditions according to the inverse square law; and the theoretical signal transmission intensity correction unit introduces an environmental correction coefficient based on the influence of the geometric structure of the tunnel on signal propagation to correct the theoretical signal transmission intensity. The transmission intensity difference calculation module comprises a monitoring point generation unit and a transmission intensity difference calculation unit; wherein the monitoring point generation unit obtains the antenna features and the tunnel features, clusters the potential monitoring points in the tunnel, optimizes the selection of the monitoring points, and obtains a monitoring point set; and the transmission intensity difference calculation unit compares the signal transmission intensity of the antenna in the tunnel with the theoretical signal transmission intensity based on the monitoring point set to obtain a transmission intensity difference set. The potential anomaly marking module comprises a graph structure defining unit, a transmission intensity difference binding unit and a potential anomaly marking unit; wherein the graph structure defining unit defines a graph structure by taking each node in the power carrier communication network as a vertex of the graph and a communication connection relationship between the nodes as an edge of the graph; the transmission intensity difference binding unit binds the transmission intensity difference of the monitoring point to the vertex attribute of the corresponding node according to the physical position of the monitoring point set and determines the power carrier communication coverage node corresponding to each monitoring point; and the potential anomaly marking unit calculates a threshold range of the transmission intensity difference associated with all nodes and marks the potential anomaly candidate node; The anomaly node set generating module comprises a neighborhood connection characteristic analyzing unit, an anomaly node determining unit and an anomaly node set generating unit; wherein the neighborhood connection characteristic analyzing unit analyzes the neighborhood connection characteristic of the potential anomaly candidate node; the anomaly node determining unit traces the conduction direction of the abnormal difference along the transmission path of the power carrier communication and determines the anomaly node; and the anomaly node set generating unit integrates all the vertices determined as the anomaly node to form the anomaly node set of the power carrier communication.

[0071] It is apparent for a person skilled in the art that the present application is not limited to the details of the above exemplary embodiments, but can be implemented in other concrete forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and all changes falling within the meaning and range of the equivalent elements of the claims are intended to be embraced in the present application. Any reference signs in the claims should not be considered as limiting the claims involved.

Claims

1. A method for intelligent monitoring based on power line carrier communication, characterized in that, The method comprises the following steps: Collecting working parameters and environmental parameters of the antenna and calculating antenna radiation power; based on the antenna radiation power, theoretically calculating signal transmission intensity under ideal free space conditions according to the inverse square law; Based on the influence of the geometric structure of the tunnel on signal propagation, an environmental correction coefficient is introduced to correct the theoretically calculated signal transmission intensity; Obtaining antenna characteristics and tunnel characteristics, clustering potential monitoring points in the tunnel, optimizing the selection of monitoring points, and obtaining a monitoring point set; Based on the monitoring point set, monitoring the signal transmission intensity of the antenna in the tunnel and comparing it with the theoretically calculated signal transmission intensity to obtain a signal transmission intensity difference set; Defining a graph structure by taking each node in the power carrier communication network as a vertex of the graph and taking the communication connection relationship between the nodes as an edge of the graph; determining the power carrier communication coverage node corresponding to each monitoring point according to the physical location of the monitoring point set, and binding the signal transmission intensity difference of the monitoring point to the vertex attribute of the corresponding node; Calculating the threshold range of the signal transmission intensity difference associated with all nodes to mark potential abnormal candidate nodes; For the potential abnormal candidate nodes, analyze the node neighborhood connection characteristics; along the transmission path of the power carrier communication, track the conduction direction of the abnormal difference, determine the abnormal node, and integrate all the vertices determined as abnormal to form an abnormal node set of the power carrier communication.

2. The intelligent supervisory method based on power carrier communication according to claim 1, wherein, The theoretically calculated signal transmission intensity based on the antenna radiation power under ideal free space conditions according to the inverse square law comprises: The antenna radiation power represents the total energy radiated by the antenna in an ideal state, and the propagation environment is set to be ideal free space, specifically, there are no obstacles, reflectors and electromagnetic interference, and the energy attenuation is only caused by spatial diffusion in the signal propagation process without other additional losses; the antenna is regarded as a point radiation source, and the radiated signal propagates uniformly in the form of spherical wave to all directions; In ideal free space, the wave front of the spherical wave is a complete sphere, the energy is uniformly distributed on the sphere, and the propagation direction is not hindered and extends along a straight line in all directions; the total power radiated by the antenna is uniformly distributed on the sphere with the antenna as the center and the propagation distance as the radius; the theoretically calculated signal transmission intensity at a certain distance is specifically the proportion of the radiation power allocated on the sphere area corresponding to the distance; the target distance for calculating the theoretically calculated signal transmission intensity is determined, specifically the straight line distance from the antenna to the monitoring point; according to the inverse square law, the sphere area at the distance is proportional to the square of the distance; the signal energy per unit area at the distance is obtained by dividing the antenna radiation power by the sphere area, which is the theoretically calculated signal transmission intensity.

3. The method of claim 1, wherein the power line communication-based intelligent supervision method is characterized by, The theoretically calculated signal transmission intensity based on the influence of the geometric structure of the tunnel on signal propagation, introducing an environmental correction coefficient to correct the theoretically calculated signal transmission intensity, comprises: The geometric structure of the tunnel includes the length, cross-sectional shape, diameter, degree of bending and whether there are branches; by analyzing historical data of tunnels of the same type, a correlation between the geometric structure factors and the degree of signal attenuation is obtained, which reflects the loss of signal energy under different geometric structures; taking the signal propagation state under ideal free space conditions as the benchmark, the environmental correction coefficient is 1 at this time, representing no additional attenuation; according to the correlation, an adjustment rule for the environmental correction coefficient is formulated, when there are geometric structure factors that cause signal attenuation, the environmental correction coefficient is less than 1, and the more serious the attenuation, the smaller the environmental correction coefficient; According to the geometric structure of the current tunnel, the corresponding environmental correction coefficient is calculated by comparing the geometric structure factors and the adjustment rule; the calculated environmental correction coefficient is multiplied by the theoretical signal transmission intensity to make corrections.

4. The method of claim 1, wherein the power line communication-based intelligent supervision method is characterized by, The antenna characteristics and tunnel characteristics are obtained, and potential monitoring points in the tunnel are clustered to optimize the selection of monitoring points and obtain a monitoring point set, including: The antenna characteristics, including radiation direction, coverage range and signal intensity distribution law, and the tunnel characteristics, including the length, width, bending segment position and material of the tunnel, are obtained; potential monitoring points are preset in the tunnel to cover each area of the tunnel; according to the signal intensity distribution law in the antenna characteristics, it is judged whether the signal characteristics at different potential monitoring points are similar, and the DBSCAN algorithm is used to classify potential monitoring points with similar signal characteristics into the same cluster, and the monitoring points in the same cluster have consistency in signal performance, representing the signal characteristics of the area; through clustering, the potential monitoring points are divided into several clusters; The goal of reinforcement learning is to select monitoring points from the clusters obtained by clustering, so that the monitoring points cover all key signal areas in the tunnel with the least number; the signal environment in the tunnel is regarded as the environment of reinforcement learning, each cluster is regarded as a selectable state, and the monitoring point in a certain cluster is regarded as an action; the reinforcement learning agent starts from the initial state and gradually selects monitoring points in different clusters; after each selection, rewards or punishments are given according to whether the coverage range of the selected monitoring point is comprehensive and whether it can effectively reflect signal changes; through continuous trial and adjustment of the selection strategy, the agent gradually learns the optimal selection method, filters out a number of suitable and reasonably distributed monitoring points to form a monitoring point set.

5. The method of claim 1, wherein the power line communication-based intelligent supervision method is characterized by, Based on the monitoring point set, the signal transmission intensity of the antenna in the tunnel is monitored and compared with the theoretical signal transmission intensity to obtain a transmission intensity difference set, including: Based on the monitoring point set, corresponding external signal monitoring equipment is installed at each monitoring point position in the tunnel; the external monitoring equipment is started to monitor the antenna signal transmission intensity of each monitoring point in the tunnel; the corresponding theoretical signal transmission intensity of each monitoring point is called to correspond to the position of each monitoring point; the actual signal transmission intensity of each monitoring point is compared with the corresponding theoretical signal transmission intensity at each time point; for each time point, the actual signal intensity of the monitoring point is subtracted from the theoretical signal intensity to obtain the transmission intensity difference value at the time; the transmission intensity difference values of all monitoring points at each time point are integrated and sorted according to the monitoring point position and time point sequence to obtain a transmission intensity difference value set.

6. The method of claim 1, wherein the power line communication based intelligent supervision method further comprises: The physical location of the monitoring point set is determined to determine the power carrier communication coverage node corresponding to each monitoring point, and the transmission intensity difference value of the monitoring point is bound to the vertex attribute of the corresponding node, including: The physical location of each monitoring point is compared with the coverage range of each node to determine which node the monitoring point belongs to; when the position of the monitoring point is within the coverage range of a node, and the node is the nearest node to the monitoring point and has the most stable signal connection, the node is determined as the power carrier communication coverage node corresponding to the monitoring point; for the monitoring points in the overlapping area of the coverage ranges of multiple nodes, the node with the optimal signal transmission quality is selected as the power carrier communication coverage node through historical communication data; for each power carrier communication coverage node, the transmission intensity difference values of all monitoring points corresponding to the node are collected and added to the vertex attribute of the node in the graph structure as new attributes.

7. The method of claim 1, wherein the power line communication based intelligent supervision method further comprises: The threshold range of the transmission intensity difference values associated with all nodes is calculated, and potential abnormal candidate nodes are marked, including: The transmission intensity difference values associated with all nodes are extracted from the graph structure, and a threshold range is set based on the overall distribution characteristics of the transmission intensity difference values; for each node, the transmission intensity difference values of all monitoring points corresponding to the node are obtained, and whether each value is within the threshold range is judged one by one; when part or all of the difference values of a node are outside the threshold range, the node is marked as a potential abnormal candidate node.

8. The method of claim 1, wherein the power line communication based intelligent supervision method further comprises: For the potential abnormal candidate nodes, the connection characteristics of the node neighborhood are analyzed, including: The neighborhood nodes of each potential abnormal candidate node are determined, specifically all nodes directly connected to the potential abnormal candidate node through edges; it is inquired whether each neighborhood node is a potential abnormal candidate node, the transmission intensity difference values of the neighborhood nodes are recorded, and a neighborhood node state list is formed; Based on the neighborhood node state list, the connection attributes between the potential abnormal candidate nodes and the neighborhood nodes and the label information of the potential abnormal candidate nodes are collected to obtain a data set; the support and confidence indexes in the association rule mining method are used to analyze the association strength between the connection attributes and the label information in the data set; when the support and confidence of a connection attribute and label information are both higher than a set threshold, and the neighborhood node is in the communication transmission direction between the potential abnormal candidate node and the neighborhood node, it is determined that the connection attribute and the neighborhood node have a strong matching relationship.

9. The method of claim 1, wherein the power line communication based intelligent supervision method further comprises: The transmission path of the power carrier communication is tracked along the conduction direction of the abnormal difference value, and the abnormal node is determined, including: Determine the main transmission path of data in a power carrier communication network, specifically the main node connection sequence from the signal source to the data terminal, record the node connection relationship of each branch path, and form a transmission path atlas; based on the transmission path atlas, for nodes with strong matching relationship, obtain their position in the main transmission path; when the node is the starting node of a certain path, and its abnormal difference appears earlier than the downstream node, and the abnormal difference of the downstream node is consistent with that of the node, the node is determined as the potential starting point of abnormal conduction; from the potential starting point, the abnormal situation of the downstream node is checked along the transmission path; when the abnormal difference of the downstream node gradually weakens with the increase of the distance from the starting point, and the abnormality of each node has a strong matching connection attribute with the previous node, it is confirmed that the abnormal difference is conducted along the path, and the abnormal conduction path is recorded, including the conduction direction and the abnormal appearance order of each node; In the abnormal conduction path, when a node is the original source of the abnormal difference, and the abnormal difference amplitude of the node is the largest, the node is determined as the core abnormal node; wherein the condition for judging the original source is that the node appears earliest, and no upstream node conducts the abnormality to the node through strong matching connection; in the downstream transmission path of the core abnormal node, the node that appears abnormal difference due to strong matching connection with the core abnormal node or the previous abnormal node, and has no independent abnormal trigger factor, is determined as a derivative abnormal node; for the potential abnormal candidate node, when the connection attribute between the node and the neighborhood node does not have a strong matching relationship, and no upstream node conducts the abnormality to the node in the transmission path, and its abnormal difference has no association with other nodes, it is determined as a self-fault node, and its abnormality is caused by its own hardware or local environmental problem, which is irrelevant to conduction.

10. A power line carrier communication based intelligent monitoring system using the power line carrier communication based intelligent monitoring method of any one of claims 1-9. Comprise: Theoretical signal transmission intensity calculation module: comprising: antenna radiation power calculation unit, theoretical signal transmission intensity calculation unit and theoretical signal transmission intensity correction unit; wherein the antenna radiation power calculation unit collects the working parameters and environmental parameters of the antenna, and calculates the antenna radiation power; the theoretical signal transmission intensity calculation unit calculates the theoretical signal transmission intensity based on the antenna radiation power under the ideal free space condition according to the inverse square law; the theoretical signal transmission intensity correction unit introduces an environmental correction coefficient based on the influence of the geometric structure of the tunnel on signal propagation, and corrects the theoretical signal transmission intensity; Transmission intensity difference calculation module: comprising: monitoring point generation unit and transmission intensity difference calculation unit; wherein the monitoring point generation unit obtains the antenna features and tunnel features, clusters the potential monitoring points in the tunnel, optimizes the selection of monitoring points, and obtains a monitoring point set; the transmission intensity difference calculation unit compares the signal transmission intensity of the antenna in the tunnel with the theoretical signal transmission intensity based on the monitoring point set, and obtains a transmission intensity difference set; The potential anomaly marking module comprises a graph structure defining unit, a transmission intensity difference binding unit and a potential anomaly marking unit. The graph structure defining unit defines a graph structure by taking each node in the power carrier communication network as a vertex of the graph and taking the communication connection relationship between the nodes as an edge of the graph. The transmission intensity difference binding unit binds the transmission intensity difference of the monitoring point to the vertex attribute of the corresponding node according to the physical position of the monitoring point set and determines the power carrier communication coverage node corresponding to each monitoring point. The potential anomaly marking unit calculates the threshold range of the transmission intensity difference associated with all nodes and marks the potential anomaly candidate node. The anomaly node set generation module comprises a neighborhood connection characteristic analysis unit, an anomaly node determination unit and an anomaly node set generation unit. The neighborhood connection characteristic analysis unit analyzes the neighborhood connection characteristics of the potential anomaly candidate node. The anomaly node determination unit traces the conduction direction of the abnormal difference along the transmission path of the power carrier communication and determines the anomaly node. The anomaly node set generation unit integrates all the vertices determined as abnormal to form the anomaly node set of the power carrier communication.

Images