Intelligent identification and evaluation method and system for external damage risk of power transmission channel

Abstract

The invention belongs to the technical field of power transmission channel monitoring, and relates to a power transmission channel external damage risk intelligent identification and evaluation method and system, and the method comprises the following steps: carrying out the adaptive layout of a low-cost and low-power monitoring terminal; constructing a diagnosis model for calculating an abnormal index of the power transmission channel; acquiring current data, voltage data and vibration data of the power transmission channel, and inputting the data into the diagnosis model to obtain an abnormal index of the power transmission channel; when the abnormal index of the power transmission channel is greater than an early warning threshold value, the unmanned aerial vehicle flies to an external damage risk area of the power transmission channel for rapid positioning; calculating the distance between the human or animal and the external rupture risk area to obtain a distance numerical value; and selecting different levels of positioning and early warning modes according to judgment results of the distance numerical value, the first threshold value and the second threshold value. According to the invention, the problem that the external damage risk of the power transmission channel on a rugged mountain road or a complex terrain is not easy to respond quickly can be solved.

Description

Technical Field

[0001] The invention belongs to the technical field of power transmission channel monitoring and relates to a method and system for intelligently identifying and evaluating the risk of external damage to a power transmission channel. Background Art

[0002] With the rapid development of power systems and the increasing scale of power grids, the safe and stable operation of transmission channels has become increasingly important. However, the external environment faced by transmission channels is becoming increasingly complex, and external damage risks (such as natural disasters, man-made damage, construction impacts, etc.) occur from time to time, posing severe challenges to the safe operation of power grids. Traditional transmission channel monitoring methods mainly rely on manual inspections, which have problems such as long inspection cycles, high costs, and low efficiency, making it difficult to timely discover and deal with potential risks in transmission channels.

[0003] At present, although some automated monitoring technologies have been applied to transmission channel monitoring, these technologies still have some shortcomings. For example, some monitoring systems can only monitor specific types of risks and lack comprehensive risk identification capabilities; other systems can identify multiple risks, but the monitoring accuracy and real-time performance need to be improved. For areas with difficult directions such as rugged mountain roads or complex terrain, traditional monitoring methods are difficult to implement, resulting in these areas becoming monitoring blind spots, increasing the risk of power grid operation.

[0004] Based on the above problems, when facing areas with rugged mountain roads or complex terrain, it is easy for navigation signals to be weak and people to get lost, making it difficult to quickly respond to the risk of external damage to power transmission channels on rugged mountain roads or complex terrain. Summary of the invention

[0005] In order to solve the above-mentioned problems, the present invention provides a method and system for intelligently identifying and evaluating the risk of external damage to a power transmission channel.

[0006] In a first aspect, the present invention provides a method for intelligently identifying and assessing the risk of external damage to a power transmission channel, which adopts the following technical solutions:

[0007] A method for intelligently identifying and assessing the risk of external damage to a power transmission channel comprises the following steps:

[0008] S1. Build a model for dynamically dividing the length of monitoring sections based on the total length of the line, historical data, and topography, and adaptively layout low-cost, low-power monitoring terminals;

[0009] S2. Construct a diagnostic model for calculating the abnormality index of the transmission channel;

[0010] S3, collecting current data, voltage data, and vibration data of the power transmission channel, and inputting them into the diagnostic model to obtain an abnormality index of the power transmission channel;

[0011] S4. When the abnormal index of the power transmission channel is greater than the warning threshold, the drone flies to the external damage risk area of ​​the power transmission channel for rapid positioning;

[0012] S5. Calculate the distance between the person or animal and the external injury risk area to obtain a distance value;

[0013] S6, determining the difference between the distance value and a preset first threshold and a preset second threshold;

[0014] S7. Select different levels of positioning and warning modes according to the judgment results of the distance value and the first threshold and the second threshold.

[0015] In a further solution of the present invention, the monitoring terminal comprises: a current sensor, a voltage sensor, and a vibration sensor;

[0016] The current sensor is used to monitor the current change of the line in the power transmission channel and timely detect the current abnormality of the line;

[0017] The voltage sensor is used to monitor the voltage change of the line in the power transmission channel and promptly detect the voltage abnormality of the line;

[0018] The vibration sensor is used to monitor the vibration changes of the line in the power transmission channel and timely discover the vibration abnormality of the line.

[0019] In a further embodiment of the present invention, the model for dynamically dividing the monitoring segment length satisfies the following formula:

[0020]

[0021] Where, ΔL i represents the length of the i-th monitoring section; L represents the total length of the line; A i It is a coefficient directly related to the fault location accuracy; B i is the coefficient of other factors that affect the length of the monitoring section; C i is the correction factor, which is used to fine-tune the model for dynamically dividing the monitoring segment length;

[0022] Z i It represents the weighted sum of the total length of the line, historical data, and topography, satisfying the following formula:

[0023] Z i =α i ·λ 1 +β i ·λ 2 +γ i ·λ 3

[0024] Z is the Z of all individuals j from 1 to N jThe sum of satisfies the following formula:

[0025]

[0026] Among them, λ 1 is the importance index α i The weight coefficient, λ 2 is the historical data β i The weight coefficient, λ 3 Represents the topographic coefficient γ i The weight coefficient of ; L represents the total length of the transmission channel.

[0027] In a further embodiment of the present invention, the diagnostic model of the power transmission channel abnormality index comprises the following steps:

[0028] Current abnormality index:

[0029]

[0030] Voltage abnormality index:

[0031]

[0032] Vibration abnormality index:

[0033]

[0034] Using the weighted average method, the weighted sum of the abnormality index EDRI is calculated to satisfy the following formula:

[0035] R=w 1 ×CAI+w 2 ×VAI+w 3 ×AAI

[0036] Among them, w 1 Represents the weight coefficient of the current anomaly index, w 2 Represents the weight coefficient of voltage anomaly index, w 3 Indicates the weight coefficient of the vibration abnormality index; w 1 、w 2 、w 3 Determined based on actual application scenarios and expert experience;

[0037] The current measured by the current sensor is I, and the normal current range is [I min , I max ]; the voltage measured by the voltage sensor is V, and the normal voltage range is [V min , V max ]; the vibration amplitude measured by the vibration sensor is A, and the normal vibration range is [A min , A max ].

[0038] A further solution of the present invention, step S4, comprises the following steps:

[0039] In the diagnostic model of the transmission channel abnormality index, the R value range is between 0 and 1. The larger the R value, the higher the risk of transmission channel failure. Based on historical data and operation and maintenance experience, a reasonable warning threshold R is set. thresh , used to determine whether there is a risk of external damage in the transmission channel;

[0040] If R≤R thresh , indicating that the weighted sum R of the abnormal index does not exceed the warning threshold of the transmission channel external damage risk, indicating that no external damage risk is found in this area, and the data monitored in this area is entered into the historical data to optimize the diagnosis model;

[0041] If R>R thresh , indicating that the weighted sum of the abnormal index exceeds the warning threshold of the transmission channel external failure risk, indicating that the area is found to have external failure risk. The system triggers the alarm mechanism and provides detailed information on the abnormal data.

[0042] A further solution of the present invention, step S5, comprises the following steps:

[0043] There are construction workers or idle personnel around the external damage risk area, and even animals or livestock around the external damage risk area of ​​the transmission channel. The drone is equipped with a ranging device to monitor the distance between people or animals and the external damage risk area in real time.

[0044] A further solution of the present invention, step S6, comprises the following steps:

[0045] With the risk area of ​​external injury as the center, a first threshold and a second threshold are pre-set according to the distance value; when the distance value is greater than the first threshold, it indicates that the person or animal is in a safe area; when the distance value is less than the first threshold but greater than the second threshold, it indicates that the person or animal is in a warning area; when the distance value is less than the second threshold, it indicates that the person or animal is in a dangerous area.

[0046] A further solution of the present invention, step S7, comprises the following steps:

[0047] When people or animals are in a safe area, the drone lights up a green safety light to assist maintenance personnel in quickly locating the fault point;

[0048] When people or animals are in the warning area, the drone flashes a yellow warning light and emits a harsh alarm sound; the yellow warning light reminds people around the risk area to pay attention to safety, and reminds maintenance personnel that there are wild animals and livestock; the harsh alarm sound can scare away animals or livestock around the risk area;

[0049] When people or animals are in a dangerous area, the drone flashes a red emergency light and emits a dazzling light at the people or animals; the red emergency light reminds operation and maintenance personnel to avoid harm to frightened wild animals and livestock, and the dazzling light can scare people or animals away from the risk area.

[0050] A further solution of the present invention, step S7, further comprises the following steps:

[0051] The drone is equipped with a voice broadcast device to inform surrounding construction workers of the current situation, location, and safe distance of the external demolition area, reminding them to pay attention to safety.

[0052] In a second aspect, the present invention provides a system for intelligently identifying and assessing the risk of external damage to a power transmission channel, which adopts the following technical solutions:

[0053] An intelligent identification and assessment system for external damage risk of power transmission channels, the system comprises a monitoring terminal layout module, a diagnosis model construction module, an abnormal index calculation module, an abnormal index diagnosis module, a distance value calculation module, a distance value diagnosis module, and an early warning mode selection module;

[0054] The monitoring terminal layout module is used to build a model for dynamically dividing the monitoring section length according to the total line length, historical data, and topography, and to adaptively layout low-cost, low-power monitoring terminals;

[0055] A diagnostic model building module is used to build a diagnostic model for calculating the abnormal index of the power transmission channel;

[0056] An abnormality index calculation module, used to collect current data, voltage data, and vibration data of the power transmission channel, and input them into the diagnostic model to obtain an abnormality index of the power transmission channel;

[0057] The abnormal index diagnosis module is used to compare the abnormal index of the transmission channel with the warning threshold, and the drone flies to the external damage risk area of ​​the transmission channel for rapid positioning;

[0058] A distance value calculation module calculates the distance between a person or an animal and the external damage risk area to obtain a distance value;

[0059] A distance value diagnosis module, used to determine the distance value and the size of the preset first threshold and second threshold;

[0060] The warning mode selection module is used to select different levels of positioning and warning modes according to the judgment results of the distance value and the first threshold and the second threshold.

[0061] In summary, the present invention includes the following beneficial technical effects:

[0062] 1. The present invention uses a phased monitoring strategy, including a comprehensive monitoring phase, a risk location phase, and a precise monitoring phase, to achieve rapid location and precise assessment of the risk of external failure of the transmission channel. Especially in rugged mountain roads or complex terrains, the use of intelligent means such as drones significantly improves the accuracy and efficiency of identification, thereby enhancing the safety and reliability of power grid operation. The use of low-cost, low-power distributed fault location monitoring terminals for preliminary identification effectively reduces unnecessary resource investment;

[0063] 2. The present invention utilizes the eye-catching lights and harsh alarm sounds of drones, so that maintenance personnel can quickly locate the fault area; the images taken by the high-definition camera and infrared thermal imager equipped by the drone can be used to analyze the possible danger sources or abnormal phenomena (such as tree growth, construction activities, animal activities, etc.) around the transmission channel line, and can warn construction personnel or idle personnel around the risk area of ​​external damage of the transmission channel to pay attention to safety, and can also scare away animals or livestock around the risk area of ​​external damage of the transmission channel;

[0064] 3. The present invention aims at rugged mountain roads or complex terrains, where maintenance personnel are prone to weak navigation signals and getting lost. By combining the images taken by the drone and the data from on-site monitoring, maintenance personnel can locate the fault point more accurately. The maintenance personnel can use the voice broadcasting device equipped on the drone to inform surrounding construction personnel, including but not limited to the current situation, location, and safe distance of the external damage area, and remind surrounding personnel to pay attention to safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A flow chart of the intelligent identification and assessment method of external failure risks of power transmission channels is disclosed.

[0066] Figure 2 A hardware block diagram of a distributed fault location monitoring terminal is disclosed.

[0067] Figure 3 A structural schematic diagram of the intelligent identification and assessment system for external damage risks of transmission channels is disclosed. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0069] The following is combined with Figure 1-3 The preferred embodiments of the present invention are described in detail.

[0070] See attached Figure 1 The present invention proposes an intelligent identification and assessment method for the risk of power transmission channel failure. The method takes the power transmission channel on rugged mountain roads or complex terrain as the research object, and uses intelligent means such as drones to achieve rapid positioning and accurate assessment of the risk of power transmission channel failure, thereby improving the safety and reliability of power grid operation. The method includes the following steps:

[0071] S1. Build a model for dynamically dividing the length of monitoring sections based on the total length of the line, historical data, and topography, and adaptively layout low-cost, low-power monitoring terminals;

[0072] S2. Construct a diagnostic model for calculating the abnormality index of the transmission channel;

[0073] S3, collecting current data, voltage data, and vibration data of the power transmission channel, and inputting them into the diagnostic model to obtain an abnormality index of the power transmission channel;

[0074] S4. When the abnormal index of the power transmission channel is greater than the warning threshold, the drone flies to the external damage risk area of ​​the power transmission channel for rapid positioning;

[0075] S5. Calculate the distance between the person or animal and the external injury risk area to obtain a distance value;

[0076] S6, determining the difference between the distance value and a preset first threshold and a preset second threshold;

[0077] S7. Select different levels of positioning and warning modes according to the judgment results of the distance value and the first threshold and the second threshold.

[0078] In one embodiment of the present invention, see the attached Figure 2 , the monitoring terminal includes: a current sensor, a voltage sensor, a vibration sensor, and a communication unit;

[0079] Current sensors are used to monitor the current changes of the lines in the power transmission channel and detect abnormal current of the lines in a timely manner;

[0080] Voltage sensors are used to monitor voltage changes in the lines in the power transmission channel and detect voltage anomalies in the lines in a timely manner;

[0081] Vibration sensors are used to monitor the vibration changes of the lines in the power transmission channel and detect abnormal vibration of the lines in a timely manner;

[0082] The communication unit is used to transmit the data collected by the current sensor, voltage sensor and vibration sensor to the central processing module. The communication unit ensures the real-time transmission and remote communication of the data through a high-reliability communication protocol.

[0083] In one embodiment of the present invention, the step S1 comprises the following steps:

[0084] According to the specific conditions of the line and operation and maintenance experience, different weights are assigned to the total length of the line, historical data, and topography, and a model for dynamically dividing the length of the monitoring section is constructed. The key positions of the monitoring terminals are dynamically divided and comprehensively analyzed.

[0085] In one embodiment of the present invention, the model for dynamically dividing the monitoring segment length satisfies the following formula:

[0086]

[0087] Where, ΔL i represents the length of the i-th monitoring section; L represents the total length of the line; A i It is a coefficient directly related to the fault location accuracy; B i is the coefficient of other factors that affect the length of the monitoring section; C i is the correction factor, which is used to fine-tune the model for dynamically dividing the monitoring segment length;

[0088] Z i It represents the weighted sum of the total length of the line, historical data, and topography, satisfying the following formula:

[0089] Z i =α i ·λ 1 +β i ·λ 2 +γ i ·λ 3

[0090] Among them, λ 1 is the importance index α i The weight coefficient, λ 2 is the historical data β i The weight coefficient, λ 3 Represents the topographic coefficient γ i The weight coefficient needs to be set according to the actual situation; L represents the total length of the transmission channel.

[0091] Z is the Z of all individuals j from 1 to N j The sum of satisfies the following formula:

[0092]

[0093] For example, the total length of the transmission channel is set to L = 100 km; the weight coefficient λ of the importance index is 1 =0.5, weight coefficient of historical data λ 1 =0.3, weight coefficient of topographic coefficient λ 3=0.2.

[0094] The coefficients associated with each monitoring segment are set according to actual conditions, including:

[0095] Monitoring segment 1 sets the relevant coefficient: α 1 =0.6,β 1 =0.2,γ 1 =0.2;

[0096] Monitoring segment 2 sets the relevant coefficient: α 1 =0.5,β 1 =0.3,γ 1 =0.2.

[0097] The fault location accuracy coefficient is set according to the monitoring equipment performance and signal transmission quality, including:

[0098] Monitoring segment 1: A 1 =1.2 (indicates that the fault location accuracy of monitoring section 1 is higher);

[0099] Monitoring segment 2: A 2 =1.0 (indicating that the fault location accuracy of monitoring section 2 is moderate).

[0100] Other factors that affect the length of the monitoring segment are set based on monitoring costs and data transmission delays, including:

[0101] Monitoring segment 1: B 1 =1.0 (indicates that the cost and delay of monitoring segment 1 are moderate);

[0102] Monitoring segment 2: B 2 =0.9 (indicating that monitoring segment 2 needs to reduce cost and delay through optimization).

[0103] The correction coefficient is fine-tuned according to the actual situation, including:

[0104] Monitoring segment 1: C 1 =1.0 (indicates that monitoring segment 1 is moderate);

[0105] Monitoring segment 2: C 2 =1.05 (indicating that monitoring section 2 needs fine-tuning to improve economic efficiency).

[0106] Substitute the above parameters into the formula to calculate the length ΔL of the i-th monitoring segment i The length of is obtained by the following formula:

[0107] Weighted sum of monitoring segment 1: Z 1 =0.6×0.5+0.2×0.3+0.2×0.2=0.37;

[0108] Weighted sum of monitoring segment 2: Z2 =0.5×0.5+0.3×0.3+0.2×0.2=0.365.

[0109] According to the weighted sum of all monitoring segments, the total sum Z′ is calculated;

[0110] Calculate the length of each monitoring section ΔL using the formula i , satisfying the following formula:

[0111] Length of monitoring segment 1:

[0112] Length of monitoring segment 2:

[0113] And so on, calculate the length of all monitoring segments.

[0114] In one embodiment of the present invention, the diagnosis model of the power transmission channel abnormality index comprises the following steps:

[0115] Abnormal current indicates problems such as short circuit, overload or equipment failure; voltage fluctuations may cause equipment damage or unstable operation; excessive vibration may be caused by wind deviation, dancing, etc., and long-term vibration may cause line fatigue and fracture.

[0116] The current sensor measures the current I, and the normal current range is [I min , I max ];

[0117] The voltage measured by the voltage sensor is V, and the normal voltage range is [V min , V max ];

[0118] The vibration amplitude measured by the vibration sensor is A, and the normal vibration range is [A min , A max ].

[0119] Define the abnormal index of current, voltage and vibration to satisfy the following formula:

[0120] Current Anomaly Index (CAI):

[0121]

[0122] Voltage Anomaly Index (VAI):

[0123]

[0124] Vibration Anomaly Index (AAI):

[0125]

[0126] Using the weighted average method, the weighted sum of the abnormality index EDRI is calculated to satisfy the following formula:

[0127] R=w 1 ×CAI+w 2 ×VAI+w 3 ×AAI

[0128] Among them, w 1 Represents the weight coefficient of the current anomaly index, w 2 Represents the weight coefficient of voltage anomaly index, w 3 Indicates the weight coefficient of the vibration abnormality index; w 1 、w 2 、w 3 Determined based on actual application scenarios and expert experience.

[0129] The current sensor, voltage sensor and vibration sensor in the monitoring terminal are used to collect the current data, voltage data and vibration data of the line in the transmission channel to provide basic data for subsequent fault location and analysis; the current data, voltage data and vibration data of the line are cleaned, converted and integrated to obtain pre-processed data; the pre-processed data is transmitted to the central processing module through the communication unit.

[0130] In one embodiment of the present invention, the step S4 comprises the following steps:

[0131] In the diagnostic model of the transmission channel abnormality index, the R value range is between 0 and 1. The larger the R value, the higher the risk of transmission channel failure. Based on historical data and operation and maintenance experience, a reasonable warning threshold R is set. thresh , used to determine whether there is a risk of external damage in the transmission channel.

[0132] If R≤R thresh , indicating that the weighted sum R of the abnormal index does not exceed the warning threshold of the transmission channel external damage risk, indicating that no external damage risk is found in this area, and the data monitored in this area is entered into the historical data to optimize the diagnosis model;

[0133] If R>R thresh , indicating that the weighted sum of the abnormal index exceeds the warning threshold of the transmission channel external failure risk, indicating that the area is found to have external failure risk. The system triggers the alarm mechanism and provides detailed information on the abnormal data.

[0134] In one embodiment of the present invention, the system triggers an alarm mechanism and provides detailed information of abnormal data, including the following steps:

[0135] If the monitoring terminal identifies that there is a risk of external damage to the transmission channel, it will initially locate the risk area of ​​the transmission channel, and the drone will respond quickly and go to the risk area. The drone is pre-equipped with a high-definition camera, infrared thermal imager, rangefinder, sound warning device, voice broadcasting device, strong light equipment and warning lights;

[0136] As the drone follows the preset route to the risk area, the drone's high-definition camera and infrared thermal imager work simultaneously to take detailed photos and analyze the transmission line and its surrounding environment, identifying the danger sources around the line, including tree growth, construction activities, and animal activities.

[0137] In one embodiment of the present invention, step S5 comprises the following steps:

[0138] There are construction workers or idle personnel around the external damage risk area, and even animals or livestock around the external damage risk area of ​​the transmission channel. The drone is equipped with a ranging device to monitor the distance between people or animals and the external damage risk area in real time.

[0139] In one embodiment of the present invention, step S6 comprises the following steps:

[0140] With the risk area of ​​external injury as the center, a first threshold and a second threshold are pre-set according to the distance value. When the distance value is greater than the first threshold, it indicates that the person or animal is in a safe area; when the distance value is less than the first threshold and greater than the second threshold, it indicates that the person or animal is in a warning area; when the distance value is less than the second threshold, it indicates that the person or animal is in a dangerous area.

[0141] In one embodiment of the present invention, the step S7 comprises the following steps:

[0142] When people or animals are in a safe area, the drone lights up a green safety light to assist operation and maintenance personnel in quickly locating the fault point.

[0143] When people or animals are in the warning area, the drone flashes a yellow warning light and emits a shrill alarm sound; the yellow warning light reminds people around the external damage risk area to pay attention to safety, and also reminds operation and maintenance personnel that there are wild animals and livestock; the shrill alarm sound can scare away animals or livestock around the external damage risk area.

[0144] When people or animals are in a dangerous area, the drone flashes a red emergency light and emits a dazzling light at the people or animals; the red emergency light reminds the operation and maintenance personnel to avoid harm to frightened wild animals and livestock, and the dazzling light can scare people or animals away from the risk area;

[0145] The operation and maintenance personnel can use the voice broadcast device equipped on the drone to inform the surrounding construction personnel, including but not limited to the current situation, location, and safe distance of the external demolition area, and remind the surrounding personnel to pay attention to safety.

[0146] See attached Figure 3 The present invention also proposes an intelligent identification and assessment system for the risk of external damage to a power transmission channel, which includes a monitoring terminal layout module, a diagnosis model construction module, an abnormality index calculation module, an abnormality index diagnosis module, a distance value calculation module, a distance value diagnosis module, and an early warning mode selection module.

[0147] The monitoring terminal layout module is used to build a model for dynamically dividing the monitoring section length according to the total line length, historical data, and topography, and to adaptively layout low-cost, low-power monitoring terminals;

[0148] A diagnostic model building module is used to build a diagnostic model for calculating the abnormal index of the power transmission channel;

[0149] An abnormality index calculation module, used to collect current data, voltage data, and vibration data of the power transmission channel, and input them into the diagnostic model to obtain an abnormality index of the power transmission channel;

[0150] The abnormal index diagnosis module is used to compare the abnormal index of the transmission channel with the warning threshold, and the drone flies to the external damage risk area of ​​the transmission channel for rapid positioning;

[0151] A distance value calculation module calculates the distance between a person or an animal and the external damage risk area to obtain a distance value;

[0152] A distance value diagnosis module, used to determine the distance value and the size of the preset first threshold and second threshold;

[0153] The warning mode selection module is used to select different levels of positioning and warning modes according to the judgment results of the distance value and the first threshold and the second threshold.

[0154] The modules described above may be implemented in whole or in part through software, hardware, or a combination thereof, supporting processors embedded in or independent of a computer device in hardware form, and also supporting memories stored in a computer device in software form, so that the processor can call and execute operations corresponding to the modules described above.

[0155] It should be noted that the user information (including but not limited to user device information and personal information, etc.) and data (including but not limited to data used for analysis, stored data and displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0156] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention is described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for intelligent identification and assessment of external damage risk of power transmission channels, characterized in that: The following steps are involved: S1. Build a model for dynamically dividing the length of monitoring sections based on the total length of the line, historical data, and topography, and adaptively layout low-cost, low-power monitoring terminals; S2. Construct a diagnostic model for calculating the abnormality index of the transmission channel; S3, collecting current data, voltage data, and vibration data of the power transmission channel, and inputting them into the diagnostic model to obtain an abnormality index of the power transmission channel; S4. When the abnormal index of the transmission channel is greater than the warning threshold, the drone flies to the external damage risk area of ​​the transmission channel for rapid positioning; S5. Calculate the distance between the person or animal and the external injury risk area to obtain a distance value; S6, determining the difference between the distance value and a preset first threshold and a preset second threshold; S7. Select different levels of positioning and warning modes according to the judgment results of the distance value and the first threshold and the second threshold.

2. According to claim 1, a method for intelligent identification and assessment of transmission channel external damage risk is characterized in that: The monitoring terminal includes: a current sensor, a voltage sensor, and a vibration sensor; The current sensor is used to monitor the current change of the line in the power transmission channel and timely detect the current abnormality of the line; The voltage sensor is used to monitor the voltage change of the line in the power transmission channel and promptly detect the voltage anomaly of the line; The vibration sensor is used to monitor the vibration changes of the line in the power transmission channel and timely discover the vibration abnormality of the line.

3. According to claim 1, a method for intelligent identification and assessment of transmission channel external damage risk is characterized in that: The model for dynamically dividing the monitoring segment length satisfies the following formula: Where, ΔL i represents the length of the i-th monitoring section; L represents the total length of the line; A i It is a coefficient directly related to the fault location accuracy; B i is the coefficient of other factors that affect the length of the monitoring section; C i is the correction factor, which is used to fine-tune the model for dynamically dividing the monitoring segment length; Z i It represents the weighted sum of the total length of the line, historical data, and topography, satisfying the following formula: Z i =a i ·λ1+β i ·λ2+γ i ·λ3 Z is the Z of all individuals j from 1 to N j The sum of satisfies the following formula: Among them, λ1 is the importance index α i The weight coefficient of λ2 is the historical data β i The weight coefficient, λ3 represents the topographic coefficient γ i The weight coefficient of ; L represents the total length of the transmission channel.

4. According to claim 3, a method for intelligent identification and assessment of transmission channel external damage risk is characterized in that: The diagnostic model of the power transmission channel abnormality index comprises the following steps: Current abnormality index: Voltage abnormality index: Vibration abnormality index: Using the weighted average method, the weighted sum of the abnormality index EDRI is calculated to satisfy the following formula: R=w1×CAI+w2×VAI+w3×AAI Among them, w1 represents the weight coefficient of the current anomaly index, w2 represents the weight coefficient of the voltage anomaly index, and w3 represents the weight coefficient of the vibration anomaly index; w1, w2, and w3 are determined according to the actual application scenario and expert experience; The current measured by the current sensor is I, and the normal current range is [I min , I max ]; the voltage measured by the voltage sensor is V, and the normal voltage range is [V min , V max ]; the vibration amplitude measured by the vibration sensor is A, and the normal vibration range is [A min , A max ].

5. According to claim 3, a method for intelligent identification and assessment of external damage risk of power transmission channels is characterized in that: Step S4 includes the following steps: In the diagnostic model of the transmission channel abnormality index, the R value range is between 0 and 1. The larger the R value, the higher the risk of transmission channel failure. Based on historical data and operation and maintenance experience, a reasonable warning threshold R is set. thresh , used to determine whether there is a risk of external damage in the transmission channel; If R≤R thresh , indicating that the weighted sum R of the abnormal index does not exceed the warning threshold of the transmission channel external damage risk, indicating that no external damage risk is found in this area, and the data monitored in this area is entered into the historical data to optimize the diagnosis model; If R>R thresh , indicating that the weighted sum of the abnormal index exceeds the warning threshold of the transmission channel external failure risk, indicating that the area is found to have external failure risk. The system triggers the alarm mechanism and provides detailed information on the abnormal data.

6. The method for intelligent identification and assessment of external damage risk of power transmission channels according to claim 5 is characterized in that: Step S5 includes the following steps: There are construction workers or idle personnel around the external damage risk area, and even animals or livestock around the external damage risk area of ​​the transmission channel. The drone is equipped with a ranging device to monitor the distance between people or animals and the external damage risk area in real time.

7. The method for intelligent identification and assessment of transmission channel external damage risk according to claim 6 is characterized in that: Step S6 includes the following steps: With the risk area of ​​external injury as the center, a first threshold and a second threshold are pre-set according to the distance value; when the distance value is greater than the first threshold, it indicates that the person or animal is in a safe area; when the distance value is less than the first threshold but greater than the second threshold, it indicates that the person or animal is in a warning area; when the distance value is less than the second threshold, it indicates that the person or animal is in a dangerous area.

8. The method for intelligent identification and assessment of external damage risk of power transmission channels according to claim 7 is characterized in that: Step S7 includes the following steps: When people or animals are in a safe area, the drone lights up a green safety light to assist maintenance personnel in quickly locating the fault point; When people or animals are in the warning area, the drone flashes a yellow warning light and emits a harsh alarm sound; the yellow warning light reminds people around the risk area to pay attention to safety, and reminds maintenance personnel that there are wild animals and livestock; the harsh alarm sound can scare away animals or livestock around the risk area; When people or animals are in a dangerous area, the drone flashes a red emergency light and emits a dazzling light at the people or animals; the red emergency light reminds operation and maintenance personnel to avoid harm to frightened wild animals and livestock, and the dazzling light can scare people or animals away from the risk area.

9. The method for intelligent identification and assessment of external damage risk of power transmission channels according to claim 8 is characterized in that: Step S7 further includes the following steps: The drone is equipped with a voice broadcast device to inform surrounding construction workers of the current situation, location, and safe distance of the external demolition area, reminding them to pay attention to safety.

10. An intelligent identification and assessment system for external damage risk of power transmission channels, characterized by: It includes a monitoring terminal layout module, a diagnosis model building module, an abnormal index calculation module, an abnormal index diagnosis module, a distance value calculation module, a distance value diagnosis module, and an early warning mode selection module; The monitoring terminal layout module is used to build a model for dynamically dividing the monitoring section length according to the total line length, historical data, and topography, and to adaptively layout low-cost, low-power monitoring terminals; A diagnostic model building module is used to build a diagnostic model for calculating the abnormal index of the power transmission channel; An abnormality index calculation module, used to collect current data, voltage data, and vibration data of the power transmission channel, and input them into the diagnostic model to obtain an abnormality index of the power transmission channel; The abnormal index diagnosis module is used to compare the abnormal index of the transmission channel with the warning threshold, and the drone flies to the external damage risk area of ​​the transmission channel for rapid positioning; A distance value calculation module calculates the distance between a person or an animal and the external damage risk area to obtain a distance value; A distance value diagnosis module, used to determine the distance value and the size of the preset first threshold and second threshold; The warning mode selection module is used to select different levels of positioning and warning modes according to the judgment results of the distance value and the first threshold and the second threshold.

Images