Cross-industry multi-source fault intelligent research and judgment method and system based on large model

Abstract

The invention discloses a cross-industry multi-source fault intelligent research and judgment method and system based on a large model, and relates to the technical field of large models, and the method comprises the steps: calling a historical fault record of a power transmission line, deploying a sensor on the power transmission line, and obtaining target data corresponding to each fault position in each physical type; obtaining an associated physical type and an associated function corresponding to each fault type; extracting all detection points on the target power transmission line to obtain first target values of the detection points; extracting a management and control area where personnel are limited to enter in the power transmission line, and obtaining a second target value of each detection point; setting a weight to obtain a total target value of each detection point; and obtaining a first judgment criterion and a second judgment criterion, and judging whether to carry out early warning prompt on the selected sampling point or not. According to the method, the fault record and the control area are analyzed, so that the current sampling point is more reasonable and representative, the power transmission line fault is intelligently researched and judged, and the reliable judgment on the power transmission line is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of large models, in particular to a cross-industry multi-source fault intelligent research and judgment method and system based on a large model. BACKGROUND

[0002] The safety of the power transmission line is the core prerequisite for ensuring the stable, efficient and accident-free operation of the power transmission process, and is directly related to the reliable transmission of electricity from the power generation side to the load side, as well as the power use of personnel in multiple industries; in actual power transmission line fault detection, since the power transmission line is usually long, it is costly, difficult and time-consuming to conduct comprehensive and continuous detection on the entire line, so a sampling point setting method is used for detection, first the sampling points are collected by means of a drone or the like, and then the staff identifies the defects to realize timely discovery, accurate positioning and analysis of the fault conditions in the power transmission line, and quickly take repair measures to ensure the safe and stable operation of the power grid; however, in the actual sampling process, if the sampling points are randomly selected without fully considering the positions and defect degrees of the sampling points, the selection of the sampling points will not be targeted and representative, and it will be difficult to reliably judge the power transmission line in a timely and effective manner. SUMMARY

[0003] The purpose of the present application is to provide a cross-industry multi-source fault intelligent research and judgment method and system based on a large model to solve the problems in the prior art.

[0004] To solve the above technical problems, the present application provides the following technical scheme: The cross-industry multi-source fault intelligent research and judgment method based on a large model comprises the following steps: Retrieve the historical fault records of the power transmission line, extract the fault time, fault position and fault type of the fault records; Pre-deploy sensors for monitoring different physical types at different positions on the power transmission line to obtain the positions of the sensors and historical sensor data, and obtain the target data corresponding to each physical type at each fault position; Obtain the normal value range monitored by the sensors and the defect level of the fault position, and obtain the correlation degree between each fault type and each physical type according to the target data, and then obtain the associated physical type and the associated function corresponding to each fault type; Extract all detection points on the target power transmission line, obtain the target data corresponding to each detection point in each physical type according to the positions of the sensors and the detection points, and obtain the first target value of the detection points according to the target data, the associated physical type and the associated function; Establish a three-dimensional model of the power transmission line, extract the control area in the power transmission line where personnel are restricted from entering, and obtain the second target value of each detection point according to the time when personnel enter the control area in the historical monitoring video; Set the weight values of the first target value and the second target value to obtain a total target value of each detection point; According to the current sampling mode, all sampling points are selected from the detection points, a first discrimination criterion is obtained based on the positions of the detection points and the sampling points, a second discrimination criterion is obtained based on the total target values of the detection points and the sampling points, and it is determined whether to give a pre-warning prompt to the currently selected sampling point according to the first discrimination criterion and the second discrimination criterion.

[0005] Preferably, the target data corresponding to each fault location in each physical type is obtained, including: The fault location P, the fault time and the fault type of a certain fault record are extracted, a range with a radius of r around the fault location P is taken as a detection range, all sensors monitoring a certain physical type m in the detection range are obtained, and the sensor closest to the fault location P in the historical several days of sensing data is taken as the target data corresponding to the fault location P in the physical type m; If there is no sensor monitoring a certain physical type n in the detection range, all sensors monitoring the physical type n in the power transmission line are obtained, the reciprocal of the distance between each sensor and the fault location P is taken as the characteristic distance corresponding to each sensor, all characteristic distances are added to obtain a characteristic value, and each characteristic distance is divided by the characteristic value to obtain the distance weight value corresponding to each sensor; the sensing value of each sensor at each time in the historical several days is obtained, and the distance weight value is used to obtain the target data corresponding to the fault location P in the physical type n.

[0006] Since the closer the distance, the closer the sensing value corresponding to the sensor to the fault location P, the reciprocal of the distance is taken as the characteristic distance to calculate the distance weight value corresponding to each sensor, and then the sensing value of the fault location at each time is obtained according to the sensing value of several sensors at each time and the distance weight value, and the target data is obtained.

[0007] Preferably, the associated physical type and the associated function corresponding to each fault type are obtained, including: The normal value range monitored by the sensor of a certain physical type q is obtained, the target data Dte corresponding to the fault location P in the physical type q is extracted, the fault type corresponding to the fault location P is taken as h, and the ratio of the number of time points at which the sensing value in the target data Dte exceeds the normal value range to the total number of time points in the target data Dte is taken as the target ratio of the fault location P in the fault type h and the physical type q; A neural network model is established, a plurality of fault location data sets belonging to the fault type h but having different defect levels are obtained, and the neural network model is trained; the fault location P is substituted into the trained neural network model to obtain the target defect level of the fault location P in the fault type h; According to historical failure records, target ratio and target defect level corresponding to a plurality of failure types h and physical types q are obtained, and a first function fitting of the target defect level with respect to the target ratio is performed, and a fitting goodness corresponding to the fitting process is taken as a correlation degree between the failure type h and the physical type q; and then a correlation degree between the failure type h and each physical type is obtained, and a physical type corresponding to a maximum correlation degree is taken as a correlation physical type of the failure type h, and a corresponding first function fitting is taken as a correlation function of the failure type h.

[0008] Fitting goodness R 2 As a core evaluation index of function fitting, the fitting goodness R is used to quantify the explanatory power of a regression model to observation data, that is, the degree of fit between the predicted value of the model and the actual observation value. 2 The greater the fitting goodness R is, the more the corresponding failure type and physical type conform to the causal relationship.

[0009] Preferably, the first target value of the detection point is obtained by: extracting all detection points on the target transmission line, obtaining a corresponding detection range according to the position of a certain detection point DP, obtaining target data of the detection point DP corresponding to each physical type according to the detection range and the position of each sensor; The target ratio in the target data corresponding to a certain physical type w is obtained, and then the failure level of each failure type of the detection point DP is obtained according to the correlation physical type and the correlation function corresponding to each failure type, and then the first target value of the detection point DP is obtained: , wherein D is the number of failure types, e is a natural constant, R d is the failure level of the dth failure type; and then the first target value of each detection point is obtained.

[0010] Preferably, the total target value of each detection point is obtained by: establishing a three-dimensional model of the transmission line, obtaining a control area where personnel are restricted to enter corresponding to each detection point according to the position of each detection point; obtaining monitoring videos in the past several days to obtain the duration of personnel entering the control area corresponding to each detection point, and normalizing the duration to obtain a second target value of each detection point; setting the weight values of the first target value and the second target value, and obtaining the total target value of each detection point according to the first target value and the second target value of each detection point.

[0011] Preferably, whether to give a warning prompt to the currently selected sampling point is determined by: Obtain the positions of all current sampling points, extract a sampling point b closest to a certain sampling point a, take the distance between the sampling point a and the sampling point b as the target distance of the sampling point a, and mark the sampling point a; obtain a non-marked sampling point c closest to the sampling point b, take the distance between the sampling point b and the sampling point c as the target distance of the sampling point b, and also mark the sampling point b, and so on, to obtain the target distance of each sampling point and calculate the average value L1; then, according to the position of each detection point, obtain the target distance of each detection point and calculate the average value L2; According to the total target value of each sampling point, calculate the average value P1, according to the total target value of each detection point, calculate the average value P2, if L1 < k1 * L2 or P1 < k2 * P2 exists, k1 and k2 are the first ratio and the second ratio respectively, then the current selected sampling point is prompted for early warning.

[0012] When the sampling points are too dense, it means that the sampling points are not set reasonably, so in the present scheme, L1 < k1 * L2 is used to compare the sampling points with the detection points as the first discrimination criterion; when the total target value of each sampling point is small, it means that the sampling points are not set reasonably, so in the present scheme, P1 < k2 * P2 is used to compare the sampling points with the detection points as the second discrimination criterion, and the first discrimination criterion and the second discrimination criterion are combined to determine whether the current selected sampling point is prompted for early warning.

[0013] The cross-industry multi-source fault intelligent research and judgment system based on a large model comprises a target data obtaining module, a first target value calculating module, a total target value calculating module and a warning prompting module. The target data obtaining module is used to call the historical fault records of the power transmission line, extract the fault time, fault position and fault type of the fault records; sensors of different physical types are deployed in advance at different positions on the power transmission line to obtain the positions of the sensors and the historical sensing data, and the target data of each fault position corresponding to each physical type is obtained; The first target value calculating module is used to obtain the normal value range monitored by the sensors and the defect level of the fault position, and according to the target data, the correlation degree between each fault type and each physical type is obtained, and then the associated physical type corresponding to each fault type and the associated function are obtained; All detection points on the target power transmission line are extracted, and according to the positions of the sensors and the detection points, the target data of each detection point corresponding to each physical type is obtained; according to the target data, the associated physical type and the associated function, the first target value of the detection point is obtained; The total target value calculation module is configured to establish a three-dimensional model of the power transmission line, extract a control area in which personnel are restricted from entering in the power transmission line, obtain a second target value of each detection point according to a time at which personnel enter the control area in historical monitoring videos, and set a weight value of the first target value and the second target value to obtain a total target value of each detection point. The early warning prompt module is configured to select all sampling points from the detection points according to a current sampling mode, obtain a first discrimination criterion based on positions of the detection points and the sampling points, obtain a second discrimination criterion based on total target values of the detection points and the sampling points, and determine whether to perform early warning prompting on the currently selected sampling points according to the first discrimination criterion and the second discrimination criterion.

[0014] Preferably, the target data obtaining module comprises a target data obtaining unit. The target data obtaining unit is configured to extract a fault position, a fault time and a fault type of a certain fault record, obtain a detection range, determine whether a sensor for monitoring a certain physical type exists in the detection range, and obtain target data of each fault position corresponding to each physical type according to sensor data of the sensor in a historical number of days and a position of the sensor.

[0015] Preferably, the total target value calculation module comprises a second target value calculation unit and a total target value calculation unit. The second target value calculation unit is configured to establish a three-dimensional model of the power transmission line, obtain a control area in which personnel are restricted from entering corresponding to each detection point according to a position of each detection point, obtain monitoring videos in a historical number of days, obtain a time length during which personnel enter the control area corresponding to each detection point, and obtain a second target value of each detection point by normalizing the time length. The total target value calculation unit is configured to set a weight value of the first target value and the second target value, and obtain a total target value of each detection point according to the first target value and the second target value of each detection point.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a cross-industry multi-source fault intelligent analysis method and system based on a large model, including: retrieving historical fault records of the transmission line, deploying sensors on the transmission line, obtaining target data corresponding to each physical type of each fault location; obtaining the associated physical type and associated function corresponding to each fault type; extracting all detection points on the target transmission line to obtain the first target value of the detection point; extracting the control area where personnel are restricted from entering in the transmission line to obtain the second target value of each detection point; setting weights to obtain the total target value of each detection point; obtaining the first discrimination criterion and the second discrimination criterion to determine whether to issue an early warning prompt for the selected sampling point. The present invention makes the current sampling point more reasonable and representative by analyzing the fault records and control areas, intelligently analyzes the transmission line fault, and effectively improves the reliable judgment of the transmission line. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of the cross-industry multi-source fault intelligent analysis method based on a large model of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Example: Figure 1 As shown, the present invention provides a cross-industry multi-source fault intelligent analysis and judgment method and technical solution based on a large model, including the following steps: 1. Retrieve historical fault records of the transmission line and extract the fault time, fault location, and fault type from the fault records. Pre-deploy sensors that monitor different physical types at different locations on the transmission line to obtain the sensor locations and historical sensor data, and obtain the target data corresponding to each physical type at each fault location.

[0021] Extract the fault location P, fault time and fault type of a fault record, take the range with a radius of r around the fault location P as the detection range, obtain all sensors monitoring a certain physical type m in the detection range, and take the sensor closest to the fault location P in the historical several-day sensor data as the target data of the fault location P corresponding to the physical type m; If there is no sensor monitoring a certain physical type n in the detection range, obtain all sensors monitoring the physical type n in the power transmission line, take the reciprocal of the distance between each sensor and the fault location P as the feature distance corresponding to each sensor, add all feature distances to obtain a feature value, and divide each feature distance by the feature value to obtain the distance weight corresponding to each sensor; obtain the sensor value of each sensor at each time in the historical several days, and obtain the target data of the fault location P corresponding to the physical type n according to the distance weight.

[0022] In the embodiment, the fault types include wire strand, corrosion and overheating, etc., and the physical types include wind, humidity and temperature, etc., wherein each fault type has its corresponding physical type, for example, when the wind is often strong, the wire is prone to strand defects, but not prone to corrosion defects, so the purpose of obtaining the target data in the scheme is to find out the associated physical type corresponding to each fault type and obtain the association function therebetween, and the specific steps are as follows: 2. Obtain the normal value range monitored by the sensor and the defect level of the fault location, and obtain the association degree between each fault type and each physical type according to the target data, and further obtain the associated physical type corresponding to each fault type and the association function.

[0023] Obtain the normal value range monitored by the sensor of a certain physical type q, extract the target data Dte of the fault location P corresponding to the physical type q, take the fault type corresponding to the fault location P as h, and take the ratio of the number of times when the sensor value in the target data Dte exceeds the normal value range to the total number of times of the target data Dte as the target ratio of the fault location P in the fault type h and the physical type q; Establish a neural network model, obtain a plurality of fault location data sets belonging to the fault type h but having different defect levels, and train the neural network model; substitute the fault location P into the trained neural network model to obtain the target defect level of the fault location P in the fault type h; Here, the fault locations with different defect levels are those with greater defect levels and more serious defect degrees, in the embodiment, the training data set and the verification data set are divided into 7:3, the neural network model is trained, and the specific establishment and verification process is not described again, and the fault location P is substituted into the finally trained neural network model to obtain the target defect level of the fault location P in the fault type h. According to the historical failure records, the target ratio and the target defect level corresponding to the failure type h and the physical type q are obtained, and a first function fitting of the target defect level with the target ratio is performed, and the fitting goodness corresponding to the fitting process is taken as the correlation degree between the failure type h and the physical type q; and then the correlation degree between the failure type h and each physical type is obtained, and the physical type corresponding to the maximum correlation degree is taken as the associated physical type of the failure type h, and the corresponding first function fitting is taken as the associated function of the failure type h.

[0024] 3. Extract all detection points on the target transmission line, and obtain the target data of each detection point corresponding to each physical type according to the positions of the sensors and the detection points; and obtain the first target value of the detection point according to the target data, the associated physical type and the associated function.

[0025] Extract all detection points on the target transmission line, and obtain the corresponding detection range according to the position of a certain detection point DP, and obtain the target data of the detection point DP corresponding to each physical type according to the detection range and the position of each sensor; Obtain the target ratio in the target data corresponding to a certain physical type w, and then obtain the failure level of the detection point DP in each failure type according to the associated physical type and the associated function corresponding to each failure type, and then obtain the first target value of the detection point DP: Wherein, D is the number of failure types, e is a natural constant, R d is the failure level of the dth failure type; and then the first target value of each detection point is obtained.

[0026] Since not all sections on the transmission line are detection meaningful sections, the detection points on the transmission line are points that have important influence on the transmission of the transmission line, and the sampling points extracted from the detection points are more reliable, so in this scheme, the detection points need to be analyzed to obtain the first target value and the second target value, and then the total target value of the detection point is obtained, and then whether the selected sampling point is reasonable is judged according to the total target value of the detection point and the total target value of the selected sampling point.

[0027] 4. A three-dimensional model of the transmission line is established, and a control area in which personnel are restricted to enter in the transmission line is extracted, and the second target value of each detection point is obtained according to the time when personnel enter the control area in the historical monitoring video; and the weight values of the first target value and the second target value are set to obtain the total target value of each detection point.

[0028] A three-dimensional model of the power transmission line is established, and a control area in which personnel are restricted from entering is obtained according to the position of each detection point corresponding to the detection point; historical monitoring videos for several days are obtained, and the time length of personnel entering the control area corresponding to each detection point is obtained, and the time length is normalized to obtain a second target value of each detection point; The weight values of the first target value and the second target value are set, and a total target value of each detection point is obtained according to the first target value and the second target value of each detection point.

[0029] In this embodiment, the weight values of the first target value and the second target value are W1 and W2 respectively, W1+W2=1, and the total target value X of the detection point is obtained according to the first target value X1 and the second target value X2 of the detection point. The first target value represents the situation of the detection point appearing a defect accident, and the second target value represents the situation of the control area of the detection point appearing a dangerous accident, and both the first target value and the second target value are the greater the value, the greater the supervision intensity of the detection point should be, so the greater the total target value, the greater the supervision intensity of the detection point should be.

[0030] 5、According to the current sampling mode, all sampling points are selected from the detection points, a first discrimination criterion is obtained based on the positions of the detection points and the sampling points, a second discrimination criterion is obtained based on the total target values of the detection points and the sampling points, and whether to perform a pre-warning prompt on the currently selected sampling point is determined according to the first discrimination criterion and the second discrimination criterion.

[0031] The positions of all the current sampling points are obtained, the sampling point b closest to the sampling point a is extracted, the distance between the sampling point a and the sampling point b is taken as the target distance of the sampling point a, and the sampling point a is marked; the non-marked sampling point c closest to the sampling point b is obtained, the distance between the sampling point b and the sampling point c is taken as the target distance of the sampling point b, and the sampling point b is also marked, and so on, to obtain the target distance of each sampling point and calculate the average value L1; then the target distance of each detection point is obtained according to the position of each detection point, and the average value L2 is calculated; The average value P1 is calculated according to the total target value of each sampling point, the average value P2 is calculated according to the total target value of each detection point, if L1<k1*L2 or P1<k2*P2, k1 and k2 are the first ratio and the second ratio respectively, then a pre-warning prompt is performed on the currently selected sampling point.

[0032] The embodiment also provides a large model-based cross-industry multi-source fault intelligent research and judgment system, including a target data obtaining module, a first target value calculation module, a total target value calculation module and a warning prompt module, the target data obtaining module includes a target data obtaining unit, the total target value calculation module includes a second target value calculation unit and a total target value calculation unit; the system realizes the large model-based cross-industry multi-source fault intelligent research and judgment method described above when executing a computer program, and since the large model-based cross-industry multi-source fault intelligent research and judgment method has been described in detail above, no further description is given here.

[0033] It should be noted that the above-mentioned sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0034] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0035] The above is only the preferred embodiment of the application, and is not used to limit the application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A cross-industry multi-source fault intelligent analysis method based on a large model, characterized by: The following steps are involved: Retrieve historical fault records of transmission lines and extract the fault time, fault location and fault type; Deploy sensors of different physical types at different locations on the transmission line in advance to obtain the sensor locations and historical sensor data, and obtain the target data corresponding to each physical type at each fault location; Obtain the normal value range monitored by the sensor and the defect level of the fault location, and obtain the degree of correlation between each fault type and each physical type based on the target data, and then obtain the associated physical type and correlation function corresponding to each fault type; Extract all detection points on the target transmission line and obtain the target data corresponding to each detection point in each physical type based on the location of the sensor and the detection point; obtain the first target value of the detection point based on the target data, the associated physical type and the correlation function; Build a three-dimensional model of the transmission line, extract the control areas where people are restricted from entering the transmission line, and obtain the second target value for each detection point based on the time when people enter the control areas in historical surveillance videos; Set the weights of the first target value and the second target value to obtain the total target value of each detection point; According to the current sampling method, all sampling points are selected from the detection points, and the first discrimination criterion is obtained based on the position of each detection point and the sampling point. The second discrimination criterion is obtained based on the total target value of each detection point and the sampling point. According to the first discrimination criterion and the second discrimination criterion, it is determined whether to issue an early warning prompt for the currently selected sampling point.

2. The cross-industry multi-source fault intelligent analysis method based on a large model according to claim 1 is characterized in that: Obtain the target data corresponding to each fault location and each physical type, including: Extract the fault location P, fault time, and fault type of a fault record. Use the radius r around the fault location P as the detection range. Obtain all sensors within the detection range that monitor a physical type m. Use the sensor data from the sensor closest to the fault location P over several days as the target data corresponding to the fault location P in physical type m. If there is no sensor monitoring a certain physical type n within the detection range, obtain all sensors monitoring physical type n in the transmission line, use the reciprocal of the distance between the location of each sensor and the fault location P as the characteristic distance corresponding to each sensor, add all characteristic distances to obtain a characteristic value, and divide each characteristic distance by the characteristic value to obtain the distance weight corresponding to each sensor; obtain the sensing value of each sensor at each moment for several historical days, and obtain the target data corresponding to the fault location P in physical type n based on the distance weight.

3. The cross-industry multi-source fault intelligent analysis method based on a large model according to claim 2 is characterized in that: Obtain the associated physical type and associated function corresponding to each fault type, including: Obtain the normal value range monitored by a sensor of a certain physical type q, extract the target data Dte corresponding to the fault location P in physical type q, set the fault type corresponding to the fault location P as h, and use the ratio of the number of moments when the sensor value in the target data Dte exceeds the normal value range to the total number of moments in the target data Dte as the target ratio of the fault location P in fault type h to physical type q. Build a neural network model, obtain a number of fault location datasets that belong to fault type h but have different defect levels, and train the neural network model; substitute the fault location P into the trained neural network model to obtain the target defect level of the fault location P in fault type h. According to historical fault records, obtain the target ratio and target defect level corresponding to a number of fault types h and physical types q, and perform a linear function fitting of the change of the target defect level with the target ratio. Take the goodness of fit corresponding to the fitting process as the degree of association between fault type h and physical type q; further obtain the degree of association between fault type h and each physical type, and take the physical type corresponding to the largest degree of association as the associated physical type of the fault type h, and take the corresponding linear function of the fitting as the associated function of the fault type h.

4. The cross-industry multi-source fault intelligent analysis method based on a large model according to claim 3 is characterized in that: Obtain the first target value of the detection point, including: extract all detection points on the target transmission line, obtain the corresponding detection range according to the position of a certain detection point DP, and obtain the target data corresponding to each physical type of the detection point DP according to the detection range and the position of each sensor. Obtain the target ratio in the target data corresponding to a physical type w, and then obtain the fault level of the detection point DP for each fault type based on the associated physical type and correlation function corresponding to each fault type, and then obtain the first target value of the detection point DP: , where D is the number of fault types, e is a natural constant, and R d is the fault level of the dth fault type; and then the first target value of each detection point is obtained.

5. The cross-industry multi-source fault intelligent analysis method based on a large model according to claim 1 is characterized in that: Obtain the total target value of each detection point, including: build a three-dimensional model of the transmission line, and obtain the control area that restricts personnel entry corresponding to each detection point according to the position of each detection point; obtain the monitoring videos of several historical days, obtain the duration of personnel entering the control area corresponding to each detection point, and normalize the duration to obtain the second target value of each detection point; set the weights of the first target value and the second target value, and obtain the total target value of each detection point according to the first target value and the second target value of each detection point.

6. The cross-industry multi-source fault intelligent analysis method based on a large model according to claim 1 is characterized in that: Judge whether to give a warning prompt for the currently selected sampling point, including: Obtain the positions of all current sampling points, extract the sampling point b closest to a certain sampling point a, take the distance between the sampling point a and the sampling point b as the target distance of the sampling point a, and mark the sampling point a; obtain the unmarked sampling point c closest to the sampling point b, take the distance between the sampling point b and the sampling point c as the target distance of the sampling point b, and mark the sampling point b as well, and so on, to obtain the target distance of each sampling point, and calculate the average value L1; then obtain the target distance of each detection point according to the position of each detection point, and calculate the average value L2. Calculate the average value P1 according to the total target value of each sampling point, calculate the average value P2 according to the total target value of each detection point. If there is L1 < k1 * L2 or P1 < k2 * P2, where k1 and k2 are the first ratio and the second ratio respectively, then give a warning prompt for the currently selected sampling point.

7. A cross-industry multi-source fault intelligent analysis and judgment system, used to execute the cross-industry multi-source fault intelligent analysis and judgment method based on a large model according to any one of claims 1 to 6, characterized in that: The system includes a target data acquisition module, a first target value calculation module, a total target value calculation module, and a warning prompt module. The target data acquisition module: is used to retrieve the historical fault records of the transmission line and extract the fault time, fault location, and fault type of the fault records. Deploy sensors of different physical types at different locations on the transmission line in advance to obtain the sensor locations and historical sensor data, and obtain the target data corresponding to each physical type at each fault location; The first target value calculation module is used to obtain the normal value range monitored by the sensor and the defect level of the fault location, and obtain the degree of correlation between each fault type and each physical type based on the target data, and then obtain the associated physical type and correlation function corresponding to each fault type; Extract all detection points on the target transmission line and obtain the target data corresponding to each detection point in each physical type based on the location of the sensor and the detection point; Obtaining a first target value of the detection point according to the target data, the associated physical type and the associated function; Total target value calculation module: used to build a three-dimensional model of the transmission line, extract the control area where personnel are restricted from entering the transmission line, and obtain the second target value of each detection point based on the time when personnel entered the control area in the historical monitoring video; Set the weights of the first target value and the second target value to obtain the total target value of each detection point; Early warning prompt module: used to select all sampling points from the detection points according to the current sampling method, obtain the first discrimination criterion based on the position of each detection point and sampling point, obtain the second discrimination criterion based on the total target value of each detection point and sampling point, and determine whether to issue an early warning prompt for the currently selected sampling point based on the first discrimination criterion and the second discrimination criterion.

8. The cross-industry multi-source fault intelligent analysis and judgment system according to claim 7 is characterized in that: The target data obtaining module includes a target data obtaining unit; Target data acquisition unit: used to extract the fault location, fault time and fault type of a fault record, obtain the detection range, determine whether there is a sensor monitoring a certain physical type within the detection range, and obtain the target data corresponding to each fault location for each physical type based on the sensor's sensor data and the sensor's location over several days of history.

9. The cross-industry multi-source fault intelligent analysis and judgment system according to claim 7 is characterized in that: The total target value calculation module includes a second target value calculation unit and a total target value calculation unit; The second target value calculation unit is used to establish a three-dimensional model of the transmission line and obtain the control area corresponding to each detection point where personnel are restricted from entering based on the location of each detection point. The monitoring video of several days in the past is obtained to obtain the length of time that personnel have been in the control area corresponding to each detection point, and the time is normalized to obtain the second target value for each detection point. Total target value calculation unit: used to set the weights of the first target value and the second target value, and obtain the total target value of each detection point based on the first target value and the second target value of each detection point.

Images