Multi-sensor cooperative adaptive factor monitoring method, device, equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a multi-sensor cooperative adaptive factor monitoring method, device, equipment and medium, and the method comprises the steps: obtaining the sensor data of a plurality of sensors, carrying out the preprocessing, obtaining a target sensor data set, solving an error variable, calculating the state information and observability, and obtaining a target sensor data set; and judging whether the crossing of the power transmission line is abnormal or not according to the observability. The beneficial effects of the invention are that the method achieves the cooperative detection according to a plurality of sensors, obtains the high-reliability information, achieves the more effective and more accurate troubleshooting of potential safety hazards, achieves the precise recognition and early warning of the safety risk of a crossing section, improves the safety operation level of a power grid, and promotes the construction of an intelligent power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-sensor collaborative adaptive factor monitoring, and in particular to a multi-sensor collaborative adaptive factor monitoring method, device, equipment and medium. Background Art

[0002] "Three spans" refers to the sections where power transmission and distribution lines cross railways, first-class and above highways, and important transmission channels. In recent years, various engineering construction activities have caused accidents of external force damage to overhead lines to occur from time to time, and the trend is accelerating, seriously threatening the safe operation of the power grid. Among them, when the transmission line intersects with other lines such as telecommunication lines, power lines, pipelines, cableways, railways, and highways, the conductors will increase their sag or undergo drastic deformation under the influence of external environmental factors, which will lead to insufficient safety distance from the crossing objects in the channel, thus causing power failures and even disasters in multiple fields. Therefore, the cross-over failure of the transmission line will bring unpredictable serious consequences.

[0003] However, in order to reduce or even eliminate the occurrence of power grid accidents, the traditional method is to use manual inspections, but this requires a lot of manpower and material resources and is highly dangerous. Based on the background of digital transformation, the relevant expert team has cited a variety of new real-time monitoring equipment, including video cameras, millimeter-wave radars, lidars, etc., but the existing transmission line inspection equipment is relatively simple, so it has certain limitations. For example, lidars are greatly affected by weather conditions, video cameras have weak detection capabilities for dynamic targets, and millimeter-wave radars face the problem of low resolution. At the same time, a single inspection device faces the problem of a single data analysis method. The above methods have not yet solved the problem of cross-over faults in transmission lines. Summary of the invention

[0004] Based on this, it is necessary to propose a multi-sensor collaborative adaptive factor monitoring method, device, equipment and medium for the existing multi-sensor collaborative adaptive factor monitoring problem.

[0005] A multi-sensor collaborative adaptive factor monitoring method, the method comprising:

[0006] Collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0007] Preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0008] Calculate the error variable of each sensor data according to the target data set and the sensor data set;

[0009] Calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable;

[0010] Determining whether the observability is within a preset range;

[0011] Determine whether the crossover of the transmission line is abnormal based on the judgment result.

[0012] Furthermore, the step of calculating the state information at each time point according to the target data set includes:

[0013] According to the formula Calculate the initialization data of each target sensor data in each target data set; where f pri (x it ) represents the initialization data at time point t in the i-th target data set, x it represents the target sensor data at time point t in the i-th target data set, m i represents the mean of the target sensor data in the i-th target data set, σ mi Represents the covariance of the i-th target data set;

[0014] According to the formula Calculate the status information at the first time point, and according to the formula Calculate the state information at each time point; where P t represents the state information at the tth time point, n represents the number of target data sets, x it-1 represents the target sensor data at time point t-1 in the i-th target data set, c it Represents the error variable corresponding to the target creation at time point t in the i-th target data set.

[0015] Furthermore, the step of calculating the state information at each time point according to the target data set, and calculating the observability according to the state information and the error variable includes:

[0016] According to the formula Compute the observability at each time point.

[0017] Furthermore, before the step of determining whether the crossover of the transmission line is abnormal according to the judgment result, the method further includes:

[0018] According to the formula Set weights for each state information; γ t Represents the weight of the state information corresponding to the t-th time point;

[0019] Preset credibility thresholds A and B, where B>A;

[0020] According to the formula Calculate the credibility of each state information; where K represents the credibility;

[0021] Calculate the mean credibility of all status information, and determine whether the mean credibility is greater than a preset credibility;

[0022] If it is greater than the preset credibility, the step of determining whether the crossover of the power transmission line is abnormal according to the judgment result is executed.

[0023] Furthermore, the multiple sensors include at least three sensors: millimeter wave radar, laser radar, and binocular camera.

[0024] Furthermore, the step of preprocessing each sensor data in each sensor data set to obtain a target data set corresponding to each sensor data set includes:

[0025] Obtain the detection environment of each sensor during detection;

[0026] Setting a data conversion function according to the detection environment;

[0027] The corresponding sensor data is preprocessed according to the data conversion function to obtain the corresponding target sensor data, and then the target data set is obtained.

[0028] Furthermore, the step of determining whether the crossover of the transmission line is abnormal according to the judgment result comprises:

[0029] If the observability is within a preset range, it is determined that the transmission line crossing is normal;

[0030] If the observability is not within a preset range, it is determined that the transmission line crossing is abnormal.

[0031] A multi-sensor collaborative adaptive factor monitoring device is used to monitor the cross-span of a transmission line, the device comprising:

[0032] A collection module, used to collect sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0033] A preprocessing module, used for preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0034] A first calculation module, configured to calculate an error variable of each sensor data according to the target data set and the sensor data set;

[0035] A second calculation module, used to calculate the state information of each time point according to the target data set, and calculate the observability according to the state information and the error variable;

[0036] A judging module, used to judge whether the observability is within a preset range;

[0037] The determination module is used to determine whether the crossover of the transmission line is abnormal according to the determination result.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0039] Collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0040] Preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0041] Calculate the error variable of each sensor data according to the target data set and the sensor data set;

[0042] Calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable;

[0043] Determining whether the observability is within a preset range;

[0044] Determine whether the crossover of the transmission line is abnormal based on the judgment result.

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0046] Collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0047] Preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0048] Calculate the error variable of each sensor data according to the target data set and the sensor data set;

[0049] Calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable;

[0050] Determining whether the observability is within a preset range;

[0051] Determine whether the crossover of the transmission line is abnormal based on the judgment result.

[0052] The beneficial effects of the present invention are as follows: by acquiring sensor data from multiple sensors and performing preprocessing to obtain a target sensor data set, then obtaining error variables, and calculating state information and observability, a judgment is made as to whether the crossing of transmission lines is abnormal based on the observability, thereby achieving collaborative detection based on multiple sensors to obtain highly reliable information, thereby more effectively and accurately troubleshooting potential safety hazards, achieving accurate identification and early warning of safety risks in the crossing section, improving the safe operation level of the power grid, and promoting the construction of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0054] in:

[0055] Figure 1 A diagram showing an application environment of a multi-sensor collaborative adaptive factor monitoring method in one embodiment;

[0056] Figure 2 A flowchart of multi-sensor collaborative adaptive factor monitoring in one embodiment;

[0057] Figure 3 It is a structural block diagram of a multi-sensor collaborative adaptive factor monitoring device in one embodiment;

[0058] Figure 4 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Figure 1 FIG. 1 is a diagram of an application environment for multi-sensor collaborative adaptive factor monitoring in an embodiment. Figure 1, the multi-sensor collaborative adaptive factor monitoring method is applied to a multi-sensor collaborative adaptive factor monitoring system. The multi-sensor collaborative adaptive factor monitoring system includes a terminal 110 and a server 120. The terminal 110 and the server 120 are connected through a network. The terminal 110 can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented as an independent server or a server cluster composed of multiple servers. The terminal 110 is used to obtain sensor data, and the server 120 is used to analyze the sensor data.

[0061] like Figure 2 As shown, in one embodiment, a multi-sensor collaborative adaptive factor monitoring method is provided. The method can be applied to both a terminal and a server. This embodiment is illustrated by applying to a server. The multi-sensor collaborative adaptive factor monitoring method specifically includes the following steps:

[0062] S1: collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0063] S2: preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0064] S3: Calculate the error variable of each sensor data according to the target data set and the sensor data set;

[0065] S4: calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable;

[0066] S5: Determine whether the observability is within a preset range;

[0067] S6: Determine whether the crossover of the transmission line is abnormal based on the judgment result.

[0068] As described in step S1 above, multiple sensors are used to collect sensor data at multiple time points within a period of time to obtain multiple sensor data sets; in the actual detection process, the sensor will continuously collect data, so a period of time usually refers to the most recent time period, and the selection of time points can be selected according to the actual situation, such as an interval of one hour, or an interval of ten minutes, etc., so as to obtain a sensor data set. When selecting the time interval, the system can be flexibly adjusted according to the actual monitoring needs, such as setting the data collection every ten minutes to observe rapidly changing situations, or collecting data once an hour to meet relatively stable monitoring needs. This flexibility enables the system to respond to different environmental changes and external factors in a timely manner, thereby improving the accuracy of monitoring.

[0069] As described in step S2 above, each sensor data in each of the sensor data sets is preprocessed to obtain a target data set corresponding to each sensor data set. Since there will be some errors between the collected data and the actual data, the data needs to be preprocessed. The specific processing method is not limited. For example, the detection result can be adjusted according to the environmental factors in which the sensor is located. After data collection, each sensor data set needs to be preprocessed. Due to various environmental factors (such as temperature, humidity and other weather conditions), there may be differences between sensor data and actual status. Calibration and adjustment of the collected data by technical means not only improves the accuracy of the data, but also enhances the reliability of the system. There are many preprocessing methods, and means such as denoising, smoothing or using filters can be selected to improve data quality. For different monitoring environments and types, the preprocessing scheme should be flexible enough to adapt to a variety of complex data and environmental conditions. Through these precise preprocessing steps, the system can better reflect the true state of the transmission line and lay a solid foundation for subsequent data analysis.

[0070] As described in the above step S3, the error variable of each sensor data is calculated according to the target data set and the sensor data set. Since the sensor data and the target sensor data will be different after adjustment, the error variable can be calculated based on the sensor data and the target sensor data. Specifically, the sensor data is subtracted from the target sensor data, and the absolute value is obtained, and then the absolute value is divided by the target sensor data to obtain the error variable. The data is preprocessed and the error variable is calculated. By comparing the sensor data with the target value, calculating the absolute value of the difference and normalizing it, the error degree of each sensor data can be derived. This analysis not only helps to evaluate the accuracy of the sensor, but is also an important indicator for judging data quality and identifying abnormal signals.

[0071] As described in step S4 above, the state information at each time point is calculated according to the target data set, and the observability is calculated according to the state information and the error variable. Since the target data set has been obtained, the target sensor data of each target data set at each time point is fused. The specific fusion method is not limited. For example, weighted summation or other methods can be performed, and then the observability is calculated based on the state information and error variables. The observability can be calculated according to the Jacobian matrix and noise. The target data set is used to combine the state information and error variables at each time point to calculate the observability. By performing weighted summation or other fusion methods on each target data set, the system can integrate the information provided by different sensors to obtain an overall state assessment. The calculation of observability involves complex mathematical models, and the combination of Jacobian matrix and noise analysis will further improve the sensitivity of the monitoring system. The system can identify state changes under different environments, making the monitoring results more accurate and effective.

[0072] As described in the above steps S5-S6, it is determined whether the observability is within a preset range, and whether the crossover of the transmission line is abnormal according to the judgment result. Among them, the preset range is a range pre-set by relevant personnel according to actual conditions. When it is within this range, it is determined that the crossover of the transmission line is normal, and when it is not within this range, it is determined that the crossover of the transmission line is abnormal. Thus, it is realized that collaborative detection is performed according to multiple sensors to obtain highly reliable information, so as to more effectively and accurately check the potential safety hazards, achieve accurate identification and early warning effects of safety risks in the crossover section, improve the safe operation level of the power grid, and promote the construction of smart grids. The monitoring system compares the calculated observability with the preset range. According to the judgment result, the system can quickly determine whether the crossover state of the transmission line is abnormal. The preset range should be set based on historical data and experience to ensure its rationality. When the observability is within the preset range, the system will determine that the line state is normal; otherwise, it will prompt potential risks. This can effectively reduce the probability of accidents, and to a certain extent avoid delays caused by unmanned monitoring or manual inspection, thereby further improving the safety and reliability of the transmission line. Through the comprehensive application of multi-sensor collaborative adaptive factor monitoring methods, multiple benefits can be achieved. First, this method can provide highly reliable information support to ensure the rapid identification of potential risks. The introduction of such intelligent monitoring methods can significantly improve the safe operation level of the power system and provide data support for relevant decisions. Secondly, this monitoring method plays an important role in promoting the intelligent construction of power grids. Through real-time analysis and processing of data, power companies can manage resources more effectively, optimize operating modes, and improve emergency response capabilities to emergencies. In addition, intelligent monitoring and control can integrate more innovative technologies for future power systems, such as the Internet of Things (IoT) and artificial intelligence (AI), to realize the vision of smart grids.

[0073] In one embodiment, the step S4 of calculating the state information at each time point according to the target data set includes:

[0074] S401: According to the formula Calculate the initialization data of each target sensor data in each target data set; where f pri (x it ) represents the initialization data at time point t in the i-th target data set, x it represents the target sensor data at time point t in the i-th target data set, m i represents the mean of the target sensor data in the i-th target data set, σ mi Represents the covariance of the i-th target data set;

[0075] S402: According to the formula Calculate the status information at the first time point, and according to the formula Calculate the state information at each time point; where P t represents the state information at the tth time point, n represents the number of target data sets, x it-1 represents the target sensor data at time point t-1 in the i-th target data set, c it Represents the error variable corresponding to the target creation at time point t in the i-th target data set.

[0076] As described in the above steps 401-S402, the calculation of the state information is realized, that is, according to the formula Calculate the initialization data of each target sensor data in each target data set; encode the posterior probability of the state information, which can effectively solve the problem of multi-time series data fusion. Introduce a sliding window, take the information outside the window as prior information, and then use the algorithm to eliminate the state quantity in the window until the time point to be calculated. Assuming that the time point to be calculated is a new factor node, then on the basis of the original, slide the window to the right so that the new window contains a new factor node, take the variables outside the new window as prior information, use the elimination algorithm to calculate, and then perform multiple iterations through the Gauss-Newton iteration method to finally calculate the state information.

[0077] In one embodiment, the step S4 of calculating the state information at each time point according to the target data set and calculating the observability according to the state information and the error variable includes:

[0078] S411: According to the formula Compute the observability at each time point.

[0079] As described in step S411 above, the observability is calculated. To characterize the multi-sensor information fusion effect, the formula Perform calculations.

[0080] In one embodiment, before the step S6 of determining whether the crossover of the transmission line is abnormal according to the judgment result, the method further includes:

[0081] S501: According to the formula Set weights for each state information; γ t Represents the weight of the state information corresponding to the t-th time point;

[0082] S502: presetting credibility thresholds A and B, where B>A;

[0083] S503: According to the formula Calculate the credibility of each state information; where K represents the credibility;

[0084] S504: Calculate the mean credibility of all state information, and determine whether the mean credibility is greater than a preset credibility;

[0085] S505: If it is greater than the preset credibility, the step of determining whether the cross-crossing of the power transmission line is abnormal according to the judgment result is executed.

[0086] As described in the above steps S501-S505, since the above calculated state information has a certain error, it is verified by introducing the credibility method, that is, according to the formula A weight is set for each state information, and credibility thresholds A and B are preset, wherein A and B are preset thresholds, which are set by relevant personnel according to actual conditions. The idea of ​​piecewise function is used to set the critical credibility thresholds A and B, and the access process of each combination factor is actively optimized to ensure full use of credible information. If it is greater than the preset credibility, the step of determining whether the transmission line crossing is abnormal according to the judgment result is executed.

[0087] In one embodiment, the multiple sensors include at least three sensors: millimeter wave radar, laser radar, and binocular camera.

[0088] In one embodiment, the step S2 of preprocessing each sensor data in each sensor data set to obtain a target data set corresponding to each sensor data set includes:

[0089] S201: Acquire the detection environment of each sensor during detection;

[0090] S202: Setting a data conversion function according to the detection environment;

[0091] S203: Preprocessing the corresponding sensor data according to the data conversion function to obtain corresponding target sensor data, and then obtaining a target data set.

[0092] As described in the above steps S201-S203, the sensor data is preprocessed, that is, the sensor has different errors in different environments, and the test cross-crossing fault problem usually occurs in the wild, which causes the sensor to have a large error. Therefore, based on big data, a conversion function can be established for the error caused by the environment in which the sensor is located. Specifically, the conversion function can be a linear function, a quadratic function, a logarithmic function, an exponential function, etc., and a related calculation model can also be used to replace the calculation function, so that the sensor data can be preprocessed according to the corresponding conversion function to obtain the target sensor data to reduce the error caused by the test.

[0093] In one embodiment, the step S6 of determining whether the crossover of the transmission line is abnormal according to the judgment result includes:

[0094] S601: If the observability is within a preset range, it is determined that the transmission line crossing is normal;

[0095] S602: If the observability is not within a preset range, it is determined that there is a transmission line crossing abnormality.

[0096] As described in the above steps S601-S602, if the observability is within the preset range, it means that the detection data is in line with normal conditions and the crossover of the transmission lines is normal. If the observability is not within the preset range, it means that the detection data is not in line with normal conditions and the crossover of the transmission lines is abnormal, thereby realizing the judgment of whether the crossover of the transmission lines is abnormal.

[0097] In a specific embodiment, in the time series t1 to tn, the signal values ​​obtained by sensor x are represented by x1 to xn, the signal values ​​obtained by sensor 2 are represented by y1 to yn, the signal values ​​obtained by sensor 3 are represented by z1 to zn, and the signal values ​​obtained by sensor n are represented by θ1 to θn. The sensors are represented by rectangles, and the signal errors are represented by ellipses. The connecting lines in the figure represent the input and output of information. When the signal state is updated, they are added and re-fused into the next moment, and then multiple sensors are fused. The initialization value of the known information is recorded as f pri (x), the specific calculation method is:

[0098]

[0099] Among them, m x is the mean of the states, σ m is the covariance matrix.

[0100] The factor graph encodes the posterior probability of the state information, which can effectively solve the problem of multi-time series data fusion. The sliding window is introduced, the information outside the window is used as the prior information, and then the algorithm is used to eliminate the state quantity in the window until the update time. The specific steps of the algorithm are as follows:

[0101] First, insert a new factor node at a specific time point and move the sliding window to the right. At this time, the window includes the newly added factor node. Second, the variables outside the sliding window can be used as prior information and calculated using the elimination algorithm at the next moment. Third, multiple iterations are performed through the Gauss-Newton iteration method to finally calculate the optimal state. Fourth, information fusion is performed on multiple sensors. The line state estimates after multi-sensor parameter perception fusion are:

[0102] P1(x,y,z,…,θ)=f x-pri (x1)f y-pri (y1)f z-pri (z1)…f θ-pri (θ1)

[0103] P2(x,y,z,…,θ)=f x (x2,x1,c x1 )f y (y2,y1,c y1 )f z (z2,z1,c z1 )…f θ (θ2,θ1,θ z1 )

[0104] P i (x,y,z,…,θ)=f x (x i ,x i-1 ,c xi )f y (y i ,y i-1 ,c y(i-1) )f z (z i ,z i-1 ,c z(i-1) )…f θ (θ i ,θ i-1 ,θ z(i-1) )

[0105]

[0106] Among them, i is a moment in the time series, n is the total number of moments, is the signal error variable at a certain moment, f x-pri 、f y-pri 、f z-pri 、f θ-pri are the initialization values ​​of each sensor, P i (x, y, z, …, θ) is the predicted value of the transmission line state at a certain moment, f y (y2,y1,c y1 ), f z (z2,z1,c z1 ) and f θ (θ2,θ1,θ z1 ) is the information function of each sensor.

[0107] Specifically, a multi-sensor fusion perception inspection architecture is used for the key section of the "three spans" of a 220kV transmission line in a certain area, and an example of obtaining accurate status information of the transmission line in real time through the cross-span adaptive factor graph algorithm is described as follows:

[0108] Step 1: Based on the real-time monitoring requirements of the cross-section of transmission lines, design an application architecture suitable for real-time monitoring of the cross-section of transmission lines;

[0109] Based on the investigation of the key "three spans" section of the 220kV transmission line in a certain area, a patrol inspection architecture with collaborative perception of millimeter-wave radar, lidar, and binocular camera was adopted, and the signal data at three times t1, t2, and t3 were used as examples for calculation.

[0110] Step 2: Analyze the data fusion requirements generated by multiple sensor joint detection methods in the cross-span monitoring of the key sections of the "three spans", and construct a factor graph model for multi-sensor collaborative detection;

[0111] Based on the data fusion requirements generated by the joint inspection of three sensors: millimeter-wave radar, lidar, and binocular camera.

[0112] Step 3: Use a global optimization strategy to design an adaptive factor graph information fusion algorithm for multi-sensor collaborative perception.

[0113] Take t1 = 10s, t2 = 20s, t3 = 30s;

[0114] 41 = 26dB, 42 = 3dB, 43 = 27dB; therefore, m x =18.67dB,σ mx =5,

[0115] but

[0116] y1=32dB,y2=26dB,y3=29dB;therefore,m y =29dB,σ my =-15,

[0117] but

[0118] z1=28dB,z2=33dB,z3=25dB; therefore, m z =28.67dB,

[0119] but

[0120] because in Therefore:

[0121]

[0122] because in Therefore:

[0123]

[0124] because in Therefore:

[0125]

[0126] At t1, t2, and t3, the line status estimates after the fusion of the three sensors, millimeter-wave radar, lidar, and binocular camera, are:

[0127] P1(x,y,z)=f x-pri (x1)f y-pri (y1)f z-pri (z1)=134.4*(-67.5)*(-3.33)=30250dB

[0128] P2(x,y,z)=f LiDAR (x2,x1,c x1 )f MMW (y2,y1,c y1 )f Bin (z2,z1,c z1 )=26.12*166.27*5=21715dB

[0129]

[0130] Step 4: Establish an observability and allocation weight model that reflects the algorithm's operating performance.

[0131] At t1, t2, and t3, the observability D1, D2, and D3 are:

[0132]

[0133]

[0134]

[0135] The corresponding allocation weights γ1, γ2, and γ3 at time t1, t2, and t3 are:

[0136]

[0137]

[0138] Step 5: Obtain the validity of the calculation results for the cross-span fault problem identification through credibility calculation.

[0139] The specific calculation of credibility K is as follows:

[0140]

[0141] According to the consideration of the signal acquisition boundary conditions due to the influencing factors of the transmission line crossing, A=0.01, B=0.015 are taken. Since γ1, γ2 and γ3 are all greater than 0.015, that is, at each time t1, t2 and t3, the value of the credibility K is 1, so the reliability of the algorithm is 1. It can be seen that the multi-sensor collaborative adaptive factor graph fusion perception method suitable for transmission line crossing monitoring has high reliability and strong applicability.

[0142] Reference Figure 3 The present invention also provides a multi-sensor collaborative adaptive factor monitoring device, the device comprising:

[0143] The acquisition module 10 is used to acquire sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data acquired by a single sensor;

[0144] A preprocessing module 20, used for preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0145] A first calculation module 30, configured to calculate an error variable of each sensor data according to the target data set and the sensor data set;

[0146] A second calculation module 40, configured to calculate state information at each time point according to the target data set, and calculate observability according to the state information and the error variable;

[0147] A judging module 50, configured to judge whether the observability is within a preset range;

[0148] The determination module 60 is used to determine whether the crossover of the transmission line is abnormal according to the determination result.

[0149] In one embodiment, the second calculation module 40 includes:

[0150] Initialize the data calculation submodule to calculate the Calculate the initialization data of each target sensor data in each target data set; where f pri (x it ) represents the initialization data at time point t in the i-th target data set, x it represents the target sensor data at time point t in the i-th target data set, m i represents the mean of the target sensor data in the i-th target data set, σ mi Represents the covariance of the i-th target data set;

[0151] The state information calculation submodule is used to calculate the state information according to the formula Calculate the status information at the first time point, and according to the formula Calculate the state information at each time point; where P t represents the state information at the tth time point, n represents the number of target data sets, x it-1 represents the target sensor data at time point t-1 in the i-th target data set, c it Represents the error variable corresponding to the target creation at time point t in the i-th target data set.

[0152] In one embodiment, the second calculation module 40 includes:

[0153] The observability calculation submodule is used to calculate the Compute the observability at each time point.

[0154] In one embodiment, the multi-sensor collaborative adaptive factor monitoring device further includes:

[0155] The weight setting module is used to set the weight according to the formula Set weights for each state information; γ t Represents the weight of the state information corresponding to the t-th time point;

[0156] A credibility threshold setting module, used to pre-set credibility thresholds A and B, where B>A;

[0157] Credibility calculation module, used to calculate the Calculate the credibility of each state information; where K represents the credibility;

[0158] A credibility mean calculation module, used to calculate the credibility mean of all state information and determine whether the credibility mean is greater than a preset credibility;

[0159] The execution module is used to execute the step of determining whether the cross-crossing of the power transmission line is abnormal according to the judgment result if the reliability is greater than a preset reliability.

[0160] In one embodiment, the multiple sensors include at least three sensors: millimeter wave radar, laser radar, and binocular camera.

[0161] In one embodiment, the preprocessing module 20 includes:

[0162] The detection environment acquisition submodule is used to obtain the detection environment of each sensor during detection;

[0163] A function setting submodule, used for setting a data conversion function according to the detection environment;

[0164] The preprocessing submodule is used to preprocess the corresponding sensor data according to the data conversion function to obtain the corresponding target sensor data, and then obtain the target data set.

[0165] In one embodiment, the determination module 60 includes:

[0166] A first determination submodule, configured to determine that the crossover of the transmission line is normal if the observability is within a preset range;

[0167] The second determination submodule is configured to determine that a transmission line crossing is abnormal if the observability is not within a preset range.

[0168] The beneficial effects of the present invention are as follows: by acquiring sensor data from multiple sensors and performing preprocessing to obtain a target sensor data set, then obtaining error variables, and calculating state information and observability, a judgment is made as to whether the crossing of transmission lines is abnormal based on the observability, thereby achieving collaborative detection based on multiple sensors to obtain highly reliable information, thereby more effectively and accurately troubleshooting potential safety hazards, achieving accurate identification and early warning of safety risks in the crossing section, improving the safe operation level of the power grid, and promoting the construction of smart grids.

[0169] Figure 4 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement a multi-sensor collaborative adaptive factor monitoring method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement a multi-sensor collaborative adaptive factor monitoring method. Those skilled in the art will appreciate that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0170] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0171] Collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0172] Preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0173] Calculate the error variable of each sensor data according to the target data set and the sensor data set;

[0174] Calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable;

[0175] Determining whether the observability is within a preset range;

[0176] Determine whether the crossover of the transmission line is abnormal based on the judgment result.

[0177] It realizes collaborative detection based on multiple sensors and obtains highly reliable information, so as to check safety hazards more effectively and accurately, achieve accurate identification and early warning of safety risks in cross-sections, improve the safe operation level of the power grid, and promote the construction of smart grids.

[0178] In one embodiment, a computer-readable storage medium is provided, storing a computer program, wherein when the computer program is executed by a processor, the processor performs the following steps:

[0179] Collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor;

[0180] Preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set;

[0181] Calculate the error variable of each sensor data according to the target data set and the sensor data set;

[0182] Calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable;

[0183] Determining whether the observability is within a preset range;

[0184] Determine whether the crossover of the transmission line is abnormal based on the judgment result.

[0185] It realizes collaborative detection based on multiple sensors and obtains highly reliable information, so as to check safety hazards more effectively and accurately, achieve accurate identification and early warning of safety risks in cross-sections, improve the safe operation level of the power grid, and promote the construction of smart grids.

[0186] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0187] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0188] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multi-sensor collaborative adaptive factor monitoring method for monitoring the cross-span of a transmission line, characterized in that: The method comprises: Collecting sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor; Preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set; Calculate the error variable of each sensor data according to the target data set and the sensor data set; Calculating state information at each time point according to the target data set, and calculating observability according to the state information and the error variable; Determining whether the observability is within a preset range; Determine whether the crossover of the transmission line is abnormal based on the judgment result.

2. The multi-sensor collaborative adaptive factor monitoring method according to claim 1, characterized in that: The step of calculating the state information at each time point according to the target data set includes: According to the formula Calculate the initialization data of each target sensor data in each target data set; where f pri (x it ) represents the initialization data at time point t in the i-th target data set, x it represents the target sensor data at time point t in the i-th target data set, m i represents the mean of the target sensor data in the i-th target data set, σ mi Represents the covariance of the i-th target data set; According to the formula Calculate the status information at the first time point, and according to the formula Calculate the state information at each time point; where P t represents the state information at the tth time point, n represents the number of target data sets, x it-1 represents the target sensor data at time point t-1 in the i-th target data set, c it Represents the error variable corresponding to the target creation at time point t in the i-th target data set.

3. The multi-sensor collaborative adaptive factor monitoring method according to claim 2, characterized in that: The step of calculating the state information of each time point according to the target data set, and calculating the observability according to the state information and the error variable comprises: According to the formula Compute the observability at each time point.

4. The multi-sensor collaborative adaptive factor monitoring method according to claim 3, characterized in that: Before the step of determining whether the crossover of the transmission line is abnormal according to the judgment result, the method further includes: According to the formula Set weights for each state information; γ t Represents the weight of the state information corresponding to the t-th time point; Preset credibility thresholds A and B, where B>A; According to the formula Calculate the credibility of each state information; where K represents the credibility; Calculate the mean credibility of all status information, and determine whether the mean credibility is greater than a preset credibility; If it is greater than the preset credibility, the step of determining whether the crossover of the power transmission line is abnormal according to the judgment result is executed.

5. The multi-sensor collaborative adaptive factor monitoring method according to claim 1, characterized in that: The multiple sensors include at least three sensors: millimeter wave radar, laser radar, and binocular camera.

6. The multi-sensor collaborative adaptive factor monitoring method according to claim 1, characterized in that: The step of preprocessing each sensor data in each sensor data set to obtain a target data set corresponding to each sensor data set includes: Obtain the detection environment of each sensor during detection; Setting a data conversion function according to the detection environment; The corresponding sensor data is preprocessed according to the data conversion function to obtain the corresponding target sensor data, and then the target data set is obtained.

7. The multi-sensor collaborative adaptive factor monitoring method according to claim 1, characterized in that: The step of determining whether the crossover of the transmission line is abnormal according to the determination result comprises: If the observability is within a preset range, it is determined that the transmission line crossing is normal; If the observability is not within a preset range, it is determined that the transmission line crossing is abnormal.

8. A multi-sensor collaborative adaptive factor monitoring device for monitoring the cross-span of a transmission line, characterized in that: The device comprises: A collection module, used to collect sensor data at multiple time points within a period of time through multiple sensors to obtain multiple sensor data sets; wherein the sensor data set is sensor data collected by a single sensor; A preprocessing module, used for preprocessing each sensor data in each of the sensor data sets to obtain a target data set corresponding to each sensor data set; A first calculation module, configured to calculate an error variable of each sensor data according to the target data set and the sensor data set; A second calculation module, used to calculate the state information of each time point according to the target data set, and calculate the observability according to the state information and the error variable; A judging module, used to judge whether the observability is within a preset range; The determination module is used to determine whether the crossover of the transmission line is abnormal according to the determination result.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the steps of the multi-sensor collaborative adaptive factor monitoring method as claimed in any one of claims 1 to 7.

10. A computer device, characterized in that: The device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the multi-sensor collaborative adaptive factor monitoring method as described in any one of claims 1 to 7.

Images