A method, system, terminal and storage medium for monitoring disconnection of overhead cables

Abstract

The present invention relates to the technical field of power supply cables, and specifically provides a method, system, terminal and storage medium for monitoring the disconnection of an overhead cable, including: S1, obtaining electrical characteristic data, tension detection data and vibration detection data of the overhead cable in real time based on detection equipment; S2, comprehensively processing the current electrical characteristic data, tension detection data and vibration detection data with the data at the previous moment to obtain the difference between adjacent moments; S3, training a random forest model based on historical electrical characteristic data, tension detection data and vibration detection data, inputting the current electrical characteristic data, tension detection data and vibration detection data, and outputting the predicted cable score at the next moment; S4, when the difference between adjacent moments is greater than the difference threshold and / or the predicted cable score is greater than the score threshold, the cable is at risk of disconnection. The risk of disconnection can be discovered in time, the safe and stable operation of the overhead cable can be guaranteed, and various losses caused by cable disconnection can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply cables, and in particular to a method, system, terminal and storage medium for monitoring the disconnection of an overhead cable. Background Art

[0002] Overhead cables refer to cables that are installed on supports such as electric poles and towers and laid in the air. They are mainly used in fields such as power transmission and communications and are extremely commonly used in the national economy.

[0003] Due to the complex structure of overhead cables, their large scale and numerous branches, overhead cables are prone to cable breakage and failures under the influence of mechanical external forces, electrical effects, lightning strikes, line wear and other factors, which can easily cause various losses. With the increasing demand for power supply and use, it is very important to monitor overhead cables.

[0004] Existing overhead cable monitoring is performed through detection and analysis of their electrical characteristics. When the overhead cables are not completely disconnected, it often does not immediately cause obvious changes in electrical characteristics or significant mechanical deformation, making it difficult to monitor subtle damage in the early stages. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides a method, a system, a terminal and a storage medium to solve the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides a doctor-patient interaction management method, comprising:

[0007] A method for monitoring an overhead cable breakage comprises the following steps:

[0008] S1, obtaining electrical characteristic data, tension detection data and vibration detection data of overhead cables in real time based on detection equipment;

[0009] S2, comprehensively processing the current electrical characteristic data, tension detection data and vibration detection data with the data at the previous moment to obtain the difference between adjacent moments;

[0010] S3, training a random forest model based on historical electrical characteristic data, tension detection data, and vibration detection data, inputting current electrical characteristic data, tension detection data, and vibration detection data, and outputting a predicted cable score at the next moment;

[0011] S4: When the difference between adjacent moments is greater than a difference threshold and / or the predicted cable score is greater than a score threshold, there is a risk of cable disconnection.

[0012] In an optional implementation, in step S2, obtaining the difference between adjacent moments specifically includes:

[0013] Obtain the mutation situation of electrical characteristic data, the mutation situation of tension detection data and the mutation situation of vibration detection data at the current moment respectively;

[0014] Obtain the correlation between the electrical characteristic data, tension detection data and vibration detection data at different times;

[0015] When two of the mutation conditions of the gas characteristic data, the tension detection data, and the vibration detection data exceed the mutation threshold, or when the correlation at the current moment changes significantly, it is determined that there is a severe risk of disconnection.

[0016] In an optional implementation, obtaining the sudden change of electrical characteristic data, the sudden change of tension detection data, and the sudden change of vibration detection data at the current moment specifically includes:

[0017] Based on multiple moments before the current moment, sliding windows are constructed for electrical characteristic data, tension detection data, and vibration detection data respectively;

[0018] Calculate the local mean and local standard deviation of each sliding window respectively;

[0019] When the electrical characteristic data at the current moment exceeds the local standard deviation of a preset multiple compared with the local mean of its sliding window, the electrical characteristic data at the current moment has a mutation;

[0020] When the tension detection data at the current moment exceeds the local standard deviation of a preset multiple compared with the local mean of its sliding window, the tension detection data at the current moment has a mutation;

[0021] When the vibration detection data at the current moment exceeds the local standard deviation of a preset multiple compared with the local mean of the sliding window, the vibration detection data at the current moment has a mutation.

[0022] In an optional implementation, obtaining correlations between electrical characteristic data, tension detection data, and vibration detection data at different moments specifically includes:

[0023] Obtaining electrical characteristic data time series, tension detection data time series and vibration detection data time series respectively;

[0024] Based on the Pearson correlation coefficient formula, the correlation coefficients between the electrical characteristic data, the tension detection data and the vibration detection data at each moment are calculated;

[0025] Determining whether the relevance at the current moment has changed significantly specifically includes:

[0026] Apply Fisher Z transform to each correlation coefficient at the current moment and the previous moment;

[0027] Calculate the correlation difference between the current moment and the previous moment based on the Fisher Z transform result;

[0028] The correlation difference is tested for significance in combination with the preset correlation threshold. When the correlation difference is less than the correlation threshold, there is a significant change.

[0029] In an optional implementation, the process of training the random forest model specifically includes:

[0030] After preprocessing, the historical electrical characteristic data, tension detection data, and vibration detection data are divided into a training set and a test set;

[0031] Set the parameters of the random forest and initialize the random forest model;

[0032] Build multiple decision trees. For each decision tree, randomly extract a subset from the training set with replacement, randomly select a part of the features in the training set as splitting conditions, and evaluate the optimal split to split the node.

[0033] Each decision tree outputs a prediction result, and the prediction results of each tree are combined to obtain the predicted cable score;

[0034] The performance of the random forest model is evaluated using the test set based on the evaluation indicators, and the parameters of the random forest are adjusted according to the evaluation results to obtain the final random forest model.

[0035] In an optional implementation, in step S4, the scoring threshold includes a first scoring threshold and a second scoring threshold, and step S4 specifically includes:

[0036] When the predicted cable score is less than the first score threshold and the difference between adjacent moments is not greater than the difference threshold, there is no risk of disconnection;

[0037] When the predicted cable score is not less than the first score threshold and less than the second score threshold and the difference between adjacent moments is not greater than the difference threshold, there is a slight risk of disconnection;

[0038] When the predicted cable score is greater than a first score threshold and / or the difference between adjacent moments is greater than a difference threshold, the cable is at risk of severe disconnection.

[0039] In an alternative embodiment,

[0040] The detection device includes a current transformer and a voltage transformer for detecting electrical characteristic data, a tension sensor for detecting tension detection data, and a vibration sensor for detecting vibration detection data.

[0041] In a second aspect, the present invention provides a method for monitoring the breakage of an overhead cable. When the system is executed, the steps of the above-mentioned method for monitoring the breakage of an overhead cable are implemented. The system includes:

[0042] The data acquisition module acquires the electrical characteristic data, tension detection data and vibration detection data of the overhead cable in real time based on the detection equipment;

[0043] The difference acquisition module comprehensively processes the current electrical characteristic data, tension detection data and vibration detection data with the data at the previous moment to obtain the difference between adjacent moments;

[0044] Model training module, which trains the random forest model based on historical electrical characteristic data, tension detection data and vibration detection data, inputs the current electrical characteristic data, tension detection data and vibration detection data, and outputs the predicted cable score at the next moment;

[0045] The risk judgment module determines that when the difference between adjacent moments is greater than a difference threshold and / or the predicted cable score is greater than a score threshold, the cable is at risk of disconnection.

[0046] In a third aspect, a terminal is provided, including:

[0047] processor, memory, wherein:

[0048] The memory is used to store computer programs.

[0049] The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0050] In a fourth aspect, a computer storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the computer-readable storage medium is run on a computer, the computer executes the methods described in the above aspects.

[0051] The beneficial effect of the present invention is that the overhead cable break monitoring method, system, terminal and storage medium provided by the present invention can obtain the electrical characteristics, tension and vibration data of the overhead cable in real time through the detection equipment, and can comprehensively and accurately capture the operating status of the cable. The current data and the data at the previous moment are comprehensively processed to obtain the difference between adjacent moments, and the random forest model is trained based on historical data to predict the cable score at the next moment. This multi-dimensional data processing and analysis method can accurately evaluate the cable status. When the difference between adjacent moments exceeds the threshold or the predicted cable score is higher than the threshold, the risk of breakage can be discovered in time, which helps to take maintenance measures in advance, ensure the safe and stable operation of the overhead cable, and reduce various losses caused by cable breakage.

[0052] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 It is a schematic flow chart of a method for monitoring overhead cable breakage according to an embodiment of the present invention.

[0055] Figure 2 It is a schematic block diagram of an overhead cable break monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 should fall within the scope of protection of the present invention.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0058] The overhead cable break monitoring method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the overhead cable break monitoring system runs in the computer device.

[0059] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be an overhead cable break monitoring system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0060] like Figure 1 As shown, the method includes:

[0061] S1, obtaining electrical characteristic data, tension detection data and vibration detection data of overhead cables in real time based on detection equipment;

[0062] The electrical characteristic data can reflect the electrical performance of the cable. For example, the current and voltage data can be used to understand the load of the cable and determine whether the cable's conductivity has changed due to aging or damage.

[0063] The tension test data provides information about the mechanical tension on the cable. Different tension levels reflect the stress state of the cable under different environmental conditions (such as wind load, ice load, etc.). Appropriate tension is essential to maintain the normal suspension and operation of the cable. Too high or too low tension may indicate potential problems with the cable.

[0064] Vibration detection data records the vibration of the cable. In the natural environment, the cable will vibrate due to factors such as wind vibration and ground vibration caused by vehicles passing by. Its vibration frequency, amplitude and other parameters can reflect the dynamic stability of the cable. By monitoring this data, abnormal vibration that may cause cable fatigue damage or resonance can be discovered in time.

[0065] Combining these three types of data, it is possible to comprehensively evaluate the operating status of overhead cables from multiple perspectives, including electrical, mechanical, and dynamics. This comprehensive evaluation helps to more accurately determine the health of the cables and avoid misjudgments that may be caused by a single data type.

[0066] S2, comprehensively processing the current electrical characteristic data, tension detection data and vibration detection data with the data at the previous moment to obtain the difference between adjacent moments;

[0067] It can promptly detect abnormal changes in the cable operation status, whether it is an electrical fault, abnormal tension or abnormal vibration. It can accurately locate the time when the problem occurred, which is convenient for troubleshooting the cause of the fault in combination with the environment and working conditions at the time. It can also achieve early warning. Even if the parameters have not reached the dangerous threshold, if the change trend is abnormal, it can also prompt the operation and maintenance personnel to take preventive measures in advance. The data differences accumulated over a long period of time can provide a basis for optimizing maintenance strategies, help operation and maintenance personnel determine vulnerable parts and working conditions, adjust maintenance priorities and cycles, and improve maintenance efficiency.

[0068] S3, training a random forest model based on historical electrical characteristic data, tension detection data, and vibration detection data, inputting current electrical characteristic data, tension detection data, and vibration detection data, and outputting a predicted cable score at the next moment;

[0069] By using a large amount of historical data for training, the model can fully learn the operating rules of overhead cables under different working conditions and environments, so as to accurately analyze the current data. The predicted cable score at the next moment can evaluate the health status of the cable in advance, provide forward-looking decision-making basis for operation and maintenance personnel, and enable them to take preventive measures before potential problems evolve into actual failures, reduce power outages and equipment damage caused by cable failures, and ensure the stable operation of the power system. At the same time, it optimizes the allocation of operation and maintenance resources and improves operation and maintenance efficiency.

[0070] S4: When the difference between adjacent moments is greater than a difference threshold and / or the predicted cable score is greater than a score threshold, there is a risk of cable disconnection.

[0071] Through comprehensive judgment of data differences and predictive scores, potential risks of overhead cable breaks can be identified in a timely and accurate manner, allowing operation and maintenance personnel to take targeted prevention and repair measures before a break occurs, thereby avoiding a series of serious consequences such as power outages, equipment damage, and public safety accidents caused by cable breaks, ensuring the stability and reliability of power supply, and at the same time helping to rationally arrange operation and maintenance resources and improve the efficiency and accuracy of operation and maintenance work.

[0072] To facilitate understanding of the present invention, the overhead cable breakage monitoring method provided by the present invention is further described below based on the principle of the overhead cable breakage monitoring method of the present invention and in combination with the process of monitoring the overhead cable breakage in the embodiment.

[0073] Optionally, as an embodiment of the present invention, the detection device includes a current transformer and a voltage transformer for detecting electrical characteristic data, a tension sensor for detecting tension detection data, and a vibration sensor for detecting vibration detection data.

[0074] Optionally, as an embodiment of the present invention, in step S2, obtaining the difference between adjacent moments specifically includes:

[0075] Obtain the mutation situation of electrical characteristic data, the mutation situation of tension detection data and the mutation situation of vibration detection data at the current moment respectively;

[0076] Obtain the correlation between the electrical characteristic data, tension detection data and vibration detection data at different times;

[0077] When two of the mutation conditions of the gas characteristic data, the tension detection data, and the vibration detection data exceed the mutation threshold, or when the correlation at the current moment changes significantly, it is determined that there is a severe risk of disconnection.

[0078] Optionally, as an embodiment of the present invention, obtaining the sudden change of electrical characteristic data, the sudden change of tension detection data, and the sudden change of vibration detection data at the current moment specifically includes:

[0079] Based on multiple moments before the current moment, a sliding window is constructed for the electrical characteristic data, tension detection data, and vibration detection data; a suitable window size W (such as 10 time points) is selected to calculate local statistics. The selection of the window size should be determined according to the sampling frequency and change rate of the data.

[0080] Calculate the local mean and local standard deviation of each sliding window respectively; specifically include:

[0081] When processing the data at time t, the local mean and standard deviation are calculated as follows:

[0082]

[0083]

[0084] in, Represents the value of the i-th eigenvalue at time j.

[0085] When the electrical characteristic data at the current moment exceeds the local standard deviation of a preset multiple compared with the local mean of its sliding window, the electrical characteristic data at the current moment has a mutation;

[0086] When the tension detection data at the current moment exceeds the local standard deviation of a preset multiple compared with the local mean of its sliding window, the tension detection data at the current moment has a mutation;

[0087] When the vibration detection data at the current moment exceeds the local standard deviation of a preset multiple compared with the local mean of the sliding window, the vibration detection data at the current moment has a mutation.

[0088] Based on the above formula, we can get:

[0089]

[0090] For each feature, if the value at a certain time point exceeds M times the local standard deviation (usually M is 2 or 3) compared with the local mean at that time point, it can be considered that a mutation has occurred at that point.

[0091] Optionally, as an embodiment of the present invention, respectively obtaining correlations between electrical characteristic data, tension detection data, and vibration detection data at different times specifically includes:

[0092] Obtaining electrical characteristic data time series, tension detection data time series and vibration detection data time series respectively;

[0093] The correlation coefficients between the electrical characteristic data, tension detection data, and vibration detection data at each moment are calculated based on the Pearson correlation coefficient formula; assuming that the two time series for calculating the correlation coefficient are X and Y, the specific calculation is as follows:

[0094]

[0095] in, is the ith value in the time series X, is the i-th value of Y in the time series, is the mean of the time series X, is the mean of the time series Y, and n is the number of data in the time series;

[0096] The value of each correlation coefficient is between -1 and 1. If ρ≈1, then the two are strongly positively correlated. If ρ≈−1, then the two are strongly negatively correlated. If ρ≈0: there is no linear correlation between the two.

[0097] Determining whether the relevance at the current moment has changed significantly specifically includes:

[0098] Fisher Z transform is applied to each correlation coefficient at the current moment and the previous moment; the specific calculation is:

[0099] Assume that a correlation coefficient is obtained at the current moment Correlation coefficient with the previous moment , perform Fisher Z transformation respectively;

[0100]

[0101]

[0102] Wherein, ln represents the natural logarithm;

[0103] Based on the Fisher Z transformation results, the correlation difference between the current moment and the previous moment is calculated; in order to compare the two correlation coefficients, the values ​​under the standard normal distribution are used:

[0104]

[0105] in, and are the number of data in the two time series respectively;

[0106] The correlation difference is tested for significance in combination with the preset correlation threshold. When the correlation difference is less than the correlation threshold, there is a significant change; specifically:

[0107] get After that, we look up the corresponding p-value through the standard normal distribution table. The p-value is the probability value of the position of the z-score in the normal distribution, which is specifically expressed as the probability of obtaining the current z-score under the null hypothesis. If the p-value is less than the set correlation threshold (usually 0.05 or 0.01), we believe that the correlation coefficients of the two time periods are significantly different. If the p-value is greater than the set correlation threshold, no conclusion of significant difference can be drawn.

[0108] Optionally, as an embodiment of the present invention, the process of training the random forest model specifically includes:

[0109] Preprocess the historical electrical characteristic data, tension detection data and vibration detection data; the preprocessing process includes:

[0110] Cleaning data: removing missing values, outliers, or invalid data;

[0111] Feature engineering: extracting features useful for prediction, such as the rate of change of electrical characteristics, tension fluctuations, frequency and amplitude of vibration, etc.

[0112] Standardization or normalization: Ensure that the dimensions of different features are consistent. Usually, z-score standardization or min-max normalization can be used;

[0113] Label encoding: If the data contains categorical features (such as cable type, environmental conditions, etc.), label encoding or one-hot encoding is required;

[0114] Create training and test sets: The data is usually divided into a certain proportion (such as 70% training set and 30% test set).

[0115] Divide the preprocessed data into training set and test set;

[0116] Set the parameters of random forest and initialize the random forest model; set the parameters of random forest, such as the number of trees (n_estimators), maximum depth (max_depth), minimum number of sample splits (min_samples_split), etc.

[0117] Construct multiple decision trees. For each decision tree, randomly extract a subset from the training set with replacement. For each node, randomly select a portion of features (usually a subset of the total number of features) as candidate split features. Select the best split feature and split point based on the optimal splitting condition (such as Gini impurity, information gain, etc.) until the stopping condition is reached (such as reaching the maximum depth, the number of samples contained in the node is less than the minimum number of samples, etc.); for each decision tree, randomly extract the same number of samples as the training set samples with replacement from the training set.

[0118] At each node of each tree, split according to the randomly selected feature subset and the optimal splitting condition until the stopping condition is met;

[0119] For example, if the training set has 1,000 samples, 1,000 samples (possibly repeated) are randomly selected each time to build a decision tree. When each tree node splits, a portion of the features are randomly selected for evaluation. Assuming that the original data has 10 features (including different parameters related to electrical characteristics, tension, and vibration), only 3-5 features may be randomly selected to determine the best splitting feature each time the node splits. This method of randomly sampling samples and randomly selecting features makes each decision tree unique, reduces the correlation between trees, and helps improve the generalization ability of the model.

[0120] Each decision tree outputs a prediction result, and the prediction results of each tree are combined to obtain the predicted cable score;

[0121] Based on the evaluation indicators, the performance of the random forest model is evaluated using the test set, and the parameters of the random forest are adjusted according to the evaluation results to obtain the final random forest model. Common evaluation indicators include Accuracy: the proportion of correct model predictions; Precision: the proportion of samples predicted by the model as disconnected that are actually disconnected; Recall: the proportion of all actual disconnected samples that are correctly predicted by the model; F1-score: the harmonic mean of precision and recall, which comprehensively evaluates the prediction ability of the model.

[0122] Optionally, as an embodiment of the present invention, in step S4, the scoring threshold includes a first scoring threshold and a second scoring threshold, and step S4 specifically includes:

[0123] When the predicted cable score is less than the first score threshold and the difference between adjacent moments is not greater than the difference threshold, there is no risk of disconnection;

[0124] When the predicted cable score is not less than the first score threshold and less than the second score threshold and the difference between adjacent moments is not greater than the difference threshold, there is a slight risk of disconnection;

[0125] When the predicted cable score is greater than a first score threshold and / or the difference between adjacent moments is greater than a difference threshold, the cable is at risk of severe disconnection.

[0126] By accurately classifying the risk level of cable disconnection, the status of overhead cables can be evaluated more carefully and accurately. When the predicted cable score and the difference between adjacent moments meet specific conditions, it can be judged that there is no, slight or severe disconnection risk, which helps operation and maintenance personnel take targeted measures. For situations where there is no risk, unnecessary inspections can be reduced, for slight risks, appropriate monitoring and maintenance can be arranged, and for severe risks, emergency plans can be quickly launched to ensure cable safety, while optimizing the allocation of operation and maintenance resources and improving operation and maintenance efficiency.

[0127] At the same time, when the difference between adjacent moments meets specific conditions, there is a serious risk of line breakage. At this time, the difference is used as the risk judgment standard instead of the predicted cable score, making the cable breakage monitoring more comprehensive and reasonable.

[0128] In some embodiments, the overhead cable break monitoring system may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the overhead cable break monitoring system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Overhead cable break monitoring function.

[0129] In this embodiment, the overhead cable break monitoring system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules of the system may include: a data acquisition module, a difference acquisition module, a model training module, and a risk judgment module. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0130] An embodiment of the present invention provides a terminal, which can be used to execute the overhead cable break monitoring method provided by the embodiment of the present invention.

[0131] The terminal may include: a processor, a memory and a communication unit. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention. It may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0132] The memory can be used to store the execution instructions of the processor, and the memory can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory are executed by the processor, the terminal is enabled to execute some or all of the steps in the following method embodiments.

[0133] The processor is the control center of the storage terminal, which uses various interfaces and lines to connect various parts of the entire electronic terminal, and executes various functions and / or processes data of the electronic terminal by running or executing software programs and / or modules stored in the memory, and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0134] The communication unit is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0135] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0136] Therefore, the technical effects that can be achieved by the present invention, a method, system, terminal and storage medium for monitoring the breakage of an overhead cable, can be found in the description above and will not be repeated here.

[0137] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0138] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0139] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0140] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0142] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A method for monitoring the breakage of an overhead cable, characterized in that: The following steps are involved: S1, obtaining electrical characteristic data, tension detection data and vibration detection data of overhead cables in real time based on detection equipment; S2, comprehensively processing the current electrical characteristic data, tension detection data and vibration detection data with the data at the previous moment to obtain the difference between adjacent moments; In step S2, obtaining the difference between adjacent moments specifically includes: Obtain the correlation between the electrical characteristic data, tension detection data and vibration detection data at different times; When the correlation at the current moment changes significantly, it is determined that there is a serious risk of disconnection; The correlation between the electrical characteristic data, tension detection data and vibration detection data at different times is specifically obtained as follows: Obtaining electrical characteristic data time series, tension detection data time series and vibration detection data time series respectively; Based on the Pearson correlation coefficient formula, the correlation coefficients between the electrical characteristic data, the tension detection data and the vibration detection data at each moment are calculated; Determining whether the relevance at the current moment has changed significantly specifically includes: Apply Fisher Z transform to each correlation coefficient at the current moment and the previous moment; Calculate the correlation difference between the current moment and the previous moment based on the Fisher Z transform result; A significance test is performed on the correlation difference in combination with the preset correlation threshold. When the correlation difference is less than the correlation threshold, there is a significant change. S3, training a random forest model based on historical electrical characteristic data, tension detection data, and vibration detection data, inputting current electrical characteristic data, tension detection data, and vibration detection data, and outputting a predicted cable score at the next moment; The random forest model training process specifically includes: After preprocessing, the historical electrical characteristic data, tension detection data, and vibration detection data are divided into a training set and a test set; Set the parameters of the random forest and initialize the random forest model; Build multiple decision trees. For each decision tree, randomly extract a subset from the training set with replacement, randomly select a part of the features in the training set as splitting conditions, and evaluate the optimal split to split the node. Each decision tree outputs a prediction result, and the prediction results of each tree are combined to obtain the predicted cable score; The performance of the random forest model is evaluated using the test set based on the evaluation indicators, and the parameters of the random forest are adjusted according to the evaluation results to obtain the final random forest model; S4: When the difference between adjacent moments is greater than the difference threshold and the predicted cable score is greater than the score threshold, there is a risk of cable disconnection.

2. The overhead cable break monitoring method according to claim 1, characterized in that: In step S4, the scoring threshold includes a first scoring threshold and a second scoring threshold. Step S4 specifically includes: When the predicted cable score is less than the first score threshold and the difference between adjacent moments is not greater than the difference threshold, there is no risk of disconnection; When the predicted cable score is not less than the first score threshold and less than the second score threshold and the difference between adjacent moments is not greater than the difference threshold, there is a slight risk of disconnection; When the predicted cable score is greater than the first score threshold and the difference between adjacent moments is greater than the difference threshold, the cable is at risk of severe disconnection.

3. The method for monitoring the breakage of an overhead cable according to claim 1, characterized in that: The detection device includes a current transformer and a voltage transformer for detecting electrical characteristic data, a tension sensor for detecting tension detection data, and a vibration sensor for detecting vibration detection data.

4. An overhead cable break monitoring system, characterized in that: When the system is executed, the steps of the overhead cable disconnection monitoring method according to any one of claims 1 to 3 are implemented, and the system includes: The data acquisition module acquires the electrical characteristic data, tension detection data and vibration detection data of the overhead cable in real time based on the detection equipment; The difference acquisition module comprehensively processes the current electrical characteristic data, tension detection data and vibration detection data with the data at the previous moment to obtain the difference between adjacent moments; Model training module, which trains the random forest model based on historical electrical characteristic data, tension detection data and vibration detection data, inputs the current electrical characteristic data, tension detection data and vibration detection data, and outputs the predicted cable score at the next moment; Risk judgment module, when the difference between adjacent moments is greater than the difference threshold and the predicted cable score is greater than the score threshold, there is a risk of cable disconnection.

5. An overhead cable break monitoring terminal, characterized in that: include: A memory, used for storing an overhead cable break monitoring program; A processor is used to implement the steps of the overhead cable breakage monitoring method as described in any one of claims 1 to 3 when executing the overhead cable breakage monitoring program.

6. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores an overhead cable break monitoring program, and when the overhead cable break monitoring program is executed by the processor, the steps of the overhead cable break monitoring method according to any one of claims 1 to 3 are implemented.

Images