Underground cable monitoring data integration method and system based on swarm intelligence algorithm

Abstract

The invention discloses an underground cable monitoring data integration method and system based on a swarm intelligence algorithm, and relates to the technical field of data integration, and the method comprises the steps: carrying out the preprocessing of the monitoring data of a target underground cable, and obtaining the preprocessed data; searching an optimal data integration scheme for carrying out data integration on the preprocessed data based on a swarm intelligence algorithm; the optimal data integration scheme comprises a sensor data combination mode, a data fusion algorithm and parameters of the data fusion algorithm; and performing data integration on the preprocessed data based on the optimal data integration scheme to obtain a target data set for reflecting the operation state of the target underground cable. The technical problem that potential faults and potential safety hazards of the cable cannot be found in time due to the fact that potential values of the data cannot be fully mined in a traditional data integration method is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data integration, and in particular to an underground cable monitoring data integration method and system based on a swarm intelligence algorithm. Background Art

[0002] With the development of cities, underground cable networks are becoming increasingly large and complex, and effective monitoring and management are essential. Underground cable monitoring systems involve various types of sensors, such as temperature sensors, humidity sensors, current sensors, etc. The data collected by these sensors are diverse, real-time, and uncertain. Traditional data integration methods cannot fully tap the potential value of these data, resulting in the failure to timely discover potential cable failures and safety hazards. Summary of the invention

[0003] The purpose of the present invention is to provide an underground cable monitoring data integration method and system based on swarm intelligence algorithm in order to solve at least one of the above technical problems.

[0004] In the first aspect, an embodiment of the present invention provides an underground cable monitoring data integration method based on a swarm intelligence algorithm, comprising: preprocessing the monitoring data of the target underground cable to obtain preprocessed data; finding an optimal data integration scheme for integrating the preprocessed data based on the swarm intelligence algorithm; the optimal data integration scheme includes: a sensor data combination method, a data fusion algorithm and parameters of the data fusion algorithm; integrating the preprocessed data based on the optimal data integration scheme to obtain a target data set for reflecting the operating status of the target underground cable.

[0005] Furthermore, the monitoring data of the target underground cable is preprocessed to obtain preprocessed data, including: filtering outliers on the monitoring data based on a statistical analysis method to obtain filtered data; smoothing the filtered data based on a filtering algorithm to obtain denoised data; filling missing values ​​and normalizing the denoised data to obtain the preprocessed data.

[0006] Furthermore, the swarm intelligence algorithm includes an ant colony algorithm; based on the swarm intelligence algorithm, finding the optimal data integration plan for integrating the preprocessed data, including: initializing the ant colony size and the initial pheromone concentration of the ants, and determining the objective function; based on the pheromone concentration and the transition probability equation, iteratively searching the ant selection path; wherein each ant selection path corresponds to a data integration plan; based on the objective function, determining the optimal ant selection path, and determining the data integration plan corresponding to the optimal ant selection path as the optimal data integration plan.

[0007] Furthermore, the swarm intelligence algorithm includes a particle swarm algorithm; based on the swarm intelligence algorithm, an optimal data integration scheme for integrating the preprocessed data is found, including: initializing the particle swarm scale and the initial speed and position of the particles, and determining the objective function; wherein each particle corresponds to a data integration scheme; in the search space, the speed and position of each particle are adjusted based on the historical optimal position of the particle and the historical optimal position of the particle swarm, and a state transfer is performed; based on the fitness value of each particle and the objective function, the optimal position of the particle is iteratively searched, and the optimal data integration scheme is determined based on the optimal position of the particle.

[0008] Furthermore, after obtaining a target data set for reflecting the operating status of the target underground cable, the method further includes: inputting the target data set into a trained fault diagnosis model to perform fault diagnosis and status evaluation on the target underground cable.

[0009] In the second aspect, an embodiment of the present invention also provides an underground cable monitoring data integration system based on a swarm intelligence algorithm, comprising: a preprocessing module, an optimization module and an integration module; wherein the preprocessing module is used to preprocess the monitoring data of the target underground cable to obtain the preprocessed data; the optimization module is used to find the optimal data integration plan for integrating the preprocessed data based on the swarm intelligence algorithm; the optimal data integration plan includes: a sensor data combination method, a data fusion algorithm and parameters of the data fusion algorithm; the integration module is used to integrate the preprocessed data based on the optimal data integration plan to obtain a target data set for reflecting the operating status of the target underground cable.

[0010] Furthermore, the preprocessing module is also used to: filter outliers on the monitoring data based on a statistical analysis method to obtain filtered data; smooth the filtered data based on a filtering algorithm to obtain denoised data; fill missing values ​​and normalize the denoised data to obtain the preprocessed data.

[0011] Furthermore, it also includes a fault diagnosis module, which is used to input the target data set into a trained fault diagnosis model to perform fault diagnosis and status evaluation on the target underground cable.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the embodiment of the present invention when executing the computer program.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.

[0014] The present invention provides an underground cable monitoring data integration method and system based on a swarm intelligence algorithm. By optimizing the underground cable monitoring data integration scheme through the swarm intelligence algorithm, it can effectively integrate multi-source sensor data in the underground cable monitoring system, improve the quality and availability of the data, and alleviate the technical problem that the traditional data integration method cannot fully tap the potential value of these data, resulting in the failure to timely discover the potential faults and safety hazards of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flowchart of an underground cable monitoring data integration method based on a swarm intelligence algorithm provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of an underground cable monitoring data integration system based on a swarm intelligence algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] 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.

[0019] Embodiment 1

[0020] Figure 1 FIG. 1 is a flow chart of a method for integrating underground cable monitoring data based on a swarm intelligence algorithm according to an embodiment of the present invention. Figure 1 As shown, the method specifically comprises the following steps:

[0021] Step S102, preprocessing the monitoring data of the target underground cable to obtain preprocessed data.

[0022] Step S104, searching for an optimal data integration solution for preprocessed data based on a swarm intelligence algorithm; the optimal data integration solution includes: a sensor data combination method, a data fusion algorithm, and parameters of the data fusion algorithm.

[0023] Step S106, integrating the pre-processed data based on the optimal data integration solution to obtain a target data set for reflecting the operating status of the target underground cable.

[0024] Specifically, the preprocessing in step S102 includes data cleaning and data normalization. Specifically, it includes the following steps:

[0025] Step S1021, filtering outliers on the monitoring data based on a statistical analysis method to obtain filtered data;

[0026] Step S1022, smoothing the filtered data based on a filtering algorithm to obtain noise-reduced data;

[0027] Step S1023, performing missing value filling and normalization processing on the denoised data to obtain preprocessed data.

[0028] Specifically, underground cable monitoring data may have problems such as noise, outliers, and missing values. First, a statistical analysis-based method is used to detect outliers, such as calculating the mean and standard deviation of the data, and treating data that exceeds a certain range (such as μ±3σ, where μ is the mean and σ is the standard deviation) as outliers. For noisy data, filtering algorithms can be used for smoothing, such as median filtering, mean filtering, etc. For missing values, a suitable filling method is selected according to the characteristics of the data, such as using the average value of adjacent data or linear interpolation for filling.

[0029] The data collected by different sensors may have different dimensions and value ranges. In order to facilitate subsequent algorithm processing, the data needs to be normalized. The commonly used maximum-minimum normalization method is used to map the data to the [0,1] interval. The formula is:

[0030]

[0031] Where x is the original data, x min and x max are the minimum and maximum values ​​in the data sequence, respectively.

[0032] Optionally, the swarm intelligence algorithm in the embodiment of the present invention includes an ant colony algorithm and a particle swarm algorithm. Among them, the ant colony algorithm is a swarm intelligence algorithm that simulates the foraging behavior of ants. In the integration of underground cable monitoring data, ants can be regarded as "intelligent agents" for data processing. During the search process, each ant will choose a path based on the concentration of pheromones and the constraints of the problem. The path here can correspond to a strategy or rule for data integration. For example, ants can choose different sensor data combinations, data fusion algorithms, etc. When ants find a better data integration solution, they will leave pheromones on the corresponding path to attract other ants to choose the path. With the iteration of the algorithm, more and more ants will focus on the better solution, thereby achieving effective data integration.

[0033] The particle swarm optimization algorithm simulates the foraging behavior of bird flocks to find the optimal solution. In the cable monitoring data integration, each particle represents a possible data integration solution, including data screening, preprocessing methods, and fusion model parameters. In the search space, the particle adjusts its speed and position according to its own historical optimal position and the historical optimal position of the entire group, and flies in a better direction. Through continuous iteration, the particle swarm can gradually converge to a better data integration solution, so that the integrated data can more accurately reflect the operating status of the cable.

[0034] Implementation method 1: The swarm intelligence algorithm includes an ant colony algorithm; step S104 also includes the following steps:

[0035] Step S1041, initialize the ant colony size and the initial pheromone concentration of the ants, and determine the objective function; optionally, the objective function includes minimizing the error after data fusion or maximizing the correlation of data, etc.; wherein the objective function will be used to evaluate the pros and cons of each data integration scheme.

[0036] Step S1042, based on the pheromone concentration and the transition probability equation, iteratively search the ant selection path; wherein each ant selection path corresponds to a data integration solution.

[0037] Step S1043: determining an optimal ant selection path based on the objective function, and determining the data integration solution corresponding to the optimal ant selection path as the optimal data integration solution.

[0038] Specifically, the ant selects the next sensor data or operation to be accessed (such as data fusion method) based on the pheromone concentration and transition probability. The calculation formula is:

[0039]

[0040] Among them, τ ij(t) is the pheromone concentration from node i to node j at time t, η ij (t) is the heuristic information, which is usually related to the local characteristics of the problem. α and β are parameters that control the relative importance of pheromone and heuristic information. k is the set of nodes that ant k can currently select.

[0041] After the ant completes a path search, it calculates the fitness value of this data integration scheme based on the objective function. Update pheromone concentration:

[0042] τ ij (t+1)=(1―ρ)τ ij (t)+Δτ ij

[0043] Where ρ is the pheromone volatility coefficient, 0<ρ<1, Δτ ij is the increment of pheromone left by the ant on the path (i, j) in this iteration, Q is a constant, f k is the fitness value of ant k in this search.

[0044] Repeat the above steps until the termination condition of the algorithm is met, such as reaching the maximum number of iterations or the fitness value no longer improves significantly.

[0045] Implementation method 2: The swarm intelligence algorithm includes a particle swarm algorithm; step S104 also includes the following steps:

[0046] Step S1044, initializing the particle group size and the initial velocity and position of the particles, and determining the objective function; wherein each particle corresponds to a data integration scheme;

[0047] Step S1045, in the search space, adjusting the speed and position of each particle based on the historical optimal position of the particle and the historical optimal position of the particle group, and performing state transfer;

[0048] Step S1046, based on the fitness value of each particle and the objective function, iteratively search for the optimal position of the particle, and determine the optimal data integration solution based on the optimal position of the particle.

[0049] Specifically, the fitness value of each particle is calculated, and the pros and cons of the current data integration scheme are evaluated according to the objective function.

[0050] Update the particle's velocity and position. The velocity update formula is:

[0051]

[0052] in is the velocity of particle i in the dth dimension at the k+1th iteration, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers uniformly distributed in the interval [0,1], is the historical optimal position (individual extreme value) of particle i at the kth iteration, is the historical optimal position (global extreme value) of the entire particle swarm at the kth iteration, is the position of particle i in the dth dimension at the kth iteration. The position update formula is:

[0053]

[0054] Check whether the particle's position exceeds the boundary of the search space. If so, take appropriate action, such as limiting it within the boundary or adopting strategies such as reflection and absorption.

[0055] Repeat the above steps until the termination condition is met.

[0056] When the swarm intelligence algorithm terminates, the optimal data integration solution is output, including the selected sensor data combination, data fusion algorithm and its parameters, etc. According to the solution, the underground cable monitoring data is integrated to obtain a data set that comprehensively reflects the cable operation status, which can be used for subsequent fault diagnosis, status assessment and predictive analysis.

[0057] Specifically, after step S106, the method provided by the embodiment of the present invention further includes: inputting the target data set into the trained fault diagnosis model to perform fault diagnosis and status assessment on the target underground cable.

[0058] In order to illustrate the effect of the method provided by the embodiment of the present invention on the selection of data integration solutions, a comparative experiment is set up to verify and analyze the results as follows:

[0059] (1) Experimental setup:

[0060] 1. Collect actual data from the underground cable monitoring system, including cable temperature, humidity, current and other data at different time periods and locations, as well as corresponding cable operation status labels (normal or faulty).

[0061] 2. Divide the data set into a training set and a test set in a ratio of 7:3. The training set is used to train the swarm intelligence algorithm and find the optimal data integration solution; the test set is used to evaluate the performance of the data after the algorithm is integrated.

[0062] 3. Set up a comparative experiment, including traditional data integration methods (such as weighted average method, principal component analysis method) and the underground cable monitoring data integration method based on swarm intelligence algorithm provided by an embodiment of the present invention.

[0063] (2) Evaluation indicators:

[0064] 1. Root mean square error RMSE: used to measure the error between the integrated data and the true value:

[0065]

[0066] Among them, y i is the true value, is the predicted value of the integrated data, and n is the number of samples.

[0067] 2. Correlation coefficient R: used to evaluate the correlation between the integrated data and the true value:

[0068]

[0069] in, and are the average values ​​of the true value and the predicted value after integration.

[0070] 3. Fault detection accuracy: By inputting the integrated data into the fault diagnosis model, the proportion of samples with correctly detected faults to the total number of fault samples is calculated.

[0071] (3) Experimental results and analysis:

[0072] 1. Comparing the RMSE and R values ​​of different methods on the training set and test set, the results show that the data integration method based on swarm intelligence algorithm is superior to the traditional method in terms of error indicators and has higher accuracy and relevance.

[0073] 2. In terms of fault detection accuracy, the data integration method based on swarm intelligence algorithm can more accurately identify the fault status of the cable. Compared with the traditional method, the fault detection accuracy is higher, which means that by optimizing data integration, the characteristic information of cable faults can be better extracted and the reliability of fault diagnosis can be improved.

[0074] 3. Analyze the performance of swarm intelligence algorithms, such as the convergence speed and stability of the algorithms. Through multiple experiments, it is found that the ant colony algorithm and particle swarm optimization algorithm can converge to a better solution in a relatively small number of iterations under reasonable parameter settings, and have a certain degree of stability, and the fluctuation of different experimental results is small.

[0075] From the above description, it can be seen that the embodiment of the present invention provides an underground cable monitoring data integration method based on swarm intelligence algorithm. Through swarm intelligence algorithms such as ant colony algorithm and particle swarm optimization algorithm, it can effectively integrate multi-source sensor data in the underground cable monitoring system and improve the quality and availability of data. Experimental results show that this method is superior to traditional methods in terms of data integration accuracy, relevance, and fault detection capabilities. In the future, more complex swarm intelligence algorithms and optimization strategies can be further studied to adapt to more complex underground cable monitoring scenarios, improve the performance and intelligence level of data integration, and provide more powerful support for the safe operation and maintenance management of underground cables.

[0076] Embodiment 2

[0077] Figure 2 FIG. 1 is a schematic diagram of an underground cable monitoring data integration system based on a swarm intelligence algorithm according to an embodiment of the present invention. Figure 2 As shown, the system includes: a preprocessing module 10, an optimization module 20 and an integration module 30.

[0078] Specifically, the preprocessing module 10 is used to preprocess the monitoring data of the target underground cable to obtain the preprocessed data;

[0079] The optimization module 20 is used to find the optimal data integration scheme for integrating the pre-processed data based on the swarm intelligence algorithm; the optimal data integration scheme includes: sensor data combination mode, data fusion algorithm and parameters of the data fusion algorithm; preferably, the swarm intelligence algorithm includes an ant colony algorithm and a particle swarm algorithm;

[0080] The integration module 30 is used to integrate the pre-processed data based on the optimal data integration solution to obtain a target data set for reflecting the operating status of the target underground cable.

[0081] Specifically, the preprocessing module 10 is also used for:

[0082] Filter outliers in the monitoring data based on statistical analysis methods to obtain filtered data;

[0083] Smoothing the filtered data based on the filtering algorithm to obtain the noise-reduced data;

[0084] The data after noise reduction is filled with missing values ​​and normalized to obtain the preprocessed data.

[0085] Specifically, Figure 2 As shown, the system further includes a fault diagnosis module 40 for inputting the target data set into the trained fault diagnosis model to perform fault diagnosis and status evaluation on the target underground cable.

[0086] The present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the embodiment of the present invention when executing the computer program.

[0087] The present invention also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.

[0088] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0089] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for integrating underground cable monitoring data based on swarm intelligence algorithm, characterized in that: include: Preprocessing the monitoring data of the target underground cable to obtain preprocessed data; Finding an optimal data integration solution for integrating the pre-processed data based on a swarm intelligence algorithm; The optimal data integration solution includes: a sensor data combination method, a data fusion algorithm and parameters of the data fusion algorithm; The pre-processed data is integrated based on the optimal data integration solution to obtain a target data set for reflecting the operating status of the target underground cable.

2. The method according to claim 1, characterized in that: The monitoring data of the target underground cable is preprocessed to obtain the preprocessed data, including: Perform outlier filtering on the monitoring data based on a statistical analysis method to obtain filtered data; Smoothing the filtered data based on a filtering algorithm to obtain noise-reduced data; The data after noise reduction is subjected to missing value filling and normalization processing to obtain the data after preprocessing.

3. The method according to claim 1, characterized in that: The swarm intelligence algorithm includes an ant colony algorithm; Finding an optimal data integration solution for integrating the pre-processed data based on a swarm intelligence algorithm includes: Initialize the size of the ant colony and the initial concentration of ant pheromones, and determine the objective function; Based on the pheromone concentration and transition probability equation, the ant selection path is iteratively searched; each ant selection path corresponds to a data integration scheme; Based on the objective function, an optimal ant selection path is determined, and a data integration solution corresponding to the optimal ant selection path is determined as the optimal data integration solution.

4. The method according to claim 1, characterized in that: The swarm intelligence algorithm includes a particle swarm algorithm; Finding an optimal data integration solution for integrating the pre-processed data based on a swarm intelligence algorithm includes: Initialize the particle swarm size and the initial velocity and position of the particles, and determine the objective function; each particle corresponds to a data integration scheme; In the search space, the speed and position of each particle are adjusted based on the historical optimal position of the particle and the historical optimal position of the particle group, and the state is transferred; Based on the fitness value of each particle and the objective function, the optimal position of the particle is iteratively searched, and the optimal data integration solution is determined based on the optimal position of the particle.

5. The method according to claim 1, characterized in that: After obtaining a target data set for reflecting the operating status of the target underground cable, the method further includes: inputting the target data set into a trained fault diagnosis model to perform fault diagnosis and status evaluation on the target underground cable.

6. An underground cable monitoring data integration system based on swarm intelligence algorithm, characterized in that: include: Preprocessing module, optimization module and integration module; among them, The preprocessing module is used to preprocess the monitoring data of the target underground cable to obtain the preprocessed data; The optimization module is used to find the optimal data integration solution for integrating the pre-processed data based on a swarm intelligence algorithm; the optimal data integration solution includes: a sensor data combination method, a data fusion algorithm and parameters of the data fusion algorithm; The integration module is used to integrate the pre-processed data based on the optimal data integration solution to obtain a target data set for reflecting the operating status of the target underground cable.

7. The system according to claim 6, characterized in that: The preprocessing module is further used for: Perform outlier filtering on the monitoring data based on a statistical analysis method to obtain filtered data; Smoothing the filtered data based on a filtering algorithm to obtain noise-reduced data; The data after noise reduction is subjected to missing value filling and normalization processing to obtain the data after preprocessing.

8. The system according to claim 6, characterized in that: It also includes a fault diagnosis module, which is used to input the target data set into a trained fault diagnosis model to perform fault diagnosis and status evaluation on the target underground cable.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images