Method and device for state monitoring and fault alarm of buried cable current collection circuit

Abstract

The invention provides a buried cable current collection line state monitoring and fault alarm method and device, which is suitable for the technical field of power systems, and comprises the following steps: obtaining a line information set, a target fault set and a monitoring equipment information set of a buried cable current collection line; based on the line information set, constructing a buried cable current collection line simulation model of the target area, and based on the target fault set and the simulation model, performing simulation to obtain the fault information set, and training the deep learning model to obtain an initial fault recognition model; correcting the initial fault identification model based on the monitoring equipment information set to obtain a fault identification model of the buried cable current collection line; and performing state monitoring on the buried cable current collection line of the target area to obtain real-time operation data, obtaining fault information according to the fault identification model, and performing fault alarm based on the fault information. According to the invention, the fault identification model is corrected through the parameters of the current collection line and the monitoring equipment, and the accuracy of fault identification is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power systems, and in particular relates to a method and a device for monitoring the state of an underground cable collector line and providing a fault alarm. Background Art

[0002] As an important power transmission facility, underground cables play a key role in power transmission. They can safely and stably transmit power from the power generation end to various power consumption areas, effectively avoiding the risk of overhead lines being affected by bad weather (such as strong winds, lightning, ice and snow, etc.) and causing failures, reducing the damage to the surrounding environment caused by exposed lines and potential safety hazards to personnel activities, while also improving the utilization efficiency of land resources. They play an indispensable role in ensuring power supply in cities and various places.

[0003] At present, there are many methods used for the status monitoring of underground cable collector lines. For example, the installation of temperature sensors can monitor the temperature changes of cables in real time to determine whether there are abnormal conditions such as overload; the use of partial discharge monitoring devices to detect insulation defect discharge phenomena that may occur inside the cable; and the use of current transformers to monitor the current size and fluctuations to assist in analyzing the operation status of the line. As for fault alarm, once the monitoring system detects that the relevant parameters are out of the normal range, it will send alarm information to the monitoring terminal in a timely manner through network communication, so that relevant personnel can quickly know and take countermeasures. Some systems can also associate sound and light alarms to enhance the alarm prompt effect.

[0004] However, the sensors are affected by the complex underground environment (such as humidity, changes in pH, etc.), and the data accuracy is easily compromised. Measurement deviations may occur due to moisture. In addition, since the buried cables are located underground, once a fault occurs, it is extremely difficult to locate. It takes a lot of time and effort to find the specific fault location, and the maintenance and update of the entire system are relatively complicated, which is not conducive to long-term and efficient guarantee of normal operation of the cable line. Summary of the invention

[0005] The embodiment of the present invention provides a method and device for monitoring the state of an underground cable collector line and for alarming a fault, so as to solve the problem in existing monitoring methods that sensors are affected by the complex underground environment and data may have measurement deviations due to moisture.

[0006] The present invention is achieved through the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for monitoring the state of an underground cable collector line and providing a fault alarm, comprising:

[0008] Obtaining a line information set, a target fault set, and a monitoring equipment information set of the underground cable collection line in the target area;

[0009] Based on the line information set, a simulation model of the buried cable collection line in the target area is constructed, and simulation is performed based on the target fault set and the simulation model to obtain a fault information set;

[0010] Based on the fault information set, a pre-set deep learning model is trained to obtain an initial fault identification model for the underground cable collector line in the target area;

[0011] The initial fault identification model is modified based on the monitoring equipment information set to obtain a fault identification model of the underground cable collector line in the target area;

[0012] The state of the underground cable collector line in the target area is monitored to obtain real-time operation data of the underground cable collector line, fault information is obtained based on the real-time operation data and the fault identification model, and a fault alarm is issued based on the fault information.

[0013] In a second aspect, an embodiment of the present invention provides a device for monitoring the state of an underground cable collector line and for alarming a fault, comprising:

[0014] An acquisition module, used to acquire a line information set, a target fault set, and a monitoring equipment information set of an underground cable collector line in a target area;

[0015] A simulation module, used to construct a simulation model of the buried cable collection line in the target area based on the line information set, and to perform simulation based on the target fault set and the simulation model to obtain a fault information set;

[0016] A training module, used to train a pre-set deep learning model based on the fault information set to obtain an initial fault identification model for the underground cable collector line in the target area;

[0017] A correction module, used to correct the initial fault identification model based on the monitoring equipment information set to obtain a fault identification model of the underground cable collector line in the target area;

[0018] The alarm module is used to monitor the status of the underground cable collection line in the target area, obtain the real-time operation data of the underground cable collection line, obtain fault information based on the real-time operation data and the fault identification model, and issue a fault alarm based on the fault information.

[0019] The embodiment of the present invention provides a method and device for monitoring the state of an underground cable collector line and alarming for a fault. A simulation model is constructed through the line information of the underground cable collector line, and a target fault is simulated through the simulation model to obtain a fault information set. A pre-set deep learning model is trained through the fault information set to obtain an initial fault identification model of the underground cable collector line in the target area, and the initial fault identification model is corrected through equipment information to obtain a fault identification model. Real-time operation data is obtained by monitoring the state of the underground cable collector line, and fault information is obtained based on the actual operation data and the fault identification model, and finally an alarm is issued based on the fault information. The fault identification model is corrected through equipment parameters, the data deviation caused by the influence of the equipment is reduced, and the accuracy of fault identification is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or related technical descriptions are 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 labor.

[0021] Figure 1 It is a flow chart of a method for monitoring the state of an underground cable collector line and providing a fault alarm according to an embodiment of the present invention;

[0022] Figure 2 It is a schematic diagram of segmented processing of an underground cable collector line of an underground cable collector line state monitoring and fault alarm method provided by an embodiment of the present invention;

[0023] Figure 3 It is another schematic diagram of segmented processing of an underground cable collector line in a method for monitoring the state of an underground cable collector line and providing a fault alarm according to an embodiment of the present invention;

[0024] Figure 4 It is a structural schematic diagram of an underground cable collector line state monitoring and fault alarm device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0026] Figure 1FIG. 1 is a flow chart of a method for monitoring the state of an underground cable collector line and providing a fault alarm according to an embodiment of the present invention. Figure 1 , the method is described in detail as follows:

[0027] S110, obtaining a line information set, a target fault set, and a monitoring equipment information set of the underground cable collection line in the target area.

[0028] In some embodiments, the line information set includes various types of information related to the physical structure and layout of the underground cable collection line. It contains cable layout information, such as the cable path, laying depth, cable length, etc., which determine the actual laying of the cable underground. At the same time, the line information set also includes node information, such as the location of the cable's connection nodes, node types (such as branch nodes, transfer nodes, etc.). For example, in an urban power grid, a buried cable may be laid along a specific street, and its path needs to be accurately recorded. The laying depth may vary due to the geological conditions and safety requirements of different sections of the road, and the cable length directly affects the distance and loss of power transmission.

[0029] It should be noted that before determining the target fault set, the underground cable collector line needs to be segmented. Figure 2 , the underground cable collector line can be divided into fixed lengths, such as every 100 meters as a section; refer to Figure 3 , the buried cable collection line can be divided according to the line information in the line information set. For example, the cable between two connecting nodes is divided into two or three sections according to length, the cable between node a and node b is divided into two sections according to length, and the cable between node c and node d is divided into three sections according to length.

[0030] In some embodiments, the target fault set includes various fault types and related parameters that may occur in each section of the underground cable collector line. The fault types include short circuit faults (such as phase-to-phase short circuit, phase-to-ground short circuit), ground faults (single-phase grounding, multi-point grounding, etc.), line break faults (single-phase line break, multi-phase line break), insulation aging faults, and cable moisture faults.

[0031] In some embodiments, the equipment information set mainly involves relevant information of various types of equipment used to monitor and ensure the operation of underground cable collector lines. It includes basic attributes of the equipment, such as equipment model, equipment manufacturer, equipment production date, etc. At the same time, the equipment information set covers the operating parameters of the equipment, such as the measurement range and accuracy of the temperature sensor, the detection sensitivity and frequency range of the partial discharge monitoring device, the transformation ratio and rated current of the current transformer, etc. In addition, it also includes the maintenance records of the equipment, such as the last maintenance time, maintenance content, whether the equipment has potential fault hazards, etc.

[0032] S120, constructing a buried cable collection line simulation model in the target area based on the line information set, and performing simulation based on the target fault set and the simulation model to obtain a fault information set.

[0033] In some embodiments, the fault information set covers various types of fault-related information obtained through simulation of the target fault set and the buried cable collection line simulation model, including electrical parameter changes (such as abnormal values ​​of current, voltage, partial discharge, etc.) presented when different fault types (such as short circuit, grounding, line break, insulation damage, etc.) occur at specific locations, the time node of the fault, the impact of the fault on the overall operating status of the line (such as high-frequency partial discharge peak, changes in the number of high-frequency partial discharge pulses, etc.), and chain reactions that may be caused by the fault.

[0034] In a possible implementation, the specific processing process of step S120 is: based on the target fault set, multiple target faults in the underground cable collection line are obtained; based on the simulation model, each target fault is simulated separately to obtain the fault information of the corresponding target fault; based on the fault information of all target faults, a fault information set is obtained.

[0035] In some embodiments, the number of target faults is related to the number of fault types in the target fault set and the segmentation results. For example, the underground cable collection line in area a is divided into 55 sections, and the number of fault types includes eight types: phase-to-phase short circuit, phase-to-ground short circuit, single-phase grounding, multi-point grounding, single-phase line break, multi-phase line break, insulation aging fault, and cable moisture fault. Then the number of target faults in area a is 440.

[0036] In some embodiments, the fault information of a target fault includes: changes in relevant electrical parameters (partial discharge, current, voltage anomaly, etc.) when different faults occur at different times in a section of underground cable collector line corresponding to the target fault, possible impacts on the line and surrounding equipment, and specific parameters collected by each device related to the section of underground cable collector line. Among them, different faults include different fault types (short circuit, grounding, broken wire, etc.), different fault locations (precise or approximate locations), different fault degrees (minor, severe, etc.), different fault occurrence times, etc. Different times can be different time periods, or they can be times corresponding to different seasons and different weather conditions. The simulation of different times is mainly to obtain a set of fault information when the underground cable collector line fails in different environments.

[0037] In some embodiments, the fault information set includes fault information of all target faults in the underground cable collector lines in the target area.

[0038] Through the target fault set, multiple target faults are obtained, and before obtaining the target fault, the underground cable collector line is processed in sections. After obtaining the target fault, each target fault is simulated separately to obtain the corresponding fault information, and the fault information set is obtained comprehensively, which can accurately simulate the fault scenario, comprehensively consider the actual layout of the line and the node conditions, and truly restore various fault characteristics. It can also cover a variety of fault types and parameters, efficiently obtain fault information, and generate a large number of detailed conditions under different faults in a short time, which greatly improves the efficiency compared with the actual line detection and analysis, and provides strong support for the fault research, prevention and treatment of the underground cable collector line.

[0039] S130, training a pre-set deep learning model based on the fault information set to obtain an initial fault identification model for the underground cable collection line in the target area.

[0040] In some embodiments, the initial fault identification model is obtained by using a fault information set containing detailed electrical parameter changes, fault locations and other information under various fault conditions as training data, and inputting it into a pre-set deep learning model for learning and optimization. It can preliminarily analyze and process the operating data of the buried cable collection line in the target area to determine whether there is a fault, as well as a model of the fault parameters when a fault exists.

[0041] In one possible implementation, the specific processing process of step S130 is: determining multiple fault information at different times based on the fault information set, and training a pre-set deep learning model based on all the fault information to obtain an initial fault identification model for the buried cable collection line in the target area.

[0042] Among them, the pre-set deep learning model is a computational model with a complex structure and powerful learning ability built based on the deep learning algorithm. It has multiple hidden layers and can automatically learn feature representations from a large amount of data. For the status monitoring of underground cable collection lines, the input fault information set (covering electrical parameters, locations and other information under various fault scenarios) can be deeply analyzed, and the internal parameters can be continuously adjusted to discover patterns and laws in the data, thereby providing a basis for accurately identifying the fault type and location of the underground cable collection line. The basic architecture (such as the number of layers and nodes of the neural network) and initial parameter settings of the model have been determined before training, so that the fault information set can be used for subsequent targeted training to obtain an initial fault identification model suitable for the target area.

[0043] In some embodiments, the pre-set deep learning model may include convolutional neural network (CNN), recurrent neural network (RNN) and its variants (such as long short-term memory network LSTM, gated recurrent unit GRU) and deep belief network (DBN), etc. CNN has the characteristics of local perception and weight sharing, can extract high-level features of input data, and is suitable for monitoring cable insulation status, etc.; RNN and its variants are good at processing sequence data, LSTM and GRU solve long sequence problems through gating mechanism, and can predict cable fault trends; DBN is composed of multiple restricted Boltzmann machines stacked together, can learn data probability distribution, and can accurately classify cable fault types after unsupervised pre-training and supervised fine-tuning.

[0044] In some embodiments, a pre-set deep learning model can be determined according to the requirements of monitoring and fault alarm. For example, if the cable fault type needs to be accurately identified, a deep belief network (DBN) model can be selected as the pre-set deep learning model.

[0045] In some embodiments, the initial fault identification model is obtained by training a pre-set deep learning model based on a fault information set of the underground cable collector line.

[0046] Training the pre-set deep learning model according to the fault information set can make full use of the rich fault information set, allowing the deep learning model to deeply explore the complex fault modes and characteristics. The initial fault identification model obtained through training has strong self-learning and adaptive capabilities, and can accurately capture the subtle signs of various faults in the underground cable collection lines in the target area, effectively improving the accuracy, reliability and generalization ability of fault identification, and laying a solid foundation for the subsequent stable operation of the cable lines.

[0047] S140, modifying the initial fault identification model based on the monitoring equipment information set to obtain a fault identification model for the underground cable collection line in the target area.

[0048] In some embodiments, the fault identification model is a precise model obtained by modifying and optimizing the initial model based on the initial fault identification model by comprehensively considering the operating parameters of each device in the device information set. It can accurately analyze the real-time operating data of the underground cable collector line, accurately identify various fault types (such as short circuit, grounding, broken wire, etc.), fault location and fault degree, thereby providing a reliable basis for timely and effective fault alarms and targeted maintenance measures, greatly improving the accuracy and reliability of underground cable collector line fault diagnosis, and effectively ensuring the safe and stable operation of the power system.

[0049] In a possible implementation, the specific processing method of step S140 is: determine the operating parameters of each monitoring device based on the monitoring device information set, and determine the influence factor of each monitoring device based on the operating parameters of each monitoring device; based on the influence factors of all monitoring devices in the monitoring device information set, obtain the early warning deviation matrix of the underground cable collection line in the target area; based on the early warning deviation matrix, correct the initial fault identification model to obtain the fault identification model of the underground cable collection line in the target area.

[0050] In some embodiments, the fault identification model can identify multiple fault parameters when a fault occurs. The number of fault parameters is related to the segmentation result of the underground cable collector line. If the underground cable collector line is divided into x segments, a total of x fault parameters can be obtained.

[0051] In some embodiments, the influence factor of the monitoring device is a quantitative indicator that reflects the influence of the monitoring device on the fault identification result in the process of monitoring the state of the buried cable collector line. It is closely related to the operating parameters of the monitoring device, including the stability, sensitivity, response time of the monitoring device, and the relationship between the measurement deviation of the monitoring device and the environment. The combined effect of these factors determines the relative importance and influence of the monitoring device on fault judgment in the entire monitoring system, which in turn affects the accuracy and reliability of the fault identification model.

[0052] In some embodiments, the impact factor is calculated as:

[0053]

[0054] Among them, θ k is the influencing factor of the kth monitoring device, ω1 is the stability weight of the kth monitoring device, ω2 is the sensitivity weight of the kth monitoring device, ω3 is the response time weight of the kth monitoring device, ω4 is the measurement deviation weight of the kth monitoring device, Δk1 is the stability error of the kth monitoring device, Δk2 is the sensitivity error of the kth monitoring device, Δk3 is the response time error of the kth monitoring device, and Δk4 is the measurement deviation of the monitoring device caused by the environmental influence on the kth monitoring device. And ω1+ω2+ω3+ω4=1, Δk p is the difference between the operating parameters of the kth monitoring device and the standard operating parameters, which can be positive or negative.

[0055] In some embodiments, the early warning deviation matrix includes data of each monitoring device and its influencing factor, the row factors of the early warning deviation matrix are the monitoring device number and the influencing factor, and the column factors are each monitoring device number and its corresponding influencing factor.

[0056] When determining the influencing factors of each monitoring device, the impact of the environment on the monitoring equipment is taken into account. Therefore, it is possible to compensate for environmental interference deviations and optimize feature extraction accuracy, thereby improving the accuracy of fault identification. At the same time, it can enable the model to dynamically adapt to environmental changes, enhance anti-interference capabilities, improve its adaptability and robustness, stabilize fault diagnosis results, reduce the risks of false alarms and missed alarms, enhance the reliability and stability of fault diagnosis, and provide strong support for underground cable fault identification and operation and maintenance.

[0057] In a possible implementation, the specific processing method of step S140 is: based on the early warning deviation matrix, the fault information set is updated, and the fault information deviation set is obtained based on the fault information set and the updated fault information set; based on the fault information deviation set, the initial fault identification model is corrected to obtain the fault identification model of the buried cable collection line in the target area.

[0058] In some embodiments, updating the fault information set according to the early warning deviation matrix refers to determining the precise deviation compensation value based on the deviation of each device in the matrix. For example, for devices such as temperature sensors with measurement deviations, the data collected by them are compensated by the corresponding numerical increase or decrease; then, considering the relationship between the devices, the affected fault characteristic data are adjusted, such as correcting the fault current characteristic value due to current transformer deviation; finally, the equipment deviation compensation and fault characteristic adjustment are combined to comprehensively update the fault information set so that it can more accurately reflect the actual operating status of the buried cable.

[0059] Among them, the fault information deviation set is obtained by comparing the fault information set with the updated fault information set. The fault information deviation set includes the fault information deviation corresponding to the fault type of each fault link, which can reflect the fault information deviation caused by the influence of equipment.

[0060] In a possible implementation, the specific processing method of step S140 is: determining the repair parameters of each fault type-link based on the fault information deviation set, and correcting the initial fault identification model based on the repair parameters to obtain the fault identification model of the underground cable collector line in the target area;

[0061] The repair parameters of the fault type-link are:

[0062]

[0063] Among them, X (i,j) is the repair parameter of the (i,j)th fault type-link, is the equipment accuracy of the kth monitoring device in the (i, j)th fault type-link, K is the total number of monitoring devices in the (i, j)th fault type-link, Δm (i,j)is the fault deviation value of the (i,j)th fault type-link, Δm j is the fault deviation value of the jth fault link of the i-th fault type, α j is the weight parameter of the jth fault link of the i-th fault type, and J is the total number of fault links related to the i-th fault type.

[0064] In some embodiments, a link refers to the segmentation of the underground cable collector line in the target area, and the number of links is consistent with the number of segments of the underground cable collector line in the target area.

[0065] In some embodiments, after obtaining the corrected model parameters, the adjustment direction and amplitude of the model weights are first determined based on the repair parameters, the impact of the monitoring equipment in each fault type-link and the importance of the fault characteristics are comprehensively considered, the weights between neurons in different layers are redistributed, and the weight distribution is optimized to improve accuracy and robustness; secondly, the neuron bias correction amount is calculated based on the fault deviation value in the repair parameters, and then applied to the bias parameters of the initial model to update the bias, so that the model can still accurately identify the fault type and location when the data is biased.

[0066] The influencing factors and early warning deviation matrix are determined through the equipment information set, and the fault information deviation set is further obtained. The repair coefficient of each fault type-link is calculated, and the initial fault identification model is corrected to obtain the fault identification model of the underground cable collector line in the target area. It can effectively improve the accuracy of fault identification, and adjust the model parameters by compensating for equipment errors and constructing early warning deviation matrices based on equipment operating parameters and influencing factors, so as to accurately judge faults and avoid misjudgment; at the same time, it can optimize the adaptability of the model and dynamically respond to changes in equipment performance. It can accurately identify complex faults. With the update of the equipment information set, the model can also be continuously optimized to provide stable and reliable diagnostic results for cable operation and maintenance, and effectively ensure the safe and stable operation of the power system.

[0067] S150, monitor the status of the underground cable collection line in the target area, obtain real-time operation data of the underground cable collection line, obtain fault information based on the real-time operation data and the fault identification model, and issue a fault alarm based on the fault information.

[0068] In some embodiments, real-time operation data includes electrical parameter data, such as partial discharge monitoring data (such as single discharge amount and statistical distribution of discharge amount, discharge phase related data, such as starting phase, extinction phase and phase distribution characteristics, discharge frequency related data, discharge pulse waveform related data), current size, rate of change, voltage and its fluctuation, active and reactive power, etc., as well as parameters monitored by temperature sensors, insulation performance monitoring sensors (such as partial discharge sensors, insulation resistance sensors), temperature and humidity sensors, gas sensors, etc.

[0069] In a possible implementation, the specific processing method of step S150 is: input the real-time operation data into the fault identification model to obtain the fault parameter, and compare the fault parameter with the preset parameter threshold; if the fault parameter exceeds the preset parameter threshold, the fault parameter is input into a pre-set fault parameter-fault information mapping table to obtain the fault information corresponding to the fault parameter, and a fault alarm is performed based on the fault information; if the fault parameter does not exceed the preset parameter threshold, no fault alarm is performed.

[0070] In some embodiments, real-time operation data are input into a fault identification model, and multiple fault parameters can be obtained through the real-time operation data, and further, fault information can be obtained through the fault parameters.

[0071] In some embodiments, the preset parameter threshold can be determined by the electrical parameters of the underground cable collector line in the target area under normal operation and the fluctuation range of the monitoring results of each sensor. The specific determination method is not limited here.

[0072] In some embodiments, the fault parameter-fault information mapping table includes fault information corresponding to each parameter range. Fault information can be obtained through the fault parameter-fault information mapping table, and the fault information includes the fault type corresponding to the fault parameter at each position.

[0073] In a possible implementation, the specific processing method of step S150 is: determine the fault location based on the fault information, and obtain real-time monitoring data of multiple monitoring devices corresponding to the fault location; determine the real-time fault status of the fault location based on the real-time monitoring data, and issue a fault alarm based on the real-time fault status.

[0074] In some embodiments, the fault location refers to one or more faulty sections of the underground cable collector line in the target area, and the fault type corresponding to each fault location can be determined through the fault information. The fault location can be one or more.

[0075] In some embodiments, the number of fault locations is related to the number of fault parameters exceeding a preset parameter threshold. For example, if a total of three fault parameters exceed the preset parameter threshold, three fault parameters may be obtained.

[0076] Through the line information of the underground cable collector line, a simulation model is constructed, and the target fault is simulated through the simulation model to obtain a fault information set. The pre-set deep learning model is trained through the fault information set to obtain the initial fault identification model of the underground cable collector line in the target area, and the initial fault identification model is corrected through the monitoring equipment information to obtain a fault identification model. Through the status monitoring of the underground cable collector line, real-time operation data is obtained, and fault information is obtained based on the actual operation data and the fault identification model, and finally an alarm is issued based on the fault information. When obtaining the correction parameters, the deviation caused by the environmental influence of the monitoring equipment is taken into account, and the fault identification model is corrected through the monitoring equipment parameters, which reduces the data deviation caused by the influence of the monitoring equipment during the fault identification process and improves the accuracy of fault identification of the underground cable collector line.

[0077] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0078] A method for monitoring the state of an underground cable collector line and providing a fault alarm corresponding to the above embodiment, Figure 4 A schematic structural diagram of an underground cable collector line state monitoring and fault alarm device provided by an embodiment of the present invention is shown. For ease of description, only the parts related to the embodiment of the present invention are shown.

[0079] See also Figure 4 , a buried cable collector line state monitoring and fault alarm device 4 in an embodiment of the present invention may include:

[0080] An acquisition module 41 is used to acquire a line information set, a target fault set and a monitoring equipment information set of an underground cable collector line in a target area;

[0081] A simulation module 42 is used to construct a simulation model of the buried cable collection line in the target area based on the line information set, and to perform simulation based on the target fault set and the simulation model to obtain a fault information set;

[0082] A training module 43 is used to train a pre-set deep learning model based on a fault information set to obtain an initial fault identification model for the underground cable collector line in the target area;

[0083] A correction module 44 is used to correct the initial fault identification model based on the monitoring equipment information set to obtain a fault identification model of the underground cable collector line in the target area;

[0084] The alarm module 45 is used to monitor the status of the underground cable collector line in the target area, obtain the real-time operation data of the underground cable collector line, obtain fault information based on the real-time operation data and the fault identification model, and issue a fault alarm based on the fault information.

[0085] In a possible implementation, the simulation module 42 is specifically used to obtain multiple target faults in the underground cable collection line based on the target fault set; simulate each target fault separately based on the simulation model to obtain the fault information of the corresponding target fault; and obtain a fault information set based on the fault information of all target faults.

[0086] In one possible implementation, the training module 43 is specifically used to determine fault information at multiple different times based on the fault information set, and train a pre-set deep learning model based on all the fault information to obtain an initial fault identification model for the buried cable collection line in the target area.

[0087] In one possible implementation, the correction module 44 is specifically used to determine the operating parameters of each monitoring device based on the monitoring device information set, and determine the influence factor of each monitoring device based on the operating parameters of each monitoring device; obtain the early warning deviation matrix of the underground cable collection line in the target area based on the influence factors of all monitoring devices in the monitoring device information set; correct the initial fault identification model based on the early warning deviation matrix to obtain the fault identification model of the underground cable collection line in the target area.

[0088] In one possible implementation, the correction module 44 is also used to update the fault information set based on the early warning deviation matrix, and obtain a fault information deviation set based on the fault information set and the updated fault information set; based on the fault information deviation set, the initial fault identification model is corrected to obtain a fault identification model of the buried cable collection line in the target area.

[0089] In a possible implementation, the correction module 44 is further used to determine the repair parameters of each fault type-link based on the fault information deviation set, and to correct the initial fault identification model based on the repair parameters to obtain a fault identification model of the underground cable collector line in the target area;

[0090] The repair parameters of the fault type-link are:

[0091]

[0092] Among them, X (i,j) is the repair parameter of the (i,j)th fault type-link, is the equipment accuracy of the kth monitoring device in the (i, j)th fault type-link, K is the total number of monitoring devices in the (i, j)th fault type-link, Δm (i,j) is the fault deviation value of the (i,j)th fault type-link, Δm j is the fault deviation value of the jth fault link of the i-th fault type, α j is the weight parameter of the jth fault link of the i-th fault type, and J is the total number of fault links related to the i-th fault type.

[0093] In one possible implementation, the alarm module 45 is specifically used to input real-time operating data into a fault identification model to obtain fault parameters, and compare the fault parameters with a preset parameter threshold; if the fault parameters exceed the preset parameter threshold, the fault parameters are input into a pre-set fault parameter-fault information mapping table to obtain fault information corresponding to the fault parameters, and a fault alarm is issued based on the fault information; if the fault parameters do not exceed the preset parameter threshold, no fault alarm is issued.

[0094] In a possible implementation, the alarm module 45 is also used to determine the fault location based on the fault information, obtain real-time monitoring data of multiple monitoring devices corresponding to the fault location; determine the real-time fault status of the fault location based on the real-time monitoring data, and perform a fault alarm based on the real-time fault status.

[0095] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] Those of ordinary skill in the art will appreciate that the templates, units, and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of each of the above-mentioned embodiments of the method for monitoring the state of the buried cable collector line and the fault alarm. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc.

[0098] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for monitoring the state of an underground cable collector line and for alarming a fault, characterized in that: include: Obtaining a line information set, a target fault set, and a monitoring equipment information set of the underground cable collection line in the target area; Based on the line information set, a simulation model of the buried cable collection line in the target area is constructed, and simulation is performed based on the target fault set and the simulation model to obtain a fault information set; Based on the fault information set, a pre-set deep learning model is trained to obtain an initial fault identification model for the underground cable collector line in the target area; The initial fault identification model is modified based on the monitoring equipment information set to obtain a fault identification model of the underground cable collector line in the target area; The state of the underground cable collector line in the target area is monitored to obtain real-time operation data of the underground cable collector line, fault information is obtained based on the real-time operation data and the fault identification model, and a fault alarm is issued based on the fault information.

2. The method for monitoring the state of the underground cable collector line and for alarming faults according to claim 1, characterized in that: The method of correcting the initial fault identification model based on the monitoring equipment information set to obtain the fault identification model of the underground cable collector line in the target area includes: Determine the operating parameters of each monitoring device based on the monitoring device information set, and determine the influencing factor of each monitoring device based on the operating parameters of each monitoring device; Based on the influencing factors of all monitoring devices in the monitoring device information set, an early warning deviation matrix of the buried cable collector line in the target area is obtained; The initial fault identification model is modified based on the early warning deviation matrix to obtain a fault identification model of the underground cable collector line in the target area.

3. The method for monitoring the state of the underground cable collector line and for alarming faults according to claim 2, characterized in that: The initial fault identification model is corrected based on the early warning deviation matrix to obtain the fault identification model of the underground cable collector line in the target area, including: Based on the early warning deviation matrix, the fault information set is updated, and a fault information deviation set is obtained based on the fault information set and the updated fault information set; The initial fault identification model is modified based on the fault information deviation set to obtain a fault identification model for the underground cable collector line in the target area.

4. The method for monitoring the state of an underground cable collector line and providing a fault alarm as claimed in claim 3, characterized in that: The method of correcting the initial fault identification model based on the fault information deviation set to obtain the fault identification model of the underground cable collector line in the target area includes: Determine the repair parameters of each fault type-link based on the fault information deviation set, and modify the initial fault identification model based on the repair parameters to obtain a fault identification model of the underground cable collector line in the target area; The repair parameters of the fault type-link are: Among them, X (i,j) is the repair parameter of the (i,j)th fault type-link, is the equipment accuracy of the kth monitoring device in the (i, j)th fault type-link, K is the total number of monitoring devices in the (i, j)th fault type-link, Δm (i,j) is the fault deviation value of the (i,j)th fault type-link, Δm j is the fault deviation value of the jth fault link of the i-th fault type, α j is the weight parameter of the jth fault link of the i-th fault type, and J is the total number of fault links related to the i-th fault type.

5. The method for monitoring the state of the underground cable collector line and for alarming faults according to claim 1, characterized in that: The step of constructing a buried cable power collection line simulation model of the target area based on the line information set includes: Determining the layout information and node information of the buried cable based on the line information set; Constructing an initial simulation model of the underground cable collector line in the target area based on the layout information; The initial simulation model is adjusted based on the node information to obtain a simulation model of the buried cable collector line.

6. The method for monitoring the state of the underground cable collector line and for alarming for faults according to claim 1, characterized in that: The simulating based on the target fault set and the simulation model to obtain a fault information set includes: Based on the target fault set, a plurality of target faults in the underground cable collector line are obtained; Simulating each target fault based on the simulation model to obtain fault information of the corresponding target fault; Based on the fault information of all target faults, a fault information set is obtained.

7. The method for monitoring the state of an underground cable collector line and providing a fault alarm according to claim 1, characterized in that: The acquiring fault information based on the real-time operation data and the fault identification model, and performing a fault alarm based on the fault information, includes: Inputting the real-time operation data into the fault identification model to obtain fault parameters, and comparing the fault parameters with preset parameter thresholds; If the fault parameter exceeds the preset parameter threshold, the fault parameter is input into a preset fault parameter-fault information mapping table to obtain the fault information corresponding to the fault parameter, and a fault alarm is issued based on the fault information; If the fault parameter does not exceed the preset parameter threshold, no fault alarm is issued.

8. The method for monitoring the state of the underground cable collector line and for alarming for faults according to claim 7, characterized in that: Performing a fault alarm based on the fault information includes: Determine the fault location based on the fault information, and obtain real-time monitoring data of multiple monitoring devices corresponding to the fault location; Based on the real-time monitoring data, the real-time fault status of the fault location is determined, and a fault alarm is issued based on the real-time fault status.

9. The method for monitoring the state of underground cable collector lines and providing fault alarms as claimed in claim 1, characterized in that: The method of training a pre-set deep learning model based on the fault information set to obtain an initial fault identification model for the underground cable collector line in the target area includes: Based on the fault information set, multiple fault information at different times are determined, and based on all the fault information, the pre-set deep learning model is trained to obtain an initial fault identification model for the underground cable collection line in the target area.

10. A device for monitoring the state of an underground cable collector line and for alarming faults, characterized in that: include: An acquisition module, used to acquire a line information set, a target fault set, and a monitoring equipment information set of an underground cable collector line in a target area; A simulation module, used to construct a simulation model of the buried cable collection line in the target area based on the line information set, and to perform simulation based on the target fault set and the simulation model to obtain a fault information set; A training module, used to train a pre-set deep learning model based on the fault information set to obtain an initial fault identification model for the underground cable collector line in the target area; A correction module, used to correct the initial fault identification model based on the monitoring equipment information set to obtain a fault identification model of the underground cable collector line in the target area; The alarm module is used to monitor the status of the underground cable collection line in the target area, obtain the real-time operation data of the underground cable collection line, obtain fault information based on the real-time operation data and the fault identification model, and issue a fault alarm based on the fault information.

Images