CN117590159A - Tunnel cable power supply state monitoring method and system based on deep learning - Google Patents
Tunnel cable power supply state monitoring method and system based on deep learning Download PDFInfo
- Publication number
- CN117590159A CN117590159A CN202410077453.8A CN202410077453A CN117590159A CN 117590159 A CN117590159 A CN 117590159A CN 202410077453 A CN202410077453 A CN 202410077453A CN 117590159 A CN117590159 A CN 117590159A
- Authority
- CN
- China
- Prior art keywords
- cable
- power supply
- monitoring
- fault
- supply state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 193
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000013135 deep learning Methods 0.000 title claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 36
- 238000013210 evaluation model Methods 0.000 claims abstract description 11
- 238000012423 maintenance Methods 0.000 claims description 39
- 238000012549 training Methods 0.000 claims description 27
- 238000012795 verification Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000013136 deep learning model Methods 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 239000000779 smoke Substances 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 7
- 238000011282 treatment Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000012552 review Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 8
- 230000004044 response Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/083—Locating faults in cables, transmission lines, or networks according to type of conductors in cables, e.g. underground
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Laying Of Electric Cables Or Lines Outside (AREA)
Abstract
The invention relates to the technical field of tunnel cable monitoring, in particular to a method and a system for monitoring the power supply state of a tunnel cable based on deep learning, which can improve the safety and the stability of the tunnel cable and ensure the normal operation of an urban power supply system; the method comprises the following steps: dividing the tunnel cable into units, and endowing each cable unit with a unique coordinate mark; according to preset monitoring frequency, data acquisition is carried out on each cable unit, and a first-order sensitive monitoring index data set of each cable unit is obtained; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves; sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model to obtain a cable power supply state evaluation index of each cable unit; and comparing and traversing the cable power supply state evaluation index of each cable unit by using a preset cable power supply state threshold value.
Description
Technical Field
The invention relates to the technical field of tunnel cable monitoring, in particular to a method and a system for monitoring a power supply state of a tunnel cable based on deep learning.
Background
With the rapid development of urban infrastructure construction, tunnel cables are an important component of urban power supply systems, and the safety and stability of the tunnel cables are critical to the normal operation of cities. However, since the tunnel cable is in a high-load, high-humidity environment for a long period of time, various faults such as voltage abnormality, current fluctuation, cable aging, etc., which may cause not only power interruption but also other safety accidents. Therefore, the real-time monitoring and fault early warning of the tunnel cable are key for guaranteeing safe and stable operation of the tunnel cable.
The traditional tunnel cable monitoring method mainly depends on manual inspection and periodic testing, and the method is low in efficiency, is easily affected by human factors, and is difficult to realize real-time and accurate monitoring. In recent years, with the development of sensor technology and data acquisition technology, monitoring systems based on sensor networks are becoming a hotspot for research.
However, most of the existing monitoring systems based on the sensor network only pay attention to the electrical performance of the cable, such as voltage, current, temperature, etc., but neglect the influence of the physical state of the cable and environmental factors on the state of the cable, which results in failure type and failure point location of the tunnel cable cannot be accurately identified.
Disclosure of Invention
In order to solve the technical problems, the invention provides a tunnel cable power supply state monitoring method based on deep learning, which can improve the safety and stability of a tunnel cable and ensure the normal operation of an urban power supply system.
In a first aspect, the present invention provides a method for monitoring a power supply state of a tunnel cable based on deep learning, the method comprising:
dividing the tunnel cable into units, and endowing each cable unit with a unique coordinate mark;
according to preset monitoring frequency, data acquisition is carried out on each cable unit, and a first-order sensitive monitoring index data set of each cable unit is obtained; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves;
sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model to obtain a cable power supply state evaluation index of each cable unit;
comparing and traversing the cable power supply state evaluation index of each cable unit by using a preset cable power supply state threshold, extracting cable units with the cable power supply state evaluation index lower than the preset cable power supply state threshold, and obtaining a fault cable unit set;
Data acquisition is carried out on each fault cable set in the fault cable unit sets, and a second-order sensitive monitoring index data set of each fault cable unit is obtained; the second-order sensitive monitoring index data set comprises cable deformation, cable tension, cable vibration, temperature, humidity, harmful gas concentration, smoke concentration and tunnel air pressure;
sequentially inputting the second-order sensitive monitoring index data set of each fault cable unit into a pre-constructed cable fault type identification model to obtain the fault type of the corresponding cable unit;
and displaying the fault type of the cable unit and the corresponding coordinate mark to an operation and maintenance worker.
Further, the method for acquiring the first-order sensitive monitoring index data set comprises the following steps:
selecting sensors suitable for monitoring the tunnel cable and installing the sensors in each cable unit; the sensor comprises a voltage sensor, a current sensor, a voltage fluctuation sensor and a current harmonic sensor;
setting a monitoring system, and acquiring data of each cable unit according to preset monitoring frequency through the monitoring system;
under the set monitoring frequency, the sensor collects the voltage, current, voltage fluctuation and current harmonic wave of the tunnel cable, and records the data according to the time stamp;
And storing the acquired data in a database, and cleaning, denoising and correcting the data.
Further, the cable power supply state evaluation model construction method comprises the following steps:
acquiring a historical first-order sensitive monitoring index data set, and carrying out normalization and trending removal treatment on the data set;
taking the spatial relationship of the cable units and the time sequence of the data into consideration, and selecting a multi-layer sensor as a basis of a model;
dividing the data set into a training set and a verification set;
constructing a deep neural network architecture comprising a plurality of hidden layers;
selecting an average absolute error as a loss function of the model, and measuring the difference between the model output and the true value;
training a model by using a training set, and optimizing model parameters;
evaluating the performance of the model by using a verification set, monitoring the change of a loss function, and ensuring that the model has better generalization performance on unseen data;
after training is completed, the model is deployed in an actual application system.
Further, the second-order sensitive monitoring index data set acquisition method of the fault cable unit comprises the following steps:
installing a deformation sensor on the cable, periodically collecting deformation data of the cable, and monitoring whether the cable is influenced by external force;
Installing a tension sensor on the cable, periodically collecting tension data of the cable, and judging whether the cable is stressed normally or not;
the vibration sensor is arranged on the cable, vibration data of the cable are collected periodically, and whether the cable is interfered by external vibration is detected;
installing a temperature and humidity sensor around the cable, and periodically collecting environmental data;
installing a gas sensor near the cable, and periodically collecting harmful gas and smoke concentration data;
and installing an air pressure sensor in the tunnel, and periodically collecting air pressure data.
Further, the method for constructing the cable fault type identification model comprises the following steps:
acquiring a second-order sensitive monitoring index data set of each fault cable unit and fault types of the corresponding cable units, dividing the data into a training set and a verification set, and carrying out standardization, normalization and characteristic engineering treatment on the data sets;
constructing a deep learning model, and selecting a convolutional neural network as a basis of the model;
constructing a framework of a deep learning model, wherein the framework comprises an input layer, a hidden layer and an output layer;
training the model by using a training set, wherein in the training process, the model continuously adjusts parameters to minimize the difference between the predicted value and the actual label;
Verifying the trained model by using a verification set, and evaluating generalization capability of the model on unseen data;
performing super-parameter adjustment on the model according to the verification result to improve the performance of the model;
the trained model is deployed into an actual monitoring system, so that the real-time and accurate processing of new monitoring data can be ensured.
Further, the fault type of the cable unit and the corresponding coordinate mark display method comprise the following steps:
combining the tunnel plan with the coordinate marks of the cable units by using a graphical interface, and displaying the fault type of each fault cable unit in different colors or marking modes;
providing a histogram to show the distribution situation of different types of faults;
when operation and maintenance personnel clicks a specific coordinate mark, the system pops up a detailed information window to display the fault type, monitoring data and other related information of the cable unit;
providing real-time state monitoring, and combining and displaying the cable fault state and real-time monitoring data;
when a fault occurs, reminding operation and maintenance personnel in an alarm and notification mode;
the function of inquiring the history record is provided, so that operation and maintenance personnel can review past fault conditions and know the evolution and trend of the cable system.
Further, the set influencing factors of the cable power supply state threshold value comprise cable types and specifications, environmental conditions, load changes and historical data analysis.
In another aspect, the present application further provides a tunnel cable power supply state monitoring system based on deep learning, the system including:
the cable unit dividing module is used for dividing the tunnel cable into different units, assigning unique coordinate marks for each cable unit and sending unit dividing information;
the first-order data acquisition module is used for receiving unit division information, carrying out data acquisition on each cable unit according to preset monitoring frequency, obtaining a first-order sensitive monitoring index data set of each cable unit and sending the first-order sensitive monitoring index data set; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves;
the power supply state evaluation module is used for receiving the first-order sensitive monitoring index data set of each cable unit, sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model, obtaining a cable power supply state evaluation index of each cable unit and sending the cable power supply state evaluation index;
The fault screening module is used for receiving the cable power supply state evaluation index of each cable unit, comparing and traversing the cable power supply state evaluation index of each cable unit by utilizing a preset cable power supply state threshold value, extracting cable units with the cable power supply state evaluation index lower than the preset cable power supply state threshold value, obtaining a fault cable unit set and sending the fault cable unit set;
the second-order data acquisition module is used for receiving the fault cable unit sets, carrying out data acquisition on each fault cable set in the fault cable unit sets, obtaining second-order sensitive monitoring index data sets of each fault cable unit and sending the second-order sensitive monitoring index data sets; the second-order sensitive monitoring index data set comprises cable deformation, cable tension, cable vibration, temperature, humidity, harmful gas concentration, smoke concentration and tunnel air pressure;
the fault type identification module is used for receiving the second-order sensitive monitoring index data set of each fault cable unit, sequentially inputting the second-order sensitive monitoring index data set of each fault cable unit into a pre-constructed cable fault type identification model, obtaining the fault type of the corresponding cable unit and transmitting the fault type;
the result display module is used for receiving the fault type of the cable unit and displaying the fault type of the cable unit and the corresponding coordinate mark to operation and maintenance staff.
In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, the computer program implementing the steps of any of the methods described above when executed by the processor.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that: according to the method, the electrical performance of the cable can be comprehensively monitored by carrying out unit division on the cable and combining data acquisition of first-order sensitive monitoring indexes, so that comprehensive cable state information is provided; the deep learning model is used for cable power supply state evaluation and fault type identification, so that complex cable state data can be analyzed more accurately, and the sensitivity and accuracy of monitoring are improved;
the preset monitoring frequency is adopted, so that the real-time data acquisition of each cable unit is realized, and the monitoring system is more time-efficient; meanwhile, by applying the deep learning model, the accuracy of the cable state is improved; by utilizing a preset cable power supply state threshold value, the evaluation indexes of the traversed cable units can be automatically compared, and the units with abnormal cable power supply states are extracted, so that automatic fault identification is realized, and the requirement for manual intervention is reduced;
Through data acquisition of second-order sensitive monitoring indexes, not only the electrical performance of the cable is concerned, but also the physical state and environmental factors of the cable are considered, so that the omnibearing identification of the fault type is realized; the fault type of the cable unit and the corresponding coordinate mark are provided for operation staff, so that the monitoring result is easier to understand and operate;
in conclusion, the method has remarkable advantages in the aspects of comprehensive monitoring, deep learning model application, real-time performance and accuracy, automatic fault identification, omnibearing fault identification and the like, can improve the safety and stability of tunnel cables, and ensures the normal operation of an urban power supply system.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of a method of cable power state assessment model construction;
FIG. 3 is a flow chart of a method of constructing a cable fault type identification model;
fig. 4 is a block diagram of a tunnel cable power state monitoring system based on deep learning.
Detailed Description
In the description of the present application, those skilled in the art will appreciate that the present application may be embodied as methods, apparatuses, electronic devices, and computer-readable storage media. Accordingly, the present application may be embodied in the following forms: complete hardware, complete software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, the present application may also be embodied in the form of a computer program product in one or more computer-readable storage media, which contain computer program code.
Any combination of one or more computer-readable storage media may be employed by the computer-readable storage media described above. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer readable storage medium include the following: portable computer magnetic disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disk read-only memories, optical storage devices, magnetic storage devices, or any combination thereof. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device.
The present application describes methods, apparatus, and electronic devices provided by the flowchart and/or block diagram.
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer readable program instructions may also be stored in a computer readable storage medium that can cause a computer or other programmable data processing apparatus to function in a particular manner. Thus, instructions stored in a computer-readable storage medium produce an instruction means which implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The present application is described below with reference to the drawings in the present application.
Embodiment one: as shown in fig. 1 to 3, the method for monitoring the power supply state of the tunnel cable based on deep learning specifically comprises the following steps:
s1, carrying out unit division on tunnel cables, and endowing each cable unit with a unique coordinate mark;
The tunnel cable unit dividing method comprises the following steps:
A. digitally modeling a tunnel structure by using a geographic information system, and dividing the tunnel into cable units; the geographic information system divides the tunnel network into logic units based on geographic space information, so that monitoring and management are facilitated;
B. dividing the cable path into proper units according to the actual tunnel structure and the cable wiring diagram; based on the actual wiring diagram, the boundaries and locations of the cable units can be determined;
C. installing global positioning system equipment, and marking unique coordinates for each cable unit; being able to provide accurate geographic coordinates;
D. establishing a relative coordinate system in the tunnel, and distributing coordinates relative to the datum point for each cable unit; is suitable for simplifying position marks in a limited space;
E. using a laser rangefinder to assign coordinates by measuring the distance between the cable unit and the tunnel structure; the method is suitable for tunnels with smaller structures and complicated structures.
In the step, the tunnel is divided into logic cable units, so that accurate monitoring and management of a cable system can be realized, and operation and maintenance personnel can more easily locate, identify and process problems; by assigning unique coordinate marks to each cable unit, the possible fault area can be rapidly and accurately positioned, and the maintenance time and loss are reduced;
The global positioning system or the relative coordinate system is utilized to realize real-time monitoring of the position of the cable unit, so that potential problems can be found in time, and the early warning system is more flexible and efficient; the distance between the cable unit and the tunnel structure can be accurately measured in a complex structure by means of tools such as a laser range finder, reliable data support is provided for accurate division of the cable unit, and monitoring precision is improved; by dividing the tunnel into cable units and giving unique coordinate marks to the cable units, maintenance personnel can more orderly carry out inspection and maintenance, and the influence of human factors on monitoring is reduced;
in summary, the method can improve the accuracy and efficiency of monitoring, and simultaneously provides a solid foundation for subsequent data acquisition and deep learning models.
S2, acquiring data of each cable unit according to a preset monitoring frequency to obtain a first-order sensitive monitoring index data set of each cable unit; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves;
the method for acquiring the first-order sensitive monitoring index data set comprises the following steps:
s21, selecting sensors suitable for monitoring tunnel cables, and installing the sensors in each cable unit; the sensor comprises a voltage sensor, a current sensor, a voltage fluctuation sensor and a current harmonic sensor;
S22, setting a monitoring system, and acquiring data of each cable unit according to preset monitoring frequency through the monitoring system;
s23, under a set monitoring frequency, the sensor collects voltage, current, voltage fluctuation and current harmonic waves of the tunnel cable, and records the data according to a time stamp;
s24, storing the acquired data in a database, and cleaning, denoising and correcting the data;
the setting influence factors of the monitoring frequency comprise:
A. the cable is operated, different cables have different response time and change rate in the operation process, and proper monitoring frequency is determined according to the operation characteristics of the cables;
B. real-time requirements, which are different in real-time requirements of different application scenes on monitoring data, can directly influence the setting of the monitoring frequency;
C. data storage and processing capabilities, high frequency data collection generates large amounts of data, thus requiring sufficient storage and processing capabilities to store, transmit, and analyze such data; when determining the monitoring frequency, the data management capability of the monitoring system needs to be considered;
D. energy consumption, the cable monitoring system needs to use sensors and data transmission equipment, and high-frequency monitoring can lead to higher energy consumption; in an environment with limited energy, it is necessary to balance the relationship between the monitoring frequency and the energy consumption;
E. Sensor response time, the response time of the sensor itself is an important factor affecting the monitoring frequency.
In the step, through selecting a plurality of sensors suitable for monitoring the tunnel cable, the comprehensive monitoring of the cable unit is realized, and comprehensive information is provided for comprehensively evaluating the power supply state of the cable; the cable unit can be accurately monitored through the preset monitoring frequency, so that the relationship between real-time property and resource consumption is balanced, and the monitoring system can be effectively operated in different scenes;
the collected data is recorded according to the time stamp and stored in the database, so that the monitoring system is ensured to record and store the cable state in time, and a reliable data basis is provided for subsequent analysis and fault diagnosis; after data acquisition, the data are subjected to cleaning, denoising, correction and other treatments, so that the accuracy and the reliability of the data are improved, and the monitoring result is more credible;
when the monitoring frequency is determined, a plurality of factors are comprehensively considered, so that the monitoring frequency can adapt to different running environments and requirements, and the effect of balancing the requirements in all aspects is achieved;
in summary, the step S2 provides a reliable data base for monitoring the power supply state of the tunnel cable through comprehensive monitoring and accurate monitoring frequency setting, and can realize timely fault early warning and accurate power supply state evaluation.
S3, sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model to obtain a cable power supply state evaluation index of each cable unit;
the cable power supply state evaluation model construction method comprises the following steps:
s31, acquiring a historical first-order sensitive monitoring index data set, and carrying out normalization and trending removal on the data set;
s32, taking the spatial relationship of the cable units and the time sequence of the data into consideration, and selecting a multi-layer sensor as a basis of a model;
s33, dividing the data set into a training set and a verification set;
s34, constructing a deep neural network architecture, wherein the architecture comprises a plurality of hidden layers, and the node number of each hidden layer is required to be adjusted according to the complexity of the problem;
s35, selecting an average absolute error as a loss function of the model, and measuring the difference between the model output and the true value;
s36, training a model by using a training set, and optimizing model parameters;
s37, evaluating the performance of the model by using a verification set, monitoring the change of a loss function, and ensuring that the model has better generalization performance on unseen data;
s38, after training is completed, the model is deployed in an actual application system for subsequent use.
In the step, through carrying out normalization and trending treatment on the historical first-order sensitive monitoring index data, ensuring that the data has a consistent scale and removing the trend which possibly interferes with model learning; the architecture of the deep neural network is constructed, and the architecture comprises a plurality of hidden layers, so that complex characteristics of a cable power supply state can be better captured; by dividing the data set, the model can not only learn the characteristics of the data during training, but also generalize on the verification set, so that overfitting is avoided; the average absolute error is selected as a loss function, so that the model is more concerned with the accuracy of the power supply state evaluation index of each cable unit, and the sensitivity of the model to abnormal conditions is improved;
model training is carried out by using a training set, the model can learn the mode of historical data, and model parameters are optimized to adapt to actual conditions; evaluating the performance of the model by using a verification set, monitoring the change of a loss function, ensuring that the model has better generalization performance on unseen data, and improving the robustness of the model; the trained model is deployed into an actual application system, so that real-time prediction and monitoring are provided for subsequent cable power supply state evaluation, potential problems can be found in time, and corresponding measures can be taken;
In summary, the cable power supply state evaluation model can accurately predict the power supply state of each cable unit, improves the real-time performance and accuracy of the monitoring system, is beneficial to preventing potential cable faults and ensures the stable operation of the urban power supply system.
S4, comparing and traversing the cable power supply state evaluation indexes of each cable unit by using a preset cable power supply state threshold, extracting cable units with the cable power supply state evaluation indexes lower than the preset cable power supply state threshold, and obtaining a fault cable unit set;
the setting influence factors of the cable power supply state threshold value comprise:
A. the cable types and specifications have different electrical performances and bearing capacities in design, so that the power supply state threshold value of the cable needs to be adjusted according to the specific cable types and specifications;
B. the environmental conditions, the humidity and the temperature of the tunnel environment influence the running state of the cable; humidity and temperature changes can cause changes in cable insulation properties, so that the cable power state threshold needs to take into account environmental conditions;
C. when the load changes and the load increases, the cable can face larger current and voltage pressure, so that the power supply state threshold value of the cable needs to be adjusted according to the load condition;
D. Analysis of historical data, analysis of historical cable operational data may provide a deeper understanding of cable behavior, by analyzing past fault conditions and operational data, a more reasonable and accurate cable power state threshold can be determined.
In the step, the actual performance and the bearing capacity of the cable can be more accurately matched by adjusting according to the type and the specification of the cable, and the adaptability of the power supply state threshold of the cable is further improved by considering the environmental condition and the historical data, so that the power supply state threshold is more close to the actual working environment and the past operation condition;
by comprehensively considering historical data analysis, potential and unconventional fault modes can be found; the robustness of the system is improved, so that the system can better cope with various complex and changing conditions, and misjudgment and missing report are reduced;
the threshold value is adjusted according to the load change, so that the real-time fluctuation of the urban power load can be more flexibly adapted, the real-time monitoring and timely response of the power supply state of the cable are further realized, and the real-time performance and the flexibility of the system are improved; considering the influence of environmental conditions, the false alarm rate is reduced, and the fine threshold adjustment can reduce the false judgment; the threshold value is adjusted according to the historical data and the actual load condition, so that the utilization of system resources can be optimized, and further a cable unit with a problem can be accurately positioned, and unnecessary manpower and material resource waste on a normally operated cable is avoided;
In summary, the step S4 improves the efficiency of the monitoring system, so that the monitoring system has higher adaptability, robustness and operability, and further ensures the safe and stable operation of the tunnel cable.
S5, data acquisition is carried out on each fault cable set in the fault cable unit sets, and a second-order sensitive monitoring index data set of each fault cable unit is obtained; the second-order sensitive monitoring index data set comprises cable deformation, cable tension, cable vibration, temperature, humidity, harmful gas concentration, smoke concentration and tunnel air pressure;
through the data acquisition of the second-order sensitive monitoring indexes, the physical state and the environmental influence of the cable can be comprehensively known, and more powerful basis is provided for the subsequent fault type identification;
the second-order sensitive monitoring index data set acquisition method of the fault cable unit comprises the following steps:
s51, installing a deformation sensor on the cable, periodically collecting deformation data of the cable, and monitoring whether the cable is influenced by external force;
s52, installing a tension sensor on the cable, periodically collecting tension data of the cable, and judging whether the cable is stressed normally or not;
s53, installing a vibration sensor on the cable, periodically collecting vibration data of the cable, and detecting whether the cable is interfered by external vibration;
S54, installing a temperature and humidity sensor around the cable, and periodically collecting environmental data, wherein the insulation performance of the cable can be affected by the change of temperature and humidity;
s55, installing a gas sensor near the cable, periodically collecting harmful gas and smoke concentration data, and finding out environmental factors affecting the state of the cable as soon as possible;
s56, installing an air pressure sensor in the tunnel, and periodically collecting air pressure data.
In the step, various sensitive monitoring indexes are integrated, so that a data set is more comprehensive, and the state of the cable can be comprehensively known from multiple angles; by regularly collecting data such as deformation, tension and vibration, whether the cable is influenced by external force, whether the cable is normally stressed or not and whether the cable is interfered by vibration or not can be found early, early fault early warning is facilitated, potential problems are found in advance, and the possibility of accidents is reduced;
the comprehensive consideration of environmental factors can evaluate the change of the surrounding environment of the cable more comprehensively, provide more characteristics and dimensions, help to construct a more accurate cable fault type identification model, and help operation and maintenance personnel to locate and solve cable faults more quickly and accurately; by monitoring various indexes, a data-driven maintenance strategy is realized, a reasonable maintenance plan is formulated according to actual conditions, and the maintenance efficiency is improved;
In summary, the beneficial effects of the step S5 include comprehensive data collection, early fault early warning, comprehensive consideration of environmental factors, accurate fault type identification and data-driven maintenance strategies, which together provide important support for safe and stable operation of the tunnel cable.
S6, sequentially inputting the second-order sensitive monitoring index data set of each fault cable unit into a pre-constructed cable fault type identification model to obtain the fault type of the corresponding cable unit;
the cable fault type identification model construction method comprises the following steps:
s61, acquiring a second-order sensitive monitoring index data set of each fault cable unit and fault types of the corresponding cable units, dividing the data into a training set and a verification set, and carrying out standardization, normalization and characteristic engineering treatment on the data sets;
s62, constructing a deep learning model, selecting a convolutional neural network as a basis of the model, receiving a plurality of input features, and outputting predictions corresponding to cable fault types;
s63, constructing a deep learning model framework, wherein the deep learning model framework comprises an input layer, a hidden layer and an output layer;
s64, training the model by using a training set, wherein in the training process, the model continuously adjusts parameters to minimize the difference between the predicted value and the actual label;
S65, verifying the trained model by using a verification set, evaluating generalization capability of the model on unseen data, and checking whether the model is over-fitted or under-fitted;
s66, performing super-parameter adjustment on the model according to the verification result to improve the performance of the model;
s67, deploying the trained model into an actual monitoring system, and ensuring that the model can process new monitoring data accurately in real time.
In the step, the cable fault type can be accurately identified by using the deep learning model, and the complex mode in the second-order sensitive monitoring index can be effectively learned and captured, so that the identification accuracy is improved; the convolutional neural network is selected as a model base, so that the system can process a plurality of input features, and multi-feature fusion is beneficial to improving the adaptability of the model to complex scenes; the time sequence monitoring index data can be better processed through the deep learning model; the constructed deep learning model can automatically learn and identify fault types, reduces the requirement for manual intervention, improves the automation level of a monitoring system, and reduces the dependence on human resources;
through effective model design and super parameter adjustment, rapid and accurate fault type identification can be performed under real-time requirements; the verification set is utilized to carry out model evaluation and super-parameter adjustment, which is beneficial to continuously optimizing the performance of the model, and ensures that the model can perform well under different scenes and conditions;
The trained model is deployed into an actual monitoring system, so that the stability of the whole system can be improved, and the accurate cable fault type identification service can be continuously provided in long-term operation;
in summary, the accuracy can be improved, multi-feature fusion, adaptive time sequence and automatic processing can be realized, the instantaneity and the system stability can be improved, and positive contribution is made to the reliability and the efficiency of the tunnel cable monitoring system.
S7, displaying the fault type of the cable unit and the corresponding coordinate mark to operation and maintenance staff;
the fault type of the cable unit and the corresponding coordinate mark display method comprise the following steps:
s71, combining the tunnel plan view with the coordinate marks of the cable units by using a graphical interface, and displaying the fault type of each fault cable unit in different colors or marking modes;
s72, providing a histogram, and displaying the distribution situation of different types of faults, so that operation and maintenance personnel can know the frequency and relative importance of different fault types;
s73, when an operation and maintenance person clicks a specific coordinate mark, the system pops up a detailed information window to display the fault type, monitoring data and other related information of the cable unit;
S74, providing real-time state monitoring, and combining and displaying the cable fault state and the real-time monitoring data;
s75, reminding operation and maintenance personnel in an alarm and notification mode when faults occur;
s76, providing a function of inquiring the history record, so that operation and maintenance personnel can review past fault conditions and know the evolution and trend of the cable system.
In the step, by using a graphical interface and through a color or marking mode, an operation and maintenance personnel can rapidly position a cable unit with a fault on a tunnel plan, so that the response speed is improved, a problem area is accurately positioned, and the fault positioning time is shortened; providing a histogram to show the distribution condition of different types of faults, so that operation and maintenance personnel can know the relative frequencies and importance of different fault types, and further, common or serious faults are preferentially processed, and the overall reliability of the system is improved.
When an operation and maintenance person clicks a specific coordinate mark, the system pops up a detailed information window to display the related information such as the fault type, the monitoring data and the like of the cable unit, so that deeper understanding is provided, and the operation and maintenance person is facilitated to make a more specific maintenance plan; the cable fault state and the real-time monitoring data are combined and displayed, so that operation and maintenance personnel can monitor the state of the system in real time, respond to real-time changes quickly, prevent potential problems and ensure the stable operation of the system;
By means of alarming and informing, the system informs operation and maintenance personnel in time when a fault occurs, so that the fault discovery and response speed is improved, and the potential risk is reduced; the function of inquiring the history record is provided, so that operation and maintenance personnel can review the past fault condition, know the evolution and trend of the cable system, and are beneficial to formulating a long-term maintenance strategy and preventing future problems;
in summary, the method has the beneficial effects that a comprehensive, real-time and historical data display mode is provided, so that operation and maintenance personnel can understand the state of the cable system more quickly and accurately, and the operation and maintenance efficiency and the system reliability are improved effectively.
Embodiment two: as shown in fig. 4, the tunnel cable power supply state monitoring system based on deep learning of the invention specifically comprises the following modules;
the cable unit dividing module is used for dividing the tunnel cable into different units, assigning unique coordinate marks for each cable unit and sending unit dividing information;
the first-order data acquisition module is used for receiving unit division information, carrying out data acquisition on each cable unit according to preset monitoring frequency, obtaining a first-order sensitive monitoring index data set of each cable unit and sending the first-order sensitive monitoring index data set; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves;
The power supply state evaluation module is used for receiving the first-order sensitive monitoring index data set of each cable unit, sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model, obtaining a cable power supply state evaluation index of each cable unit and sending the cable power supply state evaluation index;
the fault screening module is used for receiving the cable power supply state evaluation index of each cable unit, comparing and traversing the cable power supply state evaluation index of each cable unit by utilizing a preset cable power supply state threshold value, extracting cable units with the cable power supply state evaluation index lower than the preset cable power supply state threshold value, obtaining a fault cable unit set and sending the fault cable unit set;
the second-order data acquisition module is used for receiving the fault cable unit sets, carrying out data acquisition on each fault cable set in the fault cable unit sets, obtaining second-order sensitive monitoring index data sets of each fault cable unit and sending the second-order sensitive monitoring index data sets; the second-order sensitive monitoring index data set comprises cable deformation, cable tension, cable vibration, temperature, humidity, harmful gas concentration, smoke concentration and tunnel air pressure;
The fault type identification module is used for receiving the second-order sensitive monitoring index data set of each fault cable unit, sequentially inputting the second-order sensitive monitoring index data set of each fault cable unit into a pre-constructed cable fault type identification model, obtaining the fault type of the corresponding cable unit and transmitting the fault type;
the result display module is used for receiving the fault type of the cable unit and displaying the fault type of the cable unit and the corresponding coordinate mark to operation and maintenance staff.
The system can acquire and monitor data of each cable unit in real time through preset monitoring frequency, so that timely sensing and fault early warning of the power supply state of the cable are realized, and potential power supply interruption and safety accidents can be avoided; the cable power supply state is evaluated and the fault type is identified by using the deep learning model, so that the system has higher flexibility and accuracy, can learn complex features and modes from a large amount of data, and improves the accuracy of the monitoring system;
the system comprehensively considers the electrical performance and the physical environment of the cable, so that the cable state is monitored more comprehensively; the fault screening module automatically compares the evaluation indexes of the traversed cable units through a preset cable power supply state threshold value to extract the units with abnormal cable power supply states, so that automatic fault identification is realized, and the influence of human factors is reduced; through the second-order sensitive monitoring index data set, the system can identify various fault types, and the omnibearing fault identification can accurately position and solve the cable problem;
The result display module displays the fault type of the cable unit and the corresponding coordinate mark to operation and maintenance staff, provides clear and visual information for the operation and maintenance staff, and is beneficial to quick response and maintenance;
in conclusion, the system has remarkable advantages in the aspects of improving monitoring accuracy, realizing real-time monitoring, comprehensively considering monitoring indexes, automatically screening faults and the like, can improve the safety and stability of tunnel cables, and ensures the normal operation of the urban power supply system.
The various modifications and embodiments of the tunnel cable power supply state monitoring method based on deep learning in the foregoing embodiment are equally applicable to the tunnel cable power supply state monitoring system based on deep learning in this embodiment, and by the foregoing detailed description of the tunnel cable power supply state monitoring method based on deep learning, those skilled in the art can clearly know the implementation method of the tunnel cable power supply state monitoring system based on deep learning in this embodiment, so that the details will not be described in detail herein for brevity of description.
In addition, the application further provides an electronic device, which comprises a bus, a transceiver, a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the transceiver, the memory and the processor are respectively connected through the bus, and when the computer program is executed by the processor, the processes of the method embodiment for controlling output data are realized, and the same technical effects can be achieved, so that repetition is avoided and redundant description is omitted.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that modifications and variations can be made without departing from the technical principles of the present invention, and these modifications and variations should also be regarded as the scope of the invention.
Claims (10)
1. The tunnel cable power supply state monitoring method based on deep learning is characterized by comprising the following steps of:
dividing the tunnel cable into units, and endowing each cable unit with a unique coordinate mark;
according to preset monitoring frequency, data acquisition is carried out on each cable unit, and a first-order sensitive monitoring index data set of each cable unit is obtained; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves;
sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model to obtain a cable power supply state evaluation index of each cable unit;
comparing and traversing the cable power supply state evaluation index of each cable unit by using a preset cable power supply state threshold, extracting cable units with the cable power supply state evaluation index lower than the preset cable power supply state threshold, and obtaining a fault cable unit set;
Data acquisition is carried out on each fault cable set in the fault cable unit sets, and a second-order sensitive monitoring index data set of each fault cable unit is obtained; the second-order sensitive monitoring index data set comprises cable deformation, cable tension, cable vibration, temperature, humidity, harmful gas concentration, smoke concentration and tunnel air pressure;
sequentially inputting the second-order sensitive monitoring index data set of each fault cable unit into a pre-constructed cable fault type identification model to obtain the fault type of the corresponding cable unit;
and displaying the fault type of the cable unit and the corresponding coordinate mark to an operation and maintenance worker.
2. The method for monitoring the power supply state of a tunnel cable based on deep learning as claimed in claim 1, wherein the method for acquiring the first-order sensitive monitoring index data set comprises the following steps:
selecting sensors suitable for monitoring the tunnel cable and installing the sensors in each cable unit; the sensor comprises a voltage sensor, a current sensor, a voltage fluctuation sensor and a current harmonic sensor;
setting a monitoring system, and acquiring data of each cable unit according to preset monitoring frequency through the monitoring system;
Under the set monitoring frequency, the sensor collects the voltage, current, voltage fluctuation and current harmonic wave of the tunnel cable, and records the data according to the time stamp;
and storing the acquired data in a database, and cleaning, denoising and correcting the data.
3. The tunnel cable power supply state monitoring method based on deep learning as claimed in claim 1, wherein the cable power supply state evaluation model construction method comprises the following steps:
acquiring a historical first-order sensitive monitoring index data set, and carrying out normalization and trending removal treatment on the data set;
taking the spatial relationship of the cable units and the time sequence of the data into consideration, and selecting a multi-layer sensor as a basis of a model;
dividing the data set into a training set and a verification set;
constructing a deep neural network architecture comprising a plurality of hidden layers;
selecting an average absolute error as a loss function of the model, and measuring the difference between the model output and the true value;
training a model by using a training set, and optimizing model parameters;
evaluating the performance of the model using the validation set, monitoring the change in the loss function;
after training is completed, the model is deployed in an actual application system.
4. The tunnel cable power supply state monitoring method based on deep learning as claimed in claim 1, wherein the second-order sensitive monitoring index data set acquisition method of the fault cable unit comprises the following steps:
installing a deformation sensor on the cable, periodically collecting deformation data of the cable, and monitoring whether the cable is influenced by external force;
installing a tension sensor on the cable, periodically collecting tension data of the cable, and judging whether the cable is stressed normally or not;
the vibration sensor is arranged on the cable, vibration data of the cable are collected periodically, and whether the cable is interfered by external vibration is detected;
installing a temperature and humidity sensor around the cable, and periodically collecting environmental data;
installing a gas sensor near the cable, and periodically collecting harmful gas and smoke concentration data;
and installing an air pressure sensor in the tunnel, and periodically collecting air pressure data.
5. The tunnel cable power supply state monitoring method based on deep learning as claimed in claim 1, wherein the cable fault type identification model construction method comprises the following steps:
acquiring a second-order sensitive monitoring index data set of each fault cable unit and fault types of the corresponding cable units, dividing the data into a training set and a verification set, and carrying out standardization, normalization and characteristic engineering treatment on the data sets;
Constructing a deep learning model, and selecting a convolutional neural network as a basis of the model;
constructing a framework of a deep learning model, wherein the framework comprises an input layer, a hidden layer and an output layer;
training the model by using a training set, wherein in the training process, the model continuously adjusts parameters to minimize the difference between the predicted value and the actual label;
verifying the trained model by using a verification set, and evaluating generalization capability of the model on unseen data;
performing super-parameter adjustment on the model according to the verification result to improve the performance of the model;
the trained model is deployed into an actual monitoring system, so that the real-time and accurate processing of new monitoring data can be ensured.
6. The method for monitoring the power supply state of the tunnel cable based on deep learning according to claim 1, wherein the fault type of the cable unit and the corresponding coordinate mark display method comprise the following steps:
combining the tunnel plan with the coordinate marks of the cable units by using a graphical interface, and displaying the fault type of each fault cable unit in different colors and marking modes;
providing a histogram to show the distribution situation of different types of faults;
when operation and maintenance personnel clicks a specific coordinate mark, the system pops up a detailed information window to display the fault type, monitoring data and other related information of the cable unit;
Providing real-time state monitoring, and combining and displaying the cable fault state and real-time monitoring data;
when a fault occurs, reminding operation and maintenance personnel in an alarm and notification mode;
the function of inquiring the history record is provided, so that operation and maintenance personnel can review past fault conditions and know the evolution and trend of the cable system.
7. The method for monitoring the power supply state of the tunnel cable based on deep learning according to claim 1, wherein the set influencing factors of the power supply state threshold value of the cable comprise cable type and specification, environmental conditions, load change and historical data analysis.
8. A deep learning-based tunnel cable power state monitoring system, the system comprising:
the cable unit dividing module is used for dividing the tunnel cable into different units, assigning unique coordinate marks for each cable unit and sending unit dividing information;
the first-order data acquisition module is used for receiving unit division information, carrying out data acquisition on each cable unit according to preset monitoring frequency, obtaining a first-order sensitive monitoring index data set of each cable unit and sending the first-order sensitive monitoring index data set; the first-order sensitive monitoring index data set comprises voltage, current, voltage fluctuation and current harmonic waves;
The power supply state evaluation module is used for receiving the first-order sensitive monitoring index data set of each cable unit, sequentially inputting the first-order sensitive monitoring index data set of each cable unit into a pre-constructed cable power supply state evaluation model, obtaining a cable power supply state evaluation index of each cable unit and sending the cable power supply state evaluation index;
the fault screening module is used for receiving the cable power supply state evaluation index of each cable unit, comparing and traversing the cable power supply state evaluation index of each cable unit by utilizing a preset cable power supply state threshold value, extracting cable units with the cable power supply state evaluation index lower than the preset cable power supply state threshold value, obtaining a fault cable unit set and sending the fault cable unit set;
the second-order data acquisition module is used for receiving the fault cable unit sets, carrying out data acquisition on each fault cable set in the fault cable unit sets, obtaining second-order sensitive monitoring index data sets of each fault cable unit and sending the second-order sensitive monitoring index data sets; the second-order sensitive monitoring index data set comprises cable deformation, cable tension, cable vibration, temperature, humidity, harmful gas concentration, smoke concentration and tunnel air pressure;
The fault type identification module is used for receiving the second-order sensitive monitoring index data set of each fault cable unit, sequentially inputting the second-order sensitive monitoring index data set of each fault cable unit into a pre-constructed cable fault type identification model, obtaining the fault type of the corresponding cable unit and transmitting the fault type;
the result display module is used for receiving the fault type of the cable unit and displaying the fault type of the cable unit and the corresponding coordinate mark to operation and maintenance staff.
9. A deep learning based tunnel cable power status monitoring electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, characterized in that the computer program when executed by the processor implements the steps of the method according to any one of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410077453.8A CN117590159A (en) | 2024-01-19 | 2024-01-19 | Tunnel cable power supply state monitoring method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410077453.8A CN117590159A (en) | 2024-01-19 | 2024-01-19 | Tunnel cable power supply state monitoring method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117590159A true CN117590159A (en) | 2024-02-23 |
Family
ID=89922787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410077453.8A Withdrawn CN117590159A (en) | 2024-01-19 | 2024-01-19 | Tunnel cable power supply state monitoring method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117590159A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118040904A (en) * | 2024-04-09 | 2024-05-14 | 宁波市电力设计院有限公司 | Cable trench operation and maintenance state monitoring method and monitoring and analyzing cloud platform |
-
2024
- 2024-01-19 CN CN202410077453.8A patent/CN117590159A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118040904A (en) * | 2024-04-09 | 2024-05-14 | 宁波市电力设计院有限公司 | Cable trench operation and maintenance state monitoring method and monitoring and analyzing cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105551549A (en) | Method and system for on-line monitoring of running state of nuclear power equipment | |
| CN101999101B (en) | The defining method of system cloud gray model prediction | |
| CN117590159A (en) | Tunnel cable power supply state monitoring method and system based on deep learning | |
| CN117060409B (en) | Automatic detection and analysis method and system for power line running state | |
| CN115640860B (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
| CN117082105B (en) | Environment-friendly intelligent hospital facility monitoring system and method | |
| CN110703743A (en) | Equipment failure prediction and detection system and method | |
| CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN116822115A (en) | Environment management method and system for intelligent park based on digital twin technology | |
| CN114462820A (en) | Bearing state monitoring and health management system performance testing and optimizing method and system | |
| CN116777088B (en) | Power supply emergency repair environment monitoring method and system for guaranteeing life safety | |
| CN113204919B (en) | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment | |
| CN104317778A (en) | Massive monitoring data based substation equipment fault diagnosis method | |
| CN116754022B (en) | On-line detection emergency early warning method and system for cable tunnel | |
| CN116843314A (en) | Monitoring terminal operation and maintenance management method, system, equipment and storage medium | |
| CN114837902B (en) | Health degree evaluation method, system, equipment and medium for wind turbine generator | |
| RU2735296C1 (en) | Method for multi-parameter monitoring of complex electrotechnical objects state | |
| Nielsen et al. | Quantifying the value of SHM for wind turbine blades | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
| CN117391459B (en) | Electric power operation risk early warning method and system based on deep learning | |
| CN117783769B (en) | Power distribution network fault positioning method, system, equipment and storage medium based on visual platform | |
| Savić et al. | Business intelligence in managing of technical-information system | |
| CN117937768B (en) | Intelligent electrical cabinet remote monitoring system | |
| CN116258467B (en) | Electric power construction management and control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240223 |