CN114638380A - Cable parameter fault determination method and device for multi-type parameter network model - Google Patents

Cable parameter fault determination method and device for multi-type parameter network model Download PDF

Info

Publication number
CN114638380A
CN114638380A CN202210095663.0A CN202210095663A CN114638380A CN 114638380 A CN114638380 A CN 114638380A CN 202210095663 A CN202210095663 A CN 202210095663A CN 114638380 A CN114638380 A CN 114638380A
Authority
CN
China
Prior art keywords
cable
parameter
parameters
attribute parameters
fault
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.)
Pending
Application number
CN202210095663.0A
Other languages
Chinese (zh)
Inventor
邹科敏
黄应敏
王骞能
胡超强
陈喜东
邵源鹏
高伟光
许翠珊
杨航
冯泽华
梁志豪
严伟聪
徐兆良
游仿群
徐加健
徐秋燕
陆松记
李晋芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Panyu Cable Group Co Ltd
Original Assignee
Guangzhou Panyu Cable Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Panyu Cable Group Co Ltd filed Critical Guangzhou Panyu Cable Group Co Ltd
Priority to CN202210095663.0A priority Critical patent/CN114638380A/en
Publication of CN114638380A publication Critical patent/CN114638380A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Monitoring And Testing Of Transmission In General (AREA)

Abstract

The embodiment of the invention discloses a cable parameter fault determination method of a multi-type parameter network model, which comprises the following steps: determining corresponding main attribute parameters and auxiliary attribute parameters according to different cable types; training different network models based on historical data of different main attribute parameters and auxiliary attribute parameters to obtain a plurality of different training network models, wherein each training network model corresponds to one type of cable; acquiring cable parameters to be processed, determining main attribute parameters and auxiliary attribute parameters in the cable parameters, and inputting the parameters into a corresponding training network model to output a fault detection result. According to the scheme, the corresponding training network model is established based on the main attribute parameters and the auxiliary attribute parameters of different cable types, and the cable fault is detected according to multiple parameters, so that an efficient and reasonable comprehensive judgment mechanism is provided. The problems of low cable fault prediction efficiency and poor accuracy in the prior art are solved, the cable fault prediction precision is improved, and a cable monitoring mechanism is optimized.

Description

Cable parameter fault determination method and device for multi-type parameter network model
Technical Field
The embodiment of the application relates to the field of cables, in particular to a method and a device for determining cable parameter faults of a multi-type parameter network model.
Background
In order to ensure the normal operation of the cable, various sensors or monitoring devices are usually arranged to monitor the parameters of the cable in real time, so as to ensure that a fault point and a fault reason can be determined at the first time when the cable has a fault.
In the existing intelligent cable monitoring process, if the real-time monitoring is realized through the acquired cable related parameter data and the acquired surrounding environment data, such as cable temperature, monitoring images, environment wind speed, humidity and the like, parameters used for predicting the cable fault are single, and an efficient and reasonable comprehensive judgment mechanism is lacked.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining cable parameter faults of a multi-type parameter network model, solves the problems of low cable fault prediction efficiency and poor accuracy in the prior art, improves the prediction precision of cable faults and optimizes a cable monitoring mechanism.
In a first aspect, an embodiment of the present invention provides a method for determining a cable parameter fault of a multi-type parametric network model, including:
determining corresponding main attribute parameters and auxiliary attribute parameters according to different cable types;
training different network models based on historical data of different main attribute parameters and auxiliary attribute parameters to obtain a plurality of different training network models, wherein each training network model corresponds to one type of cable;
acquiring cable parameters to be processed, determining main attribute parameters and auxiliary attribute parameters in the cable parameters, and inputting the parameters into a corresponding training network model to output a fault detection result.
Further, the determining the corresponding primary attribute parameter and the secondary attribute parameter according to different cable types includes:
the method comprises the steps that corresponding main attribute parameters and auxiliary attribute parameters are determined according to abnormal fault parameter conditions when different cable types are in fault, the cable types comprise at least one of power cables, rubber sleeve cables, tower crane cables, communication cables, overhead cables, oil-resistant cables, waterproof cables or control cables, the main attribute parameters comprise one, and the auxiliary attribute parameters comprise one or more.
Further, determining corresponding main attribute parameters and auxiliary attribute parameters according to abnormal fault parameter conditions when different cable types have faults, including:
and determining the abnormal fault parameter with the maximum change rate as a main attribute parameter and determining the abnormal fault parameter with the change rate meeting a set threshold value as a secondary attribute parameter aiming at the determined cable type, wherein the parameter types of the main attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
Further, the training of different network models based on the historical data of different primary attribute parameters and secondary attribute parameters to obtain a plurality of different training network models includes:
and respectively inputting historical data of the main attribute parameters and the secondary attribute parameters under non-fault and fault conditions as training samples, and training the network models corresponding to the current main attribute parameters and the secondary attribute parameters to obtain training network models.
Further, the acquiring a cable parameter to be processed, determining a primary attribute parameter and a secondary attribute parameter in the cable parameter, and inputting the parameters to a corresponding training network model to output a fault detection result includes:
acquiring cable parameters to be processed, and determining a corresponding cable type according to the type and the number of the cable parameters;
and inputting the main attribute parameters and the auxiliary attribute parameters in the cable parameters to be processed corresponding to the cable type into the corresponding training network model to output a fault detection result.
In a second aspect, the present embodiment provides a cable parameter fault determining apparatus for a multi-type parametric network model, including:
the parameter determining module is used for determining corresponding main attribute parameters and auxiliary attribute parameters according to different cable types;
the network training module is used for training different network models based on historical data of different main attribute parameters and auxiliary attribute parameters to obtain a plurality of different training network models, wherein each training network model corresponds to one type of cable;
and the fault determining module is used for acquiring the cable parameters to be processed, determining the main attribute parameters and the auxiliary attribute parameters in the cable parameters, and inputting the parameters into the corresponding training network model to output a fault detection result.
Further, the parameter determining module is specifically configured to:
the method comprises the steps that corresponding main attribute parameters and auxiliary attribute parameters are determined according to abnormal fault parameter conditions when different cable types are in fault, the cable types comprise at least one of power cables, rubber sleeve cables, tower crane cables, communication cables, overhead cables, oil-resistant cables, waterproof cables or control cables, the main attribute parameters comprise one, and the auxiliary attribute parameters comprise one or more.
Further, the parameter determining module is specifically configured to:
and determining the abnormal fault parameter with the maximum change rate as a main attribute parameter and determining the abnormal fault parameter with the change rate meeting a set threshold value as a secondary attribute parameter aiming at the determined cable type, wherein the parameter types of the main attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
In a third aspect, the present embodiment provides a cable parameter fault determining apparatus for a multi-type parametric network model, where the apparatus includes: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for cable parameter fault determination for a multi-type parametric network model of any of the above.
In a fourth aspect, embodiments of the present disclosure provide a storage medium storing computer-executable instructions that, when executed by a computer processor, are configured to perform a method of cable parameter fault determination for a multi-type parametric network model as described in any one of the above.
According to the embodiment of the scheme, the corresponding training network model is established based on the main attribute parameters and the auxiliary attribute parameters of different cable types, and the cable fault is detected according to multiple parameters, so that an efficient and reasonable comprehensive judgment mechanism is provided. The problems of low cable fault prediction efficiency and poor accuracy in the prior art are solved, the cable fault prediction precision is improved, and a cable monitoring mechanism is optimized.
Drawings
Fig. 1 is a detailed flowchart of a method for determining a cable parameter fault of a multi-type parameter network model according to the present embodiment;
fig. 2 is a specific flowchart of a cable parameter fault determination method of another multi-type parametric network model according to the present embodiment;
fig. 3 is a schematic structural diagram of a cable parameter fault determination apparatus of a multi-type parametric network model according to the present embodiment;
fig. 4 is a schematic structural diagram of a cable parameter fault determination device of a multi-type parametric network model according to this embodiment.
Detailed Description
The embodiments of the present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad invention. It should be further noted that, for convenience of description, only some structures, not all structures, relating to the embodiments of the present invention are shown in the drawings.
Fig. 1 is a specific flowchart of a method for determining a cable parameter fault of a multi-type parameter network model according to this embodiment, which may be implemented by a cable parameter fault determining apparatus of the multi-type parameter network model implemented in hardware and/or software and integrated in a computer device. Referring to fig. 1, the method may specifically include:
s101, determining corresponding main attribute parameters and auxiliary attribute parameters according to different cable types.
The cable can be divided into a power cable, a rubber sleeve cable, a tower crane cable, a communication cable, an overhead cable, an oil-resistant cable, a waterproof cable or a control cable according to the application, wherein the type of the cable refers to one or more of the cables. The parameter refers to a quantity of which the value can be changed within a certain range, when the quantity is different, different states or performances are reflected, the main attribute parameter value is the abnormal fault parameter with the maximum change rate, and the auxiliary attribute parameter refers to the abnormal fault parameter with the change rate meeting the set threshold value. It is understood that there is only one primary attribute parameter, and there may be one or more secondary attribute parameters.
In one embodiment, various parameters causing cable faults are determined according to the type of the cable, the abnormal fault parameter with the maximum change rate is determined as a main attribute parameter, and the abnormal fault parameter with the change rate meeting a set threshold value is determined as a secondary attribute parameter. Specifically, the threshold is set by technicians according to actual conditions, and if the threshold is set too high, some parameters which may affect the cable fault are ignored, and the cable fault cannot be detected comprehensively from multiple parameters; if the threshold is set too low, some parameters that may not affect the cable fault may be considered, which not only requires more time and cost to monitor and calculate, but also may affect the accuracy of the final cable fault detection result. So the technician needs to set the threshold value reasonably according to the actual situation.
S102, training different network models based on historical data of different main attribute parameters and different auxiliary attribute parameters to obtain a plurality of different training network models, wherein each training network model corresponds to one type of cable.
The training network model refers to a judgment mechanism which can analyze the monitoring parameters to obtain a cable fault result. Specifically, historical data of main attribute parameters and secondary attribute parameters when different cable types have faults are recorded, and the historical data of the different cable types are input into different network models for training, so that different training network models are obtained, wherein each training network model corresponds to one type of cable, and the training network models can evaluate and predict whether the cable has the faults or not according to the comparison between the values of the historical data of the main attribute parameters and the secondary attribute parameters in the models and an actual monitoring value.
In one embodiment, historical data of main attribute parameters and secondary attribute parameters of different cable types is collected and processed, and the historical data can be data sets corresponding to different cable types when faults occur, wherein the data sets comprise historical data sets of the main attribute parameters and the secondary attribute parameters of different cable types and recording time corresponding to the data, and the larger the sample size in the data sets is, the more cable fault information is, the more accurate the constructed network model is. Before the model is constructed, whether each group of historical data has missing values, outliers or abnormal values is checked, the distribution of parameters in each group of historical data is evaluated, and the abnormal values in the historical data are correspondingly processed. Selecting a historical data set for constructing the network model in the data set, and inputting the historical data of the main attribute parameters and the auxiliary attribute parameters when a plurality of groups of different cable types have faults into the network model, thereby obtaining different network models.
Furthermore, after a plurality of network models are obtained, the network models need to be trained to ensure the stability of the network models and to predict different types of cable faults with high quality. Illustratively, the network model may be trained by using a cross-validation method, a data set corresponding to different cables when the cables fail is split into multiple failure subsets, then the above-mentioned model building steps are repeated, and the network model performance is trained multiple times by using the subset data, and one failure subset is selected for evaluating the network model performance and all other subsets are used for building the network model each time iteration. The training method can ensure that data used in network model verification is data which is not used in the model fitting process, then the process is repeated, different subsets are reserved in a training data set for constructing the network model each time until all the subsets are used for network model verification, and therefore a plurality of training network models capable of efficiently and accurately judging faults of different cable types are obtained.
S103, obtaining cable parameters to be processed, determining main attribute parameters and auxiliary attribute parameters in the cable parameters, and inputting the parameters into a corresponding training network model to output a fault detection result.
The cable parameters to be processed refer to actually monitored cable parameters, specifically, the cable type is determined according to the actually monitored cable parameters, then the main attribute parameters and the secondary attribute parameters in the cable parameters are determined according to the change rate of the actual parameters and input into the corresponding training network model, and the training network model analyzes the main attribute parameters and the secondary attribute parameters in the actually monitored parameter data and outputs the prediction result of the cable fault.
In one embodiment, the training network model compares the main attribute parameters and the auxiliary attribute parameters in the actually monitored cable fault parameter data with corresponding data in the self model, and if the main attribute parameters and the auxiliary attribute parameters in the actually monitored cable fault parameter data are continuously the same as the corresponding data in the self model or continuously the same in a preset floating interval in the same preset time period, the cable fault is judged.
Furthermore, this scheme still includes alarm module, if the judged result of training network model output is that the cable has the trouble, then triggers alarm module and generates fault alarm information to with fault information transmission to control end, remind technical staff cable fault, make technical staff in time maintain the cable, avoid having a power failure and major accident for a long time because of cable fault causes.
In conclusion, the network model is constructed and trained by collecting and processing the historical data of the main attribute parameters and the auxiliary attribute quantities of the faults of different cable types, so that a high-efficiency and accurate cable fault analysis model is obtained, the data parameters of different cable types monitored in actual life are brought into the training network model for analysis, and the cable fault result is output. The problems of low cable fault prediction efficiency and poor accuracy in the prior art are solved, the cable fault prediction precision is improved, and a cable monitoring mechanism is optimized.
On the basis of the foregoing embodiments, fig. 2 is a specific flowchart of a cable parameter fault determination method of another multi-type parametric network model provided in the present embodiment. The cable parameter fault determining method of the multi-type parameter network model is an embodiment of the cable parameter fault determining method of the multi-type parameter network model.
Referring to fig. 2, the method for determining the cable parameter fault of the multi-type parametric network model includes:
s201, determining corresponding main attribute parameters and auxiliary attribute parameters according to abnormal fault parameter conditions when different cable types have faults, wherein the cable types comprise at least one of a power cable, a rubber sleeve cable, a tower crane cable, a communication cable, an overhead cable, an oil-resistant cable, a waterproof cable or a control cable, the main attribute parameters comprise one, and the auxiliary attribute parameters comprise one or more.
According to the practical application of the cable, the cable is divided into a power cable, a rubber sleeve cable, a tower crane cable, a communication cable, an overhead cable, an oil-resistant cable, a waterproof cable and a control cable. In one embodiment, the cable type includes at least one of the above cables, a fault parameter corresponding to a fault of the cable is determined according to the cable, and a primary attribute parameter and a secondary attribute parameter corresponding to the cable type are determined according to the specific situation of the fault parameter, wherein the primary attribute parameter includes one, and the secondary attribute parameters include one or more.
S202, aiming at the determined cable type, determining the abnormal fault parameter with the maximum change rate as a main attribute parameter, and determining the abnormal fault parameter with the change rate meeting a set threshold value as a secondary attribute parameter, wherein the parameter types of the main attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
In one embodiment, a cable type is determined, the change rates of a plurality of corresponding cable fault parameters are analyzed, the abnormal fault parameter with the maximum change rate is determined as a main attribute parameter, the abnormal fault parameter with the change rate meeting a set threshold value is determined as a secondary attribute parameter, and the parameter types of the main attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
In another embodiment, the cable type is a power cable, and the temperature sensor is disposed at the cable joint, and the temperature sensor has a plurality of temperature sensing probes uniformly distributed throughout the cable. According to a preset time interval, the data acquisition module acquires temperature data detected by each temperature sensing probe of the temperature sensor and transmits the maximum temperature data to the background database. The preset time interval is set by technicians according to actual conditions, and the maximum temperature data is selected to avoid cable faults caused by overhigh local temperature of the cable. The wind speed collection device and the rainfall collection device are arranged around the environment where the cable is located, the wind speed collection device can be used for monitoring the wind speed of the environment where the cable is located by utilizing a wind speed collection module or a wind speed sensing cup and the like, the rainfall collection device can comprise a box body, a collection metering unit, a drain pipe and the like are used for monitoring the rainfall of the environment where the cable is located, and a data collection module is used for collecting and transmitting the parameter data of the monitored wind speed and the monitored rainfall to a background database. The background database analyzes the change rates of the temperature, the wind speed and the rainfall, the abnormal fault parameter with the maximum change rate is the temperature parameter and is determined as a main attribute parameter, and the change rates of the wind speed parameter and the rainfall parameter exceed a set threshold value, so that the wind speed parameter and the rainfall parameter are determined as auxiliary attribute parameters.
And S203, respectively inputting historical data of the main attribute parameters and the secondary attribute parameters under non-failure and failure conditions as training samples, and training the network models corresponding to the current main attribute parameters and the secondary attribute parameters to obtain training network models.
In another embodiment, a corresponding data set from the time when the cable has not failed can be selected as the training sample, wherein the data set comprises historical data sets of the main attribute parameters and the secondary attribute parameters of different cable types and corresponding recording time of the data. Similarly, before the model is constructed, whether each group of historical data has missing values, outliers or abnormal values is checked, the distribution of parameters in each group of historical data is also evaluated, and the abnormal values in the historical data are correspondingly processed. Selecting a historical data set for constructing the network model in the data set, and inputting the historical data of the main attribute parameters and the auxiliary attribute parameters when a plurality of groups of different cable types have faults into the network model, thereby obtaining different network models.
Furthermore, the network model is trained through historical data sets of the main attribute parameters and the auxiliary attribute parameters of different cable types and the recording time corresponding to the data, so that the stability of the network model is ensured, and high-quality prediction is carried out on different types of cable faults. And continuously and repeatedly bringing cable fault sample data into the network model, verifying an output result, if the output result shows that the fault exists, indicating that the network model still needs to be perfected, and continuously iterating the training network model through repeated training of a large amount of sample data until the cable fault can be efficiently and accurately judged by the training network model. It can be understood that the process of inputting the parameters to be detected into the training network model to analyze and judge the cable fault may also be a training process of the network model.
S204, obtaining cable parameters to be processed, and determining a corresponding cable type according to the type and the number of the cable parameters;
and inputting the main attribute parameters and the secondary attribute parameters in the cable parameters to be processed corresponding to the cable type into the corresponding training network model to output a fault detection result.
The cable parameters to be processed refer to actually monitored cable parameters, specifically, the cable type is determined according to the actually monitored cable parameters, the main attribute parameters and the auxiliary attribute parameters in the cable parameters are determined according to the change rate of the actual parameters and are input into the corresponding training network model, the training network model analyzes the main attribute parameters and the auxiliary attribute parameters in the actually monitored parameter data, and the prediction result of the cable fault is output.
Furthermore, this scheme still includes alarm module, if the judged result of training network model output is that the cable has the trouble, then triggers alarm module and generates fault alarm information to with fault information transmission to control end, remind technical staff cable fault, make technical staff in time maintain the cable, avoid having a power failure and major accident for a long time because of cable fault causes.
The historical data of the main attribute parameters and the secondary attribute parameters during the faults and the non-faults of different cable types are collected and processed and are input into the network model as training samples to be trained, so that the training network model is iterated, and a plurality of training network models capable of efficiently and accurately judging the faults of different cable types are obtained. If the judgment result output by the training network model indicates that the cable has a fault, the alarm module is triggered to generate fault alarm information, the fault information is transmitted to the control end, and technicians are reminded of the cable fault, so that the technicians can maintain the cable in time, and long-time power failure and major accidents caused by the cable fault are avoided.
Fig. 3 is a schematic structural diagram of a cable parameter fault determination apparatus of a multi-type parameter network model according to this embodiment, and referring to fig. 3, the schematic structural diagram of the cable parameter fault determination apparatus of the multi-type parameter network model according to this embodiment specifically includes: the parameter determining module 301, the network training module 302, and the fault determining module 303 may be connected by a bus or other means, and fig. 3 illustrates an example of a connection by a bus.
The parameter determining module 301 is configured to determine corresponding primary attribute parameters and secondary attribute parameters according to different cable types.
In one embodiment, the parameter determining module 301 is specifically configured to: according to the abnormal fault parameter condition when different cable types are in fault, determining corresponding main attribute parameters and secondary attribute parameters, wherein the cable types comprise at least one of a power cable, a rubber sleeve cable, a tower crane cable, a communication cable, an overhead cable, an oil-resistant cable, a waterproof cable or a control cable, the main attribute parameters comprise one, and the secondary attribute parameters comprise one or more.
The network training module 302 is configured to train different network models based on historical data of different primary attribute parameters and secondary attribute parameters to obtain a plurality of different training network models, where each training network model corresponds to one type of cable.
In an embodiment, the network training module 302 is specifically configured to: and training the network model through the historical data sets of the main attribute parameters and the auxiliary attribute parameters of different cable types and the recording time corresponding to the data so as to ensure the stability of the network model and predict the faults of different types of cables in high quality. And continuously and repeatedly introducing cable fault sample data into the network model, verifying an output result, if the output result indicates that the fault exists, indicating that the network model still needs to be perfected, and continuously iterating the training network model through repeated training of a large amount of sample data until the cable fault can be efficiently and accurately judged by the training network model.
The fault determining module 303 is configured to obtain a cable parameter to be processed, determine a primary attribute parameter and a secondary attribute parameter in the cable parameter, and input the parameters to a corresponding training network model to output a fault detection result.
In one embodiment, the parameter determining module 303 is specifically configured to: and aiming at the determined cable type, determining the abnormal fault parameter with the maximum change rate as a primary attribute parameter, and determining the abnormal fault parameter with the change rate meeting a set threshold value as a secondary attribute parameter, wherein the parameter types of the primary attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
The cable parameter fault determining device for the multi-type parameter network model provided by the embodiment of the application can be used for executing the cable parameter fault determining method for the multi-type parameter network model provided by the embodiment, and has corresponding functions and beneficial effects.
Fig. 4 is a schematic structural diagram of a cable parameter fault determination device of a multi-type parametric network model according to this embodiment. As shown in fig. 4, the apparatus includes a processor 401, a memory 402, an input device 403, and an output device 404; the number of the processors 401 in the device may be one or more, and one processor 401 is taken as an example in fig. 4; the processor 401, the storage 402, the input means 403 and the output means 404 in the device may be connected by a bus or other means, as exemplified by a bus in fig. 4. The memory 402, which is a computer-readable storage medium, may be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the message queue-based order processing method in the embodiments of the present invention. The processor 401 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 402, that is, implements the message queue-based order processing method described above. The input device 403 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the apparatus. The output device 404 may include a display device such as a display screen.
Of course, the storage medium containing the computer-executable instructions provided in the embodiments of the present application is not limited to the cable parameter fault determination method of the multi-type parametric network model described above, and may also perform related operations in the cable parameter fault determination method of the multi-type parametric network model provided in any embodiments of the present application.
It should be noted that, in the embodiment of the cable parameter fault determining apparatus of the multi-type parametric network model, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the present invention.
It should be noted that the foregoing is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will appreciate that the embodiments of the present invention are not limited to the specific embodiments described herein, and that various obvious changes, adaptations, and substitutions are possible, without departing from the scope of the embodiments of the present invention. Therefore, although the embodiments of the present invention have been described in more detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and many other equivalent embodiments may be included without departing from the concept of the embodiments of the present invention, and the scope of the embodiments of the present invention is determined by the scope of the appended claims.

Claims (10)

1. The cable parameter fault determining method of the multi-type parameter network model is characterized by comprising the following steps:
determining corresponding main attribute parameters and auxiliary attribute parameters according to different cable types;
training different network models based on historical data of different main attribute parameters and auxiliary attribute parameters to obtain a plurality of different training network models, wherein each training network model corresponds to one type of cable;
acquiring cable parameters to be processed, determining main attribute parameters and auxiliary attribute parameters in the cable parameters, and inputting the parameters into a corresponding training network model to output a fault detection result.
2. The method of claim 1, wherein said determining corresponding primary and secondary attribute parameters according to different cable types comprises:
the method comprises the steps that corresponding main attribute parameters and auxiliary attribute parameters are determined according to abnormal fault parameter conditions when different cable types are in fault, the cable types comprise at least one of power cables, rubber sleeve cables, tower crane cables, communication cables, overhead cables, oil-resistant cables, waterproof cables or control cables, the main attribute parameters comprise one, and the auxiliary attribute parameters comprise one or more.
3. The method of claim 2, wherein determining the corresponding primary attribute parameters and secondary attribute parameters according to abnormal fault parameter conditions at the time of faults of different cable types comprises:
and aiming at the determined cable type, determining the abnormal fault parameter with the maximum change rate as a primary attribute parameter, and determining the abnormal fault parameter with the change rate meeting a set threshold value as a secondary attribute parameter, wherein the parameter types of the primary attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
4. The method of claim 1, wherein the training of different network models based on historical data of different primary and secondary attribute parameters to obtain multiple different training network models comprises:
and respectively inputting historical data of the main attribute parameters and the secondary attribute parameters under non-fault and fault conditions as training samples, and training the network models corresponding to the current main attribute parameters and the secondary attribute parameters to obtain training network models.
5. The method for determining cable parameter faults of a multi-type parameter network model according to claim 1, wherein the obtaining of cable parameters to be processed, the determination of primary attribute parameters and secondary attribute parameters in the cable parameters, and the input of the primary attribute parameters and the secondary attribute parameters to a corresponding training network model to output fault detection results comprises:
acquiring cable parameters to be processed, and determining a corresponding cable type according to the type and the number of the cable parameters;
and inputting the main attribute parameters and the secondary attribute parameters in the cable parameters to be processed corresponding to the cable type into the corresponding training network model to output a fault detection result.
6. Cable parameter fault determination device of polymorphic type parameter network model, its characterized in that includes:
the parameter determining module is used for determining corresponding main attribute parameters and auxiliary attribute parameters according to different cable types;
the network training module is used for training different network models based on historical data of different main attribute parameters and auxiliary attribute parameters to obtain a plurality of different training network models, wherein each training network model corresponds to one type of cable;
and the fault determining module is used for acquiring the cable parameters to be processed, determining the main attribute parameters and the auxiliary attribute parameters in the cable parameters, and inputting the parameters into the corresponding training network model to output a fault detection result.
7. The apparatus of claim 6, wherein the parameter determination module is specifically configured to:
the method comprises the steps that corresponding main attribute parameters and auxiliary attribute parameters are determined according to abnormal fault parameter conditions when different cable types are in fault, the cable types comprise at least one of power cables, rubber sleeve cables, tower crane cables, communication cables, overhead cables, oil-resistant cables, waterproof cables or control cables, the main attribute parameters comprise one, and the auxiliary attribute parameters comprise one or more.
8. The apparatus of claim 7, wherein the parameter determination module is specifically configured to:
and determining the abnormal fault parameter with the maximum change rate as a main attribute parameter and determining the abnormal fault parameter with the change rate meeting a set threshold value as a secondary attribute parameter aiming at the determined cable type, wherein the parameter types of the main attribute parameter and the secondary attribute parameter comprise at least one of temperature, deformation, humidity, ambient wind speed, ambient rainfall or data transmission rate.
9. A cable parameter fault determination device for a multi-type parametric network model, the device comprising: one or more processors; storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the cable parameter failure determination method of the multi-type parametric network model of any of claims 1-5.
10. A storage medium storing computer-executable instructions for performing a cable parameter failure determination method of a multi-type parametric network model as recited in any of claims 1-5 when executed by a computer processor.
CN202210095663.0A 2022-01-26 2022-01-26 Cable parameter fault determination method and device for multi-type parameter network model Pending CN114638380A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210095663.0A CN114638380A (en) 2022-01-26 2022-01-26 Cable parameter fault determination method and device for multi-type parameter network model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210095663.0A CN114638380A (en) 2022-01-26 2022-01-26 Cable parameter fault determination method and device for multi-type parameter network model

Publications (1)

Publication Number Publication Date
CN114638380A true CN114638380A (en) 2022-06-17

Family

ID=81945907

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210095663.0A Pending CN114638380A (en) 2022-01-26 2022-01-26 Cable parameter fault determination method and device for multi-type parameter network model

Country Status (1)

Country Link
CN (1) CN114638380A (en)

Similar Documents

Publication Publication Date Title
CN108375715B (en) Power distribution network line fault risk day prediction method and system
CN111459700B (en) Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium
KR20180108446A (en) System and method for management of ict infra
KR102427205B1 (en) Apparatus and method for generating training data of artificial intelligence model
CN108376184A (en) A kind of method and system of bridge health monitoring
CN117060409B (en) Automatic detection and analysis method and system for power line running state
CN114255784A (en) Substation equipment fault diagnosis method based on voiceprint recognition and related device
KR20190069213A (en) Apparatus and method for operation and management of distributed photovoltaic energy generator based on remote monitoring
CN113763667A (en) Fire early warning and state monitoring device and method based on 5G edge calculation
CN110941558B (en) Intelligent office remote operation and maintenance method and system
CN111627199A (en) Hydropower station dam safety monitoring system and monitoring method
CN115453254A (en) Power quality monitoring method and system based on special transformer acquisition terminal
CN112580858A (en) Equipment parameter prediction analysis method and system
CN114154722A (en) Power distribution station management method, system and device based on digital twin technology
CN117639251A (en) Intelligent online monitoring system for high-voltage switch cabinet
CN114895163A (en) Cable inspection positioning device and method based on cable insulation performance
CN112650068B (en) Household fault detection method and device based on intelligent current sensor
CN117110794A (en) Intelligent diagnosis system and method for cable faults
CN116823220A (en) Cable running state monitoring platform and equipment
CN114638380A (en) Cable parameter fault determination method and device for multi-type parameter network model
CN112885049B (en) Intelligent cable early warning system, method and device based on operation data
CN102497025B (en) Remote state monitoring method for automatic sectionalizer
CN114200334A (en) Storage battery early warning method and device, vehicle and medium
CN114279492A (en) Method and device for determining cable fault information based on different fault parameter records
CN112363432A (en) Monitoring system and monitoring method for hydropower station auxiliary equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination