CN116861797A - Tunnel cable residual life prediction method and device based on machine learning - Google Patents
Tunnel cable residual life prediction method and device based on machine learning Download PDFInfo
- Publication number
- CN116861797A CN116861797A CN202311100340.7A CN202311100340A CN116861797A CN 116861797 A CN116861797 A CN 116861797A CN 202311100340 A CN202311100340 A CN 202311100340A CN 116861797 A CN116861797 A CN 116861797A
- Authority
- CN
- China
- Prior art keywords
- tunnel cable
- monitoring period
- monitoring
- expressed
- tunnel
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000010801 machine learning Methods 0.000 title claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 199
- 238000004458 analytical method Methods 0.000 claims description 33
- 230000005540 biological transmission Effects 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 31
- 230000008859 change Effects 0.000 claims description 23
- 238000009413 insulation Methods 0.000 claims description 22
- 239000011810 insulating material Substances 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 16
- 239000012774 insulation material Substances 0.000 claims description 9
- 238000012512 characterization method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- -1 period Chemical class 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 9
- 238000005457 optimization Methods 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000003993 interaction Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000012407 engineering method Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
-
- 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/16—Cables, cable trees or wire harnesses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention relates to the technical field of cable life prediction, and particularly discloses a method and a device for predicting the residual life of a tunnel cable based on machine learning, wherein the method comprises the following steps: according to the invention, the residual life of the tunnel cable is predicted through machine learning, and complex relations between the life of the cable and various features can be learned from a large amount of historical data, so that more accurate prediction is realized, the interaction between the nonlinear relation of the life of the cable and the features can be better captured, meanwhile, through monitoring the loss degree of each part of the cable, maintenance optimization and decision support are carried out by utilizing the loss degree results of different parts, the loss caused by cable faults is avoided, the maintenance efficiency and the cost benefit are improved, and the reliability and the stability of the power network are maintained.
Description
Technical Field
The invention relates to the technical field of cable life prediction, in particular to a method and a device for predicting the residual life of a tunnel cable based on machine learning.
Background
Cables are an important component widely used in the modern industry and carry critical tasks such as power and data transmission. However, over time, the cable may be subjected to various factors, such as load changes, temperature changes, mechanical stresses, etc., causing it to age and fail. These cable failures may lead to increased downtime, production costs, and even risk to personal safety. Thus, accurate prediction of cable life is one of the key tasks for safe production.
Today, there are also some drawbacks to the cable life prediction, specifically in the following several aspects:
(1) The current prediction of the service life of the cable lacks precision, on one hand, the service life of the cable is estimated by too relying on experience rules and industry experience and considering the service time, working conditions, environmental factors and the like of the cable, individuation and accuracy are lacking, the physical characteristics and influence factors of the cable need to be understood deeply, the influence of subjective factors is easy, on the other hand, the construction of a cable service life prediction model is too simple, the application condition is relatively narrow, a complex cable system is not accurate enough to process, only linear or simple nonlinear relations can be processed, and high-order or interactive effects between the service life of the cable and the influence factors can not be captured;
(2) The current prediction to cable life is relative to the general, do not specifically have the loss to each position of cable, can't accurately reflect each factor that influences cable life, for example the monitoring of the power transmission performance and the partial discharge phenomenon of cable, and power transmission performance is the important sign that reflects cable service conditions, and the partial discharge phenomenon can seriously influence the life of cable, neglects the monitoring to power transmission performance and the partial discharge phenomenon of cable, is unfavorable for follow-up fault detection and prevention, leads to the transmission energy consumption to increase, causes the waste of resource to easily initiate the incident, influence the reliability and the stability of power network.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a tunnel cable residual life prediction method and device based on machine learning, which can effectively solve the problems related to the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the first aspect of the invention provides a machine learning-based tunnel cable residual life prediction method, which comprises the following steps:
step one, carrying out statistics and division on tunnel cables: carrying out statistics division on the target tunnel cable, and marking the target tunnel cable as each tunnel cable segment;
step two, monitoring the power transmission performance of the tunnel cable: monitoring the power transmission performance of each tunnel cable section, and calculating the power transmission performance loss degree value of each tunnel cable section in each monitoring period;
Step three, monitoring the performance of the insulating material of the tunnel cable: monitoring the performance of the insulating material of each tunnel cable section, and calculating the loss degree value of the performance of the insulating material of each tunnel cable section in each monitoring period;
Fourth, the synthesis characteristic combination construction analysis: collecting information data of each tunnel cable section, performing characteristic combination analysis, and comprehensively constructing each tunnel cable section in each tunnel cable sectionMonitoring combined eigenvalues of a cycle;
Fifthly, predicting the residual life of the cable: calculating the index of the characterization change degree of the target tunnel cable in each monitoring period, constructing a specified reference prediction curve model of the target tunnel cable, and predicting the residual life of the cable.
As a further method, the monitoring of the power transmission performance of each tunnel cable segment includes the following specific analysis processes: dividing the life cycle of the target tunnel cable at set intervals, marking the life cycle as each monitoring cycle, dividing each monitoring cycle by set number to obtain each monitoring time point, and monitoring to obtain the resistance of each tunnel cable section at each monitoring time point of each monitoring cycleObtaining rated specification resistance of target tunnel cable from cable information base>。
Comprehensively calculating the resistance fluctuation degree of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Expressed as a set tolerance resistance, +.>Number denoted as each tunnel cable segment +.>,/>Expressed as total number of target monitoring segments, +.>Indicated as the number of each monitoring period,,/>expressed as total number of monitoring cycles>Number expressed as each monitoring time point, +.>,/>Expressed as the total number of monitoring time points.
Monitoring to obtain the electric energy transmission loss of each tunnel cable section at each monitoring time point of each monitoring periodComprehensively calculating the power loss fluctuation degree of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Indicated as set allowable power loss;
monitoring the electric signals of the output end and the input end of each tunnel cable section in each monitoring period to obtain electric signal waveform diagrams of the output end and the input end of each tunnel cable section in each monitoring period, and performing overlapping comparison on the electric signal waveform diagrams of the output end and the input end to obtain overlapping signals of each tunnel cable section in each monitoring periodWaveform lengthOutput end signal waveform length ∈>And input signal waveform length ∈ ->And obtaining the reference operation theoretical signal waveform length of the target tunnel cable from the cable information base>;
Comprehensively calculating the signal fluctuation degree of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Represented as the allowable deviation waveform length between the set output and input.
As a further method, the power transmission performance loss degree value of each tunnel cable section in each monitoring period is calculated according to the following calculation formula:
wherein->Expressed as natural constant>、/>And->The set resistance fluctuation degree, the set power loss fluctuation degree and the set signal fluctuation degree are respectively expressed as the duty ratio weights.
As a further method, the performance of the insulating material of each tunnel cable section is monitored, and the specific analysis process is as follows: monitoring partial discharge phenomena of each tunnel cable section in each monitoring period, and counting partial discharge frequency of each tunnel cable section in each monitoring periodAnd the pulse current intensity of each partial discharge is monitored, marked +.>Obtaining rated pulse input current of target tunnel cable from cable information base>。
Comprehensively calculating the partial discharge hazard degree value of the insulating material of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Expressed as a set partial discharge frequency limit value,/, for>Number expressed as partial discharge of each time, +.>,/>Expressed as the total number of partial discharges during the monitoring period.
To a set number ofArranging insulation screening points on the surface of the insulation layer of each tunnel cable section, and monitoring and extracting the thickness of the insulation layer of each insulation screening point of each tunnel cable section in each monitoring periodObtaining insulation layer specification thickness of target tunnel cable from cable information base>Further, the thickness loss degree of the insulating layer of each tunnel cable section in each monitoring period is calculated>The calculation formula is as follows:
wherein->Expressed as a set allowable deviation insulating layer thickness, < >>Number expressed as each insulation screening point, < >>,/>Expressed as the total number of insulation screening points.
As a further method, the calculation formula of the insulation material performance loss degree value of each tunnel cable section in each monitoring period is as follows:
wherein->And->Respectively denoted asThe set proportion weight of the local discharge hazard degree of the insulating material and the thickness loss degree of the insulating layer is calculated.
As a further method, the information data of each tunnel cable section is collected, and the specific analysis process is as follows: environmental data of each tunnel cable segment in each monitoring period is collected, wherein the environmental data comprises environmental temperature, tunnel cable load current and voltage, environmental vibration stress and vibration frequency.
As a further method, the combined characteristic value of the comprehensively constructed target tunnel cable comprises the following specific analysis processes: according to the temperature, load current and voltage, environmental vibration stress and vibration frequency of each tunnel cable section in each monitoring period, carrying out characteristic combination analysis, sequentially constructing combined characteristic values of each tunnel cable section in each monitoring period, and respectively marking as、/>、/>、/>、/>、/>And->。
Thermal-vibration stress characteristicsThe specific expression is: />Wherein->And->Expressed as maximum temperature and maximum vibration stress of each tunnel cable segment in each monitoring period,/respectively>And->The average temperature and the average vibration stress of each tunnel cable section in each monitoring period are respectively expressed;
thermo-electric-vibration stress characteristicsThe specific expression is: />WhereinExpressed as maximum current of each tunnel cable segment in each monitoring period,/for each monitoring period>Represented as the average current of each tunnel cable segment over each monitoring period;
thermo-electric-vibration characteristicsThe specific expression is: />Wherein->Expressed as the vibration frequency of each tunnel cable segment in each monitoring period;
frequency domain analysis features of vibration dataThe specific expression is: />Wherein->Represented as +.f. in the frequency domain signal for each tunnel cable segment during each monitoring period>Complex values of the individual frequency components, +.>,/>Expressed as the total number of signal sampling points;
temperature difference-time-frequency characteristicsThe specific expression is: />Wherein->And->Expressed as minimum temperature and vibration period of each tunnel cable segment in each monitoring period, +.>Expressed as the age of the target tunnel cable;
current-voltage-vibration characteristicsThe specific expression is: />Wherein->Expressed as the maximum voltage of each tunnel cable segment during each monitoring period;
current-voltage-temperature characteristicsThe specific expression is: />;
Constructing a correlation matrix to perform feature screening, wherein the screened combined sub-feature markers are as followsComprehensively constructing combined characteristic values of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Numbers expressed as sub-features of each combination, +.>,/>Expressed as the total number of combined sub-features.
As a further method, the calculating the characterization change degree index of the target tunnel cable in each monitoring period comprises the following specific analysis processes: comprehensively calculating the characterization change degree index of the target tunnel cable in each monitoring period according to the power transmission performance loss degree value, the insulation material performance loss degree value and the combined characteristic value of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Expressed as a set reference combined characteristic value, +.>、/>And->The power transmission performance loss degree value, the insulation material performance loss degree value and the duty ratio weight of the combination characteristic value are respectively set.
As a further method, the cable residual life is predicted, and the specific analysis process is as follows: according to the representation change degree index of each monitoring period of the target tunnel cable, matching the representation change degree index with a reference prediction curve model corresponding to each set representation change degree index interval to obtain a reference prediction curve model corresponding to each monitoring period of the target tunnel cable, constructing a designated reference prediction curve model of the target tunnel cable through dynamic fitting, carrying out mean value processing on the representation change degree index of each monitoring period of the target tunnel cable to obtain a representation change degree index mean value of the target tunnel cable, and carrying out positioning extraction on the estimated residual service life value of the target tunnel cable to output and display.
The second aspect of the present invention provides a machine learning-based device for predicting remaining life of a tunnel cable, comprising: a processor, a memory and a network interface connected with the processor; the network interface is connected with a nonvolatile memory in the server; the processor, when running, retrieves the computer program from the non-volatile memory via the network interface and runs the computer program via the memory to perform the method of any of the above.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
(1) According to the method and the device for predicting the residual life of the tunnel cable based on machine learning, the complex relation between the life of the cable and various features can be learned from a large amount of historical data, so that more accurate prediction is realized, and compared with the traditional prediction technology based on an empirical rule or statistical method, the method based on machine learning can better capture the nonlinear relation of the life of the cable and interaction between the features;
(2) According to the method, the dynamic time point data are generated, the life cycle of each cable is taken as a reference to divide each monitoring period, the dynamic data information of the cable in each monitoring period is collected, the influence of uncertainty and time dependence of the service life of the cable on a cable service life prediction result can be effectively avoided by using the dynamic time point data generation method, so that the data are more close to the actual situation, meanwhile, the collected data are subjected to data cleaning and abnormal value processing, the quality and the credibility of a data set are guaranteed, and the stability and the accuracy of a prediction model are improved;
(3) According to the invention, through monitoring the power transmission performance and the partial discharge phenomenon of the cable, not only is the prediction of the service life of the tunnel cable realized, but also maintenance optimization and decision support can be carried out by utilizing the loss degree results of different parts, and the loss caused by cable faults is avoided, maintenance planning and resource allocation are optimized, so that the maintenance efficiency and cost benefit are improved, and the reliability and stability of the power network are maintained;
(4) According to the invention, new characteristics are created through multi-source data characteristic fusion, including characteristic information such as temperature, vibration, current and voltage, and the multi-source data characteristics are fused into the prediction model by utilizing a characteristic engineering method, so that more comprehensive and multi-dimensional information is provided, the complexity and expressive force of the prediction model are enhanced, and the accuracy of a prediction result is improved.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings;
FIG. 1 is a flow chart of the method steps of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making creative efforts based on the embodiments of the present invention are included in the protection scope of the present invention.
Referring to fig. 1, a first aspect of the present invention provides a method for predicting a remaining life of a tunnel cable based on machine learning, including:
step one, carrying out statistics and division on tunnel cables: carrying out statistics division on the target tunnel cable, and marking the target tunnel cable as each tunnel cable segment;
step two, monitoring the power transmission performance of the tunnel cable: and monitoring the power transmission performance of each tunnel cable section, and calculating the power transmission performance loss degree value of each tunnel cable section in each monitoring period.
Specifically, the monitoring of the power transmission performance of each tunnel cable section includes the following specific analysis processes: dividing the life cycle of the target tunnel cable at set intervals, marking the life cycle as each monitoring cycle, dividing each monitoring cycle by set number to obtain each monitoring time point, and monitoring to obtain the resistance of each tunnel cable section at each monitoring time point of each monitoring cycleObtaining rated specification resistance of target tunnel cable from cable information base>。
In a specific embodiment, through dynamic time point data generation, each monitoring period is divided by taking the life period of each cable as a reference, dynamic data information of the cable in each monitoring period is collected, and the influence of uncertainty and time dependence of the service life of the cable on a cable service life prediction result can be effectively avoided by utilizing the dynamic time point data generation method, so that the data is more close to the actual situation, and meanwhile, the collected data is subjected to data cleaning and abnormal value processing, and the quality and the reliability of a data set are ensured, so that the stability and the accuracy of a prediction model are improved.
Comprehensively calculating the resistance fluctuation degree of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Expressed as a set tolerance resistance, +.>Number denoted as each tunnel cable segment +.>,/>Expressed as total number of target monitoring segments, +.>Indicated as the number of each monitoring period,,/>expressed as total number of monitoring cycles>Number expressed as each monitoring time point, +.>,/>Expressed as the total number of monitoring time points.
Monitoring to obtain the electric energy transmission loss of each tunnel cable section at each monitoring time point of each monitoring periodComprehensively calculating the power loss fluctuation degree of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Indicated as set allowable power loss;
it should be explained that the power transmission loss value is calculated by subtracting the output power from the input power of each tunnel cable section, and the calculation formula is as follows:wherein->And->Respectively expressed as input voltage and output voltage of each tunnel cable segment at each monitoring time point of each monitoring period, < >>And->Respectively expressed as input current and output current of each tunnel cable segment at each monitoring time point of each monitoring period, < >>Expressed as a set monitoring duration。
Monitoring the electric signals of the output end and the input end of each tunnel cable section in each monitoring period to obtain electric signal waveform diagrams of the output end and the input end of each tunnel cable section in each monitoring period, and performing overlapping comparison on the electric signal waveform diagrams of the output end and the input end to obtain the overlapping signal waveform length of each tunnel cable section in each monitoring periodOutput end signal waveform length ∈>And input signal waveform length ∈ ->And obtaining the reference operation theoretical signal waveform length of the target tunnel cable from the cable information base>;
Comprehensively calculating the signal fluctuation degree of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Represented as the allowable deviation waveform length between the set output and input.
Further, the calculation formula of the power transmission performance loss degree value of each tunnel cable section in each monitoring period is as follows:
wherein->Representation ofIs natural constant (18)>、/>And->The set resistance fluctuation degree, the set power loss fluctuation degree and the set signal fluctuation degree are respectively expressed as the duty ratio weights.
Step three, monitoring the performance of the insulating material of the tunnel cable: and monitoring the performance of the insulating material of each tunnel cable section, and calculating the loss degree value of the performance of the insulating material of each tunnel cable section in each monitoring period.
Specifically, the performance of the insulating material of each tunnel cable section is monitored, and the specific analysis process is as follows: monitoring partial discharge phenomena of each tunnel cable section in each monitoring period, and counting partial discharge frequency of each tunnel cable section in each monitoring periodAnd the pulse current intensity of each partial discharge is monitored, marked +.>Obtaining rated pulse input current of target tunnel cable from cable information base>;
Comprehensively calculating the partial discharge hazard degree value of the insulating material of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Expressed as a set partial discharge frequency limit value,/, for>Number expressed as partial discharge of each time, +.>,/>Expressed as the total number of partial discharges during the monitoring period.
Arranging insulation screening points on the surface of the insulation layer of each tunnel cable section in a set number, and monitoring and extracting the thickness of the insulation layer of each insulation screening point of each tunnel cable section in each monitoring periodObtaining insulation layer specification thickness of target tunnel cable from cable information base>Further, the thickness loss degree of the insulating layer of each tunnel cable section in each monitoring period is calculated>The calculation formula is as follows:
wherein->Expressed as a set allowable deviation insulating layer thickness, < >>Number expressed as each insulation screening point, < >>,/>Expressed as the total number of insulation screening points.
Further, the calculation formula of the insulation material performance loss degree value of each tunnel cable section in each monitoring period is as follows:
wherein->And->The local discharge hazard degree of the insulating material and the thickness loss degree of the insulating layer are respectively expressed as the duty ratio weight of the set local discharge hazard degree of the insulating material and the thickness loss degree of the insulating layer.
In a specific embodiment, through monitoring of the power transmission performance and the partial discharge phenomenon of the cable, not only is prediction of the service life of the tunnel cable realized, but also maintenance optimization and decision support can be performed by using the loss degree results of different positions, loss caused by cable faults is avoided by early warning and optimizing a maintenance strategy, maintenance planning and resource allocation are optimized, maintenance efficiency and cost effectiveness are improved, and reliability and stability of a power network are maintained.
Fourth, the synthesis characteristic combination construction analysis: and collecting information data of each tunnel cable section, so as to perform characteristic combination analysis, and comprehensively constructing combined characteristic values of each tunnel cable section in each monitoring period.
Specifically, the information data of each tunnel cable section is collected, and the specific analysis process is as follows: and collecting environmental data of each tunnel cable section in each monitoring period, wherein the environmental data comprises environmental temperature, tunnel cable load current and voltage, environmental vibration stress and vibration frequency.
Further, the specific analysis process of the combined characteristic value of the comprehensively constructed target tunnel cable is as follows: according to the temperature, load current and voltage, environmental vibration stress and vibration frequency of each tunnel cable section in each monitoring period, carrying out characteristic combination analysis, sequentially constructing combined characteristic values of each tunnel cable section in each monitoring period, and respectively marking as、/>、/>、、/>、/>And->;
Thermal-vibration stress characteristicsThe specific expression is: />Wherein->And->Expressed as maximum temperature and maximum vibration stress of each tunnel cable segment in each monitoring period,/respectively>And->The average temperature and the average vibration stress of each tunnel cable section in each monitoring period are respectively expressed;
thermo-electric-vibration stress characteristicsThe specific expression is: />WhereinExpressed as maximum current of each tunnel cable segment in each monitoring period,/for each monitoring period>Represented as the average current of each tunnel cable segment over each monitoring period;
thermo-electric-vibration characteristicsThe specific expression is: />Wherein->Expressed as the vibration frequency of each tunnel cable segment in each monitoring period;
frequency domain analysis features of vibration dataThe specific expression is: />Wherein->Represented as +.f. in the frequency domain signal for each tunnel cable segment during each monitoring period>Complex values of the individual frequency components, +.>,/>Expressed as the total number of signal sampling points;
it should be explained that the specific analysis process of the frequency domain analysis characteristics of the vibration data is as follows: and carrying out Fourier transform on the vibration signals obtained by monitoring to extract characteristics, wherein the calculation formula is as follows:
wherein->Expressed as +.f. in each tunnel cable segment in each monitoring period time domain signal>Values of the individual sampling points +.>Expressed as natural constants;
the energy of the frequency domain signal is calculated to represent the energy distribution of the signal at different frequencies, and the intensity of the signal at the frequency is described by the square sum of the frequency spectrum amplitude, wherein the calculation formula is as follows:
wherein->Represented as frequency domain signal +.>Real part of->Represented as frequency domain signal +.>Is the imaginary part of (2);
temperature difference-time-frequency characteristicsThe specific expression is: />Wherein->And->Expressed as minimum temperature and vibration period of each tunnel cable segment in each monitoring period, +.>Expressed as the age of the target tunnel cable;
current-voltage-vibration characteristicsThe specific expression is: />Wherein->Expressed as the maximum voltage of each tunnel cable segment during each monitoring period;
current-voltage-temperature characteristicsThe specific expression is: />。
In a specific embodiment, new features are created through multi-source data feature fusion, including temperature, vibration, current, voltage and other feature information, and the multi-source data features are fused into a prediction model by utilizing a feature engineering method, so that more comprehensive and multi-dimensional information is provided, the complexity and expressive force of the prediction model are enhanced, and the accuracy of a prediction result is improved.
Constructing a correlation matrix to perform feature screening, wherein the screened combined sub-feature markers are as followsComprehensively constructing combined characteristic values of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Numbers expressed as sub-features of each combination, +.>,/>Expressed as the total number of combined sub-features.
It should be explained that, the influence characteristics are subjected to correlation screening, and the specific analysis process is as follows: computing correlations for all features pairwiseObtaining a correlation coefficient matrix, deleting one of the characteristics with too high correlation among the characteristics, deleting the characteristic with too low correlation between the characteristics and the loss degree value, wherein a calculation formula of the correlation coefficient is as follows:
wherein X and Z are represented as respective influence characteristic values, and (2)>And->Expressed as standard deviation of X and Z, respectively, < >>Expressed as desired value +.>And->Represented as the mean of X and Z, respectively.
Fifthly, predicting the residual life of the cable: calculating the characterization change degree index of the target tunnel cable in each monitoring period, constructing a specified reference prediction curve model of the target tunnel cable, and predicting the residual life of the cable;
specifically, the calculating the index of the characterization change degree of the target tunnel cable in each monitoring period includes the following specific analysis processes: comprehensively calculating the characterization change degree index of the target tunnel cable in each monitoring period according to the power transmission performance loss degree value and the insulation material performance loss degree value of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Expressed as a set reference combined characteristic value, +.>、/>And->The power transmission performance loss degree value, the insulation material performance loss degree value and the duty ratio weight of the combination characteristic value are respectively set.
Further, the residual life of the cable is predicted, and the specific analysis process is as follows: according to the representation change degree index of each monitoring period of the target tunnel cable, matching the representation change degree index with a reference prediction curve model corresponding to each set representation change degree index interval to obtain a reference prediction curve model corresponding to each monitoring period of the target tunnel cable, constructing a designated reference prediction curve model of the target tunnel cable through dynamic fitting, carrying out mean value processing on the representation change degree index of each monitoring period of the target tunnel cable to obtain a representation change degree index mean value of the target tunnel cable, and carrying out positioning extraction on the estimated residual service life value of the target tunnel cable to output and display.
It should be explained that the dynamic fitting of the prediction curve adopts a least square method, so that a plurality of curves are fitted into one curve, thereby being beneficial to the noise reduction treatment of data, reducing the interference of abnormal data on a final result and improving the accuracy of prediction.
The second aspect of the present invention provides a machine learning-based device for predicting remaining life of a tunnel cable, comprising: a processor, a memory and a network interface connected with the processor; the network interface is connected with a nonvolatile memory in the server; the processor, when running, retrieves the computer program from the non-volatile memory via the network interface and runs the computer program via the memory to perform the method of any of the above.
The invention provides a method and a device for predicting the residual life of a tunnel cable based on machine learning, which carefully consider the selection and optimization of a machine learning algorithm, select a proper regression algorithm and an integrated learning algorithm, and perform parameter tuning, so that a prediction model can obtain good prediction performance under the condition of complex data, and can learn the mode and rule of the life of the tunnel cable from a large amount of data by utilizing the automation and intelligent characteristics of the machine learning algorithm, so that the model can be adaptively updated and optimized, adapt to new data and changing conditions, and improve the accuracy and stability of prediction.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.
Claims (7)
1. The machine learning-based tunnel cable residual life prediction method is characterized by comprising the following steps of:
step one, carrying out statistics and division on tunnel cables: carrying out statistics division on the target tunnel cable, and marking the target tunnel cable as each tunnel cable segment;
step two, monitoring the power transmission performance of the tunnel cable: monitoring the power transmission performance of each tunnel cable section, and calculating the power transmission performance loss degree value of each tunnel cable section in each monitoring period;
Step three, monitoring the performance of the insulating material of the tunnel cable: monitoring the performance of the insulating material of each tunnel cable section, and calculating the loss degree value of the performance of the insulating material of each tunnel cable section in each monitoring period;
Fourth, the synthesis characteristic combination construction analysis: collecting information data of each tunnel cable section, performing feature combination analysis, and comprehensively constructing combined feature values of each tunnel cable section in each monitoring period;
Fifthly, predicting the residual life of the cable: comprehensively calculating the characterization change degree index of the target tunnel cable in each monitoring period according to the power transmission performance loss degree value, the insulation material performance loss degree value and the combined characteristic value of each tunnel cable section in each monitoring period, constructing a specified reference prediction curve model of the target tunnel cable, and predicting the residual life of the cable;
the power transmission performance loss degree value of each tunnel cable section in each monitoring periodThe calculation formula of (2) is as follows:
wherein->Expressed as natural constant>、/>And->Respectively expressed as the set duty weight of the resistance fluctuation degree, the electric energy loss fluctuation degree and the signal fluctuation degree, < ->Indicating the extent of resistance variation of each tunnel cable segment during each monitoring period,/>Indicating the extent of variation of the power loss of each tunnel cable section during each monitoring period, < >>The signal fluctuation degree of each tunnel cable section in each monitoring period is represented;
the insulation material performance loss degree value of each tunnel cable section in each monitoring periodThe calculation formula of (2) is as follows:
wherein->And->Respectively expressed as the set proportion weight of the local discharge hazard degree of the insulating material and the insulating layer thickness loss degree, < ->Indicating the partial discharge hazard level value of the insulating material of each tunnel cable section in each monitoring period, +.>Indicating the degree of insulation thickness loss of the tunnel cable section during each monitoring period, < >>Expressed as natural constants;
the combined characteristic value of each tunnel cable section in each monitoring periodThe calculation formula is as follows: />Wherein->Numbers expressed as sub-features of each combination, +.>,/>Expressed as total number of combined sub-features, +.>Carrying out characteristic combination analysis according to the information data of each tunnel cable segment, sequentially constructing combined characteristic values of each tunnel cable segment in each monitoring period, constructing a correlation matrix for characteristic screening, and carrying out combined sub-characteristic marking after screening;
the calculation formula of the characterization change degree index of the target tunnel cable in each monitoring period is as follows:
wherein->Expressed as a set reference combined characteristic value, +.>、/>And->Respectively expressed as the set power transmission performance loss degree value, the insulation material performance loss degree value and the duty ratio weight of the combination characteristic value>Expressed as a natural constant.
2. The machine learning-based tunnel cable remaining life prediction method of claim 1, wherein: the specific analysis process of the monitoring of the power transmission performance of each tunnel cable section comprises the following steps:
dividing the life cycle of the target tunnel cable at set intervals, marking the life cycle as each monitoring cycle, dividing each monitoring cycle by set number to obtain each monitoring time point, and monitoring to obtain the resistance of each tunnel cable section at each monitoring time point of each monitoring cycleObtaining rated specification resistance of target tunnel cable from cable information base>The method comprises the steps of carrying out a first treatment on the surface of the Comprehensively calculating the resistance variation degree of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Expressed as a set tolerance resistance, +.>Number denoted as each tunnel cable segment +.>,/>Expressed as total number of target monitoring segments, +.>Indicated as the number of each monitoring period,,/>expressed as total number of monitoring cycles>Number expressed as each monitoring time point, +.>,/>Expressed as the total number of monitoring time points;
monitoring to obtain the electric energy transmission loss of each tunnel cable section at each monitoring time point of each monitoring periodComprehensively calculating the power loss fluctuation degree of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Indicated as set allowable power loss;
monitoring the electric signals of the output end and the input end of each tunnel cable section in each monitoring period to obtain electric signal waveform diagrams of the output end and the input end of each tunnel cable section in each monitoring period, and performing overlapping comparison on the electric signal waveform diagrams of the output end and the input end to obtain the overlapping signal waveform length of each tunnel cable section in each monitoring periodOutput end signal waveform length ∈>And input signal waveform length ∈ ->And obtaining the reference operation theoretical signal waveform length of the target tunnel cable from the cable information base>;
Comprehensively calculating the signal fluctuation degree of each tunnel cable section in each monitoring periodThe calculation formula is as follows:
wherein->Represented as the allowable deviation waveform length between the set output and input.
3. The machine learning-based tunnel cable remaining life prediction method of claim 1, wherein: the specific analysis process of the monitoring of the performance of the insulating material of each tunnel cable section comprises the following steps:
monitoring partial discharge phenomena of each tunnel cable section in each monitoring period, and counting partial discharge frequency of each tunnel cable section in each monitoring periodAnd the pulse current intensity of each partial discharge is monitored, marked +.>Obtaining rated pulse input current of target tunnel cable from cable information base>The method comprises the steps of carrying out a first treatment on the surface of the Comprehensively calculating the partial discharge hazard degree value +.f of the insulating material of each tunnel cable section in each monitoring period>The calculation formula is as follows:
wherein->Expressed as a set partial discharge frequency limit value,/, for>Number expressed as partial discharge of each time, +.>,/>Expressed as the total number of partial discharges in the monitoring period;
arranging insulation screening points on the surface of the insulation layer of each tunnel cable section in a set number, and monitoring and extracting the thickness of the insulation layer of each insulation screening point of each tunnel cable section in each monitoring periodObtaining insulation layer specification thickness of target tunnel cable from cable information base>Further, the thickness loss degree of the insulating layer of each tunnel cable section in each monitoring period is calculated>The calculation formula is as follows:
wherein->Expressed as a set allowable deviation insulating layer thickness, < >>Number expressed as each insulation screening point, < >>,/>Expressed as the total number of insulation screening points.
4. The machine learning-based tunnel cable remaining life prediction method of claim 1, wherein: the specific analysis process of the information data of each tunnel cable section is as follows: environmental data of each tunnel cable segment in each monitoring period is collected, wherein the environmental data comprises environmental temperature, tunnel cable load current and voltage, environmental vibration stress and vibration frequency.
5. The machine learning-based tunnel cable remaining life prediction method of claim 1, wherein: the combined characteristic value of the comprehensively constructed target tunnel cable comprises the following specific analysis processes:
according to the temperature, load current and voltage, environmental vibration stress and vibration frequency of each tunnel cable section in each monitoring period, carrying out characteristic combination analysis, sequentially constructing combined characteristic values of each tunnel cable section in each monitoring period, and respectively marking as、/>、/>、/>、/>、/>And->;
Thermal-vibration stress characteristicsThe specific expression is: />Wherein->And->Expressed as maximum temperature and maximum vibration stress of each tunnel cable segment in each monitoring period,/respectively>And->The average temperature and the average vibration stress of each tunnel cable section in each monitoring period are respectively expressed;
thermo-electric-vibration stress characteristicsThe specific expression is: />Wherein->Expressed as maximum current of each tunnel cable segment in each monitoring period,/for each monitoring period>Represented as the average current of each tunnel cable segment over each monitoring period;
thermo-electric-vibration characteristicsThe specific expression is: />Wherein->Expressed as the vibration frequency of each tunnel cable segment in each monitoring period;
frequency domain analysis features of vibration dataThe specific expression is: />Wherein->Represented as +.f. in the frequency domain signal for each tunnel cable segment during each monitoring period>Complex values of the individual frequency components, +.>,/>Expressed as the total number of signal sampling points;
temperature difference-time-frequency characteristicsThe specific expression is: />Wherein->And->Expressed as minimum temperature and vibration period of each tunnel cable segment in each monitoring period, +.>Expressed as the age of the target tunnel cable;
current-voltage-vibration characteristicsThe specific expression is: />Wherein->Expressed as the maximum voltage of each tunnel cable segment during each monitoring period;
current-voltage-temperature characteristicsThe specific expression is: />;
Constructing a correlation matrix to perform feature screening, wherein the screened combined sub-feature markers are as followsComprehensively constructing combined characteristic values of each tunnel cable section in each monitoring period>。
6. The machine learning-based tunnel cable remaining life prediction method of claim 1, wherein: the cable residual life is predicted, and the specific analysis process is as follows:
according to the representation change degree index of each monitoring period of the target tunnel cable, matching the representation change degree index with a reference prediction curve model corresponding to each set representation change degree index interval to obtain a reference prediction curve model corresponding to each monitoring period of the target tunnel cable, constructing a designated reference prediction curve model of the target tunnel cable through dynamic fitting, carrying out mean value processing on the representation change degree index of each monitoring period of the target tunnel cable to obtain a representation change degree index mean value of the target tunnel cable, and carrying out positioning extraction on the estimated residual service life value of the target tunnel cable to output and display.
7. Tunnel cable residual life prediction device based on machine learning, its characterized in that: comprising the following steps:
a processor, a memory and a network interface connected with the processor; the network interface is connected with a nonvolatile memory in the server; the processor, when running, retrieving a computer program from the non-volatile memory via the network interface and running the computer program via the memory to perform the method of any of the preceding claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311100340.7A CN116861797B (en) | 2023-08-30 | 2023-08-30 | Tunnel cable residual life prediction method and device based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311100340.7A CN116861797B (en) | 2023-08-30 | 2023-08-30 | Tunnel cable residual life prediction method and device based on machine learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116861797A true CN116861797A (en) | 2023-10-10 |
CN116861797B CN116861797B (en) | 2023-11-24 |
Family
ID=88228857
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311100340.7A Active CN116861797B (en) | 2023-08-30 | 2023-08-30 | Tunnel cable residual life prediction method and device based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116861797B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117056875A (en) * | 2023-10-10 | 2023-11-14 | 湖南华菱线缆股份有限公司 | Cable transmission performance analysis method and device based on test data |
CN118134116A (en) * | 2024-05-07 | 2024-06-04 | 国网山东省电力公司烟台供电公司 | Cable and channel state monitoring and evaluating method based on big data analysis |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09251003A (en) * | 1996-03-15 | 1997-09-22 | Chubu Electric Power Co Inc | Testing method for judging life of rubber and plastic cable |
JP2005345450A (en) * | 2004-06-07 | 2005-12-15 | J-Power Systems Corp | Nondestructive degradation diagnosis method and degradation positioning method for cable |
US20130196857A1 (en) * | 2010-05-10 | 2013-08-01 | International Superconductivity Technology Center | Superconducting cable |
CN105243520A (en) * | 2015-11-18 | 2016-01-13 | 国网上海市电力公司 | Full life-cycle cost evaluation method based on power cable heat transfer model |
CN108399286A (en) * | 2018-02-05 | 2018-08-14 | 三峡大学 | A kind of cable run steel bracket evaluation of life cycle cost method |
CN111382542A (en) * | 2020-02-26 | 2020-07-07 | 长安大学 | Road electromechanical equipment life prediction system oriented to full life cycle |
CN115481806A (en) * | 2022-09-23 | 2022-12-16 | 广东电网有限责任公司广州供电局 | Cable residual life online prediction method and device based on correlation coefficient retention rate |
US20230086049A1 (en) * | 2021-09-21 | 2023-03-23 | Abb Schweiz Ag | Systems and methods of predicting the remaining useful life of industrial mechanical power transmission equipment using a machine learning model |
-
2023
- 2023-08-30 CN CN202311100340.7A patent/CN116861797B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09251003A (en) * | 1996-03-15 | 1997-09-22 | Chubu Electric Power Co Inc | Testing method for judging life of rubber and plastic cable |
JP2005345450A (en) * | 2004-06-07 | 2005-12-15 | J-Power Systems Corp | Nondestructive degradation diagnosis method and degradation positioning method for cable |
US20130196857A1 (en) * | 2010-05-10 | 2013-08-01 | International Superconductivity Technology Center | Superconducting cable |
CN105243520A (en) * | 2015-11-18 | 2016-01-13 | 国网上海市电力公司 | Full life-cycle cost evaluation method based on power cable heat transfer model |
CN108399286A (en) * | 2018-02-05 | 2018-08-14 | 三峡大学 | A kind of cable run steel bracket evaluation of life cycle cost method |
CN111382542A (en) * | 2020-02-26 | 2020-07-07 | 长安大学 | Road electromechanical equipment life prediction system oriented to full life cycle |
US20230086049A1 (en) * | 2021-09-21 | 2023-03-23 | Abb Schweiz Ag | Systems and methods of predicting the remaining useful life of industrial mechanical power transmission equipment using a machine learning model |
CN115481806A (en) * | 2022-09-23 | 2022-12-16 | 广东电网有限责任公司广州供电局 | Cable residual life online prediction method and device based on correlation coefficient retention rate |
Non-Patent Citations (2)
Title |
---|
李彬 等: "动车双螺旋电缆线剩余寿命预测模型设计与实验", 机械研究与应用, vol. 33, no. 2, pages 181 - 183 * |
潘江江 等: "航天器电线电缆寿命预测模型研究", 宇航计测技术, vol. 39, no. 6, pages 14 - 18 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117056875A (en) * | 2023-10-10 | 2023-11-14 | 湖南华菱线缆股份有限公司 | Cable transmission performance analysis method and device based on test data |
CN117056875B (en) * | 2023-10-10 | 2024-01-02 | 湖南华菱线缆股份有限公司 | Cable transmission performance analysis method and device based on test data |
CN118134116A (en) * | 2024-05-07 | 2024-06-04 | 国网山东省电力公司烟台供电公司 | Cable and channel state monitoring and evaluating method based on big data analysis |
Also Published As
Publication number | Publication date |
---|---|
CN116861797B (en) | 2023-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116861797B (en) | Tunnel cable residual life prediction method and device based on machine learning | |
Meng et al. | Remaining useful life prediction of rolling bearing using fractal theory | |
CN103711645B (en) | Based on the wind power generating set state evaluating method of modeling parameters signature analysis | |
JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
CN105740975A (en) | Data association relationship-based equipment defect assessment and prediction method | |
CN108921409B (en) | Voltage sag severity grade determination method | |
CN115796059B (en) | Electrical equipment service life prediction method and system based on deep learning | |
KR20200128232A (en) | Apparatus for predicting electricity demand and method thereof | |
CN103699668A (en) | Power distribution network electric equipment combination state evaluation method based on data section consistency | |
CN109670652A (en) | A kind of failure prediction method of photovoltaic module | |
Wang et al. | Data-driven prediction method for characteristics of voltage sag based on fuzzy time series | |
CN113821931A (en) | Method and system for predicting output power of fan | |
CN114925614A (en) | Method for predicting residual life of coal mining machine | |
McMillan et al. | Towards quantification of condition monitoring benefit for wind turbine generators | |
CN112347663B (en) | Fault probability prediction method integrating health state and service life of transformer | |
CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
CN112597607A (en) | Predictive maintenance method and system for high-speed bearing of wind driven generator | |
CN108123436B (en) | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm | |
Lima et al. | Wind turbine failure prediction using SCADA data | |
CN115455684A (en) | Oil-immersed transformer non-contact state evaluation method and system based on noise analysis | |
Wu et al. | XLPE cable health assessment based on Relief-F feature weighted FSVM | |
CN108071562B (en) | Wind turbine generator energy efficiency state diagnosis method based on energy flow | |
Wang et al. | A review on data-driven predictive maintenance approach for hydro turbines/generators | |
Kadhem et al. | Differential evolution optimization algorithm based on generation systems reliability assessment integrated with wind energy | |
CN110927488B (en) | Transformer running state monitoring method based on membership function |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |