CN117540644A - Intelligent cable with life cycle index analysis based on cable measurement temperature - Google Patents
Intelligent cable with life cycle index analysis based on cable measurement temperature Download PDFInfo
- Publication number
- CN117540644A CN117540644A CN202410036105.6A CN202410036105A CN117540644A CN 117540644 A CN117540644 A CN 117540644A CN 202410036105 A CN202410036105 A CN 202410036105A CN 117540644 A CN117540644 A CN 117540644A
- Authority
- CN
- China
- Prior art keywords
- cable
- monitoring value
- monitoring
- value
- fluctuation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 36
- 238000005259 measurement Methods 0.000 title claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims abstract description 119
- 239000013598 vector Substances 0.000 claims abstract description 60
- 238000011156 evaluation Methods 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 18
- 230000008447 perception Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 16
- 238000004364 calculation method Methods 0.000 description 6
- 239000000243 solution Substances 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010790 dilution Methods 0.000 description 1
- 239000012895 dilution Substances 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012360 testing method Methods 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
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03H—IMPEDANCE NETWORKS, e.g. RESONANT CIRCUITS; RESONATORS
- H03H17/00—Networks using digital techniques
- H03H17/02—Frequency selective networks
- H03H17/0248—Filters characterised by a particular frequency response or filtering method
- H03H17/0255—Filters based on statistics
- H03H17/0257—KALMAN filters
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of cable detection, in particular to an intelligent cable with life cycle index analysis based on cable measurement temperature, which comprises a data acquisition cable unit, a data processing cable unit and a cable life detection unit, wherein the data acquisition cable unit is used for acquiring working environment monitoring data of the cable; acquiring a system state vector; acquiring a sigma point set to be detected; constructing a local fluctuation interval; analyzing the monitoring value distribution of the local fluctuation interval, and constructing a local fluctuation description factor and a monitoring value fluctuation element; constructing a fluctuation trend vector; analyzing similarity relation between the fluctuation trend vector and column vectors of each sigma point, and constructing and selecting evaluation; acquiring a preferred sigma point set; therefore, the life index analysis of the cable is completed by adopting the convolutional neural network, the intelligence of the intelligent cable to the external environment perception is improved, and the accuracy of the life index analysis of the intelligent cable is improved.
Description
Technical Field
The application relates to the technical field of cable detection, in particular to an intelligent cable with life cycle index analysis based on cable measurement temperature.
Background
For judging the load condition of the cable, the conductor temperature of the cable is an important index, and the load temperature refers to the temperature of the cable caused by the passing of load current. The cable can produce resistance heat in the process of conveying electric energy, and the larger load current is, the cable temperature can rise correspondingly, and the external environment can also produce great degree influence to the temperature of cable. The change of the working temperature of the cable can cause the ageing of the coating material, reduce the insulation and isolation performance and finally influence the normal working life of the cable.
The traditional single measurement type means can intuitively find the aging phenomenon of the cable, but has low detection efficiency, so that life cycle analysis can be carried out by using a computer through cable working environment sensing monitoring data to provide convenient data reference for cable maintenance work, the maintenance cost is reduced, meanwhile, the usability of the cable is improved, and the intelligent cable can be conveniently deployed in different working environments.
Disclosure of Invention
In order to solve the technical problems, the invention provides a smart cable with life cycle index analysis based on cable measurement temperature, so as to solve the existing problems.
The intelligent cable with life cycle index analysis based on cable measurement temperature adopts the following technical scheme:
one embodiment of the present invention provides a smart cable having a life cycle index analysis based on a measured temperature of the cable, the smart cable comprising:
the data acquisition cable unit acquires the working environment monitoring data of the cable;
the data processing cable unit is used for acquiring a system state vector according to the detection data of the cable working environment; acquiring a sigma point set to be detected according to the working environment monitoring data of the cable and the system state vector; according to the working environment detection data of the cable, acquiring a local fluctuation interval at the current moment by adopting an STL algorithm; acquiring a local fluctuation description factor of each monitoring value dimension at the current moment according to the monitoring value distribution of the local fluctuation interval at the current moment; acquiring monitoring value fluctuation elements of each monitoring value dimension at the current moment according to the local fluctuation description factors of each monitoring value dimension at the current moment and the monitoring value differences at the corresponding moment and the previous moment; the monitoring value fluctuation elements of all monitoring value dimensions at the current moment form a fluctuation trend vector at the current moment; acquiring selection evaluation of each sigma point according to the similarity relation between the fluctuation trend vector at the current moment and the split column vector of each sigma point; acquiring a preferred sigma point set according to the selection evaluation of each sigma point;
and the cable life detection unit is used for completing life index analysis of the cable according to the preferred sigma point set.
Preferably, the working environment monitoring data of the cable comprises the temperature of the cable, the external environment temperature, the external environment humidity, the external atmospheric pressure, the cable working voltage and the cable working current.
Preferably, the system state vector is obtained according to the cable working environment detection data, and the specific steps include:
the cable self temperature, the external environment humidity, the external atmospheric pressure, the cable working voltage and the cable working current at the current moment are taken as elements of a system state vector.
Preferably, the sigma point set to be detected is obtained according to the working environment monitoring data of the cable and the system state vector, specifically:
and taking the working environment monitoring data of the cable and the system state vector as inputs of the UKF filter, wherein the output of the UKF filter is a sigma point set to be detected.
Preferably, the local fluctuation interval at the current moment is obtained by adopting an STL algorithm according to the detection data of the working environment of the cable, and the obtaining method comprises the following steps:
taking the working environment monitoring data of the cable from the initial moment to the current moment as the input of the STL algorithm; taking the period term as the output of the STL algorithm; and taking the time range formed by the period of the current moment and the period adjacent to the period as the local fluctuation interval of the current moment.
Preferably, the local fluctuation description factor of each monitored value dimension at the current moment is obtained according to the monitored value distribution of the local fluctuation interval at the current moment, and the specific expression is as follows:
；
in the method, in the process of the invention,describing factors for local fluctuation of the monitored value dimension R at the current time t; r is (r) t The monitoring value of the monitoring value dimension R at the current time t is obtained; />A monitoring value set of a local fluctuation interval of the monitoring value dimension R at the current moment; max (), min () are maximum value function, minimum value function respectively; />An ith monitoring value in the local fluctuation interval; /> Respectively, the average value and standard deviation of the monitoring value dimension R in the current local fluctuation interval are->The number of the monitoring values in the local fluctuation interval of the current moment is represented by the monitoring value dimension R.
Preferably, the obtaining the monitoring value fluctuation element of each monitoring value dimension at the current moment according to the local fluctuation description factor of each monitoring value dimension at the current moment and the monitoring value difference at the corresponding moment and the previous moment specifically includes:
for each monitoring value dimension, calculating the difference value between the monitoring value at the current moment and the monitoring value at the previous moment; calculating the ratio of the difference value to the monitoring value at the previous moment; and taking the product of the ratio and the local fluctuation descriptive factor at the current moment as a monitoring value fluctuation element of each monitoring value dimension at the current moment.
Preferably, the selecting evaluation of each sigma point is obtained according to the similarity relation between the fluctuation trend vector at the current moment and the split column vector of each sigma point, and the expression is as follows:
；
wherein: x is X a Selecting and evaluating the point a; n is n a ' the number of column vectors for point a; a, a j ' is the j-th column vector of point a; d (D) t Is the fluctuation trend vector of the current time t; θ () is a cosine similarity function; sinc () is a sine function.
Preferably, the obtaining the preferred sigma point set according to the selection evaluation of each sigma point specifically includes:
arranging the selection evaluation of each sigma point in a descending order; selecting a descending sequence number with the largest difference between two adjacent selected evaluations in the descending sequence arrangement and small descending sequence number value; and selecting sigma points corresponding to the first to the descending sequence numbers as a preferable sigma point set.
Preferably, the service life index analysis of the cable is completed according to the preferred sigma point set, and the specific steps include:
the system state vector at the next moment is predicted by adopting a UKF filter by replacing the sigma point set with the preferred sigma point set; taking a time sequence data set of combining the system state vector and the monitoring value at the next moment according to the time sequence as the input of the convolutional neural network; the output of the convolutional neural network is the remaining life of the current cable.
The invention has at least the following beneficial effects:
according to the invention, the self-adaptive state identification of the cable environment measured value is mainly carried out through unscented Kalman filtering, and further the life index analysis is carried out according to the working environment of the predicted value, in the actual detection process, the sigma points of the UKF have partial redundancy, the sigma points are required to be screened through the influence condition represented by the sigma points and the redundancy condition existing in the actual working environment of the cable, the comprehensive description of the cable environment monitoring influence fluctuation at the current moment is reserved, and meanwhile, the predicted time length of increasing the UKF by a large number of sigma points is reduced, so that the calculation instantaneity is reduced.
On the other hand, the sigma points are screened according to the influence condition represented by the sigma points and the redundancy condition existing in the actual working environment of the cable, so that the monitoring numerical value result of the working environment of the intelligent cable at the next moment represented by the predicted value obtained by calculating the optimal sigma points is more consistent with the monitoring value at the next moment, the intelligence of the intelligent cable for sensing the external environment is finally improved, and the accuracy of the intelligent cable for analyzing the life index is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a smart cable with life cycle index analysis based on cable measured temperature provided by the present invention;
fig. 2 is a flow chart of life detection of a smart cable.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given of specific implementation, structure, characteristics and effects of a smart cable with life cycle index analysis based on cable measured temperature according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a smart cable with life cycle index analysis based on cable measured temperature according to the present invention.
One embodiment of the invention provides a smart cable with life cycle index analysis based on cable measured temperature.
Specifically, referring to fig. 1, a smart cable having life cycle index analysis based on a cable measured temperature is provided, and includes a data acquisition cable unit 101, a data processing cable unit 102, and a cable life detection unit 103.
The data acquisition cable unit 101 acquires current cable working environment monitoring data, and further constructs a UKF system state vector.
The cable working environment monitoring data is obtained through a data acquisition cable unit in the intelligent cable, and the type of the working environment monitoring numerical analysis of the cable in the embodiment is (can be changed according to different implementation environments): the temperature of the cable, the external environment temperature, the external environment humidity, the external atmospheric pressure, the cable working voltage and the cable working current.
The system state vectors that make up the UKF are as follows:
；
in which T, C, S, P, V, I is the temperature of the cable itself, the ambient temperature, the ambient humidity, the ambient atmospheric pressure, the cable operating voltage and the cable operating current, respectively, () T Representing the transpose of the vector.
In this embodiment, the default current time t represents the last time of the current monitored value, and no subsequent detected value is obtained yet.
So far, the system state vector is obtained through the data acquisition cable unit.
The data processing cable unit 102 performs redundant sigma point screening by using the influence condition represented by the sigma point and the fluctuation condition of the cable actual working environment monitoring data.
The data processing unit of the intelligent cable in this embodiment processes the data based on the UKF algorithm (unscented kalman filter). The UKF algorithm is a nonlinear filtering algorithm that approximates the propagation and measurement update process of a nonlinear function by selecting a set of sigma points to be selected. The choice of the sigma point to be selected plays an important role in the performance and accuracy of the UKF.
sigma points (sigma points) are a set of sampling points used to approximate the state variables of the nonlinear function propagation and measurement update process. These sampling points represent the range of state changes possible under current state estimation by a mean distribution of the monitored values around the current state. By carrying out the propagation of the nonlinear function and the mapping of the observation model on the sigma points, the propagation result and the prediction observation value of the nonlinear function under the current state estimation can be obtained, so that the state prediction and the state update are realized.
Therefore, one sigma point to be selected at the current moment represents an estimated value of the current system state, provides important estimation and update information in the UKF algorithm, and is beneficial to improving the accuracy and performance of filtering.
All observed values from the initial time to the current time and the system state vector at the current time are input into a UKF filter to obtain a sigma point set to be measured, and the sigma point set to be measured is recorded as a sigma [ a1, a2, ] point set to be measured at the current time t. The UKF filter is a known technology, and will not be described in detail in this embodiment.
So far, the sigma point to be measured is obtained through UKF filter processing.
Because each point in the sigma point set represents the value deviation degree of each monitored value dimension at the current moment, the actual data deviation condition in the actual working environment of the intelligent cable has a certain limitation, and the data deviation direction of part of sigma points represents the extremely small possible deviation direction of actual data, the embodiment further screens the coverage degree of the fluctuation trend direction of the local monitored values through the sigma data deviation direction by removing part of redundant sigma points, and obtains the sigma points to be selected.
Because the intelligent cable continuously acquires data in the working process, a local fluctuation interval is obtained by splitting global data, the dilution effect of larger data quantity of the global data on the fluctuation condition of the local data is eliminated, and the local data provides obvious description on the fluctuation condition for a calculation unit of the intelligent cable.
Specifically, the initial time T 0 The data of each dimension monitoring value reaching the current time t is decomposed to generate a period term through an STL algorithm, and the monitoring value range divided in time sequence by extracting the period where the current time t is located and the period adjacent to the period is taken as a local fluctuation interval Q of the current time t t . It should be noted that, the STL algorithm is a known technology, and will not be described in detail in this embodiment. The reason that the local fluctuation interval contains two period ranges is that: the local fluctuation interval is ensured to at least contain one complete monitoring value period, and the phenomenon that the reference accuracy of the predicted data to the historical data is affected due to the fact that the data quantity in the period of the current moment is small because the current moment is positioned near the ending moment of the last period is avoided.
Calculating any monitoring value dimension R at current time t t Local fluctuation descriptive factor of (2)The expression is:
；
in the method, in the process of the invention,describing factors for local fluctuation of the monitored value dimension R at the current time t; r is (r) t The monitoring value of the monitoring value dimension R at the current time t is obtained; />Local fluctuation interval Q at the current moment for monitoring value dimension R t Is a set of monitored values of (2); max (), min () are maximum value function, minimum value function respectively; r is (r) i For local fluctuation interval Q t An ith monitored value in the database; /> Respectively the monitored value dimension R is in the current local fluctuation interval Q t Mean value, standard deviation, +.>The number of the monitoring values in the local fluctuation interval of the current moment is represented by the monitoring value dimension R.
For data fluctuation of the monitored value at the current moment, since two data periods exist in the current fluctuation interval, the numerical value of the partial formula represents the numerical significance in the background of the last complete period, and the larger the numerical value of the partial formula is, the description that the current monitored value is in the local fluctuation interval Q t The more outstanding the center, the more easily the monitoring data is disturbed by noise at the current moment t, and then the working environment where the intelligent cable is located is explained to possibly generate certain change.
For the current partThe overall fluctuation condition of the data of the monitoring values in the fluctuation interval, when the monitoring values existing in the interval generate large fluctuation relative to the average value of the monitoring values, the monitoring values are +.>The value of the division is larger, so that the fluctuation direction is converted into the fluctuation amplitude for comparison while the difference of the tiny data is increased by the square, and when the large fluctuation in the interval is more frequently generated, the small fluctuation is generated by ∈>The larger the processed numerical value is, the larger the fluctuation amplitude and the higher the fluctuation frequency generated by the monitoring numerical value in the current local fluctuation interval are comprehensively represented.
To this end, a local fluctuation descriptive factor is calculated for any monitored value dimension R within the current local fluctuation intervalFurther, the dimension R of all the monitoring values obtained through iterative calculation calculates local fluctuation descriptive factors of each dimension +.>。
Sigma points describe the trend of fluctuation of each dimension of the current monitored value data, so that the deviation from the excessive Sigma points is screened by monitoring the local value trend of the value.
And judging the trend of the current local numerical value. The more similar the variation condition of the monitoring value generated by the current dimension R at the time t and the time t-1 is to the difference of the predicted value corresponding to the two times, the more accurate the influence condition of the sigma point on the current dimension is, so that the construction of the fluctuation trend vector is carried out through the proportional relation of the difference value of the monitoring value, and the screening of the sigma point is carried out through the fluctuation trend vector, so that the sigma point similar to the data trend condition can be screened.
Specifically, as the sigma point represents the influence direction of the monitoring value at the previous moment, the deviation direction is judged and identified through the measured value at the previous moment, and the monitoring value fluctuation element representing the deviation direction of the monitoring value is obtained, and the specific expression is as follows:
；
in the method, in the process of the invention,a monitoring value fluctuation element for monitoring value of the monitoring value dimension R at the time t; />Describing factors for local fluctuation of the monitored value dimension R at the current time t; r is (r) t-1 、r t The monitoring values of the monitoring value dimension R at the time t-1 and the time t are respectively.
Placing according to the dimension sequence of the monitoring values in the state monitoring vector to obtain a fluctuation trend vector, wherein the expression is as follows:
；
wherein D is t Is the fluctuation trend vector of the current time t;、/>、/>respectively the dimension R of the monitoring value 1 、R 2 、R 6 The monitored value of the monitored value at time t fluctuates. It should be noted that D t The order of the monitored value dimensions R in (a) and the system state vector V t The same applies.
After the fluctuation trend vector is calculated, calculating the selection evaluation of any sigma point to be detected by taking a sigma point a to be detected as an example in the embodiment, wherein the number of lines of the sigma point is the same as the state monitoring vector, and the number of lines represents the data dimension number of the monitoring value; since the spatial sample dimension of each dimension is two-dimensional in this embodiment, the number of columns is the same as the sample dimension. And therefore, extracting column vectors of the current sigma points according to columns, and calculating the selection evaluation of the points, wherein the expression is as follows:
；
wherein: x is X a Selecting and evaluating the point a; n is n a ' is the number of column vectors split by the points; a, a j ' j-th column vector split for point a; d (D) t Is the fluctuation trend vector of the current time t; θ () is a cosine similarity function; sinc is a sine function. The sing function is a prior art, and the function value approaches the maximum value 1 when the independent variable value approaches 0.
For the similarity of partial column vectors and fluctuation trend vectors split by sigma points, when the similarity is higher, the data deviation influence condition of the sigma points is similar to the actual local data fluctuation trend under the current sample dimension, the more accurate the fluctuation direction description of the current sigma points to the monitoring value is represented, the monitoring value result of the working environment of the intelligent cable at the next moment represented by the predicted value can be more consistent with the monitoring value at the next moment, the perception intelligence of the intelligent cable to the external environment is finally improved, and the accuracy of the intelligent cable to life index analysis is increased. Meanwhile, as the value range of the sine function has partial negative values, the calculation abnormality is avoided through the absolute value.
So far, similarity judgment is carried out on the data deviation influence characteristics of each monitored value dimension in the sigma points on the sample dimension, and the selection evaluation of each sigma point at the current time t is calculated.
Because of the redundancy of partial directions of the sigma points, the selection and judgment of similar coverage characteristics of the deviation direction are carried out through the high evaluation to-be-selected points, and the preferable sigma point at the current time t is obtained.
Specifically, the selected evaluations are arranged in descending order, and the maximum selected evaluation position max (X a ) Further, the difference between adjacent selection evaluations is calculated on the descending orderSelecting the maximum differenceCorresponding two adjacent positions for selecting evaluation are represented by X' m、 X' m+1 For example (m, m+1 are all sequence numbers), the selected evaluation with smaller sequence number is larger in value, namely, the selected evaluation X 'is selected due to the descending order' m Is larger, max (X a ) With X' m And intercepting the selected evaluation on the descending sequence as a sequence endpoint respectively, and marking sigma points corresponding to each selected evaluation as a preferred sigma point set A'. After the preferred sigma point set A' of the current time t is obtained, a UKF filter is adopted to predict the system state vector of the next time instead of the sigma point set A.
To this end, a predicted system state vector is obtained by the data processing cable unit.
The cable life detection unit 103 performs predictive analysis on the life index of the cable based on the preferred sigma point set.
After the predicted value and the monitoring value of each dimension in the predicted system state vector are combined according to time sequence, the neural network of the fatigue model which is trained in advance through cable working environment data obtained through historical acquisition carries out temperature life index analysis: and combining the predicted value and the monitoring value of each dimension in the state vector according to the time sequence, and then inputting the combined predicted value and the monitoring value into a network for calculation. According to the characteristics and requirements of the fatigue model, the neural network adopts a Convolutional Neural Network (CNN), and a Mean Square Error (MSE) is selected as a loss function of the fatigue model. The input of the network is a time sequence data set obtained by combining the predicted value and the monitoring value of each dimension in the state vector according to the time sequence, and the output of the network is the life index of the current cable. It should be noted that, the convolutional neural network is a known technology, and the embodiment is not repeated, and the implementer may select other neural networks for analysis, which is not limited in the embodiment. The life test of the smart cable is shown in fig. 2.
So far, the life index of the intelligent cable is obtained through the cable life detection unit.
In summary, the embodiment of the invention mainly carries out the self-adaptive state identification of the cable environment measured value through unscented Kalman filtering, and further carries out the analysis of the life index according to the working environment of the predicted value, in the actual detection process, the sigma points of the UKF have partial redundancy conditions, the sigma points need to be screened through the influence condition represented by the sigma points and the redundancy condition existing in the actual working environment of the cable, and the comprehensive description of the fluctuation of the cable environment monitoring influence at the current moment is maintained, and meanwhile, the prediction time length of a large number of sigma points for increasing the UKF is reduced, so that the calculation instantaneity is reduced.
On the other hand, the sigma points are screened according to the influence condition represented by the sigma points and the redundancy condition existing in the actual working environment of the cable, so that the monitoring numerical value result of the working environment of the intelligent cable at the next moment represented by the predicted value obtained by calculating the optimal sigma points is more consistent with the monitoring value at the next moment, the intelligence of the intelligent cable for sensing the external environment is finally improved, and the accuracy of the intelligent cable for analyzing the life index is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.
Claims (10)
1. A smart cable having a life cycle index analysis based on cable measured temperature, the smart cable comprising:
the data acquisition cable unit acquires the working environment monitoring data of the cable;
the data processing cable unit is used for acquiring a system state vector according to the detection data of the cable working environment; acquiring a sigma point set to be detected according to the working environment monitoring data of the cable and the system state vector; according to the working environment detection data of the cable, acquiring a local fluctuation interval at the current moment by adopting an STL algorithm; acquiring a local fluctuation description factor of each monitoring value dimension at the current moment according to the monitoring value distribution of the local fluctuation interval at the current moment; acquiring monitoring value fluctuation elements of each monitoring value dimension at the current moment according to the local fluctuation description factors of each monitoring value dimension at the current moment and the monitoring value differences at the corresponding moment and the previous moment; the monitoring value fluctuation elements of all monitoring value dimensions at the current moment form a fluctuation trend vector at the current moment; acquiring selection evaluation of each sigma point according to the similarity relation between the fluctuation trend vector at the current moment and the split column vector of each sigma point; acquiring a preferred sigma point set according to the selection evaluation of each sigma point;
and the cable life detection unit is used for completing life index analysis of the cable according to the preferred sigma point set.
2. A smart cable having a life cycle index analysis based on cable measured temperature according to claim 1, wherein the operating environment monitoring data of the cable comprises cable self temperature, ambient humidity, ambient atmospheric pressure, cable operating voltage, cable operating current.
3. A smart cable having a life cycle index analysis based on cable measured temperature according to claim 2, wherein said system state vector is obtained from cable operating environment detection data, comprising the steps of:
the cable self temperature, the external environment humidity, the external atmospheric pressure, the cable working voltage and the cable working current at the current moment are taken as elements of a system state vector.
4. The intelligent cable with life cycle index analysis based on cable measured temperature according to claim 1, wherein the sigma point set to be measured is obtained according to the cable working environment monitoring data and the system state vector, specifically:
and taking the working environment monitoring data of the cable and the system state vector as inputs of the UKF filter, wherein the output of the UKF filter is a sigma point set to be detected.
5. The intelligent cable with life cycle index analysis based on cable measured temperature according to claim 1, wherein the local fluctuation interval at the current moment is obtained by using STL algorithm according to the working environment detection data of the cable, and the obtaining method comprises the following steps:
taking the working environment monitoring data of the cable from the initial moment to the current moment as the input of the STL algorithm; taking the period term as the output of the STL algorithm; and taking the time range formed by the period of the current moment and the period adjacent to the period as the local fluctuation interval of the current moment.
6. The intelligent cable with life cycle index analysis based on cable measured temperature according to claim 1, wherein the local fluctuation descriptive factor of each monitored value dimension at the current moment is obtained according to the monitored value distribution of the local fluctuation interval at the current moment, and the specific expression is:
；
in the method, in the process of the invention,describing factors for local fluctuation of the monitored value dimension R at the current time t; r is (r) t The monitoring value of the monitoring value dimension R at the current time t is obtained; />A monitoring value set of a local fluctuation interval of the monitoring value dimension R at the current moment; max (), min () are maximum value function, minimum value function, r i An ith monitoring value in the local fluctuation interval; respectively, the average value and standard deviation of the monitoring value dimension R in the current local fluctuation interval are->The number of the monitoring values in the local fluctuation interval of the current moment is represented by the monitoring value dimension R.
7. The intelligent cable with life cycle index analysis based on cable measured temperature according to claim 1, wherein the obtaining the monitoring value fluctuation element of each monitoring value dimension at the current moment according to the local fluctuation descriptive factor of each monitoring value dimension at the current moment and the monitoring value difference at the corresponding moment and the previous moment specifically comprises:
for each monitoring value dimension, calculating the difference value between the monitoring value at the current moment and the monitoring value at the previous moment; calculating the ratio of the difference value to the monitoring value at the previous moment; and taking the product of the ratio and the local fluctuation descriptive factor at the current moment as a monitoring value fluctuation element of each monitoring value dimension at the current moment.
8. The intelligent cable with life cycle index analysis based on cable measurement temperature according to claim 1, wherein the selection evaluation of each sigma point is obtained according to the similarity relation between the fluctuation trend vector at the current moment and the split column vector of each sigma point, and the expression is:
；
wherein: x is X a Selecting and evaluating the point a; n is n a ' the number of column vectors for point a; a, a j ' is the j-th column vector of point a; d (D) t Is the fluctuation trend vector of the current time t; θ () is a cosine similarity function; sinc () is a sine function.
9. The smart cable of claim 1 having a life cycle index analysis based on cable measured temperature, wherein the obtaining the preferred sigma point set based on the selected evaluation of each sigma point is specifically:
arranging the selection evaluation of each sigma point in a descending order; selecting a descending sequence number with the largest difference between two adjacent selected evaluations in the descending sequence arrangement and small descending sequence number value; and selecting sigma points corresponding to the first to the descending sequence numbers as a preferable sigma point set.
10. The smart cable of claim 1 having a life cycle index analysis based on cable measured temperature, wherein said cable life cycle index analysis is performed based on a preferred sigma point set, the steps comprising:
the system state vector at the next moment is predicted by adopting a UKF filter by replacing the sigma point set with the preferred sigma point set; taking a time sequence data set of combining the system state vector and the monitoring value at the next moment according to the time sequence as the input of the convolutional neural network; the output of the convolutional neural network is the remaining life of the current cable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410036105.6A CN117540644A (en) | 2024-01-10 | 2024-01-10 | Intelligent cable with life cycle index analysis based on cable measurement temperature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410036105.6A CN117540644A (en) | 2024-01-10 | 2024-01-10 | Intelligent cable with life cycle index analysis based on cable measurement temperature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117540644A true CN117540644A (en) | 2024-02-09 |
Family
ID=89788546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410036105.6A Withdrawn CN117540644A (en) | 2024-01-10 | 2024-01-10 | Intelligent cable with life cycle index analysis based on cable measurement temperature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117540644A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118033409A (en) * | 2024-04-15 | 2024-05-14 | 三峡金沙江川云水电开发有限公司 | GCB arc extinguishing chamber switch resistance testing method |
| CN118091325A (en) * | 2024-04-17 | 2024-05-28 | 江苏裕荣光电科技有限公司 | Intelligent cable detection method and system |
-
2024
- 2024-01-10 CN CN202410036105.6A patent/CN117540644A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118033409A (en) * | 2024-04-15 | 2024-05-14 | 三峡金沙江川云水电开发有限公司 | GCB arc extinguishing chamber switch resistance testing method |
| CN118091325A (en) * | 2024-04-17 | 2024-05-28 | 江苏裕荣光电科技有限公司 | Intelligent cable detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117540644A (en) | Intelligent cable with life cycle index analysis based on cable measurement temperature | |
| Hsu et al. | Multiple time-series convolutional neural network for fault detection and diagnosis and empirical study in semiconductor manufacturing | |
| CN106644162B (en) | Ring main unit wire core temperature soft measurement method based on neighborhood preserving embedding regression algorithm | |
| CN109508835B (en) | Smart power grid short-term power load prediction method integrating environmental feedback | |
| CN113537844B (en) | Method and system for analyzing load behaviors of regional energy Internet based on random matrix | |
| CN110865260A (en) | Method for monitoring and evaluating MOV actual state based on outlier detection | |
| CN112596016A (en) | Transformer fault diagnosis method based on integration of multiple one-dimensional convolutional neural networks | |
| CN111856209A (en) | Power transmission line fault classification method and device | |
| CN115238831A (en) | Fault prediction method, apparatus, computer device, storage medium and program product | |
| CN114626304B (en) | Online prediction soft measurement modeling method for ore pulp copper grade | |
| Simula et al. | Analysis and modeling of complex systems using the self-organizing map | |
| CN117371207A (en) | Extra-high voltage converter valve state evaluation method, medium and system | |
| CN117289668B (en) | Distributed speed reducer network cooperative control method, device, equipment and storage medium | |
| CN117388893B (en) | Multi-device positioning system based on GPS | |
| CN113984389A (en) | Rolling bearing fault diagnosis method based on multi-receptive-field and improved capsule map neural network | |
| CN112149054B (en) | Construction and application of orthogonal neighborhood preserving embedding model based on time sequence expansion | |
| CN116821828A (en) | Multi-dimensional time sequence prediction method based on industrial data | |
| Stamatescu et al. | Reporting interval impact on deep residential energy measurement prediction | |
| CN116341366A (en) | GIS state sensing digital twin system construction method | |
| Yang et al. | Dual-frequency enhanced attention network for aircraft engine remaining useful life prediction | |
| CN112990542B (en) | Service life prediction method for air compressor | |
| CN115796058B (en) | Equipment data analysis method and system of CVD equipment | |
| WO2019142344A1 (en) | Analysis device, analysis method, and recording medium | |
| Chen et al. | A transformer vibration amplitude prediction method via fusion of multi-signals | |
| CN117828314B (en) | Method, device, equipment and storage medium for testing insulation resistance of charging gun |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240209 |
|
| WW01 | Invention patent application withdrawn after publication |