CN117007904B - High-temperature superconducting cable monitoring system and method - Google Patents
High-temperature superconducting cable monitoring system and method Download PDFInfo
- Publication number
- CN117007904B CN117007904B CN202310753417.4A CN202310753417A CN117007904B CN 117007904 B CN117007904 B CN 117007904B CN 202310753417 A CN202310753417 A CN 202310753417A CN 117007904 B CN117007904 B CN 117007904B
- Authority
- CN
- China
- Prior art keywords
- superconducting cable
- current
- deep learning
- network model
- data
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000010791 quenching Methods 0.000 claims abstract description 62
- 238000013135 deep learning Methods 0.000 claims description 45
- 238000001514 detection method Methods 0.000 claims description 37
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 34
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 239000007788 liquid Substances 0.000 claims description 17
- 229910052757 nitrogen Inorganic materials 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 239000010410 layer Substances 0.000 description 75
- 230000008859 change Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000004020 conductor Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- 238000007499 fusion processing Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000000171 quenching effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000011185 multilayer composite material Substances 0.000 description 1
- 239000011241 protective layer Substances 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 239000002887 superconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/083—Locating faults in cables, transmission lines, or networks according to type of conductors in cables, e.g. underground
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/60—Superconducting electric elements or equipment; Power systems integrating superconducting elements or equipment
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Superconductors And Manufacturing Methods Therefor (AREA)
Abstract
本公开涉及超导电缆监测技术领域，提出了一种高温超导电缆监测系统及方法，能够通过智能学习算法实现电缆失超故障的提前预测，提前对高风险运行电缆通过切除检修，来避免重大故障导致电缆的损坏，减少输电的运行成本，能够实现在线实时监控超导电缆的运行状态，提高了系统运行的安全性和稳定性。
The present invention relates to the technical field of superconducting cable monitoring, and proposes a high-temperature superconducting cable monitoring system and method. The system and method can realize early prediction of cable quench faults through intelligent learning algorithms, and can remove and repair high-risk operating cables in advance to avoid damage to cables caused by major faults, reduce the operating cost of power transmission, and realize online real-time monitoring of the operating status of superconducting cables, thereby improving the safety and stability of system operation.
Description
Technical Field
The disclosure relates to the technical field of superconducting cable monitoring, in particular to a high-temperature superconducting cable monitoring system and a method.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
For high temperature superconducting cables, the main body for transmitting electric energy is a superconducting tape, and in order to enable the superconducting tape to work normally, the superconducting tape must be prevented from quenching, and the superconducting state is converted into a normal state with larger resistance. Causes of quench of the high-temperature superconducting cable include defects of the superconducting tape itself, failure of the superconducting cable low-temperature system, failure of the superconducting cable power grid operation, and failure of the superconducting cable power grid. Wherein, the influence of the characteristics of the superconducting tape, including the non-uniformity of the superconducting tape, the heating point is concentrated in a certain fixed area in the current rising process, if the heating point is not effectively restrained, the local quench phenomenon is caused. And damage points of the strips and joints between the strips are potential heating points, and when the heating points generate heat accumulation in the running process, local quench can be caused by long-time running. If the strip is locally quenched, the quenching area is continuously enlarged, the temperature of the superconducting strip is rapidly increased, the superconductor structure is destroyed, and the normal operation of the superconducting cable is finally affected.
The inventor finds that the existing detection method has low detection efficiency on local quench, generally, the fault can be detected after the whole cable is quenched, the fault is detected after the fault is adopted, the probability of damaging the superconducting cable is high, and the running stability of a power grid adopting the superconducting cable can not be ensured.
Disclosure of Invention
In order to solve the problems, the disclosure provides a high-temperature superconducting cable monitoring system and a method, which can realize the advanced prediction of the cable quench fault through an intelligent learning algorithm, cut and overhaul a high-risk operation cable in advance, so as to avoid the damage of the cable caused by the major fault, reduce the operation cost of power transmission, realize the on-line real-time monitoring of the operation state of the superconducting cable, and improve the safety and stability of the system operation.
In order to achieve the above purpose, the present disclosure adopts the following technical scheme:
One or more embodiments provide a high temperature superconducting cable monitoring method, comprising the steps of:
Acquiring operation data of the superconducting cable, wherein the operation data comprise electric quantity operation data and non-electric quantity operation data;
Aiming at the acquired electrical quantity signals, calculating a current difference value and a current phase difference value of the conducting layer and the shielding layer;
And constructing a deep learning network model, and transmitting the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the voltage value and the non-electric quantity operation data to the deep learning network model to obtain the probability of superconducting cable quench.
One or more embodiments provide a high temperature superconducting cable monitoring system comprising:
the acquisition module is configured to acquire operation data of the superconducting cable, including electric quantity operation data and non-electric quantity operation data;
The current data processing module is configured to calculate a current difference value and a current phase difference value of the conducting layer and the shielding layer according to the acquired electric quantity signal;
The probability prediction module is configured to construct a deep learning network model, and takes the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the voltage value and the non-electric quantity operation data as input to transmit the data to the deep learning network model so as to obtain the probability of superconducting cable quench.
One or more embodiments provide a high temperature superconducting cable monitoring system, including a monitoring terminal, an electrical quantity detection device and a non-electrical quantity detection device which are in communication connection with the monitoring terminal;
The monitoring terminal is configured as the steps of the high-temperature superconducting cable monitoring method.
Compared with the prior art, the beneficial effects of the present disclosure are:
In the method, based on a deep learning network model, key factors of the quench are learned, fine changes of detection signals can be identified, fusion processing is conducted on multidimensional data of the quench detection through the deep learning network, before the occurrence of full-section quench, superconducting cable quench advance can be conducted at high probability according to the identification probability, corresponding protection actions are conducted, the damage probability of the superconducting cable is reduced, and therefore stable and safe operation of the superconducting cable can be guaranteed.
The advantages of the present disclosure, as well as those of additional aspects, will be described in detail in the following detailed description of embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain and do not limit the disclosure.
FIG. 1 is a schematic view of a high temperature superconducting cable of example 1 of the present disclosure;
FIG. 2 is a schematic diagram of a high temperature superconducting cable monitoring system according to embodiment 1 of the present disclosure;
fig. 3 is a flow chart of a method for monitoring a high temperature superconducting cable according to embodiment 2 of the present disclosure.
Detailed Description
The disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present disclosure. 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 disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof. It should be noted that, without conflict, the various embodiments and features of the embodiments in the present disclosure may be combined with each other. The embodiments will be described in detail below with reference to the accompanying drawings.
Example 1
In the technical scheme disclosed in one or more embodiments, as shown in fig. 1 to 3, a high-temperature superconducting cable monitoring system comprises a monitoring terminal, an electric quantity detection device and a non-electric quantity detection device, wherein the electric quantity detection device and the non-electric quantity detection device are in communication connection with the monitoring terminal, the monitoring terminal obtains electric quantity and non-electric quantity detected by the high-temperature superconducting cable, and the probability of quench of the superconducting cable is obtained based on prediction of a deep learning network model.
The structure of the superconducting cable is shown in fig. 1, and is a multi-layer composite material structure, which sequentially comprises a liquid nitrogen inlet flow channel, a stainless steel corrugated pipe framework, a three-phase conductive layer formed by high-temperature superconducting phase conductor layers passing through insulation intervals, a shielding layer, a liquid nitrogen return flow channel, a protective layer and a cryostat from inside to outside, wherein liquid nitrogen (LN 2) is input by a low-temperature refrigerating system and flows in the liquid nitrogen flow channel.
The three-phase conductive layer comprises an A phase, a B phase and a C phase, and an electric insulating layer and a semi-conductive layer are arranged between each phase. The cryogenic refrigeration system comprises a refrigerator and a circulating pump, and can provide liquid nitrogen meeting the low-temperature requirement for the superconducting cable.
In some embodiments, the non-electrical quantity detection means includes means for effecting liquid nitrogen temperature, pressure and flow detection.
Optionally, the device for detecting the temperature of the liquid nitrogen comprises temperature sensors arranged at two ends of the superconducting cable, specifically, the device can be arranged at an inlet and an outlet of the liquid nitrogen of the superconducting cable and used for collecting temperature signals of an input end and an output end of a low-temperature refrigerating system, and the device can also be used for respectively arranging the temperature sensors at two ends of a three-phase conducting layer of the superconducting cable and used for collecting temperature changes in the operation process of the three-phase conducting layer.
Optionally, the pressure detection device comprises a pressure sensor arranged at an inlet and an outlet of the liquid nitrogen of the superconducting cable.
Optionally, the flow detection device comprises a flow meter disposed at an inlet and an outlet of the superconducting cable liquid nitrogen.
In some embodiments, the electrical quantity sensing device includes a sensor for sensing current and voltage signals of the layers of the superconducting cable.
Alternatively, the current detection device can adopt a current transformer CT which is arranged at two ends of each phase of conductive layer to respectively measure the current values of the two ends, and also can detect the current of the shielding layer of the superconducting cable and is arranged at the leading-out end of the shielding layer of the terminal of the superconducting cable.
Alternatively, the voltage detection device may use a voltage transformer PT, and may collect voltages of the conductive layers of each phase.
According to a further technical scheme, the monitoring terminal is configured to execute a high-temperature superconducting cable monitoring method, prediction is carried out based on a deep learning network model, the probability of superconducting cable quench is obtained, and the method comprises the following steps:
step 1, acquiring operation data of a superconducting cable, wherein the operation data comprise electric quantity operation data and non-electric quantity operation data;
The electrical quantity operation data comprise current signals of all layers of the superconducting cable and three-phase voltage signals, and the non-electrical quantity data can comprise flow, temperature and pressure signals of liquid nitrogen.
Step 2, calculating a current difference value and a current phase difference value of the conducting layer and the shielding layer according to the acquired electric quantity signals;
And 3, constructing a deep learning network model, and transmitting the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the voltage value and the non-electric quantity operation data to the deep learning network model to obtain the probability of quench of the superconducting cable.
When the full-segment quench occurs, the existing detection method can effectively detect the occurrence of faults; however, aiming at the problem that local quench phenomenon is not easy to detect, in the embodiment, based on a deep learning network model, key factors of quench are learned, fine changes of detection signals can be identified, fusion processing is carried out on multidimensional data of quench detection through the deep learning network, and before full-section quench occurs, superconducting cables can be prevented from being advanced in a large probability according to the identification probability, corresponding protection actions are carried out, the damage probability of the superconducting cables is reduced, and therefore stable and safe operation of the superconducting cables can be guaranteed.
The superconducting cable is provided with a shielding layer, quench judgment can be carried out by using a current difference quench detection method, the current of the conductor layer is basically equal to that of the superconducting shielding layer before a fault, and the current of the superconducting shielding layer after the fault is smaller than that of the conductor layer.
Specifically, the current difference between the conducting layer and the shielding layer is set to be I 1, the current of the superconducting shielding layer is set to be I 2, the sizes of I 1 and I 2 are basically equal when the cable runs normally, when the cable is over-current, the shielding layer is quenched, the impedance of the shielding layer is increased, the induced current value is smaller than the current of the conducting layer, and if a local fault occurs, the current when the difference exceeds a set value I A is a serious quench fault.
The current difference between the conducting layer and the shielding layer is calculated by the formula I 1-I2|<IA
Specifically, when the superconducting cable operates normally, the phase difference between the current I 1 of the conductive layer and the current I 2 of the superconducting shielding layer is basically stabilized at about 180 °, and after the superconducting cable is quenched, the shielding layer is quenched to generate a resistive component, so that the phase difference between the current I 1 of the conductive layer and the current I 2 of the superconducting shielding layer is changed. The formula for judging whether the superconducting cable is quenched or not based on the current phase difference is as follows:
|Φ1-Φ2|-180°<Φd
Wherein, phi 1 is the initial phase angle of the current of the conducting layer, phi 2 is the initial phase angle of the current of the superconducting shielding layer, and phi d is the phase difference detection setting threshold.
In this embodiment, the quench fault in the cable can be identified based on the current magnitude and the phase change of the current through the current signal, but the simple numerical comparison is adopted, so that after the fault develops to a certain extent, if the quench area exceeds a set value, the quench fault can be judged, the fault can not be identified in the early stage of the fault development, the hysteresis is serious, the superconducting cable is a novel cable, the preparation cost is high, and the damage loss is serious. Therefore, it is necessary to pre-judge the quench fault of the superconducting cable in advance.
After local quench occurs, the operation parameter data of the superconducting cable starts to change gradually, and the multi-dimensional data of the cable, which can judge quench, including temperature, flow, pressure, current difference, phase change and voltage are subjected to fusion treatment, so that quench faults can be recognized in advance, and overhaul can be performed in advance.
Optionally, the deep learning network model may be a support vector machine, a random forest model and a neural network model, and in this embodiment, a BP neural network may be used to construct the deep learning network model, and after extracting features of the obtained data, the probability of quench of the superconducting cable is predicted based on the BP neural network.
Further, training the deep learning network model before predicting by the deep learning network model, comprising the steps of:
step S1, acquiring historical data of superconducting cable operation, and preprocessing, wherein the historical data comprises normal operation data and fault data;
The preprocessing comprises preprocessing singular values of signals, missing value processing, normalization processing and the like by adopting a prediction average filtering algorithm.
S2, converting the acquired historical data into feature vectors, abstracting feature attributes from the historical interaction data, and generating a multidimensional feature vector set;
The process of vectorizing the data may be a method in the prior art, which is not described herein.
Step S3, clustering the historical interaction data according to faults based on the feature vectors to obtain a plurality of clusters;
step S4, aiming at the obtained clustering result of the quench fault, identifying the corresponding abnormal characteristic values, and determining the average number N of the abnormal characteristic values in the fault clustering result as the number of the fault characteristic values;
the abnormal data is the abnormal value which exceeds the normal running value, and the set percentage of the fluctuation of the set data exceeding the normal value is the abnormal value;
Step S5, defining the ratio of the number of abnormal characteristic values to the number of fault characteristic values as cluster risk probability for each cluster, namely predicting the risk probability of occurrence of quench faults based on data in the cluster, and taking the risk probability as a label;
Specifically, identifying abnormal characteristic values in each cluster X, and determining the number m of the abnormal characteristic values, wherein the probability of occurrence of quench faults in the running state corresponding to the cluster X is as follows:
s6, taking the feature vector of each cluster as input, taking the risk probability of each cluster as output, and inputting the output to a deep learning network model for training;
And S7, calculating the cross entropy loss of the risk probability and the actual risk of the model prediction, and adjusting parameters of the deep learning network model until the accuracy requirement of the prediction is met, so as to obtain the trained deep learning network model.
In the using stage of the model, fault prediction is carried out on the superconducting cable, vectorization processing is carried out on the obtained data to be processed, and the feature vector obtained after the processing is input into a trained deep learning model for prediction and identification.
In the embodiment, the corresponding relation between the abnormal value and the fault occurrence probability is established, the relation is learned through the deep learning network model, the advanced prediction of the cable quench fault can be realized through an intelligent learning algorithm, the cable damage caused by major faults is avoided by cutting and overhauling the high-risk operation cable in advance, the operation cost of power transmission is reduced, the operation state of the superconducting cable can be monitored in real time on line, and the safety and the stability of the system operation are improved.
Example 2
Based on embodiment 1, the embodiment provides a method for monitoring a high-temperature superconductive cable, as shown in fig. 3, including the following steps:
step 1, acquiring operation data of a superconducting cable, wherein the operation data comprise electric quantity operation data and non-electric quantity operation data;
The electrical quantity operation data comprise current signals of all layers of the superconducting cable and three-phase voltage signals, and the non-electrical quantity data can comprise flow, temperature and pressure signals of liquid nitrogen.
Step 2, calculating a current difference value and a current phase difference value of the conducting layer and the shielding layer according to the acquired electric quantity signals;
And 3, constructing a deep learning network model, and transmitting the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the voltage value and the non-electric quantity operation data to the deep learning network model to obtain the probability of quench of the superconducting cable.
When the full-segment quench occurs, the existing detection method can effectively detect the occurrence of faults; however, aiming at the problem that local quench phenomenon is not easy to detect, in the embodiment, based on a deep learning network model, key factors of quench are learned, fine changes of detection signals can be identified, fusion processing is carried out on multidimensional data of quench detection through the deep learning network, and before full-section quench occurs, superconducting cables can be prevented from being advanced in a large probability according to the identification probability, corresponding protection actions are carried out, the damage probability of the superconducting cables is reduced, and therefore stable and safe operation of the superconducting cables can be guaranteed.
The superconducting cable is provided with a shielding layer, quench judgment can be carried out by using a current difference quench detection method, the current of the conductor layer is basically equal to that of the superconducting shielding layer before a fault, and the current of the superconducting shielding layer after the fault is smaller than that of the conductor layer.
Specifically, the current difference between the conducting layer and the shielding layer is set to be I 1, the current of the superconducting shielding layer is set to be I 2, the sizes of I 1 and I 2 are basically equal when the cable runs normally, when the cable is over-current, the shielding layer is quenched, the impedance of the shielding layer is increased, the induced current value is smaller than the current of the conducting layer, and if a local fault occurs, the current when the difference exceeds a set value I A is a serious quench fault.
The current difference between the conducting layer and the shielding layer is calculated by the formula I 1-I2|<IA
Specifically, when the superconducting cable operates normally, the phase difference between the current I 1 of the conductive layer and the current I 2 of the superconducting shielding layer is basically stabilized at about 180 °, and after the superconducting cable is quenched, the shielding layer is quenched to generate a resistive component, so that the phase difference between the current I 1 of the conductive layer and the current I 2 of the superconducting shielding layer is changed. The formula for judging whether the superconducting cable is quenched or not based on the current phase difference is as follows:
|Φ1-Φ2|-180°<Φd
Wherein, phi 1 is the initial phase angle of the current of the conducting layer, phi 2 is the initial phase angle of the current of the superconducting shielding layer, and phi d is the phase difference detection setting threshold.
In this embodiment, the quench fault in the cable can be identified based on the current magnitude and the phase change of the current through the current signal, but the simple numerical comparison is adopted, so that after the fault develops to a certain extent, if the quench area exceeds a set value, the quench fault can be judged, the fault can not be identified in the early stage of the fault development, the hysteresis is serious, the superconducting cable is a novel cable, the preparation cost is high, and the damage loss is serious. Therefore, it is necessary to pre-judge the quench fault of the superconducting cable in advance.
After local quench occurs, the operation parameter data of the superconducting cable starts to change gradually, and the multi-dimensional data of the cable, which can judge quench, including temperature, flow, pressure, current difference, phase change and voltage are subjected to fusion treatment, so that quench faults can be recognized in advance, and overhaul can be performed in advance.
Optionally, the deep learning network model may be a support vector machine, a random forest model and a neural network model, and in this embodiment, a BP neural network may be used to construct the deep learning network model, and after extracting features of the obtained data, the probability of quench of the superconducting cable is predicted based on the BP neural network.
Further, training the deep learning network model before predicting by the deep learning network model, comprising the steps of:
step S1, acquiring historical data of superconducting cable operation, and preprocessing, wherein the historical data comprises normal operation data and fault data;
The preprocessing comprises preprocessing singular values of signals, missing value processing, normalization processing and the like by adopting a prediction average filtering algorithm.
S2, converting the acquired historical data into feature vectors, abstracting feature attributes from the historical interaction data, and generating a multidimensional feature vector set;
The process of vectorizing the data may be a method in the prior art, which is not described herein.
Step S3, clustering the historical interaction data according to faults based on the feature vectors to obtain a plurality of clusters;
step S4, aiming at the obtained clustering result of the quench fault, identifying the corresponding abnormal characteristic values, and determining the average number N of the abnormal characteristic values in the fault clustering result as the number of the fault characteristic values;
the abnormal data is the abnormal value which exceeds the normal running value, and the set percentage of the fluctuation of the set data exceeding the normal value is the abnormal value;
Step S5, defining the ratio of the number of abnormal characteristic values to the number of fault characteristic values as cluster risk probability for each cluster, namely predicting the risk probability of occurrence of quench faults based on data in the cluster, and taking the risk probability as a label;
Specifically, identifying abnormal characteristic values in each cluster X, and determining the number m of the abnormal characteristic values, wherein the probability of occurrence of quench faults in the running state corresponding to the cluster X is as follows:
s6, taking the feature vector of each cluster as input, taking the risk probability of each cluster as output, and inputting the output to a deep learning network model for training;
And S7, calculating the cross entropy loss of the risk probability and the actual risk of the model prediction, and adjusting parameters of the deep learning network model until the accuracy requirement of the prediction is met, so as to obtain the trained deep learning network model.
Example 3
Based on embodiment 1, this embodiment provides a high temperature superconducting cable monitoring system, including:
the acquisition module is configured to acquire operation data of the superconducting cable, including electric quantity operation data and non-electric quantity operation data;
The current data processing module is configured to calculate a current difference value and a current phase difference value of the conducting layer and the shielding layer according to the acquired electric quantity signal;
The probability prediction module is configured to construct a deep learning network model, and takes the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the voltage value and the non-electric quantity operation data as input to transmit the data to the deep learning network model so as to obtain the probability of superconducting cable quench.
Here, the modules in this embodiment are in one-to-one correspondence with the steps in embodiment 1, and the implementation process is the same, which is not described here.
The foregoing description of the preferred embodiments of the present disclosure is provided only and not intended to limit the disclosure so that various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
While the specific embodiments of the present disclosure have been described above with reference to the drawings, it should be understood that the present disclosure is not limited to the embodiments, and that various modifications and changes can be made by one skilled in the art without inventive effort on the basis of the technical solutions of the present disclosure while remaining within the scope of the present disclosure.
Claims (9)
1. The high-temperature superconducting cable monitoring method is characterized by comprising the following steps of:
Acquiring operation data of the superconducting cable, wherein the operation data comprise electric quantity operation data and non-electric quantity operation data;
Aiming at the acquired electrical quantity signals, calculating a current difference value and a current phase difference value of the conducting layer and the shielding layer;
Constructing a deep learning network model, and transmitting the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the three-phase voltage signal and the non-electric quantity operation data as input to the deep learning network model to obtain the probability of superconducting cable quench;
training the deep learning network model, comprising the following steps:
acquiring historical data of superconducting cable operation, and preprocessing;
converting the acquired historical data into feature vectors, abstracting feature attributes from the historical interaction data, and generating a multidimensional feature vector set;
Clustering the historical interaction data according to faults based on the feature vectors to obtain a plurality of clusters;
Aiming at the obtained clustering result of the quench fault, identifying the corresponding abnormal characteristic values, and determining the average number of the abnormal characteristic values in the fault clustering result as the number of the fault characteristic values;
For each cluster, defining the ratio of the number of abnormal characteristic values to the number of fault characteristic values as cluster risk probability, and taking the risk probability as a label;
Taking the feature vector of each cluster as input, taking the risk probability of each cluster as output, and inputting the output to a deep learning network model for training;
and calculating a predicted loss function, and adjusting parameters of the deep learning network model until the prediction accuracy requirement is met, so as to obtain the trained deep learning network model.
2. The method for monitoring a high temperature superconducting cable of claim 1, wherein:
the electrical quantity operation data comprise current signals of all layers of the superconducting cable and three-phase voltage signals, and the non-electrical quantity data comprise flow, temperature and pressure signals of liquid nitrogen.
3. The method for monitoring a high temperature superconducting cable of claim 1, wherein:
The abnormal data is a set value exceeding the normal value of the operation, and the set percentage of the fluctuation of the set data exceeding the normal value is an abnormal value.
4. The method of claim 1, wherein the loss function is a cross entropy loss of risk probability and actual risk predicted by a model.
5. A high temperature superconducting cable monitoring system, comprising:
the acquisition module is configured to acquire operation data of the superconducting cable, including electric quantity operation data and non-electric quantity operation data;
The current data processing module is configured to calculate a current difference value and a current phase difference value of the conducting layer and the shielding layer according to the acquired electric quantity signal;
the probability prediction module is configured to construct a deep learning network model, and takes the calculated current difference value and current phase difference value of the conducting layer and the shielding layer, the three-phase voltage signal and the non-electric quantity operation data as input to transmit the current difference value and the current phase difference value to the deep learning network model to obtain the probability of quench of the superconducting cable;
training the deep learning network model, comprising the following steps:
acquiring historical data of superconducting cable operation, and preprocessing;
converting the acquired historical data into feature vectors, abstracting feature attributes from the historical interaction data, and generating a multidimensional feature vector set;
Clustering the historical interaction data according to faults based on the feature vectors to obtain a plurality of clusters;
Aiming at the obtained clustering result of the quench fault, identifying the corresponding abnormal characteristic values, and determining the average number of the abnormal characteristic values in the fault clustering result as the number of the fault characteristic values;
For each cluster, defining the ratio of the number of abnormal characteristic values to the number of fault characteristic values as cluster risk probability, and taking the risk probability as a label;
Taking the feature vector of each cluster as input, taking the risk probability of each cluster as output, and inputting the output to a deep learning network model for training;
and calculating a predicted loss function, and adjusting parameters of the deep learning network model until the prediction accuracy requirement is met, so as to obtain the trained deep learning network model.
6. The high-temperature superconducting cable monitoring system is characterized by comprising a monitoring terminal, an electric quantity detection device and a non-electric quantity detection device, wherein the electric quantity detection device and the non-electric quantity detection device are in communication connection with the monitoring terminal;
The monitoring terminal is configured to perform the steps of a high temperature superconducting cable monitoring method as claimed in any one of claims 1-4.
7. A high temperature superconducting cable monitoring system according to claim 6 wherein the non-electrical quantity detecting device comprises a liquid nitrogen temperature detecting device comprising temperature sensors arranged at both ends of the superconducting cable at the inlet and outlet of the superconducting cable liquid nitrogen and temperature sensors arranged at both ends of the superconducting cable three-phase conductive layer.
8. The high temperature superconducting cable monitoring system of claim 6 wherein the non-electrical quantity detection device comprises a pressure detection device and a flow detection device;
the pressure detection device comprises a pressure sensor arranged at an inlet and an outlet of the liquid nitrogen of the superconducting cable;
The flow detection device comprises a flowmeter arranged at the inlet and outlet of the liquid nitrogen of the superconducting cable.
9. The high temperature superconducting cable monitoring system of claim 6 wherein the electrical quantity detecting means comprises means for detecting current and voltage signals for each layer of the superconducting cable;
the current detection device adopts a current transformer, is arranged at two ends of each phase of conductive layer, and is arranged at a shielding layer leading-out end of a superconducting cable terminal;
The voltage detection device adopts a voltage transformer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310753417.4A CN117007904B (en) | 2023-06-25 | 2023-06-25 | High-temperature superconducting cable monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310753417.4A CN117007904B (en) | 2023-06-25 | 2023-06-25 | High-temperature superconducting cable monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117007904A CN117007904A (en) | 2023-11-07 |
| CN117007904B true CN117007904B (en) | 2025-01-03 |
Family
ID=88573581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310753417.4A Active CN117007904B (en) | 2023-06-25 | 2023-06-25 | High-temperature superconducting cable monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117007904B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20240344898A1 (en) * | 2024-01-10 | 2024-10-17 | Southwest Jiaotong University | Method and device for detecting temperature rise inside superconducting levitation device based on deep learning |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4300517B2 (en) * | 2003-09-24 | 2009-07-22 | 住友電気工業株式会社 | Superconducting cable |
| JP2010092967A (en) * | 2008-10-06 | 2010-04-22 | Hitachi Ltd | Quench position determination device and superconducting coil used for the same, and quench position determination method |
| US10477668B2 (en) * | 2014-09-19 | 2019-11-12 | Fermi Research Alliance, Llc | Vector control of radio frequency signal in narrow band loads driven by injection locked magnetron using carrier amplitude modulation by spectral energy spreading via phase modulation |
| GB2540623A (en) * | 2015-07-24 | 2017-01-25 | Tesla Eng Ltd | Superconducting winding arrangements |
| KR101768211B1 (en) * | 2016-11-01 | 2017-08-17 | 한국기초과학지원연구원 | Simulation apparatus for predicting temperature at phase change of super conducting coil and the method thereof |
| CN113657022B (en) * | 2021-07-15 | 2024-05-14 | 华为技术有限公司 | Chip fault recognition method and related equipment |
| CN114912638A (en) * | 2022-05-24 | 2022-08-16 | 广州番禺电缆集团有限公司 | Digital cable for reporting effective operation parameters |
-
2023
- 2023-06-25 CN CN202310753417.4A patent/CN117007904B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Open AccessArticle Intelligent Probability Estimation of Quenches Caused by Weak Points in High-Temperature Superconducting Tapes;Alireza Sadeghi;Energies;20221224;16(1);PP 193-193 * |
| 低温绝缘的高温超导电缆失超检测研究;刘宏伟;范霄汉;张慧媛;李亚西;王银顺;滕仪;李诗梦;;低温与超导;20140218(第02期);42-46+98 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117007904A (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650451B (en) | Converter transformer fault reason identification method and system | |
| CN104990629B (en) | A kind of electrical equipment fault automatic early-warning system of infrared imaging temperature measuring | |
| CN102590683B (en) | Online diagnosing and early warning method for current-carrying faults of power equipment | |
| CN112103923B (en) | A method to realize GIL protection based on abnormal thermal characteristics | |
| WO2019127440A1 (en) | Method and device for handling direct current arc | |
| CN104135074A (en) | Extra-high-voltage substation equipment temperature monitoring and alarming method based on outlier detection | |
| CN117074844A (en) | Intelligent real-time on-line monitoring system for high-voltage power transmission line | |
| CN114169237A (en) | Power cable joint temperature abnormity early warning method combining EEMD-LSTM and isolated forest algorithm | |
| CN117007904B (en) | High-temperature superconducting cable monitoring system and method | |
| CN106771801B (en) | A capacitor bank online monitoring device and its application method | |
| CN117289162A (en) | Battery health prediction method and system based on group end convergence method | |
| CN116973498A (en) | Transformer bushing safety monitoring system based on artificial intelligence | |
| CN116961226A (en) | Monitoring method and system for transformer in transformer substation | |
| CN115112978B (en) | Fault detection method for insulating ring main unit of power system | |
| CN116679241A (en) | System and method suitable for cable connector fault detection and early warning | |
| CN111157045A (en) | Artificial intelligence electric line abnormal risk degree monitoring method and system | |
| CN113484658A (en) | Method, system, medium, and electronic device for diagnosing arc fault | |
| CN208488118U (en) | A kind of intelligent transformer Integrated Fault Diagnosis System | |
| Sun et al. | Voltage transformer secondary circuit anomaly detection based on k-means algorithm | |
| CN112327220B (en) | Distribution transformer health on-line diagnosis method and equipment based on multi-source data | |
| Tian et al. | Intelligent Detection Method of Power Grid Fault Big Data Based on Deep Learning | |
| CN112486071B (en) | High-temperature superconducting cable system online monitoring method, computer equipment, storage medium | |
| CN117686783B (en) | High-voltage cable grounding current on-line monitoring device based on load dynamic management | |
| CN119001591B (en) | A real-time detection method for operation status of electric meter box | |
| US20230341477A1 (en) | Series arc detection firmware |
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 |