CN116299030A - Method for detecting abnormality of follow current loop of parallel direct current power supply system - Google Patents
Method for detecting abnormality of follow current loop of parallel direct current power supply system Download PDFInfo
- Publication number
- CN116299030A CN116299030A CN202310537383.5A CN202310537383A CN116299030A CN 116299030 A CN116299030 A CN 116299030A CN 202310537383 A CN202310537383 A CN 202310537383A CN 116299030 A CN116299030 A CN 116299030A
- Authority
- CN
- China
- Prior art keywords
- power supply
- supply system
- current
- loop
- parallel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 75
- 238000001514 detection method Methods 0.000 claims abstract description 51
- 230000001105 regulatory effect Effects 0.000 claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims description 81
- 239000002775 capsule Substances 0.000 claims description 68
- 230000008859 change Effects 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 25
- 238000012360 testing method Methods 0.000 claims description 23
- 238000005070 sampling Methods 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 10
- 238000002360 preparation method Methods 0.000 claims description 9
- 230000001276 controlling effect Effects 0.000 claims description 8
- 238000007599 discharging Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 230000008602 contraction Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000015556 catabolic process Effects 0.000 abstract description 4
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010019233 Headaches Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 231100000869 headache Toxicity 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
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
- G01R31/40—Testing power supplies
-
- 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
- G01R31/26—Testing of individual semiconductor devices
- G01R31/2601—Apparatus or methods therefor
-
- 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
- G01R31/26—Testing of individual semiconductor devices
- G01R31/2607—Circuits therefor
- G01R31/2632—Circuits therefor for testing diodes
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
-
- 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
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a method for detecting abnormality of a follow current loop of a parallel direct current power supply system, which comprises the following steps: the direct current bus voltage of the parallel direct current power supply system is regulated down to a preset first voltage value through the intelligent management terminal; detecting a first current value of a continuous loop through a shunt preset on the continuous loop, and sending the first current value to an intelligent management terminal; and comparing the first current value with a preset first current threshold value through the intelligent management terminal, and judging whether the follow current loop is abnormal or not according to a comparison result. The invention can realize the intellectualization of the detection of the follow current loop of the parallel direct current power supply system, can effectively save the investment of human resources and time cost, and avoids the problem of breakdown of a switch tube due to too high induced voltage caused by the fact that the failure detection of the follow current loop is not enough to timely release the energy stored in the transformer coil.
Description
Technical Field
The invention relates to the field of parallel direct-current power supply systems, in particular to a detection method for abnormality of a follow current loop of a parallel direct-current power supply system.
Background
In the actual use process of the direct current power supply, in order to meet the requirement of output power, a scheme that a plurality of direct current power supplies are operated in parallel is often adopted. For a plurality of direct current power supplies with the same capacity and running in parallel, certain current sharing control measures are needed to realize the average distribution of load current, so that the running safety of each power supply is improved. In the current sharing control process, a power transformer is needed to perform transformation adjustment on the output voltage of the storage battery on each parallel branch in the parallel direct current power supply, so that the stable output of the whole parallel direct current power supply is realized. In this way, the existence of the power transformer and the inductance element in the parallel dc power supply makes the parallel dc power supply easily have strong reverse electromotive force in the process of switching charge/discharge, and affects the parallel dc power supply circuit, so that a freewheeling circuit is introduced to solve the problem.
However, when the follow current loop fails, the failure phenomenon is not obvious enough, and only when the parallel direct current power supply system fails to perform problem review, the problem that the follow current loop fails to cause the circuit safety problem is not guaranteed is often found, so that the parallel direct current power supply system is finally caused to have great loss. Therefore, detection of the freewheel loop on the parallel dc power supply system has been a very headache problem for workers.
Disclosure of Invention
The invention provides a method for detecting abnormality of a follow current loop of a parallel direct current power supply system, which realizes the intellectualization of the detection of the follow current loop of the parallel direct current power supply system, can effectively save manpower resources and investment of time cost, and avoids the problem of breakdown of a switch tube due to overhigh induced voltage caused by insufficient timely detection of the follow current loop and incapability of timely releasing energy stored in a transformer coil.
The invention provides a method for detecting abnormality of a follow current loop of a parallel direct current power supply system, which comprises the following steps:
the direct current bus voltage of the parallel direct current power supply system is regulated down to a preset first voltage value through the intelligent management terminal;
detecting a first current value of a continuous loop through a shunt preset on the continuous loop, and sending the first current value to an intelligent management terminal;
and comparing the first current value with a preset first current threshold value through the intelligent management terminal, and judging whether the follow current loop is abnormal or not according to a comparison result.
Preferably, the parallel direct current power supply system is composed of a plurality of parallel branches, and each parallel branch is composed of at least one storage battery in series;
the freewheeling circuit is a closed circuit formed by connecting two ends of each parallel shunt with a direct current bus through freewheeling diodes, and the freewheeling diodes are arranged at the positive and negative output ends of each parallel shunt;
and a shunt is arranged on each continuous loop and is in communication connection with the intelligent management terminal.
Preferably, the step of reducing the dc bus voltage of the parallel dc power supply system to a preset first voltage value through the intelligent management terminal includes:
timing is carried out through the intelligent management terminal, and when the timing duration meets the detection period of the preset follow current loop, the preparation work for detecting the abnormality of the follow current loop is started;
when the preparation work of the follow current loop abnormality detection is carried out, an intelligent management terminal is used for controlling an AC-DC module in a parallel direct current power supply system to downwards regulate the output voltage to a preset first voltage value, so that the DC-DC module is switched to a discharge state;
and controlling the discharge output voltage of the DC-DC module in the parallel direct-current power supply system to be regulated to a preset first voltage value through the intelligent management terminal, so that the direct-current bus voltage of the parallel power supply system is kept at the preset first voltage value.
Preferably, the method further comprises the step of detecting abnormality of the flywheel diode on the flywheel loop, wherein the detection method is as follows:
the discharging output voltage of the DC-DC module is regulated back to a rated output value through the intelligent management terminal; the load is borne by the DC-DC module;
the output voltage of the AC-DC module is regulated back to a rated output value through the intelligent management terminal, so that the load is borne by the AC-DC module and the DC-DC module is charged;
and detecting a second voltage value of the freewheel loop, and judging that the freewheel diode on the freewheel loop has a short circuit abnormality when the second voltage value is smaller than a preset second voltage threshold value.
Preferably, the method further comprises the step of positioning the problems existing in the parallel direct current power supply system through the intelligent management terminal when the follow current loop is abnormal, and the steps are as follows:
the method comprises the steps that data monitoring is conducted on a parallel direct-current power supply system through an intelligent management terminal in advance to generate a monitoring data set, and the monitoring data set is stored in a cloud platform through the intelligent management terminal;
when detecting that the follow current loop is abnormal, the monitoring data set of the parallel direct current power supply system corresponding to the follow current loop is called;
analyzing the monitoring data set, and determining abnormal data and corresponding data types thereof;
and comparing the abnormal data and the corresponding data types in a preset abnormal data comparison library to determine the problems of the direct current power supply system.
Preferably, analyzing the monitoring data set, and determining the abnormal data and the corresponding data type thereof includes:
determining relative current information of the freewheeling circuit and voltage information at two ends of the freewheeling diode in a plurality of detection periods according to the monitoring data set;
fitting a monocycle current information change curve by utilizing current information of corresponding freewheel loops in a plurality of detection cycles;
fitting a single-period voltage information change curve by utilizing voltage information at two ends of a corresponding freewheeling diode in a plurality of detection periods in the past;
determining corresponding loop current information of an abnormal follow current loop and voltage information at two ends of a follow current diode in the current detection period according to the monitoring data set;
generating a first curve according to corresponding loop current information in the current detection period;
generating a second curve according to the voltage information at two ends of the corresponding freewheeling diode in the current detection period;
matching and comparing the first curve with a single-period current information change curve, and judging whether current information abnormality occurs according to a matching result;
and matching and comparing the second curve with the single-period voltage information change curve, and judging whether the voltage information is abnormal or not according to a matching result.
Preferably, the step of matching and comparing the second curve with the single-period voltage information change curve, and the step of judging whether the voltage information is abnormal according to the matching result includes:
determining a preset segmentation length, dividing a first curve into a plurality of first curve segments according to the segmentation length and a preset first segmentation rule, and dividing a single-period current information change curve into a plurality of third curve segments according to the segmentation length and the preset first segmentation rule;
determining the time corresponding relation between the first curve segment and the third curve segment in a single detection period, and grouping the plurality of first curve segments and the plurality of third curve segments pairwise;
and matching the first curve segment and the third curve segment of any group to obtain a matching value, and determining that the data corresponding to the first curve segment and the third curve segment of the group is abnormal data when the matching value is smaller than a preset matching threshold value.
Preferably, analyzing the monitoring data set, and determining the abnormal data and the corresponding data type thereof further includes:
extracting a plurality of monitoring data sets for testing stored in a cloud database, and determining abnormal data and corresponding data types of the abnormal data in each monitoring data set for testing;
taking a plurality of monitoring data sets for testing as training set data, and taking abnormal data in each monitoring data set for testing and corresponding data types thereof as verification set data;
the U-net model is used as a basic network architecture to fuse the capsule model and establish an analysis model;
training the analysis model by using the training set data and the verification set data to obtain a trained analysis model;
and analyzing the monitoring data set by using the trained analysis model, and determining abnormal data and data types corresponding to the abnormal data.
Preferably, the analytical model comprises:
the feature extraction module comprises an input convolution layer and a convolution capsule layer, wherein the input convolution layer is used for extracting low-level features of an input monitoring data set for testing, and the convolution capsule layer is used for converting the extracted low-level features into capsules through convolution filtering;
the path shrinkage module comprises a plurality of main capsule layers and is used for carrying out downsampling treatment on the capsules obtained by the feature extraction module;
the path expansion module comprises a plurality of main capsule layers and a plurality of deconvolution capsule layers which are staggered with each other and is used for carrying out up-sampling processing on the capsule subjected to the down-sampling processing; the output main capsule layer is used for outputting the data obtained by the up-sampling processing in the path expansion module after the convolution processing; a jump connection layer for cutting and copying low-level features in the path contraction module and for up-sampling in the path expansion module;
the classification module comprises a classification capsule layer with a plurality of capsules, and the activation vector modulo length of each capsule in the classification capsule layer is used for calculating the probability of whether the instance of each class exists.
Preferably, after determining the problem existing in the dc power supply system, a corresponding problem solution is determined according to a pre-stored problem type-solution correspondence table, and the problem solution is sent to the relevant personnel.
By the embodiment of the invention, the following beneficial effects are obtained:
1. the intelligent detection of the follow current loop of the parallel direct current power supply system can be realized, the investment of human resources and time cost can be effectively saved, and the problem that the switch tube breaks down due to too high induced voltage caused by the fact that the energy stored in the transformer coil cannot be timely released due to failure detection of the follow current loop is avoided.
2. And collecting various data information in the parallel direct current power supply system, generating a monitoring data set, analyzing the monitoring data set corresponding to the parallel direct current power supply system to be monitored by training an analysis model, finally obtaining abnormal data and the type corresponding to the abnormal data, and realizing the analysis and positioning of the abnormal data causing the abnormality of the follow current loop.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of steps of a method for detecting abnormality of a freewheeling circuit of a parallel DC power supply system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a parallel DC power supply system according to an embodiment of the present invention;
fig. 3 is a flowchart of a step of locating a problem existing in a parallel dc power system according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides a method for detecting abnormality of a follow current loop of a parallel direct current power supply system, which referring to fig. 1, comprises the following steps:
step S1, regulating the voltage of a direct current bus of a parallel direct current power supply system to a preset first voltage value through an intelligent management terminal;
s2, detecting a first current value on a continuous loop through a shunt preset on the continuous loop, and sending the first current value to an intelligent management terminal;
and S3, comparing the first current value with a preset first current threshold value through the intelligent management terminal, and judging whether the follow current loop is abnormal or not according to a comparison result.
The working principle and beneficial effects of the technical scheme are as follows: the voltage of a direct current bus of the parallel direct current power supply system is regulated down to a preset first voltage value by utilizing an intelligent management terminal; detecting a first current value of a continuous loop through a shunt preset on the continuous loop, and sending the first current value to an intelligent management terminal; and finally, comparing the first current value with a preset first current threshold value through the intelligent management terminal, and judging whether the follow current loop is abnormal or not according to a comparison result. For example, the DC bus voltage of the parallel power supply system is periodically regulated down to 200V (220V) or 100V (110V) or 45V (48V); the freewheeling circuit shunt at this time if it detects a current greater than 1A (settable) and a voltage greater than 200V or 100V or 45V; the freewheel loop is normal and vice versa. Through the technical scheme, the intelligent detection of the follow current loop of the parallel direct current power supply system is realized, the input of human resources and time cost can be effectively saved, and the problem that the switch tube breaks down due to too high induced voltage caused by the fact that the follow current loop fails to detect in time and energy stored in the transformer coil cannot be timely released is avoided.
In a preferred embodiment, referring to fig. 2, the parallel dc power supply system is composed of a plurality of parallel branches, each parallel branch being composed of at least one battery in series;
the freewheeling circuit is a closed circuit formed by connecting two ends of each parallel shunt with a direct current bus through freewheeling diodes, and the freewheeling diodes are arranged at the positive and negative output ends of each parallel shunt;
and a shunt is arranged on each continuous loop and is in communication connection with the intelligent management terminal.
The working principle and beneficial effects of the technical scheme are as follows: the parallel direct current power supply system comprises a plurality of parallel branches, wherein each parallel branch is formed by connecting at least one storage battery in series, a follow current loop is a closed loop formed by connecting two ends of each parallel branch with a direct current bus through a follow current diode, and the positive and negative output ends of each parallel branch are provided with the follow current diode; and a shunt is arranged on each continuous loop and is in communication connection with the intelligent management terminal. Thus, independent detection of each parallel shunt in the parallel direct current power supply system is realized.
In a preferred embodiment, the step of reducing the dc bus voltage of the parallel dc power system to a preset first voltage value by the intelligent management terminal includes:
timing is carried out through the intelligent management terminal, and when the timing duration meets the detection period of the preset follow current loop, the preparation work for detecting the abnormality of the follow current loop is started;
when the preparation work of the follow current loop abnormality detection is carried out, an intelligent management terminal is used for controlling an AC-DC module in a parallel direct current power supply system to downwards regulate the output voltage to a preset first voltage value, so that the DC-DC module is switched to a discharge state;
and controlling the discharge output voltage of the DC-DC module in the parallel direct-current power supply system to be regulated to a preset first voltage value through the intelligent management terminal, so that the direct-current bus voltage of the parallel power supply system is kept at the preset first voltage value.
The working principle and beneficial effects of the technical scheme are as follows: the intelligent management terminal is used for timing, and when the timing time length meets the detection period of a preset follow current loop, the preparation work for detecting the abnormality of the follow current loop is started, so that the preparation work for periodically detecting the follow current loop is finished, wherein the detection period can be automatically adjusted or manually adjusted according to the charge and discharge frequency of the parallel direct current power supply system; when the preparation work of the follow current loop abnormality detection is carried out, an intelligent management terminal is used for controlling an AC-DC module in a parallel direct current power supply system to downwards regulate the output voltage to a preset first voltage value, so that the DC-DC module is switched to a discharge state; and then controlling the discharge output voltage of the DC-DC module in the parallel direct current power supply system to be regulated to a preset first voltage value through the intelligent management terminal, and finally enabling the voltage of the direct current bus of the parallel direct current power supply system to be kept at the preset first voltage value. Thereby, the DC bus voltage of the parallel DC power supply system can be stably maintained at a preset first voltage value.
In a preferred embodiment, the method further comprises detecting abnormality of the freewheeling diode on the freewheeling circuit, and the detection method is as follows:
the discharging output voltage of the DC-DC module is regulated back to a rated output value through the intelligent management terminal; the load is borne by the DC-DC module;
the output voltage of the AC-DC module is regulated back to a rated output value through the intelligent management terminal, so that the load is borne by the AC-DC module and the DC-DC module is charged;
and detecting a second voltage value of the freewheel loop, and judging that the freewheel diode on the freewheel loop has a short circuit abnormality when the second voltage value is smaller than a preset second voltage threshold value.
The working principle and beneficial effects of the technical scheme are as follows: when the follow current loop is detected, the discharge output voltage of the DC-DC module can be adjusted back to a rated output value through the intelligent management terminal; the load is borne by the DC-DC module, the output voltage of the AC-DC module is regulated back to the rated output value through the intelligent management terminal, the load is borne by the AC-DC module, the DC-DC module is charged, the second voltage value of the freewheel loop is detected, and when the second voltage value is smaller than the preset second voltage threshold value, the freewheel diode on the freewheel loop is judged to have abnormal short circuit, so that the detection of the state of the freewheel diode on the freewheel loop is realized.
In a preferred embodiment, referring to fig. 3, the method further includes locating, by the intelligent management terminal, a problem existing in the parallel dc power supply system when an abnormality occurs in the freewheel circuit, as follows:
step S11, carrying out data monitoring on the parallel direct current power supply system through an intelligent management terminal in advance to generate a monitoring data set, and storing the monitoring data set in a cloud platform through the intelligent management terminal;
step S12, when detecting that the follow current loop is abnormal, a monitoring data set of the parallel direct current power supply system corresponding to the follow current loop is called;
s13, analyzing the monitoring data set, and determining abnormal data and corresponding data types thereof;
and S14, comparing the abnormal data and the corresponding data types in a preset abnormal data comparison library to determine the problems of the direct current power supply system.
The working principle and beneficial effects of the technical scheme are as follows: the method comprises the steps that when a follow current loop is abnormal, the problems of a parallel direct current power supply system can be located through an intelligent management terminal, the parallel direct current power supply system is subjected to data monitoring through the intelligent management terminal in advance to generate a monitoring data set, and the monitoring data set is stored in a cloud platform through the intelligent management terminal, wherein the monitoring data set can comprise voltage and current at two ends of the follow current loop, charging voltage and charging current of the parallel direct current power supply system, discharging voltage and discharging current of the parallel direct current power supply system, charging voltage and charging current on each parallel branch of the parallel direct current power supply system and discharging voltage and discharging current, so that all operation details of the parallel direct current power supply system can be monitored; when detecting that the follow current loop is abnormal, the monitoring data set of the parallel direct current power supply system corresponding to the follow current loop is called; analyzing the monitoring data set, and determining abnormal data and corresponding data types thereof, such as abnormal voltage and current values, abnormal charge and discharge information and the like; comparing the abnormal data and the corresponding data types in a preset abnormal data comparison library to determine the problems of the direct current power supply system, such as the breakdown of a free-wheeling diode in the free-wheeling loop, the breakdown of an inductance element or a coil in the free-wheeling loop and the like, which are determined according to abnormal voltage and current values on the free-wheeling loop.
In a preferred embodiment, analyzing the monitoring data set to determine abnormal data and corresponding data types thereof comprises:
determining relative current information of the freewheeling circuit and voltage information at two ends of the freewheeling diode in a plurality of detection periods according to the monitoring data set;
fitting a monocycle current information change curve by utilizing current information of corresponding freewheel loops in a plurality of detection cycles;
fitting a single-period voltage information change curve by utilizing voltage information at two ends of a corresponding freewheeling diode in a plurality of detection periods in the past;
determining corresponding loop current information of an abnormal follow current loop and voltage information at two ends of a follow current diode in the current detection period according to the monitoring data set;
generating a first curve according to corresponding loop current information in the current detection period;
generating a second curve according to the voltage information at two ends of the corresponding freewheeling diode in the current detection period;
matching and comparing the first curve with a single-period current information change curve, and judging whether current information abnormality occurs according to a matching result;
and matching and comparing the second curve with the single-period voltage information change curve, and judging whether current information abnormality occurs according to a matching result.
The working principle and beneficial effects of the technical scheme are as follows: when the monitoring data set is analyzed, according to the monitoring data set, determining that the current information of the corresponding follow current loop and the voltage information at two ends of the follow current diode of the abnormal follow current loop in a plurality of detection periods, fitting a single-period current information change curve by using the current information of the corresponding follow current loop in the plurality of detection periods, and using the single-period current information change curve to represent the current information change condition of the follow current loop under the normal condition, so that the comparison of the current information change condition under the abnormal condition is facilitated, fitting a single-period voltage information change curve by using the voltage information at two ends of the corresponding follow current diode in the plurality of detection periods, and using the single-period voltage information change curve to represent the voltage information change condition of the follow current loop under the normal condition, thereby facilitating the comparison of the voltage information change condition under the abnormal condition; determining corresponding loop current information of an abnormal follow current loop and voltage information at two ends of a follow current diode in the current detection period according to the monitoring data set; generating a first curve according to corresponding loop current information in the current detection period; generating a second curve according to the voltage information at two ends of the corresponding freewheeling diode in the current detection period; and matching and comparing the first curve with the single-period current information change curve, judging whether current information abnormality occurs according to a matching result, and determining whether the follow current loop has an abnormal condition by comparing the change information of current and voltage under abnormal conditions with the change information of current and voltage under normal conditions.
In a preferred embodiment, matching and comparing the second curve with the single-period voltage information change curve, and judging whether the current information abnormality occurs according to the matching result includes:
determining a preset segmentation length, dividing a first curve into a plurality of first curve segments according to the segmentation length and a preset first segmentation rule, and dividing a single-period current information change curve into a plurality of third curve segments according to the segmentation length and the preset first segmentation rule;
determining the time corresponding relation between the first curve segment and the third curve segment in a single detection period, and grouping the plurality of first curve segments and the plurality of third curve segments pairwise;
and matching the first curve segment and the third curve segment of any group to obtain a matching value, and determining that the data corresponding to the first curve segment and the third curve segment of the group is abnormal data when the matching value is smaller than a preset matching threshold value.
The working principle and beneficial effects of the technical scheme are as follows: when comparing the voltage information change curve or the current information change curve, a preset segmentation length can be determined, the first curve is divided into a plurality of first curve segments according to the segmentation length and a preset first segmentation rule, and the single-period current information change curve is divided into a plurality of third curve segments according to the segmentation length and the preset first segmentation rule; determining the time corresponding relation between the first curve segment and the third curve segment in a single detection period, and grouping the plurality of first curve segments and the plurality of third curve segments pairwise; and matching the first curve segment and the third curve segment of any group to obtain a matching value, and determining that the data corresponding to the first curve segment and the third curve segment of the group is abnormal data when the matching value is smaller than a preset matching threshold value. Therefore, the multithreading matching of the data is realized, and the analysis speed of the system can be effectively improved.
In a preferred embodiment, analyzing the monitoring data set to determine the anomaly data therein and the corresponding data type thereof further comprises:
extracting a plurality of monitoring data sets for testing stored in a cloud database, and determining abnormal data and corresponding data types of the abnormal data in each monitoring data set for testing; wherein, the expression form of the monitoring data set for testing is a two-dimensional data matrix P:
in the method, in the process of the invention,
indicate->
The data value corresponding to the m-th type of monitoring data in the time period;
taking a plurality of monitoring data sets for testing as training set data, and taking abnormal data in each monitoring data set for testing and corresponding data types thereof as verification set data;
the U-net model is used as a basic network architecture to fuse the capsule model and establish an analysis model;
training the analysis model by using the training set data and the verification set data to obtain a trained analysis model;
and analyzing the monitoring data set by using the trained analysis model, and determining abnormal data and data types corresponding to the abnormal data.
The working principle and beneficial effects of the technical scheme are as follows: when analyzing the monitoring data sets, extracting a plurality of monitoring data sets for testing stored in a cloud database, and determining abnormal data and corresponding data types in each monitoring data set for testing; taking a plurality of monitoring data sets for testing as training set data, and taking abnormal data in each monitoring data set for testing and corresponding data types thereof as verification set data; the U-net model is used as a basic network architecture to fuse the capsule model and establish an analysis model; training the analysis model by using the training set data and the verification set data to obtain a trained analysis model; and finally, analyzing the monitoring data set by using the trained analysis model, and determining abnormal data and data types corresponding to the abnormal data. According to the method, a large data platform is built at a cloud end, a neural network is trained by the cloud end platform to perform continuous deep learning on a monitoring data set, data iteration is performed continuously, an intelligent and efficient neural network model is obtained, the abnormal monitoring data set of a parallel direct current power supply system corresponding to an existing follow current loop can be rapidly analyzed by the aid of the neural network model, and a source point of data abnormality is obtained. On the basis, prediction of the follow current loop which is about to fail can be realized by carrying out trend analysis on the normal monitoring data set, and an effective prevention means is provided for staff.
In a preferred embodiment, the method further comprises the step of performing direct data anomaly analysis on the newly acquired multiple data by using the monitoring data set, wherein the analysis process is as follows:
determining a stored monitoring data set corresponding to a certain parallel direct current power supply system, and representing by using a two-dimensional data matrix P:
in the method, in the process of the invention,
indicate->
The data value corresponding to the m-th type of monitoring data in the time period;
according to the data type of the monitoring data in the two-dimensional data matrix P, the normal mean value of the monitoring data of each type is calculated, and the calculation formula is as follows:
in the method, in the process of the invention,
the normal average value of the monitoring data of the jth data type in the two-dimensional data matrix P is represented, and n is the total number of times of sampling the monitoring data in the two-dimensional data matrix P;
according to the data type of the monitoring data in the two-dimensional data matrix P, covariance is obtained for each type of monitoring data, and the calculation formula is as follows:
in the method, in the process of the invention,
covariance of monitoring data representing the jth data type in the two-dimensional data matrix P +.>
Indicating that the bracket content is transposed;
for the first two-dimensional data matrix P
And (3) performing anomaly degree calculation on m monitoring data obtained by subsampling, wherein the calculation formula is as follows:
in the method, in the process of the invention,
indicate->
Abnormality degree, ++of various monitoring data corresponding to subsampling>
Representing the total number of data types>
The abnormality degree weight of the monitoring data of the j-th preset data type is represented;
comparing the anomaly degree with an anomaly degree threshold value, and when the anomaly degree is larger than the anomaly degree threshold value, indicating that various data corresponding to the sampling have anomalies.
In a preferred embodiment, the analytical model comprises:
the feature extraction module comprises an input convolution layer and a convolution capsule layer, wherein the input convolution layer is used for extracting low-level features of an input monitoring data set for testing, and the convolution capsule layer is used for converting the extracted low-level features into capsules through convolution filtering;
the path shrinkage module comprises a plurality of main capsule layers and is used for carrying out downsampling treatment on the capsules obtained by the feature extraction module;
the path expansion module comprises a plurality of main capsule layers and a plurality of deconvolution capsule layers which are staggered with each other and is used for carrying out up-sampling processing on the capsule subjected to the down-sampling processing; the output main capsule layer is used for outputting the data obtained by the up-sampling processing in the path expansion module after the convolution processing; a jump connection layer for cutting and copying low-level features in the path contraction module and for up-sampling in the path expansion module;
the classification module comprises a classification capsule layer with a plurality of capsules, and the activation vector modulo length of each capsule in the classification capsule layer is used for calculating the probability of whether the instance of each class exists.
The working principle and beneficial effects of the technical scheme are as follows: the analysis model comprises a feature extraction module, a path contraction module, a path expansion module and a classification module, wherein the feature extraction module comprises an input convolution layer and a convolution capsule layer, the input convolution layer is used for extracting low-level features of an input monitoring data set for testing, the convolution capsule layer is used for converting the extracted low-level features into capsules through convolution filtering, and the capsules are new neurons designed by Sabour et al to replace traditional scalar neurons to construct a capsule network. Each capsule contains two components: a weight matrix and a coupling coefficient. Each weight matrix represents a linear transformation, and carries the spatial relationship between the low-level features and the high-level features and other important relationships, such as parallel shunt abnormality (voltage and current during charging or discharging), flywheel loop abnormality, parallel direct current power supply system data abnormality, and the like, and the coupling coefficient determines which high-level capsule the output of one low-level capsule is sent to. Unlike the weights, the updating is performed by means of dynamic routing. The coupling coefficient thus essentially determines how information flows between the capsules. The sum of the coupling coefficients between each lower capsule and all potential higher capsules is 1. The capsule network is based on capsules, and aims to overcome the defect that the partial-whole relation between abnormal data of a parallel direct current power supply system and main reasons for abnormal flywheel circuits cannot be expressed due to the limitation of the traditional neural network. The path shrinkage module comprises a plurality of main capsule layers, is used for carrying out downsampling treatment on the capsules obtained by the characteristic extraction module, and is used for carrying out a process of reducing the signal sampling rate on continuous electric signals and reducing the data sampling rate or the data size so as to improve the extraction speed of data in the monitoring data set for testing; the path expansion module comprises a plurality of main capsule layers and a plurality of deconvolution capsule layers, wherein the plurality of main capsule layers and the plurality of deconvolution capsule layers are connected in a staggered manner and are used for carrying out up-sampling treatment on the capsule subjected to the down-sampling treatment; the output main capsule layer is used for outputting the data obtained by the up-sampling processing in the path expansion module after the convolution processing; a jump connection layer for cutting and copying low-level features in the path contraction module and for up-sampling in the path expansion module; the classification module comprises a classification capsule layer with a plurality of capsules, and the activation vector module length of each capsule in the classification capsule layer is used for calculating the probability of whether an instance of each class exists, so that the data analysis and training of a monitoring data set for testing corresponding to each problem class (or abnormal data group type) are finally realized, and a neural network analysis model aiming at a plurality of problem classes (or abnormal data group types) is obtained.
In a preferred embodiment, after determining the problem existing in the dc power supply system, a corresponding problem solution is determined according to a pre-stored problem type-solution correspondence table, and the problem solution is transmitted to the relevant person.
The working principle and beneficial effects of the technical scheme are as follows: after determining the problems existing in the direct-current power supply system, determining corresponding problem solutions according to a pre-stored problem type-solution corresponding table, and sending the problem solutions to related personnel. To find out a preset reasonable solution for the staff to process.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The method for detecting the abnormality of the follow current loop of the parallel direct current power supply system is characterized by comprising the following steps of:
the direct current bus voltage of the parallel direct current power supply system is regulated down to a preset first voltage value through the intelligent management terminal;
detecting a first current value of a continuous loop through a shunt preset on the continuous loop, and sending the first current value to an intelligent management terminal;
and comparing the first current value with a preset first current threshold value through the intelligent management terminal, and judging whether the follow current loop is abnormal or not according to a comparison result.
2. The method for detecting abnormality of a freewheel loop of a parallel direct current power supply system according to claim 1 characterized in that the parallel direct current power supply system is composed of a plurality of parallel branches, each parallel branch is composed of at least one storage battery connected in series;
the freewheeling circuit is a closed circuit formed by connecting two ends of each parallel shunt with a direct current bus through freewheeling diodes, and the freewheeling diodes are arranged at the positive and negative output ends of each parallel shunt;
and a shunt is arranged on each continuous loop and is in communication connection with the intelligent management terminal.
3. The method for detecting an abnormality of a freewheeling circuit of a parallel dc power supply system according to claim 1, wherein the step of reducing the dc bus voltage of the parallel dc power supply system to a preset first voltage value by the intelligent management terminal includes:
timing is carried out through the intelligent management terminal, and when the timing duration meets the detection period of the preset follow current loop, the preparation work for detecting the abnormality of the follow current loop is started;
when the preparation work of the follow current loop abnormality detection is carried out, an intelligent management terminal is used for controlling an AC-DC module in a parallel direct current power supply system to downwards regulate the output voltage to a preset first voltage value, so that the DC-DC module is switched to a discharge state;
and controlling the discharge output voltage of the DC-DC module in the parallel direct-current power supply system to be regulated to a preset first voltage value through the intelligent management terminal, so that the direct-current bus voltage of the parallel power supply system is kept at the preset first voltage value.
4. The method for detecting abnormality of a freewheeling circuit of a parallel dc power supply system according to claim 1, further comprising detecting abnormality of a freewheeling diode on the freewheeling circuit, the detection method comprising:
the discharging output voltage of the DC-DC module is regulated back to a rated output value through the intelligent management terminal; the load is borne by the DC-DC module;
the output voltage of the AC-DC module is regulated back to a rated output value through the intelligent management terminal, so that the load is borne by the AC-DC module and the DC-DC module is charged;
and detecting a second voltage value of the freewheel loop, and judging that the freewheel diode on the freewheel loop has a short circuit abnormality when the second voltage value is smaller than a preset second voltage threshold value.
5. The method for detecting abnormality of a freewheel loop of a parallel dc power supply system according to claim 1 further comprising the step of locating a problem existing in the parallel dc power supply system through an intelligent management terminal when abnormality occurs in the freewheel loop, as follows:
the method comprises the steps that data monitoring is conducted on a parallel direct-current power supply system through an intelligent management terminal in advance to generate a monitoring data set, and the monitoring data set is stored in a cloud platform through the intelligent management terminal;
when detecting that the follow current loop is abnormal, the monitoring data set of the parallel direct current power supply system corresponding to the follow current loop is called;
analyzing the monitoring data set, and determining abnormal data and corresponding data types thereof;
and comparing the abnormal data and the corresponding data types in a preset abnormal data comparison library to determine the problems of the direct current power supply system.
6. The method for detecting an abnormality in a freewheeling circuit of a parallel dc power supply system according to claim 5, wherein analyzing the monitored data set to determine abnormal data and a data type corresponding to the abnormal data includes:
determining relative current information of the freewheeling circuit and voltage information at two ends of the freewheeling diode in a plurality of detection periods according to the monitoring data set;
fitting a monocycle current information change curve by utilizing current information of corresponding freewheel loops in a plurality of detection cycles;
fitting a single-period voltage information change curve by utilizing voltage information at two ends of a corresponding freewheeling diode in a plurality of detection periods in the past;
determining corresponding loop current information of an abnormal follow current loop and voltage information at two ends of a follow current diode in the current detection period according to the monitoring data set;
generating a first curve according to corresponding loop current information in the current detection period;
generating a second curve according to the voltage information at two ends of the corresponding freewheeling diode in the current detection period;
matching and comparing the first curve with a single-period current information change curve, and judging whether current information abnormality occurs according to a matching result;
and matching and comparing the second curve with the single-period voltage information change curve, and judging whether current information abnormality occurs according to a matching result.
7. The method for detecting abnormality of freewheeling circuit of parallel DC power supply system according to claim 6, wherein comparing the second curve with the variation curve of single-period voltage information, and judging whether the abnormality of voltage information occurs according to the result of the matching comprises:
determining a preset segmentation length, dividing a first curve into a plurality of first curve segments according to the segmentation length and a preset first segmentation rule, and dividing a single-period current information change curve into a plurality of third curve segments according to the segmentation length and the preset first segmentation rule;
determining the time corresponding relation between the first curve segment and the third curve segment in a single detection period, and grouping the plurality of first curve segments and the plurality of third curve segments pairwise;
and matching the first curve segment and the third curve segment of any group to obtain a matching value, and determining that the data corresponding to the first curve segment and the third curve segment of the group is abnormal data when the matching value is smaller than a preset matching threshold value.
8. The method for detecting an abnormality in a freewheeling circuit of a parallel dc power supply system according to claim 5, wherein analyzing the monitored data set to determine abnormal data and a data type corresponding thereto further comprises:
extracting a plurality of monitoring data sets for testing stored in a cloud database, and determining abnormal data and corresponding data types of the abnormal data in each monitoring data set for testing;
taking a plurality of monitoring data sets for testing as training set data, and taking abnormal data in each monitoring data set for testing and corresponding data types thereof as verification set data;
the U-net model is used as a basic network architecture to fuse the capsule model and establish an analysis model;
training the analysis model by using the training set data and the verification set data to obtain a trained analysis model;
and analyzing the monitoring data set by using the trained analysis model, and determining abnormal data and data types corresponding to the abnormal data.
9. The method for detecting abnormality of a freewheel loop of a parallel dc power supply system according to claim 8 characterized in that the analysis model includes:
the feature extraction module comprises an input convolution layer and a convolution capsule layer, wherein the input convolution layer is used for extracting low-level features of an input monitoring data set for testing, and the convolution capsule layer is used for converting the extracted low-level features into capsules through convolution filtering;
the path shrinkage module comprises a plurality of main capsule layers and is used for carrying out downsampling treatment on the capsules obtained by the feature extraction module;
the path expansion module comprises a plurality of main capsule layers and a plurality of deconvolution capsule layers which are staggered with each other and is used for carrying out up-sampling processing on the capsule subjected to the down-sampling processing; the output main capsule layer is used for outputting the data obtained by the up-sampling processing in the path expansion module after the convolution processing; a jump connection layer for cutting and copying low-level features in the path contraction module and for up-sampling in the path expansion module;
the classification module comprises a classification capsule layer with a plurality of capsules, and the activation vector modulo length of each capsule in the classification capsule layer is used for calculating the probability of whether the instance of each class exists.
10. The method according to claim 5, wherein after determining the problem of the dc power system, determining a corresponding problem solution according to a pre-stored problem type-solution correspondence table, and sending the problem solution to a person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310537383.5A CN116299030B (en) | 2023-05-15 | 2023-05-15 | Method for detecting abnormality of follow current loop of parallel direct current power supply system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310537383.5A CN116299030B (en) | 2023-05-15 | 2023-05-15 | Method for detecting abnormality of follow current loop of parallel direct current power supply system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116299030A true CN116299030A (en) | 2023-06-23 |
| CN116299030B CN116299030B (en) | 2023-08-01 |
Family
ID=86801654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310537383.5A Active CN116299030B (en) | 2023-05-15 | 2023-05-15 | Method for detecting abnormality of follow current loop of parallel direct current power supply system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116299030B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116505105A (en) * | 2023-06-27 | 2023-07-28 | 深圳市泰昂能源科技股份有限公司 | Storage battery on-line management method based on parallel module |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR9705930A (en) * | 1997-11-25 | 1999-10-13 | Nelson Guilherme Bardini | Matrix or groups of diodes, operating under special conditions for switching RF signals |
| CN102118913A (en) * | 2009-12-31 | 2011-07-06 | 北大方正集团有限公司 | Device and method for monitoring abnormal state of light-emitting diode |
| CN103091598A (en) * | 2013-01-28 | 2013-05-08 | 中国矿业大学 | Fault diagnosis method for switch reluctance motor dual-switch power converter fly-wheel diode |
| US20190041938A1 (en) * | 2018-07-27 | 2019-02-07 | Intel Corporation | Fault tolerance for power loss imminent circuitry failure |
| CN111596195A (en) * | 2020-05-13 | 2020-08-28 | 北京星河泰视特科技有限公司 | Method and device for detecting diode circuit |
| CN112798976A (en) * | 2020-12-14 | 2021-05-14 | 航天科工防御技术研究试验中心 | Power failure judgment method, equipment, electronic equipment and storage medium |
| CN114640168A (en) * | 2022-03-30 | 2022-06-17 | 石家庄通合电子科技股份有限公司 | Parallel DC power supply freewheeling circuit diode fault judgment method and circuit thereof |
| CN115934714A (en) * | 2022-11-30 | 2023-04-07 | 国网浙江省电力有限公司 | Information storage and classification system for micro-grid |
-
2023
- 2023-05-15 CN CN202310537383.5A patent/CN116299030B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR9705930A (en) * | 1997-11-25 | 1999-10-13 | Nelson Guilherme Bardini | Matrix or groups of diodes, operating under special conditions for switching RF signals |
| CN102118913A (en) * | 2009-12-31 | 2011-07-06 | 北大方正集团有限公司 | Device and method for monitoring abnormal state of light-emitting diode |
| CN103091598A (en) * | 2013-01-28 | 2013-05-08 | 中国矿业大学 | Fault diagnosis method for switch reluctance motor dual-switch power converter fly-wheel diode |
| US20190041938A1 (en) * | 2018-07-27 | 2019-02-07 | Intel Corporation | Fault tolerance for power loss imminent circuitry failure |
| CN111596195A (en) * | 2020-05-13 | 2020-08-28 | 北京星河泰视特科技有限公司 | Method and device for detecting diode circuit |
| CN112798976A (en) * | 2020-12-14 | 2021-05-14 | 航天科工防御技术研究试验中心 | Power failure judgment method, equipment, electronic equipment and storage medium |
| CN114640168A (en) * | 2022-03-30 | 2022-06-17 | 石家庄通合电子科技股份有限公司 | Parallel DC power supply freewheeling circuit diode fault judgment method and circuit thereof |
| CN115934714A (en) * | 2022-11-30 | 2023-04-07 | 国网浙江省电力有限公司 | Information storage and classification system for micro-grid |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116505105A (en) * | 2023-06-27 | 2023-07-28 | 深圳市泰昂能源科技股份有限公司 | Storage battery on-line management method based on parallel module |
| CN116505105B (en) * | 2023-06-27 | 2023-11-17 | 深圳市泰昂能源科技股份有限公司 | Storage battery on-line management method based on parallel module |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116299030B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111027058B (en) | Method for detecting data attack of power system, computer equipment and storage medium | |
| Bagheri et al. | A robust transform-domain deep convolutional network for voltage dip classification | |
| CN116299030B (en) | Method for detecting abnormality of follow current loop of parallel direct current power supply system | |
| Santoso et al. | A scalable PQ event identification system | |
| CN109409444B (en) | Multivariate power grid fault type discrimination method based on prior probability | |
| CN110516912A (en) | A kind of power distribution station family becomes the recognition methods of relationship | |
| CN110322135A (en) | A kind of method for real-time monitoring and system of grid equipment safe operation state | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN109272713A (en) | A kind of the breakdown judge method for early warning and system of photovoltaic plant group set of strings | |
| CN108287317A (en) | Power of battery prediction model generation method and system, power forecasting method and system | |
| CN110311709A (en) | Power information acquisition system fault distinguishing method | |
| CN104715342A (en) | Electrical equipment fault handling and aid decision making method based on case-based reasoning | |
| CN108304931A (en) | A kind of Condition-based Maintenance of Substation Equipment method for diagnosing faults | |
| CN109582657A (en) | Capacitor faults prediction technique based on machine learning and big data analysis | |
| CN113283602A (en) | Power grid system fault diagnosis method based on offline knowledge learning and online dynamic correction | |
| CN113092900A (en) | State detection method and device of photovoltaic inverter and computer readable storage medium | |
| Singh et al. | Power system fault diagnosis using fuzzy decision tree | |
| CN110378585A (en) | Electric network fault disposes calculating task layout call method, system and storage medium | |
| CN112924813B (en) | Power distribution network short-circuit fault monitoring method and device based on electrical data | |
| CN113702767A (en) | Island direct-current microgrid fault diagnosis method based on wavelet sliding window energy | |
| CN109450051A (en) | A kind of battery system and its control method | |
| CN107256415A (en) | A kind of computational methods and computing system of power system operation mode scene | |
| CN116154829A (en) | Power battery echelon utilization power grid energy storage system | |
| CN116432027A (en) | Transformer running state detection method and system based on vibration signals | |
| CN115115131A (en) | Multi-center power system fault prediction method and system based on transfer learning |
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 |