CN116702081A - Intelligent inspection method for power distribution equipment based on artificial intelligence - Google Patents
Intelligent inspection method for power distribution equipment based on artificial intelligence Download PDFInfo
- Publication number
- CN116702081A CN116702081A CN202310984001.3A CN202310984001A CN116702081A CN 116702081 A CN116702081 A CN 116702081A CN 202310984001 A CN202310984001 A CN 202310984001A CN 116702081 A CN116702081 A CN 116702081A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- value
- period
- obtaining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000007689 inspection Methods 0.000 title claims abstract description 24
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 185
- 230000005856 abnormality Effects 0.000 claims abstract description 58
- 230000005611 electricity Effects 0.000 claims abstract description 35
- 238000012512 characterization method Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 15
- 241000728173 Sarima Species 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000001932 seasonal effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
- H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention relates to the technical field of power distribution devices, in particular to an intelligent inspection method for power distribution equipment based on artificial intelligence; decomposing the monitored data sequence; and obtaining a first degree of abnormality of the electricity according to the change characteristics of the trend item, and obtaining a second degree of abnormality of the electricity according to the residual item and the change characteristics of the trend item. And obtaining an abnormal fluctuation value and an abnormal characteristic value according to the data sequence, the first abnormal degree of electricity consumption and the second abnormal degree of electricity consumption. Obtaining a moving average window according to the abnormal characteristic value, and obtaining abnormal weight according to the data difference of the data points and the abnormal characteristic value; and obtaining a moving average value according to the data points and the abnormal weights in the moving average window and constructing a prediction model. Finally, the invention adjusts the size of the moving average window and the self-adaptive abnormal weight according to the abnormal condition of the data sequence, improves the prediction reliability and ensures the inspection accuracy of the power distribution equipment.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent inspection method for power distribution equipment based on artificial intelligence.
Background
Distribution equipment refers to various devices for transmitting power from a power transmission system to end users, and can play an important role in converting high-voltage power into low-voltage power, distributing electric energy and protecting a power system; common power distribution equipment is: transformers, distribution boards, power control devices, etc. The intelligent inspection of the power distribution equipment is realized by utilizing advanced technology and method to conduct intelligent inspection on the power distribution equipment so as to realize automation, high efficiency and accuracy. The wireless sensor nodes are arranged on the power distribution equipment, so that parameters such as current, voltage and temperature are monitored in real time; and monitoring the running state of the power distribution equipment according to the change of various data, and judging whether the power distribution equipment has faults or not.
In the prior art, when the running state of the power distribution equipment is monitored, whether an abnormality occurs is determined according to the difference between an actual value and a predicted value mainly by analyzing the change trend of data, and the power consumption behavior is easily influenced by seasons and periods, so that the data is predicted by using a SARIMA model, and the SARIMA model is a seasonal difference autoregressive sliding average model and is suitable for seasonal and periodic time sequence prediction. However, the probability that the data fluctuation of the operation of the power distribution equipment is influenced by environmental factors is high, the influence degree of sudden abnormal conditions is not considered in the construction of the SARIMA model, and a proper moving average item in the model is difficult to determine, so that a prediction result is inaccurate; and finally, the inspection reliability of the power distribution equipment is affected.
Disclosure of Invention
In order to solve the problem that the prediction result is inaccurate because the influence degree of the emergency abnormal situation is not considered in the construction of the SARIMA model; the invention aims to provide an intelligent inspection method for power distribution equipment based on artificial intelligence, which is characterized by comprising the following steps of:
acquiring a data sequence for monitoring the running state of the power distribution equipment; decomposing the data sequence to obtain a trend item, a period item, a residual item and a data interval of the data sequence; obtaining first power consumption abnormal degrees of different data intervals according to the change characteristics of the data in the trend item; obtaining second abnormal degrees of electricity consumption of different data intervals according to the change characteristics of the data in the residual error items and the data characteristics in the trend items;
obtaining an abnormal fluctuation value of each period according to the change characteristics of the data sequence corresponding to each period in the period item, the first power consumption abnormality degree and the second power consumption abnormality degree; obtaining an abnormal characteristic value of each period according to the difference characteristic of the abnormal fluctuation value between each period and other periods;
obtaining the size of a moving average window according to the abnormal characteristic values of different periods; obtaining abnormal weights of the data points according to data difference characteristics of the data points in the data sequence and other data points in a preset neighborhood range and abnormal characteristic values of periods of the data points; obtaining a moving average according to the data characteristics of the data points in the moving average window and the abnormal weights; and constructing a prediction model according to the moving average value and carrying out inspection monitoring on the power distribution equipment.
Further, the step of decomposing the data sequence to obtain a trend term, a period term, a residual term, and a data interval of the data sequence includes:
decomposing the data sequence through an STL time sequence decomposition algorithm to obtain a trend term, a period term and a residual term of the data sequence; and for any extreme point in the trend item, dividing the trend item according to the extreme point and other adjacent extreme points to obtain a section of data interval.
Further, the step of obtaining the first power consumption abnormality degree of different data intervals according to the change characteristics of the data in the trend item includes:
calculating the absolute value of the difference value of the amplitude values of the two extreme points of the data interval as an amplitude difference value; calculating the time difference value of the two extreme points of the data interval to be used as a time difference value; calculating the ratio of the amplitude difference value to the time difference value to obtain an interval variation degree value;
calculating the average value of the absolute values of the tangential slopes of all data points in the data interval to obtain an interval variation trend value; and calculating the product of the interval change degree value and the interval change trend value and performing positive correlation mapping to obtain the first abnormal degree of electricity consumption of the data interval.
Further, the step of obtaining the second abnormal degree of electricity consumption of different data intervals according to the change characteristics of the data in the residual error item and the data characteristics in the trend item comprises the following steps:
calculating a fitting function between two data points of any two adjacent data points in a residual error item interval corresponding to the data interval, and calculating a fixed integral of the fitting function to obtain residual error degree; calculating the sum value of all residual difference constants in the interval of the residual error items corresponding to the data interval, and obtaining a residual error anomaly characterization value;
and calculating the product and positive correlation mapping of the maximum amplitude value in the data interval of the trend item and the residual error abnormality degree characterization value, and obtaining the second power consumption abnormality degree of the data interval.
Further, the step of obtaining the abnormal fluctuation value of each period according to the change characteristic of the data sequence corresponding to each period in the period item, the first degree of abnormality of the power consumption and the second degree of abnormality of the power consumption includes:
for any period in the period items, calculating the variance of the amplitude of the data points in the data sequence corresponding to the period to obtain a fluctuation characterization value; calculating accumulated values of power consumption first abnormal degrees and power consumption second abnormal degrees of all data intervals corresponding to the period to obtain a period abnormal representation value; and calculating the product of the fluctuation characteristic value and the period abnormal characteristic value to obtain the period abnormal fluctuation value.
Further, the step of obtaining the abnormal characteristic value of each cycle from the difference characteristic of the abnormal fluctuation value between each cycle and other cycles includes:
for any period, calculating the difference value between the abnormal fluctuation value and the minimum value of the abnormal fluctuation value of the period to obtain an abnormal difference characterization value; calculating a pearson correlation coefficient value and a negative correlation mapping between the period and the data sequence of the period of the minimum value of the abnormal fluctuation value to obtain an abnormal correlation characterization value; and calculating the product of the abnormal difference characterization value and the abnormal correlation characterization value to obtain the abnormal characteristic value of the period.
Further, the step of obtaining the size of the moving average window according to the abnormal characteristic values of different periods includes:
and calculating the product of the average value of the abnormal characteristic values of all the periods of the data sequence and a preset first numerical value, and rounding upwards to obtain the size of a moving average window.
Further, the step of obtaining the abnormal weight of the data point according to the data difference characteristic of the data point in the data sequence and other data points in the preset neighborhood range and the abnormal characteristic value of the period of the data point comprises the following steps:
and for any one data point of the data sequence, calculating the average value of amplitude differences of the any one data point and other data points in a preset neighborhood range to obtain a data difference characteristic value, calculating the product of the absolute value of the data difference characteristic value and an abnormal characteristic value of the period of the any one data point, and normalizing to obtain the abnormal weight of the any one data point.
Further, the step of obtaining a moving average from the data characteristics of the data points within the moving average window and the outlier weights comprises:
and calculating the average value of the products of the amplitudes of all data points and the abnormal weights in a moving average window of the data sequence, and obtaining the moving average value.
Further, the step of constructing a prediction model according to the moving average value and carrying out patrol monitoring of the power distribution equipment comprises the following steps:
constructing an SARIMA model according to the moving average value, and obtaining a predicted value of the data sequence through the SARIMA model; calculating the absolute value of the difference between the predicted value and the corresponding actual value to obtain an abnormal index of the power distribution equipment; when the abnormal index of the power distribution equipment does not exceed the preset abnormal threshold, the power distribution equipment is judged to be normal in operation, and when the abnormal index of the power distribution equipment exceeds the preset abnormal threshold, the power distribution equipment is judged to be abnormal and early warning is needed.
The invention has the following beneficial effects:
in the embodiment of the invention, the data sequence is decomposed to obtain a trend item, a period item, a residual item and a data interval of the data sequence; different abnormal characteristics of the data sequence can be characterized in detail according to data characteristics of different data intervals and different items, and the accuracy of subsequent analysis is improved. The first abnormal degree of electricity is used for representing the abnormal degree of the change of the data sequence through the change condition in the trend item; the second degree of abnormality of electricity is used for representing the degree of abnormality of the data sequence related to factors such as random noise and the like through the data characteristics of the residual error item and the trend item. The abnormal fluctuation value is calculated to reflect the abnormal degree characteristics of different periods of the data sequence, and the abnormal characteristic value is calculated to more accurately reflect the abnormal degree relation of different periods according to the abnormal fluctuation value difference conditions among different periods, so that the size of a moving average window is more accurately obtained, and the accuracy of final prediction is improved. The purpose of calculating the abnormal weight is to consider the abnormal electricity consumption condition of the data point, determine the importance degree of the data point in the prediction process, and further improve the final prediction accuracy. And finally, a prediction model is built according to the moving average value, so that the reliability of prediction is improved, and the accuracy of inspection and monitoring of the power distribution equipment is further ensured.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an intelligent inspection method for a power distribution device based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of an intelligent inspection method for power distribution equipment based on artificial intelligence according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an intelligent inspection method for power distribution equipment based on artificial intelligence, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an intelligent inspection method for a power distribution device based on artificial intelligence according to an embodiment of the present invention is shown, where the method includes the following steps:
step S1, acquiring a data sequence for monitoring the running state of power distribution equipment; decomposing the data sequence to obtain a trend item, a period item, a residual item and a data interval of the data sequence; obtaining first power consumption abnormality degrees of different data intervals according to the change characteristics of the data in the trend item; and obtaining the second abnormal degree of electricity consumption of different data intervals according to the change characteristics of the data in the residual error item and the data characteristics in the trend item.
In the embodiment of the invention, the implementation scene is intelligent patrol of the power distribution equipment. Firstly, acquiring a data sequence for monitoring the running state of power distribution equipment, and acquiring running data, such as current, voltage, temperature and the like, of the power distribution equipment through a wireless sensor, wherein the data sequence is generally called as the running state in the embodiment of the invention; it should be noted that, the subsequent processing methods for all the running state parameters are the same, and the implementer can collect the relevant parameters according to the implementation scenario. In order to improve the accuracy of subsequent analysis, the missing data is complemented by using a linear difference method through the data acquired by the sensor, the data is denoised by a mean value filtering method, noise interference is reduced, the linear difference method and the mean value filtering method are required to be described in the prior art, and specific calculation steps are not repeated, so that a data sequence for monitoring the running state of the power distribution equipment is obtained.
Further, in order to accurately analyze the change trend characteristics of the data sequence of the running state of the monitoring distribution equipment in detail, the prediction accuracy is improved; the data sequence is decomposed to obtain trend terms, period terms, residual terms and data intervals of the data sequence.
Preferably, in one embodiment of the present invention, the data sequence is decomposed by an STL time sequence decomposition algorithm, and it should be noted that, the STL algorithm is called as a whole-serial-Loss, and is an algorithm for decomposing the time sequence into a Trend term, a season term and a residual term by a filtering mode; the trend item reflects the long-term change trend of the sequence, the seasonal item reflects the periodical trend of the sequence change, the periodical item is expressed later, the residual item represents the rest of the decomposed trend item and the seasonal item, and the random noise and other conditions are reflected. It should be noted that, the STL algorithm belongs to the prior art, and specific decomposition steps are not repeated; after the data sequence is decomposed by STL, the change characteristics of the data sequence can be more accurately characterized. Obtaining trend items, period items and residual items of a data sequence; for any extreme point in the trend item, dividing the trend item according to the extreme point and other adjacent extreme points to obtain a data interval; it should be noted that, in the embodiment of the present invention, the extreme point is divided from the other extreme points adjacent to the next extreme point, and two data points at two ends of the trend term are not considered, that is, different data intervals are obtained from the range from the first extreme point to the last extreme point. The purpose of acquiring different data intervals is to more accurately analyze the abnormal situation of the variation trend of the data sequence at different moments.
Because the change trend of the monitored data sequence of the power distribution equipment is stable under the normal condition, if larger change fluctuation occurs in a certain period of time, the power distribution equipment is possibly influenced by abnormality such as environmental factors, and the abnormal degree of the change needs to be analyzed in order to improve the prediction accuracy of the subsequent data sequence. Because the trend item reflects the change trend of the sequence, the first abnormal degree of electricity consumption of different data intervals is obtained according to the change characteristics of the data in the trend item.
Preferably, in one embodiment of the present invention, obtaining the first degree of abnormality of the electricity consumption includes: calculating the absolute value of the difference value of the amplitude values of the two extreme points of the data interval as an amplitude difference value; when the amplitude difference value between the maximum value point and the minimum value point is larger, the trend of the data sequence in the data interval is larger, and the numerical value of the data sequence is abnormally fluctuated. Calculating the time difference value of two extreme points of the data interval as a time difference value; and calculating the ratio of the amplitude difference value to the time difference value to obtain the interval variation degree value. When the time difference value is smaller and the amplitude difference value is larger, the interval change degree value is larger, the change trend and the change degree of the data interval are larger, and the data sequence has more drastic fluctuation; when the interval variation degree value is smaller, the variation trend and variation degree of the data interval are smaller, and the data sequence variation is smoother. Calculating the average value of the absolute values of the tangential slopes of all data points in the data interval to obtain an interval variation trend value; when the interval change trend value is larger, the trend item is more obvious in an increasing or decreasing trend in the data interval, and the change degree of the data sequence in the data interval is more obvious. Calculating the product of the interval change degree value and the interval change trend value and performing positive correlation mapping to obtain the first abnormal degree of electricity consumption of the data interval; when the first degree of abnormality of the power consumption is larger, this means that the degree of variation of the data sequence is more severe and abnormal in the data section. The formula for obtaining the first degree of abnormality of the power consumption comprises the following steps:
in the method, in the process of the invention,indicating a first degree of abnormality in electricity consumption, +.>Representing the magnitude difference value, +.>Representing a time difference value,/->Representing the value of the interval change trend,/->Indicating the extent of change value of the interval. />The normalization function is represented for the purpose of positive correlation mapping.
After the first degree of abnormality of electricity consumption is obtained through the trend term, in order to improve the analysis accuracy of the degree of abnormality of the data sequence, the residual term can reflect random noise which cannot be interpreted through the trend term and the period term, aperiodic variation and other influence factors which cannot be captured; and obtaining the second abnormal degree of electricity consumption of different data intervals according to the change characteristics of the data in the residual error item and the data characteristics in the trend item.
Preferably, in one embodiment of the present invention, obtaining the second degree of abnormality of the electricity consumption includes: for any two data points in the interval of the residual error item corresponding to the data interval, calculating a fitting function between the two data points, wherein the calculation is performed between any data point and the next adjacent data point in the embodiment of the invention; the fitting function uses Bezier curve to fit, the algorithm belongs to the prior art, and the specific fitting steps are not repeated. Calculating the fixed integral of the fitting function to obtain the residual difference constant; the constant integral represents the area of the integrated function within the interval, and the area of the calculated continuous data points represents the degree of abnormality of the data held in the residual term, and the larger the residual, the larger the abnormality of the data sequence. Calculating the sum value of residual error abnormality degrees in the intervals of the residual error items corresponding to the data intervals, and obtaining a residual error abnormality degree representation value; the larger the residual anomaly characterization value, the more anomalous the data sequence is in the data interval. Calculating the product and positive correlation mapping of the maximum amplitude value in the data interval of the trend item and the residual error abnormality degree characterization value, and obtaining the second power consumption abnormality degree of the data interval; the data point corresponding to the maximum amplitude has the maximum variation trend, and the more likely to have abnormality, the abnormal condition of the data interval is represented according to the amplitude degree of the data point. The greater the second degree of abnormality when power is used means that the greater the degree of abnormality of the data sequence in the data section. The formula for obtaining the second degree of abnormality of the power consumption comprises the following steps:
in the method, in the process of the invention,indicating the second degree of abnormality of electricity consumption, +.>Maximum amplitude point of trend item representing data interval, +.>Data point number representing residual term corresponding to data interval, < ->Indicate->Residual anomalies of data points, +.>And representing the residual error anomaly degree representation value of the data interval. />The normalization function is represented for the purpose of positive correlation mapping.
Thus, the first electricity consumption abnormality degree and the second electricity consumption abnormality degree of different data intervals are obtained, and the subsequent steps need to analyze abnormal conditions of different periods in the period items.
Step S2, obtaining an abnormal fluctuation value of each period according to the change characteristics of the data sequence corresponding to each period in the period item, the first abnormal degree of electricity consumption and the second abnormal degree of electricity consumption; the abnormal characteristic value of each cycle is obtained from the difference characteristic of the abnormal fluctuation value between each cycle and the other cycles.
The monitored data sequence of the power distribution device follows the periodic variation in the power consumption. Therefore, according to the variation of the period term, the data sequence has a plurality of similar periods, and each period has a certain period variation although not having strict period characteristics. When the SARIMA model is built, the moving average term is used for carrying out average estimation on a predicted value part of the data sequence; in order to improve the prediction accuracy, it is necessary to analyze the abnormal condition of the period of each data sequence. Since each cycle includes a plurality of data sections, the abnormal fluctuation value of each cycle is obtained according to the change characteristics of the data sequence corresponding to each cycle in the cycle term, the first degree of abnormality of power consumption and the second degree of abnormality of power consumption.
Preferably, in one embodiment of the present invention, acquiring the abnormal fluctuation value includes: for any period in the period item, calculating the variance of the data point amplitude in the data sequence corresponding to the period to obtain a fluctuation characterization value; the larger the variance is, the larger the fluctuation characterization value is, which means that the more obvious the fluctuation of the data sequence in the period is, the less the data sequence accords with the characteristic of stable operation of the power distribution equipment, and the more serious the abnormal fluctuation is. Calculating accumulated values of the first power consumption degree and the second power consumption degree of all data intervals corresponding to the period to obtain a period abnormality characterization value; when the first abnormal degree of electricity consumption and the second abnormal degree of electricity consumption of the data interval in the period are larger, the data sequence changes abnormally in the period, and the period abnormal characteristic value is larger. Calculating the product of the fluctuation characteristic value and the period abnormality characteristic value to obtain the period abnormality fluctuation value; the larger the abnormal fluctuation value is, the more abnormal the data sequence change of the period is. The formula for acquiring the abnormal fluctuation value specifically comprises the following steps:
in the method, in the process of the invention,abnormal fluctuation value representing period, +.>Represents the number of data points in the cycle, +.>Indicate->Amplitude of data points, +.>Represents the mean value of the magnitudes of the data points during the period, +.>Representing a fluctuation characterization value; />The number of data intervals representing the period, +.>And->Respectively represent +.>The first power consumption degree and the second power consumption degree of the data interval; />Representing the periodic anomaly characterization value.
Further, after the abnormal characteristic value of each cycle is obtained, since it is difficult to judge the degree of abnormality by analyzing a single cycle, it is necessary to judge the abnormal condition of each cycle according to the magnitude relation of the abnormal characteristic values of different cycles, so that the abnormal characteristic value of each cycle is obtained according to the difference characteristics of the abnormal fluctuation values between each cycle and other cycles.
Preferably, in one embodiment of the present invention, acquiring the abnormality characteristic value includes: for any period, calculating the difference value between the abnormal fluctuation value and the minimum value of the abnormal fluctuation value of the period to obtain an abnormal difference characterization value; the greater the anomaly characterization value, the more severe the anomaly degree of the cycle. Calculating a pearson correlation coefficient value and a negative correlation mapping between the period and a data sequence of a period of the minimum value of the abnormal fluctuation value to obtain an abnormal correlation characterization value; when the pearson correlation coefficient is closer to 1, the data sequences of the two periods are more similar, and it is to be noted that the pearson correlation coefficient belongs to the prior art, and specific calculation steps are not repeated; therefore, when the abnormality related characteristic value is smaller, the data series of the period, which means that the period is more similar to the period of the minimum value of the abnormal fluctuation value, is smaller. Calculating the product of the abnormal difference characterization value and the abnormal correlation characterization value to obtain an abnormal characteristic value of the period; the smaller the abnormality characteristic value of the period means the lower the abnormality degree of the period, the more the change characteristic of the period is close to the minimum value of the abnormal fluctuation value, and the lower the abnormality characteristic value of the period means the more serious the abnormality degree of the period, the more the change characteristic of the period is not close to the minimum value of the abnormal fluctuation value.
After obtaining the abnormal characteristic value of each period, the size of the moving average window required by constructing the SARIMA model can be determined according to the abnormal degree of the period.
Step S3, obtaining the size of a moving average window according to abnormal characteristic values of different periods; obtaining abnormal weights of the data points according to data difference characteristics of the data points in the data sequence and other data points in a preset neighborhood range and abnormal characteristic values of periods of the data points; obtaining a moving average according to the data characteristics and the abnormal weights of the data points in the moving average window; and constructing a prediction model according to the moving average value and carrying out inspection monitoring on the power distribution equipment.
In calculating the moving average term, it is necessary to adjust the range of the average by using different weights and window sizes based on the average value of the history monitoring. First, it is necessary to determine the appropriate moving average window size, a shorter moving average window will more sensitively reflect recent data changes, and a longer window will more closely account for longer data changes, requiring a longer moving average window if a data anomaly occurs. The size of the moving average window is obtained according to the abnormal characteristic values of different periods.
Preferably, in one embodiment of the present invention, obtaining the size of the moving average window includes: and calculating the product of the average value of the abnormal characteristic values of all the periods of the data sequence and a preset first numerical value, and rounding upwards to obtain the size of a moving average window. The larger the average value of the abnormal characteristic values, the more data support is required for more accurate prediction, so the larger the moving average window is; the first value is preset to determine the basic size of the window, 10 in the implementation of the present invention, and the implementation can determine the window according to the implementation scenario.
Further, after determining the window size of the moving average, since the purpose of the present invention is to detect the operation state of the power distribution equipment, it is necessary to construct a data prediction model according to the change of each data point, and it is necessary to obtain a weight according to the change of each data point when calculating the moving average term. And obtaining the abnormal weight of the data point according to the data difference characteristics of the data point in the data sequence and other data points in the preset neighborhood range and the abnormal characteristic value of the period of the data point.
Preferably, in one embodiment of the present invention, acquiring the anomaly weight includes: for any one data point of the data sequence, calculating the average value of amplitude differences between the data point and other data points in a preset neighborhood range, and obtaining a data difference characteristic value; the larger the amplitude difference value between the data point and other data points in the preset neighborhood range is, the larger the data difference characteristic value is, which means that the larger the change degree of the data point is, the more power utilization abnormality is likely to exist in the data point, and the more data fluctuation condition of the data point needs to be considered in the subsequent prediction process. And calculating and normalizing the product of the absolute value of the data difference characteristic value and the abnormal characteristic value of the period of the data point to obtain the abnormal weight of the data point. If the abnormal characteristic value of the period is larger, the more serious the power consumption abnormality of the period is, and the more the abnormal condition of the period needs to be considered in the subsequent prediction process; therefore, the product of the two characteristics of the abnormal weight of the data point, when the abnormal weight is close to 1, the abnormal power consumption behavior of the data point in the period is indicated, the influence of the abnormal behavior on the subsequent moment is considered in the subsequent prediction process, and the prediction accuracy is improved. It should be noted that, the preset neighborhood range is a sequence length with the data point as the center and the length of 45 data points, and the implementer can determine according to the implementation scenario. The formula for acquiring the abnormal weight specifically comprises the following steps:
in the method, in the process of the invention,represents the>Abnormal weight of data points +_>Indicate->Abnormal characteristic value of period of data point, +.>Represents the>Amplitude of data points, +.>Representing the number of other data points than the data point in the preset neighborhood>Representing the +.o within the preset neighborhood>Amplitude of other data points, +.>Representing a data difference characteristic value; />Representing the normalization function.
Thus, after obtaining the abnormal weight of each data point, a moving average value can be obtained according to the data characteristics and the abnormal weight of the data point in the moving average window, which specifically comprises: and calculating the average value of the products of the amplitudes of all the data points and the abnormal weights in a moving average window of the data sequence, and obtaining the moving average value. By adding the moving average value obtained by the abnormal weights of different data points, the data characteristics and the change characteristics of the data points in the moving average window can be more accurately represented, and the accuracy of model construction is improved. The formula for obtaining the moving average value specifically includes:
in the method, in the process of the invention,represents a moving average, +.>Representing the number of data points within the moving average window, +.>Indicating +.>Abnormal weight of data points +_>Indicating +.>The magnitude of the data points.
Further, after the moving average term value is obtained, a prediction model can be built according to the moving average value, and inspection and monitoring of the power distribution equipment can be performed; the method specifically comprises the following steps: constructing an SARIMA model according to the moving average value, and obtaining a predicted value of the data sequence through the SARIMA model; it should be noted that the SARIMA model is a seasonal differential autoregressive moving average model, which belongs to the prior art, and specific calculation steps are not repeated. Calculating the absolute value of the difference between the predicted value and the corresponding actual value to obtain an abnormal index of the power distribution equipment; the greater the difference between the predicted value and the corresponding actual value, the more likely an abnormal fault may occur in the power distribution equipment. And when the abnormality index of the power distribution equipment exceeds the preset abnormality threshold, the power distribution equipment is judged to be abnormal and early warning is needed. In the embodiment of the invention, the preset abnormal threshold is 5, and the implementer can determine according to the implementation scene.
In summary, the embodiment of the invention provides an intelligent inspection method for power distribution equipment based on artificial intelligence, which decomposes a monitored data sequence; and obtaining a first degree of abnormality of the electricity according to the change characteristics of the trend item, and obtaining a second degree of abnormality of the electricity according to the residual item and the change characteristics of the trend item. And obtaining an abnormal fluctuation value and an abnormal characteristic value according to the data sequence, the first abnormal degree of electricity consumption and the second abnormal degree of electricity consumption. Obtaining a moving average window according to the abnormal characteristic value, and obtaining abnormal weight according to the data difference of the data points and the abnormal characteristic value; and obtaining a moving average value according to the data points and the abnormal weights in the moving average window and constructing a prediction model. Finally, the invention adjusts the size of the moving average window and the self-adaptive abnormal weight according to the abnormal condition of the data sequence, improves the prediction reliability and ensures the inspection accuracy of the power distribution equipment.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. An intelligent inspection method for power distribution equipment based on artificial intelligence is characterized by comprising the following steps:
acquiring a data sequence for monitoring the running state of the power distribution equipment; decomposing the data sequence to obtain a trend item, a period item, a residual item and a data interval of the data sequence; obtaining first power consumption abnormal degrees of different data intervals according to the change characteristics of the data in the trend item; obtaining second abnormal degrees of electricity consumption of different data intervals according to the change characteristics of the data in the residual error items and the data characteristics in the trend items;
obtaining an abnormal fluctuation value of each period according to the change characteristics of the data sequence corresponding to each period in the period item, the first power consumption abnormality degree and the second power consumption abnormality degree; obtaining an abnormal characteristic value of each period according to the difference characteristic of the abnormal fluctuation value between each period and other periods;
obtaining the size of a moving average window according to the abnormal characteristic values of different periods; obtaining abnormal weights of the data points according to data difference characteristics of the data points in the data sequence and other data points in a preset neighborhood range and abnormal characteristic values of periods of the data points; obtaining a moving average according to the data characteristics of the data points in the moving average window and the abnormal weights; and constructing a prediction model according to the moving average value and carrying out inspection monitoring on the power distribution equipment.
2. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of decomposing the data sequence to obtain trend items, period items, residual items and data intervals of the data sequence comprises:
decomposing the data sequence through an STL time sequence decomposition algorithm to obtain a trend term, a period term and a residual term of the data sequence; and for any extreme point in the trend item, dividing the trend item according to the extreme point and other adjacent extreme points to obtain a section of data interval.
3. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of obtaining the first degree of abnormality of electricity consumption of different data intervals according to the change characteristics of data in the trend item comprises:
calculating the absolute value of the difference value of the amplitude values of the two extreme points of the data interval as an amplitude difference value; calculating the time difference value of the two extreme points of the data interval to be used as a time difference value; calculating the ratio of the amplitude difference value to the time difference value to obtain an interval variation degree value;
calculating the average value of the absolute values of the tangential slopes of all data points in the data interval to obtain an interval variation trend value; and calculating the product of the interval change degree value and the interval change trend value and performing positive correlation mapping to obtain the first abnormal degree of electricity consumption of the data interval.
4. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of obtaining the second degree of abnormality of electricity consumption of different data intervals according to the change characteristics of data in the residual items and the data characteristics in the trend items comprises:
calculating a fitting function between two data points of any two adjacent data points in a residual error item interval corresponding to the data interval, and calculating a fixed integral of the fitting function to obtain residual error degree; calculating the sum value of all residual difference constants in the interval of the residual error items corresponding to the data interval, and obtaining a residual error anomaly characterization value;
and calculating the product and positive correlation mapping of the maximum amplitude value in the data interval of the trend item and the residual error abnormality degree characterization value, and obtaining the second power consumption abnormality degree of the data interval.
5. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of obtaining the abnormal fluctuation value of each period according to the change characteristics of the data sequence corresponding to each period in the period item, the first abnormal degree of electricity consumption and the second abnormal degree of electricity consumption comprises:
for any period in the period items, calculating the variance of the amplitude of the data points in the data sequence corresponding to the period to obtain a fluctuation characterization value; calculating accumulated values of power consumption first abnormal degrees and power consumption second abnormal degrees of all data intervals corresponding to the period to obtain a period abnormal representation value; and calculating the product of the fluctuation characteristic value and the period abnormal characteristic value to obtain the period abnormal fluctuation value.
6. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of obtaining an abnormal characteristic value of each cycle from a difference characteristic of the abnormal fluctuation value between each cycle and other cycles comprises:
for any period, calculating the difference value between the abnormal fluctuation value and the minimum value of the abnormal fluctuation value of the period to obtain an abnormal difference characterization value; calculating a pearson correlation coefficient value and a negative correlation mapping between the period and the data sequence of the period of the minimum value of the abnormal fluctuation value to obtain an abnormal correlation characterization value; and calculating the product of the abnormal difference characterization value and the abnormal correlation characterization value to obtain the abnormal characteristic value of the period.
7. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of obtaining the size of a moving average window according to the abnormal characteristic values of different periods comprises:
and calculating the product of the average value of the abnormal characteristic values of all the periods of the data sequence and a preset first numerical value, and rounding upwards to obtain the size of a moving average window.
8. The intelligent inspection method for power distribution equipment based on artificial intelligence according to claim 1, wherein the step of obtaining the abnormal weight of the data point according to the data difference characteristic of the data point in the data sequence and other data points in the preset neighborhood range and the abnormal characteristic value of the period of the data point comprises the following steps:
and for any one data point of the data sequence, calculating the average value of amplitude differences of the any one data point and other data points in a preset neighborhood range to obtain a data difference characteristic value, calculating the product of the absolute value of the any one data difference characteristic value and an abnormal characteristic value of the period in which the any one data point is positioned, and normalizing to obtain the abnormal weight of the data point.
9. The intelligent patrol method for power distribution equipment based on artificial intelligence according to claim 1, wherein said step of obtaining a moving average from data characteristics of data points within a moving average window and said abnormal weights comprises:
and calculating the average value of the products of the amplitudes of all data points and the abnormal weights in a moving average window of the data sequence, and obtaining the moving average value.
10. The intelligent inspection method for power distribution equipment based on artificial intelligence according to claim 1, wherein the steps of constructing a prediction model according to the moving average and performing inspection monitoring for the power distribution equipment comprise:
constructing an SARIMA model according to the moving average value, and obtaining a predicted value of the data sequence through the SARIMA model; calculating the absolute value of the difference between the predicted value and the corresponding actual value to obtain an abnormal index of the power distribution equipment; when the abnormal index of the power distribution equipment does not exceed the preset abnormal threshold, the power distribution equipment is judged to be normal in operation, and when the abnormal index of the power distribution equipment exceeds the preset abnormal threshold, the power distribution equipment is judged to be abnormal and early warning is needed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310984001.3A CN116702081B (en) | 2023-08-07 | 2023-08-07 | Intelligent inspection method for power distribution equipment based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310984001.3A CN116702081B (en) | 2023-08-07 | 2023-08-07 | Intelligent inspection method for power distribution equipment based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116702081A true CN116702081A (en) | 2023-09-05 |
| CN116702081B CN116702081B (en) | 2023-10-24 |
Family
ID=87837831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310984001.3A Active CN116702081B (en) | 2023-08-07 | 2023-08-07 | Intelligent inspection method for power distribution equipment based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702081B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116388111A (en) * | 2023-04-18 | 2023-07-04 | 杭州欣美成套电器制造有限公司 | In-situ measurement and control protection integrated device of electric micro-grid |
| CN116902177A (en) * | 2023-09-14 | 2023-10-20 | 山东航宇游艇发展有限公司 | Yacht abnormal state intelligent monitoring method and system based on Internet of things |
| CN116961242A (en) * | 2023-09-21 | 2023-10-27 | 浙江赫斯电气有限公司 | Real-time data management method and system for secondary fusion on-column circuit breaker |
| CN117057517A (en) * | 2023-10-12 | 2023-11-14 | 国网吉林省电力有限公司长春供电公司 | Efficient processing method and system for electric power data based on digital twin |
| CN117076934A (en) * | 2023-10-16 | 2023-11-17 | 罗普特科技集团股份有限公司 | Monitoring data acquisition and analysis method based on Internet of things |
| CN117112514A (en) * | 2023-10-23 | 2023-11-24 | 山东同利新材料有限公司 | Recording and storing method based on p-chloromethyl styrene production data |
| CN117109487A (en) * | 2023-10-23 | 2023-11-24 | 北京华力兴科技发展有限责任公司 | Automatic nondestructive measurement method for metal thickness |
| CN117293758A (en) * | 2023-11-24 | 2023-12-26 | 山东德源电力科技股份有限公司 | Automatic protection method for digital distribution feeder monitoring terminal based on fault identification |
| CN117312803A (en) * | 2023-11-29 | 2023-12-29 | 广州市悦到信息科技有限公司 | Digital processing method and system for cloud cooperative passenger transport service |
| CN117330816A (en) * | 2023-12-01 | 2024-01-02 | 南京中旭电子科技有限公司 | Monitoring data optimization method for Hall current sensor |
| CN117349711A (en) * | 2023-12-04 | 2024-01-05 | 湖南京辙科技有限公司 | Electronic tag data processing method and system for railway locomotive parts |
| CN117370917A (en) * | 2023-12-07 | 2024-01-09 | 城光（湖南）节能环保服务股份有限公司 | Urban intelligent street lamp service life prediction method and system |
| CN117407700A (en) * | 2023-12-14 | 2024-01-16 | 国网山东省电力公司莱芜供电公司 | Method for monitoring working environment in live working process |
| CN117411189A (en) * | 2023-12-14 | 2024-01-16 | 山东德源电力科技股份有限公司 | Monitoring data enhancement method of micro-grid coordination controller |
| CN117421610A (en) * | 2023-12-19 | 2024-01-19 | 山东德源电力科技股份有限公司 | Data anomaly analysis method for electric energy meter running state early warning |
| CN117572137A (en) * | 2024-01-17 | 2024-02-20 | 山东海纳智能装备科技股份有限公司 | Seven-level ANPC high-voltage frequency converter remote monitoring system |
| CN117648590A (en) * | 2024-01-30 | 2024-03-05 | 山东万洋石油科技有限公司 | Omnibearing gamma logging data optimization processing method |
| CN117786325A (en) * | 2024-02-27 | 2024-03-29 | 山东晨晖电子科技有限公司 | Ambient temperature wisdom early warning system of heavy-calibre thing networking water gauge |
| CN117786582A (en) * | 2024-02-23 | 2024-03-29 | 江苏斐能软件科技有限公司 | Intelligent monitoring method and system for abnormal power consumption state based on data driving |
| CN117786582B (en) * | 2024-02-23 | 2024-05-07 | 江苏斐能软件科技有限公司 | Intelligent monitoring method and system for abnormal power consumption state based on data driving |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909306A (en) * | 2018-09-17 | 2020-03-24 | 阿里巴巴集团控股有限公司 | Service abnormity detection method and device, electronic equipment and storage equipment |
| CN112149860A (en) * | 2019-06-28 | 2020-12-29 | 中国电力科学研究院有限公司 | Automatic anomaly detection method and system |
| CN113139610A (en) * | 2021-04-29 | 2021-07-20 | 国网河北省电力有限公司电力科学研究院 | Abnormity detection method and device for transformer monitoring data |
| KR20220132824A (en) * | 2021-03-24 | 2022-10-04 | 한국전력공사 | Distribution facility condition monitoring system and method |
| US20230082012A1 (en) * | 2021-06-24 | 2023-03-16 | Tencent Technology (Shenzhen) Company Limited | Service data processing method and apparatus, computer device, and storage medium |
| CN115994248A (en) * | 2023-03-24 | 2023-04-21 | 青岛精锐机械制造有限公司 | Data detection method and system for valve faults |
-
2023
- 2023-08-07 CN CN202310984001.3A patent/CN116702081B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909306A (en) * | 2018-09-17 | 2020-03-24 | 阿里巴巴集团控股有限公司 | Service abnormity detection method and device, electronic equipment and storage equipment |
| CN112149860A (en) * | 2019-06-28 | 2020-12-29 | 中国电力科学研究院有限公司 | Automatic anomaly detection method and system |
| KR20220132824A (en) * | 2021-03-24 | 2022-10-04 | 한국전력공사 | Distribution facility condition monitoring system and method |
| CN113139610A (en) * | 2021-04-29 | 2021-07-20 | 国网河北省电力有限公司电力科学研究院 | Abnormity detection method and device for transformer monitoring data |
| US20230082012A1 (en) * | 2021-06-24 | 2023-03-16 | Tencent Technology (Shenzhen) Company Limited | Service data processing method and apparatus, computer device, and storage medium |
| CN115994248A (en) * | 2023-03-24 | 2023-04-21 | 青岛精锐机械制造有限公司 | Data detection method and system for valve faults |
Non-Patent Citations (2)
| Title |
|---|
| LIAO, SHIWEN ET AL.: "Modeling and Analysis of Residential Electricity Consumption Statistics: A Tracy-Widom Mixture Density Approximation", 《IEEE ACCESS 》, pages 163558 - 163567 * |
| 张勇;关伟;: "预测交通流量时间序列的组合动态建模方法", 吉林大学学报(工学版), no. 05, pages 1209 - 1214 * |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116388111A (en) * | 2023-04-18 | 2023-07-04 | 杭州欣美成套电器制造有限公司 | In-situ measurement and control protection integrated device of electric micro-grid |
| CN116902177A (en) * | 2023-09-14 | 2023-10-20 | 山东航宇游艇发展有限公司 | Yacht abnormal state intelligent monitoring method and system based on Internet of things |
| CN116902177B (en) * | 2023-09-14 | 2023-12-08 | 山东航宇游艇发展有限公司 | Yacht abnormal state intelligent monitoring method and system based on Internet of things |
| CN116961242A (en) * | 2023-09-21 | 2023-10-27 | 浙江赫斯电气有限公司 | Real-time data management method and system for secondary fusion on-column circuit breaker |
| CN116961242B (en) * | 2023-09-21 | 2023-12-19 | 浙江赫斯电气有限公司 | Real-time data management method and system for secondary fusion on-column circuit breaker |
| CN117057517A (en) * | 2023-10-12 | 2023-11-14 | 国网吉林省电力有限公司长春供电公司 | Efficient processing method and system for electric power data based on digital twin |
| CN117057517B (en) * | 2023-10-12 | 2024-01-12 | 国网吉林省电力有限公司长春供电公司 | Efficient processing method and system for electric power data based on digital twin |
| CN117076934B (en) * | 2023-10-16 | 2023-12-26 | 罗普特科技集团股份有限公司 | Monitoring data acquisition and analysis method based on Internet of things |
| CN117076934A (en) * | 2023-10-16 | 2023-11-17 | 罗普特科技集团股份有限公司 | Monitoring data acquisition and analysis method based on Internet of things |
| CN117112514B (en) * | 2023-10-23 | 2024-01-09 | 山东同利新材料有限公司 | Recording and storing method based on p-chloromethyl styrene production data |
| CN117109487B (en) * | 2023-10-23 | 2024-01-23 | 北京华力兴科技发展有限责任公司 | Automatic nondestructive measurement method for metal thickness |
| CN117109487A (en) * | 2023-10-23 | 2023-11-24 | 北京华力兴科技发展有限责任公司 | Automatic nondestructive measurement method for metal thickness |
| CN117112514A (en) * | 2023-10-23 | 2023-11-24 | 山东同利新材料有限公司 | Recording and storing method based on p-chloromethyl styrene production data |
| CN117293758A (en) * | 2023-11-24 | 2023-12-26 | 山东德源电力科技股份有限公司 | Automatic protection method for digital distribution feeder monitoring terminal based on fault identification |
| CN117293758B (en) * | 2023-11-24 | 2024-02-02 | 山东德源电力科技股份有限公司 | Automatic protection method for digital distribution feeder monitoring terminal based on fault identification |
| CN117312803A (en) * | 2023-11-29 | 2023-12-29 | 广州市悦到信息科技有限公司 | Digital processing method and system for cloud cooperative passenger transport service |
| CN117312803B (en) * | 2023-11-29 | 2024-03-15 | 广州市悦到信息科技有限公司 | Digital processing method and system for cloud cooperative passenger transport service |
| CN117330816A (en) * | 2023-12-01 | 2024-01-02 | 南京中旭电子科技有限公司 | Monitoring data optimization method for Hall current sensor |
| CN117330816B (en) * | 2023-12-01 | 2024-01-26 | 南京中旭电子科技有限公司 | Monitoring data optimization method for Hall current sensor |
| CN117349711A (en) * | 2023-12-04 | 2024-01-05 | 湖南京辙科技有限公司 | Electronic tag data processing method and system for railway locomotive parts |
| CN117349711B (en) * | 2023-12-04 | 2024-02-13 | 湖南京辙科技有限公司 | Electronic tag data processing method and system for railway locomotive parts |
| CN117370917B (en) * | 2023-12-07 | 2024-02-23 | 城光（湖南）节能环保服务股份有限公司 | Urban intelligent street lamp service life prediction method and system |
| CN117370917A (en) * | 2023-12-07 | 2024-01-09 | 城光（湖南）节能环保服务股份有限公司 | Urban intelligent street lamp service life prediction method and system |
| CN117411189A (en) * | 2023-12-14 | 2024-01-16 | 山东德源电力科技股份有限公司 | Monitoring data enhancement method of micro-grid coordination controller |
| CN117411189B (en) * | 2023-12-14 | 2024-03-15 | 山东德源电力科技股份有限公司 | Monitoring data enhancement method of micro-grid coordination controller |
| CN117407700B (en) * | 2023-12-14 | 2024-04-16 | 国网山东省电力公司莱芜供电公司 | Method for monitoring working environment in live working process |
| CN117407700A (en) * | 2023-12-14 | 2024-01-16 | 国网山东省电力公司莱芜供电公司 | Method for monitoring working environment in live working process |
| CN117421610B (en) * | 2023-12-19 | 2024-03-15 | 山东德源电力科技股份有限公司 | Data anomaly analysis method for electric energy meter running state early warning |
| CN117421610A (en) * | 2023-12-19 | 2024-01-19 | 山东德源电力科技股份有限公司 | Data anomaly analysis method for electric energy meter running state early warning |
| CN117572137A (en) * | 2024-01-17 | 2024-02-20 | 山东海纳智能装备科技股份有限公司 | Seven-level ANPC high-voltage frequency converter remote monitoring system |
| CN117572137B (en) * | 2024-01-17 | 2024-03-29 | 山东海纳智能装备科技股份有限公司 | Seven-level ANPC high-voltage frequency converter remote monitoring system |
| CN117648590A (en) * | 2024-01-30 | 2024-03-05 | 山东万洋石油科技有限公司 | Omnibearing gamma logging data optimization processing method |
| CN117648590B (en) * | 2024-01-30 | 2024-04-19 | 山东万洋石油科技有限公司 | Omnibearing gamma logging data optimization processing method |
| CN117786582A (en) * | 2024-02-23 | 2024-03-29 | 江苏斐能软件科技有限公司 | Intelligent monitoring method and system for abnormal power consumption state based on data driving |
| CN117786582B (en) * | 2024-02-23 | 2024-05-07 | 江苏斐能软件科技有限公司 | Intelligent monitoring method and system for abnormal power consumption state based on data driving |
| CN117786325A (en) * | 2024-02-27 | 2024-03-29 | 山东晨晖电子科技有限公司 | Ambient temperature wisdom early warning system of heavy-calibre thing networking water gauge |
| CN117786325B (en) * | 2024-02-27 | 2024-04-30 | 山东晨晖电子科技有限公司 | Ambient temperature wisdom early warning system of heavy-calibre thing networking water gauge |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116702081B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116702081B (en) | Intelligent inspection method for power distribution equipment based on artificial intelligence | |
| CN109444791B (en) | Error state evaluation method and system for capacitor voltage transformer | |
| CN111259717B (en) | Method and system for judging abnormal state of rotating equipment | |
| CN106873571B (en) | early warning method based on data and model fusion | |
| EP2518520B1 (en) | Device and method for detecting and locating defects in underground cables | |
| CN116703183B (en) | Novel power distribution network system power load assessment method | |
| CN112187528B (en) | Industrial control system communication flow online monitoring method based on SARIMA | |
| CN117390573B (en) | Wind turbine generator operation abnormality early warning method based on time sequence prediction | |
| CN111797365B (en) | Converter transformer temperature abnormity judgment method and system | |
| CN114252103B (en) | Fusion power station operation fault prediction method | |
| CN111209934A (en) | Fan fault prediction and alarm method and system | |
| CN112883634B (en) | DC measurement system state prediction method and system based on multi-dimensional analysis | |
| CN106656669A (en) | Equipment parameter abnormity detection system and method based on self-adaptive setting of threshold | |
| CN114062993A (en) | CVT error state prediction method based on time convolution network | |
| CN109635430B (en) | Power grid transmission line transient signal monitoring method and system | |
| CN117150419B (en) | Energy storage power supply operation environment detection system based on data analysis | |
| CN117371339A (en) | Transformer operation monitoring system based on Internet of things | |
| CN112085043A (en) | Intelligent monitoring method and system for network security of transformer substation | |
| CN114499409A (en) | Photovoltaic module hot spot fault diagnosis method | |
| LIU et al. | An application of multistep long-short term memory algorithm to predict the performance of capacitor voltage transformer | |
| Cross et al. | Model-based condition monitoring for wind turbines | |
| CN117034157B (en) | Hydropower equipment fault identification method and system combining multimodal operation data | |
| CN117668684B (en) | Power grid electric energy data anomaly detection method based on big data analysis | |
| CN113722977B (en) | Gas turbine rotor fault early warning method based on hybrid prediction | |
| CN110048393B (en) | Transient voltage disturbance suppression method and device based on direct current commutation influence degree |
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 |