CN113657622B - Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment - Google Patents
Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment Download PDFInfo
- Publication number
- CN113657622B CN113657622B CN202110791353.8A CN202110791353A CN113657622B CN 113657622 B CN113657622 B CN 113657622B CN 202110791353 A CN202110791353 A CN 202110791353A CN 113657622 B CN113657622 B CN 113657622B
- Authority
- CN
- China
- Prior art keywords
- state
- data
- encoder
- self
- multidimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007500 overflow downdraw method Methods 0.000 title description 4
- 238000012544 monitoring process Methods 0.000 claims abstract description 114
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000005856 abnormality Effects 0.000 claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 230000002688 persistence Effects 0.000 claims abstract description 4
- 230000004927 fusion Effects 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000009191 jumping Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of power equipment state diagnosis, in particular to a method, a device, a terminal and a storage medium for fusing multidimensional state data of power equipment. The trend factor mainly consists of three parts, and the state quantity weight reflects the severity of the abnormality of the monitoring quantity data. The repetition factor reflects the persistence of the state monitoring quantity data anomaly. The attenuation factor reflects the restorability of the state monitoring quantity data abnormality. In order to adaptively adjust and fuse the transformer monitoring data processed by the trend factors into corresponding transformer fault key variables, a self-encoder is adopted to fuse the multidimensional state data processed by the trend factors. The fused data can automatically extract the features, so that the defect of traditional manual feature extraction is effectively overcome, the fused data is utilized for state evaluation, and the accuracy is high.
Description
Technical Field
The present invention relates to the field of power equipment data processing technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for multi-dimensional state data fusion of a power equipment.
Background
The electric power equipment is one of the most expensive equipment with the strongest importance and the most complex maintenance in the electric power transmission and transformation system, and the monitoring parameters reflecting the state of the electric power equipment are various and comprise electric quantity and non-electric quantity parameters such as partial discharge, dielectric loss, oil temperature, dissolved gas in oil and the like. Monitoring the multidimensional state parameters of the power equipment and diagnosing the state of the power equipment according to the multidimensional state parameters has important significance for the reliable operation of the power transmission and transformation system.
However, at present, the state diagnosis of the power equipment mostly passes the industry standard, but the mode for judging the insulation fault of the power equipment usually has hysteresis, and the multi-state quantity is unfavorable for operation and maintenance personnel to judge, so that the fault-related state quantity is often lost in actual operation, and therefore, the feature extraction is required.
The current state diagnosis is mostly to directly judge the faults through the magnitude relation between the monitoring quantity and the guide threshold value, and the direct judgment ignores the relevance of the monitoring quantity on the time sequence, and most of the time, the abnormal stage of the power equipment is greatly related to the faults of the power equipment.
In summary, the state of multi-dimensional state information redundancy of the power equipment, difficulty in extracting effective state monitoring information, and lack of fusion of multi-dimensional state information have hampered technological progress in this field.
Based on this, there is a need for a method for fusing and evaluating the multidimensional state data of an electrical device.
Disclosure of Invention
The embodiment of the invention provides a method, a device, a terminal and a storage medium for fusing multidimensional state data of power equipment, which are used for solving the problem of insufficient relevance of the state data of the power equipment.
In a first aspect, an embodiment of the present invention provides a method for fusing multidimensional state data of electrical equipment, including:
acquiring a state monitoring quantity and a fault type database corresponding to the state monitoring quantity;
obtaining trend factors according to the state monitoring amount and the fault type database, wherein the trend factors are used for reflecting the severity degree and the time relevance of the monitoring amount;
calculating to obtain multidimensional state data according to the trend factors and the state monitoring quantity, wherein the multidimensional state data is used for representing the degree of abnormality of the state monitoring quantity deviating from a normal value;
and inputting the multidimensional state data into a self-encoder to obtain multidimensional state fusion data.
In one possible implementation manner, after the multi-dimensional state data is input from the encoder and multi-dimensional state fusion data is obtained, the method further includes:
and comparing the size of the multi-dimensional state fusion data with that of the fault type database to obtain the state of the power equipment.
In one possible implementation manner, the obtaining a trend factor according to the state monitoring amount and the fault type database includes:
obtaining state quantity weight, repetition factor and attenuation factor according to the state monitoring quantity and the fault type database;
obtaining the trend factor according to the state quantity weight, the repetition factor, the attenuation factor and a first formula, wherein the first formula is as follows:
trend factor = state quantity weight x repetition factor (1-decay factor).
In one possible implementation manner, the acquiring a state monitoring amount and a fault type database corresponding to the state monitoring amount includes:
acquiring monitoring data of power equipment;
and grouping the power equipment monitoring data according to the power equipment fault types which can be caused by the power equipment monitoring data, and obtaining the state monitoring quantity and the fault type database corresponding to the state monitoring quantity.
In one possible implementation manner, the calculating to obtain multidimensional state data according to the trend factor and the state monitoring amount includes:
the state monitoring amount is multiplied by the trend factor to obtain the multidimensional state data.
In one possible implementation manner, the inputting the multidimensional state data from the encoder to obtain multidimensional state fusion data includes:
a self-encoder training step: inputting the multidimensional state data into the self-encoder, training the self-encoder, wherein the input and the preset output of the self-encoder are multidimensional state data;
determining a calculated squared loss function value from the self-encoder input, the self-encoder actual output, and a second formula, the second formula:
L＝(y-f(x)) 2
wherein L is a squared loss function value, y is the self-encoder input, and f (x) is the actual output of the self-encoder;
if the square loss function value is in the receiving range, taking the output of the self-encoder hidden layer as the multidimensional state fusion data;
and if the square loss function value is not in the receiving range, jumping to the self-encoder training step.
In a second aspect, an embodiment of the present invention provides a multi-dimensional status data fusion apparatus for an electrical device, including: the data acquisition module is used for acquiring the state monitoring quantity and a fault type database corresponding to the state monitoring quantity;
the trend factor calculation module is used for obtaining trend factors according to the state monitoring amount and the fault type database, and the trend factors are used for reflecting the severity degree of the monitoring amount and the relevance in time;
the multidimensional state data calculation module is used for calculating and obtaining multidimensional state data according to the trend factors and the state monitoring quantity, and the multidimensional state data are used for representing the degree of abnormality of the state monitoring quantity deviating from a normal value; the method comprises the steps of,
and the multidimensional state fusion data output module is used for inputting the multidimensional state data into the self-encoder to obtain multidimensional state fusion data.
In one possible implementation, the method further includes: and the power equipment state evaluation module is used for comparing the size of the power equipment with the size of the fault type database according to the multidimensional state fusion data to obtain the state of the power equipment.
In a third aspect, embodiments of the present invention provide a terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect or any one of the possible implementations of the first aspect, when the computer program is executed.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
the embodiment of the invention discloses a multi-dimensional state data fusion method of power equipment, which is based on the combination of a trend factor and a self-encoder, can characterize the abnormal degree of the power equipment deviating from a normal value, and reflect the damage accumulation effect generated by abnormal state monitoring quantity, so as to reflect the front-back dependence of data in a time dimension, and adopts the self-encoder to fuse the multi-dimensional state data processed by the trend factor. The fused data can automatically extract the features, so that the defect of traditional manual feature extraction is effectively overcome, the fused data is utilized for state evaluation, and the accuracy is high.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for fusing multidimensional state data of electrical equipment provided by an embodiment of the invention;
FIG. 2 is a flowchart of a method for calculating multidimensional state data according to an embodiment of the present invention;
FIG. 3 is a flow chart of the fusion of multi-dimensional state data by a self-encoder provided by an embodiment of the present invention;
FIG. 4 is a block diagram of a self-encoder provided by an embodiment of the present invention;
FIG. 5 is a functional block diagram of a multi-dimensional state data fusion device for electrical equipment provided by an embodiment of the invention;
fig. 6 is a functional block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made with reference to the accompanying drawings.
The following describes in detail the embodiments of the present invention, and the present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation procedure are given, but the protection scope of the present invention is not limited to the following embodiments.
Fig. 1 is a flowchart of a method for fusing multidimensional state data of electrical equipment according to an embodiment of the present invention.
As shown in fig. 1, the implementation flow of the method for fusing multi-dimensional state data of electrical equipment according to the embodiment of the present invention may include steps 101 to 104.
In step 101, a status monitoring quantity and a fault type database corresponding to the status monitoring quantity are acquired.
In some embodiments, step 101 may comprise:
acquiring monitoring data of power equipment;
and grouping the power equipment monitoring data according to the power equipment fault types which can be caused by the power equipment monitoring data, and obtaining the state monitoring quantity and the fault type database corresponding to the state monitoring quantity.
In step 102, a trend factor is obtained according to the condition monitoring amount and the fault type database, wherein the trend factor is used for reflecting the severity degree of the monitoring amount and the time relevance.
In some embodiments, step 102 may include:
obtaining state quantity weight, repetition factor and attenuation factor according to the state monitoring quantity and the fault type database;
obtaining a trend factor according to the state quantity weight, the repetition factor, the attenuation factor and a first formula, wherein the first formula is as follows:
trend factor = state quantity weight x repetition factor (1-decay factor).
For better fusion of the multiple state monitoring quantities, the correlation among the multiple state monitoring quantities is utilized, and the correlation is in an action relation with the preset power equipment faults, so that the state monitoring quantities are subjected to data preprocessing. One way of preprocessing that can be implemented is to determine the weight of the condition monitoring amount based on the magnitude of the condition monitoring amount and the frequency of occurrence.
Therefore, in order to embody the severity and the time relevance of the state monitoring amount, the trend factor concept is proposed based on the corresponding relation between the state monitoring amount and the fault type.
The trend factor mainly comprises three parts, namely a state quantity weight, a repetition factor and an attenuation factor, and the trend factor and the state quantity weight, the repetition factor and the attenuation factor meet the following relation:
trend factor = state quantity weight x repetition factor x (1-decay factor)
The state quantity weight is used for reflecting the severity of state monitoring quantity data abnormality and representing the severity of detected state monitoring quantity. And on the basis of exceeding the fault limit value, different state quantity weights are given in different state value intervals through section division, and the more the state quantity weights deviate from the normal value, the more the state monitoring data are abnormal.
The state quantity weight will be described using the discharge amount of partial discharge as an example. When the partial discharge capacity is smaller than the 50pC limit value, the state quantity weight is reset to 1; when the partial discharge amount is between 50pC and 100pC, the state quantity weight is set to 1.5, and so on. After the partial discharge amount exceeds the 50pC limit value, the larger the discharge amount is, the higher the weight set value is.
The repetition factor is used for reflecting the persistence of the state monitoring quantity data abnormality, and is expressed by the proportion of the state monitoring quantity deviating from the normal value in a short-time detection period with a fixed duration. The more the state monitoring quantity deviates from the normal value, the longer the deviation time, and the larger the corresponding repetition factor. Thus, the repetition factor may also reflect the severity of the abnormal condition monitoring amount from the side. The repetition factor is determined according to the difference between the state monitoring value and the limiting value, and the larger the difference is, the larger the value of the repetition factor is.
The repetition factor will be described by taking the number of partial discharges as an example. When the partial discharge times in one hour is less than the set limiting value, the repetition factor is 1; when the number of partial discharge times is higher than the limit value in one hour, the corresponding repetition factor value (more than 1) is set according to the number of partial discharge times. As in one embodiment, the repetition factor is 1 when the number of partial discharges is less than 3 in one hour, 2 when the number of partial discharges reaches 3 in one hour, 3 when the number of partial discharges reaches 4 in one hour, and so on.
The attenuation factor is used for reflecting the restorability of the state monitoring quantity data abnormality, and is expressed by the frequency of occurrence of the event that the state monitoring quantity deviates from the normal value in a long-time detection period, namely the time interval of two adjacent events. The shorter the interval between two events, the smaller the attenuation factor and correspondingly the larger the (1-attenuation factor). Also, the attenuation factor may reflect the severity of the abnormal condition monitoring amount from the side.
And determining the state quantity weight, the repetition factor and the numerical value of the attenuation factor in the trend factor through expert preset or genetic algorithm, calculating the value of the trend factor and calculating the value of the trend factor.
In step 103, multi-dimensional state data is obtained according to the trend factor and the state monitoring amount calculation, wherein the multi-dimensional state data is used for representing the degree of abnormality of the state monitoring amount from a normal value.
In some embodiments, step 103 may comprise:
the state monitoring amount is multiplied by the trend factor to obtain the multidimensional state data.
Illustratively, as shown in fig. 2, the state monitoring amount is multiplied by a trend factor, and multidimensional state data processed by the trend factor is calculated.
After the trend factors are processed, the multidimensional state data can represent the abnormal degree of the state monitoring quantity deviating from the normal value, and reflect the damage accumulation effect generated by the abnormal state monitoring quantity, so that the front-back dependence of the data in the time dimension is reflected.
After the monitoring quantity data of the power equipment is processed by the trend factors, the multi-monitoring quantity data are required to be fused, so that state key variable values which can represent different fault types of the power equipment are obtained.
Some fault types can only be reflected by some fixed monitored quantities, while they are insensitive to changes in other monitored quantities. Meanwhile, for the same fault type, the influence degree caused by different monitoring quantity changes is different.
In step 104, the multi-dimensional state data is input from the encoder to obtain multi-dimensional state fusion data.
In some embodiments, step 104 may include:
a self-encoder training step: inputting the multidimensional state data into the self-encoder, training the self-encoder, wherein the input and the preset output of the self-encoder are multidimensional state data;
determining a calculated squared loss function value from the self-encoder input, the self-encoder actual output, and a second formula, the second formula:
L＝(y-f(x)) 2
wherein L is a squared loss function value, y is the self-encoder input, and f (x) is the actual output of the self-encoder;
if the square loss function value is in the receiving range, taking the output of the self-encoder hidden layer as the multidimensional state fusion data;
and if the square loss function value is not in the receiving range, jumping to the self-encoder training step.
For example, the traditional data preprocessing method needs to build a corresponding full-connection network coefficient matrix through guidance and engineering actual conditions. And establishing a relation between each monitored quantity and the fault type of the power equipment through a connecting network, and representing the influence of the monitored quantity on the fault through the coefficient. The method can only describe the relation between the monitored quantity and the fault type roughly, but cannot show the influence magnitude relation in a very accurate quantitative mode, and meanwhile, the method cannot realize self-adaptive adjustment according to different monitored quantities.
In order to be able to adaptively adjust and fuse into power equipment fault key variables according to the multidimensional state monitoring data, the data are fused by adopting an automatic encoder.
The self-encoder is one of artificial intelligent networks, and mainly has the function of compressing and processing data, and has two parts: the encoder responsible for data compression or special encoding, and the decoder that restores the encoded data to the original input, may also be referred to as compression and decompression, respectively. According to the limitation that the input of the self-encoder is equal to the output, the network is enabled to carry out self-training through input data, the weight is continuously modified and forgotten, and a network model which is most suitable for the function is built.
As shown in fig. 3, the operation steps of fusing multi-dimensional state data using the self-encoder are as follows:
(1) An encoder and a decoder shown in fig. 4 are constructed by using a plurality of layers of fully-connected neural networks, wherein X is input data, H is hidden layer output data, X' is preset output data, a weight matrix and a bias vector of the encoder and the decoder are initialized by using random numbers, and the number of neurons of an intermediate hidden layer is set to be 1.
(2) The multidimensional state data is input to the self-encoder, the set input is the same as the preset output, and the encoder and decoder of the self-encoder are trained.
(3) Comparing the actual decoder output with a preset output, namely input data (the preset output is the same as the input), and calculating a square loss function value L for representing the error:
L＝(y-f(x)) 2
wherein: l is a square loss, y is a preset output value, and f (x) is an actual output value. Judging whether the error is in a preset acceptable range, if so, taking the hidden layer output as a self-encoder output, and representing the fused key variable reflecting the state of the power equipment; if not, continuing training the self-encoder, and repeating the step (2).
In some embodiments, after step 104, the method for multi-dimensional state data fusion of electrical equipment may further include step 105, where the state of electrical equipment is estimated.
In step 105, the multidimensional status fusion data is compared with the fault type database in size to obtain the status of the electrical equipment.
Illustratively, a trained self-encoder is used for power device state assessment. The evaluation steps are as follows:
(1) And processing the detected power equipment monitoring data through trend factors, representing the degree of abnormality of the state monitoring quantity deviating from a normal value, and reflecting the damage accumulation effect generated by the abnormality of the state monitoring quantity, thereby reflecting the front-back dependence of the data in the time dimension.
(2) And fusing the multidimensional state data processed by the trend factors by using a trained self-encoder, extracting hidden layer output as self-encoder output, comparing the magnitude of the hidden layer output data with that of the data used in training, and evaluating the state of the power equipment.
The following describes embodiments of the present invention in detail, and the present examples are provided by carrying out the technical solutions of the present invention on the premise of providing detailed embodiments and specific operation procedures, but the scope of protection of the present invention is not limited to the following examples.
(1) According to the embodiment, the partial discharge multidimensional monitoring data of the 500kV voltage class transformer are arranged, so that two monitoring values of the partial discharge average amplitude and the discharge time interval of the transformer are formed. And determining parameters in the calculation of the trend factors according to the historical training results.
(2) And (5) calculating state quantity weight: when the average amplitude of the partial discharge is smaller than the 50pC limit value, the weight of the state quantity is 1, and when the average amplitude of the partial discharge is between 50pC and 100pC, the weight of the state quantity is 1.5; when the average value of the discharge time interval is greater than 1 minute, the state quantity weight is set to 1, and when the average value of the discharge time interval is less than 1 minute, the state quantity weight is set to 1.5.
(3) And (3) calculating a repetition factor: when the number of times of partial discharge average amplitude values greater than 100pC in one hour is less than 10 times, the repetition factor is 1, and when the number of times is greater than 10 times, the repetition factor value is 1.5; the repetition factor is 1 when the number of times of discharge time interval average value less than 1 minute within one hour is less than 10, and the repetition factor value is 1.5 when it is more than 10.
(4) And (3) calculating an attenuation factor: when the appearance time of the partial discharge average amplitude value in one day is longer than 2 hours and is longer than 100pC, the attenuation factor is 0.8, and when the partial discharge average amplitude value is shorter than 2 hours, the attenuation factor value is 0.9; the decay factor was 0.8 when the time of occurrence of the discharge time interval average value of less than 1 minute in one day was longer than 2 hours, and was 0.9 when it was shorter than 2 hours.
(5) Data values of partial discharge amplitude and time interval after passing the decay factor are calculated and input from the encoder.
(6) The encoder and decoder of the self-encoder are respectively two layers of fully-connected neural networks, the number of neurons of an implicit layer is 1, the input and the output are set to be data values after the training part discharge amplitude and the time interval pass through the attenuation factor, and the self-encoder is trained so that the loss function value is smaller than 10 -4 。
(7) And outputting data of an hidden layer, wherein the data is the fused transformer discharge characteristic state quantity, the data output is 0.8, and the transformer has a discharge fault when the comparison database finds that the output is more than 0.7, so that the transformer has the discharge fault.
The embodiment of the multi-dimensional state data fusion method of the power equipment is based on the combination of the trend factors and the self-encoder, can represent the abnormal degree of the power equipment deviating from a normal value, and simultaneously reflects the damage accumulation effect generated by abnormal state monitoring quantity, so that the front-back dependence of the data in the time dimension is reflected, and the self-encoder is adopted to fuse the multi-dimensional state data processed by the trend factors. The fused data can automatically extract the features, so that the defect of traditional manual feature extraction is effectively overcome, the fused data is utilized for state evaluation, and the accuracy is high.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 5 shows a functional block diagram of a multi-dimensional state data fusion device for an electrical device according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, which is described in detail below:
a multi-dimensional state data fusion device for an electrical device, comprising: a data acquisition module 51, a trend factor calculation module 52, a multi-dimensional state data calculation module 53, and a multi-dimensional state fusion data output module 54.
The data acquisition module 51 is configured to acquire a state monitoring amount and a fault type database corresponding to the state monitoring amount.
A trend factor calculation module 52, configured to obtain a trend factor according to the condition monitoring amount and the fault type database, where the trend factor is used to represent the severity of the monitoring amount and the relevance in time.
A multidimensional state data calculation module 53, configured to obtain multidimensional state data according to the trend factor and the state monitoring amount, where the multidimensional state data is used to characterize an anomaly of the state monitoring amount deviating from a normal value.
The multidimensional state fusion data output module 54 is configured to input the multidimensional state data into the encoder to obtain multidimensional state fusion data.
In some embodiments, further comprising: and the power equipment state evaluation module 55 is used for comparing the size of the power equipment with the size of the fault type database according to the multidimensional state fusion data to obtain the state of the power equipment.
Fig. 6 is a functional block diagram of a terminal according to an embodiment of the present invention. As shown in fig. 6, the terminal 6 of this embodiment includes: a processor 60, a memory 61 and a computer program 62 stored in said memory 61 and executable on said processor 60. The processor 60 executes the computer program 62 to implement the steps of the above-described embodiments of the method for fusing multi-dimensional state data of each electrical device and the method for fusing multi-dimensional state data of electrical devices, for example, steps 101 to 104 shown in fig. 1. Alternatively, the processor 60 may perform the functions of the modules/units in the above-described embodiments of the apparatus, such as the functions of the modules/units 51 to 55 shown in fig. 5, when executing the computer program 62.
Illustratively, the computer program 62 may be partitioned into one or more modules/units that are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program 62 in the terminal 6. For example, the computer program 62 may be divided into modules/units 51 to 55 shown in fig. 5.
The terminal 6 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal 6 may include, but is not limited to, a processor 60, a memory 61. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the terminal 6 and is not meant to be limiting as the terminal 6 may include more or fewer components than shown, or may combine some of the components, or different components, e.g., the terminal may further include input and output devices, network access devices, buses, etc.
The processor 60 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 61 may be an internal storage unit of the terminal 6, such as a hard disk or a memory of the terminal 6. The memory 61 may also be an external storage device of the terminal 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the terminal 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the terminal 6. The memory 61 is used for storing the computer program and other programs and data required by the terminal. The memory 61 may also be used for temporarily storing data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, and will not be described herein again.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and the details or descriptions of other embodiments may be referred to for those parts of an embodiment that are not described in detail or are described in detail.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the apparatus/terminal embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the procedures in the above-described method of embodiments, or may be implemented by instructing related hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of the above-described method for multi-dimensional state data fusion of electrical equipment and the embodiment of the multi-dimensional state data fusion device of electrical equipment when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium may include content that is subject to appropriate increases and decreases as required by jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is not included as electrical carrier signals and telecommunication signals.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limited thereto; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and they should be included in the protection scope of the present invention.
Claims (8)
1. A method for multi-dimensional state data fusion of electrical equipment, comprising:
acquiring a state monitoring quantity and a fault type database corresponding to the state monitoring quantity;
obtaining trend factors according to the state monitoring amount and the fault type database, wherein the trend factors are used for reflecting the severity degree and the time relevance of the monitoring amount;
calculating to obtain multidimensional state data according to the trend factors and the state monitoring quantity, wherein the multidimensional state data is used for representing the degree of abnormality of the state monitoring quantity deviating from a normal value;
inputting the multi-dimensional state data into a self-encoder to obtain multi-dimensional state fusion data;
wherein the obtaining a trend factor according to the condition monitoring amount and the fault type database includes:
obtaining state quantity weight, repetition factor and attenuation factor according to the state monitoring quantity and the fault type database, wherein the state quantity weight is used for reflecting the severity of state monitoring quantity data abnormality, the repetition factor is used for reflecting the persistence of state monitoring quantity data abnormality, and the attenuation factor is used for reflecting the restorability of state monitoring quantity data abnormality;
obtaining the trend factor according to the state quantity weight, the repetition factor, the attenuation factor and a first formula, wherein the first formula is as follows:
；
the step of inputting the multidimensional state data into an encoder to obtain multidimensional state fusion data comprises the following steps:
a self-encoder training step: inputting the multidimensional state data into the self-encoder, training the self-encoder, wherein the input and the preset output of the self-encoder are multidimensional state data;
determining a calculated squared loss function value from the self-encoder input, the self-encoder actual output, and a second formula, the second formula:
wherein,Lis the square lossThe value of the loss function,yfor the input of the self-encoder,f（x) Actually outputting the signal to the self-encoder;
if the square loss function value is in a preset range, taking the output of the hidden layer of the self-encoder as the multidimensional state fusion data;
and if the square loss function value is not in the preset range, jumping to the self-encoder training step.
2. The method of claim 1, wherein after the multi-dimensional state data is input from the encoder to obtain multi-dimensional state fusion data, the method further comprises:
and comparing the multi-dimensional state fusion data with the fault type database in size to obtain the state of the power equipment.
3. The method for merging multi-dimensional state data of electrical equipment according to claim 1, wherein the acquiring a state monitoring amount and a fault type database corresponding to the state monitoring amount comprises:
acquiring monitoring data of power equipment;
and grouping the power equipment monitoring data according to the power equipment fault types which can be caused by the power equipment monitoring data, and obtaining the state monitoring quantity and the fault type database corresponding to the state monitoring quantity.
4. The method of claim 1, wherein the calculating the multi-dimensional state data from the trend factor and the state monitoring amount comprises:
the state monitoring amount is multiplied by the trend factor to obtain the multidimensional state data.
5. A multi-dimensional state data fusion device for an electrical device, comprising:
the data acquisition module is used for acquiring the state monitoring quantity and a fault type database corresponding to the state monitoring quantity;
the trend factor calculation module is used for obtaining trend factors according to the state monitoring amount and the fault type database, and the trend factors are used for reflecting the severity degree of the monitoring amount and the relevance in time;
the multidimensional state data calculation module is used for calculating and obtaining multidimensional state data according to the trend factors and the state monitoring quantity, and the multidimensional state data are used for representing the degree of abnormality of the state monitoring quantity deviating from a normal value; the method comprises the steps of,
the multidimensional state fusion data output module is used for inputting the multidimensional state data into the self-encoder to obtain multidimensional state fusion data;
wherein the obtaining a trend factor according to the condition monitoring amount and the fault type database includes:
obtaining state quantity weight, repetition factor and attenuation factor according to the state monitoring quantity and the fault type database, wherein the state quantity weight is used for reflecting the severity of state monitoring quantity data abnormality, the repetition factor is used for reflecting the persistence of state monitoring quantity data abnormality, and the attenuation factor is used for reflecting the restorability of state monitoring quantity data abnormality;
obtaining the trend factor according to the state quantity weight, the repetition factor, the attenuation factor and a first formula, wherein the first formula is as follows:
；
the step of inputting the multidimensional state data into an encoder to obtain multidimensional state fusion data comprises the following steps:
a self-encoder training step: inputting the multidimensional state data into the self-encoder, training the self-encoder, wherein the input and the preset output of the self-encoder are multidimensional state data;
determining a calculated squared loss function value from the self-encoder input, the self-encoder actual output, and a second formula, the second formula:
wherein,Lfor the value of the square loss function,yfor the input of the self-encoder,f（x) Actually outputting the signal to the self-encoder;
if the square loss function value is in a preset range, taking the output of the hidden layer of the self-encoder as the multidimensional state fusion data;
and if the square loss function value is not in the preset range, jumping to the self-encoder training step.
6. The power plant multidimensional state data fusion device of claim 5, further comprising:
and the power equipment state evaluation module is used for comparing the size of the power equipment with the size of the fault type database according to the multidimensional state fusion data to obtain the state of the power equipment.
7. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 4 when the computer program is executed.
8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791353.8A CN113657622B (en) | 2021-07-13 | 2021-07-13 | Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791353.8A CN113657622B (en) | 2021-07-13 | 2021-07-13 | Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657622A CN113657622A (en) | 2021-11-16 |
| CN113657622B true CN113657622B (en) | 2024-02-27 |
Family
ID=78478006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110791353.8A Active CN113657622B (en) | 2021-07-13 | 2021-07-13 | Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657622B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114254879B (en) * | 2021-11-30 | 2023-10-20 | 南方电网数字电网研究院有限公司 | Multi-sensor information fusion type power equipment safety diagnosis method and device |
| CN117572837B (en) * | 2024-01-17 | 2024-04-16 | 普金硬科技(南通)有限公司 | Intelligent power plant AI active operation and maintenance method and system |
| CN117851897A (en) * | 2024-03-08 | 2024-04-09 | 国网山西省电力公司晋城供电公司 | Multi-dimensional feature fusion oil immersed transformer online fault diagnosis method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016176913A1 (en) * | 2015-05-06 | 2016-11-10 | 杨启蓓 | Smart multi-dimensional big data analyzing expert system for high-voltage circuit breaker in power grid |
| CN106469356A (en) * | 2016-09-28 | 2017-03-01 | 国家电网公司 | Transmission facility state evaluation based on multidimensional data and risk analysis method and device |
| CN106779407A (en) * | 2016-12-15 | 2017-05-31 | 国网浙江省电力公司杭州供电公司 | A kind of electric power data fusion method based on data pool |
| CN107220469A (en) * | 2017-07-14 | 2017-09-29 | 华北电力大学（保定） | A kind of method and system of fan condition estimation |
| CN109711663A (en) * | 2018-11-15 | 2019-05-03 | 国网山东省电力公司淄博供电公司 | Substation's oil-immersed transformer status assessment and modification method and system based on big data analysis |
| WO2020087829A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳壹账通智能科技有限公司 | Data trend analysis method and system, computer device and readable storage medium |
| CN111443259A (en) * | 2020-03-30 | 2020-07-24 | 国网山东省电力公司德州供电公司 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
| CN111881000A (en) * | 2020-08-07 | 2020-11-03 | 广州云从博衍智能科技有限公司 | Fault prediction method, device, equipment and machine readable medium |
| CN112417791A (en) * | 2020-11-19 | 2021-02-26 | 山东山大电力技术股份有限公司 | Power equipment monitoring and early warning method and system based on linear regression and AHP algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074021A (en) * | 2016-11-10 | 2018-05-25 | 中国电力科学研究院 | A kind of power distribution network Risk Identification system and method |
-
2021
- 2021-07-13 CN CN202110791353.8A patent/CN113657622B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016176913A1 (en) * | 2015-05-06 | 2016-11-10 | 杨启蓓 | Smart multi-dimensional big data analyzing expert system for high-voltage circuit breaker in power grid |
| CN106469356A (en) * | 2016-09-28 | 2017-03-01 | 国家电网公司 | Transmission facility state evaluation based on multidimensional data and risk analysis method and device |
| CN106779407A (en) * | 2016-12-15 | 2017-05-31 | 国网浙江省电力公司杭州供电公司 | A kind of electric power data fusion method based on data pool |
| CN107220469A (en) * | 2017-07-14 | 2017-09-29 | 华北电力大学（保定） | A kind of method and system of fan condition estimation |
| WO2020087829A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳壹账通智能科技有限公司 | Data trend analysis method and system, computer device and readable storage medium |
| CN109711663A (en) * | 2018-11-15 | 2019-05-03 | 国网山东省电力公司淄博供电公司 | Substation's oil-immersed transformer status assessment and modification method and system based on big data analysis |
| CN111443259A (en) * | 2020-03-30 | 2020-07-24 | 国网山东省电力公司德州供电公司 | Active power distribution network fault diagnosis method and system based on local abnormal factor detection |
| CN111881000A (en) * | 2020-08-07 | 2020-11-03 | 广州云从博衍智能科技有限公司 | Fault prediction method, device, equipment and machine readable medium |
| CN112417791A (en) * | 2020-11-19 | 2021-02-26 | 山东山大电力技术股份有限公司 | Power equipment monitoring and early warning method and system based on linear regression and AHP algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 基于堆叠自编码网络的风电机组发电机状态监测与故障诊断;赵洪山;刘辉海;刘宏杨;林酉阔;;电力***自动化(11);第102-108页 * |
| 基于大数据分析的输变电设备状态数据异常检测方法;严英杰;盛戈;陈玉峰;江秀臣;郭志红;杜修明;;中国电机工程学报(01);第52-59页 * |
| 基于高维随机矩阵大数据分析模型的输变电设备关键性能评估方法;严英杰;盛戈;王辉;刘亚东;陈玉峰;江秀臣;郭志红;;中国电机工程学报(02);第435-442页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657622A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113657622B (en) | Multi-dimensional state data fusion method, device, terminal and storage medium for power equipment | |
| CN111585948B (en) | Intelligent network security situation prediction method based on power grid big data | |
| CN110766059A (en) | Transformer fault prediction method, device and equipment | |
| CN116757534B (en) | Intelligent refrigerator reliability analysis method based on neural training network | |
| CN111652496A (en) | Operation risk assessment method and device based on network security situation awareness system | |
| CN112508243B (en) | Training method and device for multi-fault prediction network model of power information system | |
| CN109921415B (en) | Hybrid measurement-oriented online defense method for power grid malignant data injection attack | |
| CN112039903B (en) | Network security situation assessment method based on deep self-coding neural network model | |
| CN112001644B (en) | Method, device, terminal and storage medium for detecting operation reliability of power distribution network | |
| CN109374063B (en) | Cluster management-based transformer anomaly detection method, device and equipment | |
| CN111723367A (en) | Power monitoring system service scene disposal risk evaluation method and system | |
| CN112731260A (en) | Online evaluation method for error state of voltage transformer based on concept drift recognition | |
| CN115685045B (en) | Online evaluation method for voltage transformer | |
| CN115221982B (en) | Traction power supply operation and maintenance method and device, terminal and storage medium | |
| RU2364926C2 (en) | Way of control of multiparameter object state | |
| CN112380763A (en) | System and method for analyzing reliability of in-pile component based on data mining | |
| CN112633331A (en) | Self-encoder-based thermal power plant auxiliary machine health state assessment method | |
| CN116776209A (en) | Method, system, equipment and medium for identifying operation state of gateway metering device | |
| CN116522993A (en) | Chemical process fault detection method based on countermeasure self-coding network | |
| CN116307700A (en) | Electric power system and risk assessment device and method thereof | |
| CN115494431A (en) | Transformer fault warning method, terminal equipment and computer readable storage medium | |
| CN115389881A (en) | Insulation state evaluation method and device for cable intermediate joint | |
| CN114510469A (en) | Method, device, equipment and medium for identifying bad data of power system | |
| CN117783792B (en) | Valve side sleeve insulation state detection method and system based on multiparameter real-time monitoring | |
| CN113988687A (en) | Nuclear power device state monitoring method and system |
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 |