Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a UPFC equipment image display and performance analysis method and system, which are characterized in that UPFC relevant performance evaluation labels are set by taking UPFC technical specifications into consideration by collecting various performance information of UPFC, the UPFC equipment image is established to display label relevant data, and data extraction, label extraction and label weight calculation are carried out on a UPFC performance evaluation label library, so that comprehensive analysis and evaluation on UPFC performance are realized, and the change of state quantity in different sampling periods is synthesized while UPFC information is displayed in multiple directions, and the weight is adjusted in an online mode in real time, thereby realizing more accurate UPFC performance evaluation.
The invention adopts the following technical scheme.
A UPFC equipment portrait display and performance analysis method comprises the following steps:
s1: acquiring UPFC operation related data, performing data preprocessing and labeling processing to form a UPFC performance evaluation tag library comprising a primary tag reflecting UPFC quality and functions and a secondary tag reflecting various indexes of the primary tag, wherein the secondary tag comprises a tag name and a marking value, and establishing a UPFC equipment portrait to display the tag related data;
s2: carrying out data extraction on secondary label marking values in a UPFC basic performance evaluation label library obtained at different data sampling moments to obtain a secondary label data matrix;
S3: based on the secondary label data matrix obtained in the step S2, extracting a label main component of a secondary label in a UPFC performance evaluation label library to obtain a main secondary label and a marking value thereof;
s4: carrying out importance weight and contribution degree weight calculation on the primary secondary label obtained in the step S3, and obtaining single label comprehensive weight;
s5: and combining the marking value of the primary and secondary labels with the comprehensive weight of the single label to obtain a final performance evaluation result.
Preferably, in step S1, a UPFC quality evaluation tag system including four primary tags of a device basic performance, a device test condition, a device operation condition, and a device history record, and a UPFC function evaluation tag system including four primary tags of a device bearing capacity index, a device technical index, a scheduling management index, and a device operation index are established, and for each primary tag, a secondary tag is constructed, specifically:
in the UPFC quality evaluation label system:
the secondary label of the basic performance of the equipment comprises technical parameters, quality grade and performance effect;
the secondary label of the equipment test condition comprises an insulation test, a characteristic test, a non-electrical test and on-line monitoring;
the secondary labels of the equipment operation conditions comprise real-time operation conditions, operational years and operational environments;
The second-level label of the equipment history record comprises a state before operation, an overhaul record, a family quality history, a fault defect and an abnormality record;
in the UPFC function evaluation label system:
the secondary labels of the equipment bearing capacity indexes comprise transformer load rate, transformer voltage transformation rate, line section standardization rate and branch circuit neck line proportion;
the secondary labels of the equipment technical indexes comprise equipment defect rate, equipment failure rate and equipment average operation rate;
the second-level label of the dispatching management index comprises equipment integrity rate, equipment defect eliminating rate, equipment abnormal operation lifting rate and personnel misoperation rate;
the secondary labels of the equipment operation indexes comprise line loss rate, equipment average load rate, equipment average overload rate, comprehensive voltage qualification rate and terminal voltage unqualified line proportion;
the UPFC quality evaluation tag system and a first-level tag and a corresponding second-level tag in the UPFC function evaluation tag system form a UPFC performance evaluation tag library.
Preferably, the secondary label marking value in the UPFC quality evaluation label system is determined based on UPFC operation related data;
the method for evaluating the secondary label marking value in the label system by the UPFC function comprises the following steps:
for a secondary label with a nominal value, the nominal value is: calculating a numerical value-rated value/rated value 1- |;
For a secondary label with a best state value of 1, the label value is: calculating a numerical value by a label;
for a secondary label with an optimal state value of 0, the marking value is as follows: 1-calculating a numerical value;
wherein the calculated value is a tag value calculated based on the operational data.
Preferably, in step S1, the label-related data of the UPFC performance evaluation label library is divided into different device data sets according to the period of day, month, and year, considering the acquisition source of the data, so as to generate and display the corresponding UPFC device portrait.
Preferably, S2 specifically includes:
s2.1: normalizing the normal distribution of the secondary label marking values to obtain a normal distribution normalized secondary label marking value matrixX’;
S2.2: calculating a normal distribution standardized secondary label marking value matrixX’The eigenvalues of the covariance matrix are ordered from big to small, and the corresponding eigenvectors form a matrixPObtaining the feature value with the maximum covariance matrix and the feature vector matrix normalized by the feature valueP 1 Will beP 1 After transpositionX’The multiplication results in a matrix that is converted into the newly constructed space, i.e., a secondary label data matrix.
Preferably, S2.1 specifically comprises:
(1) The data set formed by the secondary label marking values obtained by the primary label at different data sampling moments is defined as X,XIs a multidimensional matrix;
(2) Matrix is formedXNormalizing each column to obtain [0,1 ] of each secondary label marking value]Normalizing the data, and then carrying out the following normal distribution normalization processing on the normalized data:
calculating the mean value and standard deviation of the normalized data of the secondary label marking value, and carrying the obtained mean value and the corresponding standard deviation into the following formula to calculate and obtain the secondary label marking value after normalization distribution normalizationThe standardized distribution of the two-level label values is realized, and a standardized two-level label marking value matrix of the standardized distribution is obtainedX’:
(1)
Wherein:Ānormalizing data for secondary label tag valuesAIs the average value of (2);σis thatAStandard deviation of (2).
Preferably, S3 specifically includes:
s3.1: calculating the secondary label data matrix obtained in S2YCovariance matrix eigenvalue and corresponding eigenvector of (a), and matrix composed of all eigenvectors obtainedPAnd secondary tag data matrixYMultiplying to obtain a secondary label matrix;
S3.2: sequencing the covariance matrix eigenvalues calculated in S3.1 from large to small, calculating the cumulative variance contribution rate according to the eigenvalues, and obtaining a secondary label matrixAnd extracting the names and matrix values of the secondary labels corresponding to the characteristic values when the accumulated variance contribution rate meets the requirement, and taking the names and matrix values as main component labels and marking values thereof.
Preferably, the cumulative variance contribution rate calculation formula is:
,
wherein:λ k is the kth eigenvalue;ρcontributing rate for accumulated variance; n is the total number of tags.
Preferably, in S4, the importance weight calculation method is as follows:
and comparing the two important degrees of the main and secondary labels according to the history experience of the equipment, wherein the important value is 1, and calculating the ratio of the number of 1 obtained by the labels to the total number of 1 obtained by all the labels to obtain the importance weight of the corresponding label.
Preferably, in S4, the contribution weight calculation formula is:
,
wherein:is the firstiThe marking value of each primary secondary label; />、/>、/>、/>1 st, 2 nd, 3 rd, and/or->The marking value of each primary secondary label; />The number of the primary secondary labels;
P i 、P j is the firsti、jContribution degree of each primary secondary label relative to all primary secondary labels;
E i 、E j is the firsti、jUncertainty of the individual primary secondary labels;
W i is the firstiContribution weights of the individual primary secondary labels.
Preferably, in S4, the importance weight and the contribution weight are multiplied and normalized to obtain a single label comprehensive weight.
Preferably, in S5, the performance evaluation value is obtained by multiplying the labeled value of each primary and secondary label by the corresponding single label comprehensive weight, and the performance evaluation result representing the condition of the UPFC device is obtained according to the interval range where the performance evaluation value is located.
A UPFC device representation display and performance analysis system, comprising:
the label library construction and equipment portrait display module is used for acquiring UPFC operation related data, performing data preprocessing and labeling processing to form a UPFC performance evaluation label library comprising a primary label reflecting UPFC quality and functions and a secondary label reflecting indexes of the primary label, wherein the secondary label comprises a label name and a label value, and establishing a UPFC equipment portrait to display the label related data;
the main data extraction module is used for carrying out data extraction on the secondary label marking values in the UPFC basic performance evaluation label library obtained at different data sampling moments to obtain a secondary label data matrix;
the label principal component extraction module is used for extracting label principal components of the secondary labels in the UPFC performance evaluation label library based on the secondary label data matrix to obtain a main secondary label and a marking value thereof;
the comprehensive weight calculation module is used for calculating importance weights and contribution weights aiming at the primary and secondary labels and obtaining single label comprehensive weights;
and the performance evaluation module is used for combining the marking value of the primary secondary label with the comprehensive weight of the single label to obtain a final performance evaluation result.
A terminal comprising a processor and a storage medium; the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method.
The invention has the beneficial effects that compared with the prior art:
(1) The multi-dimensional data of the collected equipment is integrated by adopting an equipment information labeling technology, equipment characteristic labels can be extracted from mass data, a UPFC quality and function evaluation label system is constructed, UPFC equipment portraits are built, performance label related information of the UPFC is displayed in a specific mode, the equipment information of the UPFC can be collected in multiple directions, and related running state evaluation indexes are counted and displayed in a distinguishing mode, so that the identification and the processing of a computer are facilitated on one hand, and the later analysis and the statistics are facilitated on the other hand;
(2) Main data extraction is carried out on tag marking values of different data sampling periods of the UPFC, so that data dimension reduction is realized, and compared with direct acquisition of equipment data, the change of state quantity of different sampling periods can be better synthesized;
(3) The method has the advantages that the primary label is extracted for the secondary label in the UPFC performance evaluation library, the UPFC running state can be evaluated more accurately, and the change of the evaluation index is more convenient through the label form.
(4) The main and secondary label importance weight, contribution degree weight calculation and single label comprehensive weight calculation formula are provided, importance weight calculation is carried out on the main and secondary labels, evaluation label weight assignment is carried out through importance weight and contribution degree weight synthesis, real-time adjustment weight can be selected on line according to the frequency and degree of checking each index by operation and maintenance personnel in an actual system, and more reasonable weight assignment and UPFC performance evaluation are achieved.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. The embodiments described herein are merely some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art without inventive faculty, are within the scope of the invention, based on the spirit of the invention.
As shown in fig. 1-2, embodiment 1 of the present invention provides a method for image display and performance analysis of a UPFC device, which in a preferred but non-limiting embodiment of the present invention comprises the steps of:
s1: acquiring UPFC operation related data, performing data preprocessing and labeling processing to form a UPFC performance evaluation tag library comprising a primary tag reflecting UPFC quality and functions and a secondary tag reflecting various indexes of the primary tag, wherein the secondary tag comprises a tag name and a marking value, and establishing a UPFC equipment portrait to display the tag related data, and specifically comprising the following steps:
(1) And (3) data acquisition: acquiring data about equipment maintenance, operation, cost and the like through a PMS system, an OMS system and an ERP system, and acquiring the electric quantity of equipment operation through a UPFC engineering control device acquisition system;
(2) Data preprocessing: integrating multi-channel data, and performing pretreatment such as cleaning, de-duplication, de-invalidation, de-abnormality and the like on the data to finish screening and processing of the data;
(3) Labeling (namely, label grade and system division are carried out based on various data, and a secondary label marking value is determined) to form a label library: the basic performance of UPFC equipment can be divided into two aspects of quality and function of the equipment, so that a UPFC quality evaluation label system comprising four primary labels of basic performance of the equipment, test condition of the equipment, running condition of the equipment and history record of the equipment is established; similarly, establishing a UPFC function evaluation label system of four primary labels comprising an equipment bearing capacity index, an equipment technical index, a scheduling management index and an equipment operation index; the UPFC quality evaluation tag system and a first-level tag and a corresponding second-level tag in the UPFC function evaluation tag system form a UPFC performance evaluation tag library; the secondary label in the UPFC performance evaluation label library comprises a label name and a secondary label marking value; when each label is extracted in the subsequent step, the extracted content comprises a label name and a label marking value, and the label name and the label marking value are mutually associated.
For each primary label, a secondary label is constructed, specifically:
as shown in fig. 3, in the UPFC quality assessment tag system:
the secondary label of the basic performance of the equipment comprises technical parameters, quality grade and performance effect;
the secondary label of the equipment test condition comprises an insulation test, a characteristic test, a non-electric test and on-line monitoring.
The secondary labels of the equipment operation conditions comprise real-time operation conditions, operational years and operational environments;
the secondary labels of the equipment history record comprise a pre-operation state, an overhaul record, a family quality history, a fault defect and an abnormality record.
The secondary label marking value of the quality evaluation is obtained by the following method:
in the quality evaluation, various secondary indexes set in equipment basic performance, equipment test conditions, equipment running conditions and equipment history records comprise mostly non-electrical data, in actual engineering application, proper values are given according to equipment real-time operation and maintenance results and history records in the daily equipment maintenance process, for example, technical parameters under the equipment basic performance are related to device purchase, the values are generally selected to be best, namely, the values are 1, quality grade, performance effect and the like are changed along with the use of equipment or equipment update, so that equipment model, service life, test effect, fault record and the like can be comprehensively considered in the equipment maintenance process in actual application, and a value is directly assigned to the indexes according to working experience.
Wherein, the real-time operation and maintenance result, history record and the like required in the value process are obtained by the steps (1) and (2).
As shown in fig. 4, in the UPFC function evaluation tag system:
the secondary labels of the equipment bearing capacity indexes comprise transformer load rate, transformer voltage transformation rate, line section standardization rate and branch circuit neck line proportion;
the secondary labels of the equipment technical indexes comprise equipment defect rate, equipment failure rate and equipment average operation rate;
the second-level label of the dispatching management index comprises equipment integrity rate, equipment defect eliminating rate, equipment abnormal operation lifting rate and personnel misoperation rate;
the secondary labels of the equipment operation indexes comprise line loss rate, equipment average load rate, equipment average overload rate, comprehensive voltage qualification rate and terminal voltage disqualification line proportion. It is understood that the index herein is an index contained in the tag name.
The secondary label marking value of the function evaluation is obtained by the following value method:
in the function evaluation, the equipment bearing capacity index, the equipment technical index, the scheduling management index and various secondary indexes set under the equipment operation index comprise mostly electric data, and the indexes can be roughly divided into three types:
first category: there are ratings (transformer load rate, transformer voltage conversion rate, device average load rate);
The second category: the optimal state value is 1 (line section standardization rate, equipment integrity rate, comprehensive voltage qualification rate);
third category: the optimal state value is 0 (branch circuit neck line proportion, equipment defect rate, equipment failure rate, equipment defect eliminating rate, personnel misoperation rate, line loss rate, equipment average overload rate, terminal voltage unqualified line proportion, equipment average operation rate and equipment abnormal operation lifting rate);
calculating a numerical value-rated value/rated value according to (1- |) as a tag marking value for the first class;
directly calculating corresponding numerical values as tag marking values aiming at the second class;
the values are indicated as labels for the third class in terms of (1-calculated values).
The specific calculation formula of the calculated value is as follows:
transformer load ratio = apparent power of average output of the transformer over a specified time period/rated capacity of the transformer over the time period;
transformer voltage change rate= (transformer secondary side no-load voltage-secondary side load voltage)/secondary side rated voltage in a specified time period;
line section standardization rate = line number of specified area line section meeting power distribution network planning design guideline requirement/line number of the area;
branch neck line proportion = line number of neck branches present in designated area/line number of the area; the clamping neck is characterized in that the power supply capacity in a power grid is abundant, the sectional area of a power supply line is smaller, the power consumption on the load side is large, and the voltage is lower;
Device defect rate = number of devices with defects in a specified time period of a specified area/number of devices in the specified time period of the area;
device failure rate = sum of all device failure times in a specified time period of a specified region/the time period;
device average operation rate= (calendar time-UPFC deactivated time)/(calendar time);
device integrity = number of non-defective devices in a specified time period for a specified zone/number of devices in the zone for that time period;
device defect rate = number of timely defect removal of device in a specified time period of a specified region/total defect number of device in the time period of the region;
equipment abnormal operation lifting rate= (UPFC forced outage lifting rate+upfc fault trip recovery lifting rate);
personnel misoperation rate = number of false orders/total number of orders;
line loss ratio = difference between input power and output power in UPFC specified time period/input power in UPFC specified time period;
device average load rate = sum of UPFC load rates over a specified time period/number of transformers running over the time period;
device average overload rate = sum of uptfc overload times within a specified time period/the time period;
comprehensive voltage qualification rate=the sum of the number of voltage detection points qualified by voltage in a specified time period of a specified area/the number of voltage detection points in the time period of the area;
Terminal voltage off-specification line ratio = number of lines that terminal voltage is off-specification within a specified time period of a specified zone/number of lines that operate within that time period of that zone.
Wherein each parameter value required in the calculation process is obtained through the steps (1) and (2).
(4) UPFC device portrait generation and display:
(4.1) considering the acquisition source of the data, dividing the tag-related data into:
a data set of related equipment such as model, rated parameters, quality level, performance effect and the like obtained through an enterprise resource planning system (ERP); for the model, the corresponding label, label marking value and related data such as data participating in marking value calculation are all divided into the set;
a related equipment data set such as equipment test conditions, equipment operation conditions, equipment history records, equipment defect rates, equipment failure rates, equipment average operation rates and the like obtained through an equipment operation and maintenance management system (PMS);
and related equipment data sets such as transformer load rate, transformer voltage conversion rate, line section standardization rate, branch circuit neck line proportion, equipment integrity rate, equipment defect elimination rate, equipment abnormal operation lifting rate, personnel misoperation rate, line loss rate, equipment average load rate, equipment average overload rate, comprehensive voltage qualification rate, terminal voltage disqualification line proportion and the like are obtained through a dispatching management system (OMS) and a UPFC engineering control device.
And (4.2) dividing the data set of the related equipment according to the evaluation period of day, month and year so as to generate and display the corresponding UPFC equipment portrait, namely realizing the display of the related data of the label.
S2: main data extraction is carried out on secondary label marking values in a UPFC performance evaluation label library obtained at different data sampling moments, and a secondary label data matrix is obtained, wherein the method specifically comprises the following steps:
s2.1: normalizing the normal distribution of the secondary label marking values to obtain a normal distribution normalized secondary label marking value matrixX’:
1) The data set formed by the secondary label marking values obtained by the primary label at different data sampling moments is defined asX,XIs a multidimensional matrix;
the data set of the secondary label marking value under the primary label, such as the running condition of the equipment in fig. 3, obtained at two data sampling moments is a 2×3 order matrixXS2 hopefully, the matrix is subjected to data extraction to obtain a 1 multiplied by 3 order matrixX f 。
,
As can be seen in conjunction with figure 3,、/>、/>the marking value data of the real-time running condition, the operational years and the running environment of the secondary label under the primary label which respectively represents the running condition of the equipment obtained at the 1 st data sampling moment; />、/>、/>The marking value data of the real-time running condition, the operational years and the running environment of the secondary label under the primary label, which is the running condition of the equipment obtained at the sampling moment of the 2 nd data, are respectively represented;
2) First, matrix is formedXNormalizing each column to obtain [0,1 ] of each secondary label marking value]Normalizing the data, and then straightening the normalized dataThe following normal distribution standardization process is carried out:
calculating the mean value and standard deviation of the normalized data of the secondary label marking value before normal distribution normalization processing, and obtaining the mean valueAnd the standard deviation is brought into the formula (1) to calculate and obtain a secondary label marking value after normal distribution standardizationL\M\N,The standardized secondary label value normal distribution is realized, and a standardized secondary label marking value matrix is formed at the moment:
,
(1)
wherein: 、/> 、/>respectively indicate-> 、/> 、/>A secondary label marking value after normal distribution standardization; /> 、 、/>Respectively indicate->、/>、/>A secondary label marking value after normal distribution standardization;Āmarking values for secondary labelsAAverage value before normal distribution treatment;σis thatAStandard deviation before normal distribution treatment.
S2.2: calculating a normal distribution standardized secondary label marking value matrix through a formula (2)X’The eigenvalues of the covariance matrix are ordered from big to small, and the corresponding eigenvectors form a matrixPObtaining the feature value with the maximum covariance matrix and the feature vector normalized corresponding to the feature value P 1 The matrix converted into the new construction space is obtained by carrying out the formula (3), namely a secondary label data matrix after data extractionX f . Wherein the composition isPIs not normalized by the feature vector of (a),P 1 is a normalized feature vector.
(2)
(3)
Representing covariance operation, T being a matrix transpose symbol; />、/>、/>For a secondary tag data matrixX f Is a column matrix element of (c).
X f The method is a matrix obtained by extracting main data of three secondary labels under the running condition of equipment, the main data of the other secondary labels are extracted by the same method, and the matrix formed by all secondary label data after the extraction is completed is Y.
S3: based on the secondary label data matrix obtained in the step S2, extracting a label main component of a secondary label in a UPFC performance evaluation label library to obtain a main secondary label and a marking value thereof;
based on the secondary label data matrix extracted by the S2 data, extracting a label main component aiming at a secondary label in a UPFC performance evaluation label system, wherein the method specifically comprises the following steps:
s3.1: calculating a secondary label data matrix extracted by S2 dataYCovariance matrix eigenvalue and corresponding eigenvector of (a), and matrix composed of all eigenvectors obtainedPAnd secondary tag data matrixYMultiplying to obtain a secondary label matrix ;
For example, a 1 Xn-order matrix formed by two-level tag data obtained by S2 data extraction is recorded asYTaking a functional evaluation label system as an examplen=16. Is obtained through a formula (1) and a formula (2)YCovariance matrix eigenvalue of matrixλ i And corresponding feature vectorP i (here, all eigenvalues and eigenvectors corresponding to each eigenvalue are required) and matrixPAndYthe equation (3) is:
,
wherein,、/>、/>representing matrices separatelyPMatrix elements of rows 1, 2, n, -for each row>、/>、/>Respectively representYColumn 1, 2, 16 matrix elements in the matrix,>、/>、/>respectively represent the two-level tag matrix->The 1 st, 2 nd and 16 th column matrix elements.
S3.2: sequencing the covariance matrix eigenvalues calculated in S3.1 from large to small, calculating the cumulative variance contribution rate according to the eigenvalues, and obtaining a secondary label matrix(/>) And extracting the names and matrix values of the secondary labels corresponding to the characteristic values when the accumulated variance contribution rate meets the requirement, and taking the names and matrix values as main component labels and marking values thereof. I.e. the extracted tag has two components: tag name and tag value, the matrix operation is directed to the tag value of the tag. The method comprises the following steps:
for 16 secondary label momentsArrayY f The covariance matrix eigenvalues of the (a) are ordered from big to small, the accumulated variance contribution rate is calculated through a formula (4) until the accumulated variance contribution rate is more than 95%, at the moment, the selected secondary label is used as a main secondary label, and the information of the secondary label comprises most of quality evaluation label library information.
(4)
Wherein:λ k is the kth eigenvalue;ρto accumulate the variance contribution, n is the total number of tags.
For example, the primary secondary label and the label value obtained in S3 include:Y 1 equipment defect rate;Y 2 : abnormal lifting rate of equipment;Y 3 : line loss rate;Y 4 : and (5) synthesizing the voltage qualification rate. Wherein the 'equipment defect rate' is the name of the primary secondary label "Y 1 "is its corresponding index value; and the other several are the same.
S4: the importance weight and contribution degree weight are calculated for the main secondary label obtained in the step S3, and the single label comprehensive weight is obtained, as shown in fig. 5, specifically:
supposing that the UPFC quality evaluation secondary label is obtained by S3 after main label extractionY 1 Equipment defect rate;Y 2 : abnormal lifting rate of equipment;Y 3 : line loss rate;Y 4 : and (5) synthesizing the voltage qualification rate. The weight calculation is specifically as follows:
(1) Importance weight calculation: to simplify the description, the following equation (5) is employedY 1 、Y 2 、Y 3 、Y 4 Representing the corresponding primary secondary label name;
introducing virtual tagsY 5 The importance degree of the labels is distinguished according to the history experience of the equipment, the two labels are compared, the more important value is 1, the importance weight of the corresponding labels is obtained according to the ratio of the number of the labels obtained 1 to the total number of the labels obtained 1, and the importance weight is calculated through a formula (5) And (5) calculating importance weights of all tags:
(5)
wherein the method comprises the steps of、/>、/>、/>The importance weights of the 1 st, 2 nd, 3 rd and 4 th main secondary labels are respectively represented, and it is understood that the 1 st, 2 nd, 3 rd and 4 th main secondary labels are respectively corresponding to +.>、/>、/>、/>。
(2) Contribution degree weight calculation: calculating the first label through a formula (6) based on the marking value of the primary and secondary labelsiContribution degree weight of each primary and secondary labelW i :
(6)
Wherein:P i 、P j : first, thei、jContribution degree of each primary secondary label relative to all primary secondary labels;
E i 、E j : first, thei、jUncertainty of the individual primary secondary labels;
W i : first, theiContribution degree weights of the main secondary labels;
is the firstiThe marking value of each primary secondary label;
、/>、/>、/>the marking values of the 1 st, 2 nd, 3 rd and 4 th primary secondary labels are respectively shown.
(3) The importance weight and the contribution weight are brought into a formula (7), multiplied by each other and normalized to obtain the single label comprehensive weight。
(7)
Wherein the method comprises the steps of、/>Importance weights of the ith and j-th main secondary labels are represented; />、/>And the contribution degree weights of the ith and jth primary secondary labels are represented.
S5: combining the marking value of the main secondary label with the comprehensive weight of the single label to obtain a final performance evaluation result, wherein the final performance evaluation result comprises the following specific steps of:
marking value data of the main secondary label obtained in the step S3 Y 1 、Y 2 、Y 3 、Y 4 And the weight obtained by the S4 formula (7) is combined to obtain final performance evaluation through the following calculation to obtain a performance evaluation value。/>
(8)
Wherein the method comprises the steps ofMarking value data for the ith main secondary label; />Is the comprehensive weight of the ith primary secondary label.
The final performance evaluation result can be obtained by combining the performance evaluation value obtained in the formula (8) with the table 1, and the final performance evaluation result represents the condition of the UPFC equipment.
TABLE 1 correspondence between performance evaluation values and performance evaluation results
The embodiment 2 of the invention provides a UPFC equipment portrait display and performance analysis system, which comprises:
the label library construction and equipment portrait display module is used for acquiring UPFC operation related data, performing data preprocessing and labeling processing to form a UPFC performance evaluation label library comprising a primary label and a secondary label, wherein the secondary label comprises a label name and a label value, and establishing a UPFC equipment portrait to display the label related data;
the main data extraction module is used for extracting main data of secondary label marking values in the UPFC performance evaluation label library obtained at different data sampling moments to obtain a secondary label data matrix;
the label principal component extraction module is used for extracting label principal components of the secondary labels in the UPFC performance evaluation label library based on the secondary label data matrix to obtain a main secondary label and a marking value thereof;
The comprehensive weight calculation module is used for calculating importance weights and contribution weights aiming at the primary and secondary labels and obtaining single label comprehensive weights;
and the performance evaluation module is used for combining the marking value of the primary secondary label with the comprehensive weight of the single label to obtain a final performance evaluation result.
A terminal comprising a processor and a storage medium; the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method.
The invention has the beneficial effects that compared with the prior art:
(1) The equipment information labeling technology is adopted to combine the equipment operation data and the analyzed characteristic data, the multi-dimensional data of the collected equipment are integrated, the data are subjected to cleaning, de-duplication, de-invalidation, de-abnormality and other treatments after being obtained, equipment characteristic labels can be extracted from massive data, a UPFC quality and function evaluation label system is constructed, UPFC equipment portraits are realized through data preprocessing and labeling treatment, UPFC performance information is subjected to imaging display, the equipment information of the UPFC can be acquired in multiple directions, and related operation state evaluation indexes are counted and distinguished for display, so that the identification and the treatment of a computer are facilitated, and the later analysis and statistics are facilitated;
(2) Based on normal distribution standardization processing and covariance calculation, main data extraction is carried out on tag marking values of different data sampling periods of the UPFC, data dimension reduction is realized, and compared with direct acquisition equipment data, the change of state quantity of different sampling periods can be better synthesized;
(3) Based on covariance calculation and accumulated variance contribution rate calculation, main label extraction is performed on secondary labels in a UPFC performance evaluation library, the UPFC running state can be evaluated more accurately, and the evaluation index is changed more conveniently through the label form.
(4) The main and secondary label importance weight, contribution degree weight calculation and single label comprehensive weight calculation formula are provided, importance weight calculation is carried out on the main and secondary labels, evaluation label weight assignment is carried out through importance weight and contribution degree weight synthesis, real-time adjustment weight can be selected on line according to the frequency and degree of checking each index by operation and maintenance personnel in an actual system, and more reasonable weight assignment and UPFC performance evaluation are achieved.
The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.