CN118050579A - Intelligent analysis control method based on data analysis - Google Patents
Intelligent analysis control method based on data analysis Download PDFInfo
- Publication number
- CN118050579A CN118050579A CN202410182196.4A CN202410182196A CN118050579A CN 118050579 A CN118050579 A CN 118050579A CN 202410182196 A CN202410182196 A CN 202410182196A CN 118050579 A CN118050579 A CN 118050579A
- Authority
- CN
- China
- Prior art keywords
- preheating
- transformer
- temperature
- duration
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007405 data analysis Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 79
- 238000012423 maintenance Methods 0.000 claims abstract description 47
- 230000005856 abnormality Effects 0.000 claims abstract description 18
- 238000013500 data storage Methods 0.000 claims description 19
- 238000005457 optimization Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000000556 factor analysis Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000004804 winding Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000009413 insulation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Landscapes
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention relates to the technical field of equipment monitoring, in particular to an intelligent analysis control method based on data analysis, which comprises the following steps: the method comprises the steps of collecting preheating information, maintenance history information and downtime information of equipment, analyzing reference preheating time of the equipment before interference, optimizing preheating time reference data by adding interference factors, predicting final preheating time of the equipment, controlling fault monitoring of the equipment after the equipment is predicted to be preheated, alarming and reminding when equipment abnormality is monitored, monitoring temperature through a transformer, alarming when abnormality occurs in the monitored temperature, guaranteeing safe operation and reasonable service life of the transformer, and monitoring the temperature after the transformer is predicted to be fully preheated, so that waste of temperature monitoring work and monitoring resources before the transformer is fully preheated is reduced, transmission of deviation data during the temperature monitoring before the transformer is fully preheated is reduced, and misjudgment probability of the temperature abnormality is reduced.
Description
Technical Field
The invention relates to the technical field of equipment monitoring, in particular to an intelligent analysis control method based on data analysis.
Background
In operation, the loss of the electric energy in the iron core and the windings is converted into heat energy, so that the temperature of the transformer is heated for a long time to exceed an allowable value, insulation of the transformer is easy to age and damage, faults are easily caused by electric breakdown, safe use of the transformer is affected, the operation temperature of the transformer is monitored, safe operation and reasonable service life of the transformer can be guaranteed, however, the transformer needs a preheating process, the transformer is heated from a low voltage to a normal use temperature slowly before being put into operation, the transformer is gradually adjusted to designed voltage and current, impact current caused by sudden power on can be reduced due to the transformer preheating, meanwhile, the insulation strength of the transformer windings can be enhanced, the service life of the transformer is prolonged, the influence of various factors is easy to occur, different transformers can be different in time required for completing the preheating, temperature monitoring is carried out when the transformer is not fully preheated, error monitoring data is easy to occur, the error monitoring data is easy to compare, the error judging of the temperature is easy to occur, and if the abnormal data is transmitted to a terminal, and if the abnormal data is not monitored, the abnormal data is not only wasted, but also the monitoring resources are not used.
Therefore, an intelligent analysis control method based on data analysis is needed to solve the above problems.
Disclosure of Invention
The invention aims to provide an intelligent analysis control method based on data analysis, which aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent analysis control method based on data analysis comprises the following steps:
s10: acquiring preheating information, maintenance history information and downtime information of equipment;
s20: analyzing the reference preheating time length of the equipment before interference;
S30: optimizing preheating duration reference data by adding interference factors, and predicting the final preheating duration of the equipment;
s40: and (3) performing fault monitoring on the equipment after the equipment is predicted to be preheated, and performing alarm reminding when the equipment is monitored to be abnormal.
Further, in step S10: setting a shutdown time threshold of the transformer as T, collecting f times of running of a random transformer before maintenance is not performed and the shutdown time does not exceed the shutdown time threshold, obtaining an average shutdown exceeding time of the transformer by dividing the shutdown time exceeding T by the shutdown time exceeding T after summing the shutdown time exceeding T of each time of the transformer, and obtaining an average shutdown exceeding time of the m transformers as T '= { T 1',t2',…,tm' } by collecting the time of running of the random transformer at the random one position before maintenance is not performed and the shutdown time does not exceed the shutdown time threshold, wherein the time of collecting the previous maintenance of the m transformers is W= { W 1,W2,…,Wm }, and the time of exceeding T by collecting the previous shutdown time of the m transformers is L= { L 1,L2,…,Lm }.
Further, in step S20: according to the formulaCalculating reference preheating time length K i of a random transformer, wherein t j represents time length required by a position temperature to reach normal operation temperature at the jth time when the random transformer is not maintained and the shutdown time length does not exceed the shutdown time length threshold value, and calculating to obtain a reference preheating time length set K= { K 1,K2,…,Ki,…,Km } of m transformers in the same mode;
The method has the advantages that the time length data of the normal operation temperature of different transformers before being subjected to overlong interference of maintenance and shutdown time is collected through a big data technology, so that the reference preheating time length of the transformers, namely the reference preheating time length before the transformers are interfered, the preheating analysis data before and after the transformers are interfered are separated for reference, the preheating time length of the transformers is judged not only according to the time length data required by different times of preheating of the transformers collected from historical data, and then the time for monitoring the temperature of the transformers is selected, so that the accuracy of preheating time analysis is improved.
Further, in step S30: the number of times that the transformer is maintained in the past is used as a first interference factor, a second interference factor E i for preheating one transformer is calculated according to a formula E i=Li*ti', a second interference factor set for preheating m transformers is obtained to be E= { E 1,E2,…,Em }, a delay time set for preheating the transformer after corresponding number of times of maintenance and a plurality of times of shutdown time exceeds a shutdown time threshold of the transformer is obtained to be A= { A 1,A2,…,Am }, a model training sample {(W1,E1,A1),(W2,E2,A2),…,(Wm,Em,Am)}, is generated, data fitting is carried out on the model training sample, and a transformer preheating delay time prediction model is established: z=a×x+b×y+c, where x represents an independent variable one in the prediction model that refers to the first interference factor, y represents an independent variable two in the prediction model that refers to the second interference factor, z represents an independent variable in the prediction model that refers to the warm-up delay time duration, a, b, and c represent fitting coefficients, and a, b, and c are solved for respectively according to the following formulas:
Wherein, W i represents the number of times the ith transformer is maintained in the past, that is, the first interference factor of preheating the ith transformer, a i represents the time delay time of preheating the ith transformer after the corresponding number of times of maintenance is performed and the time delay time exceeds the time delay threshold of the transformer, the reference preheating time of the current transformer is k, the first interference factor of preheating the current transformer is W, the second interference factor is e, the current transformer is not any one of m transformers, the reference preheating time of the current transformer, the first interference factor and the second interference factor are obtained in the same manner as the m transformers, and W and e are substituted into the prediction model of the preheating time delay of the transformer: let x=w, y=e, the delay time of predicting the current transformer preheating is: a, w+b, e+c, predicting to obtain the final preheating duration of the current transformer, wherein the final preheating duration is as follows: k+a+w+b+e+c;
The preheating time length of the transformer is easily affected by various factors, wherein if the transformer is restarted after being stopped for a long time or the transformer is restarted after being maintained, the preheating time length of the transformer is easy to have a time delay condition, after analysis to obtain a reference preheating time length, two interference factors of maintenance times and data with the stopping time length exceeding a threshold value are added, the more the maintenance times are, the longer the stopping time is, the more likely the preheating time length of the transformer is, a training sample is generated, the maintenance and stopping parameters of the current transformer are substituted into the model through a prediction model of the preheating time length of the current transformer, the preheating time length of the current transformer is predicted to be obtained, the reference preheating time length of the current transformer is optimized through adding the predicted time delay time length to obtain the final preheating time length of the current transformer, the preheating time lengths of the transformers with different actual conditions are analyzed in combination with the consideration of external interference factors, the accuracy of the preheating time length prediction result is effectively improved, the preheating time length required by fully obtaining the preheating time needed by substituting the parameters into the model before the subsequent transformer monitoring time length is selected, and the preheating time is analyzed one by one without time analysis.
Further, in step S40: after the current transformer is started, controlling a temperature sensor to monitor the temperature of the current transformer at a time interval k+a+w+b+e+c, using the temperature sensor to monitor the temperature of different positions of the current transformer, setting temperature thresholds of different positions, and transmitting a temperature abnormality alarm signal to a monitoring terminal when the temperature monitored at a random position exceeds the temperature threshold, and transmitting abnormal temperature data to the monitoring terminal;
The prediction of the preheating duration aims at selecting proper time for carrying out temperature monitoring on the transformer, and carrying out temperature monitoring after the transformer is fully preheated by prediction, so that the temperature monitoring work before the full preheating is reduced, the waste of monitoring resources is reduced, the transmission of deviation data during the temperature monitoring before the full preheating is reduced, the transmission of invalid data is reduced, and the probability of misjudgment on the abnormal temperature of the transformer is reduced.
The system for realizing the intelligent analysis control method based on the data analysis comprises an equipment information acquisition module, a data storage module, an equipment preheating analysis module, a reference data optimization module and a fault monitoring control module;
The output end of the equipment information acquisition module is connected with the input end of the data storage module, the output end of the data storage module is connected with the input ends of the equipment preheating analysis module and the reference data optimization module, the output end of the equipment preheating analysis module is connected with the input end of the reference data optimization module, and the output end of the reference data optimization module is connected with the input end of the fault monitoring control module;
The equipment information acquisition module is used for acquiring preheating information, maintenance history information and downtime information of equipment and transmitting all acquired data to the data storage module; the data storage module is used for storing preheating information, maintenance history information and downtime information of the equipment; the equipment preheating analysis module is used for analyzing the reference preheating time length of the equipment before interference; the reference data optimization module is used for optimizing the reference data of the preheating duration by adding the interference factors and predicting the final preheating duration of the equipment; the fault monitoring control module is used for controlling fault monitoring of the equipment after the equipment is predicted to finish preheating.
Further, the equipment information acquisition module comprises a preheating information acquisition unit, a maintenance data acquisition unit and a start-stop data acquisition unit;
The output ends of the preheating information acquisition unit, the maintenance data acquisition unit and the start-stop data acquisition unit are connected with the input end of the data storage module;
The preheating information acquisition unit is used for acquiring the time length required by the monitored temperature of a random position of the transformer to reach the normal operation temperature when different transformers are operated for a plurality of times, the transformers are not maintained for a plurality of times, and the shutdown time length does not exceed the shutdown time length threshold; the maintenance data acquisition unit is used for acquiring the number of times data of the different transformers which are maintained in the past; the start-stop data acquisition unit is used for setting a shutdown time threshold of the transformer and acquiring the times that the past shutdown time of different transformers exceeds the shutdown time threshold of the transformer and the exceeding time information.
Further, the equipment preheating analysis module comprises a preheating information calling unit and a reference duration judging unit;
The input end of the preheating information calling unit is connected with the output end of the data storage module, and the output end of the preheating information calling unit is connected with the input end of the reference duration judging unit;
The preheating information calling unit is used for calling duration data required by a position temperature of a monitored transformer reaching a normal operation temperature to the reference duration judging unit when different transformers are operated for a plurality of times in the past; the reference duration judging unit is used for calculating the average duration required by the temperature of a random position of the transformer reaching the normal operation temperature when the transformer is operated for a plurality of times, and taking the average duration as the reference preheating duration of the corresponding transformer.
Further, the reference data optimization module comprises an interference factor analysis unit, a duration prediction model establishment unit and a preheating duration prediction unit;
the input end of the interference factor analysis unit is connected with the output end of the data storage module, the output ends of the interference factor analysis unit and the reference duration judgment unit are connected with the input end of the duration prediction model establishment unit, and the output end of the duration prediction model establishment unit is connected with the input end of the preheating duration prediction unit;
The interference factor analysis unit is used for analyzing the past maintenance data and start-stop data of the transformer to obtain a first interference factor and a second interference factor of the preheating of the transformer; the time length prediction model building unit is used for obtaining the preheating time delay time length of the transformer after corresponding times of maintenance are carried out on the transformer and a plurality of times of shutdown time length exceeds a transformer shutdown time length threshold value, building a transformer preheating time delay time length prediction model according to a first interference factor, a second interference factor and the time delay time length, wherein the preheating time delay time length refers to how long the preheating time length is after the transformer is preheated on the basis of the reference preheating time length after corresponding times of maintenance are carried out on the transformer and the plurality of times of shutdown time length exceeds the transformer shutdown time length threshold value; the preheating duration prediction unit is used for obtaining a first interference factor and a second interference factor of the preheating of the current transformer, substituting the first interference factor and the second interference factor into the transformer preheating delay duration prediction model, predicting the delay duration of the preheating of the current transformer, and adding the delay duration of the preheating of the current transformer and the reference preheating duration of the current transformer as the finally predicted preheating duration of the current transformer.
Further, the fault monitoring control module comprises a monitoring time selecting unit, an equipment temperature monitoring unit and a temperature abnormality alarming unit;
The input end of the monitoring time selecting unit is connected with the output end of the preheating duration predicting unit, the output end of the monitoring time selecting unit is connected with the input end of the equipment temperature monitoring unit, and the output end of the equipment temperature monitoring unit is connected with the input end of the temperature abnormality alarming unit;
The monitoring time selecting unit is used for selecting the time for monitoring the temperature of the current transformer to be: after the current transformer is started, carrying out temperature monitoring when the preheating duration of the current transformer is finally predicted and obtained by the starting time interval; the equipment temperature monitoring unit is used for monitoring the temperatures of different positions of the current transformer by using a temperature sensor; the temperature abnormality alarm unit is used for setting temperature thresholds of different positions, and sending a temperature abnormality alarm signal to the monitoring terminal when the temperature monitored by one random position exceeds the temperature threshold.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the temperature of the transformer is monitored, and when the abnormal temperature is detected, an alarm is timely given, so that the safe operation and the reasonable service life of the transformer are ensured;
A suitable monitoring time was selected: the temperature monitoring is carried out after the transformer is predicted to be fully preheated, so that the temperature monitoring work before the full preheating is reduced, the waste of monitoring resources is reduced, the transmission of deviation data during the temperature monitoring before the full preheating is reduced, the transmission of invalid data is reduced, and the probability of misjudgment on the temperature abnormality of the transformer is reduced;
In the preheating duration prediction process, firstly, duration data of the normal running temperature of different transformers before being not subjected to maintenance and overlong interference of the downtime are collected through a big data technology, so that the reference preheating duration of the transformers, namely the reference preheating duration of the transformers before being subjected to interference, is analyzed, preheating analysis data of the transformers before and after being subjected to interference are separated for reference, and the accuracy of preheating time analysis is improved; secondly, considering that the preheating time length of the transformer is easily influenced by various factors, after the reference preheating time length is obtained through analysis, two interference factors of data of maintenance times and downtime exceeding a threshold value are added to generate a training sample, the maintenance and downtime parameters of the current transformer are substituted into a model through building a preheating time delay time length prediction model of the transformer, the preheating time length of the current transformer is predicted to obtain the preheating time delay time length of the current transformer, the reference data of the preheating time length is optimized through adding the reference preheating time length before the current transformer is interfered with the predicted time delay time length to obtain the final preheating time length of the current transformer, and the preheating time lengths of the transformers with different actual conditions are analyzed in combination with the consideration of external interference factors, so that the accuracy of the preheating time length prediction result is effectively improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of an intelligent analysis control method based on data analysis of the present invention;
Fig. 2 is a diagram of system modules for implementing an intelligent analysis control method based on data analysis according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention is further described below with reference to fig. 1-2 and the specific embodiments.
Embodiment one:
As shown in fig. 1, the present embodiment provides an intelligent analysis control method based on data analysis, including:
S10: the method comprises the steps of collecting preheating information, maintenance history information and downtime information of equipment, setting a downtime threshold value of a transformer to be T, collecting f times of operation of a random transformer before maintenance is not carried out and the downtime is not beyond the downtime threshold value, wherein a time length set required by a corresponding transformer to reach a normal operation temperature at a random position monitored during f times of operation is t= { T 1,t2,…,tf }, and the normal operation temperature represents a normal minimum temperature of the transformer set by default, for example: for a dry-type transformer, the normal range of the temperature of a main transformer winding of the transformer is generally 70-105 ℃, when the temperature of the main transformer winding reaches 70 ℃, the transformer can normally operate, namely the fact that the transformer is preheated is shown, the normal temperature of the corresponding transformer which is set by default is 70 ℃, the time required for the temperature of a random position to reach the normal operation temperature when the m transformers are not maintained and the shutdown time is not exceeded before the shutdown time threshold is operated is acquired, the number of times of acquiring the m transformers which are maintained in the past is W= { W 1,W2,…,Wm }, the number of times of acquiring the m transformers which exceed T in the past is L= { L 1,L2,…,Lm }, the average shutdown time exceeding time of the transformer is obtained by summing the shutdown time exceeding T in comparison with the shutdown time of the transformers each time, and the average shutdown time exceeding T '= { T 1',t2',…,tm' };
S20: analyzing the reference preheating time length of the equipment before interference according to the formula Calculating reference preheating time length K i of a random transformer, wherein t j represents time length required by a position temperature to reach normal operation temperature at the jth time when the random transformer is not maintained and the shutdown time length does not exceed the shutdown time length threshold value, and calculating to obtain a reference preheating time length set K= { K 1,K2,…,Ki,…,Km } of m transformers in the same mode;
S30: the preheating time length reference data optimization is carried out by adding interference factors, the final preheating time length of the equipment is predicted, the number of times that the transformer is maintained in the past is taken as a first interference factor, a second interference factor E i for preheating one transformer is calculated according to a formula E i=Li*ti', a second interference factor set for preheating m transformers is obtained to be E= { E 1,E2,…,Em }, a delay time length set for preheating after the corresponding number of times of maintenance is carried out on the transformer and the shutdown time length exceeds a transformer shutdown time length threshold value for a plurality of times is obtained to be A= { A 1,A2,…,Am }, a model training sample {(W1,E1,A1),(W2,E2,A2),…,(Wm,Em,Am)}, is generated, data fitting is carried out on the model training sample, and a transformer preheating delay time length prediction model is established: z=a×x+b×y+c, where x represents an independent variable one in the prediction model that refers to the first interference factor, y represents an independent variable two in the prediction model that refers to the second interference factor, z represents an independent variable in the prediction model that refers to the warm-up delay time duration, a, b, and c represent fitting coefficients, and a, b, and c are solved for respectively according to the following formulas:
Wherein, W i represents the number of times the ith transformer is maintained in the past, that is, the first interference factor of preheating the ith transformer, a i represents the time delay time of preheating the ith transformer after the corresponding number of times of maintenance is performed and the time delay time exceeds the time delay threshold of the transformer, the reference preheating time of the current transformer is k, the first interference factor of preheating the current transformer is W, the second interference factor is e, the current transformer is not any one of m transformers, the reference preheating time of the current transformer, the first interference factor and the second interference factor are obtained in the same manner as the m transformers, and W and e are substituted into the prediction model of the preheating time delay of the transformer: let x=w, y=e, the delay time of predicting the current transformer preheating is: a, w+b, e+c, predicting to obtain the final preheating duration of the current transformer, wherein the final preheating duration is as follows: k+a+w+b+e+c.
S40: after the current transformer is started, the temperature sensor is controlled to monitor the temperature of the current transformer at the time interval k+a, w+b and e+c, the temperature sensor is used for monitoring the temperatures of different positions of the current transformer, temperature thresholds of the different positions are set, when the temperature monitored at a random position exceeds the temperature threshold, a temperature abnormality alarm signal is sent to the monitoring terminal, and abnormal temperature data are transmitted to the monitoring terminal.
For example: the method comprises the steps that when a random transformer is collected and operated for 5 times before maintenance is not carried out and the shutdown time length does not exceed the shutdown time length threshold value, a time length set required for the temperature of a main transformer winding of the corresponding transformer to reach the normal operation temperature, which is monitored during 5 times of operation, is t= {30, 32, 31, 35, 37}, wherein the units are as follows: the reference preheating time length of the corresponding transformer is obtained by the following steps: 33 minutes, the reference preheating duration set of the 5 transformers is K= {33, 60, 70, 32, 120}, the number of times of the 5 transformers which are maintained in the past is collected as W= {2,1,5,6,3}, the shutdown duration threshold value of the transformers is set as T=2, and the unit is: the number of times that the time length of stopping the machine for 5 transformers exceeds 2 hours in the past is L= {1,3, 10,7,2}, and the average time length of stopping the machine for 5 transformers exceeds t ' = {0.2,0.5,0.1,0.6,1}, and the unit is: the method comprises the steps of obtaining a first interference factor set {2,1,5,6,3}, a second interference factor set E= {0.2,1.5,1,4.2,2}, obtaining a delay time duration set A= {15, 12,5,8, 20}, wherein the delay time duration set A is preheated after the transformer is subjected to corresponding times of maintenance and a plurality of times of shutdown time durations exceed a shutdown time duration threshold of the transformer, and the units are as follows: and (3) minutes, generating a model training sample, and establishing a transformer preheating delay time length prediction model: z=1.36 x+1.92 x+3.96, obtaining a reference preheating duration of the current transformer as k=50, wherein a first interference factor of preheating of the current transformer is w=4, a second interference factor of preheating of the current transformer is e=1.2, and the delay duration of preheating of the current transformer is predicted by x=w=4 and y=e=1.2: a+w+b+e+c is approximately equal to 12, and the final preheating duration of the current transformer is predicted to be: k+a+w+b+e+c=62, in units of: and (3) minutes, after the current transformer is started, controlling a temperature sensor to monitor the temperature of the current transformer at intervals of 62 minutes from the starting time.
Embodiment two:
As shown in fig. 2, the present embodiment provides a system for implementing an intelligent analysis control method based on data analysis, which is implemented based on the analysis control method in the embodiment, and specifically includes: the system comprises an equipment information acquisition module, a data storage module, an equipment preheating analysis module, a reference data optimization module and a fault monitoring control module; the equipment information acquisition module is used for acquiring preheating information, maintenance history information and downtime information of equipment and transmitting all acquired data to the data storage module; the data storage module is used for storing preheating information, maintenance history information and downtime information of the equipment; the equipment preheating analysis module is used for analyzing the reference preheating time length of the equipment before interference; the reference data optimization module is used for optimizing the reference data of the preheating duration by adding the interference factors and predicting the final preheating duration of the equipment; the fault monitoring control module is used for controlling the fault monitoring of the equipment after the equipment is predicted to finish preheating.
The equipment information acquisition module comprises a preheating information acquisition unit, a maintenance data acquisition unit and a start-stop data acquisition unit; the preheating information acquisition unit is used for acquiring the time length required by the fact that the temperature of a position of a monitored transformer reaches the normal operation temperature when different transformers are operated for a plurality of times, the transformers are not maintained for a plurality of times, and the shutdown time length does not exceed the shutdown time length threshold; the maintenance data acquisition unit is used for acquiring the number of times data of the different transformers which are maintained in the past; the start-stop data acquisition unit is used for setting a shutdown time length threshold of the transformer and acquiring the times that the past shutdown time length of different transformers exceeds the shutdown time length threshold of the transformer and the exceeding time length information.
The equipment preheating analysis module comprises a preheating information calling unit and a reference time length judging unit; the preheating information calling unit is used for calling the time length data required by the fact that the temperature of a position of the monitored transformer reaches the normal operation temperature randomly to the reference time length judging unit when different transformers are operated for a plurality of times; the reference duration judging unit is used for calculating the average duration required by the random position temperature of the transformer reaching the normal operation temperature when the transformer is operated for a plurality of times, and taking the average duration as the reference preheating duration of the corresponding transformer.
The reference data optimization module comprises an interference factor analysis unit, a duration prediction model establishment unit and a preheating duration prediction unit; the interference factor analysis unit is used for analyzing the past maintenance data and start-stop data of the transformer to obtain a first interference factor and a second interference factor of the preheating of the transformer; the method comprises the steps that a duration prediction model building unit is used for obtaining the preheating delay time after the corresponding times of maintenance are carried out on the transformer and the shutdown time of the transformer exceeds a shutdown time threshold of the transformer, building a transformer preheating delay time prediction model according to a first interference factor, a second interference factor and the delay time, wherein the preheating delay time refers to the time after the corresponding times of maintenance are carried out on the transformer and the shutdown time of the transformer exceeds the shutdown time threshold of the transformer, and the preheating is delayed on the basis of the reference preheating time; the preheating duration prediction unit is used for obtaining a first interference factor and a second interference factor of the preheating of the current transformer, substituting the first interference factor and the second interference factor into the transformer preheating delay duration prediction model, predicting the delay duration of the preheating of the current transformer, and adding the delay duration of the preheating of the current transformer and the reference preheating duration of the current transformer as the finally predicted preheating duration of the current transformer.
The fault monitoring control module comprises a monitoring time selecting unit, an equipment temperature monitoring unit and a temperature abnormality alarm unit; the monitoring time selecting unit is used for selecting the time for monitoring the temperature of the current transformer to be: after the current transformer is started, carrying out temperature monitoring when the preheating duration of the current transformer is finally predicted and obtained by the starting time interval; the equipment temperature monitoring unit is used for monitoring the temperatures of different positions of the current transformer by using a temperature sensor; the temperature abnormality alarm unit is used for setting temperature thresholds of different positions, and sending a temperature abnormality alarm signal to the monitoring terminal when the temperature monitored by one random position exceeds the temperature threshold.
Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An intelligent analysis control method based on data analysis is characterized in that: the method comprises the following steps:
s10: acquiring preheating information, maintenance history information and downtime information of equipment;
s20: analyzing the reference preheating time length of the equipment before interference;
S30: optimizing preheating duration reference data by adding interference factors, and predicting the final preheating duration of the equipment;
s40: and (3) performing fault monitoring on the equipment after the equipment is predicted to be preheated, and performing alarm reminding when the equipment is monitored to be abnormal.
2. The intelligent analysis control method based on data analysis according to claim 1, wherein: in step S10: setting a shutdown time threshold of the transformer as T, collecting f times of running of a random transformer before maintenance is not performed and the shutdown time does not exceed the shutdown time threshold, obtaining an average shutdown exceeding time of the transformer by dividing the shutdown time exceeding T by the shutdown time exceeding T after summing the shutdown time exceeding T of each time of the transformer, and obtaining an average shutdown exceeding time of the m transformers as T '= { T 1',t2',…,tm' } by collecting the time of running of the random transformer at the random one position before maintenance is not performed and the shutdown time does not exceed the shutdown time threshold, wherein the time of collecting the previous maintenance of the m transformers is W= { W 1,W2,…,Wm }, and the time of exceeding T by collecting the previous shutdown time of the m transformers is L= { L 1,L2,…,Lm }.
3. The intelligent analysis control method based on data analysis according to claim 2, wherein: in step S20: according to the formulaAnd calculating the reference preheating time length K i of the random one transformer, wherein t j represents the time length required by the random one-position temperature to reach the normal operation temperature in the j-th operation before the random one transformer is not maintained and the shutdown time length is not beyond the shutdown time length threshold value, and calculating the reference preheating time length set of the m transformers to be K= { K 1,K2,…,Ki,…,Km }, by the same method.
4. A data analysis-based intelligent analysis control method according to claim 3, wherein: in step S30: the number of times that the transformer is maintained in the past is used as a first interference factor, a second interference factor E i for preheating one transformer is calculated according to a formula E i=Li*ti', a second interference factor set for preheating m transformers is obtained to be E= { E 1,E2,…,Em }, a delay time set for preheating the transformer after corresponding number of times of maintenance and a plurality of times of shutdown time exceeds a shutdown time threshold of the transformer is obtained to be A= { A 1,A2,…,Am }, a model training sample {(W1,E1,A1),(W2,E2,A2),…,(Wm,Em,Am)}, is generated, data fitting is carried out on the model training sample, and a transformer preheating delay time prediction model is established: z=a×x+b×y+c, where x represents an independent variable one in the prediction model that refers to the first interference factor, y represents an independent variable two in the prediction model that refers to the second interference factor, z represents an independent variable in the prediction model that refers to the warm-up delay time duration, a, b, and c represent fitting coefficients, and a, b, and c are solved for respectively according to the following formulas:
Wherein W i represents the number of times the ith transformer is maintained in the past, A i represents the time delay duration of preheating the ith transformer after the ith transformer is maintained for the corresponding number of times and the shutdown duration exceeds the shutdown duration threshold of the transformer for a plurality of times.
5. The intelligent analysis control method based on data analysis according to claim 4, wherein: obtaining a reference preheating time length k of a current transformer, wherein a first interference factor w and a second interference factor e of the preheating of the current transformer, and substituting w and e into a transformer preheating delay time length prediction model: let x=w, y=e, the delay time of predicting the current transformer preheating is: a, w+b, e+c, predicting to obtain the final preheating duration of the current transformer, wherein the final preheating duration is as follows: k+a+w+b+e+c;
in step S40: after the current transformer is started, a temperature sensor is controlled to monitor the temperature of the current transformer at different positions of the current transformer with a starting time interval k+a+w+b/e+c, temperature thresholds of different positions are set by using the temperature sensor, when the temperature monitored at a random position exceeds the temperature threshold, a temperature abnormality alarm signal is sent to a monitoring terminal, and abnormal temperature data is transmitted to the monitoring terminal.
6. An intelligent analysis control system based on data analysis adopts the intelligent analysis control method based on data analysis as claimed in claim 1, which is characterized in that: the system comprises: the system comprises an equipment information acquisition module, a data storage module, an equipment preheating analysis module, a reference data optimization module and a fault monitoring control module;
The output end of the equipment information acquisition module is connected with the input end of the data storage module, the output end of the data storage module is connected with the input ends of the equipment preheating analysis module and the reference data optimization module, the output end of the equipment preheating analysis module is connected with the input end of the reference data optimization module, and the output end of the reference data optimization module is connected with the input end of the fault monitoring control module;
The equipment information acquisition module is used for acquiring preheating information, maintenance history information and downtime information of equipment and transmitting all acquired data to the data storage module; the data storage module is used for storing preheating information, maintenance history information and downtime information of the equipment; the equipment preheating analysis module is used for analyzing the reference preheating time length of the equipment before interference; the reference data optimization module is used for optimizing the reference data of the preheating duration by adding the interference factors and predicting the final preheating duration of the equipment; the fault monitoring control module is used for controlling fault monitoring of the equipment after the equipment is predicted to finish preheating.
7. The intelligent analysis control method based on data analysis according to claim 6, wherein: the equipment information acquisition module comprises a preheating information acquisition unit, a maintenance data acquisition unit and a start-stop data acquisition unit;
The output ends of the preheating information acquisition unit, the maintenance data acquisition unit and the start-stop data acquisition unit are connected with the input end of the data storage module;
The preheating information acquisition unit is used for acquiring the time length required by the monitored temperature of a random position of the transformer to reach the normal operation temperature when different transformers are operated for a plurality of times, the transformers are not maintained for a plurality of times, and the shutdown time length does not exceed the shutdown time length threshold; the maintenance data acquisition unit is used for acquiring the number of times data of the different transformers which are maintained in the past; the start-stop data acquisition unit is used for setting a shutdown time threshold of the transformer and acquiring the times that the past shutdown time of different transformers exceeds the shutdown time threshold of the transformer and the exceeding time information.
8. The intelligent analysis control method based on data analysis according to claim 7, wherein: the equipment preheating analysis module comprises a preheating information calling unit and a reference duration judging unit;
The input end of the preheating information calling unit is connected with the output end of the data storage module, and the output end of the preheating information calling unit is connected with the input end of the reference duration judging unit;
The preheating information calling unit is used for calling duration data required by a position temperature of a monitored transformer reaching a normal operation temperature to the reference duration judging unit when different transformers are operated for a plurality of times in the past; the reference duration judging unit is used for calculating the average duration required by the temperature of a random position of the transformer reaching the normal operation temperature when the transformer is operated for a plurality of times, and taking the average duration as the reference preheating duration of the corresponding transformer.
9. The intelligent analysis control method based on data analysis according to claim 8, wherein: the reference data optimization module comprises an interference factor analysis unit, a duration prediction model establishment unit and a preheating duration prediction unit;
the input end of the interference factor analysis unit is connected with the output end of the data storage module, the output ends of the interference factor analysis unit and the reference duration judgment unit are connected with the input end of the duration prediction model establishment unit, and the output end of the duration prediction model establishment unit is connected with the input end of the preheating duration prediction unit;
The interference factor analysis unit is used for analyzing the past maintenance data and start-stop data of the transformer to obtain a first interference factor and a second interference factor of the preheating of the transformer; the time length prediction model building unit is used for obtaining the preheating time delay time length of the transformer after the corresponding times of maintenance are carried out on the transformer and the time length of a plurality of times of shutdown exceeds the threshold value of the time length of the transformer shutdown, and building a transformer preheating time delay time length prediction model according to the first interference factor, the second interference factor and the time delay time length; the preheating duration prediction unit is used for obtaining a first interference factor and a second interference factor of the preheating of the current transformer, substituting the first interference factor and the second interference factor into the transformer preheating delay duration prediction model, predicting the delay duration of the preheating of the current transformer, and adding the delay duration of the preheating of the current transformer and the reference preheating duration of the current transformer as the finally predicted preheating duration of the current transformer.
10. The intelligent analysis control method based on data analysis according to claim 9, wherein: the fault monitoring control module comprises a monitoring time selecting unit, an equipment temperature monitoring unit and a temperature abnormality alarming unit;
The input end of the monitoring time selecting unit is connected with the output end of the preheating duration predicting unit, the output end of the monitoring time selecting unit is connected with the input end of the equipment temperature monitoring unit, and the output end of the equipment temperature monitoring unit is connected with the input end of the temperature abnormality alarming unit;
The monitoring time selecting unit is used for selecting the time for monitoring the temperature of the current transformer to be: after the current transformer is started, carrying out temperature monitoring when the preheating duration of the current transformer is finally predicted and obtained by the starting time interval; the equipment temperature monitoring unit is used for monitoring the temperatures of different positions of the current transformer by using a temperature sensor; the temperature abnormality alarm unit is used for setting temperature thresholds of different positions, and sending a temperature abnormality alarm signal to the monitoring terminal when the temperature monitored by one random position exceeds the temperature threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410182196.4A CN118050579B (en) | 2024-02-19 | 2024-02-19 | Intelligent analysis control method based on data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410182196.4A CN118050579B (en) | 2024-02-19 | 2024-02-19 | Intelligent analysis control method based on data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118050579A true CN118050579A (en) | 2024-05-17 |
CN118050579B CN118050579B (en) | 2024-07-23 |
Family
ID=91047633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410182196.4A Active CN118050579B (en) | 2024-02-19 | 2024-02-19 | Intelligent analysis control method based on data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118050579B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0351833A2 (en) * | 1988-07-20 | 1990-01-24 | Mitsubishi Jukogyo Kabushiki Kaisha | Plant fault diagnosis system |
WO2008047098A1 (en) * | 2006-10-18 | 2008-04-24 | Bp Oil International Limited | Abnormal event detection using principal component analysis |
CN206162172U (en) * | 2016-07-27 | 2017-05-10 | 重庆汇华渝投节能科技有限公司 | Pumping station remote monitering system |
CN106841910A (en) * | 2016-12-20 | 2017-06-13 | 国网辽宁省电力有限公司沈阳供电公司 | Imitative electromagnetism algorithm is melted into the Fault Diagnosis Method for Distribution Networks of timing ambiguity Petri network |
KR101962739B1 (en) * | 2018-08-27 | 2019-03-28 | 서울교통공사 | Failure Prediction Analysis System of Machine Equipment Using Big Data Analysis and Method Thereof |
DE102020101911A1 (en) * | 2020-01-28 | 2021-07-29 | Audi Aktiengesellschaft | Computer-implemented method for training an artificial neural network, computer-implemented method for visual object recognition, method for controlling a motor vehicle, computer program and computer-readable storage medium |
CN113654686A (en) * | 2021-10-20 | 2021-11-16 | 深圳市信润富联数字科技有限公司 | Reflow furnace temperature monitoring management method and system for ICT production line |
US20220259947A1 (en) * | 2021-02-18 | 2022-08-18 | Yantai Jereh Petroleum Equipment & Technologies Co., Ltd. | Monitoring system and method for wellsite equipment |
CN115790895A (en) * | 2022-10-24 | 2023-03-14 | 广西电网有限责任公司河池供电局 | Transformer temperature online monitoring data processing and thermal state evaluation method |
CN116433136A (en) * | 2023-04-18 | 2023-07-14 | 深圳市元美供应链管理有限公司 | Freight safety monitoring system and method based on big data |
-
2024
- 2024-02-19 CN CN202410182196.4A patent/CN118050579B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0351833A2 (en) * | 1988-07-20 | 1990-01-24 | Mitsubishi Jukogyo Kabushiki Kaisha | Plant fault diagnosis system |
WO2008047098A1 (en) * | 2006-10-18 | 2008-04-24 | Bp Oil International Limited | Abnormal event detection using principal component analysis |
CN206162172U (en) * | 2016-07-27 | 2017-05-10 | 重庆汇华渝投节能科技有限公司 | Pumping station remote monitering system |
CN106841910A (en) * | 2016-12-20 | 2017-06-13 | 国网辽宁省电力有限公司沈阳供电公司 | Imitative electromagnetism algorithm is melted into the Fault Diagnosis Method for Distribution Networks of timing ambiguity Petri network |
KR101962739B1 (en) * | 2018-08-27 | 2019-03-28 | 서울교통공사 | Failure Prediction Analysis System of Machine Equipment Using Big Data Analysis and Method Thereof |
DE102020101911A1 (en) * | 2020-01-28 | 2021-07-29 | Audi Aktiengesellschaft | Computer-implemented method for training an artificial neural network, computer-implemented method for visual object recognition, method for controlling a motor vehicle, computer program and computer-readable storage medium |
US20220259947A1 (en) * | 2021-02-18 | 2022-08-18 | Yantai Jereh Petroleum Equipment & Technologies Co., Ltd. | Monitoring system and method for wellsite equipment |
CN113654686A (en) * | 2021-10-20 | 2021-11-16 | 深圳市信润富联数字科技有限公司 | Reflow furnace temperature monitoring management method and system for ICT production line |
CN115790895A (en) * | 2022-10-24 | 2023-03-14 | 广西电网有限责任公司河池供电局 | Transformer temperature online monitoring data processing and thermal state evaluation method |
CN116433136A (en) * | 2023-04-18 | 2023-07-14 | 深圳市元美供应链管理有限公司 | Freight safety monitoring system and method based on big data |
Non-Patent Citations (2)
Title |
---|
王晓云: "矿山设备预测性维修大数据分析***的建设", 科技创新导报, no. 17, 11 June 2020 (2020-06-11) * |
荆涛: "牵引变电所开关设备安全在线监测***研究", 铁路计算机应用, no. 04, 25 April 2015 (2015-04-25) * |
Also Published As
Publication number | Publication date |
---|---|
CN118050579B (en) | 2024-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101943921B (en) | Intelligent control method and intelligent control device of transformer cooling system | |
CN116184915B (en) | Method and system for monitoring running state of industrial Internet equipment | |
CN116435634B (en) | Storage battery temperature state monitoring and management system | |
CN116260119B (en) | Circuit breaker protection method and system for circuit data identification | |
CN115356592B (en) | Novel fault monitoring method and system for low-voltage distribution equipment | |
CN117689214B (en) | Dynamic safety assessment method for energy router of flexible direct-current traction power supply system | |
CN110556828B (en) | Online safety and stability emergency control method and system adaptive to equipment power flow change | |
CN116700123B (en) | Integrated EtherCAT bus I/O module | |
CN111398723A (en) | Intelligent transformer fault diagnosis model method | |
CN112762990A (en) | Prediction method and prediction system for equipment health degree | |
CN118050579B (en) | Intelligent analysis control method based on data analysis | |
CN109490675B (en) | Early warning method, electronic device and test system | |
CN112731827B (en) | Monitoring system for intelligent sensor for power equipment | |
CN110707373B (en) | Energy storage system based on storage battery fatigue monitoring and dynamic maintenance | |
CN116667632B (en) | Rectifier control method and control system | |
CN117034174A (en) | Transformer substation equipment abnormality detection method and system | |
CN115580082B (en) | Heat dissipation processing system and method for iron core of variable-pitch servo motor of wind turbine generator | |
CN116465059A (en) | Energy-saving air conditioner operation supervision system based on data analysis | |
CN116245279A (en) | Dynamic capacity-increasing decision-making method for transformer | |
CN112699104B (en) | Data processing method of intelligent sensor of power equipment and intelligent sensor | |
CN114662566A (en) | Power dispatching system fault detection equipment and detection method based on big data | |
CN114825625A (en) | Operation and maintenance system and method for battery energy storage power station | |
CN113765111A (en) | SVG fault analysis system | |
CN110609198A (en) | Operation and maintenance monitoring method for cable line and related equipment | |
CN113570473A (en) | Equipment fault monitoring method and device, computer equipment and storage medium |
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 |