CN115758733A - Method, device and equipment for predicting temperature of wire joint and storage medium - Google Patents
Method, device and equipment for predicting temperature of wire joint and storage medium Download PDFInfo
- Publication number
- CN115758733A CN115758733A CN202211453984.XA CN202211453984A CN115758733A CN 115758733 A CN115758733 A CN 115758733A CN 202211453984 A CN202211453984 A CN 202211453984A CN 115758733 A CN115758733 A CN 115758733A
- Authority
- CN
- China
- Prior art keywords
- temperature
- wire
- joint
- target
- humidity
- 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.)
- Pending
Links
Images
Abstract
The invention discloses a method, a device, equipment and a storage medium for predicting the temperature of a wire joint, wherein the method comprises the following steps: preprocessing a target wire joint by using historically measured target wire skin temperature, environment humidity, environment temperature and joint temperature to obtain a historical parameter set of a target wire; performing time sequence analysis on a historical data set of a target lead to obtain a lead joint temperature prediction model; acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire; and inputting the current wire skin temperature, the ambient humidity and the ambient temperature as a time sequence starting point label into the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period. Therefore, the temperature of the wire joint can be accurately predicted, and the conditions of fusing and the like of the wire joint are avoided.
Description
Technical Field
The invention belongs to the field of artificial intelligence, and particularly relates to a method, a device, equipment and a storage medium for predicting the temperature of a wire joint.
Background
The temperature at the joint of the wire is too high, so that the potential hazards of joint fusing, hardware fitting fire, wire droop and the like can appear in serious conditions, and the safe and stable operation of a power supply system is seriously influenced. Therefore, how to predict the temperature of the lead joint in time becomes a technical problem to be solved urgently at present, the conventional method mainly adopts expert evaluation, the expert acquires information through own sense or instrument, and then judges the temperature of the lead joint through own subjective consciousness and experience, but the expert evaluation method is easily influenced by subjective factors such as personal experience and physical condition of the expert, so that the problem of inaccurate prediction is caused.
Disclosure of Invention
The main purposes of the invention are as follows: the utility model provides a wire joint temperature prediction method, a device, equipment and a storage medium, which aims to solve the technical problems that the temperature of a wire joint is difficult to be accurately predicted in the prior art, so that the temperature at the wire joint is too high to operate, and the potential hazards of joint fusing, hardware fitting fire, wire drooping and the like can occur in serious conditions, thereby seriously affecting the safe and stable operation of a power supply system.
The technical scheme of the invention is as follows:
a wire-joint temperature prediction method, comprising the steps of:
acquiring historically measured target wire skin temperature, environment humidity, environment temperature and joint temperature;
preprocessing the target lead joint with the historically measured target lead skin temperature, environmental humidity, environmental temperature and joint temperature to obtain a historical parameter set of the target lead;
performing time sequence analysis on the historical data set of the target lead to obtain a lead joint temperature prediction model;
acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire;
and inputting the current wire surface temperature, the environmental humidity and the environmental temperature as a time sequence starting point label into the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period.
Optionally, performing a time sequence analysis on the historical data set of the target conductor to obtain a conductor joint temperature prediction model, including:
according to the historical data set of the target lead, decomposing the historical data set of the target lead of each month through a seasonal adjustment strategy to obtain a trend cyclic variable and a seasonal variable;
determining relevant parameters of a wire joint temperature prediction model according to trend cyclic variables corresponding to the historical data set of the target wire in each month;
and establishing a wire joint temperature prediction model according to the relevant parameters of the wire joint temperature prediction model.
Optionally, the preprocessing the target conductor joint of the historically measured target conductor skin temperature, ambient humidity, ambient temperature and joint temperature to obtain the historical parameter set of the target conductor includes:
counting historical data of target wire skin temperature, environmental humidity, environmental temperature and joint temperature for a plurality of months before the beginning of a prediction period;
filling missing values of historical data of the target lead skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the previous months;
identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history;
and judging whether the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity, and if not, repeatedly executing the operation until the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity.
Optionally, before the filling missing values of the historical data of the target wire skin temperature, the ambient humidity, the ambient temperature and the joint temperature of the previous months, the method further includes:
decomposing the target wire skin temperature, the ambient humidity, the ambient temperature and the joint temperature into long-term trend data and seasonal trend data which are suitable for the wire joint temperature model;
respectively carrying out stationarity check and white noise check on the long-term trend data and the seasonal trend data;
and when the stationarity test and the white noise test pass, executing a step of filling missing values of the historically measured target wire skin temperature, the environment humidity, the environment temperature and the joint temperature.
Optionally, the performing stationarity check and white noise check on the long-term trend data and the seasonal trend data respectively includes:
respectively carrying out stability detection on the long-term trend data and the seasonal trend data, and if the detection fails, carrying out differential operation on the data which do not pass the detection;
repeating the operation until the long-term trend data and the seasonal trend data pass stationarity test, and carrying out white noise test on the stationarity test data;
and if the white noise test is not passed, rejecting the long-term trend data and the seasonal trend data.
Optionally, the inputting the current wire sheath temperature, the ambient humidity, and the ambient temperature to the wire joint temperature prediction model as a timing start point tag to obtain a wire joint temperature prediction result in a future period includes:
performing prediction operation on the trend cyclic variable corresponding to the historical data set of the target conductor of each month to obtain a seasonal variable corresponding to each month in a corresponding prediction period;
and respectively multiplying the trend cycle variable corresponding to each month in the prediction period by the seasonal variable of the corresponding month to obtain the predicted value of the lead joint temperature of the corresponding month in the prediction period.
Optionally, after the current wire skin temperature, the ambient humidity, and the ambient temperature are input to the wire joint temperature prediction model as a time sequence starting point tag and a wire joint temperature prediction result in a preset time period is obtained, the method further includes:
continuously acquiring the skin temperature, the environment humidity, the environment temperature and the joint temperature of a target wire measured historically according to the prediction time period;
inputting the acquired target wire skin temperature, the acquired environment humidity, the acquired environment temperature and the acquired joint temperature into the historical data set to obtain a new historical data set;
and correcting the wire joint temperature prediction model according to the new historical data set.
In addition, in order to achieve the above object, the present invention provides a wire-terminal temperature predicting apparatus, including:
the acquisition module is used for acquiring the historically measured skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the target wire;
the processing module is used for preprocessing the target wire joint of the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature which are measured historically to obtain a historical parameter set of the target wire;
the modeling module is used for carrying out time sequence analysis on the historical data set of the target lead to obtain a lead joint temperature prediction model;
the acquisition module is also used for acquiring the current lead skin temperature, the ambient humidity and the ambient temperature;
and the prediction module is used for inputting the current wire surface skin temperature, the environment humidity and the environment temperature as a time sequence starting point label to the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a future period.
Further, to achieve the above object, the present invention also proposes a wire-terminal temperature prediction apparatus, comprising: a memory, a processor, and a wire-terminal temperature prediction program stored on the memory and run on the processor, the wire-terminal temperature prediction program configured to implement the wire-terminal temperature prediction method as described above.
In addition, in order to achieve the above object, the present invention further provides a storage medium having a wire-joint temperature prediction program stored thereon, which when executed by a processor implements the wire-joint temperature prediction method as described above.
The invention has the beneficial effects that:
the invention discloses a method, a device, equipment and a storage medium for predicting the temperature of a wire joint, wherein the method comprises the following steps: acquiring historically measured target wire skin temperature, environment humidity, environment temperature and joint temperature; preprocessing a target wire joint with historically measured target wire surface temperature, environment humidity, environment temperature and joint temperature to obtain a historical parameter set of a target wire; performing time sequence analysis on a historical data set of a target lead to obtain a lead joint temperature prediction model; acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire; and inputting the current surface temperature, the environmental humidity and the environmental temperature of the wire as a time sequence starting point label into the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period. Therefore, a time sequence prediction model of the temperature of the wire joint based on seasonal circulation is established, and when the current skin temperature, the ambient temperature and the ambient humidity of the wire are input, the temperature of the wire joint in the future period of the wire is accurately predicted.
Drawings
FIG. 1 is a schematic diagram of a wire-joint temperature prediction device for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a method for predicting a temperature of a wire joint according to the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of a method for predicting a temperature of a wire joint according to the present invention;
FIG. 4 is a schematic flow chart illustrating a third embodiment of a method for predicting a temperature of a wire joint according to the present invention;
fig. 5 is a functional block diagram of a first embodiment of a device for predicting a temperature of a wire joint according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a wire joint temperature prediction device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the wire-terminal temperature prediction apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display screen (Display), and the optional user interface 1003 may further include a standard wired interface and a wireless interface, and the wired interface for the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or a Non-volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001 described previously.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the wire-terminal temperature prediction device, and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in FIG. 1, memory 1005, identified as one type of computer storage medium, may include an operating system, a network communication module, a user interface module, and a wire-bond temperature prediction program.
In the device for predicting the temperature of a wire-terminal shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and communicating data with the background server; the user interface 1003 is mainly used for connecting user equipment; the wire-terminal temperature prediction apparatus calls a wire-terminal temperature prediction program stored in the memory 1005 by the processor 1001 and executes the wire-terminal temperature prediction method provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the wire joint temperature prediction method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a wire joint temperature prediction method according to a first embodiment of the present invention, and the wire joint temperature prediction method according to the first embodiment of the present invention is provided.
In a first embodiment, the wire-joint temperature prediction method includes the steps of:
step S10: and acquiring the historically measured target wire skin temperature, ambient humidity, ambient temperature and joint temperature.
It is understood that the main execution body of the present embodiment is a wire-terminal temperature prediction apparatus having functions of data processing, data communication, program execution, and the like.
In an implementation, a data set is established to store the measured data, a storage period is set, and the data is stored continuously according to the preset storage period.
It should be noted that the outer skin temperature, ambient temperature, joint temperature and ambient humidity selected for measurement are all important variables affecting the wire joint temperature. The high-voltage wire measured here is a high-voltage wire which is easy to fuse and the like when working in a high-voltage environment for a long time, wherein the high-voltage route in 10kv urban area mostly adopts a wire with an insulating skin, but even if the insulating skin exists, the wire pole or the iron tower needs to be insulated by one or more porcelain bottles.
Step S20: and preprocessing the target lead surface temperature, the environment humidity, the environment temperature and the joint temperature of the historical measurement to obtain a historical parameter set of the target lead.
In a specific implementation, historical data of target wire skin temperature, ambient humidity, ambient temperature and joint temperature several months before the beginning of a prediction period are counted; filling missing values of historical data of the target lead skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the previous months; identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history; and judging whether the processed historically measured target wire skin temperature, the processed environment humidity, the processed environment temperature and the processed connector temperature meet the periodicity, and if not, repeatedly executing the operation until the processed historically measured target wire skin temperature, the processed environment humidity, the processed environment temperature and the processed connector temperature meet the periodicity. And repeating the operation until a data set with strong regularity after pretreatment is obtained.
It should be understood that the historical data set preprocessing is an especially important loop in the time sequence modeling, and is used for optimizing the historical parameter set, preprocessing the historical parameter set, eliminating wrong data in the data set, and then predicting the target conductor joint temperature by using a new historical data set.
Step S30: and carrying out time sequence analysis on the historical data set of the target lead to obtain a lead joint temperature prediction model.
In specific implementation, according to the historical data set of the target lead, decomposing the historical data set of the target lead in each month through a seasonal adjustment strategy to obtain a trend cyclic variable and a seasonal variable; determining relevant parameters of a wire joint temperature prediction model according to trend cyclic variables corresponding to the historical data set of the target wire in each month; and establishing a wire joint temperature prediction model according to the relevant parameters of the wire joint temperature prediction model.
It should be understood that the ambient temperature and ambient humidity are generally greatly affected by the alternation of seasons, for example, the temperature in winter is generally lower than the ambient temperature in summer, and the humidity in plum rain in summer is also generally higher than that in autumn, so that the historical data sets are classified according to the seasonal rule, thereby improving the accuracy of prediction.
It should be noted that the timing prediction is to predict the future temperature change of the wire joint through a historical data set, for example: in the last years, the target wire is at the skin temperature of 20 ℃, the ambient temperature of 15 ℃ and the ambient humidity of 5 grams per cubic meter, and the joint temperature is 30 ℃; the temperature of the surface is 20 ℃, the ambient temperature is 20 ℃ and the ambient humidity is 5 g per cubic meter, and the temperature of the joint is 35 ℃; the temperature of the surface is 20 ℃, the ambient temperature is 25 ℃ and the ambient humidity is 5 grams per cubic meter, and the temperature of the joint is 40 ℃, so that the temperature of the surface can be estimated to be 20 ℃, the ambient temperature is 30 ℃, the ambient humidity is 5 grams per cubic meter, and the temperature of the joint is 45 ℃.
Step S40: and acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire.
In a specific implementation, the wire joint temperature prediction device sends a collection instruction to the humidity sensor and the temperature sensor, so that the humidity sensor and the temperature sensor start to collect the outer skin temperature, the ambient temperature, the joint temperature and the ambient humidity of the target wire after receiving the collection instruction.
Step S50: and inputting the current wire skin temperature, the ambient humidity and the ambient temperature as a time sequence starting point label to the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period.
In specific implementation, performing prediction operation on the trend cyclic variable corresponding to the historical data set of the target conductor of each month to obtain a seasonal variable corresponding to each month in a corresponding prediction period; and respectively multiplying the trend cycle variable corresponding to each month in the prediction period by the seasonal variable of the corresponding month to obtain the predicted value of the lead joint temperature of the corresponding month in the prediction period. Therefore, the time sequence prediction can be related to seasons, the temperature change of the season can be predicted according to the information of the corresponding season, and the prediction accuracy is improved.
It should be understood that as used herein is a multiplication model of the X12 seasonal adjustment method in Eviews software that decomposes the historical parameter set sequence into a corresponding trend loop variable sequence and the product of the seasonal variable sequence and the random variable sequence. Can be represented by equation 1.
TL = TL-TC × TL-SF × TL-IR (formula 1)
Wherein TL represents a history parameter set sequence, TL-TC represents a corresponding trend cycle variable sequence, and TL-IR represents a random variable sequence.
In the embodiment, the target wire joint is preprocessed according to the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature which are measured historically, so that a historical parameter set of the target wire is obtained; performing time sequence analysis on a historical data set of a target lead to obtain a lead joint temperature prediction model; acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire; and inputting the current surface temperature, the environmental humidity and the environmental temperature of the wire as a time sequence starting point label into the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period. Therefore, a time sequence prediction model of the temperature of the wire joint based on seasonal circulation is established, and the temperature of the wire joint in the future period of the wire is accurately predicted when the current skin temperature, the ambient temperature and the ambient humidity of the wire are input.
Referring to fig. 3, fig. 3 is a schematic flow chart of a wire-terminal temperature prediction method according to a second embodiment of the present invention, which is proposed based on the first embodiment shown in fig. 2.
In the second embodiment, the step S30 includes:
step S301: and decomposing the historical data set of the target lead of each month through a seasonal adjustment strategy according to the historical data set of the target lead to obtain a trend cyclic variable and a seasonal variable.
The trend cyclicity means that the temperature of the wire joint changes regularly with the change of the working environment, for example, every time the environmental temperature is increased by 5 degrees centigrade, the corresponding temperature of the wire joint is also increased by 5 degrees centigrade, the regularity that the temperature of the wire joint changes with the environmental temperature can be obtained, and similarly, the trend that the working environment is increased and the temperature of the wire joint is also increased is obtained.
Step S302: and determining relevant parameters of a wire joint temperature prediction model according to the trend cyclic variables corresponding to the historical data sets of the target wires in each month.
In specific implementation, a value of a difference order d in a time series model is determined according to a difference order in difference change processing, if a trend cyclic variable sequence meets a stationary sequence condition, the trend cyclic variable sequence is directly regarded as a stationary sequence, autocorrelation analysis is performed on the stationary sequence to determine possible values of an autoregressive parameter and a sliding average order parameter in the time series model, and the most appropriate combination of the autoregressive parameter and the sliding order parameter is selected from the obtained possible values of the autoregressive order parameter and the sliding average order parameter, so that the parameter of the current time model is determined.
Step S303: and establishing a wire joint temperature prediction model according to the relevant parameters of the wire joint temperature prediction model.
In a specific implementation, the relevant parameter establishing model of the wire joint temperature prediction model comprises a stationary time series and a non-stationary time series, the stationary time series comprises an autoregressive model and a moving translation model, and the p-order autoregressive model satisfies the following formula 2;
u t ＝c+φ 1 u t-1 +φ 2 u t-2 +...+φ p u t-2 +ε t t =1, 2.., tre, T-equation 2
Wherein phi 1 、φ 2 ...φ p Are regression model parameters; p is the autoregressive model order; epsilon t Is a white noise sequence with a mean value of 0.
In the embodiment, according to the historical data set of the target conductor, the historical data set of the target conductor in each month is decomposed through a seasonal adjustment strategy to obtain a trend cyclic variable and a seasonal variable; determining relevant parameters of a wire joint temperature prediction model according to trend cyclic variables corresponding to the historical data set of the target wire in each month; and establishing a wire joint temperature prediction model according to the relevant parameters of the wire joint temperature prediction model. Therefore, a corresponding lead joint temperature prediction model can be established according to the characteristics of different seasons, and the temperature of the lead joint in the preset time period can be accurately predicted.
Referring to fig. 4, fig. 4 is a flowchart illustrating a third embodiment of the method for predicting the temperature of a wire joint according to the present invention, and the third embodiment of the method for predicting the temperature of a wire joint according to the present invention is proposed based on the first embodiment shown in fig. 2.
In a third embodiment, the step S20 includes:
step S201: historical data of target wire skin temperature, ambient humidity, ambient temperature, and joint temperature several months before the start of the prediction period are counted.
It should be noted that, the accuracy of selecting the data of the previous months of the historical data and selecting the data of the same season for prediction can be improved.
Step S202: and filling missing values of historical data of the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the previous months.
In specific implementation, before preprocessing the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature which are measured historically, filling missing values of the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature which are measured historically; identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history; and judging whether the processed target wire skin temperature, the processed environment humidity, the processed environment temperature and the processed joint temperature meet the periodicity, and if not, repeatedly executing the operation. For example: an excessively high ambient temperature, for example 100 degrees celsius, which is an abnormal condition, needs to be removed, or a skin temperature of 20 degrees celsius, an ambient temperature of 15 degrees celsius, an ambient humidity of 5 grams per cubic meter, which is a 30 degree celsius, a joint temperature of 20 degrees celsius, an ambient temperature of 5 degrees celsius, an ambient humidity of 5 grams per cubic meter, which is a 80 degree celsius, which is an abnormal condition, which also needs to be removed.
Step S203: and identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured in the history.
It should be noted that, a specific sequential detection process is that, if stationarity detection of previous data fails, difference operation is performed on the long-term tendency data or seasonal data and stationarity check is performed again until the long-term tendency data all pass stationarity check, white noise check is started, and if the white noise check fails, the temperature and humidity historical data is determined to be invalid data; on the contrary, if the white noise test is passed, the data is considered to have a correlation in time sequence.
Step S204: and judging whether the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity, and if not, repeatedly executing the operation until the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity.
It should be noted that, because the alternation of the diurnal temperature difference and the seasonal change both satisfy the periodic change, the line skin temperature, the ambient humidity, the ambient temperature and the joint temperature measured by us should also satisfy the natural law, satisfy the periodic change condition, if not, may be an abnormal condition, and need to repeat the treatment process until the law is satisfied.
In the embodiment, historical data of target wire skin temperature, environmental humidity, environmental temperature and joint temperature several months before the start of the prediction period are counted; filling missing values of historical data of the target lead skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the previous months; identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically; and judging whether the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity, and if not, repeatedly executing the operation until the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity. Therefore, error data in historical measurement data are eliminated, and the accuracy of prediction is improved.
Furthermore, an embodiment of the present invention further provides a storage medium, where a wire joint temperature prediction program is stored, and the wire joint temperature prediction program, when executed by a processor, implements the steps of the wire joint temperature prediction method as described above.
Since the storage medium may adopt the technical solutions of all the embodiments, at least the beneficial effects brought by the technical solutions of the embodiments are achieved, and are not described in detail herein.
Referring to fig. 5, fig. 5 is a functional block diagram of a wire-terminal temperature predicting device according to a first embodiment of the present invention.
In a first embodiment of the wire-terminal temperature predicting apparatus according to the present invention, the wire-terminal temperature predicting apparatus includes:
and the acquisition module 10 is used for acquiring the historically measured target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature.
And the processing module 20 is configured to preprocess the target conductor joint according to the historically measured target conductor skin temperature, ambient humidity, ambient temperature, and joint temperature, so as to obtain a historical parameter set of the target conductor.
And the modeling module 30 is used for performing time sequence analysis on the historical data set of the target lead to obtain a lead joint temperature prediction model.
The obtaining module 10 is further configured to obtain a current surface temperature, an ambient humidity, and an ambient temperature of the wire.
And the prediction module 40 is configured to input the current wire sheath temperature, the ambient humidity, and the ambient temperature as a time sequence start point tag to the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a future period.
In the embodiment, the target wire joint is preprocessed according to the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature which are measured historically, so that a historical parameter set of the target wire is obtained; performing time sequence analysis on a historical data set of a target lead to obtain a lead joint temperature prediction model; acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire; and inputting the current wire skin temperature, the ambient humidity and the ambient temperature as a time sequence starting point label into the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period. Therefore, a time sequence prediction model of the temperature of the wire joint based on seasonal circulation is established, and when the current skin temperature, the ambient temperature and the ambient humidity of the wire are input, the temperature of the wire joint in the future period of the wire is accurately predicted.
In an embodiment, the processing module 20 is further configured to preprocess the target conductor joint of the historical measured target conductor skin temperature, ambient humidity, ambient temperature, and joint temperature to obtain the historical parameter set of the target conductor, where the preprocessing includes:
counting historical data of target wire skin temperature, environmental humidity, environmental temperature and joint temperature for a plurality of months before the beginning of a prediction period;
filling missing values of historical data of the target lead skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the previous months;
identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically;
and judging whether the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity, and if not, repeatedly executing the operation until the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity.
In an embodiment, before filling missing values of the historical data of the target wire skin temperature, the ambient humidity, the ambient temperature, and the joint temperature of the previous months, the processing module 20 further includes:
decomposing the target wire skin temperature, the ambient humidity, the ambient temperature and the joint temperature into long-term trend data and seasonal trend data which are suitable for the wire joint temperature prediction model;
respectively carrying out stationarity check and white noise check on the long-term trend data and the seasonal trend data;
and when the stationarity test and the white noise test pass, executing a step of filling missing values of the historically measured target wire skin temperature, the environment humidity, the environment temperature and the joint temperature.
In an embodiment, the processing module 20 is further configured to perform stationarity check and white noise check on the long-term trend data and the seasonal trend data, respectively, and includes:
respectively carrying out stability detection on the long-term trend data and the seasonal trend data, and if the detection fails, carrying out differential operation on the data which do not pass the detection;
repeating the operation until the long-term trend data and the seasonal trend data pass stationarity test, and carrying out white noise test on the stationarity test data;
and if the white noise test is not passed, rejecting the long-term trend data and the seasonal trend data.
In an embodiment, the processing module 20 is further configured to input the current wire skin temperature, the ambient humidity, and the ambient temperature as a time sequence starting point tag into the wire joint temperature prediction model, and after obtaining a wire joint temperature prediction result in a preset time period, the method further includes:
continuously acquiring the skin temperature, the environment humidity, the environment temperature and the joint temperature of a target wire measured historically according to the prediction time period;
inputting the acquired target wire skin temperature, the acquired environment humidity, the acquired environment temperature and the acquired joint temperature into the historical data set to obtain a new historical data set;
and correcting the wire temperature prediction model according to the new historical data set.
In an embodiment, the modeling module 30 is further configured to perform a time sequence analysis on the historical data set of the target conductor to obtain a conductor joint temperature prediction model, including:
according to the historical data set of the target lead, decomposing the historical data set of the target lead of each month through a seasonal adjustment strategy to obtain a trend cyclic variable and a seasonal variable;
determining relevant parameters of a wire joint temperature prediction model according to trend cyclic variables corresponding to the historical data set of the target wire in each month;
and establishing a wire joint temperature prediction model according to the relevant parameters of the wire joint temperature prediction model.
In an embodiment, the predicting module 40 is further configured to obtain the current wire sheath temperature, the ambient humidity, and the ambient temperature as time sequence start tags, which are input to the wire joint temperature predicting model, so as to obtain a wire joint temperature prediction result in a future period, and the method includes:
performing prediction operation on the trend cyclic variable corresponding to the historical data set of the target conductor of each month to obtain a seasonal variable corresponding to each month in a corresponding prediction period;
and respectively multiplying the trend cycle variable corresponding to each month in the prediction period by the seasonal variable of the corresponding month to obtain the predicted value of the lead joint temperature of the corresponding month in the prediction period.
Other embodiments or specific implementation manners of the device for predicting the temperature of the wire joint according to the present invention may refer to the above method embodiments, so that at least all the beneficial effects brought by the technical solutions of the above embodiments are provided, and no further description is provided herein.
Claims (10)
1. A method of predicting a temperature of a wire joint, the method comprising the steps of:
acquiring historically measured target wire skin temperature, environment humidity, environment temperature and joint temperature;
preprocessing the target lead joint of the target lead skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically to obtain a historical parameter set of the target lead;
performing time sequence analysis on the historical data set of the target lead to obtain a lead joint temperature prediction model;
acquiring the current surface temperature, the environmental humidity and the environmental temperature of the wire;
and inputting the current wire skin temperature, the ambient humidity and the ambient temperature as a time sequence starting point label to the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a preset time period.
2. The method of claim 1, wherein the step of performing a time series analysis on the historical data set of the target conductor to obtain a conductor joint temperature prediction model comprises:
decomposing the historical data set of the target lead of each month through a seasonal adjustment strategy according to the historical data set of the target lead to obtain a trend cyclic variable and a seasonal variable;
determining relevant parameters of a wire joint temperature prediction model according to trend cyclic variables corresponding to the historical data set of the target wire in each month;
and establishing a wire joint temperature prediction model according to the relevant parameters of the wire joint temperature prediction model.
3. The method of claim 1, wherein pre-processing the historically measured target wire skin temperature, ambient humidity, ambient temperature, and joint temperature target wire joint to obtain a historical set of parameters for the target wire comprises:
counting historical data of target wire skin temperature, environmental humidity, environmental temperature and joint temperature for a plurality of months before the beginning of a prediction period;
filling missing values of historical data of target lead skin temperature, environmental humidity, environmental temperature and joint temperature in previous months;
identifying and eliminating abnormal values in the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically, and carrying out smooth denoising on the target wire skin temperature, the environment humidity, the environment temperature and the joint temperature which are measured historically;
and judging whether the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity, and if not, repeatedly executing the operation until the processed historical measured target conductor skin temperature, the processed environmental humidity, the processed environmental temperature and the processed joint temperature meet the periodicity.
4. The method of claim 3, wherein prior to populating the missing values of the historical data for the previous months of the target wire skin temperature, ambient humidity, ambient temperature, and joint temperature, further comprising:
decomposing the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature into long-term trend data and seasonal trend data which are suitable for the wire joint temperature prediction model;
respectively carrying out stationarity check and white noise check on the long-term trend data and the seasonal trend data;
and when the stationarity test and the white noise test are passed, executing a step of filling missing values of the historically measured target wire skin temperature, the environment humidity, the environment temperature and the joint temperature.
5. The method of claim 4, wherein performing stationarity check and white noise check on the long-term trend data and the seasonal trend data, respectively, comprises:
respectively carrying out stationarity check on the long-term trend data and the seasonal trend data, and if the data do not pass the check, carrying out differential operation on the data which do not pass the check;
repeating the operation until the long-term trend data and the seasonal trend data pass stationarity test, and carrying out white noise test on the stationarity test data;
and if the white noise test is not passed, rejecting the long-term trend data and the seasonal trend data.
6. The method of claim 1, wherein inputting the current wire skin temperature, the ambient humidity, and the ambient temperature as timing start tags to the wire joint temperature prediction model to obtain a wire joint temperature prediction result for a future period of time comprises:
performing prediction operation on the trend cyclic variable corresponding to the historical data set of the target lead of each month to obtain a seasonal variable corresponding to each month in a corresponding prediction period;
and respectively multiplying the trend cycle variable corresponding to each month in the prediction period by the seasonal variable of the corresponding month to obtain the predicted value of the lead joint temperature of the corresponding month in the prediction period.
7. The method according to any one of claims 1 to 6, wherein the current wire sheath temperature, the ambient humidity and the ambient temperature are input to the wire joint temperature prediction model as time sequence starting point tags, and after a wire joint temperature prediction result in a preset time period is obtained, the method further comprises:
continuously acquiring the skin temperature, the environment humidity, the environment temperature and the joint temperature of a target wire measured historically according to the prediction time period;
inputting the acquired target wire skin temperature, the acquired environment humidity, the acquired environment temperature and the acquired joint temperature into the historical data set to obtain a new historical data set;
and correcting the wire joint temperature prediction model according to the new historical data set.
8. A wire-terminal temperature predicting apparatus, characterized by comprising:
the acquisition module is used for acquiring the historically measured skin temperature, the environmental humidity, the environmental temperature and the joint temperature of the target wire;
the processing module is used for preprocessing the target wire joint of the target wire skin temperature, the environmental humidity, the environmental temperature and the joint temperature which are measured historically to obtain a historical parameter set of the target wire;
the modeling module is used for carrying out time sequence analysis on the historical data set of the target lead to obtain a lead joint temperature prediction model;
the acquisition module is also used for acquiring the current lead skin temperature, the ambient humidity and the ambient temperature;
and the prediction module is used for inputting the current wire surface skin temperature, the environment humidity and the environment temperature as a time sequence starting point label to the wire joint temperature prediction model to obtain a wire joint temperature prediction result in a future period.
9. A wire-terminal temperature prediction apparatus comprising a memory, a processor, and a wire-terminal temperature prediction program stored on the memory and executable on the processor, the wire-terminal temperature prediction program when executed by the processor implementing the wire-terminal temperature prediction method according to any one of claims 1 to 7.
10. A storage medium having stored thereon a wire-joint temperature prediction program which, when executed by a processor, implements a wire-joint temperature prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211453984.XA CN115758733A (en) | 2022-11-21 | 2022-11-21 | Method, device and equipment for predicting temperature of wire joint and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211453984.XA CN115758733A (en) | 2022-11-21 | 2022-11-21 | Method, device and equipment for predicting temperature of wire joint and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115758733A true CN115758733A (en) | 2023-03-07 |
Family
ID=85333317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211453984.XA Pending CN115758733A (en) | 2022-11-21 | 2022-11-21 | Method, device and equipment for predicting temperature of wire joint and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115758733A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7987106B1 (en) * | 2006-06-05 | 2011-07-26 | Turgut Aykin | System and methods for forecasting time series with multiple seasonal patterns |
| CN103886374A (en) * | 2014-04-22 | 2014-06-25 | 武汉大学 | Cable joint wire temperature prediction method based on RBF neural network |
| CN105205570A (en) * | 2015-10-16 | 2015-12-30 | 国网重庆铜梁区供电有限责任公司 | Power grid power sale quantity prediction method based on season time sequence analysis |
| CN111191193A (en) * | 2020-01-17 | 2020-05-22 | 南京工业大学 | Long-term soil temperature and humidity high-precision prediction method based on autoregressive moving average model |
| CN112070284A (en) * | 2020-08-24 | 2020-12-11 | 上海东普信息科技有限公司 | Screening method, device, equipment and storage medium for component prediction |
| CN112257947A (en) * | 2020-10-30 | 2021-01-22 | 红云红河烟草(集团)有限责任公司 | Method, device and equipment for predicting temperature and humidity of cigarette making environment |
| CN113641959A (en) * | 2021-08-13 | 2021-11-12 | 山东电工电气集团有限公司 | High-voltage cable joint temperature trend prediction method |
-
2022
- 2022-11-21 CN CN202211453984.XA patent/CN115758733A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7987106B1 (en) * | 2006-06-05 | 2011-07-26 | Turgut Aykin | System and methods for forecasting time series with multiple seasonal patterns |
| CN103886374A (en) * | 2014-04-22 | 2014-06-25 | 武汉大学 | Cable joint wire temperature prediction method based on RBF neural network |
| CN105205570A (en) * | 2015-10-16 | 2015-12-30 | 国网重庆铜梁区供电有限责任公司 | Power grid power sale quantity prediction method based on season time sequence analysis |
| CN111191193A (en) * | 2020-01-17 | 2020-05-22 | 南京工业大学 | Long-term soil temperature and humidity high-precision prediction method based on autoregressive moving average model |
| CN112070284A (en) * | 2020-08-24 | 2020-12-11 | 上海东普信息科技有限公司 | Screening method, device, equipment and storage medium for component prediction |
| CN112257947A (en) * | 2020-10-30 | 2021-01-22 | 红云红河烟草(集团)有限责任公司 | Method, device and equipment for predicting temperature and humidity of cigarette making environment |
| CN113641959A (en) * | 2021-08-13 | 2021-11-12 | 山东电工电气集团有限公司 | High-voltage cable joint temperature trend prediction method |
Non-Patent Citations (1)
| Title |
|---|
| 王运金;饶和根;王蕾;廖文洲;: "基于ARIMA的路面低温短临预测方法与模型", 公路交通科技(应用技术版), no. 09 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102463764B1 (en) | Arrhythmia detection method, device, electronic device and computer storage medium | |
| CN112766342A (en) | Abnormity detection method for electrical equipment | |
| CN115878958B (en) | Transformer oil temperature prediction method, device, equipment and storage medium | |
| CN110287762B (en) | Non-invasive load identification method and device based on data mining technology | |
| CN111292020B (en) | Power grid real-time operation risk assessment method and system based on random forest | |
| CN108898238A (en) | Medical equipment failure forecasting system and correlation technique, device and equipment | |
| CN112308124B (en) | Intelligent electricity larceny prevention method for electricity consumption information acquisition system | |
| JP2021038927A (en) | Partial discharge determination device and method | |
| CN112257947A (en) | Method, device and equipment for predicting temperature and humidity of cigarette making environment | |
| CN113538370A (en) | Power grid inspection method and device, computer equipment and storage medium | |
| CN110766236A (en) | Power equipment state trend prediction method based on statistical analysis and deep learning | |
| CN111709548A (en) | Power consumer load prediction method, device, equipment and storage medium based on support vector machine | |
| CN107252323B (en) | Method and device for predicting female physiological cycle and user equipment | |
| CN117293824A (en) | Method, apparatus and computer readable storage medium for power demand prediction | |
| CN115758733A (en) | Method, device and equipment for predicting temperature of wire joint and storage medium | |
| CN112506687A (en) | Fault diagnosis method based on multi-period segmented sliding window standard deviation | |
| CN113282813A (en) | Data visualization method applied to big data and big data cloud server | |
| CN115329814B (en) | Low-voltage user link identification method and device based on image signal processing | |
| CN111784042A (en) | Power utilization node safety risk prediction method and device and storage medium | |
| CN114860617B (en) | Intelligent pressure testing method and system | |
| CN115586321A (en) | Method, system, memory and equipment for identifying online monitoring data of dissolved gas in oil | |
| CN113408730B (en) | Causal relationship generation method and device and electronic equipment | |
| CN113971136A (en) | Page testing method and system based on image recognition | |
| TW202134678A (en) | Battery performance evaluation device, electronic apparatus, charger, and battery performance evaluation method | |
| CN115906631A (en) | Method, device and equipment for predicting oil temperature of circuit breaker 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 |