CN112036004B - Method and system for predicting oil temperature of phase modulation engine oil system based on dynamic selection of similar moments - Google Patents
Method and system for predicting oil temperature of phase modulation engine oil system based on dynamic selection of similar moments Download PDFInfo
- Publication number
- CN112036004B CN112036004B CN202010674556.4A CN202010674556A CN112036004B CN 112036004 B CN112036004 B CN 112036004B CN 202010674556 A CN202010674556 A CN 202010674556A CN 112036004 B CN112036004 B CN 112036004B
- Authority
- CN
- China
- Prior art keywords
- phase modulation
- oil temperature
- day
- predicted
- oil system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003921 oil Substances 0.000 title claims abstract description 126
- 239000010705 motor oil Substances 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 239000010721 machine oil Substances 0.000 claims abstract description 3
- 238000011160 research Methods 0.000 claims description 37
- 239000010729 system oil Substances 0.000 claims description 34
- 238000005286 illumination Methods 0.000 claims description 15
- 238000013213 extrapolation Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 13
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Lubrication Details And Ventilation Of Internal Combustion Engines (AREA)
Abstract
The invention discloses a method and a system for predicting the oil temperature of a phase modulation engine oil system based on similar moment dynamic selection. The invention realizes the dynamic adjustment of the similar moments based on the comprehensive relevance limit value and the minimum quantity of the similar moments, ensures the effectiveness of the selection of the similar moments, improves the prediction precision of the oil temperature of the phase modulation machine oil system, provides a theoretical basis for the evaluation of the internal thermal state of the phase modulation machine, can discover potential hidden danger in time, and ensures the safe and reliable operation of the phase modulation machine.
Description
Technical Field
The invention relates to a method and a system for predicting oil temperature of a motor oil system of a phase modulator based on dynamic selection of similar moments, and belongs to the technical field of phase modulators.
Background
In recent years, along with the high-speed development of social economy and the steady improvement of the living standard of people, a strong intelligent power grid which takes an extra-high voltage power grid as a backbone grid frame and coordinates the development of all levels of power grids is continuously expanded, wherein large-scale construction of a direct current converter station is realized for long-distance power transmission and energy interconnection in the east and west is realized. However, currently, the converter valves of the direct current converter stations generally adopt thyristors, and a large amount of reactive power support is needed in operation. In addition, once the converter station fails, the converter valve is locked, and a great amount of active power is lost by the inversion side converter station, so that reactive power support must be provided quickly in a short time to ensure the stable regional voltage, and a camera is turned up to solve the problem.
The camera belongs to high-speed rotating equipment, and is provided with a special oil system for ensuring lubrication and insulation between a stator and a rotor, and the insulation condition and the thermal state inside the camera can be effectively judged through monitoring the oil temperature of the oil system. The existing phase modulation engine oil system lacks an effective prediction means, cannot evaluate the thermal state in advance, cannot discover internal potential faults in time, and is unfavorable for safe and stable operation of a phase modulation engine. Meanwhile, the oil temperature of the phase modulation engine oil system is influenced by various factors such as weather conditions, reactive power and the like, and has certain volatility and randomness, so that the oil temperature prediction accuracy is difficult to guarantee, the quantitative analysis of the oil temperature change trend is not facilitated, and the monitoring effect of the running state of the phase modulation engine is seriously influenced. In order to solve the above problems, it is needed to study a method for predicting the oil temperature of a phase modulation engine oil system.
Disclosure of Invention
The invention aims to: in order to overcome the defects in the prior art, the invention provides a method and a system for dynamically selecting the oil temperature of a phase modulation engine oil system based on similar moments, which solve the problems that the existing phase modulation engine oil system lacks an effective prediction means, cannot evaluate the thermal state in advance, cannot discover internal potential faults in time and is unfavorable for safe and stable operation of a phase modulation engine.
The technical scheme is as follows: in order to solve the technical problems, the invention adopts the following technical scheme: a phase modulation engine oil system oil temperature prediction method based on dynamic selection of similar moments comprises the following steps:
Obtaining a phase modulator oil system oil temperature predicted value based on the pre-obtained optimal parameters of the minimum number of the comprehensive relevance limit values and the similar moments of the day to be predicted and the research sample;
the optimal parameters are obtained in advance based on an evaluation function.
Further, the evaluation function is:
Wherein M 0j represents the actual value of the oil temperature of the phase modulation engine oil system at the j-th moment of the day to be predicted; c M is the comprehensive correlation limit value, N M is the minimum number of similar moments, and M0 j is the predicted value of the oil temperature of the phase modulation oil system.
Further, the optimal parameter calculation process is as follows:
Calculating the number N jT of similar moments between the j-th moment of the day to be predicted and the research sample;
Calculating a phase modulation engine oil system oil temperature predicted value M0 j corresponding to the j-th moment of the day to be predicted according to the number N jT of similar moments;
In response to the evaluation function ER (C M,NM) taking the minimum value, the integrated correlation limit value C M and the minimum number of similar moments N M are the optimal parameters.
Further, the method for calculating the number N jT of similar moments between the j-th moment of the day to be predicted and the study sample is as follows:
Calculating the number N jC of times when the j-th time of the day to be predicted meets the comprehensive correlation degree C ij≥CM, and responding to N jC≥NM,NjT＝NjC; in response to N jC<NM,NjT＝NM.
Further, the method for calculating the predicted value M0 j of the oil temperature of the phase modulation machine oil system corresponding to the j-th moment of the day to be predicted according to the number N jT of similar moments is as follows:
calculating a phase modulation oil system oil temperature predicted value M1 j based on a comprehensive relevance weighting method:
calculating a phase modulator oil system oil temperature predicted value M2 j based on extrapolation:
The average value of the comprehensive correlation weighting method and the extrapolation method is used as a phase modulation engine oil system oil temperature predicted value M0 j:
further, the method for predicting the oil temperature of the phase modulation engine oil system based on the obtained optimal parameter prediction of the minimum number of the comprehensive relevance limit value and the similar moment of the day to be predicted and the research sample comprises the following steps:
And substituting the optimal parameters C M and N M into a formula of an average value of the comprehensive correlation weighting method and the extrapolation method as a phase modulation engine oil system oil temperature predicted value M0 j, so as to realize the prediction of the oil temperature at each moment of the phase modulation engine oil system to be predicted.
Further, the method for calculating the comprehensive relevance C ij comprises the following steps:
Calculating the comprehensive influence coefficient of each main influence factor and the oil temperature of the phase modulation engine oil system; wherein the main influencing factors include: ambient temperature, air humidity, rainfall conditions, and illumination intensity and time factors;
and calculating the comprehensive correlation C ij between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the research sample according to the comprehensive influence coefficient.
Further, the comprehensive influence coefficients of the main influence factors and the oil temperature of the phase modulation oil system are as follows:
Wherein RR x represents the integrated influence coefficient of the x-th main influence factor and the oil temperature of the phase modulation engine oil system, and R1 x represents the direct influence coefficient of the x-th main influence factor on the oil temperature of the phase modulation engine oil system:
Wherein x represents a main influence factor, x=w, S, J, G, T, M ij represents a phase modulation engine oil system oil temperature at the i-th day and J-th time in a research sample, and x ij represents a value of the x-th main influence factor at the i-th day and J-th time; b x represents the partial regression coefficient corresponding to the x-th main influencing factor:
y ij represents the value at the jth moment on the ith day of the y-th main influencing factor, and y+.x; e is the number of samples to be studied,
R2 xy represents the indirect influence coefficient of the xth main influence factor on the oil temperature of the phase modulation oil system through the yth main influence factor,
Wherein y represents a main influence factor, y=w, S, J, G, T and y+.x, and R1 y represents a direct influence coefficient of the y-th main influence factor on the temperature of the camera oil system.
Further, the method for calculating the comprehensive correlation C ij between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the study sample comprises the following steps:
RR T represents the comprehensive influence coefficient of the temperature factor and the oil temperature of the phase modulation oil system;
b i represents the time correlation as:
a ij is the weather correlation between each time in the research sample and each time of the day to be predicted:
wherein TC 0j represents the approaching degree of the weather factor and the optimal weather factor at the j-th moment of the day to be predicted;
TC ij is the proximity of the weather factor to the optimal weather factor at each time:
TZ ij is expressed as the forward distance:
TF ij is expressed as the reverse distance:
Wherein, MY 1 represents the environmental temperature of the optimal weather factor MY, MY 2 represents the air humidity of the optimal weather factor MY, MY 3 represents the rainfall condition of the optimal weather factor MY, and MY 4 represents the illumination intensity of the optimal weather factor MY;
MC 1 represents the ambient temperature of the worst weather factor MC, MC 2 represents the air humidity of the worst weather factor MC, MC 3 represents the rainfall of the worst weather factor MC, and MC 4 represents the illumination intensity of the worst weather factor MC;
Optimal weather factor MY and worst weather factor MC:
C 0 represents a constant, and the value range is 0.01-0.49.
A phase modulation oil system oil temperature prediction system based on dynamic selection of similar moments, comprising:
The optimal parameter acquisition module is used for calculating the optimal parameters of the minimum number of comprehensive relevance limit values and similar moments of the day to be predicted and the research sample;
and the predicted value calculation module is used for obtaining the predicted value of the oil temperature of the phase modulation oil system based on the obtained optimal parameters of the minimum number of the comprehensive relevance limit values of the day to be predicted and the research sample and the similar time.
The beneficial effects are that: according to the method, the number of similar moments is dynamically adjusted, so that the prediction accuracy of the oil temperature of the phase modulation engine oil system is effectively improved, and an important support is provided for safe operation of the phase modulation engine. Has the following advantages: 1. by calculating the comprehensive influence coefficient of each influence factor and the oil temperature of the phase modulation engine oil system, the interaction among the influence factors is fully considered. 2. And the dynamic adjustment of the similar time is realized based on the comprehensive relevance limit value and the minimum number of the similar time, so that the effectiveness of the selection of the similar time is ensured. 3. And the optimal parameters are obtained by calculation through the evaluation function, so that the prediction accuracy of the oil temperature of the phase modulation engine oil system is improved.
Drawings
Fig. 1 is a flowchart of a method for predicting oil temperature of a phase modulation oil system according to an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
Example 1:
As shown in fig. 1, a phase modulation engine oil system oil temperature prediction method based on dynamic selection of similar moments includes the following steps:
step 1: selecting historical oil temperature data of a phase modulation engine oil system as a research sample;
The data of the first E days are taken as study samples, and the rest data are taken as verification prediction samples.
Step 2: determining main influencing factors of the oil temperature of the phase modulator oil system;
When the oil temperature of the phase modulation engine oil system is researched, according to the correlation between each influence factor and the oil temperature of the phase modulation engine oil system, weather factors and time factors are selected as main influence factors, wherein the weather factors mainly comprise four types of environment temperature, air humidity, rainfall condition and illumination intensity, M ij is set to represent the oil temperature of the phase modulation engine oil system at the ith and jth time in a research sample, W ij is set to represent the environment temperature at the ith and jth time in the research sample, S ij is set to represent the air humidity at the ith and jth time in the research sample, J ij is set to represent the rainfall condition at the ith and jth time in the research sample, G ij is set to represent the illumination intensity at the ith and jth time in the research sample, and T ij is set to represent the time factor at the ith and jth time in the research sample.
Step 3: and calculating the comprehensive influence coefficient of each main factor and the oil temperature of the phase modulation engine oil system.
Step 3.1: and obtaining and quantifying each influence factor.
The quantitative data can be directly obtained by considering 4 influencing factors of the ambient temperature, the air humidity, the rainfall condition and the illumination intensity, and the quantitative processing time factors are mainly based on the oil temperature size fuzzy ordering method.
Firstly, setting the number of research samples as E, sorting the oil temperature of a phase modulation engine oil system at the j-th moment in the research samples according to the size, when the oil temperature is at the maximum value, assigning a value of E to a time factor intermediate variable H ij, when the oil temperature is at the second maximum value, assigning a value of E-1 to H ij, decreasing in sequence, and when the oil temperature is at the minimum value, assigning a value of 1 to H ij.
Then, the duty ratio Z j of the oil temperature of the phase modulation oil system at the j time in the research sample at 24 times of the whole day is calculated:
Finally, T ij is available from H ij and Z j:
Tij＝HijZj (20)
step 3.2: normalization processes each influencing factor.
Normalization processing is carried out on various influencing factors, and the method is concretely as follows:
Wherein C 0 represents a constant, the value range is 0.01-0.49, x ij represents the value at the j-th time on the i-th main influencing factor of the x-th, and f (x ij) represents the x ij normalization function.
Step 3.3: and calculating the comprehensive influence coefficient of each main factor and the oil temperature of the phase modulation engine oil system.
Firstly, calculating direct influence coefficients of main influence factors and oil temperature of a phase modulation engine oil system:
Wherein R1 x represents a direct influence coefficient of the x-th main influence factor on the temperature of the camera oil system, x represents a main influence factor (x=w, S, J, G, T), and b x represents a partial regression coefficient corresponding to the x-th main influence factor:
y ij denotes the value at the jth moment on the ith day of the y-th main influencing factor, and y+.x.
Then, calculating indirect influence coefficients of each main influence factor and the oil temperature of the phase modulation oil system:
Wherein y represents a main influence factor (y=w, S, J, G, T and y+.x), R2 xy represents an indirect influence coefficient of the xth main influence factor on the oil temperature of the camera oil system by the yth main influence factor, and R1 y represents a direct influence coefficient of the yth main influence factor on the oil temperature of the camera oil system.
Finally, calculating the comprehensive influence coefficient of each main influence factor and the oil temperature of the phase modulation engine oil system:
Where RR x represents the combined influence coefficient of the x-th main influence factor and the oil temperature of the phase modulator oil system.
Step 4: and calculating the comprehensive correlation C ij between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the study sample.
Step 4.1: and calculating weather correlation between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the study sample.
According to the correlation of the oil temperature of the phase modulator oil system and 4 types of meteorological factors including the ambient temperature, the air humidity, the rainfall condition and the illumination intensity, firstly defining the optimal meteorological factors MY and the worst meteorological factors MC:
c 0 represents a constant, the value range is 0.01-0.49,
Considering that the comprehensive influence coefficients of the 4 kinds of weather factors are different, the ratio of each factor in the distance from the optimal weather factor is different, the forward direction distance TZ ij can be expressed as:
similarly, the reverse distance TF ij:
Wherein, MY 1 represents the environmental temperature of the optimal weather factor MY, MY 2 represents the air humidity of the optimal weather factor MY, MY 3 represents the rainfall condition of the optimal weather factor MY, and MY 4 represents the illumination intensity of the optimal weather factor MY;
MC 1 represents the ambient temperature of the worst weather factor MC, MC 2 represents the air humidity of the worst weather factor MC, MC 3 represents the rainfall of the worst weather factor MC, and MC 4 represents the illumination intensity of the worst weather factor MC.
From TZ ij and TF ij, the closeness TC ij of the weather factor and the optimal weather factor at each moment can be obtained:
according to TC ij, weather correlation A ij between each time in the research sample and each time of the day to be predicted can be obtained:
in the formula, TC 0j represents the approaching degree of the weather factor at the j-th moment of the day to be predicted and the optimal weather factor, and the formula is as follows:
Step 4.2: and calculating the time correlation degree between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the study sample.
According to the principle of 'far correlation is small and near correlation is large' of time, provided that the time factor correlation linearly decreases along with the time distance, the correlation is the maximum value (1+C 0)/(1+2C0) on the 1 st day before the day to be predicted, and the correlation is the minimum value C 0/(1+2C0 on the E th day before the day to be predicted), the time correlation B i can be expressed as follows:
step 4.3: and calculating the comprehensive correlation degree between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the study sample.
And according to the weather and time correlation, obtaining a comprehensive correlation C ij based on the comprehensive influence coefficient weighting:
RR T represents the integrated influence coefficient of the temperature factor and the oil temperature of the phase modulator oil system.
Step 5: the integrated correlation limit value C M and the minimum number of similar times N M are set.
Setting a comprehensive relevance limit value C M epsilon [0.50,0.95], wherein the change step length is 0.01, and the initial value is 0.50; the minimum number N M of similar moments epsilon [1, E ], the change step length is 1, and the initial value is 1.
Step 6: and calculating the number N jT of similar moments corresponding to the j-th moment of the day to be predicted.
Calculating the number N jC of times when the j-th time of the day to be predicted meets C ij≥CM, and when N jC≥NM is met, N jT＝NjC; when N jC<NM, N jT＝NM, namely:
Step 7: and calculating a phase modulation engine oil system oil temperature predicted value M0 j corresponding to the j-th moment of the day to be predicted.
And selecting N jT moments with the greatest comprehensive correlation degree with the j-th moment of the day to be predicted as similar moments, and dynamically adjusting the quantity of the similar moments of each moment through the change of the N jT value.
Firstly, calculating a phase modulation oil system oil temperature predicted value M1 j based on a comprehensive correlation weighting method:
Then, a phase modulator oil system oil temperature predicted value M2 j is calculated based on extrapolation:
finally, the average value of the comprehensive correlation weighting method and the extrapolation method is used as a phase modulation engine oil system oil temperature predicted value M0 j:
step 8: and establishing an evaluation function of the prediction method.
Based on the error square sum of the oil temperature predicted value and the actual value of the phase modulation oil system in the research sample, an evaluation function ER (C M,NM) of a prediction method is established:
Wherein M 0j represents the actual value of the oil temperature of the phase modulation engine oil system at the j-th moment of the day to be predicted.
Step 9: and calculating optimal parameters of the prediction method.
Similar time instants were selected from day E before study sample, and ER was solved (C M,NM). When ER (C M,NM) obtains the minimum value, the corresponding C M and N M are the optimal parameters of the method; when ER (C M,NM) does not take the minimum value, go back to step 5 and re-execute after changing the values of C M and N M.
Step 10: and calculating the oil temperature of the day modulator oil system to be predicted at each moment.
And substituting the optimal parameters C M and N M into the expression (35) to realize the prediction of the oil temperature at each moment of the day modulator oil system to be predicted.
Example 2:
a phase modulation oil system oil temperature prediction system based on dynamic selection of similar moments, comprising:
The optimal parameter acquisition module is used for calculating the optimal parameters of the minimum number of comprehensive relevance limit values and similar moments of the day to be predicted and the research sample;
The predicted value calculation module is used for obtaining the predicted value of the oil temperature of the phase modulation oil system based on the obtained optimal parameters of the minimum number of comprehensive relevance limit values of the day to be predicted and the research sample and the similar moment in advance;
the optimal parameters are obtained in advance based on an evaluation function.
According to the invention, the prediction accuracy of the oil temperature of the phase modulation engine oil system is effectively improved by dynamically adjusting the quantity of similar moments, and an important support is provided for safe operation of the phase modulation engine. Has the following advantages: 1. by calculating the comprehensive influence coefficient of each influence factor and the oil temperature of the phase modulation engine oil system, the interaction among the influence factors is fully considered. 2. And the dynamic adjustment of the similar time is realized based on the comprehensive relevance limit value and the minimum number of the similar time, so that the effectiveness of the selection of the similar time is ensured. 3. And the optimal parameters are obtained by calculation through the evaluation function, so that the prediction accuracy of the oil temperature of the phase modulation engine oil system is improved.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (5)
1. A phase modulation engine oil system oil temperature prediction method based on dynamic selection of similar moments is characterized by comprising the following steps:
Obtaining a phase modulator oil system oil temperature predicted value based on the pre-obtained optimal parameters of the minimum number of the comprehensive relevance limit values and the similar moments of the day to be predicted and the research sample;
the optimal parameters are obtained in advance based on an evaluation function;
The evaluation function is:
Wherein M 0j represents the actual value of the oil temperature of the phase modulation engine oil system at the j-th moment of the day to be predicted; c M is a comprehensive correlation limit value, N M is the minimum number of similar moments, and M0 j is a phase modulation oil system oil temperature predicted value;
the optimal parameter calculation process comprises the following steps:
Calculating the number N jT of similar moments between the j-th moment of the day to be predicted and the research sample;
Calculating a phase modulation engine oil system oil temperature predicted value M0 j corresponding to the j-th moment of the day to be predicted according to the number N jT of similar moments;
In response to the evaluation function ER (C M,NM), obtaining a minimum value, wherein the comprehensive relevance limit value C M and the minimum number N M of similar moments are optimal parameters;
the method for calculating the number N jT of similar moments between the j-th moment of the day to be predicted and the study sample is as follows:
Calculating the number N jC of times when the j-th time of the day to be predicted meets the comprehensive correlation degree C ij≥CM, and responding to N jC≥NM,NjT＝NjC; responsive to N jC<NM,NjT＝NM;
The method for calculating the comprehensive relevance C ij comprises the following steps:
Calculating the comprehensive influence coefficient of each main influence factor and the oil temperature of the phase modulation engine oil system; wherein the main influencing factors include: ambient temperature, air humidity, rainfall conditions, and illumination intensity and time factors;
Calculating the comprehensive correlation C ij between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the research sample according to the comprehensive influence coefficient;
the method for calculating the phase modulation engine oil system oil temperature predicted value M0 j corresponding to the j-th moment of the day to be predicted according to the number N jT of similar moments comprises the following steps:
calculating a phase modulation oil system oil temperature predicted value M1 j based on a comprehensive relevance weighting method:
wherein M ij represents the oil temperature of the phase modulation engine oil system at the j-th moment on the i-th day in the research sample;
calculating a phase modulator oil system oil temperature predicted value M2 j based on extrapolation:
Wherein M i(j-1) represents the oil temperature of the phase modulation engine oil system at the j-1 th moment on the i-th day in the research sample
The average value of the comprehensive correlation weighting method and the extrapolation method is used as a phase modulation engine oil system oil temperature predicted value M0 j:
2. The phase modulation oil system oil temperature prediction method based on dynamic selection of similar moments according to claim 1, wherein: the method for predicting the oil temperature of the phase modulation engine oil system based on the optimal parameter prediction of the minimum number of the comprehensive relevance limit value and the similar moment of the pre-obtained day to be predicted and the research sample comprises the following steps:
And substituting the optimal parameters C M and N M into a formula of an average value of the comprehensive correlation weighting method and the extrapolation method as a phase modulation engine oil system oil temperature predicted value M0 j, so as to realize the prediction of the oil temperature at each moment of the phase modulation engine oil system to be predicted.
3. The phase modulation oil system oil temperature prediction method based on dynamic selection of similar moments according to claim 1, wherein: the comprehensive influence coefficients of the main influence factors and the oil temperature of the phase modulation engine oil system are as follows:
Wherein RR x represents the integrated influence coefficient of the x-th main influence factor and the oil temperature of the phase modulation engine oil system, and R1 x represents the direct influence coefficient of the x-th main influence factor on the oil temperature of the phase modulation engine oil system:
Wherein x represents a main influencing factor, x=w, S, J, G, T, W represents an ambient temperature, S represents an air humidity, J represents a rainfall condition, G represents an illumination intensity, and T represents a time factor; m ij represents the oil temperature of the phase modulation engine oil system at the ith and jth time in the research sample, and x ij represents the value at the ith and jth time of the x main influencing factors; b x represents the partial regression coefficient corresponding to the x-th main influencing factor:
y ij represents the value at the jth moment on the ith day of the y-th main influencing factor, and y+.x; e is the number of samples to be studied,
R2 xy represents the indirect influence coefficient of the xth main influence factor on the oil temperature of the phase modulation oil system through the yth main influence factor,
Wherein y represents a main influence factor, y=w, S, J, G, T and y+.x, and R1 y represents a direct influence coefficient of the y-th main influence factor on the temperature of the camera oil system.
4. A method for predicting oil temperature of a phase modulation oil system based on dynamic selection of similar moments according to claim 3, wherein: the method for calculating the comprehensive correlation C ij between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the research sample comprises the following steps:
RR T represents the comprehensive influence coefficient of the temperature factor and the oil temperature of the phase modulation oil system;
b i represents the time correlation as:
a ij is the weather correlation between each time in the research sample and each time of the day to be predicted:
wherein TC 0j represents the approaching degree of the weather factor and the optimal weather factor at the j-th moment of the day to be predicted;
TC ij is the proximity of the weather factor to the optimal weather factor at each time:
TZ ij is expressed as the forward distance:
Wherein RR W represents the comprehensive influence coefficient of the ambient temperature and the oil temperature of the phase modulation oil system, RR S represents the comprehensive influence coefficient of the air humidity and the oil temperature of the phase modulation oil system, RR J represents the comprehensive influence coefficient of the rainfall condition and the oil temperature of the phase modulation oil system, and RR G represents the comprehensive influence coefficient of the illumination intensity and the oil temperature of the phase modulation oil system;
TF ij is expressed as the reverse distance:
Wherein, MY 1 represents the environmental temperature of the optimal weather factor MY, MY 2 represents the air humidity of the optimal weather factor MY, MY 3 represents the rainfall condition of the optimal weather factor MY, and MY 4 represents the illumination intensity of the optimal weather factor MY;
MC 1 represents the ambient temperature of the worst weather factor MC, MC 2 represents the air humidity of the worst weather factor MC, MC 3 represents the rainfall of the worst weather factor MC, and MC 4 represents the illumination intensity of the worst weather factor MC;
Optimal weather factor MY and worst weather factor MC:
C 0 represents a constant, and the value range is 0.01-0.49.
5. A phase modulation machine oil system oil temperature prediction system based on similar moment dynamic selection is characterized in that: comprising the following steps:
The optimal parameter acquisition module is used for calculating the optimal parameters of the minimum number of comprehensive relevance limit values and similar moments of the day to be predicted and the research sample based on the evaluation function;
The predicted value calculation module is used for obtaining the predicted value of the oil temperature of the phase modulation oil system based on the obtained optimal parameters of the minimum number of comprehensive relevance limit values of the day to be predicted and the research sample and the similar moment in advance;
The evaluation function is:
Wherein M 0j represents the actual value of the oil temperature of the phase modulation engine oil system at the j-th moment of the day to be predicted; c M is a comprehensive correlation limit value, N M is the minimum number of similar moments, and M0 j is a phase modulation oil system oil temperature predicted value;
the optimal parameter calculation process comprises the following steps:
Calculating the number N jT of similar moments between the j-th moment of the day to be predicted and the research sample;
Calculating a phase modulation engine oil system oil temperature predicted value M0 j corresponding to the j-th moment of the day to be predicted according to the number N jT of similar moments;
In response to the evaluation function ER (C M,NM), obtaining a minimum value, wherein the comprehensive relevance limit value C M and the minimum number N M of similar moments are optimal parameters;
the method for calculating the number N jT of similar moments between the j-th moment of the day to be predicted and the study sample is as follows:
Calculating the number N jC of times when the j-th time of the day to be predicted meets the comprehensive correlation degree C ij≥CM, and responding to N jC≥NM,NjT＝NjC; responsive to N jC<NM,NjT＝NM;
The method for calculating the comprehensive relevance C ij comprises the following steps:
Calculating the comprehensive influence coefficient of each main influence factor and the oil temperature of the phase modulation engine oil system; wherein the main influencing factors include: ambient temperature, air humidity, rainfall conditions, and illumination intensity and time factors;
Calculating the comprehensive correlation C ij between the j-th moment of the day to be predicted and the j-th moment of the i-th day in the research sample according to the comprehensive influence coefficient;
the method for calculating the phase modulation engine oil system oil temperature predicted value M0 j corresponding to the j-th moment of the day to be predicted according to the number N jT of similar moments comprises the following steps:
calculating a phase modulation oil system oil temperature predicted value M1 j based on a comprehensive relevance weighting method:
wherein M ij represents the oil temperature of the phase modulation engine oil system at the j-th moment on the i-th day in the research sample;
calculating a phase modulator oil system oil temperature predicted value M2 j based on extrapolation:
Wherein M i(j-1) represents the average value of the phase modulation oil system oil temperature at the ith day and the j-1 th moment in the research sample by using the comprehensive correlation weighting method and extrapolation method as the phase modulation oil system oil temperature predicted value M0 j:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010674556.4A CN112036004B (en) | 2020-07-14 | 2020-07-14 | Method and system for predicting oil temperature of phase modulation engine oil system based on dynamic selection of similar moments |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010674556.4A CN112036004B (en) | 2020-07-14 | 2020-07-14 | Method and system for predicting oil temperature of phase modulation engine oil system based on dynamic selection of similar moments |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112036004A CN112036004A (en) | 2020-12-04 |
| CN112036004B true CN112036004B (en) | 2024-04-19 |
Family
ID=73579836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010674556.4A Active CN112036004B (en) | 2020-07-14 | 2020-07-14 | Method and system for predicting oil temperature of phase modulation engine oil system based on dynamic selection of similar moments |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112036004B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529306B (en) * | 2020-12-16 | 2023-12-01 | 国网江苏省电力有限公司检修分公司 | Camera latent defect diagnosis method and device based on oil temperature estimation of oil system |
| CN118010554B (en) * | 2024-04-10 | 2024-07-02 | 东莞信易电热机械有限公司 | High-temperature oil type mold temperature engine oil temperature assessment method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2636049A1 (en) * | 2010-11-03 | 2013-09-11 | ABB Technology AG | Predicting the remaining life of a transformer |
| CN104299057A (en) * | 2014-10-17 | 2015-01-21 | 国家电网公司 | Method for predicting top layer oil temperature of oil-immersed transformer based on multiple factors |
| CN106055888A (en) * | 2016-05-27 | 2016-10-26 | 国网上海市电力公司 | Predication method and device for top-oil temperature of transformer based on error predicting amendment |
| CN106408119A (en) * | 2016-09-09 | 2017-02-15 | 国网安徽省电力公司电力科学研究院 | Large power grid load prediction method based on comprehensive evaluation of analog-meteorological subareas |
| CN107355663A (en) * | 2017-06-26 | 2017-11-17 | 江苏江海润液设备有限公司 | A kind of control method of phase modulation lubricating oil system |
| CN110428151A (en) * | 2019-07-18 | 2019-11-08 | 国网山东省电力公司电力科学研究院 | A kind of method for evaluating state of synchronous capacitor oil system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005302794A (en) * | 2004-04-07 | 2005-10-27 | Hitachi Industrial Equipment Systems Co Ltd | Transformer monitoring system |
-
2020
- 2020-07-14 CN CN202010674556.4A patent/CN112036004B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2636049A1 (en) * | 2010-11-03 | 2013-09-11 | ABB Technology AG | Predicting the remaining life of a transformer |
| CN104299057A (en) * | 2014-10-17 | 2015-01-21 | 国家电网公司 | Method for predicting top layer oil temperature of oil-immersed transformer based on multiple factors |
| CN106055888A (en) * | 2016-05-27 | 2016-10-26 | 国网上海市电力公司 | Predication method and device for top-oil temperature of transformer based on error predicting amendment |
| CN106408119A (en) * | 2016-09-09 | 2017-02-15 | 国网安徽省电力公司电力科学研究院 | Large power grid load prediction method based on comprehensive evaluation of analog-meteorological subareas |
| CN107355663A (en) * | 2017-06-26 | 2017-11-17 | 江苏江海润液设备有限公司 | A kind of control method of phase modulation lubricating oil system |
| CN110428151A (en) * | 2019-07-18 | 2019-11-08 | 国网山东省电力公司电力科学研究院 | A kind of method for evaluating state of synchronous capacitor oil system |
Non-Patent Citations (4)
| Title |
|---|
| Discussion of "Prediction of top-oil temperature for transformers using neural networks" and closure;S.A. Ryder etal.;IEEE Transcations on Power Delivery;20011031;第16卷(第04期);第825-826页 * |
| 变压器热点温度及顶层油温预测模型;史方正 等;内燃机与配件;20180330(第06期);第115-117页 * |
| 基于核极限学习机和Bootstrap方法的变压器顶层油温区间预测;李可军 等;中国电机工程学报;20171005;第37卷(第19期);第5821-5828+5860页 * |
| 基于通径分析和相似时刻的特高压变压器顶层油温预测;谭风雷 等;电力自动化设备;20211018;第41卷(第11期);第217-224页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112036004A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111237989B (en) | Building ventilation air conditioner control method and device based on load prediction | |
| CN112036004B (en) | Method and system for predicting oil temperature of phase modulation engine oil system based on dynamic selection of similar moments | |
| CN113315171A (en) | New energy consumption capacity evaluation method and device, computer equipment and storage medium | |
| CN112418495A (en) | Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network | |
| CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
| Chang et al. | A hybrid system for daylight responsive lighting control | |
| CN114238856A (en) | Method, device and equipment for solving future prediction error of wind and light resources and storage medium | |
| CN115313377B (en) | Power load prediction method and system | |
| CN110247399A (en) | A kind of power distribution network photovoltaic maximum consumption method and system based on Monte Carlo simulation | |
| CN114358382B (en) | Electric power system equivalent inertia probability prediction method, device, product and storage medium | |
| CN114039366B (en) | Power grid secondary frequency modulation control method and device based on peacock optimization algorithm | |
| CN111931972B (en) | Wind power plant wind energy resource assessment and prediction method and system based on SWI-RS analysis method | |
| CN108256668A (en) | Photovoltaic power generation output forecasting method based on harmony search-Elman algorithms | |
| CN112529306B (en) | Camera latent defect diagnosis method and device based on oil temperature estimation of oil system | |
| CN117578467B (en) | Electric quantity weight-based micro-grid cluster operation control method and device | |
| CN118350528A (en) | Energy optimization method, device and equipment based on large model | |
| Pan | Predicting of Power Quality Steady State Index Based on Chaotic Theory Using Least Squares Support Vector Machine | |
| CN117118063A (en) | New energy monitoring method and system based on cloud edge fusion | |
| CN117759997A (en) | Water supply temperature control method, device, equipment and storage medium | |
| CN112598221A (en) | Scheduling method and system for wind power cloud cache | |
| Abdullin et al. | Model predictive control of building heating process using exponential filtration in harmonic basis | |
| CN117688331A (en) | Method, device, system and storage medium for determining integrated temperature factor | |
| Tian et al. | Power prediction and operation scheduling strategy of pumped storage power station based on machine learning | |
| CN111625345A (en) | Scheduling method and system of distributed photovoltaic cloud cache | |
| Zhang et al. | Chilled Station Optimization Operation Based on TRNSYS Simulation of an Existing Public Building |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |