CN111930790A - Valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis - Google Patents
Valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis Download PDFInfo
- Publication number
- CN111930790A CN111930790A CN202010205445.9A CN202010205445A CN111930790A CN 111930790 A CN111930790 A CN 111930790A CN 202010205445 A CN202010205445 A CN 202010205445A CN 111930790 A CN111930790 A CN 111930790A
- Authority
- CN
- China
- Prior art keywords
- valve
- time sequence
- data
- cooling equipment
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012300 Sequence Analysis Methods 0.000 title claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 238000012731 temporal analysis Methods 0.000 claims description 3
- 238000000700 time series analysis Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 15
- 238000002360 preparation method Methods 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000013024 troubleshooting Methods 0.000 abstract description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 22
- 238000012706 support-vector machine Methods 0.000 description 20
- 239000000498 cooling water Substances 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Fuzzy Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Water Supply & Treatment (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis, which comprises the following steps: (1) preparing data, and constructing a data set; (2) analyzing data trend; (3) determining a time sequence analysis method, and establishing a linear prediction model and a non-linear prediction model; (4) and (4) performing predictive analysis on the inlet valve temperature of the valve cooling equipment. According to the invention, by analyzing and establishing the model on the monitoring data of the running state of the existing valve cooling equipment by using the time sequence, the hidden information and trend in the data are mined, the maintenance cost is reduced, and the troubleshooting efficiency is improved; the sensing capability of workers on the valve cooling equipment is improved, corresponding preparation is made for the change trend of the equipment appearing in the future, and the guiding significance is provided for the normal operation and the reliable power supply of a power grid; a prediction method of the inlet valve temperature of the valve cooling equipment is provided for analyzing and mastering equipment state information.
Description
Technical Field
The invention relates to a valve inlet temperature prediction method for valve cooling equipment, in particular to a valve inlet temperature prediction method for valve cooling equipment based on time sequence analysis.
Background
In recent years, with the increase of domestic economy and the increasing promotion of national living standard, the rapid increase of the electricity demand of China and the urgent need of green clean energy, the super and extra-high voltage power transmission and transformation projects of China have already entered the mature stage of technology. On the premise of mature technology, how to realize lean and refinement becomes higher and higher in requirements on safety, stability and intellectualization of ultra-high and extra-high voltage power transmission and transformation projects, and becomes a serious problem to be faced.
At present, the domestic electricity demand is continuously increased along with the development of society. The direct current transmission technology is developing towards the technical direction of high voltage and large capacity, and due to the fact that the territory is vast, the direct current transmission technology has practical requirements on the aspects of long-distance transmission, cross-region networking, flexible scheduling and the like. The stable operation of key equipment such as a converter valve in a power grid is guaranteed to be very important, the converter valve can continuously generate heat in the operation process, and if the heat is continuously accumulated, the normal operation of the converter valve is influenced due to the continuous rise of the temperature. The influence of the faults of key equipment such as a converter valve in a power grid on a power system is larger and larger. Currently, there are some monitoring measures for the operation of valve cooling devices, but most of them use the experience already. This approach lacks sufficient mining and analysis of the monitored data to discover information and trends hidden in the data.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a valve cooling equipment inlet valve temperature prediction method based on time sequence analysis, which realizes the analysis and the grasp of valve cooling and the state of a converter transformer.
The technical scheme is as follows: the invention discloses a valve inlet temperature prediction method of valve cooling equipment, which comprises the following steps: (1) preparing data, and constructing a data set; (2) analyzing data trend; (3) determining a time sequence analysis method, and establishing a linear prediction model and a non-linear prediction model; (4) and (4) performing predictive analysis on the inlet valve temperature of the valve cooling equipment.
And (1) constructing a clean data set.
Analyzing the data regularity and trend of the valve cooling equipment under normal working in the step (2); the data is monitoring data of the inlet valve temperature of the valve cooling equipment.
The time sequence in the step (3) is a sequence formed by arranging numerical values of the same statistical index according to the time sequence; the time series are divided into linear time series and non-linear time series.
Step (3) establishing a linear prediction model according to the linear time sequence to obtain a linear model prediction result; and establishing a nonlinear prediction model according to the nonlinear time sequence to obtain a nonlinear model prediction result.
And (4) predicting the change trend of the inlet valve temperature of the valve cooling equipment by adopting a method of combining a linear prediction model and a nonlinear prediction model according to the model prediction result obtained in the step (3).
Has the advantages that: compared with the prior art, the invention has the following remarkable effects: 1. by analyzing and establishing a model for the monitoring data of the running state of the existing valve cooling equipment by using a time sequence, the hidden information and trend in the data are mined, the maintenance cost is reduced, and the troubleshooting efficiency is improved; 2. the detection data of the valve cooling equipment in the power grid is predicted, so that the sensing capability of workers on the equipment is improved, corresponding preparation can be made for the valve cooling and the change trend of the converter transformer equipment appearing in the future, and the method has guiding significance for normal operation and reliable power supply of the power grid; 3. the method for predicting the valve inlet temperature of the valve cooling equipment is provided for analyzing and mastering the valve cooling and the state information of the converter transformer equipment.
Drawings
FIG. 1 is a general flow chart of a method for predicting inlet valve temperature of a valve cooling device according to the present invention;
fig. 2 (a) shows the inlet valve temperature of the valve cooling device of the present invention at random for seven days in the operating state,
(b) is a valve outlet temperature chart of the valve cooling equipment of the invention in a working state for seven days at random,
(c) is a pressure chart of the inlet valve of the valve cooling equipment in the working state for seven days at random
(d) The invention is a cooling water conductivity change diagram of the valve cooling equipment in a working state for seven days randomly;
in fig. 3, (a) is a random one-month intake valve temperature in the operating state of the valve cooling apparatus of the present invention,
(b) is a random one-month outlet valve temperature chart of the valve cooling equipment under the working state of the invention,
(c) for a random one month inlet valve pressure in the working state of the valve cooling device of the present invention,
(d) the change chart of the conductivity of the cooling water is a random one-month cooling water conductivity change chart under the working state of the valve cooling equipment;
FIG. 4 is a diagram of a monthly valve cooling data change in the working state of the valve cooling device of the present invention,
(a) for the inlet valve temperature of the valve cooling device of the invention randomly for three months under the working condition,
(b) is a random three-month outlet valve temperature chart of the valve cooling equipment in the working state,
(c) for the inlet valve pressure of the valve cooling device of the invention randomly for three months under the working condition,
(d) the change chart of the conductivity of the cooling water is a random three-month cooling water conductivity change chart under the working state of the valve cooling equipment;
FIG. 5 is a graph of the ARIMA model predicted inlet valve temperature prediction results of the present invention;
FIG. 6 is a graph of inlet valve temperature prediction results for SVM model prediction of the present invention;
FIG. 7 is a diagram of the prediction result of the ARIMA-SVM hybrid model of the present invention for predicting inlet valve temperature.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
The valve inlet temperature prediction method of the valve cooling equipment, provided by the invention, is a time sequence analysis method according to monitoring data of the valve inlet temperature of the valve cooling equipment, in particular to the valve inlet temperature data of the valve cooling equipment. Particularly, according to the characteristics of inlet valve temperature, outlet valve temperature, inlet valve pressure and cooling water conductivity, whether the evaluation data meet the characteristics of a stationary time sequence or not is analyzed by means of arithmetic square root, variance, Diji-Fowler test and the like, on the basis, an ARIMA model, an SVM model and an ARIMA-SVM mixed model are respectively constructed to carry out prediction research on the inlet valve temperature of the valve cooling equipment, and the root mean square error is calculated to evaluate the quality of the established model. The detailed steps are as follows:
(1) data preparation
The data of the invention is from data records of inlet valve temperature, outlet valve temperature, inlet valve pressure and cooling water conductivity (namely four monitoring indexes) of ultrahigh-pressure converter station equipment valve cooling equipment from 2017 to 2019 and 8 in the southern power grid in China.
Considering the time-series and trend characteristics of the data to be analyzed, where the initial data is scattered in the database, a series of data preprocessing is required to construct a clean data set.
Data access efficiency is guaranteed. In order to ensure that data can be divided, screened and cleaned efficiently at high speed, all data is exported from a database and stored in a JSON or CSV file format.
And data time sequence guarantee. In view of the large number of valve cooling devices, it is necessary to analyze the monitoring data of each device in order to analyze the operating state of each device over time. Dividing the data according to each device, and arranging according to date and time to ensure the integrity and time sequence of the data corresponding to each device, and finally constructing a data table containing four monitoring indexes. After the above data preprocessing, a clean data set that can be analyzed chronologically is obtained.
After a clean data set is obtained, the data of the four monitoring indexes are sampled according to the week and the month respectively, and the intrinsic regularity and the trend change of the data are analyzed.
(2) Valve cooling equipment data trend analysis
In order to better analyze the trend and the regularity of the inlet valve temperature of the valve cooling equipment changing along with time, the driving data are randomly sampled according to the week and the month respectively, and the regularity and the trend change are analyzed.
Data analysis within one week. The filtered data set was randomly sampled, and seven days of valve cooling equipment data were selected and analyzed, and their changes with time are shown in fig. 2, which contains (a), (b), (c) and (d) graphs, respectively depicting the changes of inlet valve temperature, outlet valve temperature, inlet valve pressure and cooling water conductivity for seven days.
As can be seen from graphs (a), (b), (c) and (d) of FIG. 2, the inlet valve temperature varied between 32 ℃ and 40 ℃ by a difference of 8 ℃; the temperature of the outlet valve is changed between 38 ℃ and 49 ℃, and the temperature is increased to 6 ℃ to 9 ℃; the inlet valve pressure and the cooling water conductivity fluctuate randomly, the fluctuation range of the value is not large, and the inlet valve pressure and the cooling water conductivity both change within a normal value range. The inlet valve temperature, the outlet valve temperature, the inlet valve pressure and the cooling water conductivity all fluctuate around a certain mean value and all change within a normal value range.
To further study the valve cooling trend and the smoothness of the data, the month of valve cooling plant data was analyzed. As can be seen from the graphs (a), (b), (c) and (d) of fig. 3, the inlet and outlet valve temperatures have similar trends, but the overall variation range is somewhat different, the inlet valve temperature ranges from 22 ℃ to 36 ℃, the outlet valve temperature fluctuates from 24 ℃ to 42 ℃, and the inlet and outlet valve temperatures differ by 2 ℃ to 6 ℃. The inlet valve temperature still tends to be kept in a stable range, random fluctuation exists, the fluctuation range of the value is small, and the driving current value is changed within a normal value range. To further determine whether the data is a stationary time series, it can be determined by calculating a mean, a standard deviation, etc.
(3) Valve inlet temperature analysis method of valve cooling equipment and establishment of prediction model
According to the data trend analysis in the step (2), when the valve cooling equipment is in a working state, although the corresponding inlet valve temperature can fluctuate randomly, the fluctuation amplitude is small, and the inlet valve temperature is maintained within a normal value range, so that certain stability is achieved.
And selecting and determining a time series analysis method according to the data analysis result, establishing a prediction model, and performing prediction analysis on the inlet valve temperature of the valve cooling equipment. Because ARMA can only process a stable sequence, and the ARIMA or SVM alone can hardly and completely grasp the change rule of the time sequence, the problem is solved by considering a mixed model combining the ARIMA and the SVM.
In the present invention, the valve cold time series ytCan be decomposed into linear portions LtAnd a non-linear part NtAnd (4) forming.
yt=Lt+Nt (1)
Linear part LtIt can be calculated from the past values in the valve cooling data time series by the ARMA (p, q) model, and the calculation formula is as follows:
Lt=a1yt-1+a2yt-2+…+apyt-p+b1 t-1+b2 t-2+…+bq t-q+p (2)
wherein, { ytIs a stationary time sequence, a great dealtWhite noise sequence, aiAnd bjAre each { ytSequence and a supporttThe parameters of the sequence, p is called the autoregressive order, and q is the moving average order.
When non-stationary time series data is encountered, difference processing is often needed to smooth the non-stationary sequence. The general strategy of the autoregressive moving average model (ARMA) and the integrated moving average autoregressive model (ARIMA) time sequence analysis mainly comprises three steps: firstly, determining appropriate p, d and q values; secondly, evaluating specific parameter values in the model by the most effective method; thirdly, the accuracy of the predicted data and the appropriateness of the fitting model are checked, and finally the model is continuously and appropriately improved to achieve the aim of accurately predicting the data.
AIC and BIC were used to determine p, q values, selecting a simpler model:
and (3) AIC: red pool Information Criterion (Akaike Information Criterion)
AIC=2K-2ln(L) (3)
And (3) BIC: bayesian Information Criterion (Bayesian Information Criterion)
BIC=Kln(n)-2ln(L) (4)
Wherein k is the number of model parameters, n is the number of samples, and L is a likelihood function.
Since the valve cooling equipment data is a time stationary sequence, an ARMA (p, q) model or an ARIMA (p, d, q) model can be directly established, d is set to be 0 in the model, parameters of the model are identified by adopting a step-by-step heuristic method from low order to high order, p is initially selected to be 1, q is 1 or p is 2, q is 2, the heuristic is carried out all the way up, and then the optimal parameters of the ARIMA model are found through an akage information metric (AIC) and a bayesian information metric (BIC). The AIC and the BIC are weighed before the number of parameters and the fitting precision of the model, and the smaller the calculated value is, the better the performance of the model is. The ARIMA model has unique advantages in processing linear data, can fully capture a linear part in a time sequence, and can obtain a residual error while capturing the linear part.
The residual error includes non-linear relationship, and although the ARIMA model cannot capture non-linear information, a Support Vector Machine (SVM) can capture such information. Residual analysis is important because residual is an important factor for improving prediction accuracy. The Support Vector Machine (SVM) can obtain a good effect in the aspect of nonlinear prediction, and is a learning method based on a statistical theory. Due to the rich theoretical basis of a Support Vector Machine (SVM), the solution to the high-altitude is ensuredThe dimension and the non-linearity have incomparable advantages. The nonlinear part can be obtained from a linear model, the nonlinear part NtAs input to the SVM model.
The linear part is the prediction result of the ARIMA prediction model;can be obtained from the ARIMA model at time t,the non-linear part is the residual part obtained by the ARIMA prediction model, andas an input to the SVM model, a formula may be represented
g is a non-linear model, ΔtIs the random error of the non-linear part and n is the length of the input. The final predicted value can be obtained from the above analysisComprises the following steps:
(4) valve inlet temperature prediction analysis of valve cooling equipment
And (4.1) carrying out predictive analysis on the inlet valve temperature of the valve cooling equipment under normal operation. Data of one valve cooling device from 1/2018 to 3/31/2018 are randomly selected for experimental analysis and evaluation, the time interval of valve cooling data sampling is half an hour, and the trend change of the data is shown in fig. 5. It can be seen from fig. 5 that the intake valve temperature is substantially smooth, and although there is random fluctuation, the fluctuation amplitude is mostly small, and the value is always within the normal range. Moreover, the arithmetic mean value is calculated over time, the value of which approaches a constant value; and the variance was calculated over time, with values approaching 0.
In addition, a root-mean-square check was performed using the diky-fowler test and calculated to give a p value much less than 0.01, indicating that time t is significant at a confidence level of over 99% and the data is a time-stationary sequence. And supporting the construction of an ARIMA model, and setting a model parameter d to be 0.
And establishing an ARIMA model based on the time stationary sequence of the inlet valve temperature data, and predicting. The ARIMA model prediction results are shown in FIG. 5.
As can be seen from fig. 5, the prediction result of the ARIMA model is close to the original data, and the root mean square error is calculated to evaluate the quality of the model, and the root mean square error is 0.72.
And (4.2) further constructing the SVM model. The SVM model may detect the non-linear relationship and predict the non-linear relationship in the inlet valve temperature data. The model prediction results are shown in fig. 6.
As can be seen from FIG. 6, the prediction result of the SVM model is close to the variation trend of the original data, but small fluctuation occurs, and the root mean square error is calculated to evaluate the quality of the model, and is 1.33.
And constructing an ARIMA-SVM mixed model. The method comprises the steps of firstly predicting a power grid time sequence by using ARIMA, capturing the linear variation trend of the power grid time sequence, and then improving the prediction accuracy by using the nonlinearity of SVM to the power grid time sequence. Residual data are obtained while ARIMA model prediction is carried out, and the obtained residual part is used as the input of the SVM. The prediction results of the ARIMA-SVM hybrid model are shown in FIG. 7
As can be derived from fig. 7, the predicted effect is closer to the intake valve temperature data. The output of the SVM model further adjusts the predicted value of ARIMA, so that the predicted value is closer to the true value, and the root mean square error is 0.60.
Experimental results show that the ARIMA model and the SVM model can effectively mine hidden information and trends in data, and the variation trend of inlet valve temperature can be well predicted. In order to further improve the accuracy of prediction, nonlinear data is analyzed by combining an SVM model on the basis of linear data prediction of the ARIMA model, and the prediction result of the ARIMA model is further optimized, which shows that the ARIMA-SVM mixed model can achieve an optimized result.
Claims (8)
1. A valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis is characterized by comprising the following steps: (1) preparing data, and constructing a data set; (2) analyzing data trend; (3) determining a time sequence analysis method, and establishing a linear prediction model and a non-linear prediction model; (4) and (4) performing predictive analysis on the inlet valve temperature of the valve cooling equipment.
2. The valve inlet temperature prediction method of valve cooling equipment based on time series analysis according to claim 1, characterized in that step (1) constructs a clean data set.
3. The valve inlet temperature prediction method based on time sequence analysis of valve cooling equipment as claimed in claim 1, wherein in the step (2), the data regularity and trend of the valve cooling equipment in normal operation are analyzed.
4. The valve cooling device inlet valve temperature prediction method based on time sequence analysis as claimed in claim 3, wherein the data in step (2) is monitoring data of valve cooling device inlet valve temperature.
5. The method for predicting the valve inlet temperature of the valve cooling device based on the time sequence analysis as claimed in claim 1, wherein the time sequence in the step (3) is a sequence in which the numerical values of the same statistical index are arranged according to the time sequence.
6. The valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis as claimed in claim 1, wherein the time sequence of step (3) is divided into a linear time sequence and a non-linear time sequence.
7. The valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis as claimed in claim 1 or 6, wherein the step (3) is to build a linear prediction model according to the linear time sequence to obtain a prediction result of the linear model; and establishing a nonlinear prediction model according to the nonlinear time sequence to obtain a nonlinear model prediction result.
8. The valve inlet temperature prediction method based on time series analysis of the valve cooling device as claimed in claim 1, wherein the step (4) is to predict the variation trend of the valve inlet temperature of the valve cooling device by a method of combining a linear prediction model and a non-linear prediction model according to the model prediction result obtained in the step (3).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010205445.9A CN111930790B (en) | 2020-03-20 | 2020-03-20 | Valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010205445.9A CN111930790B (en) | 2020-03-20 | 2020-03-20 | Valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111930790A true CN111930790A (en) | 2020-11-13 |
CN111930790B CN111930790B (en) | 2021-12-31 |
Family
ID=73316171
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010205445.9A Active CN111930790B (en) | 2020-03-20 | 2020-03-20 | Valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111930790B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113281218A (en) * | 2021-05-25 | 2021-08-20 | 国网河北省电力有限公司检修分公司 | Gas density monitoring method and device, storage medium and electronic equipment |
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 |
CN114047732A (en) * | 2021-11-15 | 2022-02-15 | 中国电子科技集团公司第四十八研究所 | Butterfly valve intelligent control method and system for silicon carbide epitaxial process |
CN117666462A (en) * | 2024-01-31 | 2024-03-08 | 成都苔岑智能设备有限公司 | PLC product standardization control system based on independent allocation of multiple parameters |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140034145A1 (en) * | 2012-08-06 | 2014-02-06 | Schneider Electric Buildings, Llc | Advanced Valve Actuation System with Integral Freeze Protection |
CN104899451A (en) * | 2015-06-12 | 2015-09-09 | 哈尔滨工业大学 | Time sequence prediction model selecting method based on statistical signal process |
CN106059661A (en) * | 2015-12-25 | 2016-10-26 | 国家电网公司 | Time sequence analysis based optical transmission network trend prediction method |
CN106991863A (en) * | 2017-05-31 | 2017-07-28 | 国网河南省电力公司检修公司 | A kind of voltage direct-current transmission valve cooling system operating mode prediction and fault pre-alarming platform |
CN110544003A (en) * | 2019-07-18 | 2019-12-06 | 湖南科技大学 | temperature prediction-based wind power plant wind turbine generator set frequency converter state evaluation method |
-
2020
- 2020-03-20 CN CN202010205445.9A patent/CN111930790B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140034145A1 (en) * | 2012-08-06 | 2014-02-06 | Schneider Electric Buildings, Llc | Advanced Valve Actuation System with Integral Freeze Protection |
CN104899451A (en) * | 2015-06-12 | 2015-09-09 | 哈尔滨工业大学 | Time sequence prediction model selecting method based on statistical signal process |
CN106059661A (en) * | 2015-12-25 | 2016-10-26 | 国家电网公司 | Time sequence analysis based optical transmission network trend prediction method |
CN106991863A (en) * | 2017-05-31 | 2017-07-28 | 国网河南省电力公司检修公司 | A kind of voltage direct-current transmission valve cooling system operating mode prediction and fault pre-alarming platform |
CN110544003A (en) * | 2019-07-18 | 2019-12-06 | 湖南科技大学 | temperature prediction-based wind power plant wind turbine generator set frequency converter state evaluation method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113281218A (en) * | 2021-05-25 | 2021-08-20 | 国网河北省电力有限公司检修分公司 | Gas density monitoring method and device, storage medium and electronic equipment |
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 |
CN113641959B (en) * | 2021-08-13 | 2024-04-12 | 山东电工电气集团数字科技有限公司 | Temperature trend prediction method for high-voltage cable connector |
CN114047732A (en) * | 2021-11-15 | 2022-02-15 | 中国电子科技集团公司第四十八研究所 | Butterfly valve intelligent control method and system for silicon carbide epitaxial process |
CN117666462A (en) * | 2024-01-31 | 2024-03-08 | 成都苔岑智能设备有限公司 | PLC product standardization control system based on independent allocation of multiple parameters |
CN117666462B (en) * | 2024-01-31 | 2024-05-17 | 成都苔岑智能设备有限公司 | PLC product standardization control system based on independent allocation of multiple parameters |
Also Published As
Publication number | Publication date |
---|---|
CN111930790B (en) | 2021-12-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111930790B (en) | Valve inlet temperature prediction method of valve cooling equipment based on time sequence analysis | |
CN106600447B (en) | Big data cloud analysis method for transformer substation inspection robot centralized monitoring system | |
CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
CN104504607A (en) | Method for diagnosing photovoltaic power station faults on the basis of fuzzy clustering algorithm | |
Xu et al. | An anomaly detection and dynamic energy performance evaluation method for HVAC systems based on data mining | |
CN110889088A (en) | Enterprise pollution discharge supervision method assisted by electric model | |
CN103729804A (en) | On-line decision support method for responding to power quality early warning | |
CN113420162B (en) | Equipment operation chain state monitoring method based on knowledge graph | |
CN116742799A (en) | Auxiliary power distribution monitoring and early warning system based on Internet of things technology | |
CN109787295B (en) | Wind power ultra-short term prediction calculation method considering wind power plant state | |
CN111486555A (en) | Method for carrying out energy-saving regulation and control on central air conditioner by artificial intelligence AI expert system | |
CN103236019A (en) | Method and system for automatically generating energy-saving diagnosis and modification strategy for typical energy-consuming system | |
CN117172625B (en) | Comprehensive analysis method for energy-saving reconstruction of existing building | |
CN111310854A (en) | Low false alarm rate electricity stealing detection secondary screening method based on electricity load fingerprint | |
CN103500364A (en) | Electric energy quality steady-state index prediction method and system | |
Zhang et al. | The power big data-based energy analysis for intelligent community in smart grid | |
CN117763294A (en) | Monitoring system and method for energy-saving equipment | |
CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
CN111367255A (en) | Performance evaluation test system and method for multi-variable control system | |
CN113176530A (en) | On-service electric energy meter batch fault diagnosis method based on meter-dismantling operation characteristics | |
CN111144629A (en) | Method and system for predicting water inflow of hydroelectric power station | |
CN116384622A (en) | Carbon emission monitoring method and device based on electric power big data | |
Xiong et al. | Forecasting ultra‐short‐term wind power by multiview gated recurrent unit neural network | |
CN105511454B (en) | A kind of process control loops time-varying oscillation behavior detection method | |
CN114412447A (en) | Fault detection method and device for screw pump well |
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 |