CN107909195A - A kind of design for commodities method - Google Patents
A kind of design for commodities method Download PDFInfo
- Publication number
- CN107909195A CN107909195A CN201711089514.9A CN201711089514A CN107909195A CN 107909195 A CN107909195 A CN 107909195A CN 201711089514 A CN201711089514 A CN 201711089514A CN 107909195 A CN107909195 A CN 107909195A
- Authority
- CN
- China
- Prior art keywords
- holiday
- average
- weather
- water
- daily
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 93
- 238000012417 linear regression Methods 0.000 claims abstract description 13
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims 1
- 239000008399 tap water Substances 0.000 abstract description 2
- 235000020679 tap water Nutrition 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012843 least square support vector machine Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Classifications
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of design for commodities method, using one predicted city daily water consumption of formula, formula one：Qd=QA(1+B1ΔT+B2W+B3V), wherein, QdTo predict the daily water consumption of day（m3/d）；QAFor the past average consumption of some days（m3/d）；Δ T is increment of the temperature on average for past some daily mean temperature values of prediction day（℃）；W is Changes in weather factor；V is holiday factor；B1、B2、B3For linear regression coeffficient.The precision of prediction of the design for commodities method of the present invention is high, influence factor clearly, calculate it is simple, can corrected parameter at any time, so as to further improve precision of prediction, dispatch foundation be provided for the water supply of tap water.
Description
Technical field
The present invention relates to a kind of design for commodities method.
Background technology
Factor due to influencing city day water supply had both included the conventional sexual factor such as season, weather, vacation, also including pipe network
The uncertain unconventional factor such as accident, industrial production.Therefore more generally used at present is time series analysis, gray prediction
With the non-explanation prediction model such as neutral net, it mainly establishes model according to a large amount of historical datas, generally existing influence because
Element is unknown, it is complicated to calculate, the problems such as needing historical data more.
Application publication number discloses the city based on least square method supporting vector machine model for CN104715292A and uses in short term
Water Forecasting Methodology, comprises the following steps：Historical water usage is pre-processed；Carry out correlation analysis；Using least square
Support vector machine method, establishes the short-term water demands forecasting model in city, chooses the historical water usage that related coefficient is more than setting value
Time series combination be trained as training sample set；Real-time estimate is carried out using the short-term water demands forecasting model in city；
Prediction error is calculated, if prediction error is unsatisfactory for precision of prediction requirement, the short-term water demands forecasting model in city is improved.
But this method or relatively complicated and precision of prediction need to be further improved.
The content of the invention
It is an object of the invention to provide a kind of high day forecasting providing-water method of precision of prediction.
In order to solve the above technical problems, the present invention adopts the following technical scheme that：
It is an object of the present invention to provide a kind of design for commodities method, using one predicted city civil water of formula
Amount,
Formula one：Qd=QA(1+B1ΔT+B2W+B3V),
Wherein, QdTo predict the daily water consumption (m of day3/d)；
QAFor the average consumption (m on some days of past3/d)；
Δ T is increment (DEG C) of the temperature on average for past some daily mean temperature values of prediction day；
W is Changes in weather factor；
V is holiday factor；
B1、B2、B3For linear regression coeffficient.
Specifically, the W is determined using following steps：
The daily water consumption of history day, be grouped by step (1) according to different weather situation, and calculates every kind of weather feelings
The average daily consumption of water Q of conditionWeather；
Step (2), the average daily consumption of water Q for calculating history dayIt is average；
Step (3), the assignment k for calculating according to formula two every kind of weather conditionWeather, formula two：kWeather=(QWeather-QIt is average)/
QIt is average；
Step (4), the assignment k according to the corresponding weather of weather condition selection for predicting dayWeatherUsed as W.
More specifically, the weather condition is divided into fine, cloudy, cloudy, shower, light rain, moderate rain, heavy rain, heavy rain, snow.
Specifically, the V is determined using following steps：
The daily water consumption of history day, be grouped by step (1) according to different holiday situations, and calculates every kind of holiday feelings
The average daily consumption of water Q of conditionHoliday；
Step (2), the average daily consumption of water Q for calculating history dayIt is average；
Step (3), the assignment k for calculating according to formula three every kind of holiday situationHoliday, formula three：kHoliday=(QHoliday-QIt is average)/
QIt is average；
Step (4), the assignment k according to the holiday situation selection corresponding holiday for predicting dayHolidayUsed as V.
More specifically, it is false to be divided into Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday and section for the holiday situation
Day.
Specifically, the B1、B2、B3According to the daily water consumption of history day, temperature change, weather condition and holiday situation,
Obtained by one linear regression of formula.
According to a preferred solution, the design for commodities method further includes the period progress to different characteristic of water use
Division, each different periods use different W, V, B1、B2、B3To be predicted to the daily water consumption of corresponding period.
Due to the implementation of above technical scheme, the present invention has the following advantages that compared with prior art：
The precision of prediction of the design for commodities method of the present invention is high, and influence factor is clearly, calculating is simple, can correct at any time
Parameter, so as to further improve precision of prediction, foundation is provided for the water supply scheduling of tap water.
Brief description of the drawings
Attached drawing 1 is the absolute relative error distribution histogram of water factory；
Attached drawing 2 predicts distribution situation of the absolute relative error more than 5% for water factory；
Attached drawing 3 is error prediction model contrast before and after water factory's optimization (during it's year past 2017).
Embodiment
First, design for commodities method
The daily water consumption of history day, be grouped, weather by step (1) according to different weather situation and different holiday situation
Situation is divided into fine, cloudy, cloudy, shower, light rain, moderate rain, heavy rain, heavy rain, snow；Holiday situation is divided into Monday, Tuesday, Wednesday, week
4th, Friday, Saturday, Sunday and festivals or holidays.
Step (2), the average daily consumption of water Q for calculating every kind of weather conditionIt is fine、QIt is cloudy、QIt is cloudy、QShower、QLight rain、QModerate rain、QHeavy rain、
QHeavy rain、QSnow。
Step (3), the average daily consumption of water Q for calculating every kind of holiday situationMonday、QTuesday、QWednesday、QThursday、QFriday、QSaturday、QSunday、
QFestivals or holidays。
Step (4), the average daily consumption of water Q for calculating history dayIt is average。
Step (5), the assignment k for calculating according to formula two every kind of weather conditionIt is fine、kIt is cloudy、kIt is cloudy、kShower、kLight rain、kModerate rain、kHeavy rain、
kHeavy rain、kSnow, wherein, kIt is fine、kIt is cloudy、kIt is cloudy、kShower、kLight rain、kModerate rain、kHeavy rain、kHeavy rain、kSnowRespectively corresponding weather when W, formula two：kWeather=
(QWeather-QIt is average)/QIt is average。
Step (6), the assignment k for calculating according to formula three every kind of holiday situationMonday、kTuesday、kWednesday、kThursday、kFriday、kSaturday、kSunday、
kFestivals or holidays, wherein, kMonday、kTuesday、kWednesday、kThursday、kFriday、kSaturday、kSunday、kFestivals or holidaysRespectively corresponding holiday when V, formula three：kHoliday=
(QHoliday-QIt is average)/QIt is average。
Step (7), according to the daily water consumption of history day, temperature change, weather condition and holiday situation, it is linear by formula one
Recurrence obtains B1、B2、B3；Formula one：Qd=QA(1+B1ΔT+B2W+B3V),
Wherein, QdTo predict the daily water consumption (m of day3/d)；
QAFor the average consumption (m on some days of past3/d)；
Δ T is increment (DEG C) of the temperature on average for past some daily mean temperature values of prediction day；
W is Changes in weather factor；
V is holiday factor；
B1、B2、B3For linear regression coeffficient.
Step (8), by what step (7) obtained arrive B1、B2、B3Inverse iteration enters formula one, obtains the predictor formula of daily water consumption.
Preferably, design for commodities method, which further includes, divides the period of different characteristic of water use, when each different
W, V, B different Duan Caiyong1、B2、B3To be predicted to the daily water consumption of corresponding period, for example, being before celebrating the New Year or the Spring Festival by Time segments division
1 month afterwards, multiple periods such as August part.
Wherein, the definite specific method of the linear regression coeffficient of step (7) is：
Best linear fit is carried out to given data usually using least square method.It is fitted the original of multiple linear regression model
On the basis of the error between the predicted value of dependent variable and actual value is then built upon as minimum, i.e.,For minimum.
For equation group：
After its vectorization：X β=Y
It is rightDifferential is carried out, is existedSo that S (β) is minimum, can obtain
It is assured that so as to the regression coefficient of multiple linear equation.When numerical value is more, and manual calculation is more difficult, generally
Complete to calculate using computer software.
In this way, it is possible to the linear regression coeffficient B in formula one is calculated by the data of first N days1、B2、B3。
2nd, the inspection of prediction model accuracy
Absolute relative error w
Mean absolute relative error e
yiFor the actual value of the i-th daily water consumption；FiFor the i-th design for commodities value.
3rd, application examples
3.1st, according to somewhere water factory annual data in 2015, variable assignments is tried to achieve, such as table 1.
The assignment of table 1, each variable of water factory's weather conditions
| Weather conditions | It is fine | It is cloudy | It is cloudy | Shower | Light rain | Moderate rain | Heavy rain | Heavy rain | Snow |
| Assignment | -0.060 | -0.111 | -0.132 | -0.027 | -0.163 | -0.071 | -0.176 | -0.056 | -0.204 |
The assignment of table 2, each variable of water factory's vacation situation
| Vacation situation | Monday | Tuesday | Wednesday | Thursday | Friday | Saturday | Sunday | Festivals or holidays |
| Assignment | -0.135 | -0.130 | -0.047 | 0.033 | 0.074 | 0.056 | 0.150 | -0.375 |
3.2nd, model variable is definite
(1) basis for estimation
Related coefficient is the statistical indicator for reflecting degree in close relations between variable, and data more level off to that 0 expression is related to close
System is weaker.The computational methods of related coefficient are：
By selecting different variables, and compare their related coefficients between water, can draw linear with day water supply
The best variable of correlation.
(2) judging result
According to formula one, setting day water supply variation coefficient
Try to achieve the first half of the year in 2016 day water supply variation coefficient with highest temperature Tmax, lowest temperature Tmin, temperature on average
Tave, mean temperature change Delta T, humidity, weather, the related coefficient of holiday situation, be shown in Table 3.As seen from the table, day water supply quantitative change
Change coefficient and the linear dependence of mean temperature change, weather condition and holiday situation is best.It is indicated above that to weather condition and
The assignment of holiday situation is suitable, and can be changed by the use of mean temperature, weather condition and holiday situation as variable, using polynary line
Property return.
Related coefficient between table 3, water factory day water supply variation coefficient and other variables
3.3rd, process is predicted
By Air temperature, weather conditions and the vacation situation in water factory on April 30th, 15 days 1 March in 2016 with
And day water supply data, based on the historical data of former 20 days, the linear of prediction variation per day is obtained according to least square method and is returned
Return coefficient, the day water supply of prediction day is obtained further according to formula one.
3.4th, prediction result is examined
Most literature has in the demand in view of user to water supply satisfaction degree, the accuracy to scheduling hourly water demand forcast
The clear and definite boundary requirement of a comparison, that is, 2% or so, the maximum deviation of prediction limits for the mean absolute relative error control predicted
Within 5%, therefore select absolute relative error distribution and mean absolute relative error accurate as inspection water prediction model
The two indices of degree.
3.5th, absolute relative error distribution is predicted
Water factory's average daily water supply in 2016 is 380,000 tons.According to formula four, this absolute relative error of 410 days is calculated, it is right
Error result is counted, as shown in Figure 1.As can be known from Fig. 1, water factory's prediction absolute relative error accounting within 1%
32.44%, 60.73% is accounted within 2%, 78.54% is accounted within 3%, 89.76% is accounted within 4%, 5%
Within account for 95.12%.As can be seen that the related coefficient result between water factory calculated above and each variable is consistent.
3.6th, the comparison of the model and other models
According to formula five, the average absolute predicted to water during 30 days April in 2017 water factory's on March 15th, 2016 is calculated
Relative error and maximum absolute relative error, the result for drawing water factory is respectively 1.94% and 14.42%.By itself and other documents
In data compare, find water factory mean error be less than most of documents in result.
Each model prediction mean absolute relative error and maximum absolute relative error in table 4, other documents
Wherein：Structure changes heredity least square method supporting vector machine method is referring to Chen Lei, stone also structure changes heredity least square branch
Hold vector machine method prediction daily water consumption [J], Zhejiang Polytechnical University's journal, 2017,45 (1), 69-72.
Based on dividing the period forecasting method of shape difference theory referring to Zhang Hongwei, Lu Renqiang, cities of the Niu Zhiguang based on fractal theory
City's design for commodities method [J], University Of Tianjin's journal, 2009,42 (1), 56-59.
The mutative scale chaos genetic algorithm of least square method supporting vector machine optimization is based on improving least square referring to Wu Lingyun
The design for commodities technique study [D] of support vector machines, Hangzhou：Zhejiang Polytechnical University, 2013.
Support vector regression method, single exponential smoothness, the single exponential smoothness of adjust automatically smoothing parameter, conic section
Exponential smoothing, grey GM (1,1) model, BP neural network are referring to Zhang Hongwei, Yue Lin, cities of the Wang Liang based on radial basis function
City's design for commodities method [J], University Of Tianjin's journal, 2006,39 (4), 486-489.
3.7th, model optimization
3.7.1, error statistics and analysis
Statistical classification is carried out according to different time sections to a couple of days of absolute relative error more than 5% in water factory's prediction result,
As shown in Figure 2.It can be seen from the figure that water factory predicts absolute relative error being mainly distributed on before and after the New Year more than 5% and August
Part.
According to prediction error statistics as a result, error it is maximum be concentrated mainly on before and after the New Year and high temperature season.Before and after New Year,
Go back home New Year or out on tours since user leaves city, day water supply be more usually greatly decreased, therefore this period is with before
Data consistency afterwards is poor.High temperature season is water use peak, day water supply be more usually significantly increased, therefore this period is with before
Data consistency afterwards is also poor.
3.7.2, model optimization
Now the model during the New Year is optimized.It is first that the data of one month before and after 2015 and 2016 New Year are independent
List, carry out assignment to weather condition in the section time and vacation situation again, obtain result such as table 5 and table 6.
The assignment of table 5, each variable of water factory's weather conditions
| Weather conditions | It is fine | It is cloudy | It is cloudy | Light rain | Moderate rain |
| Assignment | 0.209 | 0.019 | -0.161 | -0.154 | -0.457 |
The assignment of table 6, each variable of water factory's vacation situation
| Vacation situation | Monday | Tuesday | Wednesday | Thursday | Friday | Saturday | Sunday |
| Assignment | 0.124 | -0.169 | -0.100 | -0.176 | -0.090 | 0.250 | 0.091 |
3.7.3, optimum results examine
According to the data that the New Year in 2015 and 2016 is front and rear, with the assignment of each variable after optimization, using multiple linear regression
Method the front and rear water of New Year in 2017 is predicted, and itself and the prediction result before optimization are contrasted, see Fig. 3.From figure
In as can be seen that optimization before water factory's prediction result mean absolute relative error be 7.69%, worst error 14.43%, and
After optimization, the mean absolute relative error of water factory's prediction result is 2.36%, worst error 5.20%.Therefrom illustrate, to pre-
After survey model optimizes, front and rear prediction accuracy of celebrating the New Year or the Spring Festival greatly improves.
It is possible thereby to infer, when the historical data of accumulation is enough, can obtain in the different periods with water feature
Each variable assignments, carries out finer division, prediction result will be more accurate with this application to prediction model.
3.8th, conclusion
(1) the day water supply of water factory can be predicted using multiple linear regression model, water factory's prediction result it is exhausted
It is 1.94% to relative error, which is suitable for the water factory.Compared with other models, the accuracy of water factory prediction is excellent
In most of results reported in the literature；
(2) it is polynary can to judge whether water factory is suitable for by the linear relationship size between selected variable and day water supply
The water prediction of linear regression model (LRM), and by comparing its size most suitable variable can be selected to be predicted；
(3) when historical data accumulation is enough, the period of different characteristic of water use can finely be divided, is adopted respectively
With different variable assignments, water is predicted, can progressively improve the accuracy of prediction model.
Claims (7)
- A kind of 1. design for commodities method, it is characterised in that：Using one predicted city daily water consumption of formula,Formula one：Qd=QA(1+B1ΔT+B2W+B3V),Wherein, QdTo predict the daily water consumption of day（m3/d）；QAFor the past average consumption of some days（m3/d）；Δ T is increment of the temperature on average for past some daily mean temperature values of prediction day（℃）；W is Changes in weather factor；V is holiday factor；B1、B2、B3For linear regression coeffficient.
- 2. design for commodities method according to claim 1, it is characterised in that：The W is carried out using following steps Determine：Step（1）, the daily water consumption of history day is grouped according to different weather situation, and calculate every kind of weather condition Average daily consumption of water QWeather；Step（2）, calculate history day average daily consumption of water QIt is average；Step（3）, calculate according to formula two the assignment k of every kind of weather conditionWeather, formula two：kWeather=（QWeather-QIt is average）/ QIt is average；Step（4）, according to the assignment k of the corresponding weather of weather condition selection of prediction dayWeatherUsed as W.
- 3. design for commodities method according to claim 2, it is characterised in that：The weather condition is divided into fine, more Cloud, the moon, shower, light rain, moderate rain, heavy rain, heavy rain, snow.
- 4. design for commodities method according to claim 1, it is characterised in that：The V is carried out using following steps Determine：Step（1）, the daily water consumption of history day is grouped according to different holiday situations, and calculate every kind of holiday situation Average daily consumption of water QHoliday；Step（2）, calculate history day average daily consumption of water QIt is average；Step（3）, calculate according to formula three the assignment k of every kind of holiday situationHoliday, formula three：kHoliday=（QHoliday-QIt is average）/ QIt is average；Step（4）, according to the assignment k of holiday situation selection corresponding holiday of prediction dayHolidayUsed as V.
- 5. design for commodities method according to claim 4, it is characterised in that：The holiday situation be divided into Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday and festivals or holidays.
- 6. design for commodities method according to any one of claim 1 to 5, it is characterised in that：The B1、B2、B3 According to the daily water consumption of history day, temperature change, weather condition and holiday situation, obtained by one linear regression of formula.
- 7. design for commodities method according to claim 6, it is characterised in that：The design for commodities method is also Including being divided to the period of different characteristic of water use, each different periods use different W, V, B1、B2、B3Come to it is corresponding when The daily water consumption of section is predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711089514.9A CN107909195A (en) | 2017-11-08 | 2017-11-08 | A kind of design for commodities method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711089514.9A CN107909195A (en) | 2017-11-08 | 2017-11-08 | A kind of design for commodities method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107909195A true CN107909195A (en) | 2018-04-13 |
Family
ID=61842701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711089514.9A Pending CN107909195A (en) | 2017-11-08 | 2017-11-08 | A kind of design for commodities method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107909195A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109857157A (en) * | 2019-01-22 | 2019-06-07 | 中南大学 | A kind of regionality booster station flow of inlet water dispatching method |
| CN110070203A (en) * | 2019-02-25 | 2019-07-30 | 广州市自来水公司 | A kind of forecasting providing-water method, system, device and storage medium |
| CN112594553A (en) * | 2020-12-07 | 2021-04-02 | 熊猫智慧水务有限公司 | Pipe network pressure regulation and control method based on pressure target curve |
| CN113128827A (en) * | 2021-03-04 | 2021-07-16 | 上海威派格智慧水务股份有限公司 | Method and system for matching scheduling scheme |
| CN113537564A (en) * | 2021-06-15 | 2021-10-22 | 顺德职业技术学院 | Method for regulating daily water consumption based on seasonal changes |
| CN114477329A (en) * | 2022-02-22 | 2022-05-13 | 江苏舜维环境工程有限公司 | Integrated water treatment device for cement plant |
| CN115375199A (en) * | 2022-10-24 | 2022-11-22 | 青岛研博电子有限公司 | Long-distance intelligent water supply scheduling method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715292A (en) * | 2015-03-27 | 2015-06-17 | 上海交通大学 | City short-term water consumption prediction method based on least square support vector machine model |
-
2017
- 2017-11-08 CN CN201711089514.9A patent/CN107909195A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715292A (en) * | 2015-03-27 | 2015-06-17 | 上海交通大学 | City short-term water consumption prediction method based on least square support vector machine model |
Non-Patent Citations (1)
| Title |
|---|
| 周鹏: ""供水优化调度系统的研究与应用"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109857157A (en) * | 2019-01-22 | 2019-06-07 | 中南大学 | A kind of regionality booster station flow of inlet water dispatching method |
| CN110070203A (en) * | 2019-02-25 | 2019-07-30 | 广州市自来水公司 | A kind of forecasting providing-water method, system, device and storage medium |
| CN110070203B (en) * | 2019-02-25 | 2023-12-26 | 广州市自来水有限公司 | Water supply quantity prediction method, system, device and storage medium |
| CN112594553A (en) * | 2020-12-07 | 2021-04-02 | 熊猫智慧水务有限公司 | Pipe network pressure regulation and control method based on pressure target curve |
| CN113128827A (en) * | 2021-03-04 | 2021-07-16 | 上海威派格智慧水务股份有限公司 | Method and system for matching scheduling scheme |
| CN113537564A (en) * | 2021-06-15 | 2021-10-22 | 顺德职业技术学院 | Method for regulating daily water consumption based on seasonal changes |
| CN113537564B (en) * | 2021-06-15 | 2024-05-10 | 顺德职业技术学院 | Daily water quantity adjusting method based on quarterly change |
| CN114477329A (en) * | 2022-02-22 | 2022-05-13 | 江苏舜维环境工程有限公司 | Integrated water treatment device for cement plant |
| CN114477329B (en) * | 2022-02-22 | 2023-01-06 | 江苏舜维环境工程有限公司 | Cement plant integrates water treatment facilities |
| CN115375199A (en) * | 2022-10-24 | 2022-11-22 | 青岛研博电子有限公司 | Long-distance intelligent water supply scheduling method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107909195A (en) | A kind of design for commodities method | |
| Bakker et al. | A fully adaptive forecasting model for short-term drinking water demand | |
| Bakker et al. | Improving the performance of water demand forecasting models by using weather input | |
| CN108230049A (en) | The Forecasting Methodology and system of order | |
| Xiao et al. | Impacts of data preprocessing and selection on energy consumption prediction model of HVAC systems based on deep learning | |
| CN104464291A (en) | Traffic flow predicting method and system | |
| CN106873372B (en) | Reservoir regulation for flood control optimization method based on the control of Flood Control Dispatch data adaptive | |
| CN109242265B (en) | Urban water demand combined prediction method based on least square sum of errors | |
| CN102426674A (en) | Power system load prediction method based on Markov chain | |
| CN110033134A (en) | A kind of short-term load forecasting algorithm of segmentation day by day considering meteorologic factor | |
| CN112856572A (en) | Automatic operation adjusting method of heat supply system based on characteristic parameter identification | |
| CN109307159A (en) | A kind of pipe network model alarm method based on water consumption optimal prediction model | |
| JP2014157457A (en) | Prediction device and prediction method | |
| CN109190902A (en) | Consider the uncertain water resource optimal allocation Emulation of Newsboy Model of supply and demand | |
| CN101916335A (en) | Prediction method of city water-requirement time series-exponent smoothing model | |
| CN114925874A (en) | Carbon emission pre-judging method and device based on BERT neural network model | |
| CN112418495A (en) | Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network | |
| JP4511435B2 (en) | Water supply operation planning device | |
| CN111507507A (en) | Big data-based monthly water consumption prediction method | |
| CN105389637A (en) | Effective workday construction method for monthly electricity consumption prediction model | |
| CN117469603B (en) | Multi-water-plant water supply system pressure optimal control method based on big data learning | |
| CN102912760B (en) | Lowest navigable water level generating method of downstream river of reservoir | |
| Ravitilova et al. | Forecasting Sales: A Comprehensive Analysis of Forecasting Techniques for Sales Budget Determination | |
| CN110110890A (en) | Day wastewater quantity prediction method based on ELMAN neural network | |
| CN110175695B (en) | Method and system for predicting cargo volume during spring festival |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180413 |