CN102032935A - Soft measurement method for sewage pumping station flow of urban drainage converged network - Google Patents
Soft measurement method for sewage pumping station flow of urban drainage converged network Download PDFInfo
- Publication number
- CN102032935A CN102032935A CN 201010590749 CN201010590749A CN102032935A CN 102032935 A CN102032935 A CN 102032935A CN 201010590749 CN201010590749 CN 201010590749 CN 201010590749 A CN201010590749 A CN 201010590749A CN 102032935 A CN102032935 A CN 102032935A
- Authority
- CN
- China
- Prior art keywords
- data
- neural network
- pumping
- value
- pumping plant
- 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
Images
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a soft measurement method for sewage pumping station flow of an urban drainage converged network. The conventional drainage pipe network system has lots of uncertain factors and high measurement hardware cost. The method comprises the following steps of: analyzing main influencing factors of converged node pumping station flow by using mechanism analysis and priori information, and primarily determining influencing factors of a back-propagation (BP) neural network, namely determining input/output variables; determining lag time of different upstream pumping station flows by using a grey correlation analysis method; and establishing a grey neural network model on the basis of pumping station historical operating data, and predicting the converging node pumping station flow. By combining two methods of grey correlation analysis and grey neural network, the method solves the problem of difference of drainage time delay of different upstream pumping stations, well simulates the nonlinear pipe network drainage process, realizes soft measurement of converged node sewage pumping station flow, saves the hardware resources, and is low in cost and high in accuracy.
Description
Technical field
The invention belongs to soft fields of measurement, be specifically related to a kind of flexible measurement method of the drainage pipeline networks discharge of sewage.
Background technology
Along with the develop rapidly in city, municipal drainage has become one of bottleneck of restriction city fast development.Yet in the present existing urban drainage pipe network system, the discharge of sewage of each pipe network and pumping plant of flowing through and water level can only lean on artificial experience to estimate, because pipe network system lacks detailed measured discharge data, system's generation, pipeline of unpredictable flood thus overflows, and more can't reach the purpose of energy saving in pumping station by the unlatching of scheduling pumping plant unit.
Adopt hardware detection device (comprising mechanical type, turbine type, ultrasonic type, electromagnetic type) to measure flow and need transform drainage pipeline, this process input cost height, produce effects limited.Patent 00134362.9 " is measured the method for flow speed of thin run-off layer on earth surface " and is utilized electrolyte as tracer agent, records release position and check point calculate flow velocity after the time interval method.Yet this method can't be applied in the effluent stream, and can't real-time online measuring.Patent 201010140199.X " based on the sewage pumping station water level prediction method of neural network " is though provide the flexible measurement method of a kind of sewage pumping station water yield and water level, but this method only is applicable to simple upstream and downstream series connection pumping plant situation, pumping plant flow and water level under the unpredictable situation of confluxing.The pipe network node that confluxes is subjected to the influence of a plurality of upstream pumping units, uncertain, non-linear and hysteresis quality that the discharge of sewage has, a large amount of uncertain factors of sewerage pipeline network existence simultaneously as rainfall distribution, sanitary sewage discharging, pipeline silting, seepage etc., all will increase the prediction complicacy.
Summary of the invention
The object of the invention provides a kind of flexible measurement method that can the economize on hardware resource, realizes the conflux on-line monitoring of the pipe network discharge of sewage of complexity.
The present invention at first utilizes Analysis on Mechanism and prior imformation, analyzes the major influence factors of the node pumping plant flow that confluxes, and tentatively determines the influence factor of BP neural network, promptly determines input/output variable.Utilize Grey Incidence Analysis to determine different upstream pumping unit drain discharge retardation time then.On pumping plant history data basis, set up Grey Neural Network Model, predict the node pumping plant flow that confluxes.Concrete steps are as follows:
Step (1) is selected collecting pipe pessimistic concurrency control input/output variable.
Be mainly derived from each upstream pumping unit discharge rate and local inbound traffics (side stream, rainfall etc.) based on the Analysis on Mechanism pumping plant inflow that confluxes as can be known, the sewage quantity that upstream pumping unit promotes must flow into downstream pump station through pipe network, have certain hysteresis quality, and this locality becomes a mandarin and has uncertainty.Equal the forebay liquid level change according to the sewage inbound traffics and multiply by the forebay sectional area, though become a mandarin can't be by calculating in this locality, the forebay level value changes can reflect local flow valuve indirectly.Therefore selecting to conflux, pool water level is the output variable of neural network model before the pumping plant, and the pool water level principal element is the neural network model input variable before the pumping plant to select influence to conflux: 1. each pumping drainage amount of upstream; 2. the pumping plant forebay liquid level change amount of confluxing; 3. the pumping drainage amount of confluxing.
Be simplified model, can analyze upstream pumping drainage amount and conflux the ratio of pumping plant inflow, cast out ratio less than 10% input quantity.
Step (2) data pre-service.
May there be noise in the raw data that data acquisition and monitoring system (SCADA) gathers, data are imperfect or even inconsistent, before utilizing these data to carry out analysis modeling, need carry out pre-service to data.Mainly comprise:
(a) missing data is handled: what SCADA gathered is time series data, every sampling in 20 seconds 1 time.At the missing term that may exist, at first to roughly select, per minute selects 1 data; Utilize again and ignore tuple or historical data complementing method processing missing data.
(b) noise data is handled: the level gauging error that water level fluctuation causes during for the switch pump, by getting mean value that three measured values obtain to reduce error; Adopt the front and back data smoothing to proofread and correct for indivedual singular points; For tangible data less than normal bigger than normal, adopt the method for directly removing burr to proofread and correct.
Step (3) is determined each upstream pumping unit draining delay time
Each upstream pumping unit sewage effluent successively imports main by each arm and flow to the node pumping plant that confluxes again, because length of tube, cross section, the gradient are different with the water yield, it is also not necessarily identical that each tributary arrives the time of the pumping plant that confluxes.According to the sewage propagation law, the flow of same position phase always is later than the time that occurs at last section in the time that next section occurs, and this mistiming is exactly the delay time of flow.For the node pumping plant that confluxes, need to calculate its partial correlation.
Adopt the association of grey speed to calculate the pumping drainage delay time, by the notion of grey relational grade in the gray theory, same discharge process should be bigger at the correlation degree of upstream and downstream.Selecting downstream flow time series (daily mean flow sequence) be the reference time sequence, 2 periods forward of 1 period forward of corresponding time of upstream, corresponding time, corresponding time, 3 periods forward of correspondence time ... the flow time series is for comparing time series.The value correspondence of corresponding relatively time series and reference time preface degree of association maximum forward the time hop count be exactly the pumping drainage delay time.
The hypothetical reference time series is Y
0=[Y
0(1), Y
0(2) ..., Y
0(n)]; Relatively time series is: X
i=[X
i(1), X
i(2) ..., X
i(n)] i=1,2 ..., N, N represent comparison seasonal effect in time series number.
I expression formula that compares correlation function between time series and the reference time sequence is:
In the formula: Δ X (t)=X
i(t+1)-X
i(t), Δ Y (t)=Y
0(t+1)-Y
0(t), Δ t is for comparing the seasonal effect in time series sampling period;
I grey speed interconnection degree r that compares between time series and the reference time sequence
iFor:
Calculate each reference time sequence and seasonal effect in time series grey speed interconnection degree relatively respectively, the value of these grey relational grades relatively, the value correspondence that the degree of association is big forward the time hop count be exactly the pumping drainage delay time.Obtain each upstream pumping unit draining delay time by above-mentioned grey speed correlating method.
For the time series data of SCADA systematic sampling, select the list entries composition training sample big with the output sequence degree of association.The utilization grey correlation calculates the concrete steps in delay time:
(a) collect the sewage lifting capacity data of conflux node pumping plant sewage inflow and each upstream pumping unit, time scale as far as possible little (the data here all are sewage quantity sizes values, need not to carry out nondimensionalization).
(b) set up the reference time sequence and compare time series, the node pumping plant inflow time series of selecting to conflux is reference time sequence Y
0, the last period of corresponding time of each upstream pumping unit, corresponding time, two periods of corresponding time ... sewage lifting capacity time series be time series X relatively
i
(c) calculate grey incidence coefficient, utilization grey incidence coefficient computing formula is calculated the grey incidence coefficient between reference time sequence and each the comparison time series respectively, uses ξ
(t), ξ
(t-1), ξ
(t-2)... expression.
(d) calculate grey speed interconnection degree, utilization grey relational grade computing formula, the grey speed interconnection degree of calculating reference sequences and each comparative sequences is used r
(t), r
(t-1), r
(t-2)... expression.
(e) determine each upstream pumping unit draining delay time, notion according to grey relational grade, degree of association value maximum shows corresponding comparison time series and the correlation degree maximum between the reference time sequence, its correspondence forward the time hop count just tentatively be defined as the upstream pumping unit draining delay time.Therefore relatively the value of these grey relational grades, the value correspondence of degree of association maximum forward the time hop count just can regard as the upstream pumping unit draining delay time.
Step (4) data normalization is handled
The input data are carried out normalized, be converted into the value of [0,1] interval range, conversion formula is:
X wherein
MaxBe the maximal value in the input data, x
MinBe the minimum value in the input data.X is the input data,
Be the value after the processing of input data normalization.
Step (5) is built the BP neural network framework.
The newff function that calls in the Matlab7.1 Neural Network Toolbox is set up a BP neural network, Net=newff (PR, [s
1, s
2..., s
i], { TF
1, TF
2..., TF
i, BTF, BLF, PF); Net is the BP neural network framework, and PR is a span that is determined by greatest member and least member in the input matrix, s
iBe the neuronic number of i layer, TF
iBe the transport function of i layer, 1≤i≤N
1, N
1Be the total number of plies of neural network, BTF is the training function of BP neural network, and BLF is the parameter of control weights and threshold value, and PF is the network performance function.
Step (6) training BP neural network.Concrete grammar is:
(a) initialization BP neural network, the value assignment of utilizing random function to produce is given weights and bias, calls the init function then and comes the whole neural network of initialization.
(b) network training number of times and training objective error are set, show the training step number.
(c) training data being set is input matrix P, and it is matrix T that desired value is set, and the train function that calls in the Matlab7.1 Neural Network Toolbox carries out the data training until convergence to BP neural network Net, Net=train (Net, P, T), wherein P is a trained values, and T is a desired value.
Step (7) test b P neural network.
The BP neural network that trains is tested, historical data is formed pumping plant forebay water level forecast network test matrix P_test, directly call the sim function in the Matlab7.1 Neural Network Toolbox, (Net P_test), carries out emulation to the test input to D=sim, wherein D is an objective function, Net is the BP neural network that trains, and D is a desired value, and P_test is a test sample book.
The anti-normalized of step (8) data.
To the test gained sewage pumping station forebay waterlevel data according to formula
Carry out anti-normalized, wherein x ' is a pumping plant forebay waterlevel data final after the anti-normalized,
Be the pumping plant forebay waterlevel data that emulation testing obtains, x
MaxBe the maximal value in the waterlevel data of pumping plant forebay, x
MinBe the minimum value in the waterlevel data of pumping plant forebay.
Can also carry out verification for the neural network prediction model of having set up.
Use based on the method for root mean square variance (RMSE) and validity index (COE) index the forecast model of setting up based on the BP neural network is tested.
The root mean square calculation formula:
The validity formula of index:
Wherein, n is the checking data number, q
iBe actual value,
Be predicted value,
Average for actual value.
Root-mean-square value is good more near 0 explanation model performance more, and the validity index is good more near 1 more, and the validity index means that less than 0.7 o'clock model is inapplicable.
The present invention utilizes municipal drainage data acquisition and monitoring system (SCADA system) to accumulate a large amount of pumping station operation data, determine the upstream pumping unit draining time delay time by grey correlation analysis, utilize neural network strong non-linear mapping ability and self-learning capability that conflux pipe network flow and water level are accurately forecast.Both solve different upstream pumping unit draining delay variation problems, simulated pipe network draining non-linear process again preferably.
The beneficial effect of the inventive method:
1. by grey correlation analysis and two kinds of method combinations of neural network, both solve different upstream pumping unit draining delay variation problems, better simulated pipe network draining non-linear process again, realized confluxing node sewage pumping station flow soft measurement, the economize on hardware resource, cost is low, precision is high.
2. can be used for the difference pipe network sewage pumping station volume forecasting of confluxing, be applicable to uncertain conditions such as rainfall distribution, sanitary sewage discharging, pipeline silting, seepage.
Therefore 3. grey neural network has the ability of approaching the Nonlinear Mapping function, utilizes the pumping station operation historical data to predict pool water level before the pumping plant, the precision of prediction height that obtains than traditional steady flow computing method.
Description of drawings
Fig. 1 is that bus factory's pumping plant is to martial arts circles's door pumping plant correlation graph;
Fig. 2 is that the Hangzhoupro large pumping station is to martial arts circles's door pumping plant correlation graph.
Embodiment
With Hangzhou drainage pipeline networks martial arts circles door pumping plant pipeline section is example, is described in detail the specific embodiment of the present invention.Martial arts circles's door pumping plant has 3 upstream pumping units, is respectively bus factory's pumping plant, and Gu swings pumping plant (leaf node), Hangzhoupro large pumping station (upstream pumping unit is high-new pumping plant), and the soft measurement calculation procedure of the node flow that confluxes is as follows:
Step (1) is determined collecting pipe pessimistic concurrency control input variable and output variable:
Input variable comprises that bus factory, upstream pumping plant, Gu swing pumping plant and Hangzhoupro large pumping station water discharge, martial arts circles's door pumping plant forebay liquid level change amount and martial arts circles's door pumping drainage amount; Output variable is a pool water level before martial arts circles's door pumping plant;
Step (2) data pre-service: the data that SCADA gathers are carried out data omission processing, noise processed.
A. missing data is handled: pumping plant SCADA at first roughly selects from the time series data of gathering every 20 seconds sampling 1 secondary data, and per minute selects 1 data, and according to front and back data completion, the associated data complementing method carries out missing data to be handled; For the more data of consecutive miss,, carry out the analogy completion by the artificial contrast data of the previous day.
B. noise data is handled: the level measuring error that water level fluctuation causes during to the switch pump, and average and front and back data smoothing correction is handled by the multisensor measured value; For tangible data less than normal bigger than normal, proofread and correct by removing the burr method.
Step (3) the pumping plant volume forecasting model of determining to conflux.
A. determine the model input/output variable:
Select based on Analysis on Mechanism that pool water level is the output variable of neural network model before martial arts circles's door pumping plant, the principal element of selecting to influence this water level is the neural network model input variable: 1. each pumping plant of upstream (bus factory's pumping plant, Gu swing pumping plant and Hangzhoupro large pumping station) lifting capacity; 2. martial arts circles's door pumping plant forebay liquid level change amount; 3. martial arts circles's door pumping plant lifting capacity.
Add up three upstream pumping units (bus factory's pumping plant, Gu swing pumping plant and Hangzhoupro large pumping station) lifting capacity and the ratio of node pumping plant (martial arts circles's door pumping plant) inflow that confluxes, ignore the little input quantity of ratio.It is very little that Yin Gu swings the pumping plant proportion, and this example selects bus factory's pumping plant and Hangzhoupro large pumping station lifting capacity as input item.
B. determine to delay parameter:
For the time series data of SCADA systematic sampling, adopt the association of grey speed to calculate the delay time of each upstream pumping unit water discharge to the pumping plant that confluxes, select the list entries composition training sample big with the output sequence degree of association.
Is example with bus factory's pumping plant to martial arts circles's door pumping plant, if reference sequences is martial arts circles's door pumping plant the 90th time series constantly, comparative sequences is bus factory's pumping plant flow time series in lag behind 1 moment, 2 moment to the 89th moment that lag behind, i.e. the 89th discharge of sewage time series that begins to the 1st moment of bus factory's pumping plant.Result of calculation as shown in Figure 1, horizontal ordinate is retardation time, the 60th reaches peak value constantly the time lagging behind.Select bus factory's pumping plant [65 ,-55] time period 10 groups of discharge rates before to import as model.Similar, Hangzhoupro large pumping station grey correlation analysis result reaches peak value as shown in Figure 2 when lagging behind the 30th moment, select Hangzhoupro large pumping station [35 ,-25] time period 10 groups of discharge rates before to import as model.
The input of determining model is respectively bus factory's pumping plant discharge rate, hysteresis time delay [65 ,-55], and Hangzhoupro large pumping station discharge rate, hysteresis time delay [35 ,-25], martial arts circles's door pumping plant discharge rate, each 10 dimension data of martial arts circles's door pumping plant liquid level, input matrix P is formed in cross arrangement.Be output as martial arts circles's pit level in front of the door.
Step (4) data normalization is handled.
Comprise four in the input sample, it is bigger that the order of magnitude differs, and for guaranteeing each factor par, accelerates speed of convergence, and data are carried out normalized, is converted into the value of [0,1] interval range.
Conversion formula:
X wherein
MaxBe the maximal value in the input data, x
MinBe the minimum value in the input data.X is the input data,
Be the value after the processing of input data normalization.
Step (5) makes up the BP neural network.
Build the BP neural network framework, call the newff function in the Matlab7.1 function library, Net=newff (threshold, [20,1], ' tansig ', ' purelin ', trainlm), wherein Threshold is the minimum value and the maximal value of 40 input and output vectors of defined matrix of a 40*1; [20,1] expression ground floor has 20 neurons, and the second layer has 1 neuron; Tansig is the input layer transport function; Purelin is the output layer transport function; Trainlm is the training function based on the l-m algorithm.
Step (6) training BP neural network.
A. initialization network
The net.initFcn initialization function that decides whole network.The parameter net.layer{i}.initFcn initialization function that decides each layer.The initwb function according to the initiation parameter of each layer oneself (initializes weights is made as rands usually for net.inputWeights{i, j}.initFcn) initializes weights matrix and biasing, and concrete grammar is as follows:
net.layers{1}.initFcn＝’initwb’；
net.inputWeights{1，1}.initFcn＝’rands’；
net.layerWeights{2，1}.initFcn＝’rands’；
net.biases{1，1}.initFcn＝’rands’；
net.biases{2，1}.initFcn＝’rands’；
net＝init(net)；
Net.IW{1,1} are the weight matrix of input layer to hidden layer;
Net.LW{2,1} are the weight matrix between hidden layer and output layer;
Net.b{1,1} are the threshold values vector of hidden layer;
Net.b{2,1} are the threshold values of output contact;
B., the step number that network training number of times, training objective error is set and is used for showing
net.trainParam.epochs＝2000；
net.trainParam.goal＝0.0008；
net.trainParam.show＝50；
C., it was 2000 steps that the network training number of times is set, and the training objective error is 0.0008, showed that the training step number was 50 steps.
D., the initial momentum item is set, learning rate
net.trainParam.mc＝0.7；
LP.lr＝0.3；
E., the momentum term that network training is set is 0.7, and the training study rate is 0.3.
F. utilize input matrix P ' and objective matrix to be made as T ', by calling the train function, net=train (net, P ', T ') carries out sewage pumping station forebay water level forecast network training until convergence.
Step (7) network test.
The historical data that will be used for testing is formed the matrix p_test that is used for the preceding pool water level network test of sewage pumping station according to the input matrix form of step (1), carries out normalized according to step (2) again, and the test matrix after the normalization is p ' _ test.Call the sim () function in the Matlab tool box, the network that trains is carried out emulation.The calling program code is: and D=sim (net, p ' _ test); The D matrix is sewage pumping station forebay water level forecast value.
The anti-normalized of step (8).
To the test gained pumping plant forebay waterlevel data according to formula
Carry out anti-normalized, wherein x ' is a forebay liquid level data final after the anti-normalized,
Be the forebay liquid level data that emulation testing obtains, x
MaxBe the maximal value in the liquid level data of forebay, x
MinBe the minimum value in the liquid level data of forebay.Pool water level is T ' _ test before the sewage pumping station after the anti-normalization, and promptly testing the preceding pool water level of resulting sewage pumping station is T ' _ test.
Claims (1)
1. the municipal drainage flexible measurement method of pipe network sewage pumping station flow that confluxes is characterized in that this method comprises the steps:
Step (1) is determined collecting pipe pessimistic concurrency control input variable and output variable;
Input variable comprises each pumping drainage amount of upstream, the pumping plant forebay liquid level change amount of confluxing and the pumping drainage amount of confluxing;
Output variable is the preceding pool water level of the pumping plant that confluxes;
Step (2) is carried out pre-service to the raw data of data collection and supervisory system collection; Described raw data comprises missing data and noise data;
The preprocess method of missing data is: at first roughly select, per minute selects 1 data; Utilize again and ignore tuple or historical data complementing method processing missing data;
The preprocess method of noise data is: the level gauging error that water level fluctuation causes during for the switch pump, by getting mean value that three measured values obtain to reduce error; Adopt the front and back data smoothing to proofread and correct for indivedual singular points; For tangible data bigger than normal or less than normal, adopt the method for directly removing burr to proofread and correct;
Step (3) utilization grey correlation calculates each upstream pumping unit draining delay time, and concrete grammar is:
A, the sewage lifting capacity data of collecting conflux node pumping plant sewage inflow and each upstream pumping unit;
B, set up reference time sequence and comparison time series, the node pumping plant inflow time series of selecting to conflux is reference time sequence Y
0, Y
0=[Y
0(1), Y
0(2) ..., Y
0(n)]; The last period of corresponding time of each upstream pumping unit, corresponding time, preceding two periods of corresponding time ... the sewage lifting capacity time series of preceding n the period of corresponding time is for comparing time series X
i, X
i=[X
i(1), X
i(2) ..., X
i(n)], i=1 wherein, 2 ..., N, N represent comparison seasonal effect in time series number;
C, calculate the relatively grey incidence coefficient between the time series of reference time sequence and each respectively;
D, calculate the relatively grey speed interconnection degree between the time series of reference time sequence and each respectively;
E, determining each upstream pumping unit draining delay time, specifically is the value of each grey speed interconnection degree of obtaining among the comparison step d, determine the grey speed interconnection degree maximum the value correspondence forward the time hop count be the upstream pumping unit draining delay time;
Step (4) is carried out normalized to input variable, is converted into the value of [0,1] interval range
Step (5) is built the BP neural network framework;
The newff function that calls in the Matlab7.1 Neural Network Toolbox is set up the BP neural network, Net=newff (PR, [s
1, s
2..., s
i], { TF
1, TF
2..., TF
i, BTF, BLF, PF); Net is the BP neural network framework, and PR is the span that is determined by greatest member and least member in the input matrix, s
iBe the neuronic number of i layer, TF
iBe the transport function of i layer, 1≤i≤N
1, N
1Be the total number of plies of neural network, BTF is the training function of BP neural network, and BLF is the parameter of control weights and threshold value, and PF is the network performance function;
Step (6) training BP neural network, concrete grammar is:
I, initialization BP neural network, the value assignment of utilizing random function to produce is given weights and bias, calls the init function then and comes the whole neural network of initialization;
Ii, network training number of times and training objective error are set, show the training step number;
Iii, training data is set is input matrix P, and it is matrix T that desired value is set, and the train function that calls in the Matlab7.1 Neural Network Toolbox carries out the data training until convergence to BP neural network Net, Net=train (Net, P, T), wherein P is a trained values, and T is a desired value;
Step (7) test b P neural network;
The BP neural network that trains is tested, historical data is formed pumping plant forebay water level forecast network test matrix P_test, directly call the sim function in the Matlab7.1 Neural Network Toolbox, (Net P_test), carries out emulation to the test input to D=sim, wherein D is an objective function, Net is the BP neural network that trains, and D is a desired value, and P_test is a test sample book;
The anti-normalized of step (8) data;
To the test gained sewage pumping station forebay waterlevel data according to formula
Carry out anti-normalized, wherein x ' is a pumping plant forebay waterlevel data final after the anti-normalized,
Be the pumping plant forebay waterlevel data that emulation testing obtains, x
MaxBe the maximal value in the waterlevel data of pumping plant forebay, x
MinBe the minimum value in the waterlevel data of pumping plant forebay.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105907498A CN102032935B (en) | 2010-12-07 | 2010-12-07 | Soft measurement method for sewage pumping station flow of urban drainage converged network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105907498A CN102032935B (en) | 2010-12-07 | 2010-12-07 | Soft measurement method for sewage pumping station flow of urban drainage converged network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102032935A true CN102032935A (en) | 2011-04-27 |
| CN102032935B CN102032935B (en) | 2012-01-11 |
Family
ID=43886130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010105907498A Active CN102032935B (en) | 2010-12-07 | 2010-12-07 | Soft measurement method for sewage pumping station flow of urban drainage converged network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102032935B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102395135A (en) * | 2011-10-25 | 2012-03-28 | 江苏省邮电规划设计院有限责任公司 | VLR (Visitor Location Register) user number predicting method based on gray system model neural network |
| CN103258243A (en) * | 2013-04-27 | 2013-08-21 | 杭州电子科技大学 | Tube explosion predicting method based on grey neural network |
| CN103487096A (en) * | 2013-09-10 | 2014-01-01 | 温州大学 | Detection method of small flow based on gray correlation method |
| CN103592962A (en) * | 2013-10-23 | 2014-02-19 | 华南理工大学 | Method for effectively controlling sewage net pipe reagent quantity by predicting pump station flow |
| CN104964719A (en) * | 2015-06-30 | 2015-10-07 | 安徽工业大学 | Household electronic water meter flow metering method based on BP neural network |
| CN105975799A (en) * | 2016-06-01 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Method and system for calculating carbon emissions |
| CN103258243B (en) * | 2013-04-27 | 2016-11-30 | 杭州电子科技大学 | Tube explosion prediction method based on grey neural network |
| CN106777557A (en) * | 2016-11-29 | 2017-05-31 | 中国农业大学 | A kind of determination method of pumping plant approach channel and forebay water body carrying rate |
| CN106777558A (en) * | 2016-11-29 | 2017-05-31 | 中国农业大学 | A kind of determination method of pumping plant approach channel and forebay water body silt reference concentration |
| CN106789297A (en) * | 2016-12-29 | 2017-05-31 | 淮海工学院 | Predicting network flow system and its method for predicting based on neutral net |
| CN108536106A (en) * | 2018-04-25 | 2018-09-14 | 重庆工商大学 | A kind of aerating system dissolved oxygen based on Kalman filtering-extreme learning machine regulates and controls method online |
| CN111798108A (en) * | 2020-06-18 | 2020-10-20 | 浙江浙大中控信息技术有限公司 | Cooperative scheduling method for urban drainage area |
| CN112639829A (en) * | 2018-05-25 | 2021-04-09 | 约翰内斯堡大学 | System and method for real-time prediction of dam water level and hazard level |
| CN113139700A (en) * | 2020-11-30 | 2021-07-20 | 中科三清科技有限公司 | River flow prediction method, device, equipment and storage medium |
| WO2021249115A1 (en) * | 2020-06-08 | 2021-12-16 | International Business Machines Corporation | Generating a hybrid sensor to compensate for intrusive sampling |
| WO2022036820A1 (en) * | 2020-08-18 | 2022-02-24 | 浙江大学 | Sewage pipe network real-time simulation method based on water supply internet of things data assimilation |
| CN115271186A (en) * | 2022-07-18 | 2022-11-01 | 福建中锐网络股份有限公司 | Reservoir water level prediction early warning method based on delay factor and PSO RNN Attention model |
| CN116502809A (en) * | 2023-06-27 | 2023-07-28 | 中国市政工程华北设计研究总院有限公司 | Method for predicting sewage quantity during drainage household based on big position data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH03274031A (en) * | 1990-03-23 | 1991-12-05 | Mitsubishi Electric Corp | Neural network system predicting device for river water volume |
| EP1299697A2 (en) * | 2000-07-13 | 2003-04-09 | Simmonds Precision Products, Inc. | Liquid gauging apparatus using a time delay neural network |
| CN1760912A (en) * | 2005-11-11 | 2006-04-19 | 杭州电子科技大学 | Modeling method of uncertain hydraulics model for urban seweage and drainage system |
| CN101625733A (en) * | 2009-08-03 | 2010-01-13 | 杭州电子科技大学 | Tidewater water level and time forecasting method based on neural network |
| CN101807045A (en) * | 2010-04-02 | 2010-08-18 | 杭州电子科技大学 | Data-based urban sewage pumping station system modeling method |
| CN101819407A (en) * | 2010-04-02 | 2010-09-01 | 杭州电子科技大学 | Sewage pump station water level prediction method base on neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3274031B2 (en) * | 1993-10-13 | 2002-04-15 | キヤノン株式会社 | Ink jet head and ink jet device provided with the ink jet head |
-
2010
- 2010-12-07 CN CN2010105907498A patent/CN102032935B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH03274031A (en) * | 1990-03-23 | 1991-12-05 | Mitsubishi Electric Corp | Neural network system predicting device for river water volume |
| EP1299697A2 (en) * | 2000-07-13 | 2003-04-09 | Simmonds Precision Products, Inc. | Liquid gauging apparatus using a time delay neural network |
| CN1760912A (en) * | 2005-11-11 | 2006-04-19 | 杭州电子科技大学 | Modeling method of uncertain hydraulics model for urban seweage and drainage system |
| CN101625733A (en) * | 2009-08-03 | 2010-01-13 | 杭州电子科技大学 | Tidewater water level and time forecasting method based on neural network |
| CN101807045A (en) * | 2010-04-02 | 2010-08-18 | 杭州电子科技大学 | Data-based urban sewage pumping station system modeling method |
| CN101819407A (en) * | 2010-04-02 | 2010-09-01 | 杭州电子科技大学 | Sewage pump station water level prediction method base on neural network |
Non-Patent Citations (1)
| Title |
|---|
| 《给水排水》 20041010 刘兴坡等 污水管网模拟模型节点平均流量的估算方法 102-106页 1 , 第10期 2 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102395135A (en) * | 2011-10-25 | 2012-03-28 | 江苏省邮电规划设计院有限责任公司 | VLR (Visitor Location Register) user number predicting method based on gray system model neural network |
| CN102395135B (en) * | 2011-10-25 | 2014-02-19 | 江苏省邮电规划设计院有限责任公司 | VLR (Visitor Location Register) user number predicting method based on gray system model neural network |
| CN103258243A (en) * | 2013-04-27 | 2013-08-21 | 杭州电子科技大学 | Tube explosion predicting method based on grey neural network |
| CN103258243B (en) * | 2013-04-27 | 2016-11-30 | 杭州电子科技大学 | Tube explosion prediction method based on grey neural network |
| CN103487096A (en) * | 2013-09-10 | 2014-01-01 | 温州大学 | Detection method of small flow based on gray correlation method |
| CN103487096B (en) * | 2013-09-10 | 2016-01-20 | 温州大学 | A kind of detection method of small flow based on Grey Incidence |
| CN103592962A (en) * | 2013-10-23 | 2014-02-19 | 华南理工大学 | Method for effectively controlling sewage net pipe reagent quantity by predicting pump station flow |
| CN103592962B (en) * | 2013-10-23 | 2016-05-04 | 华南理工大学 | Realize by prediction pumping plant flow the method that sewage webmaster dosage is effectively controlled |
| CN104964719A (en) * | 2015-06-30 | 2015-10-07 | 安徽工业大学 | Household electronic water meter flow metering method based on BP neural network |
| CN105975799A (en) * | 2016-06-01 | 2016-09-28 | 广东电网有限责任公司电力科学研究院 | Method and system for calculating carbon emissions |
| CN106777558B (en) * | 2016-11-29 | 2019-08-09 | 中国农业大学 | A kind of determination method of pumping plant approach channel and forebay water body silt reference concentration |
| CN106777557B (en) * | 2016-11-29 | 2019-08-09 | 中国农业大学 | A kind of determination method of pumping plant approach channel and forebay water body carrying rate |
| CN106777558A (en) * | 2016-11-29 | 2017-05-31 | 中国农业大学 | A kind of determination method of pumping plant approach channel and forebay water body silt reference concentration |
| CN106777557A (en) * | 2016-11-29 | 2017-05-31 | 中国农业大学 | A kind of determination method of pumping plant approach channel and forebay water body carrying rate |
| CN106789297A (en) * | 2016-12-29 | 2017-05-31 | 淮海工学院 | Predicting network flow system and its method for predicting based on neutral net |
| CN108536106B (en) * | 2018-04-25 | 2021-07-30 | 重庆工商大学 | Aeration system dissolved oxygen online regulation and control method based on Kalman filtering-extreme learning machine |
| CN108536106A (en) * | 2018-04-25 | 2018-09-14 | 重庆工商大学 | A kind of aerating system dissolved oxygen based on Kalman filtering-extreme learning machine regulates and controls method online |
| CN112639829A (en) * | 2018-05-25 | 2021-04-09 | 约翰内斯堡大学 | System and method for real-time prediction of dam water level and hazard level |
| GB2612470A (en) * | 2020-06-08 | 2023-05-03 | Ibm | Generating a hybrid sensor to compensate for intrusive sampling |
| WO2021249115A1 (en) * | 2020-06-08 | 2021-12-16 | International Business Machines Corporation | Generating a hybrid sensor to compensate for intrusive sampling |
| US11422545B2 (en) | 2020-06-08 | 2022-08-23 | International Business Machines Corporation | Generating a hybrid sensor to compensate for intrusive sampling |
| CN111798108A (en) * | 2020-06-18 | 2020-10-20 | 浙江浙大中控信息技术有限公司 | Cooperative scheduling method for urban drainage area |
| CN111798108B (en) * | 2020-06-18 | 2024-02-09 | 浙江中控信息产业股份有限公司 | Urban drainage area cooperative scheduling method |
| WO2022036820A1 (en) * | 2020-08-18 | 2022-02-24 | 浙江大学 | Sewage pipe network real-time simulation method based on water supply internet of things data assimilation |
| CN113139700A (en) * | 2020-11-30 | 2021-07-20 | 中科三清科技有限公司 | River flow prediction method, device, equipment and storage medium |
| CN113139700B (en) * | 2020-11-30 | 2022-03-11 | 中科三清科技有限公司 | River flow prediction method, device, equipment and storage medium |
| CN115271186A (en) * | 2022-07-18 | 2022-11-01 | 福建中锐网络股份有限公司 | Reservoir water level prediction early warning method based on delay factor and PSO RNN Attention model |
| CN115271186B (en) * | 2022-07-18 | 2024-03-15 | 福建中锐网络股份有限公司 | Reservoir water level prediction and early warning method based on delay factor and PSO RNN Attention model |
| CN116502809A (en) * | 2023-06-27 | 2023-07-28 | 中国市政工程华北设计研究总院有限公司 | Method for predicting sewage quantity during drainage household based on big position data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102032935B (en) | 2012-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102032935B (en) | Soft measurement method for sewage pumping station flow of urban drainage converged network | |
| CN101819407B (en) | Sewage pump station water level prediction method base on neural network | |
| CN101807045B (en) | Data-based urban sewage pumping station system modeling method | |
| CN105243502B (en) | A kind of power station schedule risk appraisal procedure based on runoff interval prediction and system | |
| CN107818395B (en) | Electric energy meter error iterative calculation method based on measurement uncertainty | |
| CN104715292A (en) | City short-term water consumption prediction method based on least square support vector machine model | |
| CN107992961A (en) | A kind of adaptive basin Medium-and Long-Term Runoff Forecasting model framework method | |
| CN103810532B (en) | The method of Optimizing City drainage system operation conditions | |
| CN103729550A (en) | Multi-model integrated flood forecasting method based on propagation time clustering analysis | |
| CN109948863A (en) | Drainage pipeline networks inspection shaft liquid level prediction technique based on shot and long term memory models LSTM | |
| CN113256005A (en) | Power station water level process prediction method and device based on neural network model | |
| CN113343595B (en) | Inversion model of open channel water delivery system accident and method for determining accident flow and position | |
| CN104463358A (en) | Small hydropower station power generation capacity predicating method combining coupling partial mutual information and CFS ensemble forecast | |
| Boukhanovsky et al. | Urgent computing for operational storm surge forecasting in Saint-Petersburg | |
| CN113762618A (en) | Lake water level forecasting method based on multi-factor similarity analysis | |
| Vafakhah et al. | Application of intelligent technology in rainfall analysis | |
| CN108615098A (en) | Water supply network pipeline burst Risk Forecast Method based on Bayesian survival analysis | |
| CN114936505A (en) | Method for rapidly forecasting multi-point water depth of urban rainwater well | |
| JP4146053B2 (en) | Flow prediction method in dam or river | |
| CN114462688A (en) | Tube explosion detection method based on LSTM model and dynamic threshold determination algorithm | |
| CN117648878A (en) | Flood rapid evolution and flooding simulation method based on 1D-CNN algorithm | |
| CN109376937A (en) | Adaptive scheduling end of term water level prediction method based on set empirical mode decomposition | |
| CN111553226B (en) | Method for extracting river monitoring section water surface width based on remote sensing interpretation technology | |
| CN115470965B (en) | Method for rapidly determining and predicting tide branch estuary branch channel falling tide split ratio based on radial tide countermeasure mode | |
| CN113343439B (en) | Accident identification method for open channel water delivery system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190122 Address after: 310053 23-25, 2 building, 352 BINKANG Road, Binjiang District, Hangzhou, Zhejiang. Patentee after: Zhejiang SUPCON Information Co., Ltd. Address before: 310018 2 street, Xiasha Higher Education Park, Hangzhou, Zhejiang Patentee before: Hangzhou Electronic Science and Technology Univ |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 310053 23-25, 2 building, 352 BINKANG Road, Binjiang District, Hangzhou, Zhejiang. Patentee after: Zhejiang zhongkong Information Industry Co.,Ltd. Address before: 310053 23-25, 2 building, 352 BINKANG Road, Binjiang District, Hangzhou, Zhejiang. Patentee before: ZHEJIANG SUPCON INFORMATION TECHNOLOGY Co.,Ltd. |