CN108051035B - The pipe network model recognition methods of neural network model based on gating cycle unit - Google Patents
The pipe network model recognition methods of neural network model based on gating cycle unit Download PDFInfo
- Publication number
- CN108051035B CN108051035B CN201710998436.8A CN201710998436A CN108051035B CN 108051035 B CN108051035 B CN 108051035B CN 201710998436 A CN201710998436 A CN 201710998436A CN 108051035 B CN108051035 B CN 108051035B
- Authority
- CN
- China
- Prior art keywords
- data
- network model
- training
- neural network
- water supply
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F1/00—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Abstract
The present invention provides a kind of neural network model based on gating cycle unit and its training method and applications.Wherein, the neural network model based on gating cycle unit, comprising: multiple gating cycle elementary layers are configured to receive water supply network in traffic characteristic in different time periods；First full articulamentum, composition input layer in parallel with the multiple gating cycle elementary layer, the first full articulamentum are configured to receive the Meteorological Characteristics of water supply network；The merging layer being connect with the input layer with the concatenated mode of tensor；For the second full articulamentum being connect with the merging layer with the concatenated mode of tensor to the full articulamentum of M, M is the integer more than or equal to 2；And the output layer being connect with the full articulamentum of M with the concatenated mode of tensor, it is configured to export water supply network in the predicted flow rate of subsequent time.
Description
Technical field
The present invention relates to field of neural networks, and in particular to a kind of neural network model based on gating cycle unit and its
Training method and application.
Background technique
Under the influence of pipeline aging, the factors such as Technical investment is limited, Supervision is backward, the leakage of China's public supply mains
It is more universal to damage phenomenon.Water supply network leakage loss not only has brought tremendous economic losses to Running-water Company, also results in the energy
With the waste of resource.Major part Running-water Company, China lacks scientific and effective management method, the base of pipe network for water supply network
Plinth data are also not perfect, and these problems restrict always the efficiency of management and service level of Running-water Company.Therefore, test tube is treated
Net carries out leakage loss identification, the science decision of Added Management person, in time discovery and maintenance pipe network model region, has important economy
Meaning and realistic meaning.
The model for being commonly used in identification pipe network model is broadly divided into two major classes: one kind is the physics based on laboratory test
Mechanism study model；One kind is the data mining model based on computer simulation, including statistical model, probabilistic model, engineering
Practise model etc., it usually needs a large amount of historical data.With the arriving of cloud era, big data has attracted more and more concerns,
Good achievement is achieved in numerous areas, therefore the second class model also becomes current research hotspot, especially machine
Learning model.
China's public supply mains data volume is big, and basic data is of low quality, causes the factor of pipe network model numerous and closes
System is complicated.Existing pipe network model identification model is mostly based on normal discharge or pressure of the traditional algorithm to pipe network of some classics
Power is predicted, such as multiple linear regression, exponential smoothing, backpropagation (Back Propagation, abbreviation BP) nerve
Network etc. then identifies leakage accident by comparing predicted value and actual monitoring value.These traditional prediction techniques are big in processing
Ability in terms of amount complex nonlinear data is limited, cannot preferably excavate the hidden feature between abstract data, there are pre-
The not high problem of precision is surveyed, this is but also the accuracy of leakage accident identification has no way of ensureing.
Summary of the invention
In order to save water resource, the leak rate of water supply network is reduced, economic loss is reduced, meets the reason of sustainable development
It reads, it would be desirable to which it is good to establish precision height, stability for the hidden feature that water supply network data are deeply excavated using the prior art
Model identifies pipe network model region.In view of the deficiencies of the prior art, the present invention is intended to provide it is a kind of new based on gating cycle
The neural network model and its training method of unit and application are different from the novel mind of traditional neural network model by constructing
Through network, mass data can be handled, excavate non-linear relation and Integrated Evaluation Model effect, be applied to water supply network
Leakage accident identification, can be improved the accuracy rate of leakage loss identification, so that daily management person can have found pipe network model region in time,
Economic loss is reduced, water resource is saved, auxiliary Running-water Company makes scientific and reasonable decision.
One aspect of the present invention provides a kind of neural network model based on gating cycle unit, for identification water supply network
Leakage accident, comprising:
Multiple gating cycle unit (Gated Recurrent Unit, abbreviation GRU) layers, are configured to receive water supplying pipe
Net is in traffic characteristic in different time periods；
First full articulamentum, composition input layer in parallel with the multiple gating cycle elementary layer, the described first full connection
Layer is configured to receive the Meteorological Characteristics of water supply network；
The merging layer being connect with the input layer with the concatenated mode of tensor；
The second full articulamentum connect with the merging layer with tensor concatenated mode to the full articulamentum of M, M for greater than
Or the integer equal to 2；And
The output layer being connect with the full articulamentum of M with the concatenated mode of tensor, is configured to export water supply network
In the predicted flow rate of subsequent time.
Gating cycle neural network (Gated Recurrent Unit Network, abbreviation GRUN) provided by the present invention
It is the improvement to existing Recognition with Recurrent Neural Network.The characteristics of this network, is the implicit node common using memory module replacement,
Ensure that gradient will not disappear or explode after transmitting across many time steps, to overcome conventional recycle neural metwork training
In the difficulty that encounters, the memory module that the present invention uses is gating cycle unit (GRU).Fig. 1 shows a reality of the invention
Apply the topology diagram of the neural network model based on gating cycle unit in mode.
Another aspect of the present invention provides a kind of training method of above-mentioned neural network model, including,
Construct the neural network model；
Historical traffic feature in different time periods and history Meteorological Characteristics are randomly divided into training set and verifying collection in proportion；
Historical traffic feature in different time periods in the training set is input in the multiple gating cycle elementary layer,
And the history Meteorological Characteristics in the training set are input in the described first full articulamentum, it is defeated to obtain the neural network model
Training flow out；
Historical traffic feature in different time periods is concentrated to be input in the multiple gating cycle elementary layer the verifying,
And the history Meteorological Characteristics that the verifying is concentrated are input in the described first full articulamentum, it is defeated to obtain the neural network model
Verifying flow out；
Based on the training set and training traffic generating training curve, and is collected based on the verifying and verify traffic generating and tested
Demonstrate,prove curve, when the training curve and verifying curve square mean error amount stablize in steady state value, complete the neural network mould
The training of type.
The training method has fully considered the generalization ability of the randomness of gradient descent direction and model in the training process,
Improve the convergence rate and training effectiveness of model, the effective information between abundant mining data.
In a preferred embodiment of the invention, above-mentioned training method further includes that acquisition is described in different time periods
Historical traffic feature, comprising:
Obtain the historical traffic data of water supply network to be measured；And
Processing is extracted to the historical traffic data and normalized obtains the historical traffic feature.
According to the present invention, the historical traffic data can be obtained from the independent measure region (district of Running-water Company
Metered areas, referred to as DMA) water supply network historical traffic data.
In of the invention one preferred embodiment, extracting processing to the historical traffic data includes,
In the historical traffic data of water supply network, respectively from the first time period, second time period, in the third period with etc. between
Every the data on flows for extracting specified number, wherein
First time period is chosen before closing on moment t to be predicted,
Second time period is chosen before the initial time of the first time period,
The third period is chosen before the initial time of the second time period.
According to the present invention, consider the tendency of flow-time sequence, extract the flow number for closing on moment t moment to be predicted
According to the i.e. data on flows of first time period.Consider the periodicity of flow-time sequence, extracts and be separated by one section with moment t to be predicted
The data on flows of time, it is contemplated that be daily divided into two periods, the i.e. data on flows of second time period and third period.
It is including first time period, second time period and third time in a specific embodiment of the invention
In the entire period of section, average sample is carried out with k times/h of sample frequency, then the data on flows for including in the entire period includes
The data on flows at t-24kd, t-24kd+1 ... t-2, t-1 moment, wherein d indicates number of days, when therefrom obtaining t-m to t-1
The data on flows at quarter, wherein the value range of m be 2-24 integer, preferably 5, the data on flows as first time period；It obtains
Take t-h1To t-h2The data on flows at moment, wherein h1And h2Value range be 24k-2 to 24k+20 integer, it is preferable that h1
For 24k+2, h2For 24k-2；Obtain t-h3To t-h4The data on flows at moment, wherein h3And h4Value range be 48k-2 to 48k
+ 20 integer, it is preferable that h3For 48k+2, h4For 48k-2.
Preferably, k is the integer of 1-12, preferably 3-5.
In another preferred embodiment of the invention, above-mentioned training method further includes obtaining the meteorological spy of the history
Sign, comprising:
Obtain the history meteorological data of water supply network to be measured；And
Processing is extracted to the history meteorological data and normalized obtains the history Meteorological Characteristics.
According to the present invention, the history meteorological data can be obtained from the history meteorological data of China Meteorological data network, including
Maximum temperature, minimum temperature, relative humidity, precipitation etc..
In of the invention one preferred embodiment, extracting processing to the history meteorological data includes pair
The history meteorological data and the historical traffic data carry out Pearson correlation analysis, choose related coefficient and are greater than or wait
History meteorological data in the history meteorological data of specified value V, after obtaining extraction process.
In of the invention one preferred embodiment, the specified value V is 0.80-0.99.
According to the present invention, the normalized includes the numerical value of initial data being transformed into [0,1] range, normalizing
Shown in the formula such as formula (1) for changing processing,
In formula (1), y represents the data after normalized, and x represents the initial data of input, xmaxAnd xminIt respectively represents
The maximum value and minimum value of input data.
According to the present invention, the activation primitive of each network layer selects tanh, ReLU or Linear.
Further aspect of the present invention provides a kind of recognition methods of the leakage accident of water supply network, including,
Feature extraction step obtains the different time of water supply network to be measured in the stipulated time T that leakage accident does not occur
Section reference flow feature and refer to Meteorological Characteristics；
The reference flow feature in different time periods is input to the neural network model by predicted flow rate obtaining step
Multiple gating cycle elementary layers in, and by the first full connection for being input to the neural network model with reference to Meteorological Characteristics
In layer, the predicted flow rate of the neural network model output is obtained；
Reference data set determines step, obtain the measured discharge in the stipulated time T, and every group in mutually in the same time
Predicted flow rate and measured discharge constitute a time series vector, by all time series vector structures in the stipulated time T
At matrix as reference data set；
Identification of accidental events step calculates each time sequence that newly-increased time series vector is concentrated relative to the reference data
The COS distance of column vector, the number n of time series vector of the statistics COS distance less than distance threshold D, when n is less than or equal to
When amount threshold N, the leakage accident is had occurred in determination.
According to the present invention, the newly-increased time series vector is that the period other than the stipulated time T is according to described
Feature extraction step, predicted flow rate obtaining step, reference data value determine the time series vector that step obtains.
According to the present invention, calculated by formula (2) newly-increased time series vector concentrated relative to the reference data it is every
The COS distance of a time series vector.
In formula (2), i is newly-increased time series vector, and j is the time series vector that reference data is concentrated, and ‖ i ‖ and ‖ j ‖ is
Vector field homoemorphism.
According to the present invention, the reference flow feature in different time periods of water supply network to be measured and the acquisition with reference to Meteorological Characteristics
In mode and training method above, historical traffic feature is consistent with the acquisition modes of history Meteorological Characteristics.
According to the present invention, in above-mentioned recognition methods, the time T is set as 2 days, i.e., 48 hours, sets adopting for data
Integrate frequency as k times/h (i.e. obtaining k time series vector in hour), then time series included in reference data set
The number of vector is 48k.
In another preferred embodiment of the invention, the distance threshold D is for for the reference data set
In calculate 0.1-0.5 times, preferably 0.4-0.5 times of the medians of all COS distances of all time series vectors.
Compared with existing public supply mains leakage loss recognition methods, the advantage of recognition methods of the invention is:
First, be different from traditional neural network model, the present invention multiple GRU layers and full articulamentum by parallel or
Concatenated mode connects, and forms a complicated deep neural network.GRUN has the ability of stronger processing nonlinear data,
It is stronger especially for the processing capacity of sequence data, the memory state to past data can be generated, and establish different periods
Dependence between data.Secondly, the capability of fitting of GRUN is stronger, it is easier to restrain in learning process, is not easy to fall into office
The minimum state in portion.So prediction pipe network flow that can be more accurate using GRUN improves to identify to pipe network model
The accuracy rate of pipe network model identification.
Second, the present invention uses the rejecting outliers method based on COS distance after using the accurate predicted flow rate of GRUN
Identify leakage accident, comparing the judgement of the COS distance between time series vector (being made of predicted value and measured value) by analysis is
No generation leakage accident.On the one hand, the use of COS distance eliminates pipe network monitoring data fluctuations range greatly to rejecting outliers
Caused by influence；On the other hand, remaining between multiple time series vectors compared to the absolute difference between analysis predicted value and measured value
The comparison of chordal distance avoids subjectivity when determining leakage accident, and accuracy is higher.
Detailed description of the invention
Fig. 1 is the topological structure of the neural network model based on gating cycle unit in an embodiment of the invention
Figure.
Fig. 2 is the process of neural network model of the training based on gating cycle unit in an embodiment of the invention
Figure.
Fig. 3 is the figure for indicating the mean square error of training curve and verifying curve in the embodiment of the present invention 1.
Fig. 4 is the leakage accident knowledge that water supply network is carried out using the neural network model in an embodiment of the invention
Other flow chart.
Specific embodiment
To better understand and implementing the present invention, the present invention is explained in detail below in conjunction with the drawings and specific embodiments
It states.Although it should be understood that embodiments of the present invention are illustrated, but it is clear that the present invention is not limited to above-mentioned
Embodiment can carry out various modifications within the scope of its spirit.
In the following embodiments, using 2.7 software of Python as the development platform of model, and using Numpy and
The library Pandas is read, is stored, analyzes data, the visualization of data is done using the library Matplotlib, is taken using the library Keras
Neural network model is built, development efficiency is substantially increased.
Embodiment 1 trains neural network model
1) neural network model is constructed according to Fig. 1
Input layer (the section of 3 GRU layers of setting and the first full articulamentum is made of 3 GRU layers and the first full articulamentum parallel connection
Points are respectively that 48,32,32,8, GRU layers of activation primitive is tanh and ReLU, and the activation primitive of the first full articulamentum is
ReLU)；
Make 3 GRU layers with the concatenated mode of tensor and the first full articulamentum is connect with merging (Merge) layer respectively；
Make to merge layer and the second full articulamentum, the full articulamentum of third, the 4th full articulamentum, the 5th with the concatenated mode of tensor
Full articulamentum, the 6th full articulamentum, the 7th full articulamentum connection (number of nodes of setting the second full articulamentum to the 7th full articulamentum
It is 64,32,16,8,4,2, activation primitive ReLU)；
With the concatenated mode of tensor make the 7th full articulamentum connect with output layer (the activation primitive Linear of output layer,
Learning rate is 0.02, batch_size 60).
2) training set and verifying collection are generated
2-1) to the city the CZ DMA water supply network of Running-water Company from 2 months 2016 on January 31st, 1 day 1
Data on flows is that 4 times/h carries out average sample with frequency acquisition, that is, the data on flows every 15min is obtained, to the data of acquisition
It is pre-processed: leading to the data on flows of accident including cleaning non-natural factor (third party, artificial)；Typing mistake is corrected, clearly
Wash obvious abnormal data etc..Then, first time period, second time period, the historical traffic data of third period are therefrom extracted,
And be normalized according to formula (1), obtain historical traffic feature in different time periods, wherein
The data on flows of first time period includes t-75min, t-60min, t-45min, t-30min, t-15min moment
Data on flows；
The data on flows of second time period includes t-24.5h, t-24.25h, t-24h, t-23.75h to the t-23.5h moment
Data on flows；
The data on flows of third period includes t-48.5h, t-48.25h, t-48h, t-47.75h to the t-47.5h moment
Data on flows.
2-2) from Chinese meteorological data net obtain history meteorological data, including maximum temperature, minimum temperature, relative humidity and
Precipitation pre-processes the data of acquisition: leading to the flow number of accident including cleaning non-natural factor (third party, artificial)
According to；Typing mistake is corrected, obvious abnormal data etc. is cleaned.It is subjected to Pearson with the historical traffic data in step 2-1)
Correlation analysis, discovery maximum temperature, minimum temperature and the correlation of flow are significant, and related coefficient is greater than 0.8, therefore by highest
Temperature, the normalized of minimum temperature are as a result, as history Meteorological Characteristics.
Sample needed for 2-3) modeling historical traffic feature in different time periods and history Meteorological Characteristics composition, first sample
Upset at random, sample is then divided into 10 parts, randomly selects 1 part as verifying collection, remaining 9 parts are used as training set, training set
22500 samples, verifying 2500 samples of collection.
3) training pattern
The training of neural network model is carried out according to the flow chart of Fig. 2, specifically, by the history stream of training set and verifying collection
Measure feature and history Meteorological Characteristics are inputted respectively in the input layer of neural network model, obtain the training flow and verifying stream of output
Amount.Every to complete a wheel training, the sample in training set can all be upset primary at random.
Table 1
4) model is verified
Based on the training set and training traffic generating training curve, and is collected based on the verifying and verify traffic generating and tested
Demonstrate,prove curve.As shown in figure 3, abscissa indicates the wheel number of training, each round trains iteration 375 times；Ordinate indicates training set
With the mean square error of verifying collection.As can be seen that when the mean square error of training curve and verifying curve stablizes the explanation in steady state value
Model stability, fitting preferably, are suitable for the neural network model of identification.
On the other hand, if the mean square error of two curves is not stable in steady state value, illustrate that model is unstable, fitting compared with
Difference, training data is very little or model parameter also needs to optimize.
In this example, trained obtained neural network model can be indicated illustratively are as follows:
Qt=Qt-i×W+b
In above formula, QtFor the water requirement of moment t to be predicted；
Qt-iFor the history water requirement at t-i moment, i=1,2,3 ...；
W is weight matrix；
B is bias term.
The identification of 2 leakage accident of embodiment
It is known that any leakage accident did not occurred 1 day 2 months to 10 days 2 months 2017, with 2 days -2 months on the 1st 2 months 2017
Data on flows constructs reference data set, and 3 days 2 months to 10 days 2 months 2017 leakage accidents for identification.
In order to verify recognition effect, the artificial data on flows for giving 4,5 and 6 days 2 months 2017 increases separately the DMA
Daily average water discharge (79m3/ h) 5%, 10% and 15%.
The identification of leakage accident is carried out according to flow chart shown in Fig. 4, specifically,
Step 1, obtained in the way of step 2) in embodiment 1 do not occur on 2 1st, 2017 of leakage accident-
Reference flow feature on 2 2nd, 2017 48h and refer to Meteorological Characteristics.
The reference flow feature in different time periods that step 1 obtains is input to what the training of embodiment 1 was completed by step 2
In multiple gating cycle elementary layers of neural network model, and the reference Meteorological Characteristics that step 1 obtains are input to described first
In full articulamentum, the predicted flow rate of output is obtained.
Step 3 obtains the measured discharge data on 2 2nd, 1 on the 1st 2 months 2017 48h, by each actual measurement
The predicted flow rates that the step of flow is in phase in the same time two obtains constitute a time series vectors.So, at this two days
In, 192 time series vectors (48h, frequency acquisition are 4 times/h) is constituted altogether, this 192 time series vectors are constituted
For matrix as reference data set, table 2 is the example of a part of reference data set.
Table 2
Step 4, in the way of above-mentioned steps one to step 3, by 3 days 2 months to 10 days 2 months 2017 datas on flows
Processing is 768 newly-increased time series vectors (192h, frequency acquisition are 4 times/h).
Based on formula (2), the every of the reference data concentration that each newly-increased time series vector is obtained relative to step 3 is calculated
The COS distance of a time series vector, in calculated 192 COS distances of each newly-increased time series vector institute, statistics
The number n of time series vector of the COS distance less than distance threshold D.In this example, distance threshold D is 192 COS distances
0.45 times of median, i.e., 0.00133, amount threshold N is 42.
When n is greater than amount threshold N, assert that the newly-increased time series vector is normal vector, representing the time recognizes
There is no leakage accident；When n is below amount threshold N, assert that the newly-increased time series vector is exception vector, representing should
Time recognizes leakage accident.
3 recognition result of table
For theoretically, in total 8 days 3 days 2 months to 10 days 2 months 2017 768 newly-increased time serieses, Ying You
480 normal vectors and 288 exception vectors.According to the recognition result of table 3 it is found that the neural network model of embodiment 1 can be with
It identifies the lesser leakage loss of outflow (+5% DMA daily average water discharge), but insensitive；And biggish for flow leakage loss (+10% ,+
15% DMA daily average water discharge) it may be implemented to accurately identify, accuracy rate is 85% or more.
These results suggest that the neural network model based on gating cycle unit, can accurately identify water supply
The leakage accident of pipe network, and the practicability of this method is stronger.The present invention extends grinding for existing pipe network model identification model
Study carefully content, makes scientific and reasonable decision for Running-water Company and provide a kind of new thinking.
Although the present invention has been described in detail, it will be understood by those skilled in the art that in spirit and scope of the invention
Modification will be apparent.However, it should be understood that various aspects, different specific embodiment that the present invention records
Each section and the various features enumerated can be combined or all or part of exchange.In above-mentioned each specific embodiment, that
A little embodiments with reference to another embodiment can be combined suitably with other embodiment, this is will be by this field skill
Art personnel are to understand.In addition, it will be understood to those of skill in the art that the description of front is only exemplary mode, not purport
In the limitation present invention.
Claims (9)
1. a kind of neural network model based on gating cycle unit, the leakage accident of water supply network for identification, comprising:
Multiple gating cycle elementary layers are configured to receive water supply network in traffic characteristic in different time periods；
First full articulamentum, composition input layer in parallel with the multiple gating cycle elementary layer, the first full articulamentum quilt
It is configured to receive the Meteorological Characteristics of water supply network；
The merging layer being connect with the input layer with the concatenated mode of tensor；
For the second full articulamentum being connect with the merging layer with the concatenated mode of tensor to the full articulamentum of M, M is to be greater than or wait
In 2 integer；And
The output layer being connect with the full articulamentum of M with the concatenated mode of tensor is configured to export water supply network under
The predicted flow rate at one moment.
2. a kind of training method of neural network model described in claim 1, comprising:
Construct the neural network model；
Historical traffic feature in different time periods and history Meteorological Characteristics are randomly divided into training set and verifying collection in proportion；
Historical traffic feature in different time periods in the training set is input in the multiple gating cycle elementary layer, and will
History Meteorological Characteristics in the training set are input in the described first full articulamentum, obtain the neural network model output
Training flow；
Historical traffic feature in different time periods is concentrated to be input in the multiple gating cycle elementary layer the verifying, and will
The history Meteorological Characteristics that the verifying is concentrated are input in the described first full articulamentum, obtain the neural network model output
Verify flow；
Based on the training set and training traffic generating training curve, and it is bent based on verifying collection and verifying traffic generating verifying
Line, when the training curve and verifying curve square mean error amount stablize in steady state value, complete the neural network model
Training.
3. training method according to claim 2, which is characterized in that further include obtaining the history stream in different time periods
Measure feature, comprising:
Obtain the historical traffic data of water supply network to be measured；And
Processing is extracted to the historical traffic data and normalized obtains the historical traffic feature.
4. training method according to claim 3, which is characterized in that extract processing packet to the historical traffic data
Include, in the historical traffic data of water supply network, respectively from first time period, second time period, in the third period with etc. between
Every the data on flows for extracting specified number, wherein
First time period is chosen before closing on moment t to be predicted,
Second time period is chosen before the initial time of the first time period,
The third period is chosen before the initial time of the second time period.
5. training method according to claim 3 or 4, which is characterized in that it further include obtaining the history Meteorological Characteristics, packet
It includes:
Obtain the history meteorological data of water supply network to be measured；And
Processing is extracted to the history meteorological data and normalized obtains the history Meteorological Characteristics.
6. training method according to claim 5, which is characterized in that extract processing packet to the history meteorological data
It includes: Pearson correlation analysis is carried out to the history meteorological data and the historical traffic data, choose related coefficient and be greater than
Or the history meteorological data equal to specified value, the history meteorological data after obtaining extraction process.
7. training method according to claim 6, which is characterized in that the specified value is 0.80-0.99.
8. a kind of recognition methods of the leakage accident of water supply network, including,
Feature extraction step obtains the in different time periods of water supply network to be measured within the stipulated time that leakage accident does not occur
Reference flow feature and refer to Meteorological Characteristics；
The reference flow feature in different time periods is input to nerve described in claim 1 by predicted flow rate obtaining step
In multiple gating cycle elementary layers of network model, and the of the neural network model is input to reference to Meteorological Characteristics by described
In one full articulamentum, the predicted flow rate of the neural network model output is obtained；
Reference data set determines step, obtains the measured discharge within the stipulated time, every group in prediction mutually in the same time
Flow and measured discharge constitute a time series vector, the square that all time series vectors in the stipulated time are constituted
Battle array is used as reference data set；
Identification of accidental events step, calculate each time series that newly-increased time series vector is concentrated relative to the reference data to
The COS distance of amount, statistics COS distance are less than the number of the time series vector of distance threshold, be less than when the number of statistics or
When equal to amount threshold, the leakage accident is had occurred in determination；
Wherein, the newly-increased time series vector is that the period other than the stipulated time obtains according to the feature
Step, predicted flow rate obtaining step, reference data set determine the time series vector that step obtains.
9. recognition methods according to claim 8, which is characterized in that the distance threshold is for the reference data set
In calculate 0.1-0.5 times of the medians of all COS distances of all time series vectors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710998436.8A CN108051035B (en) | 2017-10-24 | 2017-10-24 | The pipe network model recognition methods of neural network model based on gating cycle unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710998436.8A CN108051035B (en) | 2017-10-24 | 2017-10-24 | The pipe network model recognition methods of neural network model based on gating cycle unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108051035A CN108051035A (en) | 2018-05-18 |
| CN108051035B true CN108051035B (en) | 2019-08-09 |
Family
ID=62119600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710998436.8A Active CN108051035B (en) | 2017-10-24 | 2017-10-24 | The pipe network model recognition methods of neural network model based on gating cycle unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108051035B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108900446B (en) * | 2018-05-28 | 2021-03-30 | 南京信息工程大学 | Coordinate transformation normal-mode blind equalization method based on gated cyclic unit neural network |
| CN109359698B (en) * | 2018-10-30 | 2020-07-21 | 清华大学 | Leakage identification method based on long-time memory neural network model |
| CN109522716B (en) * | 2018-11-15 | 2021-02-23 | 中国人民解放军战略支援部队信息工程大学 | Network intrusion detection method and device based on time sequence neural network |
| CN110070175B (en) * | 2019-04-12 | 2021-07-02 | 北京市商汤科技开发有限公司 | Image processing method, model training method and device and electronic equipment |
| CN110599468A (en) * | 2019-08-30 | 2019-12-20 | 中国信息通信研究院 | No-reference video quality evaluation method and device |
| CN110837933A (en) * | 2019-11-11 | 2020-02-25 | 重庆远通电子技术开发有限公司 | Leakage identification method, device, equipment and storage medium based on neural network |
| CN111062476A (en) * | 2019-12-06 | 2020-04-24 | 重庆大学 | Water quality prediction method based on gated circulation unit network integration |
| CN112101400A (en) * | 2019-12-19 | 2020-12-18 | 国网江西省电力有限公司电力科学研究院 | Industrial control system abnormality detection method, equipment, server and storage medium |
| CN113280265B (en) * | 2020-02-20 | 2022-08-05 | 中国石油天然气股份有限公司 | Working condition identification method and device, computer equipment and storage medium |
| CN112118143B (en) * | 2020-11-18 | 2021-02-19 | 迈普通信技术股份有限公司 | Traffic prediction model training method, traffic prediction method, device, equipment and medium |
| CN113944888B (en) * | 2021-11-03 | 2023-12-08 | 北京软通智慧科技有限公司 | Gas pipeline leakage detection method, device, equipment and storage medium |
| CN117490002B (en) * | 2023-12-28 | 2024-03-08 | 成都同飞科技有限责任公司 | Water supply network flow prediction method and system based on flow monitoring data |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BRPI1002159A2 (en) * | 2010-04-15 | 2012-02-07 | Asel Tech Tecnologia E Automacao Ltda | integrated system with acoustic, mass balance and neural network technology for detection, localization and quantification of pipeline leaks |
| CN103530818B (en) * | 2013-10-12 | 2016-06-01 | 杭州电子科技大学 | A kind of water supply network modeling method based on BRB system |
| CN104061445B (en) * | 2014-07-09 | 2017-07-28 | 中国石油大学(华东) | A kind of pipeline leakage detection method based on neutral net |
| CN105221933A (en) * | 2015-08-24 | 2016-01-06 | 哈尔滨工业大学 | A kind of pipeline network leak detecting method in conjunction with resistance identification |
| CN106022518B (en) * | 2016-05-17 | 2019-10-18 | 清华大学 | A kind of piping failure probability forecasting method based on BP neural network |
| CN206130547U (en) * | 2016-07-07 | 2017-04-26 | 北京信息科技大学 | Gas transmission pipeline leak testing system under multiplex condition |
| CN106287239A (en) * | 2016-08-16 | 2017-01-04 | 浙江大学 | Ball device and method is detected in the intelligence pipe of public supply mains leakage location |
| CN106352244A (en) * | 2016-08-31 | 2017-01-25 | 中国石油化工股份有限公司 | Pipeline leakage detection method based on hierarchical neural network |
| CN107013812B (en) * | 2017-05-05 | 2019-07-12 | 西安科技大学 | A kind of THM coupling line leakage method |
| CN107239859B (en) * | 2017-06-05 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | Heating load forecasting method based on series connection shot and long term memory Recognition with Recurrent Neural Network |
-
2017
- 2017-10-24 CN CN201710998436.8A patent/CN108051035B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108051035A (en) | 2018-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108051035B (en) | The pipe network model recognition methods of neural network model based on gating cycle unit | |
| Li et al. | Predicting short-term electricity demand by combining the advantages of arma and xgboost in fog computing environment | |
| CN103476051B (en) | A kind of communication net node importance evaluation method | |
| CN109523021B (en) | Dynamic network structure prediction method based on long-time and short-time memory network | |
| CN110210686A (en) | A kind of electricity charge risk model construction method of electric power big data | |
| CN109630095B (en) | A kind of rod-pumped well operating mode's switch method and system based on multi-angle of view study | |
| CN110458230A (en) | A kind of distribution transforming based on the fusion of more criterions is with adopting data exception discriminating method | |
| CN101478534B (en) | Network exception detecting method based on artificial immunity principle | |
| CA2392063A1 (en) | Method and program for simulating a physical system using object-oriented programming | |
| CN104881735A (en) | System and method of smart power grid big data mining for supporting smart city operation management | |
| CN108197425B (en) | A kind of smart grid data resolving method based on Non-negative Matrix Factorization | |
| CN104036364A (en) | Evaluation method for network structure level of power distribution network | |
| Liu et al. | A systems dynamic model of a coal-based city with multiple adaptive scenarios: A case study of Ordos, China | |
| CN109840691A (en) | Non-intrusion type subitem electricity estimation method based on deep neural network | |
| CN109872247A (en) | A kind of pump group fit method of characteristics curve | |
| CN105825430A (en) | Heterogeneous social network-based detection method | |
| CN106296315A (en) | Context aware systems based on user power utilization data | |
| CN110110907A (en) | A kind of extracting method of low-voltage platform area characteristic parameter | |
| CN103617563B (en) | A kind of water supply network theoretical based on geo-statistic spatial analysis is without monitoring node pressure determination statement | |
| CN110263945A (en) | Based on markovian Line Loss of Distribution Network System processing system | |
| CN105406461A (en) | Adaptive dynamic load monitoring method for power distribution network power failure events | |
| CN109921426A (en) | Wind-electricity integration system probability load flow calculation method based on CV-KDE | |
| CN111199298A (en) | Flood forecasting method and system based on neural network | |
| CN108038734A (en) | City commercial facility space distribution detection method and system based on comment data | |
| CN114240041A (en) | Lean line loss analysis method and system for distribution network distribution area |
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 |