CN111062476A - Water quality prediction method based on gated circulation unit network integration - Google Patents
Water quality prediction method based on gated circulation unit network integration Download PDFInfo
- Publication number
- CN111062476A CN111062476A CN201911241122.9A CN201911241122A CN111062476A CN 111062476 A CN111062476 A CN 111062476A CN 201911241122 A CN201911241122 A CN 201911241122A CN 111062476 A CN111062476 A CN 111062476A
- Authority
- CN
- China
- Prior art keywords
- water quality
- gru
- model
- prediction
- data
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000010354 integration Effects 0.000 title claims description 15
- 230000000694 effects Effects 0.000 claims abstract description 8
- 238000012935 Averaging Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 125000004122 cyclic group Chemical group 0.000 claims abstract 7
- 238000012549 training Methods 0.000 claims description 20
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 241000288105 Grus Species 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 239000010865 sewage Substances 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 abstract description 13
- 238000003911 water pollution Methods 0.000 abstract description 5
- 230000002265 prevention Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 abstract description 2
- 238000013461 design Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 230000004913 activation Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention designs a high-precision prediction algorithm aiming at the current situation that the pollution accident is caused by the fact that the water quality change is difficult to predict. The algorithm innovatively applies the integrated gating circulation unit to process the time sequence data of the historical water quality indexes, so that the water quality is predicted and analyzed. The algorithm is built by a Keras tool of PYTHON3.6.5, and comprises integrating a network of five gated cyclic units and integrating the five gated cyclic units by using an averaging method. And the time sequence data of a plurality of water quality indexes are used as the input of an algorithm, and finally the water quality effect with high accuracy is obtained. The algorithm provides a new solution for water quality prediction, can provide reliable evaluation and early warning for water pollution prevention and treatment, and is further widely applied to the field of water quality prediction.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to a water quality prediction method based on gated cycle unit network integration, and belongs to the field of water environment detection.
[ background of the invention ]
Water is a source of life and is a necessary condition for living and economic development of organisms. At present, nearly half of 666 cities in China have water shortage. What is worse, under the condition of such lack of water resources, under the influence of rapid development of industrialized process in China and reduction of river self-cleaning capability, more than 70% of river reach of seven water systems in China are polluted, and about 90% of urban water areas are seriously polluted. The problem of water pollution becomes one of the most important restriction factors for the development of the economic society of China, and the prevention and the treatment of the water pollution are highly valued by national and local governments. According to the historical data of water quality monitoring, a water quality prediction model is established, and the component change and the future development trend of pollutants in the water body are accurately predicted, so that information and technical support are provided for water pollution control and treatment, and a reliable basis is provided for concrete implementation measures of water environment protection. The establishment of a limited and reliable water quality prediction model can convert post treatment into pre-prevention, and is a hotspot of research in the field of water environment science in recent years.
Due to the diversity and complexity of water quality components, the water quality indexes directly and often have a high nonlinear relation, and a traditional linear method is difficult to establish an accurate water quality prediction model. At present, a typical water quality simulation model is researched by mainly using a MIKE21 hydraulic water quality model, an EFDC hydrodynamic module, an AnnACnPS basin hydrological non-point source model and a one-dimensional random water quality degradation and two-position migration diffusion model, but the establishment of the models needs to fully consider the influence of the natural environment, needs professional personnel to evaluate, and needs to use a large amount of prior knowledge during the establishment of the models. The gating cycle unit is used as an excellent deep learning time series prediction method, and can effectively mine and utilize hidden information of a dynamic time series. In recent years, the ensemble learning has great advantages in a plurality of classification and regression tasks, and inspired by the great performance of the ensemble learning, the applicant provides a time series prediction integration method based on a gated cycle unit network to solve the problems so as to improve the prediction accuracy of the water quality.
[ summary of the invention ]
Aiming at the defects in the prior art, the invention designs a water quality prediction method based on gated circulation unit network integration. The technical system disclosed by the invention can well utilize historical water quality index data to realize the prediction of water quality indexes and realize the prevention and treatment of water pollution.
In order to realize accurate prediction of water quality, the invention provides a water quality prediction method based on gated circulation unit network integration. In order to improve the generalization ability and robustness of a single deep learning method, in the method provided by the patent, m gated cycle units (GRUs) with different hidden layer numbers and different neuron numbers are used for respectively predicting time sequence data of a water quality index so as to explore and utilize implicit information of a time sequence. And integrating the output results of the m GRUs by using an averaging method. The beneficial effects of the invention patent are required: the invention is built by a Keras tool of PYTHON3.6.5, and combines correct data acquisition and parameter optimization to effectively improve the water quality prediction precision, thereby improving the water environment protection efficiency. Fig. 1 is a flow chart of the algorithm.
The specific steps of the structure of the whole algorithm are as follows:
step 1: preprocessing is carried out after data acquisition to obtain water quality index time sequence data, and a data set is divided into a training set and a testing set;
step 2: building GRU networks with different structures;
and step 3: inputting water quality index time sequence data training data into GRUs, and training m GRU networks by using back propagation and gradient descent;
the GRU neural network is a special variant of the Recurrent Neural Network (RNN), and the GRU can dynamically model time sequence information through its unique memory and forgetting modes, thereby obtaining a better prediction effect. The GRU gate control unit network comprises a reset gate rt and an update gate zt, and the training process comprises the following steps: at each moment, the GRU unit receives current input water quality information xt and a hidden state ht-1 at the previous moment through an updating gate, and determines whether the neuron is activated or not through matrix dot product operation and an activation function sigmoid after receiving the input information. At the same time, the reset gate of the GRU receives xtAnd ht-1The operation result of the reset gate determines how much past water quality information needs to be forgotten. In addition, the water quality information input at the current moment is superposed with the output information of the reset gate through operation, and then forms the current memory content h through an activation function tanht'. Current memory ht' with the previous step input ht-1, and finally determining the output content h of the gate control unit through the dynamic control of the update gatet. The calculation formula is as follows:
zt＝σ(W(z)xt+U(z)ht-1)
rt＝σ(W(r)xt+U(r)ht-1)
ht'＝tanh(Wxt+rt·Uht-1)
ht＝zt·ht-1+(1-zt)·ht'
wherein, W(z)And U(z)Is the weight of the GRU update gate; w(r)And U(r)Is the weight of the forgotten gate; w and U are the memory weights of the current moment; σ (-) represents a sigmoid activation function; tanh (·) represents the tanh activation function; the operational symbol "·" represents the inner product form of the vector. The GRU iteratively updates all parameters by a gradient descent method, and calculates partial derivatives of all parameters based on the loss function.
And 4, step 4: building a final prediction model, and integrating the output results of the trained m GRU networks by using an averaging method;
and 5: and storing the final model, inputting the final model into a test set for recognition effect test, and using the final model for an actual water quality prediction link.
The patent uses Mean Square Error (MSE) as a loss function,
wherein y isiIs the true water quality condition, ypiIs the predicted water quality situation.
The indexes of the measurement algorithm are RMSE (root mean square error), MAPE (maximum amplitude error), average percentage error, MAE (maximum amplitude error), average absolute error and goodness of fit R2。
The inventive algorithm can effectively predict water quality, and can achieve RMSE of 0.085, MAE of 0.056, MAPE of 0.848% and R of 0.532The predicted effect of (2).
[ description of the drawings ]
FIG. 1 is a flow chart of an algorithm
FIG. 2 is a diagram of a gated cycle cell configuration
FIG. 3 is a graph of algorithm results
[ detailed description ] embodiments
Fig. 1 shows a flow chart, and the implementation of the present patent integrates GRUs with different structures of m-5, and the internal structure of the GRU is shown in fig. 2. The algorithm comprises the following specific steps:
step 1: preprocessing is carried out after data acquisition to obtain water quality index time sequence data, and a data set is divided into a training set and a testing set;
step 2: building GRU networks with different structures;
and step 3: inputting a training set, and training the five GRU networks by using back propagation and gradient descent;
and 4, step 4: building a final prediction model, and integrating the output results of the trained five GRU networks by using an averaging method;
and 5: and storing the final model, inputting the final model into a test set for recognition effect test, and using the final model for an actual water quality prediction link.
The step 1 comprises the following steps:
step 1.1: data acquisition: the implementation method of the patent comprises the following steps of: historical time sequence data of 4 typical water quality indexes at the same position, namely PH value, DO and CODMnAnd NH3N, but not limited to these four criteria;
step 1.2: data preprocessing: and (4) carrying out averaging missing value filling and standardization on the index historical time sequence data to obtain a final historical time sequence data set.
Step 1.3: data set partitioning: the historical time series data set is divided into a training set and a test set in a ratio of 8: 2.
The step 2 comprises the following steps:
building GRU networks with different structures: GRU-1 has L1 hidden layers, and each hidden layer has Na (a ═ 1, 2.., L1) neuron numbers. GRU-2 has L2 hidden layers, and each hidden layer has Nb (b ═ 1, 2.., L2) neuron numbers. GRU-3 has L3 hidden layers, each hidden layer having Nc (c ═ 1, 2.., L3) neuron numbers. GRU-4 has L4 hidden layers, each of which has Nd (d ═ 1, 2.., L4) neuron numbers. GRU-5 has L5 hidden layers, each hidden layer having Ne (b ═ 1, 2.., L5) neuron numbers.
The step 3 comprises the following steps:
step 3.1: initializing network internal parameters, and inputting a training set into 5 different GRUs in parallel for simultaneous training;
step 3.2: adjusting internal parameters of the constructed network by using back propagation and gradient descent;
step 3.3: and carrying out model convergence after N rounds of training.
Step 3.4: and storing each trained GRU model after training.
The step 4 comprises the following steps:
and directly and respectively inputting the input data of the model into each GRU, and performing mean value integration on each obtained output result to obtain the final output prediction result of the model.
The step 5 comprises the following steps:
step 5.1: inputting untrained sample data into the finally trained prediction model
Step 5.2: feeding 5 different GRU models with the data through the models respectively to obtain different prediction results;
step 5.3: after all the prediction results are averaged, comparing the average values with the actual values to obtain the final model evaluation index;
step 5.4: the final prediction model can be used in the actual water quality monitoring link.
The evaluation results of the final model are shown in table 1, and the predicted effect is shown in fig. 3, for example, in terms of pH. As can be seen from Table 1, the effect of the GRU integration method compared to the other single GRUs achieved the lowest RMSE of 0.085, the lowest MAE of 0.056, the lowest MAPE of 0.848% and the highest R of 0.532. Therefore, the algorithm in the patent has good practical prospect and generalization capability.
TABLE 1 Integrated results Table
It should be noted that the above examples are only for illustrating the water quality prediction of the present invention, and are not intended to limit the present invention. It should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention, and all such modifications and equivalents are intended to be included within the scope of the claims of the present invention.
Claims (7)
1. The water quality prediction method based on gated cycle unit network integration comprises the following steps:
step 1: preprocessing is carried out after data acquisition to obtain water quality index time sequence data, and a data set is divided into a training set and a testing set;
step 2: building GRU networks with different structures;
and step 3: inputting a training set, and training the five GRU networks by using back propagation and gradient descent;
and 4, step 4: building a final prediction model, and integrating the output results of the trained five GRU networks by using an averaging method;
and 5: and storing the final model, inputting the final model into a test set for recognition effect test, and using the final model for an actual water quality prediction link.
2. The method for integrating gated cycle unit network in water quality prediction according to claim 1, wherein the application range is as follows: rivers, lakes, reservoirs, and artificial water systems: the application of the water quality prediction system of the water supply plant and the sewage plant can effectively predict the development of water quality indexes.
3. The water quality prediction method based on gated cyclic unit network integration of claim, wherein the step 1 comprises the steps of;
step 1.1: data acquisition: the implementation method of the patent comprises the following steps of: historical time series data of 4 typical water quality indexes at the same position, namely pH value, DO and CODMn、NH3N, TN and TP, but not limited to these six criteria;
step 1.2: data preprocessing: and (4) carrying out averaging missing value filling and standardization on the index historical time sequence data to obtain a final historical time sequence data set.
Step 1.3: data set partitioning: the historical time series data set is divided into a training set and a test set in a ratio of 8: 2.
4. The water quality prediction method based on gated cyclic unit network integration of claim, wherein the step 2 comprises the steps of;
building GRU networks with different structures: GRU-1 has L1 hidden layers, and each hidden layer has Na (a ═ 1, 2.., L1) neuron numbers. GRU-2 has L2 hidden layers, and each hidden layer has Nb (b ═ 1, 2.., L2) neuron numbers. GRU-3 has L3 hidden layers, each hidden layer having Nc (c ═ 1, 2.., L3) neuron numbers. GRU-4 has L4 hidden layers, each of which has Nd (d ═ 1, 2.., L4) neuron numbers. GRU-5 has L5 hidden layers, each hidden layer having Ne (b ═ 1, 2.., L5) neuron numbers.
5. The water quality prediction method based on gated cyclic unit network integration of claim wherein the step 3 comprises the steps of;
step 3.1: initializing network internal parameters, and inputting a training set into 5 different GRUs in parallel for simultaneous training;
step 3.2: adjusting internal parameters of the constructed network by using back propagation and gradient descent;
step 3.3: and carrying out model convergence after N rounds of training.
Step 3.4: and storing each trained GRU model after training.
6. The water quality prediction method based on gated cyclic unit network integration of claim wherein the step 4 comprises the steps of;
and directly and respectively inputting the input data of the model into each GRU, and performing mean value integration on each obtained output result to obtain the final output prediction result of the model.
7. The water quality prediction method based on gated cyclic unit network integration of claim wherein the step 5 comprises the steps of;
step 5.1: inputting untrained sample data into the finally trained prediction model
Step 5.2: feeding 5 different GRU models with the data through the models respectively to obtain different prediction results;
step 5.3: and after all the prediction results are averaged, comparing the average value with the true value to obtain the final model evaluation index.
Step 5.4: the final prediction model can be used in the actual water quality monitoring link.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911241122.9A CN111062476A (en) | 2019-12-06 | 2019-12-06 | Water quality prediction method based on gated circulation unit network integration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911241122.9A CN111062476A (en) | 2019-12-06 | 2019-12-06 | Water quality prediction method based on gated circulation unit network integration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111062476A true CN111062476A (en) | 2020-04-24 |
Family
ID=70299871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911241122.9A Pending CN111062476A (en) | 2019-12-06 | 2019-12-06 | Water quality prediction method based on gated circulation unit network integration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062476A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114184750A (en) * | 2021-11-09 | 2022-03-15 | 深圳市宇驰检测技术股份有限公司 | Method, device and equipment for monitoring underground water pollutants and storage medium |
| CN116050583A (en) * | 2022-12-15 | 2023-05-02 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Water environment quality deep learning prediction method coupled with space-time context information |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108051035A (en) * | 2017-10-24 | 2018-05-18 | 清华大学 | The pipe network model recognition methods of neural network model based on gating cycle unit |
| CN108764520A (en) * | 2018-04-11 | 2018-11-06 | 杭州电子科技大学 | A kind of water quality parameter prediction technique based on multilayer circulation neural network and D-S evidence theory |
| CN109063911A (en) * | 2018-08-03 | 2018-12-21 | 天津相和电气科技有限公司 | A kind of Load aggregation body regrouping prediction method based on gating cycle unit networks |
| CN109376848A (en) * | 2018-09-01 | 2019-02-22 | 哈尔滨工程大学 | A kind of door control unit neural network of simplification |
| WO2019071384A1 (en) * | 2017-10-09 | 2019-04-18 | Bl Technologies, Inc. | Intelligent systems and methods for process and asset health diagnosis, anomoly detection and control in wastewater treatment plants or drinking water plants |
| CN109886387A (en) * | 2019-01-07 | 2019-06-14 | 北京大学 | It is a kind of that the traffic time sequence forecasting method returned is promoted based on gating network and gradient |
| CN110292380A (en) * | 2019-07-02 | 2019-10-01 | 重庆大学 | A kind of disease diagnosing system based on GRU Recognition with Recurrent Neural Network |
| CN110414742A (en) * | 2019-08-02 | 2019-11-05 | 大连海事大学 | A kind of freshwater line intelligent Forecasting of more gaging station linkages |
-
2019
- 2019-12-06 CN CN201911241122.9A patent/CN111062476A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019071384A1 (en) * | 2017-10-09 | 2019-04-18 | Bl Technologies, Inc. | Intelligent systems and methods for process and asset health diagnosis, anomoly detection and control in wastewater treatment plants or drinking water plants |
| EP3552013A1 (en) * | 2017-10-09 | 2019-10-16 | BL Technologies, Inc. | Intelligent systems and methods for process and asset health diagnosis, anomoly detection and control in wastewater treatment plants or drinking water plants |
| CN108051035A (en) * | 2017-10-24 | 2018-05-18 | 清华大学 | The pipe network model recognition methods of neural network model based on gating cycle unit |
| CN108764520A (en) * | 2018-04-11 | 2018-11-06 | 杭州电子科技大学 | A kind of water quality parameter prediction technique based on multilayer circulation neural network and D-S evidence theory |
| CN109063911A (en) * | 2018-08-03 | 2018-12-21 | 天津相和电气科技有限公司 | A kind of Load aggregation body regrouping prediction method based on gating cycle unit networks |
| CN109376848A (en) * | 2018-09-01 | 2019-02-22 | 哈尔滨工程大学 | A kind of door control unit neural network of simplification |
| CN109886387A (en) * | 2019-01-07 | 2019-06-14 | 北京大学 | It is a kind of that the traffic time sequence forecasting method returned is promoted based on gating network and gradient |
| CN110292380A (en) * | 2019-07-02 | 2019-10-01 | 重庆大学 | A kind of disease diagnosing system based on GRU Recognition with Recurrent Neural Network |
| CN110414742A (en) * | 2019-08-02 | 2019-11-05 | 大连海事大学 | A kind of freshwater line intelligent Forecasting of more gaging station linkages |
Non-Patent Citations (4)
| Title |
|---|
| BINCHUN LU: "a novel framework with high diagnostic sensitivity for lung cancer detection by electronic nose" * |
| FU，RUI: "using lstm and gru neural network methods for traffic flow prediction" * |
| 戴克慧;方颂椽;夏德祥;: "异常数据的判断和处理" * |
| 涂吉昌: "基于深度学习的水质预测模型研究" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114184750A (en) * | 2021-11-09 | 2022-03-15 | 深圳市宇驰检测技术股份有限公司 | Method, device and equipment for monitoring underground water pollutants and storage medium |
| CN116050583A (en) * | 2022-12-15 | 2023-05-02 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Water environment quality deep learning prediction method coupled with space-time context information |
| CN116050583B (en) * | 2022-12-15 | 2024-05-28 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Water environment quality deep learning prediction method coupled with space-time context information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108469507B (en) | Effluent BOD soft measurement method based on self-organizing RBF neural network | |
| CN102854296B (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
| CN111047012A (en) | Air quality prediction method based on deep bidirectional long-short term memory network | |
| CN107358021A (en) | DO prediction model establishment method based on BP neural network optimization | |
| CN111354423A (en) | Effluent ammonia nitrogen concentration prediction method of self-organizing recursive fuzzy neural network based on multivariate time series analysis | |
| CN105510546A (en) | Intelligent biochemical oxygen demand (BOD) detection method based on self-organizing recursion radial basis function (RBF) neural network | |
| CN107247888B (en) | Method for soft measurement of total phosphorus TP (thermal transfer profile) in sewage treatment effluent based on storage pool network | |
| CN111062476A (en) | Water quality prediction method based on gated circulation unit network integration | |
| CN107664682A (en) | A kind of water quality hard measurement Forecasting Methodology of ammonia nitrogen | |
| Aali et al. | Estimation of Saturation Percentage of Soil Using Multiple Regression, ANN, and ANFIS Techniques. | |
| CN114037163A (en) | Sewage treatment effluent quality early warning method based on dynamic weight PSO (particle swarm optimization) optimization BP (Back propagation) neural network | |
| CN113077039A (en) | Task-driven RBF neural network-based water outlet total nitrogen TN soft measurement method | |
| CN110929809B (en) | Sewage key water quality index soft measurement method of characteristic self-enhanced cyclic neural network | |
| CN115713448A (en) | Catchment unit-based method for quickly tracing conventional factors of basin water pollution | |
| CN114858207A (en) | Soft measurement-based gridding source tracing investigation method for drain outlet of river channel | |
| CN105160422B (en) | Sewage treatment based on self-organizing cascade neural network is discharged total phosphorus prediction technique | |
| CN103898890A (en) | Soil layer quantization layering method based on double-bridge static sounding data of BP neural network | |
| CN111738398B (en) | Novel deep feature learning method for fault diagnosis of planetary gear | |
| CN117371616A (en) | Soil frost heaving rate prediction method for optimizing generalized regression neural network | |
| CN110837886A (en) | Effluent NH4-N soft measurement method based on ELM-SL0 neural network | |
| CN107664683A (en) | A kind of water quality hard measurement Forecasting Methodology of total nitrogen | |
| CN116341705A (en) | Long-period memory network water quality parameter prediction method based on sparse label | |
| Kang et al. | Research on forecasting method for effluent ammonia nitrogen concentration based on GRA-TCN | |
| CN113657021A (en) | Marine measurement period evaluation method based on BP neural network | |
| CN107665363A (en) | A kind of water quality hard measurement Forecasting Methodology of total phosphorus |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200424 |