CN111178602A - Circulating water loss prediction method based on support vector machine and neural network - Google Patents
Circulating water loss prediction method based on support vector machine and neural network Download PDFInfo
- Publication number
- CN111178602A CN111178602A CN201911310829.0A CN201911310829A CN111178602A CN 111178602 A CN111178602 A CN 111178602A CN 201911310829 A CN201911310829 A CN 201911310829A CN 111178602 A CN111178602 A CN 111178602A
- Authority
- CN
- China
- Prior art keywords
- neural network
- circulating water
- predicting
- water loss
- vector machine
- 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 83
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 48
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001704 evaporation Methods 0.000 claims abstract description 22
- 230000008020 evaporation Effects 0.000 claims abstract description 22
- 238000010977 unit operation Methods 0.000 claims abstract description 22
- 238000007664 blowing Methods 0.000 claims abstract description 21
- 238000004088 simulation Methods 0.000 claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 239000000498 cooling water Substances 0.000 abstract description 7
- 238000001816 cooling Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- 238000004065 wastewater treatment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas 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
Abstract
The invention relates to a circulating water loss prediction method based on a support vector machine and a neural network, which comprises the following steps: predicting the circulating water loss based on BP neural network modeling and predicting the circulating water loss based on support vector machine modeling; the method for predicting the circulating water loss based on the BP neural network modeling comprises the following steps: acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant; based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a BP neural network, and establishing a BP neural network simulation prediction model by taking total evaporation loss and wind blowing loss as output variables; and predicting the circulating water loss according to the established BP neural network simulation prediction model. The method can ensure the accuracy of prediction and provide powerful support for the intelligent monitoring of a subsequent circulating cooling water system and the scheduling and control of water taking and draining.
Description
Technical Field
The invention belongs to the technical field of thermal power generation, and particularly relates to a circulating water loss prediction method based on a support vector machine and a neural network.
Background
With the stricter and stricter national restrictions on the indexes of water taking and discharging amount and water discharging quality of thermal power enterprises, the thermal power enterprises are forced to accelerate the development of deep water saving and comprehensive wastewater treatment. For a thermal power plant utilizing circulating cooling water, the circulating cooling water system is the system with the largest water consumption, and can account for 70% -90% of the total water consumption of the whole plant, and the water consumption accounts for 50-60% of the water consumption of the whole plant.
The water loss of the circulating water system mainly comprises evaporation loss, air blowing loss and pollution discharge loss, wherein the evaporation loss accounts for 30-50% of the total water consumption of the circulating water system, and the air blowing loss is about 0.1-0.5% of the total amount of circulating water. Evaporation loss and blowing loss can result in excessive ion concentration in the circulating water and corrosion of pipeline equipment. Therefore, in order to ensure the safe operation of the equipment, part of water needs to be discharged outwards periodically (namely, pollution discharge loss), and new water needs to be supplemented to ensure that the ion concentration in the water is maintained within an acceptable range of the pipeline equipment. Therefore, the evaporation loss and the wind blowing loss are accurately calculated, the pollution discharge loss is calculated by combining the ion concentration, the water supplement amount of the circulating water can be obviously saved, and the method has important significance for the efficient and stable operation of a circulating water sewage treatment system and the water saving and consumption reduction of a power plant.
The evaporation loss and the blowing loss of the circulating water system are influenced by a plurality of factors such as the temperature of the inlet tower, the humidity of the inlet and the outlet, the operation load of a unit, the inlet air quantity and the like, and meanwhile, the parameters have a complex coupling relation, so that the water loss cannot be intuitively judged. In the actual operation process of a thermal power plant, the evaporation loss of a circulating water system is estimated by a formula method, the blowing loss is limited to be 0.05% -0.1% of the total amount of circulating water, obviously, the water taking amount cannot be accurately judged, and the calculation method has hysteresis.
Disclosure of Invention
The invention aims to provide a circulating water loss prediction method based on a support vector machine and a neural network, and the accuracy of prediction is improved.
The invention provides a circulating water loss prediction method based on a support vector machine and a neural network, which comprises the following steps: predicting the circulating water loss based on BP neural network modeling and predicting the circulating water loss based on support vector machine modeling;
the predicting of the circulating water loss based on the BP neural network modeling comprises the following steps:
1) acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant;
2) based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a BP neural network, and establishing a BP neural network simulation prediction model by taking total evaporation loss and wind blowing loss as output variables;
3) predicting the circulating water loss according to the established BP neural network simulation prediction model;
the predicting of the circulating water loss based on the modeling of the support vector machine comprises the following steps:
(1) acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant;
(2) based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a support vector machine, and establishing a support vector machine simulation prediction model by taking total evaporation loss and wind blowing loss as output variables;
(3) and predicting the circulating water loss according to the established support vector machine simulation prediction model.
Further, the step 2) of predicting the circulating water loss based on the BP neural network modeling comprises:
and (3) performing model training by using the R language, and adjusting the model calculation speed, the number of nodes and the number of hidden layers by a trial and error method to obtain an optimal BP neural network simulation prediction model.
Further, the step (2) of predicting the circulating water loss based on the support vector machine modeling comprises:
and selecting a radial basis function as a kernel function, and selecting a penalty coefficient with the minimum mean square error and the model complexity as model parameters by adopting a cross verification method.
By means of the scheme, the method for predicting the circulating water loss based on the support vector machine and the neural network can guarantee the accuracy of prediction, and can provide powerful support for the intelligent monitoring of a subsequent circulating cooling water system and the scheduling and control of water taking and draining.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
FIG. 1 is a schematic diagram of a BP neural network employed in the present invention;
fig. 2 is a schematic diagram of the support vector machine employed in the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The embodiment provides a circulating water loss prediction method based on a support vector machine and a neural network, which comprises the following steps: predicting the circulating water loss based on BP neural network modeling and predicting the circulating water loss based on support vector machine modeling;
the predicting of the circulating water loss based on the BP neural network modeling comprises the following steps:
1) acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant;
2) based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a BP neural network, and establishing a BP neural network simulation prediction model by taking total evaporation loss and wind blowing loss as output variables;
3) predicting the circulating water loss according to the established BP neural network simulation prediction model;
the predicting of the circulating water loss based on the modeling of the support vector machine comprises the following steps:
(1) acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant;
(2) based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a support vector machine, and establishing a support vector machine simulation prediction model by taking total evaporation loss and wind blowing loss as output variables;
(3) and predicting the circulating water loss according to the established support vector machine simulation prediction model.
Through the circulating water loss prediction method based on the support vector machine and the neural network, the accuracy of prediction can be ensured, and powerful support can be provided for the intelligent monitoring of a subsequent circulating cooling water system and the scheduling and control of water taking and draining.
The present invention is described in further detail below.
1. Data source
The data of the embodiment is taken from a certain 2X 300MW coal-fired unit in a certain northern province, a cooling water system adopts a secondary circulating water supply system with a counter-flow natural ventilation cooling tower, the unit No. 1 is put into production in 6 months in 2003, and the unit No. 2 is put into production in 7 months in 2003. The average temperature of the air is 9.2 ℃ for years, the average relative humidity of the air is 47% for years, the extreme maximum temperature is 40.9 ℃, and the extreme minimum temperature is-26.2 ℃. In summer or when the unit runs at high load, each unit is provided with two water pumps which are connected in parallel at high speed to transport a cooling tower; in winter or when the units run at low load, each unit is matched with a water pump to run at low speed.
Carrying out a water balance test on the power plant, drawing a full-field water balance diagram, and obtaining according to a test result: the total amount of evaporation loss and wind blowing loss can be obtained according to the water replenishing quantity, the sewage discharge quantity, the water loss quantity of a circulating cooling water cooling user and the liquid level change of a cooling tower water pool of the power plant, and the calculation formula is as follows:
Qe+Qw＝Qf-Qb-Qm-H×3.14×40.4162(1)
in the formula: qe-loss of evaporation, t/h; qw-loss of blowing, t/h; qf-amount of make-up water, t/h; qb-loss of blowdown, t/h; qm-cooling the user lost water, t/h; h-height of liquid level drop, m.
2. Data processing
The method comprises the steps of collecting operation data from 8/month 1 in 2017 to 7/month 31 in 2018 through a thermal power plant System (SIS for short), carrying out data cleaning by using an R language at a sampling time interval of one hour, screening unit shutdown and abnormal data, and finally screening 4637 groups of representative data. Considering that the operating conditions of the circulating water systems in winter and summer are different and the evaporation loss difference is large, the simulation prediction model is established by respectively utilizing the data in winter and summer. According to the data acquisition condition and the mechanism analysis of evaporation and blowing loss, the inlet and outlet temperature, the unit operation load, the vacuum degree, the condensate flow and the environment temperature are selected as modeling input variables, and the total amount of evaporation loss and blowing loss of the two machines is used as an output variable. As the result accuracy is influenced by the mutual correlation of all parameters, Principal Component Analysis (PCA) is carried out by using a 'Principal Component Analysis' function in an R language 'psych' packet, the dimension of input data is reduced, Principal components with high contribution rate are selected as input variables, and the total amount of evaporation and blowing loss of the two machines is used as output variables. Meanwhile, in order to eliminate the influence of the dimension between the variables, the embodiment applies normalization processing to the data, and the algorithm is shown in formula (2). And finally, randomly selecting 80% of valid data for model training, and using the rest 20% of valid data for model verification.
3. BP neural network modeling
The BP neural network is an operational model formed by a large number of neurons (nodes) and correlations among the neurons (nodes), and is a multi-layer feedforward neural network trained according to an error back propagation algorithm, and the network structure of the BP neural network is shown in fig. 1. The signal is transmitted from the input layer, and then transmitted to the output layer after being calculated by the hidden layer. And when the output value is not consistent with the expected value, entering a reverse propagation stage, taking the error as a calculation basis of the weight in the reverse correction process, feeding back to the input layer by layer through the hidden layer, and distributing the error to each unit. Thus, the budget speed and accuracy of the model is related to the number of nodes and the number of hidden layers.
In the embodiment, 8 main components are obtained through main component analysis and serve as BP neural network input variables, and the total amount of evaporation and wind blowing loss serves as output variables. And training the model by using the R language neultral packet, and adjusting the model calculation speed, the number of nodes and the number of hidden layers by a trial and error method to obtain the optimal BP neural network model. Experimental data show that in summer or under a high-load operation condition, the optimal model comprises two hidden layers, the number of nodes of the first hidden layer of the model is 4, the number of nodes of the second hidden layer is 2, the model structure is 8-4-2-1, the average error of the true value and the predicted value of the model is 0.070, and the correlation is 0.740. In winter or under a low-load working condition, the model comprises a hidden layer, the number of nodes is 4 according to the result of the first hidden layer of the model, the model structure is 8-4-1, the average error of the actual value and the predicted value of a BP neural network test sample is 0.046, and the correlation is 0.769. Therefore, under different working conditions, the BP neural network has high prediction precision.
4. Support vector machine modeling
Support vector machine regression (SVR) is a method of mapping linearly indivisible points in a low-dimensional space to linearly separable points in a high-dimensional feature space by using a kernel function and constructing a linear regression hyperplane, and the principle of the SVR is shown in fig. 2. And the optimal segmentation of the samples is realized by linear regression hyperplane, so that the total deviation of all samples from the hyperplane is the minimum, namely the optimal solution of the model.
The present embodiment selects the most commonly used radial basis function of the regression model as the kernel function, as shown in formula (3), where g is the kernel parameter. And selecting the c value (penalty coefficient, namely error tolerance) and the g value (model complexity) with the minimum Mean Square Error (MSE) as the parameters of the model by adopting a cross-validation method. For the two model comparisons, the SVR model and the BP neural network model use the same input variables. The result shows that in summer or under high-load operation conditions, the optimal compensation coefficients c and g of the SVR model are 0.001 and 1 respectively, the model prediction mean square error is 0.070, and the correlation is 0.739. Under the winter or low-load operation condition, the optimal compensation coefficients c and g of the SVR model are 0.1 and 1 respectively, the model prediction mean square error is 0.047, and the correlation is 0.759. The mean square error of the predicted value and the true value of the water loss of the circulating water system in winter and summer of the SVR model is less than 0.1, which shows that the prediction model meets the prediction requirement and has high model accuracy.
K(xi，xj)＝exp(-g||xi-xj||2)，g＞0 (3)
5. Model comparison
In the embodiment, both the BP neural network and the SVR are used for processing the nonlinear regression problem, and both have higher prediction accuracy, but the theoretical basis of the BP neural network and the SVR is different, and the regression mechanism is also different. In order to accurately compare the prediction effects of the two models, the prediction capabilities of the two models are comprehensively judged, 4 indexes are introduced for model evaluation, and the results are shown in table 1.
(1) Average absolute percentage error;
(2) mean square error;
(3) learning time of training samples;
(4) and (4) convergence speed.
In the formula: MAPE-mean absolute percentage error Vp-training sample simulation value; vr-original value of training sample.
TABLE 1 model evaluation index
It can be seen from table 1 that, in summer or in high load operation, the prediction accuracy of the support vector machine model is slightly higher than that of the BP neural network model, and in winter or in low load operation, the prediction accuracy is opposite, but the difference between the two is not large. Compared with a BP neural model, the support vector machine model has higher calculation speed, is more advantageous to a sample set with large data volume, does not get into local convergence in the calculation process, can obtain a global optimal solution, and is better in overall performance by comprehensively considering all aspects.
5. Conclusion
The evaporation and blowing loss of the circulating water cooling tower is influenced by factors such as inlet and outlet temperature, dry/wet bulb temperature, humidity, inlet and outlet air quantity, circulating water flow and the like, and the factors have complex coupling relation and are difficult to directly calculate by a formula.
The invention is based on the operation data of a circulating water system of a certain thermal power plant, and aims at different operation conditions, a BP neural network and a support vector machine are used for regression to establish a circulating water system evaporation and blowing loss prediction model, a test-and-run method is used for improving the BP neural network model, and punishment parameters and nuclear parameters are optimized for the support vector machine model. The results show that the mean square errors of the simulation results of the two models are 0.071 and 0.070 respectively in summer and 0.046 and 0.047 respectively in winter, the prediction requirements are met, and the precision is high. Under the condition that the modeling input values are the same, both the two models have strong simulation capability, the modeling training time of the support vector machine is short, the convergence speed is high, and the performance of the whole network model is better than that of a BP neural network.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (3)
1. A circulating water loss prediction method based on a support vector machine and a neural network is characterized by comprising the following steps: predicting the circulating water loss based on BP neural network modeling and predicting the circulating water loss based on support vector machine modeling;
the predicting of the circulating water loss based on the BP neural network modeling comprises the following steps:
1) acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant;
2) based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a BP neural network, and establishing a BP neural network simulation prediction model by taking total evaporation loss and wind blowing loss as output variables;
3) predicting the circulating water loss according to the established BP neural network simulation prediction model;
the predicting of the circulating water loss based on the modeling of the support vector machine comprises the following steps:
(1) acquiring historical data of unit operation based on a plant-level monitoring information system of a thermal power plant;
(2) based on the historical data of unit operation in winter and summer, selecting inlet and outlet temperatures, unit operation load, vacuum degree, condensate flow and environment temperature as input variables of a support vector machine, and establishing a support vector machine simulation prediction model by taking total evaporation loss and wind blowing loss as output variables;
(3) and predicting the circulating water loss according to the established support vector machine simulation prediction model.
2. The method for predicting the circulating water loss based on the support vector machine and the neural network as claimed in claim 1, wherein the step 2) of predicting the circulating water loss based on the BP neural network modeling comprises:
and (3) performing model training by using the R language, and adjusting the model calculation speed, the number of nodes and the number of hidden layers by a trial and error method to obtain an optimal BP neural network simulation prediction model.
3. The method for predicting the circulating water loss based on the support vector machine and the neural network according to claim 1, wherein the step (2) of predicting the circulating water loss based on the support vector machine modeling comprises:
and selecting a radial basis function as a kernel function, and selecting a penalty coefficient with the minimum mean square error and the model complexity as model parameters by adopting a cross verification method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911310829.0A CN111178602A (en) | 2019-12-18 | 2019-12-18 | Circulating water loss prediction method based on support vector machine and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911310829.0A CN111178602A (en) | 2019-12-18 | 2019-12-18 | Circulating water loss prediction method based on support vector machine and neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178602A true CN111178602A (en) | 2020-05-19 |
Family
ID=70652161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911310829.0A Pending CN111178602A (en) | 2019-12-18 | 2019-12-18 | Circulating water loss prediction method based on support vector machine and neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178602A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597660A (en) * | 2020-05-27 | 2020-08-28 | 西安交通大学 | Multi-channel heat exchanger flow distribution prediction method |
| CN112836935A (en) * | 2021-01-07 | 2021-05-25 | 华电电力科学研究院有限公司 | Wisdom water affairs management platform suitable for power plant |
| CN114462309A (en) * | 2022-01-19 | 2022-05-10 | 苏州浪潮智能科技有限公司 | Physical simulation model training method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180190377A1 (en) * | 2016-12-30 | 2018-07-05 | Dirk Schneemann, LLC | Modeling and learning character traits and medical condition based on 3d facial features |
| CN109242236A (en) * | 2018-07-05 | 2019-01-18 | 西安图迹信息科技有限公司 | Based on the PMU primary frequency modulation load forecasting method for being associated with full Connection Neural Network and LSTM |
| CN109521813A (en) * | 2018-11-13 | 2019-03-26 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | A kind of system and method for thermal power plant recirculated water concentration rate stability contorting |
-
2019
- 2019-12-18 CN CN201911310829.0A patent/CN111178602A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180190377A1 (en) * | 2016-12-30 | 2018-07-05 | Dirk Schneemann, LLC | Modeling and learning character traits and medical condition based on 3d facial features |
| CN109242236A (en) * | 2018-07-05 | 2019-01-18 | 西安图迹信息科技有限公司 | Based on the PMU primary frequency modulation load forecasting method for being associated with full Connection Neural Network and LSTM |
| CN109521813A (en) * | 2018-11-13 | 2019-03-26 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | A kind of system and method for thermal power plant recirculated water concentration rate stability contorting |
Non-Patent Citations (1)
| Title |
|---|
| 宋嘉梁、阮圣奇等: "基于神经网络模型的自然通风逆流湿式冷却塔热力性能研究", 《流体机械》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597660A (en) * | 2020-05-27 | 2020-08-28 | 西安交通大学 | Multi-channel heat exchanger flow distribution prediction method |
| CN112836935A (en) * | 2021-01-07 | 2021-05-25 | 华电电力科学研究院有限公司 | Wisdom water affairs management platform suitable for power plant |
| CN112836935B (en) * | 2021-01-07 | 2023-11-14 | 华电电力科学研究院有限公司 | Wisdom water management platform suitable for power plant |
| CN114462309A (en) * | 2022-01-19 | 2022-05-10 | 苏州浪潮智能科技有限公司 | Physical simulation model training method, device, equipment and storage medium |
| CN114462309B (en) * | 2022-01-19 | 2023-11-17 | 苏州浪潮智能科技有限公司 | Physical simulation model training method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108494021B (en) | Stability evaluation and static control method of electricity-heat-gas comprehensive energy system | |
| CN111178602A (en) | Circulating water loss prediction method based on support vector machine and neural network | |
| CN112901449B (en) | Air compressor system energy consumption optimization method based on machine learning | |
| CN112413831A (en) | Energy-saving control system and method for central air conditioner | |
| Gao et al. | Comprehensive study on sensitive parameters for chiller fault diagnosis | |
| CN112484560A (en) | Water-saving optimization method and system for industrial circulating water | |
| Li et al. | Development of a novel soft sensor with long short-term memory network and normalized mutual information feature selection | |
| CN116070769A (en) | Ultra-short-term wind power plant power multi-step interval prediction modularization method and device thereof | |
| CN111815039A (en) | Weekly scale wind power probability prediction method and system based on weather classification | |
| Yang et al. | Energy-saving optimization of air-conditioning water system based on data-driven and improved parallel artificial immune system algorithm | |
| CN114240687A (en) | Energy hosting efficiency analysis method suitable for comprehensive energy system | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| CN117273409A (en) | Intelligent operation and maintenance method, system and storage medium for intelligent environment-friendly system of park | |
| CN107909096A (en) | A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters | |
| CN114429236A (en) | Natural gas purification process control method | |
| CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
| CN116681171A (en) | Multi-scene comprehensive energy system distribution robust optimization scheduling method and system | |
| WO2022233101A1 (en) | Intelligent optimization control device for low-temperature thermal system | |
| CN115907198A (en) | Long-distance heat supply load intelligent prediction system | |
| Huang et al. | Nonstationary industrial process monitoring based on stationary projective dictionary learning | |
| Pan et al. | Electricity gain via integrated operation of turbine generator and cooling tower using local model network | |
| CN112560329A (en) | Data-driven robust optimization method for energy system of industrial device under uncertainty | |
| CN111859783B (en) | Water pressure prediction method, system, storage medium, equipment and urban water supply system | |
| CN113868836A (en) | Big data-based intelligent thermodynamic system online expert analysis platform | |
| Yin et al. | Prediction of circulating water loss based on support vector machine and neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |
|
| RJ01 | Rejection of invention patent application after publication |