CN112990516A - Circulating water system corrosion prediction method and application thereof - Google Patents
Circulating water system corrosion prediction method and application thereof Download PDFInfo
- Publication number
- CN112990516A CN112990516A CN201911272618.2A CN201911272618A CN112990516A CN 112990516 A CN112990516 A CN 112990516A CN 201911272618 A CN201911272618 A CN 201911272618A CN 112990516 A CN112990516 A CN 112990516A
- Authority
- CN
- China
- Prior art keywords
- corrosion
- water system
- circulating water
- data
- predicting
- 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
- 238000005260 corrosion Methods 0.000 title claims abstract description 132
- 230000007797 corrosion Effects 0.000 title claims abstract description 129
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000007246 mechanism Effects 0.000 claims abstract description 22
- 239000000498 cooling water Substances 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 238000002474 experimental method Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000012806 monitoring device Methods 0.000 claims abstract description 4
- 239000002184 metal Substances 0.000 claims description 19
- 229910052751 metal Inorganic materials 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 230000007613 environmental effect Effects 0.000 claims description 12
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 8
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 8
- 229910052760 oxygen Inorganic materials 0.000 claims description 8
- 239000001301 oxygen Substances 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 150000002739 metals Chemical class 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 5
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 4
- 229910021645 metal ion Inorganic materials 0.000 claims description 4
- 230000002906 microbiologic effect Effects 0.000 claims description 4
- 229910052757 nitrogen Inorganic materials 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 230000000813 microbial effect Effects 0.000 claims description 3
- 238000012843 least square support vector machine Methods 0.000 claims description 2
- 239000000523 sample Substances 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 229910000975 Carbon steel Inorganic materials 0.000 description 4
- 239000010962 carbon steel Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000007769 metal material Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000033116 oxidation-reduction process Effects 0.000 description 1
- 230000003134 recirculating effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine 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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/045—Combinations of networks
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
- Preventing Corrosion Or Incrustation Of Metals (AREA)
Abstract
The invention discloses a method for predicting corrosion of a circulating water system and application thereof, wherein the method comprises the following steps: acquiring data; analyzing a corrosion mechanism; preprocessing data; analyzing influence factors of corrosion and scaling; modeling corrosion and scaling characteristics based on a data analysis technology; and (6) analyzing results. The invention integrates corrosion mechanism analysis and data analysis technology, adopts a method of combining simulation analysis and a corrosion and scaling experiment monitoring device to predict the corrosion condition of the circulating cooling water system, and combines with a water treatment scheme to avoid the corrosion of the circulating water system.
Description
Technical Field
The invention belongs to the technical field of circulating water, and particularly relates to a corrosion prediction method for a circulating water system and application thereof.
Background
A large amount of metal materials are used as heat exchange media in the circulating cooling water system. The metal material has good use characteristics and process characteristics, but in practical application, the metal material is most easily influenced by surrounding environment media and is corroded and damaged. The metal corrosion mainly occurs at the interface of metal and medium, and is metal deterioration and destruction caused by chemical and electrochemical reactions between metal and medium, which is a complex heterogeneous reaction. The corrosion problem of heat exchange equipment of a circulating water system is very common, and according to statistics, the corrosion leakage of a water cooler accounts for more than 70% of the corrosion leakage of an oil refining device, and the annual leakage rate of the water cooler of some enterprises is even as high as 40%. Corrosion of the water cooler not only increases the maintenance cost of the enterprise, but also provides challenges for safe long-term operation of the device.
At present, the corrosion rate of a circulating water system is mainly detected by monitoring a corrosion coupon or a corrosion probe of a heat exchanger, but the function of prediction cannot be realized. Therefore, it is necessary to design a corrosion prediction method for a circulating water system, which predicts the corrosion rate in advance and adjusts the water treatment scheme in time.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a corrosion prediction method for a circulating water system and application thereof.
In order to solve the technical problems, the invention adopts the technical scheme that:
a method for predicting the corrosion of circulating water system features that the corrosion mechanism analysis and data analysis technique are combined to predict the corrosion state of circulating cooling water system by the combination of simulation analysis and corrosion and scaling experiment monitor.
Further, the corrosion prediction method of the circulating water system specifically comprises the following steps:
step one, data acquisition;
step two, analyzing a corrosion mechanism;
step three, preprocessing data;
analyzing influence factors of corrosion and scaling;
fifthly, modeling the corrosion and scaling characteristics based on a data analysis technology;
and sixthly, analyzing results.
Further, the specific operation of the step one is as follows: and sorting the actual measurement data, arranging according to a time sequence, and removing abnormal data in the sample.
Further, the specific operation of the step two is as follows: and analyzing the change of the metal in contact with cooling water aiming at different metals, and analyzing the corrosion and scaling mechanism to obtain a related mechanism expression.
Further, when an expression is obtained by analyzing the corrosion and scaling mechanism, the physical, chemical, electrochemical, mechanical or microbiological effects are considered.
Further, the specific operation of the third step is as follows: and (4) carrying out standardization processing on the original data of the actual measurement data obtained in the step one to enable the target parameters to be in the same magnitude.
Further, the data preprocessing is carried out by adopting a Z-score method in the standardization process, and the calculation method is shown as a formula (1):
in the formula, ziIs the original data of the ith column, μ is the mean value of the sample data of the ith column, σ is the standard deviation of the sample data of the ith column,
normalized to Z-score.
And further, when analyzing the influence factors of corrosion and scaling, analyzing the relation between corrosion and environmental factors to obtain the relation between the corrosion rate, the scaling resistance and the environmental factors.
Environmental factors affecting corrosion rate include, but are not limited to, temperature, pH, flow rate, Cl-Ions, dissolved oxygen, conductivity, redox potential, alkalinity, hardness, metal ions, and microbial population; water quality parameters that affect fouling thermal resistance include, but are not limited to, pH, conductivity, ammonia nitrogen, total nitrogen, dissolved oxygen.
Further, a shallow neural network and a deep learning algorithm are adopted to model corrosion and scaling characteristics; the shallow neural network comprises but is not limited to a BP neural network, a multilayer perceptron and a least square support vector machine, and the deep learning algorithm comprises but is not limited to a CNN, a DBN and an RNN algorithm.
And step six, predicting the corrosion rate and fouling thermal resistance of the circulating water by using the model established in step five, and further obtaining a corrosion prediction result of the circulating water.
The application of the corrosion prediction method of the circulating water system is used for predicting the corrosion rate of the circulating water system, and the corrosion of the circulating water system is avoided by combining with a water treatment scheme.
Compared with the prior art, the invention has the advantages that:
(1) the prediction method integrates corrosion mechanism analysis and data analysis technology, adopts a method of combining simulation analysis and a corrosion and scaling experiment monitoring device, realizes the prediction of the corrosion rate of the circulating cooling water system, solves the defect that the corrosion condition can only be monitored by monitoring a corrosion coupon or a corrosion probe of a heat exchanger but can not be predicted in advance in the prior art, prolongs the service life of equipment, and reduces the maintenance cost;
(2) the corrosion rate is predicted in advance, and the water treatment scheme is adjusted in time to avoid corrosion of the circulating water system.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of example 1 of the present invention;
FIG. 2 is a specific process for constructing a DBN-to-corrosion rate prediction model according to embodiment 1 of the present invention;
FIG. 3 is a graph comparing the predicted results of two models in example 1 of the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
Example 1
The design scheme of the corrosion prediction method of the circulating water system is as follows: and (3) predicting the corrosion rate of the circulating cooling water system by combining a simulation analysis and a corrosion and scaling experiment monitoring device by integrating a corrosion mechanism analysis and data analysis technology.
With reference to the flow steps shown in fig. 1, the method for predicting corrosion of a circulating water system in the embodiment specifically includes the following steps:
step one, data acquisition
And sorting the actual measurement data, arranging according to a time sequence, and removing abnormal data in the sample.
Step two, corrosion mechanism analysis
Metal corrosion is primarily the destruction or deterioration of metals by chemical or electrochemical action, sometimes accompanied by other actions such as physical, mechanical or microbiological actions. The metal corrosion process is very complex and is influenced by various factors. Therefore, in the step, the change of the metal in contact with the cooling water is analyzed according to different metals, the corrosion and scaling mechanism is analyzed, and a related mechanism expression is obtained.
Wherein, when analyzing the corrosion and scaling mechanism to obtain the expression, the physical, chemical, electrochemical, mechanical or microbiological effects are considered.
Most heat exchangers in industrial cooling water systems are made of carbon steel. For this reason, this example uses carbon steel as a representative metal, and discusses the corrosion mechanism of metals in water. Since the surface of the carbon steel is not perfectly uniform, many tiny corrosion cells are formed when it comes into contact with cooling water. Wherein, the active part becomes an anode region in the corrosion chemistry, the inactive part becomes a cathode region, the physical and chemical reaction in the anode region is considered, the corrosion and scaling mechanism is analyzed, a related mechanism expression is obtained, and the carbon steel can refer to the circulating water corrosion expression in the API 581.
Step three, data preprocessing
Due to the fact that the difference of the value ranges of the monitoring parameters is large and is at most 3 orders of magnitude different, the influence of data with small orders of magnitude on the model is reduced due to the order of magnitude difference, and the real relation between variables cannot be accurately reflected. In order to eliminate the dimensional influence between the target parameters, the target parameters are in the same order of magnitude, and the raw data are subjected to standardization processing.
Therefore, the specific operation of this step is: and (4) carrying out standardization processing on the original data of the actual measurement data obtained in the step one to enable the target parameters to be in the same magnitude.
The data preprocessing is carried out by adopting a Z-score method in the standardization treatment, and the calculation method is shown as a formula (1):
in the formula, ziIs the original data of the ith column, μ is the mean value of the sample data of the ith column, σ is the standard deviation of the sample data of the ith column,
normalized to Z-score.
And performing characteristic analysis on the acquired data, analyzing the properties of the data such as mean, variance, chaotic characteristic, randomness, predictability and the like, and selecting subsequent processing and modeling algorithms according to the data characteristics.
Step four, analyzing influence factors of corrosion and scaling
The factors influencing metal corrosion include two major types, namely intrinsic factors and extrinsic factors. The type, structure, composition and internal stress of the metal are intrinsic factors. However, the intrinsic factors of the metal after the equipment is put into use are basically determined, and only the environmental factors affecting the corrosion of the metal remain. By researching the relation between corrosion and environmental factors, the environmental factors which have large influence on the corrosion mainly comprise temperature, pH value, flow rate and Cl-Ions, dissolved oxygen, conductivity, redox potential, alkalinity, hardness, metal ions, microbial population, and the like. Parameters related to fouling thermal resistance comprise water quality parameters such as pH, conductivity, ammonia nitrogen, total nitrogen and dissolved oxygen.
Therefore, when the influence factors of corrosion and scaling are analyzed, the relationship between corrosion and environmental factors is analyzed, and the relationship between the corrosion rate, the thermal resistance of scaling and the environmental factors is obtained.
Environmental factors affecting corrosion rate include, but are not limited to, temperature, pH, flow rate, Cl-Ions, dissolved oxygen, conductivity, oxidation-reduction potential, alkalinity, hardness, metal ions, total number of microorganisms, and the like; water quality parameters that affect fouling thermal resistance include, but are not limited to, pH, conductivity, ammonia nitrogen, total nitrogen, dissolved oxygen, and the like.
Step five, modeling of corrosion and scaling characteristics based on data analysis technology
In a recirculating cooling water system, the corrosion rate is affected not only by water quality factors but also by process parameters, and therefore these factors must be taken into full account when building the model. Because a complex nonlinear relationship exists between the corrosion rate and each influencing factor, a proper method should be selected when a corrosion rate prediction model is established. And modeling the corrosion and scaling characteristics by adopting a shallow neural network and a deep learning algorithm. The shallow neural network comprises a BP neural network, a multilayer perceptron (MLP), a least squares support vector machine (LS-SVM) and the like, and can predict corrosion rate and fouling resistance. With the development of data analysis algorithms, deep learning algorithms including algorithms such as CNN, DBN and RNN can be used for prediction modeling of circulating water corrosion.
In the embodiment, a Deep Belief Network (DBN) is adopted to predict the corrosion rate, a shallow neural network comprising a BP neural network, a multilayer perceptron (MLP) and the like is adopted, a prediction model of the corrosion rate is established by using the same sample data, and the prediction model and the established DBN model are compared and analyzed. In the research of the corrosion process mechanism, a Deep Belief Network (DBN) algorithm is adopted to predict the corrosion rate. The specific construction process of the DBN to corrosion rate prediction model is shown in FIG. 2.
And sixthly, analyzing results.
And predicting the corrosion rate and fouling thermal resistance of the circulating water by using the model established in the fifth step, and further obtaining a corrosion prediction result of the circulating water.
In this embodiment, a BP neural network prediction model for predicting corrosion rate is established with the same sample data, and the effect comparison is shown in fig. 3. The prediction results of the BP neural network and the LS-SVM are contained, and the prediction results are in good correspondence with measured values.
According to the invention, three prediction models are constructed by taking three water quality parameters of the adhesion speed, the fouling thermal resistance value and the test tube corrosion rate as outputs, and the constructed LSSVM model is more suitable for predicting two outputs of the adhesion speed and the fouling thermal resistance value; after various algorithm models are constructed for the corrosion rate of the test tube, the accuracy of the DBN algorithm is higher, so that the DBN model is selected for modeling and predicting.
The specific results obtained by modeling experiments were analyzed as follows:
3 different predictive models with adhesion velocity as output: the errors generated by the LSSVM model are minimum and fluctuate around 0, so that the model is relatively more stable and has higher precision. To compare the three models in more detail, the respective error indices of the three models are compared. As can be seen from Table 2, the MAPE, MAE, R and other indexes of the LSSVM are all smaller than those of the other two models, so that the LSSVM algorithm is more suitable for constructing a prediction model with the adhesion speed as the output.
3 different prediction models with fouling thermal resistance as output: the errors generated by the LSSVM model are minimum, and the errors fluctuate around 0, so that the model is relatively more stable and has higher accuracy. To compare the three models in more detail, the respective error indices of the three models are compared. As can be seen from Table 2, the indexes such as MAPE, MAE, R and the like of the LSSVM are all smaller than those of the other two models, so that the LSSVM algorithm is more suitable for constructing a prediction model taking the fouling thermal resistance value as the output.
3 different prediction models with test tube corrosion rate as output: the errors produced by the DBN model are minimal and the model is relatively more accurate. To compare the three models in more detail, the respective error indices of the three models are compared. Although the error indexes of the models are not ideal, the indexes of MAPE, MAE, R and the like of DBN are smaller than those of other two models, so that the DBN algorithm is more suitable for a prediction model with the test tube corrosion rate as an output.
Example 2
The embodiment provides application of the corrosion prediction method for the circulating water system, which is used for predicting the corrosion rate of the circulating water system and is combined with a water treatment scheme to avoid corrosion of the circulating water system.
In this embodiment, the corrosion prediction method for a circulating water system in embodiment 1 is used to predict the corrosion rate of a circulating cooling water system, predict the corrosion rate in advance, and then adjust the water treatment scheme in time to prevent the circulating water system from being corroded.
Example 3
The embodiment provides an anti-corrosion method for a circulating water system, which comprises the steps of firstly predicting the corrosion rate of the circulating cooling water system by using the corrosion prediction method for the circulating water system described in the embodiment 1, then establishing an anti-corrosion strategy, and avoiding the corrosion of the circulating water system by adjusting the water treatment scheme in time.
It is understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art should understand that they can make various changes, modifications, additions and substitutions within the spirit and scope of the present invention.
Claims (12)
1. A method for predicting corrosion of a circulating water system is characterized in that corrosion mechanism analysis and data analysis technologies are combined, and a method combining simulation analysis and a corrosion and scaling experiment monitoring device is adopted to predict the corrosion condition of the circulating cooling water system.
2. The method for predicting corrosion of a circulating water system according to claim 1, comprising the steps of:
step one, data acquisition;
step two, analyzing a corrosion mechanism;
step three, preprocessing data;
analyzing influence factors of corrosion and scaling;
fifthly, modeling the corrosion and scaling characteristics based on a data analysis technology;
and sixthly, analyzing results.
3. The method for predicting corrosion of a circulating water system according to claim 2, wherein the specific operation of the step one is as follows: and sorting the actual measurement data, arranging according to a time sequence, and removing abnormal data in the sample.
4. The method for predicting corrosion of the circulating water system according to claim 2, wherein the specific operation of the second step is: and analyzing the change of the metal in contact with cooling water aiming at different metals, and analyzing the corrosion and scaling mechanism to obtain a related mechanism expression.
5. The method for predicting corrosion of a circulating water system as claimed in claim 4, wherein the physical, chemical, electrochemical, mechanical or microbiological effects are taken into account when analyzing the corrosion fouling mechanism to obtain the expression.
6. The corrosion prediction method for a circulating water system according to claim 3, wherein the specific operation of step three is: and (4) carrying out standardization processing on the original data of the actual measurement data obtained in the step one to enable the target parameters to be in the same magnitude.
7. The method for predicting corrosion of a circulating water system according to claim 6, wherein the data is preprocessed by a Z-score method in a standardized manner, and the calculation method is as shown in formula (1):
in the formula, ziIs the original data of the ith column, μ is the mean value of the sample data of the ith column, σ is the standard deviation of the sample data of the ith column,
normalized to Z-score.
8. The method for predicting corrosion of a circulating water system according to claim 6, wherein in the step four, when analyzing the corrosion and scaling influence factors, the relationship between corrosion and environmental factors is analyzed to obtain the relationship between the corrosion rate, the scaling resistance and the environmental factors.
9. The method of claim 8, wherein the environmental factors affecting corrosion rate include, but are not limited to, temperature, pH, flow rate, Cl-Ions, dissolved oxygen, conductivity, redox potential, alkalinity, hardness, metal ions, and microbial population; water quality parameters that affect fouling thermal resistance include, but are not limited to, pH, conductivity, ammonia nitrogen, total nitrogen, dissolved oxygen.
10. The method for predicting corrosion of the circulating water system according to claim 8, wherein step five models corrosion and scaling characteristics by adopting a shallow neural network and a deep learning algorithm; the shallow neural network comprises but is not limited to a BP neural network, a multilayer perceptron and a least square support vector machine, and the deep learning algorithm comprises but is not limited to a CNN, a DBN and an RNN algorithm.
11. The method for predicting corrosion of a circulating water system according to claim 10, wherein the model established in the fifth step is used in the sixth step to predict corrosion rate and fouling resistance of the circulating water, and further to obtain a corrosion prediction result of the circulating water.
12. The use of the method of claim 11 for predicting the corrosion rate of a circulating water system in conjunction with a water treatment protocol to avoid corrosion in the circulating water system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911272618.2A CN112990516A (en) | 2019-12-12 | 2019-12-12 | Circulating water system corrosion prediction method and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911272618.2A CN112990516A (en) | 2019-12-12 | 2019-12-12 | Circulating water system corrosion prediction method and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112990516A true CN112990516A (en) | 2021-06-18 |
Family
ID=76332113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911272618.2A Pending CN112990516A (en) | 2019-12-12 | 2019-12-12 | Circulating water system corrosion prediction method and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990516A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806964A (en) * | 2021-09-30 | 2021-12-17 | 西南石油大学 | Corrosion and scaling rate prediction method considering multi-factor coupling effect |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10153569A (en) * | 1996-11-22 | 1998-06-09 | Mitsubishi Chem Corp | Water quality control supporting system for circulated cooling water of cooling tower |
| CN1514248A (en) * | 2003-03-20 | 2004-07-21 | 北京科技大学 | Circulating cooling water quality monitoring system and equipment |
| WO2007038533A2 (en) * | 2005-09-28 | 2007-04-05 | Saudi Arabian Oil Company | System to predict corrosion and scaling, program product, and related methods |
| CN101915728A (en) * | 2010-07-27 | 2010-12-15 | 沈阳建筑大学 | Testing method for predicting residual service life of buried metal water supply pipeline |
| CN107621526A (en) * | 2017-08-16 | 2018-01-23 | 国网天津市电力公司电力科学研究院 | A kind of recirculated cooling water etch state diagnostic analysis system and method |
| CN207473382U (en) * | 2017-09-15 | 2018-06-08 | 武汉江汉化工设计有限公司 | A kind of industrial circulating cooling water intelligent operation manages system |
| US20190145722A1 (en) * | 2017-11-10 | 2019-05-16 | Ecolab Usa Inc. | Cooling water monitoring and control system |
-
2019
- 2019-12-12 CN CN201911272618.2A patent/CN112990516A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10153569A (en) * | 1996-11-22 | 1998-06-09 | Mitsubishi Chem Corp | Water quality control supporting system for circulated cooling water of cooling tower |
| CN1514248A (en) * | 2003-03-20 | 2004-07-21 | 北京科技大学 | Circulating cooling water quality monitoring system and equipment |
| WO2007038533A2 (en) * | 2005-09-28 | 2007-04-05 | Saudi Arabian Oil Company | System to predict corrosion and scaling, program product, and related methods |
| CN101915728A (en) * | 2010-07-27 | 2010-12-15 | 沈阳建筑大学 | Testing method for predicting residual service life of buried metal water supply pipeline |
| CN107621526A (en) * | 2017-08-16 | 2018-01-23 | 国网天津市电力公司电力科学研究院 | A kind of recirculated cooling water etch state diagnostic analysis system and method |
| CN207473382U (en) * | 2017-09-15 | 2018-06-08 | 武汉江汉化工设计有限公司 | A kind of industrial circulating cooling water intelligent operation manages system |
| US20190145722A1 (en) * | 2017-11-10 | 2019-05-16 | Ecolab Usa Inc. | Cooling water monitoring and control system |
Non-Patent Citations (2)
| Title |
|---|
| 李超: "工业循环水腐蚀结垢预测***设计与实现", 中国优秀硕士学位论文数据库信息科技辑, pages 10 - 15 * |
| 董超 等: "工业循环水腐蚀结垢预测***设计与实现", 化工自动化及仪表, vol. 45, pages 100 - 104 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806964A (en) * | 2021-09-30 | 2021-12-17 | 西南石油大学 | Corrosion and scaling rate prediction method considering multi-factor coupling effect |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111051806B (en) | Cooling water monitoring and control system | |
| Ye et al. | Stochastic modelling and analysis of degradation for highly reliable products | |
| CN105868164B (en) | A kind of soft-measuring modeling method based on the linear dynamic system model for having supervision | |
| CN112417765B (en) | Sewage treatment process fault detection method based on improved teacher-student network model | |
| Dong et al. | The prediction trend of enterprise financial risk based on machine learning arima model | |
| CN110046377B (en) | Selective integration instant learning soft measurement modeling method based on heterogeneous similarity | |
| Jiménez‐Come et al. | Characterization of pitting corrosion of stainless steel using artificial neural networks | |
| Zhao et al. | Improved batch process monitoring and quality prediction based on multiphase statistical analysis | |
| CN112990516A (en) | Circulating water system corrosion prediction method and application thereof | |
| CN111783354A (en) | Flow-induced corrosion characteristic prediction and service life evaluation method of RBF neural network model | |
| CN115077618A (en) | Quality detection method and system for nuclear-grade alloy steel elbow | |
| Bahr et al. | Artificial neural networks for aging simulation of electrolysis stacks | |
| CN112734201B (en) | Multi-equipment overall quality evaluation method based on expected failure probability | |
| Memon et al. | Neural network based corrosion modeling of Stainless Steel 316L elbow using electric field mapping data | |
| Lin et al. | Application of artificial intelligence (AI) in the area of corrosion protection | |
| Fouladirad et al. | A transformed gamma process for bounded degradation phenomena | |
| Ye et al. | Data‐driven soft‐sensor modelling for air cooler system pH values based on a fast search pruned‐extreme learning machine | |
| Zhang et al. | Detection of sludge bulking using adaptive fuzzy neural network and mechanism model | |
| CN113253682B (en) | Nonlinear chemical process fault detection method | |
| Li et al. | Soft Sensor Modeling Method Based on SPA‐GWO‐SVR for Marine Protease Fermentation Process | |
| CN114192583A (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| Arunthavanathan et al. | Remaining Useful Life Estimation Using Fault to Failure Transformation in Process Systems | |
| Zhou et al. | Machine learning‐based analysis and prediction of the interfacial corrosion processes of copper cathode plates during the electrolytic production of copper powders | |
| Ruiz et al. | Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines | |
| Zhao et al. | Batch process quality monitoring based on temporal convolutional networks with depthwise separable coordinated attention module |
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 |