CN109934419A - A kind of nuclear power plant's intake marine organisms amount variation prediction technique - Google Patents
A kind of nuclear power plant's intake marine organisms amount variation prediction technique Download PDFInfo
- Publication number
- CN109934419A CN109934419A CN201910288404.8A CN201910288404A CN109934419A CN 109934419 A CN109934419 A CN 109934419A CN 201910288404 A CN201910288404 A CN 201910288404A CN 109934419 A CN109934419 A CN 109934419A
- Authority
- CN
- China
- Prior art keywords
- marine organisms
- power plant
- nuclear power
- intake
- model
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of nuclear power plant's intake marine organisms amounts to change prediction technique, it is based on soft-measuring technique, it mainly include two aspect of modeling (training) and prediction (test), modeling is the variable using nuclear power plant's intake marine organisms influence factor, such as temperature, salinity, dissolved oxygen, turbidity, flow velocity, x- flow direction, Y- flow direction, the data such as Z- flow direction, it is extracted by data characteristics, is learnt and trained using algorithms of different, to obtain suitable mathematical model;It predicts to speculate the variation of intake marine organisms according to live real variable mainly by acquired model, to conclude marine growth Invasive degree and a possibility that intake blocks occurs, provides support to improve nuclear power plant's cold source reliability comprehensively.
Description
Technical field
The present invention relates to belong to npp safety field, and in particular to a kind of nuclear power plant's intake marine organisms amount variation is pre-
Survey method.
Background technique
Soft-measuring technique is that automatic control technology, computer technology, sensor technology combine, and utilizes the auxiliary easily measured
Variable, Applied Computer Techniques select other to be easy to survey for being difficult to measure or temporary immeasurable leading variable
The auxiliary variable of amount is inferred or is estimated by building mathematical model, is to carry out alternative hardware measurement with software, realizes leading become
The technology of measurement;Water inlet marine organisms amount can be predicted establishing nuclear power plant's water inlet marine organisms amount soft-sensing model, directly
The variation for reflecting marine organisms amount seen, to manager's decision, catching fishes and shrimps prevents the opportunity of linked network from having very big guidance
Meaning.
Sonar contact technology is based substantially on to marine growth Invasive degree and generation intake stopping state analysis at present, mainly
It is in analysis certain time, a certain range after specific marine growth quantity variation tendency, to subsequent marine growth unit time implosion
Heat condition is analyzed and makes related early warning;But since marine growth quantity explosion time is extremely short, and by marine hydrology, ocean current etc.
It is affected, using this detection method, there are certain lag, and the time for often leaving the precautionary measures such as salvaging for is few, Wu Fachong
The target to give warning in advance is waved in distribution.Research both at home and abroad mostly is concentrating on data analysis, is detecting the side such as to optimize, improve detection efficient
Face, and it is also fewer for the research of marine growth trend model is established by ocean characteristic.Therefore pass through front-end collection data, exploitation
WARNING IN ADVANCE SYSTEM MODEL, and seemed very necessary for the early warning of intake marine growth.
Summary of the invention
A kind of nuclear power plant's intake marine organisms quantitative change is provided the invention aims to overcome the deficiencies in the prior art
Change prediction technique.
In order to achieve the above objectives, the technical scheme adopted by the invention is as follows:
A kind of nuclear power plant's intake marine organisms amount variation prediction technique, the prediction technique include the following steps: 1., by hard
Part measurement influences the data of multiple auxiliary variables of marine organisms quantity, and extracts each data characteristics;2., according to step 1. in mention
The data characteristics taken is learnt and is trained using different learning algorithms, and obtains soft-sensing model;3., by test
The data of the data of auxiliary variable or the auxiliary variable newly measured substitute into step 2. in trained soft-sensing model, obtain
The quantity result of marine organisms;4., by step 3. in obtain marine organisms quantity result and known surveys result on trial progress
Compare, and judge whether to meet expected requirement according to comparison result, so judgment step 2. in trained soft-sensing model be
No is qualified model;If 5., 4. judge step 2. according to step in trained soft-sensing model be qualified model, utilize
The qualification model carries out marine organisms amount variation prediction in real time at the scene;If 6., 4. judged according to step step 2. in training
Good soft-sensing model is not conform to lattice model, then successively carry out again step 2., step 3., step 4..
Preferably, prediction technique further include: step 7., according to step 1. in the range of auxiliary variable that measures it is insufficient or mention
The data characteristics generality taken is insufficient and the influence of change of external conditions factor, to step 2. obtained in soft-sensing model into
The corresponding amendment of row.
Preferably, 2. the middle learning algorithm used includes neural network algorithm, deep learning algorithm to step.
Preferably, step 1. in auxiliary variable include temperature, salinity, dissolved oxygen, turbidity, flow velocity, x- flow direction, Y- flow direction,
Z- flow direction.
Preferably, step 1. in hardware include thermometer, salimity measurement instrument, oxygen content measurement instrument.
Preferably, step 4. in it is known survey result on trial be pass through sonar experiment obtain marine organisms quantity.
Due to the implementation of above technical scheme, the invention has the following advantages over the prior art: nuclear power of the invention
Factory's intake marine organisms amount changes prediction technique, be based on soft-measuring technique, by by automatic control technology, calculate
Machine technology, sensor technology combine, using the auxiliary variable easily measured by building hard measurement mathematical model, with the number of software
It is calculated according to model and replaces hard ware measure, the prediction of leading variable (marine growth quantity) is realized, to conclude marine growth Invasive degree
And a possibility that intake blocking occurs, support is provided to improve nuclear power plant's cold source reliability comprehensively.
Detailed description of the invention
Fig. 1 is soft sensor modeling and prediction process schematic of the invention.
Specific embodiment
The present invention will be further described in detail with specific embodiment with reference to the accompanying drawing.
As shown in Figure 1, nuclear power plant's water inlet marine organisms amount can carry out density measure by the sonar of water inlet, but
It is that sonar can only monitor real-time region marine organisms amount, the situation at scene can not be prejudged.In general, marine growth
Increase and be essentially exponential quick outburst, often just monitored the growth of marine growth density, actual field can not be by advance
The measures such as salvaging are prevented.Therefore pass through monitoring (the i.e. seawater to some auxiliary variables for influencing to make marine growth living environment
Parameters, temperature, salinity, dissolved oxygen, turbidity, flow velocity including seawater, x- flow direction, Y- flow direction, Z- flow direction etc.) speculate sea
Biological a possibility that breaking out in the future, for assisting decision-making in-situ to necessitate.Marine growth quantity is related to water inlet, therefore relies on
These seawater parameters easily measured establish soft-sensing model and speculate marine growth Invasive degree and the possibility of intake blocking occurs
Property, it is specific as follows:
A kind of nuclear power plant's intake marine organisms amount variation prediction technique, prediction technique include the following steps: to survey 1., by hardware
Amount influences the data of multiple auxiliary variables of marine organisms quantity, and extracts each data characteristics;2., according to step 1. in extract
Data characteristics is learnt and is trained using different learning algorithms, and obtains soft-sensing model;3., by the auxiliary of test
The data of the data of variable or the auxiliary variable newly measured substitute into step 2. in trained soft-sensing model, obtain ocean
Biomass result;4., by step 3. in obtain the quantity result of marine organisms and known survey result on trial (passes through sound
Test the marine organisms quantity obtained) it is compared, and judged whether to meet expected requirement according to comparison result, and then judge
Step 2. in trained soft-sensing model whether be qualified model;If 5., 4. judge step 2. according to step in train
Soft-sensing model be qualified model, then carry out that the variation of marine organisms amount is real-time to be predicted at the scene using the qualification model;If 6.,
In 4. being judged step 2. according to step trained soft-sensing model be do not conform to lattice model, then again successively carry out step 2.,
Step 3., step 4..The prediction technique further include: step 7., according to step 1. in the range of auxiliary variable that measures it is insufficient
Or the data characteristics generality extracted is insufficient and the influence of change of external conditions factor, to step 2. obtained in hard measurement mould
Type is corrected accordingly.
In this example, 2. the middle learning algorithm used includes neural network algorithm, deep learning algorithm to step.Step 1. in
Auxiliary variable includes temperature, salinity, dissolved oxygen, turbidity, flow velocity, x- flow direction, Y- flow direction, Z- flow direction.Step 1. in hardware include
Thermometer, salimity measurement instrument, oxygen content measurement instrument.
In conclusion nuclear power plant's intake marine organisms amount of the invention changes prediction technique, it is based on hard measurement skill
It is logical using the auxiliary variable easily measured by combining automatic control technology, computer technology, sensor technology on art
Building hard measurement mathematical model is crossed, is calculated with the data model of software and replaces hard ware measure, realizes leading variable (marine growth number
Amount) prediction, thus conclude marine growth Invasive degree and occur intake blocking a possibility that, for comprehensively improve nuclear power plant's cold source
Reliability provides support.
The above embodiments merely illustrate the technical concept and features of the present invention, and its object is to allow person skilled in the art
Scholar cans understand the content of the present invention and implement it accordingly, and it is not intended to limit the scope of the present invention, it is all according to the present invention
Equivalent change or modification made by Spirit Essence, should be covered by the protection scope of the present invention.
Claims (6)
1. a kind of nuclear power plant's intake marine organisms amount changes prediction technique, it is characterised in that: the prediction technique includes as follows
Step:
1., influenced by hard ware measure marine organisms quantity multiple auxiliary variables data, and extract each data characteristics;②,
According to step 1. in extract data characteristics, learnt and trained using different learning algorithms, and obtain soft-sensing model;
3., the data of auxiliary variable that by the data of the auxiliary variable of test or newly measure substitute into step 2. in trained soft survey
It measures in model, obtains the quantity result of marine organisms;4., by step 3. in obtain marine organisms quantity result and known survey
Result on trial is compared, and judges whether to meet expected requirement according to comparison result, so judgment step 2. in it is trained
Whether soft-sensing model is qualified model;If 5., 4. judge step 2. according to step in trained soft-sensing model be to close
Lattice model then carries out marine organisms amount using the qualification model at the scene and changes prediction in real time;If 6., 4. judged according to step
Step 2. in trained soft-sensing model be do not conform to lattice model, then again successively carry out step 2., step 3., step 4..
2. nuclear power plant's intake marine organisms amount according to claim 1 changes prediction technique, it is characterised in that: described pre-
Survey method further include: step is 7., 1. the range deficiency of the middle auxiliary variable measured or the data characteristics extracted are universal according to step
Property insufficient and change of external conditions factor influence, to step 2. obtained in soft-sensing model corrected accordingly.
3. nuclear power plant's intake marine organisms amount according to claim 1 changes prediction technique, it is characterised in that: step is 2.
The learning algorithm of middle use includes neural network algorithm, deep learning algorithm.
4. nuclear power plant's intake marine organisms amount according to claim 1 changes prediction technique, it is characterised in that: step is 1.
In auxiliary variable include temperature, salinity, dissolved oxygen, turbidity, flow velocity, x- flow direction, Y- flow direction, Z- flow direction.
5. nuclear power plant's intake marine organisms amount according to claim 1 changes prediction technique, it is characterised in that: step is 1.
In hardware include thermometer, salimity measurement instrument, oxygen content measurement instrument.
6. nuclear power plant's intake marine organisms amount according to claim 1 changes prediction technique, it is characterised in that: step is 4.
In it is known survey result on trial be pass through sonar experiment obtain marine organisms quantity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910288404.8A CN109934419A (en) | 2019-04-11 | 2019-04-11 | A kind of nuclear power plant's intake marine organisms amount variation prediction technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910288404.8A CN109934419A (en) | 2019-04-11 | 2019-04-11 | A kind of nuclear power plant's intake marine organisms amount variation prediction technique |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109934419A true CN109934419A (en) | 2019-06-25 |
Family
ID=66989781
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910288404.8A Pending CN109934419A (en) | 2019-04-11 | 2019-04-11 | A kind of nuclear power plant's intake marine organisms amount variation prediction technique |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109934419A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112817058A (en) * | 2021-01-25 | 2021-05-18 | 华中科技大学鄂州工业技术研究院 | Swarm marine organism early warning method and system, electronic device and storage medium |
CN113901557A (en) * | 2021-10-20 | 2022-01-07 | 中国水利水电科学研究院 | Power plant water intake open channel layout analysis method based on reduction of water intake entrainment effect |
CN114299332A (en) * | 2021-12-22 | 2022-04-08 | 苏州热工研究院有限公司 | Cold source marine organism intelligent detection method and system for nuclear power plant |
CN115206040A (en) * | 2021-04-12 | 2022-10-18 | 南方科技大学 | Biological invasion early warning method, device and terminal for nuclear power water intake |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080178663A1 (en) * | 2007-01-31 | 2008-07-31 | Yingping Jeffrey Yang | Adaptive real-time contaminant detection and early warning for drinking water distribution systems |
CN106407691A (en) * | 2016-09-28 | 2017-02-15 | 中国地质大学(武汉) | Red tide biomass prediction method and device |
CN107665363A (en) * | 2016-07-30 | 2018-02-06 | 复凌科技(上海)有限公司 | A kind of water quality hard measurement Forecasting Methodology of total phosphorus |
CN107977724A (en) * | 2016-10-21 | 2018-05-01 | 复凌科技(上海)有限公司 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
CN109190718A (en) * | 2018-11-07 | 2019-01-11 | 苏州热工研究院有限公司 | A kind of nuclear power plant's marine growth detecting early-warning Multi-source Information Fusion algorithm |
-
2019
- 2019-04-11 CN CN201910288404.8A patent/CN109934419A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080178663A1 (en) * | 2007-01-31 | 2008-07-31 | Yingping Jeffrey Yang | Adaptive real-time contaminant detection and early warning for drinking water distribution systems |
CN107665363A (en) * | 2016-07-30 | 2018-02-06 | 复凌科技(上海)有限公司 | A kind of water quality hard measurement Forecasting Methodology of total phosphorus |
CN106407691A (en) * | 2016-09-28 | 2017-02-15 | 中国地质大学(武汉) | Red tide biomass prediction method and device |
CN107977724A (en) * | 2016-10-21 | 2018-05-01 | 复凌科技(上海)有限公司 | A kind of water quality hard measurement Forecasting Methodology of permanganate index |
CN109190718A (en) * | 2018-11-07 | 2019-01-11 | 苏州热工研究院有限公司 | A kind of nuclear power plant's marine growth detecting early-warning Multi-source Information Fusion algorithm |
Non-Patent Citations (1)
Title |
---|
李建文等: "提升核电厂冷源安全性的海生物探测技术研究", 《电力安全技术》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112817058A (en) * | 2021-01-25 | 2021-05-18 | 华中科技大学鄂州工业技术研究院 | Swarm marine organism early warning method and system, electronic device and storage medium |
CN115206040A (en) * | 2021-04-12 | 2022-10-18 | 南方科技大学 | Biological invasion early warning method, device and terminal for nuclear power water intake |
CN115206040B (en) * | 2021-04-12 | 2023-08-04 | 南方科技大学 | Biological invasion early warning method, device and terminal for nuclear power water intake |
CN113901557A (en) * | 2021-10-20 | 2022-01-07 | 中国水利水电科学研究院 | Power plant water intake open channel layout analysis method based on reduction of water intake entrainment effect |
CN114299332A (en) * | 2021-12-22 | 2022-04-08 | 苏州热工研究院有限公司 | Cold source marine organism intelligent detection method and system for nuclear power plant |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109934419A (en) | A kind of nuclear power plant's intake marine organisms amount variation prediction technique | |
CN111949700B (en) | Intelligent safety guarantee real-time optimization method and system for petrochemical device | |
Sun et al. | Detection of mastitis and its stage of progression by automatic milking systems using artificial neural networks | |
CN109002888B (en) | Red tide early warning method | |
CN110132603A (en) | Boat diesel engine Fault Locating Method based on union confidence rule base and ant group algorithm | |
CN111881627B (en) | Nuclear power plant fault diagnosis method and system | |
Li et al. | A data-driven prediction model for maximum pitting corrosion depth of subsea oil pipelines using SSA-LSTM approach | |
CN110675036A (en) | Plateau river ecological health evaluation method based on random forest optimization microbial index | |
CN107292383A (en) | The variation water quality interval prediction method being combined based on deep learning algorithm with MILP | |
CN116595327B (en) | Sluice deformation monitoring data preprocessing system and method | |
De Masi et al. | Machine learning approach to corrosion assessment in subsea pipelines | |
CN109190718A (en) | A kind of nuclear power plant's marine growth detecting early-warning Multi-source Information Fusion algorithm | |
Yuzevych et al. | Improving the diagnostics of underground pipelines at oil-and-gas enterprises based on determining hydrogen exponent (PH) of the soil media applying neural networks | |
CN115294804A (en) | Submarine cable safety early warning method and system based on ship state monitoring | |
CN117115637A (en) | Water quality monitoring and early warning method and system based on big data technology | |
CN107632521B (en) | Constant potential rectifier control method based on decision tree and neural network | |
CN115052304A (en) | GCN-LSTM-based industrial sensor network abnormal data detection method | |
Shen et al. | SSCT-Net: A semisupervised circular teacher network for defect detection with limited labeled multiview MFL samples | |
CN117830814A (en) | Image sonar-based deep sea cage culture fish swarm quantity estimation method | |
Zhou et al. | Anode effect prediction of aluminum electrolysis using GRNN | |
CN109359624B (en) | Neural network-based prediction method and prediction device for feeding behavior of laying hens | |
Deng et al. | Application of neural network based on PSO algorithm in prediction model for dissolved oxygen in fishpond | |
Bhutada et al. | COD prediction in water using Edge Artificial Intelligence | |
Dzierzbicka-Głowacka et al. | Structure of the FindFish Knowledge Transfer Platform | |
CN115184734A (en) | Power grid line fault detection method and system |
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: 20190625 |
|
RJ01 | Rejection of invention patent application after publication |