CN116027460A - Quality control method and system for ocean observation data of wave glider and electronic equipment - Google Patents
Quality control method and system for ocean observation data of wave glider and electronic equipment Download PDFInfo
- Publication number
- CN116027460A CN116027460A CN202310286271.7A CN202310286271A CN116027460A CN 116027460 A CN116027460 A CN 116027460A CN 202310286271 A CN202310286271 A CN 202310286271A CN 116027460 A CN116027460 A CN 116027460A
- Authority
- CN
- China
- Prior art keywords
- data
- observation data
- marine
- threshold range
- ocean
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a quality control method, a system and electronic equipment for marine observation data of a wave glider, and relates to the field of quality control for the marine observation data. And the shore station monitoring end sequentially carries out second range inspection, peak inspection and BP neural network data correction on the marine observation data subjected to mean value processing to obtain corrected marine observation data. The invention can achieve the purpose of improving the accuracy of the sea-air interface observation element.
Description
Technical Field
The invention relates to the field of quality control of ocean observation data, in particular to a quality control method, a system and electronic equipment of ocean observation data of a wave glider.
Background
At present, unmanned observation platforms such as wave gliders, underwater gliders, buoys, submerged buoy and the like are widely applied to ocean observation data, and the accuracy and the reliability of the ocean observation data are the core of the data quality control method of various ocean unmanned observation platforms. Taking scalar observation data such as air temperature, air pressure and water temperature as an example, standard data quality control methods comprise missing test, range test, continuity test, comprehensive analysis test and the like.
The wave glider is an effective means for observing a sea-air interface, the sea-air interface environment comprises multiple disturbance factors such as wind, waves, solar radiation, water vapor and the like, and compared with unmanned observation platforms such as large buoys and the like, the wave glider observes sea-air interface meteorological parameters which are complex and changeable due to the working environment, and observation data comprise the multiple disturbance factors. Therefore, it is necessary to develop quality control research of marine environment data of the wave glider.
The wave glider data quality control includes a data verification and data correction algorithm. The weather data correction algorithm commonly used at present comprises a neural network algorithm, an association rule algorithm and the like. The BP neural network algorithm is mostly applied to the quality control process of the land meteorological observation data, and compared with the interaction of sea-air interfaces and the like in the marine environment, the BP neural network algorithm has relatively fewer data interference factors of land observation. Wang Baowei et al build a relationship between solar radiation and temperature error by training a BP neural network model, correct air temperature data, the maximum deviation of air temperature before correction is 6.5 ℃, the average deviation is 2 ℃, the maximum deviation of air temperature after correction is 1.7 ℃ and the average deviation is 1 ℃. The BP neural network algorithm is applied in the violent weather to correct the land air temperature abnormal data, the mode of artificial disturbance is adopted in the effectiveness verification process of the BP neural network algorithm, and the application verification of the real working condition is not carried out. Therefore, it is known from the above-mentioned documents that the prior art mainly corrects land meteorological data, and the content of quality control study on marine meteorological data is less involved.
Disclosure of Invention
The invention aims to provide a quality control method, a system and electronic equipment for marine observation data of a wave glider, so as to achieve the aim of improving accuracy of marine gas interface observation elements.
In order to achieve the above object, the present invention provides the following.
In a first aspect, the present invention provides a method for controlling quality of marine observations of a wave glider, comprising: the wave glider acquires ocean observation data acquired by the target meteorological sensor; the ocean observation data comprise air temperature data, air pressure data, wind speed data and wind direction data; the gas mark sensor is arranged on the wave glider; the wave glider sequentially performs first range inspection and mean value processing on the ocean observation data to obtain average value processed ocean observation data; the monitoring end of the shore station obtains ocean observation data after mean value processing; and the shore station monitoring end sequentially carries out second range inspection, peak inspection and BP neural network data correction on the marine observation data subjected to mean value processing to obtain corrected marine observation data.
In a second aspect, the present invention provides a wave glider marine survey data quality control system comprising: a wave glider and a shore station monitoring end; the wave glider at least comprises a water mother ship, an armored cable and an underwater tractor; the water mother ship at least comprises a main control module; the main control module is used for: acquiring ocean observation data acquired by a gas mark sensor; the ocean observation data comprise air temperature data, air pressure data, wind speed data and wind direction data; the gas mark sensor is arranged on the mother ship; sequentially performing first range inspection and mean value processing on the ocean observation data to obtain ocean observation data subjected to mean value processing; the shore station monitoring end is used for: acquiring ocean observation data after mean value processing; and sequentially carrying out second range inspection, peak inspection and BP neural network data correction on the ocean observation data subjected to mean value processing to obtain corrected ocean observation data.
In a third aspect, the invention provides an electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the wave glider marine observation data quality control method according to the first aspect.
According to the specific embodiments provided by the invention, the following technical effects are disclosed.
The invention includes data inspection and data quality control algorithm correction. The data inspection comprises range inspection and peak inspection, so that abnormal values of the wave glider ocean observation data can be effectively removed; the data quality control algorithm is corrected, the data is further corrected by training a BP neural network model, and the overall accuracy of the corrected marine observation data is further improved, so that the purpose of improving the accuracy of the marine gas interface observation element is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a quality control method for marine observation data of a wave glider according to an embodiment of the present invention.
Fig. 2 is a schematic structural view of a wave glider according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a quality control system for marine observation data of a wave glider according to an embodiment of the present invention.
Fig. 4 is a schematic flow chart of a quality control system for marine observation data of a wave glider according to an embodiment of the present invention.
Fig. 5 is a structural diagram of a BP neural network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
The wave glider is marked with an AIRMAR-BP200 meteorological sensor which is mainly suitable for observing air temperature, air pressure and wind parameters of an unmanned ocean platform. Therefore, the invention carries out data quality control algorithm research on the data observed by the AIRMAR-BP200 meteorological sensor integrated by the wave glider platform so as to improve the accuracy of the sea-air interface observation element.
According to the invention, data quality control research is carried out on meteorological data observed by the marine wave glider, a large number of detailed high-low precision data samples are adopted for model training, further data correction is carried out on the meteorological data subjected to data inspection and inspection, and data accuracy is improved.
Embodiment one: as shown in fig. 1, the method for controlling the quality of the ocean observation data of the wave glider provided by the embodiment of the invention comprises the following steps.
Step 100: the wave glider acquires ocean observation data acquired by the target meteorological sensor; the ocean observation data comprise air temperature data, air pressure data, wind speed data and wind direction data; the weather sensor is mounted on the wave glider.
Step 200: and the wave glider sequentially performs first range inspection and mean processing on the ocean observation data to obtain average processed ocean observation data.
Step 300: and the shore station monitoring end acquires the ocean observation data after mean value processing.
Step 400: and the shore station monitoring end sequentially carries out second range inspection, peak inspection and BP neural network data correction on the marine observation data subjected to mean value processing to obtain corrected marine observation data.
The step 200 specifically includes: 1) And obtaining a normal air temperature threshold range, a normal air pressure threshold range, a normal wind speed threshold range and a normal wind direction threshold range of the acquired sea area according to seasons and longitude and latitude.
2) Comparing the air temperature data in the marine observation data with the air temperature normal threshold range, comparing the air pressure data in the marine observation data with the air pressure normal threshold range, comparing the wind speed data in the marine observation data with the wind speed normal threshold range, comparing the wind direction data in the marine observation data with the wind direction normal threshold range, and eliminating the data which are not in the normal threshold range to obtain the data after the first range inspection.
3) And carrying out mean value processing on the data subjected to the first range inspection to obtain ocean observation data subjected to mean value processing.
2) Comparing the air temperature data in the average value processed marine observation data with the air temperature normal threshold range, comparing the air pressure data in the average value processed marine observation data with the air pressure normal threshold range, comparing the wind speed data in the average value processed marine observation data with the wind speed normal threshold range, comparing the wind direction data in the average value processed marine observation data with the wind direction normal threshold range, and eliminating data which are not in the normal threshold range to obtain data after the second range inspection.
3) And carrying out peak detection on the data subjected to the second range detection to obtain ocean observation data subjected to the peak detection.
4) And performing BP neural network data correction on the ocean observation data after peak inspection to obtain corrected ocean observation data.
Further, the performing BP neural network data correction on the marine observation data after spike inspection to obtain corrected marine observation data specifically includes: inputting the ocean observation data after peak inspection into a BP neural network model to obtain corrected ocean observation data; the BP neural network model is obtained by training the BP neural network by taking the ocean observation data after the standard peak test as an input value and taking the ocean observation data after the high peak test as a true value; the ocean observation data after the standard distribution peak inspection is obtained by processing the ocean observation data collected by the standard distribution image sensor, the ocean observation data after the high distribution peak inspection is obtained by processing the ocean observation data collected by the high distribution image sensor, and the high distribution image sensor is arranged on the wave glider.
The determining process of the marine observation data after the high peak test is the same as the determining process of the marine observation data after the standard peak test, and redundant description is omitted.
Embodiment two: the quality control system for the ocean observation data of the wave glider provided by the embodiment of the invention comprises the wave glider and a shore station monitoring end.
As shown in fig. 2, the wave glider according to the embodiment of the present invention is mainly composed of a surface mother ship 10, an armoured cable 20 and an underwater tractor 30.
As shown in fig. 3, a main control system is disposed in the surface mother ship 10, and the main control system includes a storage module, a main control module, a beidou communication module, and a sensor acquisition and analysis module. The sensor acquisition and analysis module includes a high gas image sensor 40 and a gas image sensor 50.
The main control module is used for: acquiring marine observation data acquired by the target gas image sensor 50; the ocean observation data comprise air temperature data, air pressure data, wind speed data and wind direction data; the mark gas image sensor 50 is mounted on the surface mother ship 10; and sequentially performing first range inspection and mean processing on the ocean observation data to obtain ocean observation data subjected to mean processing.
The shore station monitoring end is used for: acquiring ocean observation data after mean value processing; and sequentially carrying out second range inspection, peak inspection and BP neural network data correction on the ocean observation data subjected to mean value processing to obtain corrected ocean observation data.
And sequentially carrying out second range inspection, peak inspection and BP neural network data correction on the average value processed marine observation data to obtain corrected marine observation data, wherein the shore station monitoring end is used for: 1) And obtaining a normal air temperature threshold range, a normal air pressure threshold range, a normal wind speed threshold range and a normal wind direction threshold range of the acquired sea area according to seasons and longitude and latitude.
2) Comparing the air temperature data in the average value processed marine observation data with the air temperature normal threshold range, comparing the air pressure data in the average value processed marine observation data with the air pressure normal threshold range, comparing the wind speed data in the average value processed marine observation data with the wind speed normal threshold range, comparing the wind direction data in the average value processed marine observation data with the wind direction normal threshold range, and eliminating data which are not in the normal threshold range to obtain data after the second range inspection.
3) And carrying out peak detection on the data subjected to the second range detection to obtain ocean observation data subjected to the peak detection.
4) And inputting the ocean observation data after peak inspection into a BP neural network model to obtain corrected ocean observation data.
The BP neural network model is obtained by training the BP neural network by taking the ocean observation data after the standard peak test as an input value and taking the ocean observation data after the high peak test as a true value; the marine observation data after the spike test is obtained by processing the marine observation data collected by the spike test sensor 50, and the marine observation data after the spike test is obtained by processing the marine observation data collected by the high-altitude gas sensor 40, wherein the high-altitude gas sensor 40 is installed on the surface mother ship 10.
The sensor acquisition and analysis module is used for: marine observations collected by the gas mark sensor 50 and marine observations collected by the high gas mark sensor 40 are acquired and transmitted to the main control module.
The Beidou communication module is used for transmitting the ocean observation data after mean processing to a monitoring end of the shore station.
The storage module is used for: storing the marine observations collected by the gas mark sensor 50 and the marine observations collected by the high gas mark sensor 40; and storing the ocean observation data after mean processing.
One example is: the wave glider ocean observation data quality control system provided by the example comprises the following steps: taking four element parameters of air temperature, air pressure, wind speed and wind direction as an example, additionally integrating a high-distribution GILL-GMX600 meteorological sensor on the basis of integrating and distributing AIRAMR-PB200 meteorological sensors of a wave glider, acquiring a large amount of air temperature data, air pressure data, wind speed data and wind direction data acquired by the two meteorological sensors through a long-term comparison experiment, taking high-precision meteorological data (GILL-GMX 600) as a reference sample through a neural network, and carrying out data correction on the data of a gas distribution imaging sensor (AIRAMR-PB 200) of the wave glider so as to improve the data accuracy of the gas distribution imaging sensor of the wave glider.
The sensor acquisition and analysis module comprises two weather sensors, namely an AIRMAR-BP200 and a GILL-GMX 600. The data collected by the two weather sensors are sea area air temperature, air pressure, wind speed and wind direction, and the weather sensors are integrated in the middle of the water mother ship through flanges. The storage module is used for backing up the collected data. The main control module is used for performing range inspection and mean value processing on the acquired data. The Beidou communication module is used for transmitting the data processed by the main control module to the shore-based monitoring terminal.
As shown in fig. 4, in this example, two weather sensors, i.e., air-BP 200 and GILL-GMX600, mounted on a wave glider collect marine observation data in real time and send the marine observation data to a main control module of the wave glider, wherein the collected data are air temperature, air pressure, wind speed and wind direction; the main control module performs range inspection and average value obtaining processing on the acquired data, and then the data after average value processing is transmitted back to the shore-based monitoring end through the Beidou communication module. After the shore-based monitoring end receives the data, the data is subjected to further range inspection, peak inspection and BP neural network data correction.
Wherein, the acquisition frequency of the meteorological sensor is 1Hz, and the data return frequency is 10 minutes/group.
Further, after the main control module sequentially performs range inspection and average value taking processing on the data collected each time, the result data is transmitted back to the shore-based monitoring system through the Beidou communication module.
The specific process of the main control module for performing range inspection and mean value processing is as follows.
(1) And (3) range inspection: and obtaining the threshold value of the normal range of the acquired sea area air temperature, air pressure, air speed and air direction according to seasons and longitudes, comparing the threshold value range with the received acquired data, judging the data exceeding the threshold value range as an abnormal value, and further eliminating the abnormal value so as to reduce the error of data correction in the follow-up process.
(2) Mean value processing: the mean value processing is to remove the maximum value and the minimum value of the data after the range inspection, add the residual values and divide the residual values by the corresponding numbers so as to obtain the data after the mean value processing.
After receiving the data processed by the mean value of the wave glider main control module, the monitoring station receives the data, and further carries out range inspection, peak inspection and BP neural network data correction.
(1) And (3) range inspection: after receiving data processed by the mean value of the wave glider, the monitoring station firstly carries out range inspection, x i Satisfy the following requirements
（1）。
Judging according to the formula (1), and eliminating the value which does not meet the formula (1).
Wherein x is i The data after the received ith mean value is processed; x is X min And X max The minimum value and the maximum value of the normal threshold range of the air temperature, the air pressure, the wind speed and the wind direction of the acquired sea area are obtained according to seasons and longitude and latitude.
(2) Spike inspection: after the data is subjected to range inspection, the monitoring end of the shore station performs peak inspection. The principle of peak detection is as follows: the change of the observation element in the space and time ranges is limited, and if a certain observation value is obviously different from the surrounding observation values, the peak appears, the abnormal value is judged, and the abnormal value is eliminated.
Employed in the present exampleThe peak inspection method comprises the following steps:
（2）。
wherein H is j1 For peak test parameters, e.g. air pressure peak test parameter H j1-p =0.0028; the air temperature peak test parameter is H j1-t =0.8。
The range inspection and the peak inspection of the wave glider observation data are completed, and the data abnormal influence caused by disturbance of a platform, a marine environment and the like of the wave glider offshore observation is primarily eliminated.
(3) Quality control algorithm: after the peak inspection is completed, the meteorological data enter a data quality control core link: the BP neural network algorithm has the advantages of strong nonlinear approximation capability, sample noise suppression and the like, and therefore the BP neural network is selected for further correction of observed data.
The correction process comprises the following steps: as shown in fig. 5, the BP neural network structure is a two-layer feed-forward network, and comprises a Sigmoid function and a linear output neuron, wherein the Sigmoid function is used for hidden layer neuron output, so that the multidimensional mapping problem can be well fitted, and a nonlinear function can be approximated with any precision as long as hidden layer data of the hidden layer are consistent and enough neurons exist.
And taking the air temperature, air pressure, air speed and wind direction data after peak inspection as training samples, processing the data measured by AIRMAR PB200 as network input, processing the data measured by GILL-GMX600 as a true value, inputting the sample value into the network, and modifying the weight of each layer of the network by the network according to the difference value between the input value and the true value until the difference value of all samples is minimum. The learning algorithm of the network weight samples a Levenberg-Marquardt (LM) back propagation algorithm, which is a standard algorithm of the nonlinear least squares problem, and has good application effect in the neural network structure. In LM algorithm, heuristic parameters are set
The initial value is 0.01, factor->
The maximum training step number is 1000, the network training error is 0.1, and the sample test error target value is 0.1.
Embodiment III: the embodiment of the invention provides an electronic device which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the wave glider ocean observed data quality control method of the embodiment I.
Alternatively, the electronic device may be a server.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (10)
1. A quality control method for marine observation data of a wave glider is characterized by comprising the following steps:
the wave glider acquires ocean observation data acquired by the target meteorological sensor; the ocean observation data comprise air temperature data, air pressure data, wind speed data and wind direction data; the gas mark sensor is arranged on the wave glider;
the wave glider sequentially performs first range inspection and mean value processing on the ocean observation data to obtain average value processed ocean observation data;
the monitoring end of the shore station obtains ocean observation data after mean value processing;
and the shore station monitoring end sequentially carries out second range inspection, peak inspection and BP neural network data correction on the marine observation data subjected to mean value processing to obtain corrected marine observation data.
2. The method for controlling the quality of marine observation data of a wave glider according to claim 1, wherein the wave glider sequentially performs a first range inspection and a mean processing on the marine observation data to obtain the marine observation data after the mean processing, and the method specifically comprises the following steps:
acquiring an air temperature normal threshold range, an air pressure normal threshold range, a wind speed normal threshold range and a wind direction normal threshold range of the acquired sea area according to seasons and longitude and latitude;
comparing air temperature data in the marine observation data with the air temperature normal threshold range, comparing air pressure data in the marine observation data with the air pressure normal threshold range, comparing wind speed data in the marine observation data with the wind speed normal threshold range, comparing wind direction data in the marine observation data with the wind direction normal threshold range, and eliminating data which are not in the normal threshold range to obtain data after primary range inspection;
and carrying out mean value processing on the data subjected to the first range inspection to obtain ocean observation data subjected to mean value processing.
3. The method for controlling the quality of marine observation data of a wave glider according to claim 1, wherein the shore station monitoring end sequentially performs a second range inspection, a peak inspection and BP neural network data correction on the marine observation data after mean processing, and obtains corrected marine observation data, specifically comprising:
acquiring an air temperature normal threshold range, an air pressure normal threshold range, a wind speed normal threshold range and a wind direction normal threshold range of the acquired sea area according to seasons and longitude and latitude;
comparing the air temperature data in the average value processed marine observation data with the air temperature normal threshold range, comparing the air pressure data in the average value processed marine observation data with the air pressure normal threshold range, comparing the wind speed data in the average value processed marine observation data with the wind speed normal threshold range, comparing the wind direction data in the average value processed marine observation data with the wind direction normal threshold range, and eliminating data which are not in the normal threshold range to obtain data after a second range test;
carrying out peak detection on the data subjected to the second range detection to obtain ocean observation data subjected to the peak detection;
and performing BP neural network data correction on the ocean observation data after peak inspection to obtain corrected ocean observation data.
4. The method for controlling the quality of marine observation data of a wave glider according to claim 3, wherein the performing BP neural network data correction on the marine observation data after spike inspection to obtain corrected marine observation data specifically comprises:
inputting the ocean observation data after peak inspection into a BP neural network model to obtain corrected ocean observation data;
the BP neural network model is obtained by training the BP neural network by taking the ocean observation data after the standard peak test as an input value and taking the ocean observation data after the high peak test as a true value;
the marine observation data after the standard distribution peak inspection is obtained by processing marine observation data collected by the standard distribution image sensor, the marine observation data after the high distribution peak inspection is obtained by processing marine observation data collected by the high distribution image sensor, and the high distribution image sensor is arranged on the wave glider.
5. A wave glider marine survey data quality control system, comprising: a wave glider and a shore station monitoring end;
the wave glider at least comprises a water mother ship, an armored cable and an underwater tractor; the water mother ship at least comprises a main control module;
the main control module is used for:
acquiring ocean observation data acquired by a gas mark sensor; the ocean observation data comprise air temperature data, air pressure data, wind speed data and wind direction data; the gas mark sensor is arranged on the mother ship;
sequentially performing first range inspection and mean value processing on the ocean observation data to obtain ocean observation data subjected to mean value processing;
the shore station monitoring end is used for:
acquiring ocean observation data after mean value processing;
and sequentially carrying out second range inspection, peak inspection and BP neural network data correction on the ocean observation data subjected to mean value processing to obtain corrected ocean observation data.
6. The quality control system of marine observation data of a wave glider according to claim 5, wherein in the aspect of sequentially performing a second range check, a spike check and BP neural network data correction on the marine observation data after the mean processing, the shore station monitoring terminal is configured to:
acquiring an air temperature normal threshold range, an air pressure normal threshold range, a wind speed normal threshold range and a wind direction normal threshold range of the acquired sea area according to seasons and longitude and latitude;
comparing the air temperature data in the average value processed marine observation data with the air temperature normal threshold range, comparing the air pressure data in the average value processed marine observation data with the air pressure normal threshold range, comparing the wind speed data in the average value processed marine observation data with the wind speed normal threshold range, comparing the wind direction data in the average value processed marine observation data with the wind direction normal threshold range, and eliminating data which are not in the normal threshold range to obtain data after a second range test;
carrying out peak detection on the data subjected to the second range detection to obtain ocean observation data subjected to the peak detection;
inputting the ocean observation data after peak inspection into a BP neural network model to obtain corrected ocean observation data;
the BP neural network model is obtained by training the BP neural network by taking the ocean observation data after the standard peak test as an input value and taking the ocean observation data after the high peak test as a true value;
the marine observation data after the standard distribution peak inspection is obtained by processing the marine observation data collected by the standard distribution imaging sensor, the marine observation data after the high distribution peak inspection is obtained by processing the marine observation data collected by the high distribution imaging sensor, and the high distribution imaging sensor is arranged on the mother ship.
7. The wave glider marine survey data quality control system of claim 6, wherein the surface mother vessel further comprises a sensor acquisition and analysis module;
the sensor acquisition and analysis module comprises a high gas distribution image sensor and a gas distribution image sensor which are connected;
the sensor acquisition and analysis module is used for: and acquiring the ocean observation data acquired by the gas mark sensor and the ocean observation data acquired by the high gas mark sensor, and transmitting the ocean observation data and the ocean observation data to the main control module.
8. The wave glider marine survey data quality control system of claim 5, wherein the surface mother ship further comprises a Beidou communication module;
the Beidou communication module is used for transmitting the ocean observation data after mean processing to a monitoring end of the shore station.
9. The wave glider marine survey data quality control system of claim 7, wherein the surface mother vessel further comprises a storage module;
the storage module is used for:
storing the ocean observation data collected by the gas mark sensor and the ocean observation data collected by the high gas mark sensor;
and storing the ocean observation data after mean processing.
10. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform a wave glider marine survey data quality control method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310286271.7A CN116027460B (en) | 2023-03-23 | 2023-03-23 | Quality control method and system for ocean observation data of wave glider and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310286271.7A CN116027460B (en) | 2023-03-23 | 2023-03-23 | Quality control method and system for ocean observation data of wave glider and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116027460A true CN116027460A (en) | 2023-04-28 |
| CN116027460B CN116027460B (en) | 2023-07-14 |
Family
ID=86074293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310286271.7A Active CN116027460B (en) | 2023-03-23 | 2023-03-23 | Quality control method and system for ocean observation data of wave glider and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116027460B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130274964A1 (en) * | 2012-04-16 | 2013-10-17 | Flight Data Services Limited | Flight data monitoring and validation |
| US20190196062A1 (en) * | 2017-12-22 | 2019-06-27 | Ernest Wilson Coleman | Storm warning method and apparatus |
| CN111717359A (en) * | 2020-06-12 | 2020-09-29 | 西北工业大学 | Wave glider with evaporation waveguide monitoring system |
| CN111913237A (en) * | 2020-08-10 | 2020-11-10 | 中国海洋大学 | Large-scale buoy oceanographic monitoring system of intermediate latitude |
| CN112000654A (en) * | 2020-08-25 | 2020-11-27 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | High-speed railway strong wind monitoring data quality control method and device |
| KR20210053562A (en) * | 2019-11-04 | 2021-05-12 | 세종대학교산학협력단 | Quality control method and apparatus of global climate data |
-
2023
- 2023-03-23 CN CN202310286271.7A patent/CN116027460B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130274964A1 (en) * | 2012-04-16 | 2013-10-17 | Flight Data Services Limited | Flight data monitoring and validation |
| US20190196062A1 (en) * | 2017-12-22 | 2019-06-27 | Ernest Wilson Coleman | Storm warning method and apparatus |
| KR20210053562A (en) * | 2019-11-04 | 2021-05-12 | 세종대학교산학협력단 | Quality control method and apparatus of global climate data |
| CN111717359A (en) * | 2020-06-12 | 2020-09-29 | 西北工业大学 | Wave glider with evaporation waveguide monitoring system |
| CN111913237A (en) * | 2020-08-10 | 2020-11-10 | 中国海洋大学 | Large-scale buoy oceanographic monitoring system of intermediate latitude |
| CN112000654A (en) * | 2020-08-25 | 2020-11-27 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | High-speed railway strong wind monitoring data quality control method and device |
Non-Patent Citations (1)
| Title |
|---|
| 谭哲韬 等: "海洋观测数据质量控制技术研究现状及展望", 《中国科学:地球科学》, vol. 52, no. 3, pages 422 - 423 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116027460B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108230302B (en) | Detection and disposal method for marine organism invading from cold source sea area of nuclear power plant | |
| CN109900256B (en) | Self-adaptive ocean mobile acoustic tomography system and method | |
| CN112070234B (en) | Water chlorophyll and phycocyanin land-based remote sensing machine learning algorithm under complex scene | |
| CN111965608A (en) | Satellite-borne marine laser radar detection capability evaluation method based on water body chlorophyll concentration | |
| CN115342814B (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| CN115062527A (en) | Geostationary satellite sea temperature inversion method and system based on deep learning | |
| CN114492680A (en) | Buoy data quality control method and device, computer equipment and storage medium | |
| CN114018317B (en) | Data acquisition device and method for marine environment | |
| Viselli et al. | Validation of the first LiDAR wind resource assessment buoy system offshore the Northeast United States | |
| CN115659138A (en) | Underwater measurement signal noise reduction method based on dynamic water interference environment electromagnetic method | |
| CN116108995A (en) | Tidal river reach ship oil consumption prediction method and device and electronic equipment | |
| Krasnopolsky et al. | A multi-parameter empirical ocean algorithm for SSM/I retrievals | |
| CN116027460B (en) | Quality control method and system for ocean observation data of wave glider and electronic equipment | |
| CN106872979B (en) | Sea wave parameter acquisition method based on sea surface fluctuation moving target SAR image refocusing | |
| CN109374581A (en) | Water colour monitoring device based on spectrum monitoring system SAS | |
| CN110208808B (en) | Passive sonar non-cooperative target line spectrum information fusion method | |
| CN109143191B (en) | Method for improving all-terrain fine detection capability of airborne radar | |
| CN116973977B (en) | Self-adaptive denoising method for high-speed mobile platform low-frequency electric field target detection | |
| CN116242584A (en) | Floating ocean platform along with ship wave measuring device based on BP neural network | |
| CN114296046B (en) | HFSWR multi-sea-condition effective wave height extraction method and device based on artificial neural network | |
| Hageman et al. | Feasibility of using hindcast data for fatigue assessment of permanently moored offshore units in West-Africa | |
| CN111381233A (en) | Underwater confrontation situation display and control method and system | |
| CN111708007B (en) | Target depth identification method and system based on modal scintillation index matching analysis | |
| CN115062526A (en) | Deep learning-based three-dimensional ionosphere electron concentration distribution model training method | |
| CN118311576B (en) | Dual-polarized SAR shallow sea water depth inversion construction method based on physical constraint 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |