CN111461401B - Position reporting method based on marine environment - Google Patents
Position reporting method based on marine environment Download PDFInfo
- Publication number
- CN111461401B CN111461401B CN202010149749.8A CN202010149749A CN111461401B CN 111461401 B CN111461401 B CN 111461401B CN 202010149749 A CN202010149749 A CN 202010149749A CN 111461401 B CN111461401 B CN 111461401B
- Authority
- CN
- China
- Prior art keywords
- delay
- prediction model
- success rate
- entering
- transmission
- 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.)
- Active
Links
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
- G06N3/045—Combinations of networks
Abstract
The invention discloses a position reporting method based on a marine environment, which comprises the following steps: step 1: collecting environmental parameters to calculate success rate and waiting delay; step 2: judging whether the success rate is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 4; and step 3: clearing the count and reporting the bit; and 4, step 4: judging whether the count is approximately equal to a set threshold value, if so, entering a step 3, otherwise, entering a step 5; and 5: waiting for delay, and entering step 6 after the delay is finished; step 6: counting by +1, and returning to the step 1, compared with the position reporting method with a fixed period in the prior art, the position reporting method based on the marine environment improves the position reporting success rate and prolongs the working time.
Description
Technical Field
The invention relates to the technical field of position reporting of pilots after distress on the sea, in particular to a position reporting method based on the sea environment.
Background
The dangerous situations of the pilots on the sea are mostly far away from the continents, the distress information is reported mainly by a satellite system, the reliable acquisition of the distress position is the basis of the success of maritime search and rescue, and the satellite system which can be used for global search and rescue at present mainly comprises a global satellite search and rescue system (COSPAS/SARSAT), a Beidou satellite navigation system in China and the like. The invention patent (publication number: CN106353774B) discloses an intelligent Beidou search and rescue position reporting instrument and a method for carrying out search and rescue position reporting based on the position reporting instrument, one set of equipment realizes intelligent triggering of various sensors under the lifesaving condition, and has the advantages of saving electric energy, prolonging the position reporting time and the like. In the prior art, the distress call equipment usually carries out position reporting in a preset time period, but the position reporting is influenced by various factors such as severe weather, equipment immersion, difficulty in antenna pair to stars and the like, so that the position reporting is low in agility and reliability, and is difficult to reconcile with the contradiction of long-time work.
Accordingly, the invention is particularly directed to.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a position reporting method based on the marine environment, and compared with the position reporting method with a fixed period in the prior art, the method provided by the invention has the advantages that the position reporting success rate is improved, and the working time is prolonged.
The technical scheme of the invention is realized as follows:
a position reporting method based on marine environment comprises the following steps:
step 1: collecting environmental parameters to calculate success rate and waiting delay;
step 2: judging whether the success rate is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 4;
and step 3: clearing the count and reporting the bit;
and 4, step 4: judging whether the count is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 5;
and 5: waiting for delay, and entering step 6 after the delay is finished;
step 6: counting by +1, and returning to the step 1;
calculating the success rate through a transmission success rate prediction model, wherein the transmission success rate prediction model is a neural network model, inputting the current equipment pitch angle, longitude, latitude, barometric altitude, acceleration direction, received signal strength, speed, immersion, environment temperature, environment humidity, barometric pressure, residual electric quantity, Beijing time and working time, and outputting the success rate;
and calculating the delay time through a transmission delay prediction model, wherein the transmission delay prediction model is a neural network model, the acceleration direction and the pitch angle of the equipment in the past 10 seconds per second are input, and the output is the delay time.
Further, in step 5, it is determined whether the delay time calculated by the transmission delay prediction model is greater than or equal to the set maximum delay time, if so, the delay is performed according to the set maximum delay time, and if not, the delay is performed according to the delay time calculated by the transmission delay prediction model.
Further, the launch success rate prediction model is a DNN model and comprises 3 hidden layers and a softmax layer which are sequentially connected, wherein the 3 hidden layers all comprise 32 neurons, and during calculation, the current pitch angle, longitude, latitude, barometric altitude, acceleration direction, received signal strength, speed, immersion, ambient temperature, ambient humidity, barometric pressure, residual electric quantity, Beijing time and working time of the device are converted into single-precision floating points to be input into the launch success rate prediction model, and finally the success rate is output by the softmax layer.
Further, neurons in the network of the launch success rate prediction model use the corrective linear elements as activation functions.
Further, in the network of the transmission success rate prediction model, the loss value of the network is calculated by using the cross entropy.
Further, the emission delay prediction model is a DNN model and comprises a reshape layer and 10 hidden layers which are sequentially connected, the hidden layers are Recurrent Neural Networks (RNN), during calculation, the acceleration direction and the pitch angle of the device in the past 10 seconds per second are converted into single-precision floating point numbers and input into the reshape layer, the reshape layer enables a matrix of 3 x 10 to be reshaped into 1 x 30 one-dimensional data and input into the first layer of Recurrent Neural Networks (RNN), and finally the last layer of Recurrent Neural Networks (RNN) outputs delay time.
Further, neurons in the network that emit the delay prediction model use the corrective linear elements as activation functions.
Further, in the network transmitting the delay prediction model, a loss value of the network is calculated by using a quadratic cost function.
The invention has the beneficial effects that: compared with the bit reporting method with a fixed period in the center in the prior art, the method provided by the invention has the advantages that the bit reporting success rate is improved, and the working time is prolonged.
Drawings
Fig. 1 is a block diagram of a transmission success rate prediction model;
fig. 2 is a block diagram of a transmission delay prediction model.
Detailed Description
In order to make the technical solutions of the present invention better understood, the following description of the technical solutions of the present invention with reference to the accompanying drawings of the present invention is made clearly and completely, and other similar embodiments obtained by a person of ordinary skill in the art without any creative effort based on the embodiments in the present application shall fall within the protection scope of the present application.
The first embodiment is as follows:
a position reporting method based on marine environment comprises the following steps:
step 1: collecting environmental parameters to calculate success rate and waiting delay;
step 2: judging whether the success rate is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 4;
and step 3: clearing the count and reporting the bit;
and 4, step 4: judging whether the count is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 5;
and 5: waiting for delay, and entering step 6 after the delay is finished;
step 6: count +1 and return to step 1.
In the embodiment, the success rate is calculated through a transmission success rate prediction model, the transmission success rate prediction model is a neural network model, the input includes the current equipment pitch angle, longitude, latitude, barometric altitude, acceleration direction, received signal strength, speed, immersion, ambient temperature, ambient humidity, barometric pressure, residual electric quantity, Beijing time and working time, and the output includes the success rate; and calculating the delay time through a transmission delay prediction model, wherein the transmission delay prediction model is a neural network model, the acceleration direction and the pitch angle of the equipment in the past 10 seconds per second are input, and the output is the delay time.
Preferably, in step 5, it is determined whether the delay time calculated by the transmission delay prediction model is greater than or equal to the set maximum delay time, if so, the delay is performed according to the set maximum delay time, and if not, the delay is performed according to the delay time calculated by the transmission delay prediction model.
In this embodiment, the launch success rate prediction model is preferably a DNN model, and the structure of the launch success rate prediction model is as shown in fig. 1, and the launch success rate prediction model includes 3 hidden layers and a softmax layer which are sequentially connected, where each of the 3 hidden layers includes 32 neurons, and when calculating, the launch success rate prediction model is input by converting current equipment pitch angle, longitude, latitude, barometric altitude, acceleration direction, received signal strength, speed, whether the equipment is immersed in water, ambient temperature, ambient humidity, barometric pressure, remaining battery capacity, beijing time, and operating time into a single-precision floating point number, and finally the success rate is output by the softmax layer.
The present embodiment further optimizes and designs a transmission success rate prediction model, in which neurons in a network of the transmission success rate prediction model use a correction linear unit (ReLU) as an activation function, and the formula is as follows:
in the embodiment, the transmission success rate prediction model is further optimized and designed as follows, in the network of the transmission success rate prediction model, the cross entropy is used to calculate the loss value of the network, and the calculation formula is as follows:
in this embodiment, preferably, the emission delay prediction model is a DNN model, and the structure of the emission delay prediction model is as shown in fig. 2, and includes a reshape layer and 10 hidden layers connected in sequence, where the hidden layer is a recurrent neural network RNN, during calculation, the device acceleration, the acceleration direction, and the pitch angle of the past 10 seconds per second are converted into single-precision floating point numbers and input to the reshape layer, the reshape layer inputs one-dimensional data obtained by reshaping a 3 × 10 matrix into 1 × 30 to the first layer of recurrent neural network RNN, and finally, the last layer of recurrent neural network RNN outputs the delay time.
The present embodiment also optimally designs the transmission delay prediction model, in which neurons in the network use a corrective linear unit (ReLU) as an activation function.
In this embodiment, the transmission delay prediction model is further optimized as follows, and in the network of the transmission delay prediction model, a quadratic cost function is used to calculate a loss value of the network, and a calculation formula is as follows:
in the embodiment, a total of 10582 pieces of available experimental data are acquired to carry out unified training and testing on the transmission success rate prediction model and the transmission delay prediction model, the experimental points acquired by the experimental data are mainly located in coastal areas of Shandong, Hebei and Liaoning in China, the time spans four seasons, the highest grade 3 sea condition is achieved, and the weather comprises clear weather, cloudy weather and light rain. The environmental state parameters are all corresponded by using the communication success rate, the next approximate 0 value data in the continuously collected pitch angle data is searched, and the time difference between the next approximate 0 value data and the current data is used as a delay value for marking. The specific distribution of 10582 available experimental data is shown in table 1:
TABLE 1 data set sample distribution
| Data set | Number of positive samples | Number of negative samples | Total number of samples |
| Training set | 3820 | 6180 | 10000 |
| Test set | 204 | 378 | 582 |
| Total up to | 4024 | 6558 | 10582 |
In this embodiment, 30 ten thousand iterative trainings are performed on the transmission success rate prediction model and the transmission delay prediction model. After iterative training, actual measurement is performed, and 6 devices with the same hardware are used for actual measurement in total, wherein 3 devices report positions by using the method of the embodiment, that is, the method of the embodiment is repeated until the electric quantity of the device is used up, the success rate threshold is set to 0.8, the count threshold is set to 5, the maximum delay time is set to 10 seconds, in addition, 3 devices report positions by using the traditional method with a preset time period, the preset time period is once reported every thirty minutes before, and once reported every thirty minutes after thirty minutes until the electric quantity of the device is used up, and the test results are shown in table 2:
TABLE 2 test results
In summary, by using the bit reporting method of the present embodiment, compared with the conventional method, the bit reporting success rate is increased from 36.3% to 73.3%, and the working time is prolonged from 6.0 hours to 8.6 hours.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (8)
1. A position reporting method based on marine environment is characterized by comprising the following steps:
step 1: collecting environmental parameters to calculate success rate and waiting delay;
step 2: judging whether the success rate is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 4;
and step 3: clearing the count and reporting the bit;
and 4, step 4: judging whether the count is greater than or equal to a set threshold value, if so, entering a step 3, and otherwise, entering a step 5;
and 5: waiting for delay, and entering step 6 after the delay is finished;
step 6: counting by +1, and returning to the step 1;
calculating the success rate through a transmission success rate prediction model, wherein the transmission success rate prediction model is a neural network model, inputting the current equipment pitch angle, longitude, latitude, barometric altitude, acceleration direction, received signal strength, speed, immersion, environment temperature, environment humidity, barometric pressure, residual electric quantity, Beijing time and working time, and outputting the success rate;
and calculating the delay time through a transmission delay prediction model, wherein the transmission delay prediction model is a neural network model, the acceleration direction and the pitch angle of the equipment in the past 10 seconds per second are input, and the output is the delay time.
2. The method according to claim 1, wherein in step 5, it is determined whether the delay time calculated by the transmission delay prediction model is greater than or equal to a set maximum delay time, if so, the delay is performed according to the set maximum delay time, otherwise, the delay is performed according to the delay time calculated by the transmission delay prediction model.
3. The method as claimed in claim 1, wherein the launch success rate prediction model is a DNN model, and includes 3 hidden layers and a softmax layer which are sequentially connected, each of the 3 hidden layers includes 32 neurons, and during calculation, the current device pitch angle, longitude, latitude, barometric altitude, acceleration direction, received signal strength, speed, immersion, ambient temperature, ambient humidity, barometric pressure, remaining capacity, beijing time and working time are converted into a single-precision floating point number, input into the launch success rate prediction model, and finally output by the softmax layer.
4. A method of bit reporting based on offshore environment as claimed in claim 2, characterized in that neurons in the network of transmission success rate prediction model use corrective linear elements as activation functions.
5. The method of claim 2, wherein the cross entropy is used to calculate the loss value of the network in the network transmitting the success rate prediction model.
6. The bit reporting method based on the offshore environment as recited in claim 1, wherein the transmission delay prediction model is a DNN model and includes a reshape layer and 10 hidden layers connected in sequence, the hidden layers are recurrent neural networks RNN, during calculation, the device acceleration, the acceleration direction and the pitch angle of the last 10 seconds per second are converted into single-precision floating point numbers and input into the reshape layer, the reshape layer reshapes the matrix of 3 × 10 into 1 × 30 one-dimensional data and input into the first layer of recurrent neural networks RNN, and finally the last layer of recurrent neural networks RNN outputs the delay time.
7. The marine environment-based bit reporting method of claim 6, wherein neurons in the network transmitting the delay prediction model use a corrective linear element as an activation function.
8. The method of claim 6, wherein the loss value of the network is calculated by using a quadratic cost function in the network transmitting the delay prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010149749.8A CN111461401B (en) | 2020-03-06 | 2020-03-06 | Position reporting method based on marine environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010149749.8A CN111461401B (en) | 2020-03-06 | 2020-03-06 | Position reporting method based on marine environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461401A CN111461401A (en) | 2020-07-28 |
| CN111461401B true CN111461401B (en) | 2021-07-20 |
Family
ID=71682678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010149749.8A Active CN111461401B (en) | 2020-03-06 | 2020-03-06 | Position reporting method based on marine environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461401B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3777935B2 (en) * | 2000-01-26 | 2006-05-24 | 松下電工株式会社 | Reporting system |
| WO2017045109A1 (en) * | 2015-09-14 | 2017-03-23 | Qualcomm Incorporated | Position determination of a mobile device in an emergency |
| CN106353774B (en) * | 2016-11-25 | 2019-01-04 | 西安航光卫星测控技术有限公司 | Intelligent Beidou searches and rescues report position instrument and its searches and rescues report position method |
| CN106443716A (en) * | 2016-11-25 | 2017-02-22 | 西安航光卫星测控技术有限公司 | Charging detection box of Beidou search and rescue position indicator |
| CN107064978B (en) * | 2017-05-03 | 2019-09-10 | 东南大学 | First aid helicopter navigation positioning system and its navigation locating method based on Beidou |
| CN109886499B (en) * | 2019-03-04 | 2020-02-07 | 中国地质大学（武汉） | Offshore distress target drift set prediction method considering feedback information |
| CN110749324A (en) * | 2019-10-28 | 2020-02-04 | 深圳市赛为智能股份有限公司 | Unmanned aerial vehicle rescue positioning method and device, computer equipment and storage medium |
-
2020
- 2020-03-06 CN CN202010149749.8A patent/CN111461401B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461401A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111336996A (en) | Marine environment and ship motion monitoring and forecasting system and monitoring and forecasting method | |
| CN111428942B (en) | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology | |
| CN110826693A (en) | Three-dimensional atmospheric temperature profile inversion method and system based on DenseNet convolutional neural network | |
| CN114828214A (en) | Information fusion maritime search and rescue wireless sensor network positioning method | |
| CN113255239B (en) | Deep learning method for predicting icing thickness of ultrahigh voltage transmission line tower | |
| CN116794621A (en) | Fusion diagnosis method for electromagnetic wave propagation loss | |
| CN111461401B (en) | Position reporting method based on marine environment | |
| CN109187062B (en) | Shipborne equipment on-duty service life profile making method | |
| CN112084955B (en) | High-voltage line detection and identification method and device and electronic equipment | |
| CN114018317A (en) | Data acquisition device and method for marine environment | |
| CN115423810B (en) | Blade icing form analysis method for wind generating set | |
| CN116070735A (en) | Yellow sea green tide distribution area based on side length and azimuth difference rule and drift prediction initial field manufacturing method thereof | |
| CN112650116B (en) | Marine environment monitoring system based on Internet of things | |
| CN115115138A (en) | Offshore storm surge water increase prediction method | |
| Curtis et al. | An analysis of the lightning jump algorithm using geostationary lightning mapper flashes | |
| CN114358667A (en) | Scenic spot risk prediction model construction method based on RBF (radial basis function) network learning | |
| CN116258896B (en) | Quasi-real-time red tide monitoring method based on space-space integration | |
| CN117131783B (en) | Multi-mode learning-based power transmission line risk prediction model, method and system | |
| CN113281792B (en) | GPS P (Y) signal power enhancement monitoring method | |
| CN115311826B (en) | Speech platform power disaster early warning method based on intelligent recognition | |
| CN117574329B (en) | Nitrogen dioxide refined space distribution method based on ensemble learning | |
| CN116027460B (en) | Quality control method and system for ocean observation data of wave glider and electronic equipment | |
| CN117421601B (en) | Sea surface evaporation waveguide near-future rapid forecasting method | |
| Chen et al. | Effects of GPV datasets on WRF modelling of ocean surface wind in rough seas | |
| CN115755223A (en) | Individual squall wind prediction method, system and medium |
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 |