CN110987066A - Ocean wind speed and direction measuring method and system capable of achieving automatic correction - Google Patents
Ocean wind speed and direction measuring method and system capable of achieving automatic correction Download PDFInfo
- Publication number
- CN110987066A CN110987066A CN201911173949.0A CN201911173949A CN110987066A CN 110987066 A CN110987066 A CN 110987066A CN 201911173949 A CN201911173949 A CN 201911173949A CN 110987066 A CN110987066 A CN 110987066A
- Authority
- CN
- China
- Prior art keywords
- ship
- wind speed
- neural network
- elman neural
- simulated annealing
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012937 correction Methods 0.000 title description 4
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 53
- 230000002068 genetic effect Effects 0.000 claims abstract description 38
- 238000002922 simulated annealing Methods 0.000 claims abstract description 38
- 238000013528 artificial neural network Methods 0.000 claims abstract description 33
- 238000005259 measurement Methods 0.000 claims abstract description 23
- 238000003062 neural network model Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 6
- 108090000623 proteins and genes Proteins 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 4
- 238000010353 genetic engineering Methods 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 9
- 238000001514 detection method Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 4
- 238000000137 annealing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 208000033999 Device damage Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005183 dynamical system Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012224 gene deletion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004540 process dynamic Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P13/00—Indicating or recording presence, absence, or direction, of movement
- G01P13/02—Indicating direction only, e.g. by weather vane
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
- G01P5/24—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft by measuring the direct influence of the streaming fluid on the properties of a detecting acoustical wave
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Aviation & Aerospace Engineering (AREA)
- Navigation (AREA)
Abstract
The utility model provides a measuring method and a system for automatically correcting ocean wind speed and direction, wherein the measuring method comprises the following steps: acquiring measurement data of a ship to be measured; and constructing an Elman neural network model optimized based on a genetic simulated annealing algorithm, inputting the acquired measurement data of the ship to be tested into the trained Elman neural network model optimized based on the genetic simulated annealing algorithm, and outputting the corrected real wind speed and direction. The Elman neural network is optimized by adopting a method combining a genetic algorithm and a simulated annealing algorithm, the Elman neural network model optimized based on the genetic simulated annealing algorithm is obtained, the corrected real wind speed and direction can be rapidly and accurately output according to the model, errors are reduced, the measured marine true wind data is more accurate, the navigation control of the ship can be guided according to the marine true wind data, and the safety of the sailing ship is improved.
Description
Technical Field
The disclosure relates to the technical field of sea wind speed and direction correlation, in particular to a sea wind speed and direction measurement method and system for achieving automatic correction.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The ocean true wind has important meteorological navigation significance to ships sailing at sea, and if the true wind is measured and calculated inaccurately, misjudgment can be caused to a navigator to influence the safe sailing of the ships, so that the ocean true wind has an important role in the field of ocean weather research to influence the sailing safety and ocean development of the ships. Ocean true wind cannot be directly measured on motion platforms such as ships.
The inventor finds that conventional mechanical anemometers commonly used in the conventional wind speed measurement include a wing-shaped anemometer, a cup-shaped anemometer, a propeller-type anemometer, and the like, and these measurement devices mainly determine the wind speed and the wind direction by the speed and the angle of a rotating member. Over time, frictional degradation of rotating parts tends to cause damage to the parts and thus affect wind speed measurements. In addition, the wind speed and the wind direction detected on the moving platform are relative wind speed and wind direction, model solution is adopted, and measurement errors are combined with the posture change of the ship body, so that the solution model is complex, the judgment timeliness is poor, the wind direction data cannot be output in real time, and potential safety hazards exist in ship navigation.
Disclosure of Invention
The method and the system can measure the wind speed and the wind direction of the ocean true wind efficiently and accurately, automatically correct errors in the measuring process through an Elman neural network model optimized based on a genetic simulation annealing algorithm, obtain accurate data of the ocean true wind, improve the timeliness of data processing by adopting an artificial intelligence method, obtain the true wind data in real time, and are beneficial to guiding the navigation control of a ship according to the ocean true wind data and improve the safety of the sailing ship.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
the first aspect of the disclosure provides a measurement method for automatically correcting ocean wind speed and direction, which includes the following steps:
acquiring measurement data of a ship to be measured;
and constructing an Elman neural network model optimized based on a genetic simulated annealing algorithm, inputting the acquired measurement data of the ship to be tested into the trained Elman neural network model optimized based on the genetic simulated annealing algorithm, and outputting the corrected real wind speed and direction.
The second aspect of the present disclosure provides an ultrasonic measurement system for automatically correcting the wind speed and the wind direction of the ocean, which includes an ultrasonic sensor, a GPS module, an electronic compass module and a microprocessor; the ultrasonic sensor, the GPS module and the electronic compass module are respectively connected with the microprocessor and are respectively used for acquiring the relative wind speed and direction on the ship, the ship speed and the ship course, and transmitting the acquired data to the microprocessor, and the microprocessor executes the ultrasonic measuring method for automatically correcting the ocean wind speed and direction.
A third aspect of the present disclosure proposes an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, the computer instructions, when executed by the processor, performing the steps of the above method.
A fourth aspect of the present disclosure proposes a computer-readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the above-mentioned method.
Compared with the prior art, the beneficial effect of this disclosure is:
according to the method, the Elman neural network model optimized based on the genetic simulation annealing algorithm is established, on one hand, the artificial intelligence algorithm is adopted to improve the working efficiency and the intelligence of the system, on the other hand, various factors influencing the judgment of the ocean true wind on the ship are considered, the detection data of the ship to be detected is input into the model, the real wind speed and the wind direction after the correction can be rapidly and accurately output according to the model, errors are reduced, the measured ocean true wind data are more accurate, the navigation control of the ship can be guided according to the ocean true wind data, and the safety of the sailing ship is improved.
The method combining the genetic algorithm and the simulated annealing algorithm is adopted in the Elman neural network model training, the problem that the global optimal solution cannot be obtained or the convergence rate is low is solved, the genetic simulated annealing algorithm is formed by combining the genetic algorithm and the simulated annealing algorithm, the global optimal solution can be obtained, a large number of iteration times can be reduced, and the algorithm efficiency is high.
This is disclosed and is adopted ultrasonic sensor to detect ocean wind speed, has reduced the measuring error that the sensor arouses because of mechanical device damages.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure.
FIG. 1 is a block diagram of a system in accordance with one or more embodiments;
FIG. 2 is a flow chart of a measurement method according to embodiment 1 of the disclosure;
fig. 3 is a schematic structural diagram of an Elman neural network of embodiment 1 of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments in the present disclosure may be combined with each other. The embodiments will be described in detail below with reference to the accompanying drawings.
Example 1
In the technical solution disclosed in one or more embodiments, as shown in fig. 1, an ultrasonic measuring system for automatically correcting the wind speed and the wind direction of ocean comprises an ultrasonic sensor, a GPS module, an electronic compass module and a microprocessor; the ultrasonic sensor, the GPS module and the electronic compass module are respectively connected with the microprocessor and are respectively used for acquiring the relative wind speed and direction, the ship speed and the ship course on the ship and transmitting the acquired data to the microprocessor.
The ultrasonic sensor comprises an ultrasonic transducer, an ultrasonic driving module and an ultrasonic receiving module; the ultrasonic sensor is fixed on a sailing ship, and the measured relative wind speed and direction are obtained.
The ultrasonic driving module generates a high-frequency alternating electric field to drive the ultrasonic transducer;
the ultrasonic transducer is used for converting the wind speed signal into a sound wave signal; optionally, the ultrasonic wave can be transmitted and received by using a transmitting-receiving integrated ultrasonic transducer, and the measurement of the wind speed and the wind direction in the horizontal direction can be realized by using the ultrasonic transducer.
The ultrasonic receiving module amplifies, filters and detects the peak envelope of the ultrasonic signals to obtain ultrasonic analog signals, and the analog signals are converted into digital signals by the A/D converter.
As an implementable structure, the ultrasonic signal receiving module includes an amplifying circuit, a peak envelope detecting circuit, and a voltage comparing circuit.
Optionally, the amplifying circuit comprises an operational amplifier and an RC network electrically connected to amplify a signal of several millivolts or tens of millivolts.
Optionally, the peak envelope detection circuit may include a detection diode and an RC passive low-pass filter electrically connected to perform peak envelope detection on the amplified ultrasonic signal to extract an effective leading edge signal.
Optionally, the voltage comparison circuit is used for obtaining the arrival time of the ultrasonic signal. An LM193 voltage comparator is used. Setting a voltage value, when the detection signal exceeds the voltage value, the circuit outputs a high level signal, and when the detection signal is less than the voltage value, the circuit outputs a zero level; the acquired signal is finally transmitted to ZYNQ.
The data processing can adopt a fully programmable system-on-chip ZYNQ, the ARM processor is used for completing software implementation, the ZYNQ is used for completing hardware implementation, and optionally, data measured by the ultrasonic sensor and data measured by the GPS module and the electronic compass module are processed on the ZYNQ.
The ultrasonic sensor is fixed on a sailing ship, relative wind speed and wind direction are measured, and the real wind speed and wind direction of the ocean during the movement of the ship are calculated by using the ship speed measured by the GPS module and the ship course measured by the electronic compass.
The ship can be influenced by sea waves to swing back and forth in the process of sailing, so that errors occur in the relative wind speed and direction measured by the sensor, and calculation of the real wind speed and direction is influenced. In order to reduce the error, optionally, the system further comprises a gyroscope sensor arranged on the ship and used for measuring the angular velocity of the ship during sailing, and the gyroscope sensor is connected with the microprocessor and used for transmitting the collected angular velocity to the microprocessor in real time.
The embodiment also provides a measuring method for automatically correcting the ocean wind speed and direction, provides an Elman neural network model optimized based on a genetic simulated annealing algorithm and trains the Elman neural network model, and can quickly and accurately output the corrected real wind speed and direction according to the model. The method can comprise the following steps:
step 1, obtaining measurement data of a ship to be measured; the measurement data of the ship to be measured comprise the wind speed and the wind direction of relative wind on the ship, the ship speed, the ship course and the ship navigation angular speed which are obtained by the measurement of a sensor arranged on the ship;
and 2, constructing an Elman neural network model optimized based on the genetic simulated annealing algorithm, inputting the acquired measurement data of the ship to be tested into the trained Elman neural network model optimized based on the genetic simulated annealing algorithm, and outputting the corrected real wind speed and direction.
The Elman neural network model optimized based on the genetic simulated annealing algorithm is a model obtained by optimizing a weight matrix of the Elman neural network by adopting a method combining the genetic algorithm and the simulated annealing algorithm.
In step 1, the ultrasonic sensor arranged on the ship is used for detecting the relative wind on the ship, namely the wind speed and the wind direction of the synthetic wind, the ship speed can be measured through a GPS module arranged on the ship, the ship course can be measured through an electronic compass, and the ship navigation angular speed can be measured through a gyroscope sensor.
Wind speed is a constantly changing data, factors influencing the wind speed are many, temperature, air pressure, ship swing and the like, and the change of the wind speed is random, so that the wind speed measurement is a nonlinear function problem. Neural networks may implement non-linear mapping of inputs to outputs. And the Elman neural network can be used for modeling and learning the nonlinear dynamical system, solves the problem of discrete time series and has strain adaptive to the time series.
The method comprises the steps of constructing an Elman neural network model optimized based on a genetic simulated annealing algorithm, specifically establishing the Elman neural network, and optimizing by adopting the genetic simulated annealing algorithm to obtain an optimal weight matrix of the Elman neural network.
The Elman neural network model optimized based on the genetic simulated annealing algorithm outputs the corrected wind speed and direction of the real sea wind, compensates the measurement errors of wind speed and direction caused by various factors in the measurement process, and realizes the error compensation of wind speed and direction in the swinging state.
In some embodiments, as shown in fig. 2, the Elman neural network is a feedback type neural network, and includes an input layer, an implicit layer, a connection layer, and an output layer, where the connection layer functions as a time delay operator, and is mainly used to memorize and store an output value at a previous time of the implicit layer, so that the Elman neural network can process dynamic information.
Wherein, the mathematical model of the Elman neural network is as follows:
x(k)＝f(W1xC(k)+W2u(k-1))
xC(k)＝α·xC(k-1)+x(k-1)
yk＝g(W3x(k))
wherein, W1A connection weight matrix of the connection layer and the hidden layer; w2A connection weight matrix of the input layer and the hidden layer; w3A connection weight matrix of the hidden layer and the output layer; x is the number ofC(k) Refer to a connection layer output vector, x (k) refer to a hidden layer output vector, u (k) refer to an input vector, ykRefers to the output vector, 0 ≦ α<1, represents the self-chaining feedback gain factor.
The method is a process of learning and training set data based on a learning process of an Elman neural network model optimized by a genetic simulated annealing algorithm, and aims to obtain dynamic characteristics between input and output and finally obtain stable parameters. Assume that the expected output of the kth step in the training process is
The actual output is y (k), and an error function can be defined, that is, the objective function is:
the purpose of neural network learning is to find the optimal weight matrix W, so that the objective function is minimized. So, in terms of converting to an optimization problem, the present disclosure employs a genetic simulated annealing algorithm to solve the optimization problem.
The method for training the Elman neural network model based on genetic simulated annealing algorithm optimization comprises the following steps:
and step 21, constructing a training sample set, wherein data of the training sample set comprises a wind speed and wind direction value of relative wind, ship speed, ship course, ship navigation angular speed and real wind speed and wind direction, and the training sample set comprises a training set and a testing set.
The construction method of the training sample set comprises the following steps: wind speed and direction sensors are respectively arranged on the shore and the ship; the vessel moves within a set area offshore, for example the set area may be within one kilometre; the data detected by the wind speed and direction sensor on the shore is real wind speed and direction, namely ocean real wind, and the data detected by the wind speed and direction sensor arranged on the ship is a wind speed and direction value relative to wind.
On a relatively open coast, the difference of real ocean wind in a relatively short distance can be ignored, data detected by a wind speed and direction sensor fixed on the shore can be used as the real wind speed and direction on the ship, and the sensor arranged on the ship obtains a wind speed and direction value relative to wind.
Data were collected, with 80% of the data set obtained as the training set and the remaining 20% as the test set.
And step 22, taking the wind speed and direction value of the relative wind, the ship speed, the ship course and the ship navigation angular speed as input quantities, taking the output quantities as real wind speed and direction, and optimizing the weight and threshold value of each layer of the Elman neural network by adopting a genetic simulation annealing algorithm to obtain the optimal weight matrix of the Elman neural network.
In step 22, updating the weight values w and the threshold values b of each layer of the Elman neural network by adopting a genetic simulated annealing algorithm to obtain an Elman neural network optimal weight matrix, which can be as follows:
determining the topological structure of the Elman neural network; the input vector is relative wind speed and direction, ship speed and ship direction, and ship swinging acceleration and angular speed, and the output vector is corrected relative wind speed and direction.
Step 1): setting algorithm parameters of the simulated annealing algorithm, which can include population size and initial temperature t0End temperature t1Etc.;
step 2): initializing an Elman neural network weight and a threshold, and coding to obtain an initialized population;
step 3): evaluating individual fitness in the initial population;
the inverse of the objective function may be selected as the individual fitness function：
Therefore, if the target function is larger, the individual fitness is smaller; on the contrary, if the objective function is smaller, the individual fitness is larger.
Step 4): judging whether the algorithm termination criterion is met: if the current temperature satisfies t<t1And terminating the iterative loop to output the optimal weight and the threshold, assigning the optimal weight and the threshold to an Elman neural network for training, and if the optimal weight and the threshold are not met, executing genetic operation.
Step 5): executing genetic operation to obtain a new population as an initial population of the simulated annealing algorithm; the genetic manipulation may include selection, crossing, and mutation;
selecting operation: calculating the fitness value of the individual, calculating the probability of the individual being selected to enter the next generation according to the fitness value, and selecting the individual to enter the next generation when the probability is greater than a set value;
selecting an operator, if the size of the group is M, the fitness value of the individual is fiThen the probability that the individual is selected to enter the next generation is:
therefore, the higher the individual fitness is, the higher the probability of selection is, the gene deletion is avoided, and the overall convergence is improved.
And (3) cross operation: exchanging genetic genes between individuals, thereby obtaining better individuals;
the new individuals obtained by the crossover operation can adopt the following formula:
X′1＝mX2+(1-m)X1
X′2＝mX1+(1-m)X2
wherein m is a random number of (0, 1); x1And X2Two individuals are used; x'1And X'2Is a new individual;
mutation operation: and selecting a random number to replace the value of the variant gene according to the value range of the connection weight by adopting a uniform variant operator and the variant factor in the individual gene.
Step 6): performing simulated annealing operation on the individuals in the group to find out the individual with the optimal fitness;
according to the individual fitness function f, a new optimal individual is obtained by utilizing a state generation function of simulated annealing operation, an objective function is obtained as N ', the target function is obtained as f (N'), the previously generated optimal individual is obtained as N, and the target function is obtained as f (N). Calculate the difference between the objective functions:
Δf＝f(N′)-f(N)
if delta f is less than or equal to 0, accepting N' as the optimal solution, otherwise, calculating the receiving probability
T is the current temperature, if Pr>(0,1), accepting N' as the optimal solution, otherwise, keeping the optimal solution unchanged.
Step 7): judging whether the optimal individual meets the termination condition, if not, returning to the step 3); if so, decoding the optimal individual, and assigning a connection weight value of the Elman neural network for training. The optimal individual terminating condition can be set to keep the optimal individual fitness value stable and unchanged, for example, the optimal individual fitness values of 10 consecutive generations can be set to be stable and unchanged.
And step 23, testing the data of the 20% test set to obtain the predicted real wind speed and direction, and comparing the predicted real wind speed and direction with the measured real wind speed and direction.
The simulated annealing algorithm can receive a solution which is worse than the current solution with a certain probability, so that a local optimal solution is possible to jump out, and a global optimal solution of the objective function is randomly searched in a solution space; but as the number of iterations increases, the convergence rate becomes slower; the genetic algorithm is a method for searching the global optimal solution in a self-adaptive manner by simulating the natural evolution process, the convergence speed is high, but the algorithm is easy to converge prematurely, and the obtained global optimal solution is not necessarily the global optimal solution; in the embodiment, two optimization algorithms are combined to form a genetic simulated annealing algorithm, so that a global optimal solution can be obtained, a large number of iteration times can be reduced, and the algorithm efficiency is improved. And the Elman neural network is optimized by adopting a genetic simulated annealing algorithm, so that the optimal weight of the neural network is obtained, and the optimal network structure can also be obtained.
Experiments show that the error between the predicted value and the measured value obtained by comparing the method of the embodiment has a better effect than that of training by using a BP neural network, the output value is closer to the real wind speed and the real wind direction, the marine wind speed and the wind direction measuring method adopted by the embodiment optimizes the weight of the neural network by adopting a genetic simulated annealing algorithm, the marine true wind data obtained by measurement is more accurate, the navigation control of the ship is guided according to the marine true wind data, and the safety of the sailing ship is improved.
Example 2
The present embodiment provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method of embodiment 1.
Example 3
The present embodiment provides a computer readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of embodiment 1.
The electronic device provided by the present disclosure may be a mobile terminal and a non-mobile terminal, where the non-mobile terminal includes a desktop computer, and the mobile terminal includes a Smart Phone (such as an Android Phone and an IOS Phone), Smart glasses, a Smart watch, a Smart bracelet, a tablet computer, a notebook computer, a personal digital assistant, and other mobile internet devices capable of performing wireless communication.
It should be understood that in the present disclosure, the processor may be a central processing unit CPU, but may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The steps of a method disclosed in connection with the present disclosure may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here. Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a division of one logic function, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. A measuring method for automatically correcting ocean wind speed and direction is characterized by comprising the following steps:
acquiring measurement data of a ship to be measured;
and constructing an Elman neural network model optimized based on a genetic simulated annealing algorithm, inputting the acquired measurement data of the ship to be tested into the trained Elman neural network model optimized based on the genetic simulated annealing algorithm, and outputting the corrected real wind speed and direction.
2. The method for measuring the wind speed and direction of the ocean according to claim 1, wherein the method comprises the following steps:
the method for training the Elman neural network model based on genetic simulated annealing algorithm optimization comprises the following steps:
constructing a training sample set, wherein the data of the training sample set comprises a wind speed and direction value of relative wind, a ship speed, a ship course, an angular speed of ship navigation and a real wind speed and direction;
and (3) taking the wind speed and direction value of the relative wind, the ship speed, the ship course and the ship sailing angular speed as input quantities, taking the output quantity as the real wind speed and direction, and optimizing the weight value and the threshold value of each layer of the Elman neural network by adopting a genetic simulated annealing algorithm to obtain the optimal weight matrix of the Elman neural network.
3. The method for measuring the wind speed and direction of the ocean according to claim 2, wherein the method comprises the following steps: the method for updating the weight matrix and the threshold value of each layer of the Elman neural network by adopting the genetic simulated annealing algorithm to obtain the optimal weight matrix of the Elman neural network comprises the following steps:
step 1, setting algorithm parameters of a simulated annealing algorithm, including population scale and initial temperature t0End temperature t1；
Step 2, initializing an Elman neural network weight and a threshold, and coding to obtain an initial population;
step 3, evaluating the individual fitness in the initial population according to the optimization objective function;
step 4, judging whether the algorithm termination criterion is met: if the current temperature satisfies t<t1If the optimal weight and the threshold are not met, executing the next step;
step 5, executing genetic operation to obtain a new population as an initial population of the simulated annealing algorithm;
step 6, performing simulated annealing operation on the individuals in the group to find out the individual with the optimal fitness;
step 7, judging whether the optimal individual meets the termination condition, if not, executing the step 3; if so, decoding the optimal individual, and assigning a connection weight value of the Elman neural network for training.
4. A method as claimed in claim 3, wherein the method comprises the following steps:
the genetic manipulation may include selection manipulation, crossover manipulation, and mutation manipulation;
selecting operation: calculating the fitness value of the individual, calculating the probability of the individual being selected to enter the next generation according to the fitness value, and selecting the individual to enter the next generation when the probability is greater than a set value;
and (3) cross operation: exchanging genetic genes between individuals, thereby obtaining better individuals;
mutation operation: and selecting a random number to replace the value of the variant gene according to the value range of the connection weight by adopting a uniform variant operator and the variant factor in the individual gene.
5. The method for measuring the wind speed and direction of the ocean according to claim 2, wherein the method comprises the following steps:
optimizing a weight matrix of the Elman neural network by adopting a simulated annealing algorithm, wherein an optimized objective function is as follows:
wherein,
the desired output for the k-th step, and y (k) the actual output.
6. The method for measuring the wind speed and direction of the ocean according to claim 1, wherein the method comprises the following steps:
the measurement data of the ship to be measured comprise the wind speed and the wind direction of relative wind on the ship, the ship speed, the ship course and the ship navigation angular speed which are obtained by the measurement of a sensor arranged on the ship;
or
The Elman neural network comprises an input layer, a hidden layer, a connecting layer and an output layer, wherein the connecting layer is used for memorizing and storing an output value at the previous moment of the hidden layer, and the mathematical model of the Elman neural network is as follows:
x(k)＝f(W1xC(k)+W2u(k-1))
xC(k)＝α·xC(k-1)+x(k-1)
yk＝g(W3x(k))
wherein, W1A connection weight matrix of the connection layer and the hidden layer; w2A connection weight matrix of the input layer and the hidden layer; w3A connection weight matrix of the hidden layer and the output layer; x is the number ofC(k) Refer to a connection layer output vector, x (k) refer to a hidden layer output vector, u (k) refer to an input vector, ykRefers to the output vector, 0 ≦ α<1 is the self-chaining feedback gain factor.
7. The utility model provides an automatic rectify ultrasonic measurement system of ocean wind speed and direction which characterized by: the device comprises an ultrasonic sensor, a GPS module, an electronic compass module and a microprocessor; the ultrasonic sensor, the GPS module and the electronic compass module are respectively connected with the microprocessor and are respectively used for acquiring the relative wind speed and direction on the ship, the ship speed and the ship course and transmitting the acquired data to the microprocessor, and the microprocessor executes the ultrasonic measuring method for automatically correcting the wind speed and direction of the ocean according to any one of claims 1 to 6.
8. The ultrasonic measuring system for automatically correcting the wind speed and the wind direction of the ocean as claimed in claim 7, wherein: the ship navigation device is characterized by further comprising a gyroscope sensor arranged on the ship and used for measuring the ship navigation angular velocity, and the gyroscope sensor is connected with the microprocessor and used for transmitting the acquired angular velocity to the microprocessor in real time.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executable on the processor, the computer instructions when executed by the processor performing the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911173949.0A CN110987066A (en) | 2019-11-26 | 2019-11-26 | Ocean wind speed and direction measuring method and system capable of achieving automatic correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911173949.0A CN110987066A (en) | 2019-11-26 | 2019-11-26 | Ocean wind speed and direction measuring method and system capable of achieving automatic correction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110987066A true CN110987066A (en) | 2020-04-10 |
Family
ID=70087127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911173949.0A Withdrawn CN110987066A (en) | 2019-11-26 | 2019-11-26 | Ocean wind speed and direction measuring method and system capable of achieving automatic correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110987066A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113268812A (en) * | 2021-05-26 | 2021-08-17 | 山东省科学院海洋仪器仪表研究所 | Method, device and equipment for solving true wind in ship steering process and storage medium |
| CN113552382A (en) * | 2021-07-26 | 2021-10-26 | 浙江中控技术股份有限公司 | Wind speed and direction measuring method, device and system |
| CN113588153A (en) * | 2021-04-26 | 2021-11-02 | 深圳旗鱼体育传播有限公司 | Offshore real-wind remote real-time monitoring system and monitoring method |
| CN114397474A (en) * | 2022-01-17 | 2022-04-26 | 吉林大学 | FCN-MLP-based arc ultrasonic sensing array wind parameter measurement method |
| CN114609410A (en) * | 2022-03-25 | 2022-06-10 | 西南交通大学 | Portable wind characteristic measuring equipment based on acoustic signals and intelligent algorithm |
| CN117907631A (en) * | 2024-03-20 | 2024-04-19 | 北京科技大学 | Wind speed correction method and system based on wind speed sensor |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB581905A (en) * | 1943-07-17 | 1946-10-29 | Francis Stanley Burt | Calculating apparatus for vector problems |
| CN108711312A (en) * | 2018-05-24 | 2018-10-26 | 大连海事大学 | Ship based on BP neural network and static object mark risk of collision pre-judging method |
| CN108960421A (en) * | 2018-06-05 | 2018-12-07 | 哈尔滨工程大学 | The unmanned surface vehicle speed of a ship or plane online forecasting method based on BP neural network of improvement |
| CN109356800A (en) * | 2018-12-12 | 2019-02-19 | 国电联合动力技术有限公司 | The preparation method and its device of low wind speed Wind turbines nacelle wind speed correction function |
| CN110412313A (en) * | 2019-08-24 | 2019-11-05 | 大连理工大学 | A kind of scaling method of ship true wind measuring device |
-
2019
- 2019-11-26 CN CN201911173949.0A patent/CN110987066A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB581905A (en) * | 1943-07-17 | 1946-10-29 | Francis Stanley Burt | Calculating apparatus for vector problems |
| CN108711312A (en) * | 2018-05-24 | 2018-10-26 | 大连海事大学 | Ship based on BP neural network and static object mark risk of collision pre-judging method |
| CN108960421A (en) * | 2018-06-05 | 2018-12-07 | 哈尔滨工程大学 | The unmanned surface vehicle speed of a ship or plane online forecasting method based on BP neural network of improvement |
| CN109356800A (en) * | 2018-12-12 | 2019-02-19 | 国电联合动力技术有限公司 | The preparation method and its device of low wind speed Wind turbines nacelle wind speed correction function |
| CN110412313A (en) * | 2019-08-24 | 2019-11-05 | 大连理工大学 | A kind of scaling method of ship true wind measuring device |
Non-Patent Citations (4)
| Title |
|---|
| 刘胜等: "《智能预报技术及其在船舶工程中应用》", 30 November 2015, 国防工业出版社 * |
| 孙斌等: "基于ELMAN神经网络的短期风速预测", 《东北电力大学学报》 * |
| 曹芙: "基于Elman神经网络及优化算法的混合模型的研究及应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 郭彩杏等: "改进遗传模拟退火算法优化BP算法研究", 《小型微型计算机系统》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113588153A (en) * | 2021-04-26 | 2021-11-02 | 深圳旗鱼体育传播有限公司 | Offshore real-wind remote real-time monitoring system and monitoring method |
| CN113268812A (en) * | 2021-05-26 | 2021-08-17 | 山东省科学院海洋仪器仪表研究所 | Method, device and equipment for solving true wind in ship steering process and storage medium |
| CN113552382A (en) * | 2021-07-26 | 2021-10-26 | 浙江中控技术股份有限公司 | Wind speed and direction measuring method, device and system |
| CN114397474A (en) * | 2022-01-17 | 2022-04-26 | 吉林大学 | FCN-MLP-based arc ultrasonic sensing array wind parameter measurement method |
| CN114397474B (en) * | 2022-01-17 | 2022-11-08 | 吉林大学 | FCN-MLP-based arc ultrasonic sensing array wind parameter measurement method |
| CN114609410A (en) * | 2022-03-25 | 2022-06-10 | 西南交通大学 | Portable wind characteristic measuring equipment based on acoustic signals and intelligent algorithm |
| CN114609410B (en) * | 2022-03-25 | 2022-11-18 | 西南交通大学 | Portable wind characteristic measuring equipment based on acoustic signals and intelligent algorithm |
| CN117907631A (en) * | 2024-03-20 | 2024-04-19 | 北京科技大学 | Wind speed correction method and system based on wind speed sensor |
| CN117907631B (en) * | 2024-03-20 | 2024-05-24 | 北京科技大学 | Wind speed correction method and system based on wind speed sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110987066A (en) | Ocean wind speed and direction measuring method and system capable of achieving automatic correction | |
| WO2018018994A1 (en) | Method and system for indoor positioning | |
| CN105676181B (en) | Underwater movement objective Extended Kalman filter tracking based on distributed sensor energy ratio | |
| CN106599368B (en) | Based on the FastSLAM method for improving particle proposal distribution and adaptive particle resampling | |
| CN103593538A (en) | Fiber optic gyroscope temperature drift modeling method by optimizing dynamic recurrent neural network through genetic algorithm | |
| CN112432644B (en) | Unmanned ship integrated navigation method based on robust adaptive unscented Kalman filtering | |
| CN113283653B (en) | Ship track prediction method based on machine learning and AIS data | |
| CN105223241A (en) | A kind of compensation method of humidity sensor | |
| CN104199022A (en) | Target modal estimation based near-space hypersonic velocity target tracking method | |
| CN109520503A (en) | Adaptive Kalman filtering SLAM method for square root volume ambiguity | |
| CN104407337A (en) | Method and system for filtering data of turning maneuvering target | |
| CN114492217B (en) | Typhoon and wave height prediction method based on mixed time series perceptron model | |
| CN102685772B (en) | Tracking node selection method based on wireless all-around sensor network | |
| CN109857127B (en) | Method and device for calculating training neural network model and aircraft attitude | |
| CN113820062B (en) | Temperature compensation method of six-dimensional force sensor | |
| CN116559977A (en) | NPS-GRYANIK20 evaporation waveguide height prediction method based on BP neural network | |
| CN115438571A (en) | Ground wave radar wave field calculation method and device based on machine learning | |
| CN116070068A (en) | Stay cable damage identification method, device and terminal based on wavelet transformation of primary derivative of girder deflection difference | |
| CN117312783B (en) | Ship heave compensation prediction method and device based on neural network and storage medium | |
| CN110703205A (en) | Ultrashort baseline positioning method based on adaptive unscented Kalman filtering | |
| CN112800075B (en) | Ship manipulation prediction database updating method based on six-degree-of-freedom attitude data of real ship | |
| CN116993832B (en) | CNN-based position prediction method and device for flight target | |
| CN116805028B (en) | Wave surface inversion method and system based on floating body motion response | |
| CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment | |
| CN107590346B (en) | Downscaling correction model based on spatial multi-correlation solution set algorithm |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200410 |
|
| WW01 | Invention patent application withdrawn after publication |