CN114706144A - Marine environment forecasting method, device, system and storage medium - Google Patents
Marine environment forecasting method, device, system and storage medium Download PDFInfo
- Publication number
- CN114706144A CN114706144A CN202210173885.XA CN202210173885A CN114706144A CN 114706144 A CN114706144 A CN 114706144A CN 202210173885 A CN202210173885 A CN 202210173885A CN 114706144 A CN114706144 A CN 114706144A
- Authority
- CN
- China
- Prior art keywords
- marine environment
- prediction
- data
- marine
- subsystem
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013277 forecasting method Methods 0.000 title claims abstract description 25
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000006870 function Effects 0.000 claims abstract description 67
- 238000013528 artificial neural network Methods 0.000 claims abstract description 44
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 40
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 32
- 230000007613 environmental effect Effects 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims description 37
- 238000000034 method Methods 0.000 claims description 35
- 230000015654 memory Effects 0.000 claims description 32
- 230000002068 genetic effect Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000005036 nerve Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
Abstract
The invention discloses a marine environment forecasting method, a marine environment forecasting device, a marine environment forecasting system and a storage medium, wherein the marine environment forecasting method comprises the following steps: acquiring marine environment data through a marine environment monitoring subsystem, and transmitting the acquired marine environment data to a marine data processing subsystem; performing modal decomposition on the marine environment data through the marine data processing subsystem to obtain a plurality of intrinsic modal functions of the environment data, and transmitting the intrinsic modal functions of the environment data to the marine environment forecasting subsystem; and carrying out prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment prediction subsystem so as to establish a prediction model, and outputting a marine environment prediction result based on the prediction model. The marine environment forecasting method disclosed by the invention can solve the technical problems that the conventional marine environment monitoring mode is low in efficiency, high in cost, low in intelligent degree and incapable of carrying out short-term environment forecasting.
Description
Technical Field
The invention belongs to the technical field of marine environment monitoring, and particularly relates to a marine environment forecasting method, a marine environment forecasting device, a marine environment forecasting system and a computer readable storage medium.
Background
The ocean platform is an ocean engineering structure and provides a place for offshore operation and life for developing and utilizing ocean resources. With the rapid development of ocean development industry, ocean platforms are widely applied. The ocean platform has a complex structure, a large volume and high cost, the ocean environment is very complex and severe, and wind, sea waves, ocean currents, sea ice and tides constantly affect the ocean platform.
The marine environment is mainly composed of hydrologic information, meteorological information and geographical information, wherein the meteorological information and the hydrologic information have the greatest influence on the operating state of the ocean platform and can be collectively referred to as marine hydrologic meteorological information. The main factors greatly influencing the operation state of the ocean platform in the marine hydrological meteorological information include sea wind, tide, ocean current, wave, surge and the like, and the wind, wave and current influence the operation state of the ocean platform by generating ocean environment force and moment on the ocean platform.
Aiming at marine environment monitoring, the current main means comprises on-site manual sampling, monitoring by a special monitoring ship or a buoy in-situ monitoring mode, the monitoring mode has the defects of extremely high labor consumption, low monitoring efficiency, high monitoring cost and the like, the monitoring system has low intelligentization and networking degrees, the remote real-time monitoring of the marine environment cannot be realized, and the monitored data is difficult to be used for short-term environment forecast, so that the pollution or disaster of the marine environment cannot be found in time.
Disclosure of Invention
In order to overcome the above disadvantages of the prior art, the present invention aims to provide a marine environment forecasting method, which aims to solve the technical problems that the current marine environment monitoring mode has low efficiency, high cost and low intelligence degree, and cannot carry out short-term environmental forecasting.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a marine environment forecasting method, comprising the steps of:
acquiring marine environment data through a marine environment monitoring subsystem, and transmitting the acquired marine environment data to a marine data processing subsystem;
performing modal decomposition on the marine environment data through the marine data processing subsystem to obtain a plurality of environment data intrinsic modal functions, and transmitting the environment data intrinsic modal functions to the marine environment forecasting subsystem;
and performing prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment forecasting subsystem to establish a prediction model, and outputting a marine environment prediction result based on the prediction model.
Further, the step of performing predictive training on the eigenmode functions of the environmental data through the neural network algorithm of the marine environment forecasting subsystem includes:
and performing prediction test on the intrinsic mode function of the environmental data through a BP neural network algorithm.
Further, the step of performing a predictive test on the intrinsic mode function of the environmental data through a BP neural network algorithm includes:
optimizing the BP neural network by using a genetic algorithm to establish a GA-BPNN prediction model;
and performing prediction test on the environment data intrinsic mode function through the GA-BPNN prediction model.
Further, the step of performing a predictive test on the environment data eigenmode function through the GA-BPNN predictive model includes:
introducing an LSTM long-short term memory neural network into the GA-BPNN prediction model to establish an LSTM-GA-BPNN prediction model;
and performing prediction test on the environment data intrinsic mode function through the LSTM-GA-BPNN prediction model.
Further, the step of performing modal decomposition on the marine environment data by the marine data processing subsystem includes:
and performing modal decomposition on the marine environment data by an EMD empirical mode decomposition method.
Further, before the step of performing modal decomposition on the marine environment data by an EMD empirical modal decomposition method, the method includes:
adding white Gaussian noise into an original signal corresponding to the marine environment data so that the original signal is projected onto a reference system established by the white Gaussian noise;
the step of performing prediction test on the environment data intrinsic mode function through the LSTM-GA-BPNN prediction model comprises the following steps:
dividing each component of the intrinsic mode function into a high-frequency signal group, a low-frequency signal group and a remainder group according to a corresponding signal frequency band;
carrying out prediction test on the test sample data of the high-frequency signal group through an LSTM prediction module in the LSTM-GA-BPNN prediction model to obtain a first prediction result;
and performing prediction test on the test sample data of the low-frequency signal group and the residual group through a GA-BPNN prediction module in the LSTM-GA-BPNN prediction model to obtain a second prediction result.
Further, the step of outputting a marine environment prediction result based on the prediction model includes:
and accumulating the first prediction result and the second prediction result to obtain a target prediction value and outputting the target prediction value.
Correspondingly, the invention also provides a marine environment forecasting device, which comprises:
the monitoring module is used for acquiring marine environment data through the marine environment monitoring subsystem and transmitting the acquired marine environment data to the marine data processing subsystem;
the data processing module is used for carrying out modal decomposition on the marine environmental data through the marine data processing subsystem to obtain a plurality of environmental data intrinsic mode functions and transmitting the environmental data intrinsic mode functions to the marine environment forecasting subsystem;
and the prediction module is used for carrying out prediction training on the environment data intrinsic mode function through a neural network algorithm of the marine environment prediction subsystem so as to establish a prediction model and outputting a marine environment prediction result based on the prediction model.
Correspondingly, the present invention also proposes a marine environment forecasting system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the marine environment forecasting method as described above.
Correspondingly, the present invention also proposes a computer readable storage medium, on which a marine environment forecasting program is stored, which, when being executed by a processor, implements the steps of the marine environment forecasting method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the marine environment forecasting method provided by the invention constructs a set of marine environment real-time monitoring, processing and forecasting system through the marine environment monitoring subsystem, the marine data processing subsystem and the marine environment forecasting subsystem, the marine environment data acquired by the marine environment monitoring subsystem is subjected to modal decomposition by the marine data processing subsystem to obtain a stable intrinsic modal function, the intrinsic modal function is subjected to prediction training by the neural network algorithm of the marine environment forecasting subsystem to establish a prediction model, when new marine environment data is input into the prediction model, the prediction model can output a corresponding marine environment prediction result, thereby helping monitoring personnel to grasp the change of marine environment information in real time and predict marine pollution or disasters which may occur in an artificial intelligence mode to make countermeasures in advance, the interference on the normal operation of the ocean platform is effectively avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a marine environment forecasting method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a marine environment forecasting method according to another embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an apparatus according to an embodiment of the present invention;
fig. 4 is a schematic system structure diagram of a hardware operating environment according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 4, fig. 4 is a schematic structural diagram of a marine environment forecasting system according to an embodiment of the present invention.
As shown in fig. 4, the marine environment forecasting system may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the marine environment forecasting system may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. The sensor may include a light sensor, a motion sensor, an infrared sensor, and other sensors, which are not described herein.
Those skilled in the art will appreciate that the particular configuration shown in FIG. 4 does not constitute a limitation of the marine environment prediction system, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 4, a memory 1005, which is a kind of computer-readable storage medium, may include therein an operating system, a network communication module, a user interface module, and a marine environment forecasting program.
In the marine environment forecasting system shown in fig. 4, the network interface 1004 is mainly used for connecting to a background server and communicating with the background server in data; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the marine environment forecasting program stored in the memory 1005, and perform the following operations:
acquiring marine environment data through a marine environment monitoring subsystem, and transmitting the acquired marine environment data to a marine data processing subsystem;
modal decomposition is carried out on marine environment data through a marine data processing subsystem to obtain a plurality of environment data intrinsic modal functions, and the environment data intrinsic modal functions are transmitted to a marine environment forecasting subsystem;
and performing prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment prediction subsystem to establish a prediction model, and outputting a marine environment prediction result based on the prediction model.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
and performing prediction test on the intrinsic mode function of the environmental data through a BP neural network algorithm.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
optimizing the BP neural network by using a genetic algorithm to establish a GA-BPNN prediction model;
and performing prediction test on the intrinsic mode function of the environmental data through a GA-BPNN prediction model.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
introducing an LSTM long-short term memory neural network into the GA-BPNN prediction model to establish an LSTM-GA-BPNN prediction model;
and performing prediction test on the intrinsic mode function of the environmental data through an LSTM-GA-BPNN prediction model.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
and performing modal decomposition on the marine environment data by an EMD empirical mode decomposition method.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
and adding white Gaussian noise into the original signal corresponding to the marine environment data so that the original signal is projected onto a reference frame established by the white Gaussian noise.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
dividing each component of the intrinsic mode function into a high-frequency signal group, a low-frequency signal group and a remainder group according to a corresponding signal frequency band;
carrying out prediction test on test sample data of the high-frequency signal group through an LSTM prediction module in an LSTM-GA-BPNN prediction model to obtain a first prediction result;
and performing prediction test on the test sample data of the low-frequency signal group and the residual group through a GA-BPNN prediction module in the LSTM-GA-BPNN prediction model to obtain a second prediction result.
Further, the processor 1001 may call the marine environment forecasting program stored in the memory 1005, and further perform the following operations:
and accumulating the first prediction result and the second prediction result to obtain a target prediction value and outputting the target prediction value.
Referring to fig. 1, an embodiment of the present invention provides a marine environment forecasting method, including:
s1, acquiring marine environment data through the marine environment monitoring subsystem, and transmitting the acquired marine environment data to the marine data processing subsystem;
s2, performing modal decomposition on the marine environment data through the marine data processing subsystem to obtain a plurality of environment data intrinsic mode functions, and transmitting the environment data intrinsic mode functions to the marine environment forecasting subsystem;
and S3, performing prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment prediction subsystem to establish a prediction model, and outputting a marine environment prediction result based on the prediction model.
In this embodiment, the marine environment monitoring subsystem may include a sensing device for collecting various meteorological information (e.g., wind direction, wind speed, temperature, humidity, etc. of the sea area where the marine platform is located) and hydrological information (e.g., physical, chemical, and biological parameters of sea water temperature, salinity, density, ocean current, tide, wave, etc. of the sea area where the marine platform is located).
The marine data processing subsystem and the marine environment forecasting subsystem can be a computer central control and processing system which is in communication connection with the sensing device and is used for receiving monitoring data transmitted by the sensing device in real time and further analyzing and processing the monitoring data. Because most of marine environment data signals acquired by the sensing device are nonlinear non-stationary signals, modal decomposition is required to be carried out on the signals to obtain a determined eigenmode function, and the signals corresponding to the eigenmode function meet the following two conditions: 1. the number of extreme points of all signals is the same as or different from the number of zero-crossing points by one at most; 2. the average of the envelope between the maxima and minima is zero.
After the intrinsic mode function is obtained, a neural network model can be constructed through a neural network algorithm, each component of the intrinsic mode function is led into the neural network model, deep learning is carried out on the basis of the led data through training the neural network, and a prediction model is established after the neural network is trained; when the obtained marine environment data is input into the trained prediction model, the prediction model can output prediction data according to the marine environment conditions in a short period of time in the future, so that monitoring personnel can be helped to timely master the change of the marine environment information and pre-judge possible pollution or disasters, response measures are taken in advance, and the normal operation of the marine platform is prevented from being influenced.
Therefore, in the marine environment forecasting method provided by this embodiment, a set of real-time marine environment monitoring, processing and forecasting system is constructed by the marine environment monitoring subsystem, the marine data processing subsystem and the marine environment forecasting subsystem, the marine environment data acquired by the marine environment monitoring subsystem is subjected to modal decomposition by the marine data processing subsystem to obtain a stable eigen-modal function, the eigen-modal function is subjected to prediction training by the neural network algorithm of the marine environment forecasting subsystem to establish a prediction model, and when new marine environment data is input into the prediction model, the prediction model can output a corresponding marine environment prediction result, so as to help monitoring personnel to grasp the change of marine environment information in real time and predict marine pollution or disaster which may occur in an artificial intelligence manner to make countermeasures in advance, the interference on the normal operation of the ocean platform is effectively avoided.
Specifically, referring to fig. 1 and 2, step S3 includes:
and S31, performing prediction test on the intrinsic mode functions of the environmental data through a BP neural network algorithm.
The BP neural network is a multilayer feedforward network trained according to error back propagation, and the BP neural network algorithm mainly utilizes a gradient search technology to minimize the mean square error between an actual output value and an expected output value of the neural network.
The BP neural network algorithm comprises two processes of forward propagation of signals and backward propagation of errors. During forward propagation, an input signal acts on an output node through a hidden layer, an output signal is generated through nonlinear transformation, and if actual output does not accord with expected output, the process of backward propagation of errors is carried out. The error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and to distribute the error to all units of each layer, and to use the error signal obtained from each layer as the basis for adjusting the weight of each unit. And the error is reduced along the gradient direction by adjusting the connection strength of the input node and the hidden node, the connection strength of the hidden node and the output node and the threshold value. Through repeated learning and training, the weight and the threshold corresponding to the minimum error can be determined, and at the moment, the trained neural network can automatically process and output the information which has the minimum error and is subjected to nonlinear conversion to the input information of similar samples.
Specifically, referring to fig. 1 and 2, step S31 includes:
s311, optimizing the BP neural network by using a genetic algorithm to establish a GA-BPNN prediction model;
and S312, performing prediction test on the intrinsic mode function of the environmental data through a GA-BPNN prediction model.
In order to overcome the defects that the BP neural network algorithm has the defects of low convergence speed, easy trapping in local minimum and the like in application, the weight of the BP neural network can be optimized by utilizing the capability of global search of an optimal solution of a genetic algorithm so as to establish a GA-BPNN prediction model. The GA-BPNN prediction model is established and predicted by the following three steps:
1. determining a BP neural network structure: determining the structure of the BP neural network according to the number of input/output parameters of the fitting function, namely determining the number of optimized parameters of the genetic algorithm, and further obtaining the encoding length of the genetic algorithm individual;
2. genetic algorithm optimization: according to the structure of the BP neural network, the weight and the number of the threshold values can be obtained;
3. BP neural network prediction: and (3) utilizing a genetic algorithm to obtain an optimal individual to carry out assignment of an initial weight and a threshold value on the BP neural network, so that the BP neural network can output a prediction sample after being trained.
Specifically, referring to fig. 1 and 2, step S312 includes:
s3121, introducing an LSTM long-short term memory neural network into the GA-BPNN prediction model to establish an LSTM-GA-BPNN prediction model;
and S3122, carrying out prediction test on the intrinsic mode function of the environmental data through an LSTM-GA-BPNN prediction model.
As the prediction period is increased, the prediction effect of the GA-BPNN prediction model is deteriorated, so that an LSTM long-short term memory neural network is introduced into the GA-BPNN prediction model. LSTM is a special RNN (recurrent neural network) that can be used to avoid long term dependency problems. The LSTM adds a memory unit in each nerve unit of the hidden layer on the basis of the common RNN, so that the memory information on a time sequence is controllable, and the memory and forgetting degree of previous information and current information can be controlled through a plurality of controllable gates (a forgetting gate, an input gate, a candidate gate and an output gate) when the LSTM is transmitted among the nerve units of the hidden layer each time, so that the RNN nerve network has a long-term memory function.
The LSTM-GA-BPNN prediction model comprises an LSTM prediction module and a GA-BPNN prediction module, and the two modules can respectively perform prediction tests on components of the intrinsic mode function with different frequencies so as to respectively obtain marine environment prediction results.
Specifically, referring to fig. 1 and 2, step S2 includes:
and S21, performing modal decomposition on the marine environment data through an EMD empirical mode decomposition method.
An Empirical Mode Decomposition (Empirical Mode Decomposition) method can decompose a complex marine environment data signal into a finite number of Intrinsic Mode functions (Intrinsic Mode functions), and each component of the decomposed Intrinsic Mode functions contains local characteristic signals of the original signal at different time scales. The EMD empirical mode decomposition method is based on the following assumed conditions:
1. the data has at least two extreme values, namely a maximum value and a minimum value;
2. the local time domain characteristics of the data are uniquely determined by the time scale between extreme points;
3. if the data has no extreme point but has an inflection point, the data can be differentiated one or more times to obtain an extreme value, and then integrated to obtain a decomposition result.
The EMD empirical mode decomposition method is suitable for analyzing and processing non-stationary nonlinear signals and solves the problem that a basis function is not adaptive.
Further, referring to fig. 1 and 2, in an exemplary embodiment, before step S21, the method includes:
s2101, adding Gaussian white noise into an original signal corresponding to marine environment data to enable the original signal to be projected onto a reference system established by the Gaussian white noise;
step S3122, comprising:
s31221, dividing each component of the intrinsic mode function into a high-frequency signal group, a low-frequency signal group and a remainder group according to the corresponding signal frequency band;
s31222, carrying out prediction testing on test sample data of the high-frequency signal group through an LSTM prediction module in the LSTM-GA-BPNN prediction model to obtain a first prediction result;
and S31223, performing prediction test on the test sample data of the low-frequency signal group and the residual group through a GA-BPNN prediction module in the LSTM-GA-BPNN prediction model to obtain a second prediction result.
Specifically, referring to fig. 1 and 2, the step of outputting the marine environment prediction result according to the training result in S3 includes:
and S32, accumulating the first prediction result and the second prediction result to obtain a target prediction value and outputting the target prediction value.
The EMD empirical mode decomposition method has the following problems:
1. modal aliasing exists in the intrinsic mode function obtained by decomposition through an EMD empirical mode decomposition method;
2. the end effects affect the decomposition effect.
In order to inhibit the mode aliasing phenomenon of the EMD empirical mode decomposition method, white noise with limited amplitude can be added into an original signal corresponding to marine environment data, and the white noise is uniformly distributed on the whole time-frequency space. Based on this background, the original signal corresponding to the marine environment data is automatically projected onto a reference scale established by white noise under different scales, so that an EEMD Ensemble Empirical Mode Decomposition (Ensemble Empirical Mode Decomposition) method is obtained on the basis of the EMD Empirical Mode Decomposition method. The components of the intrinsic mode functions can be grouped according to signal frequency bands through an EEMD set empirical mode decomposition method, and prediction tests are respectively carried out on the components of different groups through an LSTM-GA-BPNN prediction model, so that a more accurate marine environment prediction result is obtained.
The specific treatment process is as follows:
the marine environment forecasting subsystem inputs each component in an intrinsic mode function obtained by decomposing marine environment data through an EEMD set empirical mode decomposition method into an LSTM-GA-BPNN forecasting model, initializes the number of an input layer, a hidden layer and an output layer, and initializes weight and learning rate; then, dividing each component into a high-frequency signal group (corresponding to a high-frequency signal), a low-frequency signal group (corresponding to a high-frequency signal) and a remainder group according to the fluctuation frequency; simultaneously dividing the data of each component into a training sample and a prediction sample, and normalizing the input/output samples; and finally, substituting training sample data of each component of the high-frequency signal group into an LSTM prediction module (the GA-BPNN prediction module has poor prediction effect on the high-frequency signal), substituting training sample data of each component of the low-frequency signal group and the residual group into the GA-BPNN prediction module to complete prediction tests on each component, and finally accumulating prediction results of each component to obtain a target prediction value of the original time sequence. Therefore, the accuracy of the short-term forecast of the marine environment can be improved by classifying and predicting the components of the intrinsic mode function.
Correspondingly, referring to fig. 3, an embodiment of the present invention further provides a marine environment forecasting apparatus, including:
the monitoring module 10 is used for acquiring marine environment data through the marine environment monitoring subsystem and transmitting the acquired marine environment data to the marine data processing subsystem;
the data processing module 20 is used for performing modal decomposition on the marine environmental data through the marine data processing subsystem to obtain a plurality of environmental data intrinsic mode functions, and transmitting the environmental data intrinsic mode functions to the marine environmental forecasting subsystem;
and the prediction module 30 is used for performing prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment prediction subsystem so as to establish a prediction model and output a marine environment prediction result based on the prediction model.
The marine environment prediction apparatus of the present embodiment is used to implement the marine environment prediction method, and therefore, the specific implementation of the marine environment prediction apparatus can be seen in the foregoing parts of the marine environment prediction method, for example, the monitoring module 10 is used to implement step S1 in the marine environment prediction method, the data processing module 20 is used to implement step S2 in the marine environment prediction method, and the prediction module 30 is used to implement step S3 in the marine environment prediction method. Therefore, the detailed description thereof may refer to the description of the above embodiments, and will not be repeated herein.
Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a marine environment forecasting program, and the marine environment forecasting program, when executed by a processor, implements the steps of the marine environment forecasting method in any of the above embodiments.
In the present embodiment, the computer-readable storage medium may include, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROMs (Read-Only memories), RAMs (Random access memories), EPROMs (Erasable Programmable Read-Only memories), EEPROMs (Electrically Erasable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards, and various media capable of storing program codes.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or system in which the element is included.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A marine environment forecasting method is characterized by comprising the following steps:
acquiring marine environment data through a marine environment monitoring subsystem, and transmitting the acquired marine environment data to a marine data processing subsystem;
performing modal decomposition on the marine environment data through the marine data processing subsystem to obtain a plurality of environment data intrinsic modal functions, and transmitting the environment data intrinsic modal functions to the marine environment forecasting subsystem;
and performing prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment forecasting subsystem to establish a prediction model, and outputting a marine environment prediction result based on the prediction model.
2. The marine environment forecasting method according to claim 1, wherein the step of performing predictive training on the eigenmode functions of the environmental data through a neural network algorithm of the marine environment forecasting subsystem includes:
and performing prediction test on the intrinsic mode function of the environmental data through a BP neural network algorithm.
3. The marine environment forecasting method according to claim 2, wherein the step of performing the predictive test on the intrinsic mode functions of the environmental data through the BP neural network algorithm comprises:
optimizing the BP neural network by using a genetic algorithm to establish a GA-BPNN prediction model;
and performing prediction test on the environment data intrinsic mode function through the GA-BPNN prediction model.
4. The marine environment forecasting method as claimed in claim 3, wherein the step of performing the predictive test on the eigenmode functions of the environmental data through the GA-BPNN predictive model comprises:
introducing an LSTM long-short term memory neural network into the GA-BPNN prediction model to establish an LSTM-GA-BPNN prediction model;
and performing prediction test on the environment data intrinsic mode function through the LSTM-GA-BPNN prediction model.
5. The marine environment forecasting method of claim 4, wherein the step of performing modal decomposition on the marine environment data by the marine data processing subsystem comprises:
and performing modal decomposition on the marine environment data by an EMD empirical mode decomposition method.
6. The marine environment forecasting method of claim 5, wherein the step of performing modal decomposition on the marine environment data through EMD empirical mode decomposition is preceded by:
adding white Gaussian noise into an original signal corresponding to the marine environment data so that the original signal is projected onto a reference system established by the white Gaussian noise;
the step of performing prediction test on the environment data intrinsic mode function through the LSTM-GA-BPNN prediction model comprises the following steps:
dividing each component of the intrinsic mode function into a high-frequency signal group, a low-frequency signal group and a remainder group according to a corresponding signal frequency band;
carrying out prediction test on the test sample data of the high-frequency signal group through an LSTM prediction module in the LSTM-GA-BPNN prediction model to obtain a first prediction result;
and performing prediction test on the test sample data of the low-frequency signal group and the residual group through a GA-BPNN prediction module in the LSTM-GA-BPNN prediction model to obtain a second prediction result.
7. The marine environment forecasting method of claim 6, wherein the step of outputting the marine environment prediction result based on the prediction model comprises:
and accumulating the first prediction result and the second prediction result to obtain a target prediction value and outputting the target prediction value.
8. A marine environment prediction device, characterized in that it comprises:
the monitoring module is used for acquiring marine environment data through the marine environment monitoring subsystem and transmitting the acquired marine environment data to the marine data processing subsystem;
the data processing module is used for carrying out modal decomposition on the marine environmental data through the marine data processing subsystem to obtain a plurality of environmental data intrinsic mode functions and transmitting the environmental data intrinsic mode functions to the marine environment forecasting subsystem;
and the prediction module is used for carrying out prediction training on the intrinsic mode function of the environmental data through a neural network algorithm of the marine environment prediction subsystem so as to establish a prediction model and output a marine environment prediction result based on the prediction model.
9. A marine environment forecasting system, characterized in that it comprises a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the marine environment forecasting method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a marine environment forecasting program which, when executed by a processor, implements the steps of the marine environment forecasting method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210173885.XA CN114706144A (en) | 2022-02-24 | 2022-02-24 | Marine environment forecasting method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210173885.XA CN114706144A (en) | 2022-02-24 | 2022-02-24 | Marine environment forecasting method, device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114706144A true CN114706144A (en) | 2022-07-05 |
Family
ID=82167595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210173885.XA Pending CN114706144A (en) | 2022-02-24 | 2022-02-24 | Marine environment forecasting method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114706144A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115946820A (en) * | 2023-03-15 | 2023-04-11 | 天津大学 | Training method of floating environment data prediction model, floating control method and equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8775341B1 (en) * | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| CN106126896A (en) * | 2016-06-20 | 2016-11-16 | 中国地质大学（武汉） | The mixed model wind speed forecasting method learnt based on empirical mode decomposition and the degree of depth and system |
| CN106446209A (en) * | 2016-09-30 | 2017-02-22 | 浙江大学 | Short-term prediction method for marine environment monitoring factors |
| CN110222872A (en) * | 2019-05-12 | 2019-09-10 | 天津大学 | Long-term statistical prediction methods in the more elements in ocean based on empirical orthogonal function decomposition |
| CN110956807A (en) * | 2019-12-05 | 2020-04-03 | 中通服咨询设计研究院有限公司 | Highway flow prediction method based on combination of multi-source data and sliding window |
| WO2020191801A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Lithium ion battery remaining life prediction method based on wolf pack optimization lstm network |
| CN113283642A (en) * | 2021-05-07 | 2021-08-20 | 淮阴工学院 | Poultry feed detection and formula system |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| CN113641722A (en) * | 2021-07-20 | 2021-11-12 | 西安理工大学 | Long-term time series data prediction method based on variant LSTM |
| CN113869350A (en) * | 2021-08-04 | 2021-12-31 | 中山大学 | Ocean current prediction method and system based on spatial feature difference |
-
2022
- 2022-02-24 CN CN202210173885.XA patent/CN114706144A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8775341B1 (en) * | 2010-10-26 | 2014-07-08 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| CN106126896A (en) * | 2016-06-20 | 2016-11-16 | 中国地质大学（武汉） | The mixed model wind speed forecasting method learnt based on empirical mode decomposition and the degree of depth and system |
| CN106446209A (en) * | 2016-09-30 | 2017-02-22 | 浙江大学 | Short-term prediction method for marine environment monitoring factors |
| WO2020191801A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Lithium ion battery remaining life prediction method based on wolf pack optimization lstm network |
| CN110222872A (en) * | 2019-05-12 | 2019-09-10 | 天津大学 | Long-term statistical prediction methods in the more elements in ocean based on empirical orthogonal function decomposition |
| CN110956807A (en) * | 2019-12-05 | 2020-04-03 | 中通服咨询设计研究院有限公司 | Highway flow prediction method based on combination of multi-source data and sliding window |
| CN113283642A (en) * | 2021-05-07 | 2021-08-20 | 淮阴工学院 | Poultry feed detection and formula system |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| CN113641722A (en) * | 2021-07-20 | 2021-11-12 | 西安理工大学 | Long-term time series data prediction method based on variant LSTM |
| CN113869350A (en) * | 2021-08-04 | 2021-12-31 | 中山大学 | Ocean current prediction method and system based on spatial feature difference |
Non-Patent Citations (1)
| Title |
|---|
| XIAORUI SHEN 等: "A Hybrid Forecasting Model for the Velocity of Hybrid Robotic Fish Based on Back-Propagation Neural Network With Genetic Algorithm Optimization", 《IEEE ACCESS》, 16 June 2020 (2020-06-16), pages 2 - 5 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115946820A (en) * | 2023-03-15 | 2023-04-11 | 天津大学 | Training method of floating environment data prediction model, floating control method and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784041B (en) | Wind power prediction method and system based on graph convolution neural network | |
| CN106991491B (en) | RBF neural network's environmental pollution monitoring system based on genetic algorithm optimization | |
| Gaidai et al. | Improving extreme offshore wind speed prediction by using deconvolution | |
| Samikwa et al. | Flood prediction using IoT and artificial neural networks with edge computing | |
| CN116449462B (en) | Method, system, storage medium and equipment for predicting effective wave height space-time sequence of sea wave | |
| CN113592144A (en) | Medium-and-long-term runoff probability forecasting method and system | |
| Rutagemwa et al. | Dynamic spectrum assignment for land mobile radio with deep recurrent neural networks | |
| CN115220133B (en) | Rainfall prediction method, device and equipment for multiple meteorological elements and storage medium | |
| CN114706144A (en) | Marine environment forecasting method, device, system and storage medium | |
| CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
| Yang et al. | Prediction of significant wave heights based on CS-BP model in the south China sea | |
| Jacoby et al. | Short-term prediction of the attenuation in a commercial microwave link using LSTM-based RNN | |
| CN115982534A (en) | Processing method of river hydrological monitoring data | |
| CN111141879A (en) | Deep learning air quality monitoring method, device and equipment | |
| Cui et al. | A VMD-MSMA-LSTM-ARIMA model for precipitation prediction | |
| CN116822722A (en) | Water level prediction method, system, device, electronic equipment and medium | |
| Vaishali et al. | Weather prediction model using Savitzky-Golay and Kalman Filters | |
| CN115034449A (en) | Overhead line power failure prediction neural network structure searching method and device | |
| CN114897204A (en) | Method and device for predicting short-term wind speed of offshore wind farm | |
| CN115062526A (en) | Deep learning-based three-dimensional ionosphere electron concentration distribution model training method | |
| CN114529035A (en) | CART-based wind speed forecasting method of multi-mode integrated model | |
| Upreti et al. | Wave Height Forecasting Over Ocean of Things Based on Machine Learning Techniques: An Application for Ocean Renewable Energy Generation | |
| CN112070203A (en) | Deep learning-based northern hemisphere high-latitude region ROTI prediction method | |
| Stalder et al. | Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network | |
| Ehiagwina et al. | Development of Neural Network-Based Spectrum Prediction Schemes for Cognitive Wireless Communication: A Case Study of Ilorin, North Central, Nigeria |
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 |