CN114462444B - Navigation state identification method and system of polar survey ship - Google Patents
Navigation state identification method and system of polar survey ship Download PDFInfo
- Publication number
- CN114462444B CN114462444B CN202111576087.3A CN202111576087A CN114462444B CN 114462444 B CN114462444 B CN 114462444B CN 202111576087 A CN202111576087 A CN 202111576087A CN 114462444 B CN114462444 B CN 114462444B
- Authority
- CN
- China
- Prior art keywords
- signal
- time
- power system
- real
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000008569 process Effects 0.000 claims abstract description 18
- 230000009467 reduction Effects 0.000 claims description 94
- 230000007613 environmental effect Effects 0.000 claims description 42
- 238000001914 filtration Methods 0.000 claims description 33
- 238000000354 decomposition reaction Methods 0.000 claims description 26
- 238000005070 sampling Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000011176 pooling Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 6
- 230000001537 neural effect Effects 0.000 description 6
- 238000010606 normalization Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000011835 investigation Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Abstract
The invention provides a navigation state identification method and a navigation state identification system for a polar survey ship, which relate to the technical field of computers and comprise the following steps: step S1, collecting a real-time power system operation signal and a real-time environment state signal generated in the navigation process of a polar survey ship; step S2, corresponding real-time comprehensive navigation data are obtained according to the real-time power system operation signals and the real-time environment state signals; and S3, inputting the real-time comprehensive sailing data into a recognition model which is obtained through pre-training, and processing to obtain a real-time sailing state of the polar survey ship. The navigation state identification method has the beneficial effects of improving the navigation state identification efficiency of the polar survey ship.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a navigation state identification method and system for a polar survey ship.
Background
The polar survey vessel is a specialized marine survey vessel dedicated to marine surveys and surveys in the north-south polar sea region. Because the navigation conditions of the south and north polar sea areas are bad, people need to pay attention to the navigation state of the polar investigation ship at all times so as to take corresponding measures in time when the navigation state of the polar investigation ship is abnormal. The relationship among the power system state, the environment state and the sailing state of the ship in the sailing process is studied deeply through the power system operation data, the environment state data, the sailing log and the like.
Currently, in order to analyze the navigation state of the polar survey ship, engineering personnel with rich polar survey experience are required to analyze the running state data and the environmental state data of the power system generated when the polar survey ship runs so as to judge the navigation state of the polar survey ship.
Because the data quantity related to the running data and the environmental state data of the power system generated during the running of the investigation ship is large, a data analyst is required to have strong data sensitivity and data engineering capability when analyzing the data characteristics of a large number of parameters. In addition, when the data of the power system and the environmental filling data of the polar survey are acquired, time lines corresponding to various data can not be accurately mapped, and the navigation state of the polar survey ship can not be identified in real time.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a navigation state identification method for a polar survey ship, which comprises the following steps:
step S1, collecting a real-time power system operation signal and a real-time environment state signal generated in the navigation process of a polar survey ship;
s2, processing according to the real-time power system operation signal and the real-time environment state signal to obtain corresponding real-time comprehensive navigation data;
And step S3, inputting the real-time comprehensive navigation data into a recognition model which is obtained through pre-training, and processing to obtain a real-time navigation state of the polar survey ship.
Preferably, the step S2 includes:
Step S21, noise reduction processing is carried out on the real-time power system operation signal and the real-time environment state signal to obtain a corresponding power system noise reduction signal and a corresponding environment state noise reduction signal;
Step S22, performing characteristic dimension reduction processing on the power system noise reduction signal and the environment state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environment state dimension reduction signal;
and S23, respectively carrying out standardization processing on the power system dimension reduction signal and the environment state dimension reduction signal to obtain a corresponding power system standard signal and an environment state standard signal, and processing according to the power system standard signal and the environment state standard signal to obtain the real-time comprehensive navigation data.
Preferably, in step S21, the real-time power system operation signal and the real-time environmental state signal are respectively input to a median filter to obtain a corresponding power system filtering signal and a corresponding environmental state filtering signal, and then the power system filtering signal and the environmental state filtering signal are respectively input to a pre-configured third-order low-pass butterworth filter to obtain a corresponding power system noise reduction signal and a corresponding environmental state noise reduction signal.
Preferably, in step S22, adaptive normalization processing is performed on the power system noise reduction signal and the environmental state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environmental state dimension reduction signal.
Preferably, the step S23 includes:
Step S231, respectively carrying out normal standardization processing on the power system dimension reduction signal and the environment state dimension reduction signal to obtain the power system standard signal and the environment state standard signal;
and step S232, processing according to the power system standard signal and the environment state standard signal to obtain the real-time comprehensive navigation data.
Preferably, before executing the step S3, the method includes:
A1, acquiring historical power system operation signals and historical environment state signals respectively generated by the polar survey ship in a plurality of power operation modes, wherein the power operation modes comprise an ice breaking mode, a pitch paddle mode and a combined mode;
a2, respectively constructing corresponding time sequence data sets according to the historical power system operation signals and the historical environment state signals, and respectively extracting each frequency domain signal and each time domain signal according to each time sequence data set;
Step A3, respectively constructing corresponding time domain weak classifiers according to the time domain signals, and respectively constructing corresponding frequency domain weak classifiers according to the frequency domain signals;
Step A4, integrating the time domain weak classifiers and the frequency domain weak classifiers to obtain the identification model and storing the identification model;
And in the step S3, the real-time comprehensive navigation data is input to the recognition model obtained by integrating each time domain weak classifier and each frequency domain weak classifier, and the recognition model outputs the corresponding power operation mode and is output as the real-time navigation state.
Preferably, the step A2 includes:
Step A21, sampling each time sequence data set according to a preset sampling frequency to obtain a plurality of groups of sub data sets;
Step A22, performing empirical mode decomposition on the historical power system operation signals and the historical environment state signals in each sub-data set to obtain corresponding historical power system decomposition signals and corresponding historical environment state decomposition signals;
And step A23, respectively carrying out filtering treatment on the historical power system decomposition signal and the historical environment state decomposition signal to obtain a corresponding historical power system filtering signal and a corresponding historical environment state filtering signal, then carrying out superposition treatment on the historical power system filtering signal and the historical environment state filtering signal to obtain a corresponding one-dimensional time domain signal, decomposing the one-dimensional time domain signal to obtain the frequency domain signal and outputting the frequency domain signal, and reconstructing the one-dimensional time domain signal to obtain a two-dimensional time domain signal as the time domain signal to output.
Preferably, there is also provided a navigation state recognition system of a polar survey ship, applying the navigation state recognition method as set forth in any one of the above, the navigation state recognition system comprising:
The acquisition module is used for acquiring a real-time power system operation signal and a real-time environment state signal generated in the navigation process of the polar survey ship;
The preprocessing module is connected with the acquisition module and is used for processing the real-time environmental state signals according to the real-time power system operation signals and the real-time environmental state signals to obtain corresponding real-time environmental state signals and outputting the corresponding real-time environmental state signals;
The recognition module is connected with the preprocessing module and is used for inputting the real-time comprehensive navigation data into a recognition model which is obtained through pre-training, and processing the real-time comprehensive navigation data to obtain a real-time navigation state of the polar survey ship.
Preferably, the preprocessing module includes:
the noise reduction unit is used for respectively carrying out noise reduction processing on the real-time power system operation signal and the real-time environment state signal to obtain a corresponding power system noise reduction signal and a corresponding environment state noise reduction signal;
The dimension reduction unit is connected with the noise reduction unit and is used for performing characteristic dimension reduction processing on the power system noise reduction signal and the environment state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environment state dimension reduction signal;
The standardized unit is connected with the dimension reduction unit and is used for respectively carrying out standardized processing on the dimension reduction signal of the power system and the dimension reduction signal of the environment state to obtain a corresponding power system standard signal and an environment state standard signal, and processing the power system standard signal and the environment state standard signal to obtain the real-time comprehensive navigation data.
Preferably, the system further comprises a model building module connected with the identification module, wherein the model building module comprises:
The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring historical power system operation signals and historical environment state signals generated by the polar survey ship in a plurality of power operation modes, and the power operation modes comprise an ice breaking mode, a certain pitch paddle mode and a combined mode;
the signal extraction unit is connected with the acquisition unit and used for respectively constructing corresponding time sequence data sets according to the historical power system operation signals and the historical environment state signals and respectively extracting and obtaining frequency domain signals and time domain signals according to the time sequence data sets;
The signal processing unit is connected with the signal extraction unit and is used for respectively constructing corresponding time domain weak classifiers according to the time domain signals and respectively constructing corresponding frequency domain weak classifiers according to the frequency domain signals;
The model construction unit is connected with the signal processing unit and is used for integrating and obtaining the identification model according to each time domain weak classifier and each frequency domain weak classifier and storing the identification model;
And in the identification model, inputting the real-time comprehensive navigation data into the identification model obtained by integrating each time domain weak classifier and each frequency domain weak classifier, and outputting the corresponding power operation mode by the identification model and outputting the power operation mode as the real-time navigation state.
The technical scheme has the following advantages or beneficial effects: the comprehensive navigation data is obtained according to the real-time power system operation signals and the real-time environment state signals generated by the polar survey ship in the navigation process, and then the comprehensive navigation data is input into the recognition model to obtain the real-time navigation state, so that the time and labor consumed by manually recognizing the real-time navigation state of the polar survey ship are reduced, and the recognition efficiency of the navigation state recognition is improved because the polar survey ship does not need to manually analyze the data characteristics of a large number of parameters.
Drawings
FIG. 1 is a flow chart of a method for identifying voyage status in a preferred embodiment of the present invention;
FIG. 2 is a flowchart showing a step S2 of the navigation state identification method according to a preferred embodiment of the present invention;
FIG. 3 is a flowchart showing a step S23 of the navigation state identification method according to the preferred embodiment of the present invention;
FIG. 4 is a flowchart showing the construction of an identification model according to the preferred embodiment of the present invention;
FIG. 5 is a flowchart showing the steps A2 of the navigation state identification method according to the preferred embodiment of the present invention;
FIG. 6 is a network structure diagram of a first neural convolutional network model in accordance with a preferred embodiment of the present invention;
FIG. 7 is a network structure diagram of a second neural convolutional network model in a preferred embodiment of the present invention;
FIG. 8 is a control schematic diagram of a sailing state recognition system in accordance with a preferred embodiment of the present invention;
fig. 9 is a schematic diagram of a specific control of the signal extraction unit according to a preferred embodiment of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present invention is not limited to the embodiment, and other embodiments may fall within the scope of the present invention as long as they conform to the gist of the present invention.
In a preferred embodiment of the present invention, based on the above-mentioned problems existing in the prior art, there is now provided a navigation state recognition method for a polar survey ship, as shown in fig. 1, comprising:
step S1, collecting a real-time power system operation signal and a real-time environment state signal generated in the navigation process of a polar survey ship;
step S2, corresponding real-time comprehensive navigation data are obtained according to the real-time power system operation signals and the real-time environment state signals;
and S3, inputting the real-time comprehensive sailing data into a recognition model which is obtained through pre-training, and processing to obtain a real-time sailing state of the polar survey ship.
Specifically, in the embodiment, in the process of identifying the real-time sailing state of the polar survey ship, the real-time power system operation signal is combined with the real-time environment state signal, and the real-time environment state signal reflecting the environment factors is used as one of the identification bases of the real-time sailing state of the polar survey ship, so that the real-time sailing state output by the identification model is more in line with the actual sailing state corresponding to the polar survey ship, and the applicability and reliability of the sailing state identification method are improved.
When the polar survey ship is subjected to real-time navigation state judgment, the related data volume is large, the data are redundant, and the staff for judging the real-time navigation state is required to have the professional capability of being too hard, so that the polar survey ship needs to be provided with suitable staff when executing the polar survey task, and consumed staff can incline to the polar survey task more, thereby providing convenience for polar survey.
In a preferred embodiment of the present invention, as shown in fig. 2, step S2 includes:
step S21, noise reduction processing is carried out on the real-time power system operation signal and the real-time environment state signal respectively to obtain a corresponding power system noise reduction signal and a corresponding environment state noise reduction signal;
Step S22, performing characteristic dimension reduction processing on the power system noise reduction signal and the environment state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environment state dimension reduction signal;
And S23, respectively carrying out standardized processing on the power system dimension reduction signal and the environment state dimension reduction signal to obtain a corresponding power system standard signal and environment state standard signal, and processing according to the power system standard signal and the environment state standard signal to obtain real-time comprehensive navigation data.
In the preferred embodiment of the present invention, in step S21, the real-time power system operation signal and the real-time environmental state signal are respectively input to a median filter to obtain a corresponding power system filtering signal and a corresponding environmental state filtering signal, and then the power system filtering signal and the environmental state filtering signal are respectively input to a pre-configured three-order low-pass butterworth filter to obtain a corresponding power system noise reduction signal and a corresponding environmental state noise reduction signal.
Specifically, in this embodiment, the gain of the n-order butterworth low-pass filter can be expressed as:
Where n denotes the order of the butterworth low-pass filter, ω c denotes a turn-over frequency, ω c is approximately equal to the frequency at which the amplitude drops to-3 dB, ω p denotes the passband edge frequency, A numerical value representing the passband edge of |h (ω) | 2.
In the preferred embodiment of the present invention, in step S22, adaptive normalization processing is performed on the power system noise reduction signal and the environmental state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environmental state dimension reduction signal.
Specifically, in this embodiment, the formula of adaptive normalization is:
Wherein lambda represents a non-negative regular parameter, Representing a penalty term.
In another embodiment, the adaptive normalized equation is adjusted for the integrated voyage data with variable selection inconsistencies, resulting in the adjusted equation as follows:
wherein, A weight is represented as a set of weights,Is the coefficient derived by the normal least squares method.
In a preferred embodiment of the present invention, as shown in fig. 3, step S23 includes:
Step S231, respectively carrying out normal standardized processing on the power system dimension reduction signal and the environment state dimension reduction signal to obtain a power system standard signal and an environment state standard signal;
and step S232, processing according to the power system standard signal and the environment state standard signal to obtain real-time comprehensive navigation data.
Specifically, in this embodiment, the normal normalization process is used to balance the weight ratio of the data in different dimensions, and the normal normalization formula is as follows:
wherein x represents the comprehensive navigation data after dimension reduction, mu represents a mean value, and sigma represents a standard deviation. The formula for σ is as follows:
Where N represents a sample number.
In a preferred embodiment of the present invention, before executing step S3, as shown in fig. 4, the method includes:
A1, acquiring a historical power system running signal and a historical environment state signal which are respectively generated by a polar survey ship in a plurality of power operation modes, wherein the power operation modes comprise an ice breaking mode, a certain pitch paddle mode and a combined mode;
A2, respectively constructing corresponding time sequence data sets according to the historical power system operation signals and the historical environment state signals, and respectively extracting each frequency domain signal and each time domain signal according to each time sequence data set;
Step A3, respectively constructing corresponding time domain weak classifiers according to the time domain signals, and respectively constructing corresponding frequency domain weak classifiers according to the frequency domain signals;
Step A4, integrating and obtaining an identification model according to each time domain weak classifier and each frequency domain weak classifier, and storing the identification model;
In step S3, the real-time comprehensive navigation data is input to the recognition model obtained by integrating each time domain weak classifier and each frequency domain weak classifier, and the recognition model outputs the corresponding power operation mode and is output as the real-time navigation state.
Specifically, in this embodiment, the step A2 is further performed before the step A2 is performed, where the historical power system operation signal and the historical environmental status signal are preprocessed so as to facilitate the subsequent construction of the corresponding time-series data set.
In step A1, an expert having a navigation state discrimination experience of 2 years or more manually marks the power operation modes, wherein the marking content includes an ice breaking mode, a pitch-and-pitch mode and a combination mode, and the historical power system operation signals and the historical environment state signals are classified into corresponding power operation modes.
In a preferred embodiment of the present invention, as shown in fig. 5, step A2 includes:
step A21, sampling each time sequence data set according to a preset sampling frequency to obtain a plurality of groups of sub data sets;
step A22, performing empirical mode decomposition on the historical power system operation signals and the historical environment state signals in each sub-data set to obtain corresponding historical power system decomposition signals and corresponding historical environment state decomposition signals;
And step A23, respectively carrying out filtering treatment on the historical power system decomposition signal and the historical environment state decomposition signal to obtain a corresponding historical power system filtering signal and a corresponding historical environment state filtering signal, then carrying out superposition treatment on the historical power system filtering signal and the historical environment state filtering signal to obtain a corresponding one-dimensional time domain signal, decomposing the one-dimensional time domain signal to obtain a frequency domain signal and outputting the frequency domain signal, and reconstructing the one-dimensional time domain signal to obtain a two-dimensional time domain signal as a time domain signal to be output.
Specifically, in this embodiment, sample collection is performed on the time-series data set s= { S (i) |i=1, 2,..n } according to the sampling frequency f, so as to obtain a plurality of sets of sub-data sets.
When each sub-data set is subjected to empirical mode decomposition, the data set s (i) is decomposed into m decomposition signalsWherein the j-th decomposition signal is:
Where β is a penalty term coefficient, α is a constant term, w (i) is the center frequency of the dataset s (i), For the center frequency of the jth decomposed signal,The calculation formula of (2) is as follows:
subsequently, the frequency domain signal is extracted: dividing the m signals into After Gaussian filtering processing, superposition processing is carried out to form an intermediate process signal P (i), and then the decomposition signal is decomposed based on wavelet transformation to obtain a frequency domain signal V (i);
Next, a time domain signal is extracted: the intermediate process signal P (i) (i.e., the one-dimensional time domain signal) is reconstructed into a two-dimensional time domain signal T (i) by taking a minimum period as a breakpoint, and the two-dimensional time domain signal T (i) is output as an extracted time domain signal.
Step A3 includes a process of constructing a time domain weak classifier and a process of constructing a frequency domain weak classifier.
The process of constructing the time domain weak classifier is as follows, as shown in fig. 6:
training a first neural convolution network model according to the two-dimensional time domain signal T (i) to obtain a corresponding time domain weak classifier
Wherein the first neural convolutional network model comprises:
a first input layer 100, the input time domain sample size is 64×16, and the channel number is 1;
A first convolution layer 200, connected to the first input layer 100, having a convolution kernel size of 3×3, a step size of 1, zero padding pad=1, a feature map size of 64×16, a feature map depth of 6, and a relu as an activation function;
a first pooling layer 300 connected to the first convolution layer 200, with a feature map size of 32×8, a step size of 2, and zero padding pad=0;
A second convolution layer 201, connected to the first input layer 100, having a convolution kernel size of 3×3, a step size of 1, zero padding pad=1, a feature map size of 32×8, a feature map depth of 24, and a relu as an activation function;
a second pooling layer 301 connected to the second convolution layer 201, with a feature map size of 16×4, a step size of 2, and zero padding pad=0;
A first full connection layer 400, which connects the first pooling layer 300 and the second pooling layer 301, respectively, sets the number of neurons to 64, sets the Dropout parameter to 0.5, and sets the threshold of the activation function to 0.5;
The first output layer 500 is connected to the first full connection layer 400, and has an output class of 4, and corresponds to an ice breaking mode, a pitch blade mode and a combination mode, respectively.
The process of constructing the frequency domain weak classifier is as follows, as shown in fig. 7:
Training a second neural convolution network model according to the frequency domain signal V (i) to obtain a corresponding frequency domain weak classifier
Wherein the second neural convolutional network model comprises:
a second input layer 101, the input frequency domain sample size is 28×28, and the channel number is 1;
A third convolution layer 202, connected to the second input layer 101, having a convolution kernel size of 5×5, a step size of 1, zero padding pad=0, a feature map size of 24×24, a feature map depth of 6, and a relu as an activation function;
A third pooling layer 302, connected to the third convolution layer 202, with a feature map size of 12×12, a step size of2, and zero padding pad=0;
A fourth convolution layer 203 connected to the second input layer 101, the convolution kernel size being 5×5, the step size being 1, the zero padding pad=0, the feature map size being 8×8, the feature map depth being 24, relu being an activation function;
A fourth pooling layer 303 connected to the fourth convolution layer 203, the feature map size being 4×4, the step size being 2, zero padding pad=0;
a second full connection layer 401, which connects the third pooling layer 302 and the fourth pooling layer 303, respectively, sets the number of neurons to 36, sets the Dropout parameter to 0.5, and sets the threshold of the activation function to 0.5;
the second output layer 501 is connected to the second full connection layer 401, and has an output class of 3, and corresponds to an ice breaking mode, a pitch blade mode and a combination mode.
And then integrating the 2f time domain weak classifiers and the frequency domain weak classifiers to form an identification model, wherein the formula is as follows:
wherein, Is a coefficient set of a weak classifier in the time domain,Is the coefficient set of the frequency domain weak classifier.
In a preferred embodiment of the present invention, there is also provided a navigation state identification system for polar survey of a ship, applying the navigation state identification method as described above, as shown in fig. 8, the navigation state identification system comprising:
The acquisition module 1 is used for acquiring a real-time power system operation signal and a real-time environment state signal generated in the navigation process of the polar survey ship;
The preprocessing module 2 is connected with the acquisition module 1 and is used for processing the real-time environmental state signals according to the real-time power system operation signals and the real-time environmental state signals to obtain corresponding real-time environmental state signals and outputting the corresponding real-time environmental state signals;
The recognition module 3 is connected with the preprocessing module 2 and is used for inputting the real-time comprehensive navigation data into a recognition model which is obtained through pre-training, and processing the real-time comprehensive navigation data to obtain a real-time navigation state of the polar survey ship.
In a preferred embodiment of the invention, the preprocessing module 2 comprises:
the noise reduction unit 21 is configured to perform noise reduction processing on the real-time power system operation signal and the real-time environmental state signal to obtain a corresponding power system noise reduction signal and a corresponding environmental state noise reduction signal;
the dimension reduction unit 22 is connected with the noise reduction unit 21 and is used for performing characteristic dimension reduction processing on the power system noise reduction signal and the environment state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environment state dimension reduction signal;
The normalizing unit 23 is connected with the dimension reducing unit 22, and is used for respectively carrying out normalization processing on the dimension reducing signal of the power system and the dimension reducing signal of the environmental state to obtain a corresponding standard signal of the power system and a corresponding standard signal of the environmental state, and processing according to the standard signal of the power system and the standard signal of the environmental state to obtain real-time comprehensive navigation data.
In the preferred embodiment of the present invention, the present invention further comprises a model building module 4, connected to the identification module 3, and the model building module 4 includes:
The acquisition unit 41 is configured to acquire historical power system operation signals and historical environmental status signals generated by the polar survey ship in a plurality of power operation modes, where the power operation modes include an ice breaking mode, a pitch-paddle mode and a combined mode;
The signal extraction unit 42 is connected with the acquisition unit 41 and is used for respectively constructing corresponding time sequence data sets according to the historical power system operation signals and the historical environment state signals and respectively extracting and obtaining each frequency domain signal and each time domain signal according to each time sequence data set;
A signal processing unit 43, connected to the signal extracting unit 42, configured to respectively construct a corresponding time domain weak classifier according to each time domain signal, and respectively construct a corresponding frequency domain weak classifier according to each frequency domain signal;
The model building unit 44 is connected with the signal processing unit 43, and is used for integrating and obtaining and storing an identification model according to each time domain weak classifier and each frequency domain weak classifier;
And in the identification model, inputting real-time comprehensive navigation data into the identification model obtained by integrating each time domain weak classifier and each frequency domain weak classifier, and outputting a corresponding power operation mode by the identification model and outputting the power operation mode as a real-time navigation state.
Specifically, in the present embodiment, as shown in fig. 9, the signal extraction unit 42 includes:
a sampling unit 421, configured to sample each time sequence data set according to a preset sampling frequency to obtain a plurality of groups of sub data sets;
The decomposition subunit 422 is connected with the sampling subunit 421, and is configured to perform empirical mode decomposition on the historical power system operation signal and the historical environmental state signal in each sub-data set to obtain a corresponding historical power system decomposition signal and a corresponding historical environmental state decomposition signal;
The processing subunit 423 is connected to the decomposition subunit 422, and is configured to perform filtering processing on the historical power system decomposition signal and the historical environment state decomposition signal to obtain a corresponding historical power system filtering signal and a corresponding historical environment state filtering signal, then perform superposition processing on the historical power system filtering signal and the historical environment state filtering signal to obtain a corresponding one-dimensional time domain signal, decompose the one-dimensional time domain signal to obtain a frequency domain signal, output the frequency domain signal, and reconstruct the one-dimensional time domain signal to obtain a two-dimensional time domain signal as a time domain signal to output.
In summary, the corresponding comprehensive navigation data is obtained by processing the real-time power system operation signals and the real-time environment state signals generated in the navigation process of the polar survey ship, then the comprehensive navigation data is input into the recognition models integrated by the time domain weak classifiers and the frequency domain weak classifiers, and the recognition models output the real-time navigation state of the polar survey ship, so that the time and labor consumed for recognizing the real-time navigation state of the polar survey ship are reduced, and the recognition efficiency of the navigation state recognition is improved.
The foregoing description is only illustrative of the preferred embodiments of the present invention and is not to be construed as limiting the scope of the invention, and it will be appreciated by those skilled in the art that equivalent substitutions and obvious variations may be made using the description and drawings, and are intended to be included within the scope of the present invention.
Claims (7)
1. The navigation state identification method of the polar survey ship is characterized by comprising the following steps of:
step S1, collecting a real-time power system operation signal and a real-time environment state signal generated in the navigation process of a polar survey ship;
s2, processing according to the real-time power system operation signal and the real-time environment state signal to obtain corresponding real-time comprehensive navigation data;
S3, inputting the real-time comprehensive navigation data into an identification model obtained by pre-training, and processing to obtain a real-time navigation state of the polar survey ship;
The step S2 includes:
Step S21, noise reduction processing is carried out on the real-time power system operation signal and the real-time environment state signal to obtain a corresponding power system noise reduction signal and a corresponding environment state noise reduction signal;
Step S22, performing characteristic dimension reduction processing on the power system noise reduction signal and the environment state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environment state dimension reduction signal;
Step S23, respectively carrying out standardized processing on the power system dimension reduction signal and the environment state dimension reduction signal to obtain a corresponding power system standard signal and environment state standard signal, and processing according to the power system standard signal and the environment state standard signal to obtain the real-time comprehensive navigation data;
before executing the step S3, the method includes:
A1, acquiring historical power system operation signals and historical environment state signals respectively generated by the polar survey ship in a plurality of power operation modes, wherein the power operation modes comprise an ice breaking mode, a pitch paddle mode and a combined mode;
a2, respectively constructing corresponding time sequence data sets according to the historical power system operation signals and the historical environment state signals, and respectively extracting each frequency domain signal and each time domain signal according to each time sequence data set;
Step A3, respectively constructing corresponding time domain weak classifiers according to the time domain signals, and respectively constructing corresponding frequency domain weak classifiers according to the frequency domain signals;
Step A4, integrating the time domain weak classifiers and the frequency domain weak classifiers to obtain the identification model and storing the identification model;
In the step S3, the real-time comprehensive navigation data is input to the recognition model obtained by integrating each time domain weak classifier and each frequency domain weak classifier, and the recognition model outputs the corresponding power operation mode and is output as the real-time navigation state;
The step A2 comprises the following steps:
Step A21, sampling each time sequence data set according to a preset sampling frequency to obtain a plurality of groups of sub data sets;
Step A22, performing empirical mode decomposition on the historical power system operation signals and the historical environment state signals in each sub-data set to obtain corresponding historical power system decomposition signals and corresponding historical environment state decomposition signals;
And step A23, respectively carrying out filtering treatment on the historical power system decomposition signal and the historical environment state decomposition signal to obtain a corresponding historical power system filtering signal and a corresponding historical environment state filtering signal, then carrying out superposition treatment on the historical power system filtering signal and the historical environment state filtering signal to obtain a corresponding one-dimensional time domain signal, decomposing the one-dimensional time domain signal to obtain the frequency domain signal and outputting the frequency domain signal, and reconstructing the one-dimensional time domain signal to obtain a two-dimensional time domain signal as the time domain signal to output.
2. The method according to claim 1, wherein in the step S21, the real-time power system operation signal and the real-time environmental state signal are respectively input to a median filter to obtain a corresponding power system filtering signal and a corresponding environmental state filtering signal, and then the power system filtering signal and the environmental state filtering signal are respectively input to a pre-configured third-order low-pass butterworth filter to obtain the corresponding power system noise reduction signal and the corresponding environmental state noise reduction signal.
3. The method according to claim 1, wherein in step S22, the power system noise reduction signal and the environmental state noise reduction signal are adaptively normalized to obtain the corresponding power system dimension reduction signal and the corresponding environmental state dimension reduction signal, respectively.
4. The navigation state identification method according to claim 1, wherein the step S23 includes:
Step S231, respectively carrying out normal standardization processing on the power system dimension reduction signal and the environment state dimension reduction signal to obtain the power system standard signal and the environment state standard signal;
and step S232, processing according to the power system standard signal and the environment state standard signal to obtain the real-time comprehensive navigation data.
5. A voyage state recognition system of a polar survey ship, characterized in that the voyage state recognition method according to any one of claims 1-4 is applied, the voyage state recognition system comprising:
The acquisition module is used for acquiring a real-time power system operation signal and a real-time environment state signal generated in the navigation process of the polar survey ship;
The preprocessing module is connected with the acquisition module and is used for processing the real-time environmental state signals according to the real-time power system operation signals and the real-time environmental state signals to obtain corresponding real-time environmental state signals and outputting the corresponding real-time environmental state signals;
The recognition module is connected with the preprocessing module and is used for inputting the real-time comprehensive navigation data into a recognition model which is obtained through pre-training, and processing the real-time comprehensive navigation data to obtain a real-time navigation state of the polar survey ship.
6. The voyage state identification system of claim 5, wherein the preprocessing module comprises:
the noise reduction unit is used for respectively carrying out noise reduction processing on the real-time power system operation signal and the real-time environment state signal to obtain a corresponding power system noise reduction signal and a corresponding environment state noise reduction signal;
The dimension reduction unit is connected with the noise reduction unit and is used for performing characteristic dimension reduction processing on the power system noise reduction signal and the environment state noise reduction signal to obtain a corresponding power system dimension reduction signal and a corresponding environment state dimension reduction signal;
The standardized unit is connected with the dimension reduction unit and is used for respectively carrying out standardized processing on the dimension reduction signal of the power system and the dimension reduction signal of the environment state to obtain a corresponding power system standard signal and an environment state standard signal, and processing the power system standard signal and the environment state standard signal to obtain the real-time comprehensive navigation data.
7. The voyage state identification system of claim 5, further comprising a model building module coupled to the identification module, the model building module comprising:
The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring historical power system operation signals and historical environment state signals generated by the polar survey ship in a plurality of power operation modes, and the power operation modes comprise an ice breaking mode, a certain pitch paddle mode and a combined mode;
the signal extraction unit is connected with the acquisition unit and used for respectively constructing corresponding time sequence data sets according to the historical power system operation signals and the historical environment state signals and respectively extracting and obtaining frequency domain signals and time domain signals according to the time sequence data sets;
The signal processing unit is connected with the signal extraction unit and is used for respectively constructing corresponding time domain weak classifiers according to the time domain signals and respectively constructing corresponding frequency domain weak classifiers according to the frequency domain signals;
The model construction unit is connected with the signal processing unit and is used for integrating and obtaining the identification model according to each time domain weak classifier and each frequency domain weak classifier and storing the identification model;
And in the identification model, inputting the real-time comprehensive navigation data into the identification model obtained by integrating each time domain weak classifier and each frequency domain weak classifier, and outputting the corresponding power operation mode by the identification model and outputting the power operation mode as the real-time navigation state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111576087.3A CN114462444B (en) | 2021-12-21 | Navigation state identification method and system of polar survey ship |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111576087.3A CN114462444B (en) | 2021-12-21 | Navigation state identification method and system of polar survey ship |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114462444A CN114462444A (en) | 2022-05-10 |
| CN114462444B true CN114462444B (en) | 2024-07-09 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327610A (en) * | 2016-08-27 | 2017-01-11 | 南通中远川崎船舶工程有限公司 | Intelligent ship for arctic navigation |
| CN108313236A (en) * | 2018-01-24 | 2018-07-24 | 深圳远航股份有限公司 | A kind of ship's navigation method for early warning and system |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327610A (en) * | 2016-08-27 | 2017-01-11 | 南通中远川崎船舶工程有限公司 | Intelligent ship for arctic navigation |
| CN108313236A (en) * | 2018-01-24 | 2018-07-24 | 深圳远航股份有限公司 | A kind of ship's navigation method for early warning and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109916628B (en) | Rolling bearing fault diagnosis method based on improved multi-scale amplitude perception permutation entropy | |
| CN111523509B (en) | Equipment fault diagnosis and health monitoring method integrating physical and depth expression characteristics | |
| CN102721545B (en) | Rolling bearing failure diagnostic method based on multi-characteristic parameter | |
| CN111783558A (en) | Satellite navigation interference signal type intelligent identification method and system | |
| CN111880157B (en) | Method and system for detecting target in radar image | |
| CN105841961A (en) | Bearing fault diagnosis method based on Morlet wavelet transformation and convolutional neural network | |
| CN110333076B (en) | Bearing fault diagnosis method based on CNN-Stacking | |
| CN110297469B (en) | Production line fault judgment method based on resampling integrated feature selection algorithm | |
| CN104795064A (en) | Recognition method for sound event under scene of low signal to noise ratio | |
| CN114021441A (en) | Ship motion attitude prediction method based on CNN-BilSTM | |
| CN111898447A (en) | Wind turbine generator fault feature extraction method based on octyl geometric modal decomposition | |
| CN112163472A (en) | Rolling bearing diagnosis method based on multi-view feature fusion | |
| CN102539159A (en) | Fault diagnosis method for valve mechanism of diesel engine | |
| CN104569694A (en) | Electric signal feature extraction and recognition system oriented to aircraft flying process | |
| CN104504403A (en) | Rotating machinery failure forecasting method based on scattering conversion | |
| CN104156628A (en) | Ship radiation signal recognition method based on multi-kernel learning and discriminant analysis | |
| CN113257249A (en) | Power equipment fault diagnosis method, device and equipment based on voiceprint recognition | |
| CN104318305A (en) | Inverter low-frequency noise fault diagnosis method based on wavelets and neural network | |
| CN117150359A (en) | Small sample fault diagnosis method, system, device and medium based on model independent element learning | |
| CN113076878A (en) | Physique identification method based on attention mechanism convolution network structure | |
| CN114462444B (en) | Navigation state identification method and system of polar survey ship | |
| CN114330430A (en) | Elevator fault judgment method and system based on big data characteristic analysis | |
| CN113758709A (en) | Rolling bearing fault diagnosis method and system combining edge calculation and deep learning | |
| CN114462444A (en) | Navigation state identification method and system for polar region inspection ship | |
| CN106073802A (en) | Blood oxygen saturation monitoring device under kinestate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |