CN116304829A - Ship radiation noise gear box reduction ratio feature extraction method and system - Google Patents
Ship radiation noise gear box reduction ratio feature extraction method and system Download PDFInfo
- Publication number
- CN116304829A CN116304829A CN202310290588.8A CN202310290588A CN116304829A CN 116304829 A CN116304829 A CN 116304829A CN 202310290588 A CN202310290588 A CN 202310290588A CN 116304829 A CN116304829 A CN 116304829A
- Authority
- CN
- China
- Prior art keywords
- ship
- frequency
- radiation noise
- spectrum
- reduction ratio
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method and a system for extracting characteristics of a reduction ratio of a ship radiation noise gear box, wherein the method comprises the following steps: collecting ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals to obtain framing signals; carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram, and extracting a target ship propeller shaft frequency value; performing LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram, and extracting a target ship host ignition frequency value; establishing a numerical relation among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio through a mechanical coupling structure model; and calculating and extracting the characteristics of the reduction ratio of the gear box of the target ship based on the numerical relation. The method can provide stable, reliable and interpretable characteristic parameters for ship target identification under complex working conditions of different navigational speeds.
Description
Technical Field
The invention belongs to the technical field of underwater sound target identification, and particularly relates to a ship radiation noise gear box reduction ratio feature extraction method, a system, computer equipment and a readable storage medium.
Background
The ship radiation noise recognition is an important research content in the field of underwater acoustic signal processing, is widely focused and deeply studied by researchers at home and abroad, and particularly, along with the development of deep learning theory, more and more algorithm models are applied to the field of underwater acoustic target recognition. Target recognition using deep learning, the physical interpretability of the network feature extraction mapping process is poor and a large amount of data is required as support. How to extract stable characteristics reflecting the essential characteristics of the targets under the condition of complexity of working conditions and realize accurate classification and identification of the ship targets by using a small number of characteristics under the condition of small samples is a challenging problem faced by the field.
The inherent physical characteristics of the ship targets such as the host rotation speed, the cylinder number, the axial frequency, the paddle leaf number and the like are usually in the form of line spectrum in the DEMON spectrum of the ship radiation noise signals, and the parameters are often related to the mechanical structure and the running speed, so that the ship targets have definite physical significance and can identify the types of the targets only by one or a plurality of the parameters.
The DEMON spectrum is a ship propeller cavitation noise demodulation spectrum, and regarding the propeller cavitation noise spectrum, a more mature and reliable mathematical model of two theoretical backgrounds of a pulse sequence theory and a cavitation group theory exists, and along with the development and progress of technical algorithms such as DEMON spectrum estimation, propeller axis frequency extraction, propeller leaf number identification and the like, the characteristic information contained in a DEMON harmonic line spectrum cluster is continuously extracted and utilized more effectively.
The LOFAR spectrum is a low-frequency part of a short-time fourier transform spectrum of ship radiation noise, is widely used as input of a convolution network model in ship target identification, and carries a large amount of characteristic information mainly from periodic operation of mechanical equipment and low-frequency vibration of a ship structure. The measured ship radiation noise data processing result shows that the LOFAR spectral line spectrum frequency also has a certain multiple relationship, but because of being interfered by environmental noise, the signal to noise ratio is generally lower and the phenomenon of line spectrum deletion is accompanied, and an enhancement algorithm is needed for processing before the line spectrum is extracted.
However, the correspondence between the line spectrum of the LOFAR and the running period and the vibration frequency is not clear at present, and is a difficult problem faced by the research of the ship identification characteristics and the extraction of the inherent characteristics. In addition, the existing inherent characteristic parameters are fewer, and the ability of identifying the radiation noise of the ship under complex working conditions such as different navigational speeds is limited.
In summary, in the identification of the radiation noise of the ship under the complex working conditions of different navigational speeds and the like, an inherent characteristic with definite physical significance and stability under different navigational speeds is urgently needed at present so as to improve the reliability and the accuracy of the ship target identification system.
Disclosure of Invention
In order to solve the problems, the invention aims to provide the characteristic extraction method and the characteristic extraction system for the reduction ratio of the ship radiation noise gearbox, which can provide stable, reliable and interpretable characteristic parameters for ship target identification under complex working conditions of different navigational speeds.
In order to achieve the above purpose, the technical scheme of the invention is as follows: a ship radiation noise gear box reduction ratio feature extraction method comprises the following steps: collecting ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals to obtain framing signals; carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram, and extracting a target ship propeller shaft frequency value; performing LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram, and extracting a target ship host ignition frequency value; establishing a numerical relation among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio through a mechanical coupling structure model; and calculating and extracting the characteristics of the reduction ratio of the gear box of the target ship based on the numerical relation.
Preferably, collecting the ship radiation noise signal by the passive sonar, performing frame pretreatment on the received signal to obtain a frame signal further comprises: receiving a ship radiation noise time domain signal x (n) collected by a passive sonar system: x (n) = [ x (1), x (2), …, x (f) s ),…,x(M)]Wherein f s The signal sampling rate is represented by M, which is the number of time domain sampling points;
carrying out framing pretreatment on a passive sonar receiving signal to obtain:
Preferably, the DEMON spectrum estimation is performed on the frame-divided signal, a ship radiation noise DEMON spectrum time-frequency diagram is synthesized, and the extracting the target ship propeller axis frequency value further includes: performing variation modal decomposition on the framing signals; selecting the (k+1) th frame signal X in the framing signals k The empirical mode decomposition is carried out to obtain an adaptive decomposition order j for X k Carrying out j-order variational modal decomposition to obtain j natural modal components:
calculating correlation coefficient of narrowband signal, for X k The j natural modal components of (1) are subjected to narrow-band envelope correlation two by two to obtain a correlation coefficient matrix: />
Wherein R is j The correlation coefficient of the j-th natural mode component and other-order natural mode components; for->
Square detection and power spectrum analysis are carried out on each order of natural modes to obtain j natural mode components corresponding toAnd R is performed according to the narrow-band envelope correlation coefficient kj Weighted fusion is carried out to obtain DEMON spectrum P of kth frame signal k ：/>
Combining the DEMON spectrums of the K frame signals to obtain a DEMON spectrum time-frequency diagram of the ship radiation noise receiving signal>
Extracting fundamental frequency line spectrum frequency value f in harmonic line spectrum cluster of ship radiation noise signal DEMON spectrum time-frequency diagram z The frequency value is the propeller shaft frequency of the ship.
Preferably, the method for estimating the LOFAR spectrum of the framing signal, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram, and extracting the target ship host ignition frequency value further comprises: for each frame of signal
Performing power spectrum density estimation to obtain power spectrum +.>
Wherein f= [1/f 0 ,2/f 0 ,…,f s ]，f 0 For power spectral frequency resolution; synthesizing each frame of signal power spectrum into a time-frequency power spectrum of ship radiation noise, wherein the process is equivalent to short-time Fourier transform, and taking the frequency band of 0-300 Hz of the time-frequency power spectrum as LOFAR spectrum +.>
Extracting fundamental frequency line spectrum frequency value f in ship radiation noise signal LOFAR spectrum time-frequency chart harmonic line spectrum cluster d The fundamental frequency line spectrum frequency value is the single-cylinder ignition frequency of the ship host; and under the condition of line spectrum missing, calculating the fundamental frequency line spectrum frequency value based on the frequency difference of two adjacent higher harmonic line spectrums.
Preferably, the number among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio is established through a mechanical coupling structure modelThe value relationship further includes: establishing single cylinder ignition frequency f of cylinder of ship host d Relation to crankshaft speed, for a diesel engine with i strokes, the crankshaft rotates i/2 cycles, f, 1 cylinder per firing d With crankshaft speed f q Satisfy the following requirements
Introducing a gear box reduction ratio sigma to establish the main shaft rotating speed f of the ship propeller z Relation f with the rotational speed of the crankshaft of the main engine q ：f q ＝σ·f z The method comprises the steps of carrying out a first treatment on the surface of the Providing the mapping relation between the ship radiation noise modulation spectrum and the low-frequency line spectrum frequency, the relation between the rotating speed of the main shaft of the propeller and the single-cylinder ignition frequency of the main engine cylinder, and calculating the reduction ratio of the gearbox>
Preferably, calculating and extracting the reduction ratio feature of the target ship gearbox based on the numerical relation further comprises: inputting the extracted ship propeller shaft frequency and the single-cylinder ignition frequency of the ship host into a built ship radiation noise modulation spectrum and low-frequency line spectrum frequency mapping relation model, and calculating a gearbox reduction ratio; and verifying stability and separability of the reduction ratio characteristic of the gear box under different navigational speeds based on the radiation noise data of the ship target under different navigational speeds.
Based on the same conception, the invention also provides a ship radiation noise gear box reduction ratio feature extraction system, which comprises: the acquisition module is used for acquiring ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals to acquire framing signals; the DEMON spectrum estimation module is used for carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram and extracting a target ship propeller shaft frequency value; the LOFAR spectrum estimation module is used for carrying out LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram and extracting a target ship host ignition frequency value; the numerical relation establishing module is used for establishing numerical relation among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio through the mechanical coupling structure model; and the calculation module is used for calculating and extracting the reduction ratio characteristic of the gear box of the target ship based on the numerical relation.
Preferably, the system further comprises a preprocessing module, which is used for receiving the ship radiation noise time domain signal x (n) collected by the passive sonar system: x (n) = [ x (1), x (2), …, x (f) s ),…,x(M)]Wherein f s The signal sampling rate is represented by M, which is the number of time domain sampling points;
carrying out framing pretreatment on a passive sonar receiving signal to obtain:
Based on the same conception, the present invention also provides a computer device comprising: a memory for storing a processing program; and the processor is used for realizing the ship radiation noise gear box reduction ratio characteristic extraction method according to any one of the above when executing the processing program.
Based on the same conception, the invention also provides a readable storage medium, wherein a processing program is stored on the readable storage medium, and the processing program realizes the ship radiation noise gear box reduction ratio characteristic extraction method according to any one of the above when being executed by a processor.
By adopting the technical scheme, the invention has the following advantages and positive effects compared with the prior art:
1. the invention provides a new inherent characteristic which can be used for ship target identification, and the characteristic corresponds to the mechanical structure of the ship, has definite physical significance, and has good stability under complex working conditions such as different navigational speeds. Because the gear ratios of the gear boxes of different ship targets are different, the gear boxes of the same type and even the same model ship targets have certain difference due to factors such as machining errors, and the like, the characteristics can be used for distinguishing the ship targets.
2. In the invention, in the ship radiation noise DEMON spectrum estimation, the traditional DEMON analysis technology is improved, the variation modal decomposition is introduced to replace the traditional band-pass filter, and the narrow-band envelope correlation multi-subband weighted fusion technology is adopted to adaptively and fully extract the ship radiation noise signal modulation information, so that the improvement of the ship radiation noise DEMON line spectrum signal-to-noise ratio is facilitated.
3. Based on the existing ship radiation noise LOFAR spectrum characteristic research, the invention firstly determines the actual physical meaning of the LOFAR line spectrum, and provides a method for extracting the single-cylinder ignition frequency of a ship host from the LOFAR line spectrum and a technique for extracting the parameter by utilizing the frequency difference of adjacent higher harmonic line spectrums under the condition of line spectrum deletion.
4. According to the invention, the frequency mapping relation of the host ignition frequency, the crankshaft rotation speed and the main shaft rotation to give out the ship radiation noise modulation spectrum and the low-frequency line spectrum is established according to the mechanical structure model, and the calculation method of the ship target gear box reduction ratio is provided, so that the rapid and accurate feature extraction and target identification can be realized under a small sample, the calculation amount is small, and the actual deployment of a ship target identification system is facilitated.
Drawings
The invention is described in further detail below with reference to the attached drawing figures, wherein:
FIG. 1 is a block diagram of the overall process of feature extraction of the reduction ratio of the ship radiation noise gearbox of the present invention;
FIG. 2 is a target DEMON spectrum estimation flow chart;
FIG. 3 is a DEMON spectrum for target A at different speeds; FIG. 3 (a) navigational speed 4.9kn, axial frequency 3.0Hz; FIG. 3 (b) navigational speed 6.8kn, axial frequency 4.2Hz; FIG. 3 (c) navigational speed 8.6kn, axial frequency 3.0Hz; FIG. 3 (d) navigational speed 10.5kn, axial frequency 7.0Hz;
FIG. 4 is a DEMON spectrum for target B at different speeds; FIG. 4 (a) navigational speed 5.7kn, axial frequency 6.2Hz; FIG. 4 (b) navigational speed 6.6kn, axial frequency 4.2Hz; FIG. 4 (c) navigational speed 7.2kn, axial frequency 3.0Hz; FIG. 4 (d) navigational speed 7.6kn, axial frequency 7.1Hz;
FIG. 5 is a LOFAR spectrum for target A at different speeds; FIG. 5 (a) navigational speed 5.7kn, main engine single cylinder ignition frequency 6.3Hz; FIG. 5 (b) navigational speed 6.6kn, main engine single cylinder ignition frequency 8.9Hz; FIG. 5 (c) voyage speed 7.2kn, main engine single cylinder ignition frequency 11.8Hz; FIG. 5 (d) voyage speed 7.6kn, main engine single cylinder ignition frequency 14.8Hz;
FIG. 6 is a LOFAR spectrum for target B at different speeds; FIG. 6 (a) navigational speed 5.7kn, main engine single cylinder ignition frequency 6.6Hz; FIG. 6 (b) speed 6.6kn, host single cylinder firing frequency 7.5Hz; FIG. 6 (c) voyage speed 7.2kn, main engine single cylinder ignition frequency 8.3Hz; FIG. 6 (d) voyage speed 7.6kn, main engine single cylinder ignition frequency 9.1Hz;
FIG. 7 is a schematic view of a mechanical structure model of a ship;
fig. 8 is a gear box reduction ratio of 5 boats extracted by the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and the specific examples. Advantages and features of the invention will become more apparent from the following description and from the claims. It is noted that the drawings are in a very simplified form and utilize non-precise ratios, and are intended to facilitate a convenient, clear, description of the embodiments of the invention.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present invention are merely used to explain the relative positional relationship, movement, etc. between the components in a particular posture (as shown in the drawings), and if the particular posture is changed, the directional indicator is changed accordingly.
As shown in fig. 1, the embodiment of the invention provides a method for extracting characteristics of a reduction ratio of a ship radiation noise gear box, and an implementation mode of the method comprises the following steps:
step 1: and acquiring ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals. The specific implementation is as follows:
step 101: receiving a ship radiation noise time domain signal x (n) collected by a passive sonar system:
x(n)＝[x(1),x(2),…,x(f s ),…,x(M)]
wherein f s For signal sampling rate, M is the number of time domain samples.
Step 102: carrying out framing pretreatment on the passive sonar receiving signal to obtain
Wherein L is the number of sampling points of each frame of signal, and K is the number of signal frames. In general, a signal with a duration of 5s is taken as one frame, and the duration of overlapping signals of two adjacent frames is 1s.
Step 2: and (3) carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram, and extracting a target ship propeller axis frequency value.
According to the flow shown in fig. 2, the implementation is as follows;
step 201: and carrying out variation modal decomposition on the framing signal.
Selecting the (k+1) th frame signal X in the framing signals k The method comprises the steps of obtaining an adaptive decomposition order j through Empirical Mode Decomposition (EMD) and obtaining X k Performing j-order Variational Modal Decomposition (VMD) to obtain j natural modal components (IMF), namely
Step 202: calculating correlation coefficient of narrowband signal, for X k The j natural modal components of (1) are subjected to narrow-band envelope correlation two by two to obtain a correlation coefficient matrix:
wherein R is j The correlation coefficient of the j-th natural mode component and other-order natural mode components.
Step 203: for a pair of
Square detection and power spectrum analysis are carried out on each order of natural modes to obtain envelope spectrums corresponding to j natural mode components, and R is carried out according to narrow-band envelope correlation coefficients kj Weighted fusion is carried out to obtain DEMON spectrum P of kth frame signal k I.e.
Step 204: combining the DEMON spectrums of the K frame signals to obtain a DEMON spectrum time-frequency diagram P of the ship radiation noise receiving signal, namely
Step 205: extracting fundamental frequency line spectrum frequency value f in harmonic line spectrum cluster of ship radiation noise signal DEMON spectrum time-frequency diagram z The frequency value is the propeller shaft frequency of the ship.
Fig. 3 is a time-frequency diagram of a DEMON spectrum of the target a, and fig. 4 is a time-frequency diagram of a DEMON spectrum of the target B.
Step 3: and carrying out LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram, and extracting the ignition frequency value of the target ship host.
The specific implementation is as follows:
step 301: for each frame of signal
Performing power spectrum density estimation (PSD) to obtain power spectrum S of the frame signal k (f) I.e.
Wherein f= [1/f 0 ,2/f 0 ,…,f s ]，f 0 Is the power spectrum frequency resolution.
Step 302: synthesizing each frame of signal power spectrum into a time-frequency power spectrum of ship radiation noise, wherein the process is equivalent to short-time Fourier transform (STFT), and taking the frequency band of 0-300 Hz of the time-frequency power spectrum as LOFAR spectrum S (f) of the ship radiation noise, namely
Step 303: extracting fundamental frequency line spectrum frequency value f in ship radiation noise signal LOFAR spectrum time-frequency chart harmonic line spectrum cluster d The frequency value is the single-cylinder ignition frequency of the ship host. In the case of a line spectrum missing, the frequency value can be calculated according to the frequency difference of the adjacent two higher harmonic line spectrums.
Fig. 5 is a time-frequency plot of the lover spectrum of target a, and fig. 6 is a time-frequency plot of the lover spectrum of target B.
Step 4: the numerical relationship of the propeller shaft frequency, the main engine ignition frequency, and the gear ratio of the speed reducer is established according to the mechanical coupling structure model shown in fig. 7.
The specific implementation is as follows:
step 401: establishing single cylinder ignition frequency f of cylinder of ship host d Relation to crankshaft speed. For an i-stroke diesel engine, the crankshaft rotates i/2 of a turn per 1 firing of the cylinder, thus f d With crankshaft speed f q Satisfy the following requirements
Step 402: introducing a gear box reduction ratio sigma to establish the rotating speed (axial frequency) f of a main shaft of the ship propeller z Relation f to the rotational speed (frequency) of the crankshaft of the main machine q . I.e.
f q ＝σ·f z
Step 403: gives the mapping relation between the ship radiation noise modulation spectrum and the low-frequency line spectrum frequency, namely the relation between the rotating speed (axial frequency) of the main shaft of the propeller and the single-cylinder ignition frequency of the main engine cylinder, and is used for calculating the reduction ratio of the gearbox, namely
Step 5: calculating and extracting the characteristics of the reduction ratio of the gear box of the target ship by combining the steps 1 to 4; the specific implementation is as follows:
step 501: and (3) inputting the ship propeller shaft frequency extracted in the step (2) and the single-cylinder ignition frequency of the ship host extracted in the step (3) into the ship radiation noise modulation spectrum and low-frequency line spectrum frequency mapping relation model established in the step (4), and calculating the reduction ratio of the gearbox.
Step 502: and verifying the stability and the separability of the characteristic under different navigational speeds by utilizing the radiation noise data of the ship target under different navigational speeds.
The method and the feature extraction effect of the present invention will be described in further detail below with reference to examples.
The data is from 5 target ships in a certain water area, the speed reduction ratio of target A is 2.5:1, the speed reduction ratio of target B is 4.2:1, the speed reduction ratio of target C is 3.5:1, the speed reduction ratio of target D is 3.0:1, and the speed reduction ratio of target E is 4.5:1. The data for each vessel contained at least 3 different speeds, 100 samples were randomly taken for each target, and gearbox reduction ratio features were extracted in accordance with the present invention, with the results shown in fig. 8. Therefore, the gearbox reduction ratio features extracted by the invention have better stability under different navigational speeds, and the 5 targets can be effectively identified only by the parameters.
Based on the same inventive concept, the invention also provides a ship radiation noise gear box reduction ratio feature extraction system, which comprises: the acquisition module is used for acquiring ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals to acquire framing signals; the DEMON spectrum estimation module is used for carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram and extracting a target ship propeller shaft frequency value; the LOFAR spectrum estimation module is used for carrying out LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram and extracting a target ship host ignition frequency value; the numerical relation establishing module is used for establishing numerical relation among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio through the mechanical coupling structure model; and the calculation module is used for calculating and extracting the reduction ratio characteristic of the gear box of the target ship based on the numerical relation.
Preferably, the system further comprises a preprocessing module, which is used for receiving the ship radiation noise time domain signal x (n) collected by the passive sonar system: x (n) = [ x (1), x (2), …, x (f) s ),…,x(M)]Wherein，f s The signal sampling rate is represented by M, which is the number of time domain sampling points;
carrying out framing pretreatment on a passive sonar receiving signal to obtain:
Based on the same inventive concept, the present invention also provides a computer apparatus comprising: a memory for storing a processing program; and the processor is used for realizing the ship radiation noise gear box reduction ratio characteristic extraction method according to any one of the processing procedures when executing the processing procedures.
Based on the same inventive concept, the invention further provides a readable storage medium, wherein a processing program is stored on the readable storage medium, and the processing program realizes the method for extracting the reduction ratio characteristics of the ship radiation noise gearbox when being executed by a processor.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a removable storage device, a read only memory (ReadOnlyMemory, ROM), a magnetic or optical disk, or other various media capable of storing program code.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, it is within the scope of the appended claims and their equivalents to fall within the scope of the invention.
Claims (10)
1. The method for extracting the characteristics of the reduction ratio of the ship radiation noise gearbox is characterized by comprising the following steps of:
collecting ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals to obtain framing signals;
carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram, and extracting a target ship propeller shaft frequency value;
performing LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram, and extracting a target ship host ignition frequency value;
establishing a numerical relation among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio through a mechanical coupling structure model;
and calculating and extracting the characteristics of the reduction ratio of the gear box of the target ship based on the numerical relation.
2. The method of extracting features of a reduction ratio of a ship radiation noise gearbox according to claim 1, wherein acquiring the ship radiation noise signal by a passive sonar, performing frame preprocessing on the received signal to acquire a frame signal further comprises:
receiving a ship radiation noise time domain signal x (n) collected by a passive sonar system:
x(n)＝[x(1),x(2),…,x(f s ),…,x(M)]，
wherein f s The signal sampling rate is represented by M, which is the number of time domain sampling points;
carrying out framing pretreatment on a passive sonar receiving signal to obtain:
wherein L is the number of sampling points of each frame of signal, K is the number of signal frames, a signal with the duration of 5s is taken as one frame, and the duration of overlapping signals of two adjacent frames is 1s.
3. The method for extracting features of a reduction ratio of a ship radiation noise gearbox according to claim 1, wherein the step of performing deman spectrum estimation on the framing signal, synthesizing a ship radiation noise deman spectrum time-frequency diagram, and extracting a target ship propeller axis frequency value further comprises:
performing variation modal decomposition on the framing signals;
selecting the (k+1) th frame signal X in the framing signals k The empirical mode decomposition is carried out to obtain an adaptive decomposition order j for X k Carrying out j-order variational modal decomposition to obtain j natural modal components:
calculating correlation coefficient of narrowband signal, for X k The j natural modal components of (1) are subjected to narrow-band envelope correlation two by two to obtain a correlation coefficient matrix:
wherein R is j The correlation coefficient of the j-th natural mode component and other-order natural mode components;
for a pair of
Square detection and power spectrum analysis are carried out on each order of natural modes to obtain envelope spectrums corresponding to j natural mode components, and R is carried out according to narrow-band envelope correlation coefficients kj Weighted fusion is carried out to obtain DEMON spectrum P of kth frame signal k ：
Combining the DEMON spectrums of the K frame signals to obtain a DEMON spectrum time-frequency diagram P of the ship radiation noise receiving signals:
extracting fundamental frequency line spectrum frequency value f in harmonic line spectrum cluster of ship radiation noise signal DEMON spectrum time-frequency diagram z The frequency value is the propeller shaft frequency of the ship.
4. The method for extracting features of a reduction ratio of a ship radiation noise gearbox according to claim 1, wherein the step of performing a LOFAR spectrum estimation on the split frame signal, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram, and extracting a target ship host ignition frequency value further comprises:
for each frame of signal
Estimating the power spectrum density to obtain the power spectrum S of the frame signal k (f)：
Wherein f= [1/f 0 ,2/f 0 ,…,f s ]F0 is the power spectrum frequency resolution;
synthesizing each frame of signal power spectrum into a time-frequency power spectrum of ship radiation noise, wherein the process is equivalent to short-time Fourier transform, and taking a frequency band of 0-300 Hz of the time-frequency power spectrum as LOFAR spectrum S (f) of the ship radiation noise:
extracting fundamental frequency line spectrum frequency value f in ship radiation noise signal LOFAR spectrum time-frequency chart harmonic line spectrum cluster d The fundamental frequency line spectrum frequency value is the single-cylinder ignition frequency of the ship host;
and under the condition of line spectrum missing, calculating the fundamental frequency line spectrum frequency value based on the frequency difference of two adjacent higher harmonic line spectrums.
5. The method for extracting features of the reduction ratio of the ship radiation noise gearbox according to claim 1, wherein establishing the numerical relationship among the propeller shaft frequency, the main engine ignition frequency and the reduction ratio of the gearbox through the mechanical coupling structure model further comprises:
establishing single cylinder ignition frequency f of cylinder of ship host d Relation to crankshaft speed, for a diesel engine with i strokes, the crankshaft rotates i/2 cycles, f, 1 cylinder per firing d With crankshaft speed f q Satisfy the following requirements
Introducing a gear box reduction ratio sigma to establish the main shaft rotating speed f of the ship propeller z Relation f with the rotational speed of the crankshaft of the main engine q ：f q ＝σ·f z ；
Providing the mapping relation between the ship radiation noise modulation spectrum and the low-frequency line spectrum frequency, the relation between the rotating speed of the main shaft of the propeller and the single-cylinder ignition frequency of the main engine cylinder, and calculating the reduction ratio of the gearbox
6. The method for extracting the characteristics of the reduction ratio of the ship radiation noise gearbox according to claim 1, wherein calculating and extracting the characteristics of the reduction ratio of the target ship gearbox based on the numerical relationship further comprises:
inputting the extracted ship propeller shaft frequency and the single-cylinder ignition frequency of the ship host into a built ship radiation noise modulation spectrum and low-frequency line spectrum frequency mapping relation model, and calculating a gearbox reduction ratio;
and verifying stability and separability of the reduction ratio characteristic of the gear box under different navigational speeds based on the radiation noise data of the ship target under different navigational speeds.
7. The utility model provides a naval vessel radiation noise gear box reduction ratio feature extraction system which characterized in that includes:
the acquisition module is used for acquiring ship radiation noise signals through passive sonar, and carrying out framing pretreatment on the received signals to acquire framing signals;
the DEMON spectrum estimation module is used for carrying out DEMON spectrum estimation on the framing signals, synthesizing a ship radiation noise DEMON spectrum time-frequency diagram and extracting a target ship propeller shaft frequency value;
the LOFAR spectrum estimation module is used for carrying out LOFAR spectrum estimation on the framing signals, synthesizing a ship radiation noise LOFAR spectrum time-frequency diagram and extracting a target ship host ignition frequency value;
the numerical relation establishing module is used for establishing numerical relation among the propeller shaft frequency, the main engine ignition frequency and the gear box reduction ratio through the mechanical coupling structure model;
and the calculation module is used for calculating and extracting the reduction ratio characteristic of the gear box of the target ship based on the numerical relation.
8. The ship radiation noise gearbox reduction ratio feature extraction system of claim 7, further comprising a preprocessing module for receiving a ship radiation noise time domain signal x (n) collected by a passive sonar system:
x(n)＝[x(1),x(2),…,x(f s ),…,x(M)]，
wherein f s The signal sampling rate is represented by M, which is the number of time domain sampling points;
carrying out framing pretreatment on a passive sonar receiving signal to obtain:
wherein L is the number of sampling points of each frame of signal, K is the number of signal frames, a signal with the duration of 5s is taken as one frame, and the duration of overlapping signals of two adjacent frames is 1s.
9. A computer device, comprising:
a memory for storing a processing program;
a processor, which when executing the processing program, implements the ship radiation noise gearbox reduction ratio feature extraction method according to any one of claims 1 to 6.
10. A readable storage medium, wherein a processing program is stored on the readable storage medium, and when the processing program is executed by a processor, the processing program realizes the ship radiation noise gearbox reduction ratio feature extraction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310290588.8A CN116304829A (en) | 2023-03-23 | 2023-03-23 | Ship radiation noise gear box reduction ratio feature extraction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310290588.8A CN116304829A (en) | 2023-03-23 | 2023-03-23 | Ship radiation noise gear box reduction ratio feature extraction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304829A true CN116304829A (en) | 2023-06-23 |
Family
ID=86779577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310290588.8A Pending CN116304829A (en) | 2023-03-23 | 2023-03-23 | Ship radiation noise gear box reduction ratio feature extraction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304829A (en) |
-
2023
- 2023-03-23 CN CN202310290588.8A patent/CN116304829A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110595780B (en) | Bearing fault identification method based on vibration gray level image and convolution neural network | |
| CN105092241B (en) | A kind of gear local fault diagnosis method and system | |
| CN101539597B (en) | Multi-target method for distinguishing radiation noises having same frequency band | |
| CN108919116B (en) | Ocean current generator unbalanced stator current fault diagnosis method based on MCCKAF-FFT-Softmax | |
| US5566134A (en) | Digital computer algorithm for processing sonar signals | |
| CN110855374B (en) | Underwater sound target radiation noise modulation feature extraction method | |
| CN111735525B (en) | DEMON spectral feature extraction method suitable for unmanned sonar | |
| CN109632973A (en) | A kind of ultrasound echo signal extracting method based on Based on Multiscale Matching tracking | |
| CN112255607B (en) | Sea clutter suppression method | |
| CN107689059A (en) | The abnormal recognition methods of wind generating set pitch control and device | |
| Feng et al. | A fault diagnosis for rolling bearing based on multilevel denoising method and improved deep residual network | |
| CN103412298A (en) | Method capable of automatically acquiring variable speed rotation time interval of ship propeller | |
| Huang et al. | A practical fundamental frequency extraction algorithm for motion parameters estimation of moving targets | |
| Lu et al. | Fundamental frequency detection of underwater acoustic target using DEMON spectrum and CNN network | |
| CN111929666B (en) | Weak underwater sound target line spectrum autonomous extraction method based on sequential environment learning | |
| CN116304829A (en) | Ship radiation noise gear box reduction ratio feature extraction method and system | |
| CN115830368A (en) | Vehicle shock absorber defect diagnosis method, system, equipment and medium | |
| CN117388833A (en) | Ship radiation noise demodulation spectrum phase difference feature extraction method and system | |
| Lennartsson et al. | Passive sonar signature estimation using bispectral techniques | |
| Wang et al. | Research of Modulation Feature Extraction from Ship-Radiated Noise | |
| Ambat | Performance evaluation of the DEMON processor for sonar | |
| CN114638265B (en) | Milling chatter judging method based on signal convolution neural network | |
| CN113358927B (en) | Multi-component linear frequency modulation signal time-frequency analysis method based on regional kernel function | |
| CN116027407B (en) | Underwater sound signal data processing method and system | |
| CN113865867B (en) | Bearing fault diagnosis method based on singular value decomposition of amplitude characteristic |
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 |