CN118072557A - Ship collision early warning method and system for offshore wind turbine structure - Google Patents
Ship collision early warning method and system for offshore wind turbine structure Download PDFInfo
- Publication number
- CN118072557A CN118072557A CN202410197850.9A CN202410197850A CN118072557A CN 118072557 A CN118072557 A CN 118072557A CN 202410197850 A CN202410197850 A CN 202410197850A CN 118072557 A CN118072557 A CN 118072557A
- Authority
- CN
- China
- Prior art keywords
- ship
- collision
- acceleration
- historical
- signal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000001133 acceleration Effects 0.000 claims abstract description 282
- 238000012545 processing Methods 0.000 claims abstract description 108
- 238000000605 extraction Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 24
- 238000010606 normalization Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000007667 floating Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
- G08G3/02—Anti-collision systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The application discloses a ship collision early warning method and a system for an offshore wind turbine structure, which are characterized in that a ship collision database is generated based on time-frequency domain features corresponding to each ship type by carrying out feature extraction processing on a ship historical acceleration signal acquired by an acceleration sensor so as to combine the ship collision database to quickly identify and process a current acceleration signal acquired in real time, so that the reliability of the ship collision early warning can be effectively improved by utilizing historical data, and the corresponding ship type can be quickly determined according to the ship collision database, thereby improving the accuracy of the ship collision early warning.
Description
Technical Field
The application belongs to the technical field of offshore wind power construction, and particularly relates to a ship collision early warning method and system for an offshore wind turbine structure.
Background
Under the background of increasingly severe global energy crisis, the development and utilization of clean energy become the main direction of national energy structure transformation, and at present, china has abundant offshore wind energy resources, and has ideal market conditions and huge resource potential for developing wind power. With the vigorous development of the offshore wind power industry, the scale and installed capacity of the offshore wind power plant are larger and larger, and meanwhile, the operation and maintenance work of the offshore wind power plant is also attracting attention. For example, various construction ships and operation and maintenance ships frequently appear in the construction period and the operation stage of an offshore wind farm, and under severe sea conditions, the ship can collide with a booster station platform after being out of control, so that irreversible damage is generated to the booster station structure, and the operation safety of the platform is further affected.
When the offshore wind power operation and maintenance ship performs operation and maintenance work of the fan, the offshore wind power operation and maintenance ship is propped against the operation and maintenance channel of the fan, so that operation and maintenance personnel and operation and maintenance materials can be transferred onto the fan platform from the ship. In addition to operation and maintenance vessels, the types of vessels include cargo vessels, passenger vessels, fishing vessels, tugboats, scientific research vessels, rescue vessels, engineering vessels, and the like. When different types of ships are in normal operation or accidentally propped against the fan, collision is inevitably generated to the fan platform. The offshore wind turbine structure is in long-term service in a severe marine environment, repeated long-term collision is carried out, various damages are easily generated on the structure, the dynamic characteristics are changed, the bearing capacity is reduced, and even structural failure is caused when the bearing capacity is severe, so that huge economic loss and bad social influence are caused. Therefore, the influence of ship impact on the offshore wind turbine in the running process is reduced, and the problem to be solved in the current-stage offshore wind power construction and operation is solved urgently.
The current monitoring and identifying technology for collision between the offshore wind turbine structure and the ship in the operation period is generally mainly used for judging whether the ship collides with the offshore wind turbine structure, and cannot classify the collided ship, so that the accuracy and the reliability of the ship collision early warning are easily affected.
Disclosure of Invention
The application provides a ship collision early warning method and a system for an offshore wind turbine structure, which are used for solving the technical problems that the above-mentioned current monitoring and recognition technology for collision of the offshore wind turbine structure with a ship in an operation period is mainly used for judging whether the ship collides with the offshore wind turbine structure, the ship which collides with the offshore wind turbine structure cannot be classified, further the accuracy, the reliability and the like of the ship collision early warning are easily influenced, and the technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a ship collision early warning method for an offshore wind turbine structure, including:
based on the historical ship acceleration signals acquired by the at least two acceleration sensors, determining historical collision acceleration signals corresponding to at least two ship types;
Performing feature extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain features, and generating a ship collision database according to the time-frequency domain features corresponding to all the ship types;
acquiring current acceleration signals acquired by all acceleration sensors, and identifying the current acceleration signals based on a ship collision database;
and generating a ship early warning signal according to the identification result corresponding to the current acceleration signal, and sending the ship early warning signal to the user terminal.
In a second aspect, an embodiment of the present application provides a ship collision warning system for an offshore wind turbine structure, including:
the data acquisition module is used for determining historical collision acceleration signals corresponding to at least two ship types based on the ship historical acceleration signals acquired by the at least two acceleration sensors;
The database establishing module is used for carrying out characteristic extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain characteristics, and generating a ship collision database according to the time-frequency domain characteristics corresponding to all the ship types;
the collision recognition module is used for acquiring current acceleration signals acquired by all the acceleration sensors and recognizing the current acceleration signals based on a ship collision database;
And the collision early warning module is used for generating a ship early warning signal according to the identification result corresponding to the current acceleration signal and sending the ship early warning signal to the user terminal.
In a third aspect, the embodiment of the application also provides a ship collision early warning system for an offshore wind turbine structure, which comprises a processor and a memory;
The processor is connected with the memory;
A memory for storing executable program code;
The processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the ship collision early warning method for the offshore wind turbine structure provided in the first aspect or any implementation manner of the first aspect of the embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides a computer storage medium, where a computer program is stored, where the computer program includes program instructions, where the program instructions, when executed by a processor, may implement the marine vessel collision warning method for an offshore wind turbine structure provided in the first aspect or any implementation manner of the first aspect of the present application.
In the embodiment of the application, when the marine fan structure is subjected to ship collision early warning, the historical collision acceleration signals corresponding to at least two ship types can be determined based on the historical ship acceleration signals acquired by at least two acceleration sensors; performing feature extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain features, and generating a ship collision database according to the time-frequency domain features corresponding to all the ship types; acquiring current acceleration signals acquired by all acceleration sensors, and identifying the current acceleration signals based on a ship collision database; and generating a ship early warning signal according to the identification result corresponding to the current acceleration signal, and sending the ship early warning signal to the user terminal. The characteristic extraction processing is carried out on the ship historical acceleration signals acquired by the acceleration sensor, and the ship collision database is generated based on the time-frequency domain characteristics corresponding to each ship type, so that the current acceleration signals acquired in real time are rapidly identified and processed by combining the ship collision database, the reliability of the ship collision early warning can be effectively improved by utilizing the historical data, and the corresponding ship type can be rapidly determined according to the ship collision database, so that the accuracy of the ship collision early warning is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a general flow chart of a ship collision early warning method for an offshore wind turbine structure according to an embodiment of the present application;
FIG. 2 is a schematic diagram showing the effect of an offshore wind turbine structure according to an embodiment of the present application;
FIG. 3 is a signal effect diagram for calculating approximate entropy according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of a ship collision early warning system for an offshore wind turbine structure according to an embodiment of the present application;
Fig. 5 is a schematic structural diagram of another marine vessel collision warning system for an offshore wind turbine structure according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.
The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements described without departing from the scope of the application. Various examples may omit, replace, or add various procedures or components as appropriate. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.
Referring to fig. 1, fig. 1 shows an overall flowchart of a ship collision early warning method for an offshore wind turbine structure according to an embodiment of the present application.
As shown in fig. 1, the ship collision early warning method for the offshore wind turbine structure at least comprises the following steps:
step 102, determining historical collision acceleration signals corresponding to at least two ship types based on the ship historical acceleration signals acquired by at least two acceleration sensors.
In the embodiment of the application, the ship collision early warning method for the offshore wind turbine structure can be applied to a control terminal (of course, the control terminal can also be a server corresponding to the offshore wind turbine structure), the control terminal can acquire the acceleration signal of the offshore wind turbine structure acquired by the acceleration sensor arranged on the offshore wind turbine structure through a gateway, and the analysis and the processing are carried out on the acceleration signal of the offshore wind turbine structure so as to quickly and effectively perform the ship collision early warning. The acceleration signal of the offshore wind turbine structure can be specifically divided into an acceleration signal that does not collide with the ship and an acceleration signal that collides with the ship, and there is a significant difference between the acceleration signal that collides with the ship and the acceleration signal that does not collide with the ship, for example, but not limited to, there is a significant difference in the amplitude, the floating waveform, the frequency, or the phase, etc. parameters corresponding to the acceleration signal.
Here, the number of the acceleration sensors may be, but not limited to, four, and four directions of north and south, which are respectively disposed on the flange platform of the offshore wind turbine structure, and the sampling frequency of each acceleration sensor may be set to 200 numbers per second, so that the acceleration signals of the offshore wind turbine structure may be more reliably obtained from different angles, and the acceleration signals of the offshore wind turbine structure may be sent to the control terminal by the plurality of gateways. For example, but not limited to, an effect schematic diagram of an offshore wind turbine structure provided by the embodiment of the application can be shown with reference to fig. 2, and as shown in fig. 2, acceleration sensors are respectively arranged in four directions of east, west and south on a flange platform of the offshore wind turbine structure so as to judge whether to perform ship collision early warning according to the obtained offshore wind turbine result acceleration signals in the four directions of east, west and south, and the azimuth of a ship can be quickly locked when the ship collision early warning signal is generated, so that the ship collision early warning signal can be processed and protected more specifically.
It can be understood that the control terminal performs feature extraction processing on the ship historical acceleration signals acquired by the acceleration sensor, and generates a ship collision database based on the time-frequency domain features corresponding to each ship type, so that the current acceleration signals acquired in real time are quickly identified and processed by combining the ship collision database, the reliability of ship collision early warning can be effectively improved by utilizing the historical data, and the corresponding ship type can be quickly determined according to the ship collision database, so that the accuracy of the ship collision early warning is improved.
Specifically, when performing the ship collision early warning on the offshore wind turbine structure, the control terminal may, but is not limited to, classify all the ship historical acceleration signals collected by at least two sensors disposed on the flange platform of the offshore wind turbine structure (i.e., all the offshore wind turbine structure acceleration signals corresponding to the collision of different ship types with the offshore wind turbine structure) according to the ship types to obtain all the historical acceleration signals corresponding to each ship type, where the historical acceleration signals may include the historical period acceleration signals corresponding to the non-collision of the offshore wind turbine structure with each ship type and the historical period acceleration signals corresponding to the collision of the offshore wind turbine structure with the corresponding ship type, and may screen out the historical acceleration signals corresponding to the collision of the ship (i.e., the historical collision acceleration signals) from all the historical acceleration signals corresponding to each ship type. Here, the manner of performing the screening process on all the historical acceleration signals corresponding to each ship type may be, but not limited to, performing the process according to the amplitude, the floating waveform, the frequency or the phase parameter corresponding to each historical acceleration signal, and is not limited thereto.
Of course, in the embodiment of the present application, it is also possible, but not limited to, to screen out the historical acceleration signals corresponding to the occurrence of no ship collision from all the historical acceleration signals corresponding to each type of ship, and determine whether the ship collision occurs currently according to the historical acceleration signals corresponding to the occurrence of no ship collision.
As an alternative of the embodiment of the present application, determining a historical crash acceleration signal corresponding to at least two ship types based on the historical acceleration signals of the ship collected by at least two acceleration sensors includes:
Dividing historical acceleration signals corresponding to each ship type from the historical acceleration signals of the ships collected by the at least two acceleration sensors; the historical acceleration signals comprise at least two historical period acceleration signals acquired by at least two acceleration sensors;
Filtering all historical period acceleration signals corresponding to each ship type based on preset offshore wind turbine acceleration signals to obtain a historical period acceleration signal set corresponding to each ship type;
and filtering the historical time period acceleration signal set corresponding to each ship type based on the preset time-frequency domain parameters to obtain historical collision acceleration signals corresponding to each ship type.
When the offshore wind turbine structure is in normal operation and is not collided with any ship type, the ship historical acceleration signals acquired by the corresponding acceleration sensors show a relatively stable characteristic from the time domain, namely no obvious abrupt change or fluctuation exists, and the average value of the acceleration is close to zero; there will be only some fixed frequency components from the frequency domain, such as but not limited to including the rotational frequency or the fundamental frequency of the blade, etc., due to the absence of energy input. Based on the method, the rapid filtering processing of the historical collision acceleration signals can be realized through the time domain angle and the frequency domain angle, so that the overall data processing efficiency is improved.
Specifically, in determining the historical crash acceleration signal corresponding to each ship type, the control terminal may, but is not limited to, after dividing the historical acceleration signal corresponding to each ship type (i.e., all the historical period acceleration signals), perform a filtering process on all the historical period acceleration signals corresponding to each ship type based on a preset offshore wind turbine acceleration signal to filter out all the historical period acceleration signals that are identical or approximately identical to the preset offshore wind turbine acceleration signal. Here, the preset acceleration signal of the offshore wind turbine may be understood as an acceleration signal corresponding to the result of the offshore wind turbine that no ship collision occurs, the acceleration signal has no obvious abrupt change or fluctuation, and the average value of the acceleration is close to zero.
Then, the control terminal may further, but not limited to, perform filtering processing again on all remaining historical period acceleration signals corresponding to each ship type based on the preset time-frequency domain parameter, so as to take all the historical period acceleration signals meeting the preset time-frequency domain parameter as final historical collision acceleration signals. Here, the preset time-frequency domain parameters may include, but are not limited to, vibration amplitude corresponding to a time domain, a floating waveform, and frequency and phase corresponding to a frequency domain.
It can be understood that when the remaining acceleration signals of all the historical periods corresponding to each ship type are filtered based on the preset time-frequency domain parameters, the acceleration vibration amplitude generated when the offshore wind turbine structure collides with the ship is larger, so that all the historical period acceleration signals with the acceleration amplitude not exceeding the preset vibration amplitude can be filtered, and all the historical period acceleration signals with the acceleration amplitude in accordance with the ship collision can be reserved. Then, due to the large impact force and vibration generated when the offshore wind turbine structure collides with the ship, the acceleration signal can also display waveform characteristics with quicker change, such as sharper peak values, so that all the historical period acceleration signals with completely inconsistent acceleration waveform curves (or lower similarity) with the preset waveform curves can be filtered, and the acceleration waveform curves are kept to be consistent with all the historical period acceleration signals of the ship collision.
Then, since the specific frequency component may be increased or reduced when the offshore wind turbine structure collides with the ship, for example, the specific frequency harmonic wave or resonance may be further, but not limited to, performing fourier transform processing on all remaining acceleration signals in the historical period, so as to convert each remaining acceleration signal in the historical period into a corresponding frequency domain signal, performing filtering processing on all frequency domain signals completely inconsistent with the preset frequency harmonic wave, so as to keep all frequency domain signals with the frequency harmonic wave consistent with the ship collision, and performing inverse fourier transform processing on all frequency domain signals to obtain corresponding acceleration signals in the historical period. Then, since the phase difference may be caused when the offshore wind turbine structure collides with the ship, the filtering process may be performed on the part of the frequency domain signals which are inconsistent with the preset phase in all the above-mentioned frequency domain signals, so as to keep all the frequency domain signals with the phase consistent with the ship collision, and the inverse fourier transform process may be performed on all the frequency domain signals, so as to obtain the corresponding acceleration signals of the historical period.
And 104, performing feature extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain features, and generating a ship collision database according to the time-frequency domain features corresponding to all the ship types.
Specifically, after determining the historical collision acceleration signal corresponding to each ship type, the control terminal may perform feature extraction processing on the historical collision acceleration signal, so as to generate a ship collision database according to the time-frequency domain features corresponding to each ship type, where the ship collision database may include, in addition to the time-frequency domain features corresponding to each ship type, a time and a direction corresponding to each ship type when a collision occurs, so that the content of the ship early warning signal generated later is richer.
The method of performing feature extraction processing on the historical collision acceleration signal may be divided into time domain feature extraction processing, frequency domain feature extraction processing or time domain feature extraction processing and frequency domain feature extraction processing, where the time domain feature extraction processing may be used to extract a time domain feature such as a mean value, a maximum value, a variance, a kurtosis or an approximate entropy in the historical collision acceleration signal, and the frequency domain feature extraction processing may be used to extract a frequency domain feature such as a frequency of each order or a corresponding energy in the frequency domain signal corresponding to the historical collision acceleration signal, and the more the extracted feature types, the accuracy of determining whether the ship pre-warning signal is performed later may be effectively improved.
As still another alternative of the embodiment of the present application, feature extraction processing is performed on the historical crash acceleration signal corresponding to each ship type, to obtain a corresponding time-frequency domain feature, including:
carrying out mean value calculation processing on the historical collision acceleration signals corresponding to each ship type, and obtaining corresponding variance and kurtosis according to a mean value calculation result;
Dividing historical collision acceleration signals corresponding to each ship type into at least two moment collision acceleration signals, and determining the number of the similar moment collision acceleration signals corresponding to each moment collision acceleration signal based on a preset similar tolerance threshold;
and calculating corresponding approximate entropy according to the number of the similar moment collision acceleration signals corresponding to all moment collision acceleration signals, and taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics.
Specifically, when the characteristic extraction processing is performed on the historical collision acceleration signals corresponding to each ship type, the control terminal can perform the mean value calculation processing on the historical collision acceleration signals so as to perform the mean value calculation on the acceleration values corresponding to all the moments, and a corresponding mean value calculation result is obtained.
Next, after obtaining the mean value calculation result corresponding to the historical crash acceleration signal, the corresponding variance may be calculated by, but not limited to:
In the above formula, S may correspond to the variance, n may correspond to the number of accelerations in the historical crash acceleration signal, x i corresponds to the ith acceleration in the historical crash acceleration signal, The result of the average calculation of the historical crash acceleration signal can be correspondingly obtained.
Then, after obtaining the average value calculation result corresponding to the historical crash acceleration signal, the corresponding kurtosis may also be calculated by, but not limited to:
In the above formula, K 4 may correspond to kurtosis, n may correspond to the number of accelerations in the historical crash acceleration signal, x i corresponds to the ith acceleration in the historical crash acceleration signal, The result of the average calculation of the historical crash acceleration signal can be correspondingly obtained. The kurtosis is here understood as the fourth order central moment of a random variable divided by the fourth power of the standard deviation as a dimensionless factor to verify the extent to which the signal deviates from a normal distribution.
Next, the control terminal may divide the historical crash acceleration signal corresponding to each vessel type into at least two time crash acceleration signals, such as, but not limited to, dividing the historical crash acceleration signal into x (1), x (2), x (N), x (1) representing the acceleration value at the first time, x (2) representing the acceleration value at the second time, and may construct a set of m-dimensional vectors by, but not limited to:
X(i)＝[x(i)，x(i+1)，...，x(i+m-1)]
in the above formula, i=1 to n—m+1, and m is generally 2, and the following can be obtained:
X(i)＝[x(i)，x(i+1)]
Next, a corresponding similar tolerance interval may be determined based on each of the above-mentioned vectors and a preset similar tolerance threshold, for example, but not limited to, taking X (i) as an example, a similar tolerance interval corresponding to X (i) and the preset similar tolerance threshold, and a similar tolerance interval corresponding to X (i+1) and the preset similar tolerance threshold may be determined, and the two similar tolerance intervals may be taken as the similar tolerance interval of X (i), and all the remaining vectors may be traversed to count the number of similar vectors (i.e. the number of similar time collision acceleration signals) in the similar tolerance interval.
Referring now to fig. 3, a signal effect diagram for calculating approximate entropy according to an embodiment of the present application may be shown, where, as shown in fig. 3, the signal effect diagram may be an acceleration vector-time graph generated based on all time crash acceleration signals, an ordinate may be a crash acceleration value corresponding to each time, and an abscissa may be corresponding to each time. The solid lines in the figure may be denoted as X (i) and X (j), respectively, when determining whether X (j) is within the similar tolerance interval of X (i), determining a similar tolerance interval a according to X (i) and a preset similar tolerance threshold r, and determining a similar tolerance interval B according to X (i+1) and a preset similar tolerance threshold r, and taking the similar tolerance intervals a and B as the similar tolerance interval of X (i), so as to determine whether X (j) is within the similar tolerance interval of X (i) by detecting whether X (j) and X (j+1) are both within the similar tolerance interval of X (i).
Then, after the number of similar vectors corresponding to each vector is counted, that is, the number of similar time collision acceleration signals corresponding to each time collision acceleration signal, the number of similar vectors corresponding to all vectors can be summed and calculated, and the ratio calculation process is performed on the sum of the sum calculation result and the vector combination sum corresponding to all vectors, so as to obtain a similar ratio. Here, the vector combination sum corresponding to all vectors is understood as the vector combination total number of all vectors and any one of the remaining vectors.
Then, after obtaining the similar ratio, the corresponding approximate entropy can be calculated by, but not limited to, the following formula:
In the above-mentioned method, the step of, Can be correspondingly approximate entropy,/>The calculation mode of phi m+1 (r) can be understood as replacing m in phi m (r) with m+1.
The variance, kurtosis, and approximate entropy calculated as described above for each vessel type may then be used as the corresponding time-frequency domain features.
As a further alternative of the embodiment of the present application, before taking the variance, kurtosis, and approximate entropy corresponding to each ship type as the respective time-frequency domain features, further comprising:
carrying out Fourier transform processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding first processing signals;
Filtering each first processing signal, and performing inverse Fourier transform processing on each first processing signal after the filtering processing to obtain a corresponding second processing signal;
Carrying out feature root solving processing on a symmetric matrix constructed based on each second processing signal, and calculating frequency parameters and energy parameters according to the corresponding feature roots;
Taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics, wherein the time-frequency domain characteristics comprise:
And taking the variance, kurtosis, approximate entropy and frequency parameters and energy parameters corresponding to each ship type as corresponding time-frequency domain characteristics.
Besides the above embodiment, the calculated time domain characteristic parameter is used as the time-frequency domain characteristic corresponding to each ship type, the frequency domain characteristic parameter corresponding to each ship type can be obtained through a signal decomposition processing mode and the like, and the time domain characteristic parameter and the frequency domain characteristic parameter are used as the time-frequency domain characteristic together, so that the accuracy and the reliability of the subsequent collision early warning are further improved.
Specifically, when the characteristic extraction processing is performed on the historical crash acceleration signal corresponding to each ship type, the control terminal may further perform fourier transform processing on the historical crash acceleration signal corresponding to each ship type to convert the historical crash acceleration signal into a frequency domain signal, then perform filtering processing on the redundant signal in the historical crash acceleration signal by performing filtering processing on the frequency domain signal, and may further perform inverse fourier transform processing on each processed frequency domain signal to restore a time domain signal (i.e., a second processing signal) that is more convenient to analyze.
Then, after obtaining the second processing signals corresponding to each ship type, a corresponding symmetric matrix (also known as a Hankel matrix) may be constructed according to each second processing signal, and the state matrix of the state space model may be solved through the symmetric matrix. The state matrix may then be feature root solved to calculate the frequency and attenuation factors of the respective complex exponential components in the corresponding second processed signal from the obtained feature root. Here, each complex exponential component in the second processed signal may be, but is not limited to, obtained by performing signal decomposition processing on the second processed signal, and is not limited to this. Then, based on the preset linear equation set and the frequency and attenuation factors of each complex exponential component, the amplitude and phase angle of each complex exponential component can be obtained, and the corresponding second processing signal is decomposed and reconstructed by using the preset order and the amplitude and phase angle of each complex exponential component, so as to calculate the corresponding frequency parameter and energy parameter. It is understood that the frequency parameter may be, but is not limited to, a frequency of each order corresponding to the second processed signal, and the energy parameter may be, but is not limited to, an energy of each order corresponding to the second processed signal.
Of course, in the embodiment of the present application, the time domain signal after the filtering processing may be processed by other signal decomposition processing methods to obtain the corresponding frequency domain characteristic parameter, which is not limited thereto.
Then, after obtaining the frequency parameter and the energy parameter corresponding to each ship type, the variance, kurtosis, approximate entropy, and the frequency parameter and the energy parameter corresponding to each ship type can be used as the corresponding time-frequency domain characteristics.
Further, after obtaining the time-frequency domain features corresponding to each ship type, the control terminal may perform, but not limited to, an integration process on the time-frequency domain features corresponding to each ship type, for example, through a normalization process or the like, so as to ensure consistency of all the time-frequency domain features, and may generate a ship collision database for identifying the current acceleration signal acquired by the acceleration sensor according to all the ship types and the corresponding processed features.
It can be understood that in the embodiment of the present application, a ship non-collision database may also be generated, so that the current acceleration signal acquired by the acceleration sensor is identified by using the ship non-collision database, and the generation manner of the ship non-collision database may refer to one or more embodiments mentioned above, which are not described herein in detail.
As still another alternative of the embodiment of the present application, generating a ship collision database according to the time-frequency domain features corresponding to all the ship types includes:
performing splicing processing on variances, kurtosis, approximate entropy, frequency parameters and energy parameters corresponding to each ship type, and performing normalization processing on corresponding splicing results;
And carrying out hash operation processing on the normalization result corresponding to each ship type to obtain corresponding collision signal identifiers, and generating a ship collision database according to all the ship types and the collision signal identifiers corresponding to each ship type.
Specifically, when the time-frequency domain feature corresponding to each ship type includes multiple types of feature parameters, the method may, but is not limited to, perform a splicing process on all types of feature parameters, for example, may sequentially perform a splicing process on variance, kurtosis, approximate entropy, frequency parameters and energy parameters corresponding to each ship type, so as to obtain a splicing result which may be represented as a vector or a character string, and perform a normalization process on each splicing result, thereby achieving consistency of time domain features and frequency domain features.
Then, in order to make the data corresponding to each ship type have uniqueness, hash operation processing may be performed on each normalization result by using a hash algorithm, so as to obtain corresponding collision signal identifiers, and the lengths of the collision signal identifiers corresponding to each ship type may be kept consistent, and a ship collision database may be generated according to all the ship types and the collision signal identifiers corresponding to each ship type.
In the embodiment of the present application, the ship collision database may also include, but is not limited to, a collision time and a collision direction corresponding to each ship type, where the collision time and the collision direction may be obtained by analyzing the ship historical acceleration signals collected by all the acceleration sensors, and is not limited thereto.
And 106, acquiring current acceleration signals acquired by all acceleration sensors, and identifying and processing the current acceleration signals based on a ship collision database.
Specifically, after the ship collision database is generated, the control terminal may, but is not limited to, acquire current acceleration signals acquired by all the acceleration sensors at preset time intervals, and extract corresponding time-frequency domain features from the current acceleration signals, so as to query whether similar collision signal identifiers exist in the ship collision database according to the time-frequency domain features. Here, when whether similar collision signal identifiers exist in the ship collision database is queried, referring to one or more embodiments mentioned above, the time-frequency domain features extracted from the current acceleration signal are processed to obtain corresponding current signal identifiers, and similarity results between the current signal identifiers and each collision signal identifier in the ship collision database are calculated by respectively performing similarity calculation processing on the current signal identifiers and each collision signal identifier in the ship collision database, so that whether the ship collision warning is needed or not can be judged according to all the similarity results.
It can be understood that when the similarity result between the current signal identifier and any one of the collision signal identifiers in the ship collision database exceeds the preset threshold, the current offshore wind turbine structure is indicated to have a ship collision risk, and the corresponding ship type is consistent with the ship type corresponding to the collision signal identifier in the ship collision database, so that the ship type corresponding to the collision signal identifier and the collision early warning level can be used as the identification result. The collision early-warning level may be, but not limited to, determined according to a similarity interval in which the similarity result is located, for example, when the similarity result is located in a first similarity interval, the corresponding collision early-warning level may be low; when the similarity result is in the second similarity interval, the corresponding collision early warning level can be a middle level; when the similarity result is in the third similarity interval, the corresponding collision warning level may be high, and the first similarity interval is lower than the second similarity interval, and the second similarity interval is lower than the third similarity interval.
It can be further understood that when it is detected that the similarity result between the current signal identifier and any one of the collision signal identifiers in the ship collision database does not exceed the preset threshold, only it can be indicated that no collision risk exists between the current offshore wind turbine structure and any one of the ship types in the ship collision database, but it cannot be ensured whether collision risk exists between other ship types and the offshore wind turbine structure, so that an identification result indicating that the ship type cannot be identified is generated, and a ship image corresponding to the direction in which each acceleration sensor is located can be obtained through a photographing device arranged on the offshore wind turbine structure, so that whether other ship types exist can be determined through an image identification mode.
When other ship types exist in all the ship images, specific ship names can be determined in a manual identification or automatic intelligent identification mode, and whether the ship types collide with the offshore wind turbine structure or not can be judged by an AIS system arranged on the offshore wind turbine structure. When the ship type collides with the offshore wind turbine structure, the control terminal can process the corresponding current acceleration signal to generate a corresponding current signal identifier, and update the ship type name and the corresponding current signal identifier in the ship collision database so as to improve the accuracy of judging whether to send out the ship collision early warning next time.
When other ship types are not recognized from all the ship images, the fact that no ship type exists near the current offshore wind turbine structure is indicated, and acceleration signals acquired by all the acceleration sensors can be continuously acquired according to preset time intervals, so that ship collision is monitored and early warned in real time.
In the embodiment of the present application, the manner of similarity calculation may include, but is not limited to, cosine similarity calculation or euclidean distance calculation, where the corresponding preset threshold value is different for each processing manner, and is not limited thereto.
And step 108, generating a ship early warning signal according to the identification result corresponding to the current acceleration signal, and sending the ship early warning signal to the user terminal.
Specifically, when the type of the ship and the collision pre-warning level are detected in the generated recognition result, it is indicated that the collision pre-warning of the ship needs to be performed in time, so that corresponding ship pre-warning signals can be generated according to the type of the ship and the collision pre-warning level, and different collision pre-warning levels can correspond to different ship pre-warning signal prompt identifications, for example, but not limited to, when the collision pre-warning level is low, the corresponding ship pre-warning signal identifications can be green; when the collision early-warning level is a middle level, the corresponding ship early-warning signal mark can be yellow; when the collision early warning level is high, the corresponding ship early warning signal can be red, and the ship early warning signal can be timely sent to the offshore wind turbine structure so as to remind the offshore wind turbine structure of timely early warning measures, so that larger loss caused by ship collision is prevented as much as possible.
Further, after the ship early warning signal is generated, the control terminal can also feed back the ship early warning signal to the user terminal, so that relevant preventive measures can be made by relevant users aiming at the ship type and the collision early warning level, and the marine fan structure is prevented from being collided with the ship.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a ship collision warning system for an offshore wind turbine structure according to an embodiment of the present application.
As shown in fig. 4, the ship collision pre-warning system for an offshore wind turbine structure at least comprises a data acquisition module 401, a database building module 402, a collision recognition module 403 and a collision pre-warning module 404, wherein:
the data acquisition module 401 is configured to determine historical collision acceleration signals corresponding to at least two ship types based on the historical acceleration signals of the ship acquired by the at least two acceleration sensors;
The database establishing module 402 is configured to perform feature extraction processing on the historical collision acceleration signal corresponding to each ship type, obtain corresponding time-frequency domain features, and generate a ship collision database according to the time-frequency domain features corresponding to all the ship types;
the collision recognition module 403 is configured to acquire current acceleration signals acquired by all acceleration sensors, and perform recognition processing on the current acceleration signals based on a ship collision database;
and the collision early-warning module 404 is configured to generate a ship early-warning signal according to the recognition result corresponding to the current acceleration signal, and send the ship early-warning signal to the user terminal.
In some possible embodiments, determining historical crash acceleration signals corresponding to at least two vessel types based on the vessel historical acceleration signals acquired by the at least two acceleration sensors includes:
Dividing historical acceleration signals corresponding to each ship type from the historical acceleration signals of the ships collected by the at least two acceleration sensors; the historical acceleration signals comprise at least two historical period acceleration signals acquired by at least two acceleration sensors;
Filtering all historical period acceleration signals corresponding to each ship type based on preset offshore wind turbine acceleration signals to obtain a historical period acceleration signal set corresponding to each ship type;
and filtering the historical time period acceleration signal set corresponding to each ship type based on the preset time-frequency domain parameters to obtain historical collision acceleration signals corresponding to each ship type.
In some possible embodiments, the feature extraction processing is performed on the historical collision acceleration signal corresponding to each ship type to obtain corresponding time-frequency domain features, including:
carrying out mean value calculation processing on the historical collision acceleration signals corresponding to each ship type, and obtaining corresponding variance and kurtosis according to a mean value calculation result;
Dividing historical collision acceleration signals corresponding to each ship type into at least two moment collision acceleration signals, and determining the number of the similar moment collision acceleration signals corresponding to each moment collision acceleration signal based on a preset similar tolerance threshold;
and calculating corresponding approximate entropy according to the number of the similar moment collision acceleration signals corresponding to all moment collision acceleration signals, and taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics.
In some possible embodiments, before taking the variance, kurtosis, and approximate entropy corresponding to each vessel type as the respective time-frequency domain features, further comprising:
carrying out Fourier transform processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding first processing signals;
Filtering each first processing signal, and performing inverse Fourier transform processing on each first processing signal after the filtering processing to obtain a corresponding second processing signal;
Carrying out feature root solving processing on a symmetric matrix constructed based on each second processing signal, and calculating frequency parameters and energy parameters according to the corresponding feature roots;
Taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics, wherein the time-frequency domain characteristics comprise:
And taking the variance, kurtosis, approximate entropy and frequency parameters and energy parameters corresponding to each ship type as corresponding time-frequency domain characteristics.
In some possible embodiments, generating a ship collision database according to the time-frequency domain features corresponding to all ship types includes:
performing splicing processing on variances, kurtosis, approximate entropy, frequency parameters and energy parameters corresponding to each ship type, and performing normalization processing on corresponding splicing results;
and carrying out hash operation processing on the normalization result corresponding to each ship type to obtain corresponding collision signal identifiers, and generating a ship collision database according to all the ship types and the collision signal identifiers corresponding to each ship type.
In some possible embodiments, the identifying the current acceleration signal based on the vessel collision database includes:
performing feature extraction processing on the current acceleration signal, and obtaining a current signal identifier according to the corresponding time-frequency domain feature;
respectively carrying out similarity calculation processing on the current signal identification and each collision signal identification in the ship collision database to obtain a corresponding similarity result;
And when any similarity result is detected to exceed a preset threshold value, taking the ship type and the collision early warning level corresponding to the similarity result as the recognition result.
In some possible embodiments, after performing similarity calculation processing on the current signal identifier and each collision signal identifier in the ship collision database respectively, obtaining a corresponding similarity result, the method further includes:
when any similarity result is detected not to exceed a preset threshold value, at least two ship images corresponding to the current acceleration signal are obtained;
And identifying the corresponding ship type from all the ship images, and updating the ship type and the current signal identification into a ship collision database when the ship type is determined to collide with the offshore wind turbine structure.
It will be clear to those skilled in the art that the technical solutions of the embodiments of the present application may be implemented by means of software and/or hardware. "unit" and "module" in this specification refer to software and/or hardware capable of performing a particular function, either alone or in combination with other components, such as Field-Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA), integrated circuits (INTEGRATED CIRCUIT, ICs), and the like.
Referring to fig. 5, fig. 5 shows a schematic structural diagram of another marine vessel collision warning system for an offshore wind turbine structure according to an embodiment of the application.
As shown in fig. 5, the marine vessel collision warning system 500 for an offshore wind turbine structure may include at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.
Wherein the communication bus 502 may be used to enable connectivity communication of the various components described above.
The user interface 503 may include keys, and the optional user interface may also include a standard wired interface, a wireless interface, among others.
The network interface 504 may include, but is not limited to, a bluetooth module, an NFC module, a Wi-Fi module, and the like.
Wherein the processor 501 may include one or more processing cores. The processor 501 utilizes various interfaces and wiring to connect various portions within the marine vessel collision warning system 500 for the offshore wind turbine structure to perform various functions and process data for routing the marine vessel collision warning system 500 for the offshore wind turbine structure by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 505 and invoking data stored in the memory 505. Alternatively, the processor 501 may be implemented in at least one hardware form of DSP, FPGA, PLA. The processor 501 may integrate one or a combination of several of a CPU, GPU, modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 501 and may be implemented by a single chip.
The memory 505 may include RAM or ROM. Optionally, the memory 505 comprises a non-transitory computer readable medium. Memory 505 may be used to store instructions, programs, code sets, or instruction sets. The memory 505 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described various method embodiments, etc.; the storage data area may store data or the like referred to in the above respective method embodiments. The memory 505 may also optionally be at least one storage device located remotely from the processor 501. As shown in fig. 5, an operating system, a network communication module, a user interface module, and a ship collision warning application for an offshore wind turbine structure may be included in the memory 505 as one type of computer storage medium.
In particular, the processor 501 may be configured to invoke a marine vessel collision warning application for offshore wind turbine structures stored in the memory 505 and to specifically perform the following operations:
based on the historical ship acceleration signals acquired by the at least two acceleration sensors, determining historical collision acceleration signals corresponding to at least two ship types;
Performing feature extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain features, and generating a ship collision database according to the time-frequency domain features corresponding to all the ship types;
acquiring current acceleration signals acquired by all acceleration sensors, and identifying the current acceleration signals based on a ship collision database;
and generating a ship early warning signal according to the identification result corresponding to the current acceleration signal, and sending the ship early warning signal to the user terminal.
In some possible embodiments, determining historical crash acceleration signals corresponding to at least two vessel types based on the vessel historical acceleration signals acquired by the at least two acceleration sensors includes:
Dividing historical acceleration signals corresponding to each ship type from the historical acceleration signals of the ships collected by the at least two acceleration sensors; the historical acceleration signals comprise at least two historical period acceleration signals acquired by at least two acceleration sensors;
Filtering all historical period acceleration signals corresponding to each ship type based on preset offshore wind turbine acceleration signals to obtain a historical period acceleration signal set corresponding to each ship type;
and filtering the historical time period acceleration signal set corresponding to each ship type based on the preset time-frequency domain parameters to obtain historical collision acceleration signals corresponding to each ship type.
In some possible embodiments, the feature extraction processing is performed on the historical collision acceleration signal corresponding to each ship type to obtain corresponding time-frequency domain features, including:
carrying out mean value calculation processing on the historical collision acceleration signals corresponding to each ship type, and obtaining corresponding variance and kurtosis according to a mean value calculation result;
Dividing historical collision acceleration signals corresponding to each ship type into at least two moment collision acceleration signals, and determining the number of the similar moment collision acceleration signals corresponding to each moment collision acceleration signal based on a preset similar tolerance threshold;
and calculating corresponding approximate entropy according to the number of the similar moment collision acceleration signals corresponding to all moment collision acceleration signals, and taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics.
In some possible embodiments, before taking the variance, kurtosis, and approximate entropy corresponding to each vessel type as the respective time-frequency domain features, further comprising:
carrying out Fourier transform processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding first processing signals;
Filtering each first processing signal, and performing inverse Fourier transform processing on each first processing signal after the filtering processing to obtain a corresponding second processing signal;
Carrying out feature root solving processing on a symmetric matrix constructed based on each second processing signal, and calculating frequency parameters and energy parameters according to the corresponding feature roots;
Taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics, wherein the time-frequency domain characteristics comprise:
And taking the variance, kurtosis, approximate entropy and frequency parameters and energy parameters corresponding to each ship type as corresponding time-frequency domain characteristics.
In some possible embodiments, generating a ship collision database according to the time-frequency domain features corresponding to all ship types includes:
performing splicing processing on variances, kurtosis, approximate entropy, frequency parameters and energy parameters corresponding to each ship type, and performing normalization processing on corresponding splicing results;
and carrying out hash operation processing on the normalization result corresponding to each ship type to obtain corresponding collision signal identifiers, and generating a ship collision database according to all the ship types and the collision signal identifiers corresponding to each ship type.
Claims (10)
1. The marine collision early warning method for the offshore wind turbine structure is characterized by comprising the following steps of:
based on the historical ship acceleration signals acquired by the at least two acceleration sensors, determining historical collision acceleration signals corresponding to at least two ship types;
Performing feature extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain features, and generating a ship collision database according to the time-frequency domain features corresponding to all the ship types;
Acquiring current acceleration signals acquired by all the acceleration sensors, and identifying the current acceleration signals based on the ship collision database;
And generating a ship early warning signal according to the identification result corresponding to the current acceleration signal, and sending the ship early warning signal to a user terminal.
2. The method of claim 1, wherein determining historical crash acceleration signals corresponding to at least two vessel types based on the vessel historical acceleration signals acquired by the at least two acceleration sensors comprises:
Dividing historical acceleration signals corresponding to each ship type from the historical acceleration signals of the ships collected by the at least two acceleration sensors; wherein the historical acceleration signals comprise at least two historical period acceleration signals acquired by at least two acceleration sensors;
Filtering all the historical period acceleration signals corresponding to each ship type based on preset offshore wind turbine acceleration signals to obtain a historical period acceleration signal set corresponding to each ship type;
And filtering the historical time period acceleration signal set corresponding to each ship type based on a preset time-frequency domain parameter to obtain historical collision acceleration signals corresponding to each ship type.
3. The method of claim 1, wherein the performing feature extraction processing on the historical crash acceleration signal corresponding to each ship type to obtain a corresponding time-frequency domain feature comprises:
Carrying out mean value calculation processing on the historical collision acceleration signals corresponding to each ship type, and obtaining corresponding variance and kurtosis according to the mean value calculation result;
Dividing historical collision acceleration signals corresponding to each ship type into at least two moment collision acceleration signals, and determining the number of the similar moment collision acceleration signals corresponding to each moment collision acceleration signal based on a preset similar tolerance threshold;
And calculating corresponding approximate entropy according to the number of similar moment collision acceleration signals corresponding to all the moment collision acceleration signals, and taking the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics.
4. A method according to claim 3, further comprising, prior to said characterizing as respective time-frequency domain the variance, kurtosis and approximate entropy corresponding to each of said vessel types:
Performing Fourier transform processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding first processing signals;
Performing filtering processing on each first processing signal, and performing inverse Fourier transform processing on each first processing signal after the filtering processing to obtain a corresponding second processing signal;
carrying out feature root solving processing on a symmetric matrix constructed based on each second processing signal, and calculating frequency parameters and energy parameters according to the corresponding feature roots;
The method takes the variance, kurtosis and approximate entropy corresponding to each ship type as corresponding time-frequency domain characteristics, and comprises the following steps:
And taking the variance, kurtosis, approximate entropy, frequency parameters and energy parameters corresponding to each ship type as corresponding time-frequency domain characteristics.
5. The method of claim 4, wherein generating a ship collision database from the time-frequency domain features corresponding to all of the ship types comprises:
performing splicing processing on variances, kurtosis, approximate entropy, frequency parameters and energy parameters corresponding to each ship type, and performing normalization processing on corresponding splicing results;
And carrying out hash operation processing on the normalization result corresponding to each ship type to obtain corresponding collision signal identifiers, and generating a ship collision database according to all the ship types and the collision signal identifiers corresponding to each ship type.
6. The method of claim 1, wherein the identifying the current acceleration signal based on the vessel collision database comprises:
Performing feature extraction processing on the current acceleration signal, and obtaining a current signal identifier according to the corresponding time-frequency domain feature;
Performing similarity calculation processing on the current signal identifier and each collision signal identifier in the ship collision database respectively to obtain a corresponding similarity result;
And when any similarity result is detected to exceed a preset threshold value, taking the ship type and the collision early warning level corresponding to the similarity result as recognition results.
7. The method of claim 6, further comprising, after performing a similarity calculation process on each of the current signal identifier and each of the collision signal identifiers in the ship collision database, respectively, obtaining a corresponding similarity result:
When any similarity result is detected not to exceed the preset threshold value, at least two ship images corresponding to the current acceleration signal are obtained;
And identifying the corresponding ship type from all the ship images, and updating the ship type and the current signal identification into the ship collision database when the ship type is determined to collide with the offshore wind turbine structure.
8. A marine vessel collision warning system for an offshore wind turbine structure, comprising:
the data acquisition module is used for determining historical collision acceleration signals corresponding to at least two ship types based on the ship historical acceleration signals acquired by the at least two acceleration sensors;
The database establishing module is used for carrying out characteristic extraction processing on the historical collision acceleration signals corresponding to each ship type to obtain corresponding time-frequency domain characteristics, and generating a ship collision database according to the time-frequency domain characteristics corresponding to all the ship types;
the collision recognition module is used for acquiring current acceleration signals acquired by all the acceleration sensors and recognizing the current acceleration signals based on the ship collision database;
And the collision early warning module is used for generating a ship early warning signal according to the identification result corresponding to the current acceleration signal and sending the ship early warning signal to a user terminal.
9. A ship collision early warning system for an offshore wind turbine structure is characterized by comprising a processor and a memory;
the processor is connected with the memory;
The memory is used for storing executable program codes;
The processor runs a program corresponding to executable program code stored in the memory by reading the executable program code for performing the steps of the method according to any of claims 1-7.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer readable storage medium has stored therein instructions which, when run on a computer or a processor, cause the computer or the processor to perform the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410197850.9A CN118072557A (en) | 2024-02-22 | 2024-02-22 | Ship collision early warning method and system for offshore wind turbine structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410197850.9A CN118072557A (en) | 2024-02-22 | 2024-02-22 | Ship collision early warning method and system for offshore wind turbine structure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118072557A true CN118072557A (en) | 2024-05-24 |
Family
ID=91108887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410197850.9A Pending CN118072557A (en) | 2024-02-22 | 2024-02-22 | Ship collision early warning method and system for offshore wind turbine structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118072557A (en) |
-
2024
- 2024-02-22 CN CN202410197850.9A patent/CN118072557A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104953583B (en) | Method used for online monitoring of low-frequency oscillation of electric power system and based on combination of change-point detection and Prony method | |
| CN112834224B (en) | Nuclear power steam turbine generator health state assessment method and system | |
| CN115456047A (en) | Offshore wind turbine structure state monitoring system and method based on artificial intelligence | |
| CN111881594A (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
| CN109655266A (en) | A kind of Wind turbines Method for Bearing Fault Diagnosis based on AVMD and spectral coherence analysis | |
| CN116796182A (en) | Wind turbine generator fault evaluation model training method and fault diagnosis method | |
| CN114061743A (en) | Vibration monitoring method, device, equipment and medium for wind generating set | |
| CN110543658A (en) | Power plant equipment diagnosis method based on big data | |
| CN112802011A (en) | Fan blade defect detection method based on VGG-BLS | |
| CN115859148A (en) | Fan blade vibration alarm method and device | |
| CN111400959B (en) | Blade fault diagnosis method and device for wind generating set | |
| CN113237619B (en) | Fault early warning method, device, equipment and storage medium for variable-speed rotating machinery vibration | |
| CN116757087B (en) | State evaluation method and related equipment for offshore wind power support structure | |
| CN117708637A (en) | Wind turbine generator blade fault diagnosis method based on improved k-means clustering analysis | |
| CN118072557A (en) | Ship collision early warning method and system for offshore wind turbine structure | |
| CN113112869A (en) | Method, device, equipment and medium for customizing electronic fence and processing data | |
| CN116292133B (en) | Method and device for detecting clearance abnormality of wind generating set | |
| CN115357646B (en) | Bridge state monitoring method and system | |
| CN115877128A (en) | Abnormity detection method and device for cable terminal of rail vehicle | |
| CN115561575A (en) | Method for distinguishing electrical abnormal state of offshore wind farm based on multi-dimensional matrix profile | |
| CN114895647A (en) | Small-sample ship part fault data-oriented diagnosis method and readable storage medium | |
| CN109100102B (en) | Fan modal analysis method, device, terminal and computer readable storage medium based on strain continuous monitoring | |
| CN109100103B (en) | Fan 1p signal identification method, device, terminal and computer readable storage medium based on continuous monitoring | |
| CN113219333A (en) | Frequency spectrum parameter processing method during motor fault diagnosis | |
| CN112634593B (en) | Equipment early warning method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |