Multi-source ship positioning information processing method, device and equipment

Abstract

The invention provides a multi-source ship positioning information processing method, device and equipment. The method comprises the following steps: acquiring multi-source positioning information of a ship; performing conversion processing on the multi-source positioning information to obtain first intermediate processing information; performing track association on the first intermediate processing information to obtain second intermediate processing information; obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information; obtaining a comprehensive weight according to the dynamic variance and a preset static variance; and according to the comprehensive weight, carrying out fusion processing on the second intermediate processing information to obtain target positioning information of the ship. According to the scheme, fusion of multiple ship positioning data sources can be achieved, the fusion result is close to actual ship navigation information, the credibility of ship navigation decision and the anti-interference capacity of a ship-borne navigation guiding and aiding system can be improved, and safety and high efficiency of marine traffic are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of ship positioning information processing, and in particular to a method, device and equipment for processing multi-source ship positioning information. Background Art

[0002] With the widespread application of electronic and communication technologies in the field of maritime transportation, the types and quantities of maritime communication and navigation equipment are also increasing. In view of the incomplete and inaccurate information provided by various types of heterogeneous maritime dynamic data sources, data fusion technology is used to obtain a more accurate and complete description of ship information, providing strong support for ship navigation decisions or judgments, thereby effectively ensuring the safety and efficiency of maritime transportation, and at the same time it is also beneficial to protect the marine ecological environment.

[0003] In the ship navigation scenario, there are many advantages in using data fusion technology to process maritime multi-source data. For example, maritime multi-source data has the characteristics of comprehensive description of the target ship and complementary data. Fusion operation can greatly improve the credibility of ship navigation decisions and the anti-interference ability of ship-borne navigation aids. When ships are sailing at sea, resources are limited. Fusion of multi-source data can reduce the redundancy of multi-source data, reduce the waste of storage resources, and reduce unnecessary resource consumption when transmitting data.

[0004] However, the existing multi-source fusion algorithms for ship navigation and positioning information are mostly limited to automatic identification system data and radar data in the selection of data sources, which cannot meet the processing requirements of maritime multi-source data. Summary of the invention

[0005] The present invention provides a multi-source ship positioning information processing method, device and equipment, which can realize the fusion of more than one ship positioning data source, and the fusion result is close to the actual ship's navigation information, which helps to improve the credibility of ship navigation decisions and the anti-interference ability of the ship-borne navigation aids system, and ensure the safety and efficiency of maritime traffic.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] A multi-source ship positioning information processing method, comprising:

[0008] Obtain multi-source positioning information of ships;

[0009] Performing conversion processing on the multi-source positioning information to obtain first intermediate processing information;

[0010] Performing track association on the first intermediate processing information to obtain second intermediate processing information;

[0011] Obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information;

[0012] Obtaining a comprehensive weight according to the dynamic variance and a preset static variance;

[0013] The second intermediate processed information is fused according to the comprehensive weight to obtain the target positioning information of the ship.

[0014] Optionally, converting the multi-source positioning information to obtain first intermediate processing information includes:

[0015] Performing denoising processing on the multi-source positioning information to obtain denoising preprocessing information;

[0016] The pre-processing information is subjected to coordinate transformation and time alignment processing to obtain first intermediate processing information.

[0017] Optionally, performing track association on the first intermediate processing information to obtain second intermediate processing information includes:

[0018] Performing preliminary track association on the first intermediate processed information to obtain preliminary association information;

[0019] Perform track association again on the preliminary association information to obtain the second intermediate processing information.

[0020] Optionally, obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information includes:

[0021] According to the multi-source positioning information, an arithmetic mean value of the multi-source positioning information is obtained as a reference value;

[0022] The dynamic variance is obtained according to the multi-source positioning information and the reference value.

[0023] Optionally, obtaining a comprehensive weight according to the dynamic variance and a preset static variance includes:

[0024] Determine the distribution coefficient k of dynamic error and static error, 0≤k≤1;

[0025] According to the k value, the dynamic variance and static variance are processed to obtain the comprehensive variance;

[0026] A comprehensive weight is obtained according to the comprehensive variance.

[0027] Optionally, the k value is an output result obtained by inputting the second intermediate processing information into a distribution coefficient determination model;

[0028] The training process of the distribution coefficient determination model includes:

[0029] Obtain training multi-source positioning information;

[0030] Performing conversion processing on the training multi-source positioning information to obtain first training intermediate processing information;

[0031] Performing track association on the first training intermediate processing information to obtain second training intermediate processing information;

[0032] Inputting the second training intermediate processing information into the input layer of the preset neural network model for processing to obtain a first layer output;

[0033] The first layer output and the first target parameter are input into the hidden layer for processing to obtain the second layer output;

[0034] The second layer output and the second target parameter are input into the output layer for processing to obtain a distribution coefficient determination model.

[0035] Optionally, performing fusion processing on the second intermediate processed information according to the comprehensive weight to obtain target positioning information of the ship includes:

[0036] By formula:

[0037] performing fusion processing on the second intermediate processed information to obtain target positioning information of the ship;

[0038] in, is the data fusion result, N is the number of fused sensors, y j is the second intermediate processing information corresponding to each sensor, w j is the comprehensive weight corresponding to each sensor.

[0039] The present invention also provides a multi-source ship positioning information processing device, comprising:

[0040] An acquisition module is used to obtain multi-source positioning information of the ship;

[0041] A processing module is used to convert the multi-source positioning information to obtain first intermediate processing information; perform track association on the first intermediate processing information to obtain second intermediate processing information; obtain the dynamic variance of the multi-source positioning information based on the multi-source positioning information; obtain a comprehensive weight based on the dynamic variance and a preset static variance; and perform fusion processing on the second intermediate processing information based on the comprehensive weight to obtain the target positioning information of the ship.

[0042] The present invention also provides a computing device, comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed.

[0043] The present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above.

[0044] The above solution of the present invention includes at least the following beneficial effects:

[0045] The above scheme of the present invention obtains multi-source positioning information of the ship; converts and processes the multi-source positioning information to obtain first intermediate processing information; tracks the first intermediate processing information to obtain second intermediate processing information; obtains the dynamic variance of the multi-source positioning information based on the multi-source positioning information; obtains a comprehensive weight based on the dynamic variance and a preset static variance; and fuses the second intermediate processing information based on the comprehensive weight to obtain the target positioning information of the ship. The fusion of more than one ship positioning data source can be achieved, and the fusion result is close to the actual ship's navigation information, which helps to improve the credibility of the ship's navigation decision-making and the anti-interference capability of the ship's onboard navigation aids system, thereby ensuring the safety and efficiency of maritime transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flow chart of a multi-source ship positioning information processing method provided by an embodiment of the present invention;

[0047] Figure 2 is a neural network structure diagram of a distribution coefficient determination model provided by an embodiment of the present invention;

[0048] Figure 3 is a flow chart of a training process of a distribution coefficient determination model provided by an embodiment of the present invention;

[0049] Figure 4 is a flow chart of the information processing process of the multi-source ship positioning information processing method provided by an embodiment of the present invention;

[0050] Figure 5 is a flow chart of a selection process of an adaptive fusion algorithm provided by an embodiment of the present invention;

[0051] Figure 6 A module diagram of a multi-source ship positioning information processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0053] like Figure 1 As shown, an embodiment of the present invention provides a multi-source ship positioning information processing method, comprising:

[0054] Step 11, obtaining multi-source positioning information of the ship;

[0055] Step 12, converting the multi-source positioning information to obtain first intermediate processing information;

[0056] Step 13, performing track association on the first intermediate processing information to obtain second intermediate processing information;

[0057] Step 14, obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information;

[0058] Step 15, obtaining a comprehensive weight according to the dynamic variance and the preset static variance;

[0059] Step 16: According to the comprehensive weight, the second intermediate processing information is fused to obtain the target positioning information of the ship.

[0060] In this embodiment, multi-source positioning information of the ship is acquired; the multi-source positioning information is converted and processed to obtain first intermediate processing information; the first intermediate processing information is track-associated to obtain second intermediate processing information; the dynamic variance of the multi-source positioning information is obtained based on the multi-source positioning information; the comprehensive weight is obtained based on the dynamic variance and the preset static variance; the second intermediate processing information is fused based on the comprehensive weight to obtain the target positioning information of the ship; the fusion of more than one ship positioning data source can be achieved, and the fusion result is close to the actual ship's navigation information, which helps to improve the credibility of the ship's navigation decision-making and the anti-interference capability of the ship's onboard navigation aids system, and ensures the safety and efficiency of maritime transportation.

[0061] In an optional embodiment of the present invention, step 12 includes:

[0062] Step 121, performing denoising processing on the multi-source positioning information to obtain denoising pre-processing information;

[0063] Step 122, performing coordinate conversion and time alignment processing on the pre-processing information to obtain first intermediate processing information.

[0064] In this embodiment, the multi-source positioning information includes: radar system positioning information, automatic identification system positioning information and Beidou satellite navigation system positioning information, wherein the radar system positioning information is observation data acquired by a shore-based radar system;

[0065] De-noising the multi-source positioning information, directly discarding erroneous data that do not conform to the format specification or the value range, and preventing wild values, noise or erroneous data from affecting the track association result;

[0066] In order to facilitate subsequent track association and fusion processing, coordinate transformation is performed on the denoising preprocessing information, and the denoising preprocessing information is transformed and unified into a common coordinate system, wherein the selected common coordinate system is a rectangular coordinate system;

[0067] Specific coordinate transformation:

[0068] Coordinate conversion of automatic identification system positioning information and Beidou satellite navigation system positioning information:

[0069] By formula:

[0070]

[0071] Carry out coordinate conversion between automatic identification system positioning information and Beidou satellite navigation system positioning information;

[0072] Wherein, X is the abscissa of the target ship in the rectangular coordinate system after conversion; Y is the ordinate of the target ship in the rectangular coordinate system after conversion; L is the longitude of the target ship in the coordinate system of the identification system; B is the latitude of the target ship in the coordinate system of the identification system; S is the arc length of the meridian from the equator to the latitude in the coordinate system of the identification system; N is the radius of curvature of the y-axis at the latitude; g is the acceleration of gravity; η is the second eccentricity of the earth;

[0073] Specifically, when performing coordinate conversion of automatic identification system positioning information, L is the longitude of the target ship in the WGS-84 coordinate system, B is the latitude of the target ship in the WGS-84 coordinate system, S is the meridian arc length from the equator to the latitude in the WGS-84 coordinate system, and the WGS-84 coordinate system is the 1984 World Geodetic Coordinate System;

[0074] When performing coordinate conversion of Beidou satellite navigation system positioning information, L is the longitude of the target ship in the CGCS2000 coordinate system, B is the latitude of the target ship in the CGCS2000 coordinate system, S is the meridian arc length from the equator to the latitude in the CGCS2000 coordinate system, and the CGCS2000 coordinate system is the 2000 National Geodetic Coordinate System;

[0075] Coordinate transformation of radar system positioning information:

[0076] By formula:

[0077]

[0078] Perform coordinate conversion of radar system positioning information;

[0079] Wherein, X is the horizontal coordinate of the target ship detected by the radar after the conversion in the rectangular coordinate system; Y is the vertical coordinate of the target ship detected by the radar after the conversion in the rectangular coordinate system; R is the distance in the polar coordinate system; θ is the azimuth value in the polar coordinate system;

[0080] Since the sampling periods of each system are different, time alignment processing must be performed; the radar has a fixed scanning period, which is generally 15r / min~30r / min, and the time interval is generally 2s~4s; while the data sampling periods of AIS (Automatic Identification System) and BDS (Beidou Satellite Navigation System) vary greatly, which is related to the status of the ship or the settings of the shipborne equipment. Therefore, the sampling time of the radar is used as the starting time reference for time alignment, and the positioning information of the automatic identification system and the positioning information of the Beidou Satellite Navigation System are time aligned;

[0081] Specific:

[0082] The two moments before and after moment T are T1 and T2, and the collected positioning information is: (L 1 ,B 1 )、(L 2 ,B 2 ), then at time T the target ship’s positioning information (L T ,B T )for:

[0083]

[0084] In an optional embodiment of the present invention, step 13 includes:

[0085] Step 131, performing preliminary track association on the first intermediate processing information to obtain preliminary association information;

[0086] Step 132: perform track association again on the preliminary association information to obtain the second intermediate processing information.

[0087] In this embodiment, preliminary track association is performed on the first intermediate processing information to obtain preliminary association information; the preliminary association information is re-associated with the track to obtain the second intermediate processing information; after the preliminary track association is performed, the re-track association is performed. This method can reduce the overall amount of calculation, improve the efficiency of track association, and help improve the overall performance of track fusion;

[0088] The automatic identification system positioning information and the Beidou satellite navigation system positioning information contain the basic information of the target ship, such as the ship name, MMSI number (marine mobile communication service identification code), call sign, equipment identification number, etc., while the radar system positioning information does not have the above basic information. Therefore, it is necessary to perform track association on the first intermediate processing information to determine the target ship that matches the first intermediate processing information;

[0089] The automatic identification system positioning information and the Beidou satellite navigation system positioning information can be matched through the MMSI number. After any one of the automatic identification system positioning information and the Beidou satellite navigation system positioning information matches the radar system positioning information, the track association of the automatic identification system positioning information, the Beidou satellite navigation system positioning information and the radar system positioning information can be completed; therefore, in this embodiment, the track association of the automatic identification system positioning information and the radar system positioning information is taken as an example;

[0090] Track correlation between automatic identification system positioning information and radar system positioning information:

[0091] Initial track association:

[0092] Using the time and position information in the first intermediate processing information, roughly associate several AIS tracks that may be associated with the radar track with the shore-based radar as the center;

[0093] Specific:

[0094] When multiple radars work together, their coverage area is large and only part of the area belongs to the common surveillance area. If all tracks in the entire area are traversed when calculating track association, the amount of calculation and time will be large. At the same time, the track may be terminated, and if the time interval between the latest states of two tracks is too long, the change in speed and heading information is likely to cause misassociation. In these cases, it is unnecessary to perform association. Therefore, preliminary association thresholds are set in distance and time to exclude targets outside the distance and time thresholds.

[0095] Assuming that the jth target track information of radar i is received at time n, the track state is expressed as:

[0096]

[0097] If the track has not been associated with any system track before, it will be roughly correlated with all system tracks based on time and position characteristics, and the update time interval threshold is σ t , the distance association threshold is σ z ;

[0098] At this time, the system track is:

[0099]

[0100] in,

[0101] System track The current latest system track status is:

[0102]

[0103] If the following conditions are met:

[0104]

[0105] It is considered that the jth target track received by radar i at time n is consistent with the system track association;

[0106] Through the above process, the first intermediate processing information is subjected to preliminary track association to obtain preliminary association information; performing preliminary track association can reduce the amount of calculation for subsequent secondary track association and improve the efficiency of secondary track association;

[0107] Perform track association again on the preliminary association information:

[0108] performing track association again on the preliminary association information by using a modified K-nearest neighbor (MK-NN) track association algorithm to obtain the second intermediate processing information;

[0109] Specific:

[0110] The track association state is divided into association period, check period and holding period, and the track association is processed through track association quality and separation quality;

[0111] In the association period, the track association quality and separation quality are introduced. All alternative tracks near the target track are judged one by one in a continuous period of time. When an alternative track meets the association threshold K times in the past N judgments, it is considered to be associated. If multiple alternative tracks meet the conditions, ambiguity processing is performed; when the time is greater than N, it enters the inspection period, and the target track and the selected track are continuously tested for three chi-square distribution tests. If all three tests pass, the two tracks become a fixed association pair, and the association is completed and enters the maintenance period; if one test fails, two more tests are performed. If 3 out of 5 tests pass, it is determined that the association is completed, otherwise it returns to the association period.

[0112] In an optional embodiment of the present invention, step 14 includes:

[0113] Step 141, obtaining an arithmetic mean of the multi-source positioning information as a reference value according to the multi-source positioning information;

[0114] Step 142: Obtain the dynamic variance according to the multi-source positioning information and the reference value.

[0115] In this embodiment, the multi-source positioning information is taken as radar system positioning information, automatic identification system positioning information and Beidou satellite navigation system positioning information as an example;

[0116] Initially, the arithmetic mean of multi-source positioning information is used as the reference value; subsequently, the prediction result of the track at the next moment by Kalman filtering is used as the reference value for calculating the variance at the next moment, which can reduce the deviation of the reference value and help improve the accuracy of the fusion result;

[0117] Specific:

[0118]

[0119] Among them, y 0 (t) is the state at time t predicted by Kalman filtering at time t-1; y a (t) is the positioning information observed by the automatic recognition system; r (t) is the positioning information observed by the radar system; b (t) Positioning information observed by the Beidou satellite navigation system; To automatically identify the dynamic variance of the system; is the dynamic variance of the radar system; is the dynamic variance of the BeiDou satellite navigation system.

[0120] In an optional embodiment of the present invention, step 15 includes:

[0121] Step 151, determining the distribution coefficient k of the dynamic error and the static error, 0≤k≤1;

[0122] Step 152, processing the dynamic variance and the static variance according to the k value to obtain the comprehensive variance;

[0123] Step 153, obtaining a comprehensive weight according to the comprehensive variance.

[0124] In this embodiment, the static variances calculated by the preset automatic identification system, radar system and Beidou satellite navigation system according to historical data or nominal accuracy are respectively and

[0125] Among them, static error is when the measured value (or input value) does not change with time, the measurement result (or output value) will drift slowly, which is a systematic error and is given directly;

[0126] According to the k value, the dynamic variance and static variance are processed to obtain the comprehensive variance; specifically:

[0127]

[0128] According to the k value, the dynamic variance and static variance are adjusted to obtain the comprehensive variance, which can reduce the deviation of the comprehensive variance and improve the accuracy of the subsequent fusion results;

[0129] After obtaining the comprehensive variance, the weight is calculated according to the principle that the larger the error, the smaller the weight, and the sum of the weights is 1:

[0130]

[0131] Among them, w a is the comprehensive weight of the automatic recognition system; w r is the comprehensive weight of the radar system; w b is the comprehensive weight of the Beidou satellite navigation system.

[0132] In an optional embodiment of the present invention, the k value is an output result obtained by inputting the second intermediate processing information into a distribution coefficient determination model;

[0133] The training process of the distribution coefficient determination model includes:

[0134] Obtain training multi-source positioning information;

[0135] Performing conversion processing on the training multi-source positioning information to obtain first training intermediate processing information;

[0136] Performing track association on the first training intermediate processing information to obtain second training intermediate processing information;

[0137] Inputting the second training intermediate processing information into the input layer of the preset neural network model for processing to obtain a first layer output;

[0138] The first layer output and the first target parameter are input into the hidden layer for processing to obtain the second layer output;

[0139] The second layer output and the second target parameter are input into the output layer for processing to obtain a distribution coefficient determination model.

[0140] In this embodiment, the distribution coefficient k represents the proportion of the random component and the fixed component of the error in the error calculation process; according to the error calculation principle, the smoothness of the observed data of the system for a period of time is used to judge the error situation, and the principle is as follows: if the observed data is smooth for a period of time, it means that the group of data is less affected by noise, and the proportion of the random component should be reduced and the proportion of the fixed component should be increased when calculating the error, that is, when the value range of k is 0 to 1, k should be appropriately reduced and closer to 0; similarly, if the observed data changes greatly for a period of time, the proportion of the random component should be increased, and k will be closer to 1;

[0141] The degree of smoothness of the observed data can be reflected by the standard deviation of the slope, and the calculation formula is as follows:

[0142] sr i =x i+1 -x i

[0143]

[0144] Among them, sr i The slope calculated by shifting and subtracting the array, is the mean of the slope, sd is the standard deviation of the slope, and N is the number of observations;

[0145] In order to ensure the stability of the fusion process and the accuracy of the fusion result, the present application inputs the second intermediate processing information into the distribution coefficient determination model, and uses the output result of the distribution coefficient determination model as the distribution coefficient k value of the dynamic error and the static error;

[0146] like Figure 2 As shown, the distribution coefficient determination model is set with three layers: input layer, hidden layer and output layer;

[0147] The training multi-source positioning information is converted to obtain first training intermediate processing information, which has been described in step 12 and will not be described again;

[0148] Performing track association on the first training intermediate processing information to obtain second training intermediate processing information has been described in step 13 and will not be repeated here;

[0149] like Figure 3 As shown, the distribution coefficient determines the specific training process of the model:

[0150] S1. Initialize network parameters: including network structure, number of network layers, number of nodes in each layer; initialize input and output vectors (X, D), input layer to hidden layer connection weight ω ih , the connection weight from hidden layer to output layer ω hj , network learning rate η, momentum coefficient of weight change is α, network allowable error accuracy eps, number of iterations K;

[0151] S2. Select a pattern sample and start forward pass calculation:

[0152] First calculate the hidden layer output:

[0153]

[0154] in,

[0155] Then calculate the output layer output:

[0156]

[0157] in, Or φ(x)=x;

[0158] S3. Reverse calculation of neuron error:

[0159] First, calculate the output layer error:

[0160]

[0161] Then calculate the hidden layer error:

[0162]

[0163] S4. Update weights:

[0164] New weights from hidden layer to output layer:

[0165]

[0166] New weights from input layer to hidden layer:

[0167]

[0168] S5. Calculate the network output error:

[0169]

[0170] If it is greater than eps, go to S2, otherwise the program ends and the training is completed;

[0171] Since the value of k is limited to between 0 and 1, even if the output result of the distribution coefficient determination model is too different from the actual situation, or even in extreme cases k is 1 or 0, the error is all random components or fixed components, and the impact on the final result is limited, and the result with a certain accuracy can still be output; therefore, by inputting the second intermediate processing information into the distribution coefficient determination model, and using the output result of the distribution coefficient determination model as the distribution coefficient k value of the dynamic error and the static error, the stability of the fusion result can be guaranteed, which can not only reduce the amount of calculation, but also make full use of historical information and real-time information, and further improve the accuracy of ship positioning.

[0172] In an optional embodiment of the present invention, step 16 includes:

[0173] Step 161, by formula:

[0174] performing fusion processing on the second intermediate processed information to obtain target positioning information of the ship;

[0175] in, is the data fusion result, N is the number of fused sensors, y j is the second intermediate processing information corresponding to each sensor, w j is the comprehensive weight corresponding to each sensor.

[0176] In this embodiment, the static weights and dynamic weights are combined. When the accuracy of each positioning system is reflected by historical data or nominal accuracy, the dynamic error is obtained by calculating the real-time variance. The static error proportion of each system is determined by determining the k value. According to the k value, the dynamic variance and the static variance are processed to obtain the comprehensive variance, and finally the comprehensive weight is obtained. The fusion processing is performed according to the comprehensive weight to obtain the target positioning information of the ship. The system historical data and real-time data can be considered at the same time, and effective information can be extracted from the positioning data of each system to the greatest extent, thereby improving the accuracy of the positioning fusion result.

[0177] like Figure 4 As shown in FIG. 1 , the information processing process of the multi-source ship positioning information processing method is as follows:

[0178] Obtain the ship's positioning information observed by the automatic identification system, radar system and Beidou satellite navigation system as the ship's multi-source positioning information;

[0179] Performing denoising processing on the multi-source positioning information as preprocessing to obtain denoising preprocessing information; performing coordinate transformation and time alignment processing on the preprocessing information to obtain first intermediate processing information;

[0180] Performing preliminary track association on the first intermediate processing information to obtain preliminary associated information; performing track association again on the preliminary associated information to obtain the second intermediate processing information;

[0181] According to the multi-source positioning information, an arithmetic mean value of the multi-source positioning information is obtained as a reference value; according to the multi-source positioning information and the reference value, the dynamic variance is obtained; the second intermediate processing information is input into a distribution coefficient determination model, and the output result is used as a distribution coefficient k of a dynamic error and a static error; according to the k value, the dynamic variance and the preset static variance are processed to obtain a comprehensive variance;

[0182] Obtaining a comprehensive weight according to the comprehensive variance;

[0183] According to the comprehensive weight, the second intermediate processing information is fused to obtain a preliminary fusion result;

[0184] Perform filtering calculation on the preliminary fusion result to obtain the fusion result at the current moment and the predicted value at the next moment. Use the predicted value at the next moment as the reference value at the next moment to calculate the dynamic variance at the next moment. The fusion result at the current moment is used as the target positioning information of the ship at the current moment.

[0185] Specific filtering calculation:

[0186] S1, update the state transfer matrix F, whose value is related to the last update time l of the system track and the current radar track time k时 The interval is related to:

[0187]

[0188] Where T = k 时 -1;

[0189] S2, predict the state and calculate the new information (residual):

[0190]

[0191] in, is the track status of the mth system track at the last update time l; For its current k 时 Track prediction status at the moment;

[0192] The predicted track position is:

[0193] The observation matrix is:

[0194]

[0195] The position value of the jth track of radar i is:

[0196] z ij (k 时 )=Hx ij (k 时 );

[0197] Among them, x ij (k 时 ) is the jth system track of radar i at the last update time k 时 Track status;

[0198] Subtracting two position values ​​will give you the new information:

[0199]

[0200] S3. Update the corrected observation noise covariance matrix R:

[0201] The measurement error covariance matrix of radar i is:

[0202]

[0203] Among them, the radar errors in range and azimuth are both zero-mean Gaussian white noise and are independent of each other; and Respectively represent their standard deviations; when the radar track information is converted from the polar coordinate system to the rectangular coordinate system, there is a nonlinear conversion relationship as follows. There is also a nonlinear conversion relationship between the actual radar measurement error and the measurement error in the rectangular coordinate system. The measurement error plays a vital role in the Kalman filtering process, so it is also very important to convert the measurement error and use a more accurate measurement error covariance matrix.

[0204] The position value of the jth track of radar i in the rectangular coordinate system is:

[0205] z ij =[x ij ;y ij ];

[0206] The observation noise covariance matrix is:

[0207]

[0208] Expand the above formula:

[0209]

[0210] Among them, (x' ij ,y' ij ) is the real rectangular coordinate position;

[0211] According to the trigonometric identities, the error in the rectangular coordinate system is:

[0212]

[0213] The two are not independent of each other, and each direct coordinate system measurement error is determined by the true target distance, orientation, distance error, and orientation error;

[0214] When the polar coordinate measurement noise is zero-mean Gaussian white noise:

[0215]

[0216] The average error is:

[0217]

[0218] Performing algebraic conversion, we get the elements of R as follows:

[0219]

[0220] S4, prediction error autocorrelation matrix and calculation innovation (residual) autocorrelation matrix:

[0221]

[0222] in, is the state error autocorrelation matrix of the system track m at time 1; is the system track m in k 时 The predicted state error autocorrelation matrix at the moment; Q is the covariance matrix of process noise;

[0223] The corresponding innovation autocorrelation matrix is:

[0224]

[0225] S5. Calculate the gain of the filter:

[0226]

[0227] S6. Update state and error autocorrelation matrices:

[0228]

[0229] Only one radar track is updated at a time. It is also single, and the update of the state error autocorrelation matrix is ​​more suitable for the case of single measurement track update:

[0230]

[0231] In practical applications, in order to reduce the amount of calculation in the navigation ship and identify fault data, the adaptive fusion algorithm can be selected before the fusion calculation; Figure 5 As shown in the figure, the relationship between system data is judged according to the real-time observation value to determine whether the track distance is too close or too far: (1) When the track distance is too close, no fusion is performed and the positioning information of the system with the highest accuracy is directly output; (2) When the track difference is too far, it is judged that the data source is faulty and the faulty data source is removed before calculation; (3) If there is a certain gap between the tracks but it does not reach the threshold, the fusion calculation process is entered and the fusion result is output.

[0232] like Figure 6 As shown, an embodiment of the present invention further provides a multi-source ship positioning information processing device 60, comprising:

[0233] An acquisition module 61 is used to acquire multi-source positioning information of a ship;

[0234] The processing module 62 is used to convert the multi-source positioning information to obtain first intermediate processing information; perform track association on the first intermediate processing information to obtain second intermediate processing information; obtain the dynamic variance of the multi-source positioning information based on the multi-source positioning information; obtain a comprehensive weight based on the dynamic variance and a preset static variance; and perform fusion processing on the second intermediate processing information based on the comprehensive weight to obtain the target positioning information of the ship.

[0235] Optionally, converting the multi-source positioning information to obtain first intermediate processing information includes:

[0236] Performing denoising processing on the multi-source positioning information to obtain denoising preprocessing information;

[0237] The pre-processing information is subjected to coordinate transformation and time alignment processing to obtain first intermediate processing information.

[0238] Optionally, performing track association on the first intermediate processing information to obtain second intermediate processing information includes:

[0239] Performing preliminary track association on the first intermediate processed information to obtain preliminary association information;

[0240] Perform track association again on the preliminary association information to obtain the second intermediate processing information.

[0241] Optionally, obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information includes:

[0242] According to the multi-source positioning information, an arithmetic mean value of the multi-source positioning information is obtained as a reference value;

[0243] The dynamic variance is obtained according to the multi-source positioning information and the reference value.

[0244] Optionally, obtaining a comprehensive weight according to the dynamic variance and a preset static variance includes:

[0245] Determine the distribution coefficient k of dynamic error and static error, 0≤k≤1;

[0246] According to the k value, the dynamic variance and static variance are processed to obtain the comprehensive variance;

[0247] A comprehensive weight is obtained according to the comprehensive variance.

[0248] Optionally, the k value is an output result obtained by inputting the second intermediate processing information into a distribution coefficient determination model;

[0249] The training process of the distribution coefficient determination model includes:

[0250] Obtain training multi-source positioning information;

[0251] Performing conversion processing on the training multi-source positioning information to obtain first training intermediate processing information;

[0252] Performing track association on the first training intermediate processing information to obtain second training intermediate processing information;

[0253] Inputting the second training intermediate processing information into the input layer of the preset neural network model for processing to obtain a first layer output;

[0254] The first layer output and the first target parameter are input into the hidden layer for processing to obtain the second layer output;

[0255] The second layer output and the second target parameter are input into the output layer for processing to obtain a distribution coefficient determination model.

[0256] Optionally, performing fusion processing on the second intermediate processed information according to the comprehensive weight to obtain target positioning information of the ship includes:

[0257] By formula:

[0258] performing fusion processing on the second intermediate processed information to obtain target positioning information of the ship;

[0259] in, is the data fusion result, N is the number of fused sensors, y j is the second intermediate processing information corresponding to each sensor, w j is the comprehensive weight corresponding to each sensor.

[0260] It should be noted that the device is a device corresponding to the above method, and all implementation methods in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effects.

[0261] The embodiment of the present invention further provides a computing device, including: a processor, a memory storing a computer program, and when the computer program is executed by the processor, the method described in the above embodiment is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0262] In an embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions, and when the instructions are executed on a computer, the computer executes the method described in the above embodiment. All implementations in the above method embodiment are applicable to this embodiment, and can also achieve the same technical effect.

[0263] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0264] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0265] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0266] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0267] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0268] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0269] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0270] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0271] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing multi-source ship positioning information, characterized in that: include: Obtain multi-source positioning information of ships; Performing conversion processing on the multi-source positioning information to obtain first intermediate processing information; Performing track association on the first intermediate processing information to obtain second intermediate processing information; Obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information; Obtaining a comprehensive weight according to the dynamic variance and a preset static variance; The second intermediate processed information is fused according to the comprehensive weight to obtain the target positioning information of the ship.

2. The multi-source ship positioning information processing method according to claim 1, characterized in that: The multi-source positioning information is converted to obtain first intermediate processing information, including: Performing denoising processing on the multi-source positioning information to obtain denoising preprocessing information; The pre-processing information is subjected to coordinate transformation and time alignment processing to obtain first intermediate processing information.

3. The multi-source ship positioning information processing method according to claim 1, characterized in that: Performing track association on the first intermediate processing information to obtain second intermediate processing information includes: Performing preliminary track association on the first intermediate processed information to obtain preliminary association information; Perform track association again on the preliminary association information to obtain the second intermediate processing information.

4. The multi-source ship positioning information processing method according to claim 1, characterized in that: Obtaining a dynamic variance of the multi-source positioning information according to the multi-source positioning information includes: According to the multi-source positioning information, an arithmetic mean value of the multi-source positioning information is obtained as a reference value; The dynamic variance is obtained according to the multi-source positioning information and the reference value.

5. The multi-source ship positioning information processing method according to claim 1, characterized in that: According to the dynamic variance and the preset static variance, a comprehensive weight is obtained, including: Determine the distribution coefficient k of dynamic error and static error, 0≤k≤1; According to the k value, the dynamic variance and static variance are processed to obtain the comprehensive variance; A comprehensive weight is obtained according to the comprehensive variance.

6. The multi-source ship positioning information processing method according to claim 5, characterized in that: The value k is the output result obtained by inputting the second intermediate processing information into the distribution coefficient determination model; The training process of the distribution coefficient determination model includes: Obtain training multi-source positioning information; Performing conversion processing on the training multi-source positioning information to obtain first training intermediate processing information; Performing track association on the first training intermediate processing information to obtain second training intermediate processing information; Inputting the second training intermediate processing information into the input layer of the preset neural network model for processing to obtain a first layer output; The first layer output and the first target parameter are input into the hidden layer for processing to obtain the second layer output; The second layer output and the second target parameter are input into the output layer for processing to obtain a distribution coefficient determination model.

7. The multi-source ship positioning information processing method according to claim 1, characterized in that: According to the comprehensive weight, the second intermediate processed information is fused to obtain the target positioning information of the ship, including: By formula: performing fusion processing on the second intermediate processed information to obtain target positioning information of the ship; in, is the data fusion result, N is the number of fused sensors, y j is the second intermediate processing information corresponding to each sensor, w j is the comprehensive weight corresponding to each sensor.

8. A multi-source ship positioning information processing device, characterized in that: include: An acquisition module is used to obtain multi-source positioning information of the ship; A processing module, used for converting the multi-source positioning information to obtain first intermediate processing information; The first intermediate processing information is track-correlated to obtain second intermediate processing information; a dynamic variance of the multi-source positioning information is obtained based on the multi-source positioning information; a comprehensive weight is obtained based on the dynamic variance and a preset static variance; and the second intermediate processing information is fused based on the comprehensive weight to obtain target positioning information of the ship.

9. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images