Ship docking positioning method and system based on multi-source positioning data fusion

Abstract

The invention provides a ship docking positioning method and system based on multi-source positioning data fusion, and relates to the technical field of data processing, and the method comprises the steps: obtaining the multi-source positioning data of a ship; projecting the multi-source positioning data into a unified local coordinate system through coordinate transformation; performing consistency check on the positioning data after coordinate transformation, and determining consistency factors of various positioning data; judging whether the consistency factor of the various positioning data is greater than a consistency threshold value, and if so, keeping the consistency factor in the current measurement period; otherwise, removing in the current measurement period; determining confidence factors of the various reserved positioning data according to the historical performance of the reserved positioning data; and based on the confidence factors of various positioning data, carrying out weighted fusion on the multi-source positioning data through a Kalman filtering algorithm, and determining fusion positioning data of the ship. The ship docking positioning precision and reliability can be improved, the anti-interference capability of the system is enhanced, and the system adapts to the dynamically changing environment.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for positioning a ship entering a dock based on multi-source positioning data fusion. Background Art

[0002] Ship docking positioning is not only a necessary measure to ensure shipping safety, but also an important means to improve ship operation efficiency, reduce costs and promote environmental protection. With the continuous advancement of technology, the accuracy and intelligence level of docking positioning systems will continue to improve, providing more reliable support for the modern shipping industry.

[0003] At present, the main methods of ship docking positioning include buoy positioning and cable vertical positioning. Buoy positioning technology uses buoys or buoy arrays to determine the position of the ship. Buoys are usually equipped with positioning equipment (such as GPS) and communication systems to provide real-time position information to the ship. Cable vertical positioning technology determines the docking position of the ship by pulling out a reference line perpendicular to the ship's heading line during the docking process and using measurement tools (such as lasers, total stations, etc.) to measure the distance to the shore or buoy.

[0004] However, the positioning of the buoy is easily affected by the water flow, and the fluctuation and displacement of the buoy affect the positioning accuracy. The buoy is released underwater by the cable through the guide wheel, which is easily affected by debris or the guide wheel, resulting in the buoy being unable to be released or the cable being worn off, affecting the positioning of the ship entering the dock. The cable-drawing method is subject to the limitation of tides, and the pulling and adjusting of the lead wires on both sides of the dock wall must be completed within a limited time, which requires high quality of personnel. Summary of the invention

[0005] In order to solve the problem that traditional buoy positioning is easily affected by water flow, and the fluctuation, displacement and other phenomena affect the positioning accuracy, the buoy is released underwater by a cable through a guide wheel, which is easily affected by debris or guide wheels, resulting in the buoy being unable to be released or the cable being worn out, affecting the ship's docking positioning work. The cable-drawing method is subject to the limitation of tides, and the pulling and adjustment of the lead wires on both sides of the dock wall must be completed within a limited time, which requires a high level of personnel quality. The present invention provides a ship docking positioning method and system based on multi-source positioning data fusion.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a ship docking positioning method based on multi-source positioning data fusion, comprising:

[0009] S1: Acquire multi-source positioning data of the ship;

[0010] S2: Project the multi-source positioning data into a unified local coordinate system through coordinate transformation;

[0011] S3: Perform consistency check on the positioning data after coordinate transformation to determine the consistency factors of various positioning data;

[0012] S4: Determine whether the consistency factor of various positioning data is greater than the consistency threshold. If so, retain it in the current measurement cycle; otherwise, remove it in the current measurement cycle;

[0013] S5: determining confidence factors of various retained positioning data based on the historical performance of the retained positioning data;

[0014] S6: Based on the confidence factors of various positioning data, weighted fusion is performed on multi-source positioning data through a Kalman filter algorithm to determine the fused positioning data of the ship.

[0015] Second aspect:

[0016] An embodiment of the present invention provides a ship docking positioning system based on multi-source positioning data fusion, comprising:

[0017] processor;

[0018] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the ship docking positioning method based on multi-source positioning data fusion as described in the first aspect is implemented.

[0019] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0020] In the present invention, by integrating positioning data from different sources and fusing them through consistency check and Kalman filtering, the positioning accuracy and reliability are improved, the system's anti-interference ability is enhanced, and it adapts to the dynamically changing environment, making the ship's docking process safer and more flexible, and reducing the requirements on the operator's skills. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A schematic flow chart of a method for ship docking positioning based on multi-source positioning data fusion provided by an embodiment of the present invention;

[0023] Figure 2A structural schematic diagram of a ship docking positioning method based on multi-source positioning data fusion provided by an embodiment of the present invention;

[0024] Figure 3 A schematic structural diagram of a ship docking positioning system based on multi-source positioning data fusion provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0026] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0027] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0028] Reference Manual Attached Figure 1 , shows a flow chart of a ship docking positioning method based on multi-source positioning data fusion provided by an embodiment of the present invention.

[0029] Reference Manual Attached Figure 2 , shows a structural schematic diagram of a ship docking positioning method based on multi-source positioning data fusion provided by an embodiment of the present invention.

[0030] The embodiment of the present invention provides a method for positioning a ship entering a dock based on multi-source positioning data fusion, which can be implemented by a ship entering a dock positioning device based on multi-source positioning data fusion, and the ship entering a dock positioning device based on multi-source positioning data fusion can be a terminal or a server. The processing flow of the method for positioning a ship entering a dock based on multi-source positioning data fusion can include the following steps:

[0031] S1: Obtain multi-source positioning data of the ship.

[0032] Optionally, the positioning data includes: radar positioning data, inertial navigation positioning data, global navigation positioning data and mobile observation positioning data.

[0033] Furthermore, radar measures the position of an object by emitting electromagnetic waves and receiving reflected signals. It is able to determine the distance and azimuth between the target and the radar.

[0034] Furthermore, the Inertial Navigation System (INS) measures the acceleration and angular velocity of the ship through built-in accelerometers and gyroscopes, and uses this information to calculate the current position and orientation.

[0035] Furthermore, the Global Navigation Satellite System (GNSS) determines the position by receiving signals from satellites. By calculating the time difference of receiving the signals, the system can calculate the distances to multiple satellites and determine the current position based on these distances.

[0036] Furthermore, mobile observation positioning systems typically use sensors (such as GPS, accelerometers, gyroscopes, etc.) in crew mobile devices (such as smartphones or portable navigation devices) to measure position.

[0037] Furthermore, the positioning data may also include sonar positioning data, laser ranging positioning data, visual positioning data, and Wi-Fi positioning data, etc. The present invention does not limit the specific type of positioning data.

[0038] S2: Project the multi-source positioning data into a unified local coordinate system through coordinate transformation.

[0039] Specifically, the multi-source positioning data can be projected into a unified local coordinate system through translation transformation and rotation transformation.

[0040] S3: Perform consistency check on the positioning data after coordinate transformation to determine the consistency factors of various positioning data.

[0041] In a possible implementation, S3 specifically includes: performing consistency check on the positioning data after coordinate transformation, and determining consistency factors of various positioning data based on differences between various positioning data.

[0042] Furthermore, the consistency factor is specifically:

[0043]

[0044]

[0045]

[0046] Among them, Y i represents the consistency factor of the i-th positioning data, y ij represents the consistency detection value between the i-th positioning data and the j-th positioning data, n represents the total number of positioning data categories, d ij represents the distance between the i-th positioning data and the j-th positioning data, d0 represents the distance threshold, z i represents the measured value of the i-th positioning data, z jRepresents the measurement value of the j-th positioning data.

[0047] Among them, those skilled in the art can set the size of the distance threshold according to actual conditions, and the present invention does not limit it.

[0048] It should be noted that if a positioning data is similar to other data (the distance is less than a threshold), it scores high in consistency; otherwise, it scores zero.

[0049] In the present invention, by calculating the consistency between different positioning data, outliers or erroneous measurements can be identified. At the same time, by calculating the consistency factor, the system can adjust the trust level of different data sources in real time to ensure that more reliable data sources have a greater impact on the fusion results.

[0050] S4: Determine whether the consistency factor of various positioning data is greater than the consistency threshold, if so, retain it in the current measurement cycle, otherwise, remove it in the current measurement cycle.

[0051] Among them, those skilled in the art can set the size of the consistency threshold according to actual conditions, and the present invention does not limit it.

[0052] It should be noted that in actual applications, due to environmental influences, it is inevitable that some positioning data will be inaccurate in a certain measurement cycle. By setting a consistency threshold, you can effectively filter out data that performs well and is reliable in the current measurement cycle, which helps ensure that the data used in the fusion process are of high quality and reduce the impact of low-quality data on the results.

[0053] In a possible implementation manner, after S4, the step further includes: when a consistency factor of certain positioning data is less than a consistency threshold value in a plurality of consecutive measurement cycles, issuing an alarm.

[0054] In the present invention, the situation where the consistency factor is lower than the threshold for multiple times indicates that the data source may have a persistent fault or inaccuracy. The alarm can promptly remind the operator to check or maintain the data source, reduce the risk of subsequent accidents, and ensure navigation safety.

[0055] S5: Determine confidence factors of various retained positioning data based on the historical performance of the retained positioning data.

[0056] In a possible implementation, S5 specifically includes: determining confidence factors of various retained positioning data according to the root mean square error of the retained positioning data.

[0057] Furthermore, the confidence factor is specifically:

[0058]

[0059]

[0060] Among them, C i Represents the confidence factor of the i-th positioning data, RMSE i represents the root mean square error of the i-th positioning data, N represents the total number of categories of retained positioning data, z it represents the measured value of the i-th positioning data at time t, represents the true value of the ship's position at time t, and T represents the total observation time.

[0061] In the present invention, the confidence factor can reflect the performance changes of the data source in real time, allowing the system to dynamically adjust the degree of trust in each data source according to the latest measurement performance.

[0062] Furthermore, in the data fusion process, a higher confidence factor means that the data source has a greater influence, making the fusion result more accurate. By weighting the confidence factor based on historical performance, the positioning accuracy can be significantly improved.

[0063] S6: Based on the confidence factors of various positioning data, the multi-source positioning data are weightedly fused through the Kalman filter algorithm to determine the fused positioning data of the ship.

[0064] In practical applications, the measurements of different sensors usually contain their own noise and errors. If weighted fusion is performed directly without considering the noise characteristics and errors, the fusion result may be affected by low-quality measurements, reducing the accuracy of the final positioning.

[0065] Furthermore, the Kalman filter algorithm is a recursive algorithm for estimating the state of a dynamic system, and is widely used in the fields of control, navigation, signal processing, etc. It provides the best linear estimation of the system state by fusing sensor data, and has good real-time performance and accuracy. The present invention improves the traditional Kalman filter algorithm by combining the confidence factor.

[0066] In a possible implementation, S6 specifically includes:

[0067] S601: Construct a state vector containing various positioning data:

[0068]

[0069] Among them, X(t) represents the state vector at time t, X r (t) represents the radar positioning state vector at time t, X in (t) represents the inertial navigation positioning state vector at time t, X gps (t) represents the global navigation positioning state vector at time t, X m(t) represents the mobile observation positioning state vector at time t.

[0070] S602: Based on the state vector, construct observation equations for various positioning data:

[0071] z(t)=H(t)X(t)+V(t)

[0072]

[0073] Where z(t) represents the positioning measurement value at time t, H(t) represents the measurement matrix at time t, V(t) represents the measurement noise at time t, and z r (t) represents the radar positioning measurement value at time t, z in (t) represents the inertial navigation positioning measurement value at time t, z gps (t) represents the global navigation positioning measurement value at time t, z m (t) represents the mobile observation positioning measurement value at time t, H r (t) represents the measurement matrix of radar positioning at time t, H in (t) represents the measurement matrix of inertial navigation positioning at time t, H gps (t) represents the measurement matrix of global navigation positioning at time t, H m (t) represents the measurement matrix of mobile observation positioning at time t, V r (t) represents the radar positioning measurement noise at time t, V in (t) represents the inertial navigation positioning measurement noise at time t, V gps (t) represents the global navigation positioning measurement noise at time t, V m (t) represents the mobile observation positioning measurement noise at time t.

[0074] S603: Predict system state and error covariance through Kalman filter algorithm:

[0075]

[0076] P(t|t-1)=F(t-1)P(t-1)F T (t-1)+Q(t-1)

[0077] in, represents the state estimation vector at time t, F(t-1) represents the state transfer matrix at time t-1, represents the state prediction vector at time t-1, P(t|t-1) represents the error covariance estimation matrix at time t, P(t-1) represents the error covariance at time t-1, T represents the matrix transpose operation, and Q(t-1) represents the process noise covariance matrix at time t-1.

[0078] S604: Calculate Kalman gain:

[0079] K(t)=P(t|t-1)H T (t)[H(t)P(t|t-1)H T (t)+R(t)] -1

[0080] Among them, K(t) represents the Kalman gain at time t, H(t) represents the observation matrix at time t, and R(t) represents the observation noise covariance matrix at time t.

[0081] Optionally, the observation noise covariance matrix is ​​determined based on a confidence factor:

[0082]

[0083] Where R0 represents the baseline observation noise level, C r (t) represents the confidence factor of the radar positioning data at time t, C in (t) represents the confidence factor of the inertial navigation positioning data at time t, C gps (t) represents the confidence factor of the global navigation positioning data at time t, C m (t) represents the confidence factor of the mobile observation positioning data at time t.

[0084] It should be noted that if a data source continuously provides low-quality data, resulting in a low confidence factor, its observation noise will increase, and the system will automatically reduce its reliance on it, which will help to detect potential problems in a timely manner.

[0085] In the present invention, by associating the observation noise with the confidence factor, the weight of each data source in the Kalman filter can be dynamically adjusted according to the quality of different data sources. A source with a high confidence factor will have less observation noise and thus occupy a greater weight in the fusion.

[0086] S605: Update the system state and error covariance according to the Kalman gain:

[0087]

[0088] P(t)=(IK(t)H(t))P(t|t-1)

[0089] in, represents the state prediction vector at time t, P(t) represents the error covariance at time t, and I represents the identity matrix.

[0090] S606: Determine the fused positioning data of the ship according to the updated system status and confidence factor.

[0091] Optionally, the fused positioning data is specifically:

[0092]

[0093] Among them, X * (t) represents the fused positioning data, represents the radar positioning state prediction vector at time t, represents the inertial navigation positioning state prediction vector at time t, represents the global navigation positioning state prediction vector at time t, Represents the mobile observation positioning state prediction vector at time t.

[0094] In the present invention, the multi-source positioning data is weighted and fused by the Kalman filter algorithm based on the confidence factor, which can significantly improve the positioning accuracy of the ship and the robustness of the system, while optimizing computing resources, improving user trust, and supporting long-term stable performance. Such a comprehensive approach ensures that the ship positioning system can still work reliably and efficiently in complex and dynamic environments.

[0095] Furthermore, the setting of the process noise covariance matrix and the observation noise covariance matrix has an important influence on the prediction accuracy of the Kalman filter algorithm. In order to improve the prediction accuracy of the Kalman filter algorithm, the present invention adopts a flower pollination optimization algorithm to find the optimal process noise covariance matrix and the observation noise covariance matrix.

[0096] Specifically, the inverse of the mean square error loss is used as the fitness function of the flower pollination optimization algorithm;

[0097] Initialize flower individuals and transition probabilities. Each flower individual represents a feasible combination of process noise covariance matrix and observation noise covariance matrix. Each flower individual is composed of multiple dimensional components, and each component represents an element parameter in a process noise covariance matrix and observation noise covariance matrix.

[0098] Generate a random number randomly and determine whether the conversion probability is greater than the random number; if so, enter S4 for cross-pollination; otherwise, enter S5 for self-pollination.

[0099] Optionally, the conversion probability is specifically:

[0100]

[0101] Among them, P t represents the transition probability at the tth iteration, P0 represents the basic transition probability, q represents the Weber influence factor, γ represents the scale parameter, m represents the shape parameter, exp represents the exponential function with the natural constant e as the base, and T represents the maximum number of iterations.

[0102] It should be noted that in the initial iteration stage of the algorithm, the conversion probability is high, which is conducive to the algorithm to conduct extensive search (cross-pollination), expand the search space, improve the global exploration ability, and prevent the algorithm from falling into the local optimum too early. As the number of iterations increases, the conversion probability gradually decreases, and the algorithm will be more inclined to self-pollination, increasing the accuracy of local development. At this time, the algorithm pays more attention to the fine-tuning of the current solution, thereby enhancing the convergence of the algorithm and gradually approaching the optimal solution.

[0103] When cross-pollination occurs, the individual positions of flowers are updated according to the Levy flight mechanism:

[0104]

[0105] in, represents the position of the i-th flower individual at the t+1-th iteration, represents the position of the i-th flower individual at the t-th iteration, θ represents the step length influencing factor, L represents the step length, represents the global optimal solution at the tth iteration.

[0106]

[0107] Where Γ represents the standard Gamma function, λ represents the exponential parameter, and s represents the random step variable.

[0108] It should be noted that Lévy flight is a random step generation method with long-tail distribution characteristics, which can produce alternating large and small step movements. This mechanism allows individual flowers to perform a large range of jump searches in the solution space and avoid falling into local optimality.

[0109] When self-pollination occurs, the individual positions of flowers are updated according to the golden sine mechanism:

[0110]

[0111] x1=-π+2π(1-τ)

[0112] x2=-π+2πτ

[0113] in, represents the position of the jth flower individual randomly selected at the tth iteration, represents the position of the kth flower individual randomly selected at the tth iteration, r1 and r2 represent random numbers between 0 and 2π, x1 and x2 represent the self-pollination coefficients, and τ represents the golden section number

[0114] It should be noted that the golden sine mechanism combines the characteristics of the sine function and the golden section number, producing a fine-tuning effect with a smaller step size, which is conducive to the individual to conduct a fine search near the current solution and gradually approach the local optimal solution. This is especially helpful for local development in the later convergence stage.

[0115] Determine whether the fitness value of the flower individual at the position of the t+1th iteration is greater than the fitness value at the position of the tth iteration. If so, replace the position of the flower individual. Otherwise, the flower individual maintains the current position.

[0116] Update the global optimal solution.

[0117] Determine whether the current number of iterations has reached the maximum number of iterations. If so, output the process noise covariance matrix and the observation noise covariance matrix combination of the flower individual with the highest current fitness. Otherwise, return to continue iteration.

[0118] It should be noted that the flower pollination optimization algorithm is used to find the optimal process noise covariance matrix and observation noise covariance matrix to reduce the prediction error of the system and thus improve the overall prediction accuracy.

[0119] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0120] In the present invention, by integrating positioning data from different sources and fusing them through consistency check and Kalman filtering, the positioning accuracy and reliability are improved, the system's anti-interference ability is enhanced, and it adapts to the dynamically changing environment, making the ship's docking process safer and more flexible, and reducing the requirements on the operator's skills.

[0121] Reference Manual Attached Figure 3 , showing a structural schematic diagram of a ship docking positioning system based on multi-source positioning data fusion provided by the present invention.

[0122] The present invention also provides a ship docking positioning system 20 based on multi-source positioning data fusion, comprising:

[0123] Processor 201;

[0124] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, the ship docking positioning method based on multi-source positioning data fusion as described in the method embodiment is implemented.

[0125] The ship docking positioning system 20 based on multi-source positioning data fusion provided by the present invention can execute the above-mentioned ship docking positioning method based on multi-source positioning data fusion and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0126] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0127] In the present invention, by integrating positioning data from different sources and fusing them through consistency check and Kalman filtering, the positioning accuracy and reliability are improved, the system's anti-interference ability is enhanced, and it adapts to the dynamically changing environment, making the ship's docking process safer and more flexible, and reducing the requirements on the operator's skills.

[0128] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0129] There are a few points to note:

[0130] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0131] (2) For the sake of clarity, the thickness of a film or region in the drawings used to describe the embodiments of the present invention is enlarged or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a film, a region or a substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0132] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0133] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A ship docking positioning method based on multi-source positioning data fusion, characterized in that: include: S1: Acquire multi-source positioning data of the ship; S2: Project the multi-source positioning data into a unified local coordinate system through coordinate transformation; S3: Perform consistency check on the positioning data after coordinate transformation to determine the consistency factors of various positioning data; S4: Determine whether the consistency factor of various positioning data is greater than the consistency threshold. If so, retain it in the current measurement cycle; otherwise, remove it in the current measurement cycle; S5: determining confidence factors of various retained positioning data based on the historical performance of the retained positioning data; S6: Based on the confidence factors of various positioning data, weighted fusion is performed on multi-source positioning data through a Kalman filter algorithm to determine the fused positioning data of the ship.

2. The method for ship docking positioning based on multi-source positioning data fusion according to claim 1, characterized in that: The positioning data includes: radar positioning data, inertial navigation positioning data, global navigation positioning data and mobile observation positioning data.

3. The method for ship docking positioning based on multi-source positioning data fusion according to claim 1, characterized in that: The S3 is specifically: The positioning data after coordinate transformation is checked for consistency, and the consistency factors of various positioning data are determined based on the differences between the various positioning data.

4. The method for ship docking positioning based on multi-source positioning data fusion according to claim 3, characterized in that: The consistency factor is specifically: Among them, Y i represents the consistency factor of the i-th positioning data, y ij represents the consistency detection value between the i-th positioning data and the j-th positioning data, n represents the total number of positioning data categories, d ij represents the distance between the i-th positioning data and the j-th positioning data, d0 represents the distance threshold, z i represents the measured value of the i-th positioning data, z j Represents the measurement value of the j-th positioning data.

5. The method for ship docking positioning based on multi-source positioning data fusion according to claim 1, characterized in that: After S4, the method further includes: When the consistency factor of certain positioning data is less than the consistency threshold in a plurality of consecutive measurement cycles, an alarm is issued.

6. The method for ship docking positioning based on multi-source positioning data fusion according to claim 1, characterized in that: The S5 is specifically: The confidence factors of the various retained positioning data are determined based on the root mean square error of the retained positioning data.

7. The method for ship docking positioning based on multi-source positioning data fusion according to claim 6, characterized in that: The confidence factor is specifically: Among them, C i Represents the confidence factor of the i-th positioning data, RMSE i represents the root mean square error of the i-th positioning data, N represents the total number of categories of retained positioning data, z it represents the measured value of the i-th positioning data at time t, z t * represents the true value of the ship's position at time t, and T represents the total observation time.

8. The method for ship docking positioning based on multi-source positioning data fusion according to claim 1, characterized in that: The S6 specifically includes: S601: construct a state vector containing various positioning data; S602: constructing observation equations for various positioning data according to the state vector; S603: Predicting system state and error covariance through Kalman filter algorithm; S604: Calculate Kalman gain; S605: Update the system state and error covariance according to the Kalman gain; S606: Determine the fused positioning data of the ship according to the updated system status and confidence factor.

9. The method for ship docking positioning based on multi-source positioning data fusion according to claim 8, characterized in that: The fused positioning data is specifically: Among them, X * (t) represents the fused positioning data, represents the radar positioning state prediction vector at time t, represents the inertial navigation positioning state prediction vector at time t, represents the global navigation positioning state prediction vector at time t, represents the mobile observation positioning state prediction vector at time t, C r (t) represents the confidence factor of the radar positioning data at time t, C in (t) represents the confidence factor of the inertial navigation positioning data at time t, C gps (t) represents the confidence factor of the global navigation positioning data at time t, C m (t) represents the confidence factor of the mobile observation positioning data at time t.

10. A ship docking positioning system based on multi-source positioning data fusion, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the ship docking positioning method based on multi-source positioning data fusion as described in any one of claims 1 to 9 is implemented.

Images