Steady-state identification method based on multi-factor and multi-dimensional characteristics of cold atom absolute gravimeter

Abstract

The present invention relates to the technical field related to atomic gravity measurement and provides a steady-state identification method based on the multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter. The method comprises: S1, at each steady-state level, collecting historical data of hull operation based on the cold atom absolute gravimeter, the historical data including the acceleration and inclination of the hull, and the atomic number data of the cold atom absolute gravimeter; S2, dividing the acceleration, inclination, and atomic number data into feature groups to form a multi-factor and multi-dimensional hull steady-state feature matrix; S3, establishing a hull steady-state identification model based on the hull steady-state feature matrix and a machine learning algorithm, and cross-validating the hull steady-state identification model; S4, identifying the hull steady-state based on the cross-validated hull steady-state identification model and the currently collected hull acceleration, inclination, and atomic number data. The present invention further improves the accuracy of hull stability identification based on the multi-factor and multi-dimensional information of the ship-borne cold atom absolute gravimeter.

Description

Technical Field

[0001] The present invention relates to the technical field related to atomic gravity measurement, and more specifically, to a steady-state identification method, system, electronic device and storage medium based on the multi-factor and multi-dimensional characteristics of a cold atomic absolute gravimeter. Background Art

[0002] The cold atom absolute gravimeter is a high-precision gravity measurement device based on the principle of atomic interferometry. Compared to traditional relative gravimeters, it offers advantages such as zero drift, zero mechanical wear, and the ability to provide long-term continuous gravity measurements. Generally, this type of equipment is complex, especially shipborne cold atom absolute gravimeters. As a ship moves, it inevitably experiences swaying and heaving, requiring dynamic compensation of each module using its inertial stabilization platform, triaxial acceleration data, and inclination data. Therefore, information about the ship's steady-state is crucial for the atomic gravimeter's high-precision measurements and for the safety of the ship's navigation.

[0003] Currently, various ships, while at sea, typically use inclination data (or roll, pitch, and settlement data from attitude sensors) to characterize the ship's lateral, fore-aft, and heaving vibrations in real time. This data is used to assess the ship's stability, external sea and wave conditions, and wind and wave conditions. These data are then used as feedback to ensure smoother and safer navigation and to survey and measure multiple factors, including gravity, in the waters where the ship is located. However, inclinometer observations are often instantaneous, while changes in the ship's attitude, such as pitch, roll, and settlement, typically occur over a specific period, not instantaneously. Therefore, using a single, instantaneous inclination data point to assess ship stability often results in significant errors, leading to misjudgments of navigational factors such as the ship's attitude, wind and wave conditions, and sea conditions. Shipborne cold-atom absolute gravimeters not only measure absolute gravity during navigation, but also provide real-time data from their various components, or a combination of these data points, that provide additional information on the operating status of the vessel. This information on ship stability is a key parameter that can be further explored.

[0004] Based on this, the present invention aims to provide a solution for further improving the identification of ship stability based on the multi-factor and multi-dimensional information of the ship-borne cold atomic absolute gravimeter in atomic gravity measurement technology. Summary of the Invention

[0005] In response to the shortcomings of existing methods for characterizing and identifying hull steady-state, the present invention provides a hull steady-state identification method based on the multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter. By extracting multi-factor information from the ship-borne cold atom absolute gravimeter and combining it with a machine learning algorithm, a more accurate judgment of the hull steady-state can be made.

[0006] According to a first aspect of the present invention, a method for steady-state identification based on multi-factor and multi-dimensional features of a cold atomic absolute gravimeter is provided, comprising the following steps:

[0007] S1, collecting historical data of the ship's operation based on a cold atom absolute gravimeter at each steady-state level, wherein the historical data includes acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter;

[0008] S2, dividing the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix;

[0009] S3, establishing a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and cross-validating the hull steady-state identification model;

[0010] S4, according to the cross-validated hull steady-state identification model, the hull steady-state is identified based on the currently collected hull acceleration, inclination and atomic number data.

[0011] On the basis of the above technical solution, the present invention can also make the following improvements.

[0012] Optionally, step S1 includes:

[0013] Based on the cold atomic absolute gravimeter, the three-axis acceleration data of the X, Y and Z axes of the hull are collected at various steady-state levels;

[0014] Based on the cold atomic absolute gravimeter, the inclination state of the X and Y axes of the hull at various steady-state levels is collected;

[0015] According to the interference and selected state output results of cold atoms, the total number of atoms and the number of three-state atoms of the cold atom absolute gravimeter when the hull is operating at various steady-state levels are collected.

[0016] Optionally, step S2 includes:

[0017] S201: For data collected at the same steady-state level, each axis acceleration data, each axis tilt state data, total number of atoms, and number of three-state atoms are treated as a type of single-element feature data, and each type of single-element feature data is divided into multiple feature groups according to a preset dimension to form multiple single-element multi-dimensional steady-state feature matrices.

[0018] S202, combining all single-element multidimensional steady-state characteristic matrices at the same steady-state level to obtain a multi-element multidimensional steady-state characteristic matrix at a single steady-state level;

[0019] S203, combining the multi-factor and multi-dimensional steady-state characteristic matrices at all steady-state levels to form a hull steady-state characteristic matrix.

[0020] Optionally, in step S201, the various types of single-element feature data are divided into multiple feature groups according to preset dimensions to form multiple single-element multi-dimensional steady-state feature matrices, including:

[0021] Arrange a certain type of single-factor feature data in columns;

[0022] Divide the single-element feature data of the current category into multiple feature groups according to the preset number of rows or time periods;

[0023] Arrange the multiple feature groups obtained by division into rows or columns to form a single-factor multi-dimensional steady-state feature matrix of the current category;

[0024] Traverse the single-factor feature data of all categories to obtain multiple single-factor multi-dimensional steady-state feature matrices.

[0025] Optionally, in step S201, the various types of single-element feature data are divided into multiple feature groups according to preset dimensions to form multiple single-element multi-dimensional steady-state feature matrices, including:

[0026] Arrange a certain type of single-factor feature data in rows;

[0027] Divide the single-element feature data of the current category into multiple feature groups according to the preset number of columns or time periods;

[0028] Arrange the multiple feature groups obtained by division into rows or columns to form a single-factor multi-dimensional steady-state feature matrix of the current category;

[0029] Traverse the single-factor feature data of all categories to obtain multiple single-factor multi-dimensional steady-state feature matrices.

[0030] Optionally, step S1 further includes: collecting hydrological and meteorological characteristic data of the waters where the ship is located, wherein the hydrological and meteorological characteristic data include one or more of heading speed, flow direction and velocity, wind direction and velocity, and surge conditions;

[0031] Step S201 also includes:

[0032] For the hydrological and meteorological characteristic data collected at the same steady-state level, the hydrological and meteorological characteristic data are treated as one or more categories of single-element characteristic data according to the number of items of the collected hydrological and meteorological characteristic data;

[0033] According to the preset dimensions, various types of single-element feature data are divided into multiple feature groups to form a single or multiple single-element multidimensional steady-state feature matrix corresponding to the number of hydrological and meteorological feature data items.

[0034] Optionally, in step S3, the machine learning algorithm is one of a linear discriminant analysis algorithm, a support vector machine algorithm, a random forest algorithm, a neural network algorithm, and a partial least squares algorithm; and the cross-validation method used is K-fold cross-validation, leave-one-out cross-validation, or leave-one-out cross-validation.

[0035] According to a second aspect of the present invention, there is provided a steady-state identification system based on multi-factor and multi-dimensional features of a cold atomic absolute gravimeter, comprising:

[0036] an acquisition module, configured to collect historical data of the ship's operation based on the cold atom absolute gravimeter at each steady-state level, the historical data including acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter;

[0037] a processing module, configured to divide the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix;

[0038] A construction module is used to establish a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and to cross-validate the hull steady-state identification model;

[0039] The identification module is used to identify the hull steady state based on the currently collected hull acceleration, inclination and atomic number data according to the cross-validated hull steady state identification model.

[0040] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the processor is configured to implement the steps of the above-mentioned steady-state identification method based on the multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter when executing a computer management program stored in the memory.

[0041] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the above-mentioned steady-state identification method based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter are implemented.

[0042] The present invention provides a steady-state identification method, system, electronic device, and storage medium based on the multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter. This method, combined with a machine learning algorithm, enables a more accurate assessment of a ship's stability based on the multi-factor and multi-dimensional information from the ship's cold atom absolute gravimeter. The present invention has the following beneficial effects:

[0043] 1. The present invention can use the multi-factor characteristics of the cold atomic absolute gravimeter to judge the steady state of the ship, which is more accurate than the traditional single-factor single-dimensional characteristics (such as the single inclination angle characteristic, acceleration characteristic or attitude characteristic at a certain moment);

[0044] 2. This invention groups and distinguishes multiple features, identifying the steady state of the ship by instantly judging data from a specific amount or duration in the past. This amount or duration far exceeds the ship's rolling and settling cycle, making the judgment results more continuous and reliable.

[0045] 3. This invention is the first to introduce the atomic number of the absolute gravity of cold atoms, which is easily affected by the hull posture, as a hull steady-state discrimination feature, thereby enhancing the diversity of the discrimination features and the accuracy of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic flow chart of a method for identifying steady-state of a ship based on multi-factor and multi-dimensional characteristics of a cold atomic absolute gravimeter provided by the present invention;

[0047] Figure 2 A schematic diagram of the multi-factor feature dimension transformation and combination process provided for a certain embodiment;

[0048] Figure 3 A schematic diagram of a ship steady-state identification model based on multi-factor, multi-dimensional features and a linear discriminant analysis algorithm and its cross-validation provided in a certain embodiment;

[0049] Figure 4 A comparison chart of the discrimination results of a hull steady-state identification model based on a single-element single-dimensional feature and a multi-element multi-dimensional feature provided in a certain embodiment;

[0050] Figure 5 A block diagram of a steady-state identification system based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter provided by the present invention;

[0051] Figure 6 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0052] Figure 7 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0053] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0054] Figure 1 The present invention provides a flow chart of a steady-state identification method based on the multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter, such as Figure 1 As shown, the method includes steps S1 to S4:

[0055] S1, collecting historical data of the ship's operation based on a cold atom absolute gravimeter at each steady-state level, wherein the historical data includes acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter;

[0056] S2, dividing the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix;

[0057] S3, establishing a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and cross-validating the hull steady-state identification model;

[0058] S4, according to the cross-validated hull steady-state identification model, the hull steady-state is identified based on the currently collected hull acceleration, inclination and atomic number data.

[0059] As can be understood, given the shortcomings of the background art, the present invention proposes a method for identifying ship hull stability based on the multi-factor, multi-dimensional characteristics of a cold atom absolute gravimeter. This method uses the multi-factor, multi-dimensional information from the shipboard cold atom absolute gravimeter, combined with a machine learning algorithm, to more accurately determine the hull's stability. The beneficial effects of this embodiment are primarily manifested in:

[0060] 1. This embodiment can use the multi-factor characteristics of the cold atomic absolute gravimeter to judge the steady state of the ship, which is more accurate than traditional single-factor, single-dimensional characteristics (such as a single inclination angle characteristic, acceleration characteristic, or attitude characteristic at a certain moment);

[0061] 2. This embodiment groups and distinguishes multiple features. It identifies the ship's steady state by instantaneously distinguishing data from a specific amount or duration in the past. This amount or duration far exceeds the ship's rolling and settling cycles, making the judgment results more continuous and reliable.

[0062] 3. This embodiment introduces for the first time the atomic number of the absolute gravity of cold atoms, which is easily affected by the hull posture, as a hull steady-state discrimination feature, thereby enhancing the diversity of the discrimination features and the accuracy of the results.

[0063] In a possible embodiment, step S1 includes sub-steps S101 to S103:

[0064] S101: Turn on the ship's onboard cold-atom absolute gravimeter and place it in a stable, normal operating state. The number of steady-state levels, d, is determined, and the ship is allowed to travel stably at one of the steady-state levels. The cold-atom absolute gravimeter is then confirmed to be operating normally on the ship at the current steady-state level.

[0065] S102, at the current steady-state level, based on the acceleration detection module of the cold atomic absolute gravimeter, collects the real-time three-axis acceleration data of the hull in the X, Y, and Z directions at each steady-state level, which are recorded as 、 、 , where m is the total number of rows of collected data, and n is the number of columns of collected data;

[0066] The inclination detection module based on the cold atomic absolute gravimeter collects the real-time inclination states of the X and Y axes of the hull at various steady-state levels, which are recorded as: 、 ;

[0067] According to the interference and selected state output results of the cold atoms in the cold atom absolute gravimeter, the total number of atoms and the number of three-state atoms in the cold atom absolute gravimeter in real time when the ship is running at the current steady-state level are collected. The total number of atoms is recorded as , the number of triple-state atoms is recorded as .

[0068] S103, traverse d steady-state levels to obtain the X, Y, and Z three-axis acceleration data of the hull operating at each steady-state level, as well as the X and Y axis inclination states and the total number of atoms and the three-state number of atoms of the cold atom absolute gravimeter.

[0069] It is understandable that the characteristic types of the hull obtained in step S1 include at least three-axis acceleration data / / , X / Y axis inclination status data / The total number of atoms is recorded as And the number of tri-state atoms is recorded as Each feature type can be used as a single-element feature in subsequent steps.

[0070] As a preferred option, in order to further improve the accuracy of hull steady-state identification, other hydrological and meteorological characteristic data of the waters where the ship is located, such as heading and speed, flow direction and speed, wind direction and speed, and surge conditions, can also be included in the list of optional features.

[0071] Therefore, in one possible implementation manner, step S1 further includes:

[0072] Collect hydrological and meteorological data for the waters where the vessel is located. This data may include one or more of the following: course and speed, current velocity, wind direction and speed, and surge conditions. This data will be used as feature elements for subsequent steps.

[0073] In a possible embodiment, step S2 includes sub-steps S201 to S203.

[0074] S201, such as Figure 2 As shown, for various types of feature data collected at the same steady-state level, each type of feature data (such as acceleration data of each axis, tilt state data of each axis, total number of atoms, number of three-state atoms, heading speed, flow velocity, wind direction and speed, and surge conditions) is respectively regarded as a type of single-element feature data, and each type of single-element feature data is divided into multiple feature groups according to preset dimensions to form multiple single-element multi-dimensional steady-state feature matrices.

[0075] More specifically, in one possible implementation, in step S201, each type of single-element feature data is divided into a plurality of feature groups according to a preset dimension to form a plurality of single-element multi-dimensional steady-state feature matrices, including:

[0076] Arrange a certain type of single-factor feature data in columns;

[0077] Divide the single-element feature data of the current category into multiple feature groups according to the preset number of rows or time periods;

[0078] Arrange the multiple feature groups obtained by division into rows or columns to form a single-factor multi-dimensional steady-state feature matrix of the current category;

[0079] Traverse the single-factor feature data of all categories to obtain multiple single-factor multi-dimensional steady-state feature matrices.

[0080] Alternatively, as another implementation method parallel to the previous embodiment, in step S201, the various types of single-element feature data are divided into multiple feature groups according to preset dimensions to form multiple single-element multi-dimensional steady-state feature matrices, including:

[0081] Arrange a certain type of single-factor feature data in rows;

[0082] Divide the single-element feature data of the current category into multiple feature groups according to the preset number of columns or time periods;

[0083] Arrange the multiple feature groups obtained by division into rows or columns to form a single-factor multi-dimensional steady-state feature matrix of the current category;

[0084] Traverse the single-factor feature data of all categories to obtain multiple single-factor multi-dimensional steady-state feature matrices.

[0085] In order to explain the process of generating a single-element multidimensional feature matrix in step S2 more clearly, we now combine Figure 2 Provide an example. Figure 2 The diagram shows the transformation and combination process of multiple feature dimensions at a single steady-state level. Figure 2First, we will illustrate the processing of 3-axis acceleration data with an example. / / Considered as three types of single-factor features, the acceleration data of each axis are arranged in columns, and three columns of acceleration data representing the three types of single-factor features are obtained. Then, according to the same grouping rule, each column of acceleration data is divided into feature groups with a row per group. Multiple feature groups formed by the same type of single-factor feature are arranged in rows or columns to form a single-factor multidimensional feature matrix with a dimension of , where c = m / a, a is the number of data rows in each feature group, m is the total number of data rows of the current single element feature, and c is the number of feature group columns obtained from the current single element feature. After processing the three-axis acceleration data using the above method, three types of single-element multidimensional feature matrices corresponding to the X, Y, and Z axis acceleration data are obtained. The collected X, Y axis inclination data, total number of atoms, and number of three-state atoms are then divided into feature groups according to the above steps, and the corresponding single-element multidimensional feature matrices are obtained, whose dimensions are all .

[0086] In consideration of the hydrological and meteorological characteristic data of the waters where the ship is located, step S201 further includes:

[0087] For the hydrological and meteorological characteristic data collected at the same steady-state level, the hydrological and meteorological characteristic data are treated as one or more categories of single-element characteristic data according to the number of items of the collected hydrological and meteorological characteristic data;

[0088] According to the preset dimensions, various types of single-element feature data are divided into multiple feature groups to form a single or multiple single-element multidimensional steady-state feature matrix corresponding to the number of hydrological and meteorological feature data items.

[0089] S202, combining all single-element multidimensional steady-state feature matrices at the same steady-state level, for example, by row, to obtain a multi-element multidimensional steady-state feature matrix containing all the element features considered at a single steady-state level. , where k is the type of single-element feature, is the dimension of the single-element multidimensional feature matrix; for example, the type k of single-element features considered is 7, including 3-axis acceleration data, X / Y axis tilt data, total number of atoms and number of three-state atoms, then the multi-element multidimensional steady-state feature matrix is .

[0090] S203, assuming that the number of steady-state levels is d, the The single-class single-element multi-dimensional feature groups are arranged in parallel to form a hull steady-state feature matrix containing all the element features considered at all steady-state levels. .

[0091] In a possible embodiment, in step S3, a hull steady-state identification model is established based on the multi-factor and multi-dimensional hull steady-state characteristic matrix and the machine learning algorithm obtained in step S2, and the model is cross-validated.

[0092] Among them, the machine learning algorithm is one of the linear discriminant analysis algorithm, support vector machine algorithm, random forest algorithm, neural network algorithm, and partial least squares algorithm; the cross-validation method adopted is K-fold cross-validation, leave-one-out cross-validation, or leave-one-out cross-validation.

[0093] Then, the multi-factor and multi-dimensional hull steady-state recognition model established in step S3 is used to predict the multi-factor hull steady-state characteristic data in the reserved test set, and the prediction result is output.

[0094] Finally, the current acceleration, inclination and atomic number data of the hull are collected. In step S4, the currently collected acceleration, inclination and atomic number data of the hull are input into the cross-validated hull steady-state identification model to output the hull steady-state identification result.

[0095] The technical effects of the present invention are now verified in conjunction with a specific implementation scenario.

[0096] S1, at each steady-state level, collect historical data of the ship's operation based on the cold atom absolute gravimeter. The historical data includes the acceleration and inclination of the ship, as well as the atomic number data of the cold atom absolute gravimeter. The specific operation steps are as follows:

[0097] First, turn on the ship's cold-atom absolute gravimeter and put it into a stable and normal working state;

[0098] Then, using the acceleration detection module of the cold atom absolute gravimeter, we collected acceleration data in the X, Y, and Z axes for one hour at a speed of 10 knots under different stable states (or sea conditions) from level 1 to 4. Since the data sampling rate of the cold atom absolute gravimeter is 0.6 (i.e., data is collected once every 0.6 seconds), a total of 6,000 data points can be collected, which are recorded as: 、 、 ;

[0099] At the same time, the inclinometer module of the cold atomic absolute gravimeter is used to collect the inclination states of the ship in the X and Y axes. The acquisition parameters and modes are the same as the acceleration data acquisition steps. Therefore, the obtained X and Y axis inclination state data can be recorded as: 、 ;

[0100] At the same time, based on the interference and selected state output results of the cold atoms, the total atomic number and the three-state atomic number of the cold atom absolute gravimeter are collected. The acquisition parameters and mode are the same as the acceleration data acquisition steps. The total atomic number and the three-state atomic number data can be recorded as: , .

[0101] S2, divide the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix. The specific operation steps are as follows:

[0102] First, the collected 3-axis acceleration data is arranged in columns, resulting in 3 columns of acceleration data. Each column of acceleration data is divided into feature groups with a = 10 rows per group, resulting in a total of c = 6000 / 10 = 600 feature groups. All feature groups are then arranged in parallel to form a single-element multidimensional feature matrix with the dimension of Then the collected X-axis tilt data, Y-axis tilt data, total number of atoms and number of three-state atoms are divided into feature groups according to the above steps, and the corresponding single-element multidimensional feature matrix is obtained, and its dimensions are ;

[0103] Secondly, all the single-factor multidimensional feature matrices obtained in the previous step are combined row by row to obtain the multi-factor multidimensional feature matrix at a single steady-state level (Right now ), the process is as follows Figure 2 As shown;

[0104] Then, from step S1, it can be seen that in this embodiment, there are d = 4 steady-state levels, and then all the steady-state levels are The single-class multi-dimensional feature groups are arranged in parallel, so the overall multi-factor multi-dimensional feature matrix under all steady-state levels can be obtained (i.e., the multi-factor and multi-dimensional hull steady-state characteristic matrix ).

[0105] S3: Based on the hull steady-state characteristic matrix and the machine learning algorithm, a hull steady-state identification model is established, and the hull steady-state identification model is cross-validated. The specific steps are as follows:

[0106] The overall multi-factor multi-dimensional feature matrix obtained in step S2 (i.e., the multi-factor and multi-dimensional hull steady-state characteristic matrix ) is input into the linear discriminant analysis algorithm, and a hull steady-state identification model based on the linear discriminant analysis algorithm is established. The model is cross-validated using a 6-fold cross-validation method. The process is as follows: Figure 3 As shown. After verification, the accuracy of cross-validation of the hull steady-state identification model is obtained, as shown in Figure 4 shown.

[0107] Figure 4 The accuracy of ship steady state recognition considering various single-factor features and multi-factor and multi-dimensional features was statistically analyzed. Figure 4 It can be seen that the accuracy of the hull steady-state identification method considering multi-factor and multi-dimensional features in the embodiment of the present invention is far superior to other solutions.

[0108] S4, collects the current acceleration, inclination and atomic number data of the hull, inputs the cross-validated hull steady-state identification model, and outputs the hull steady-state identification result.

[0109] In this step, the cross-validated hull steady-state recognition model established in step S3 is used to predict the 100 sets of test data from the test set, based on multi-factor, multi-dimensional features. The prediction results are output, as shown in Table 1. In Table 1, labels where the predicted level matches the standard level are considered correct, while labels with dark gray boxes indicate incorrect predictions. The results in Table 1 demonstrate that the steady-state recognition method based on multi-factor, multi-dimensional features of a cold atom absolute gravimeter, provided in this embodiment of the present invention, has a very high recognition accuracy.

[0110] Table 1 Test results

[0111]

[0112] The embodiment of the present invention provides a ship steady state identification method based on multi-factor and multi-dimensional features of cold atomic absolute gravimeter (referred to as multi-factor and multi-dimensional feature method) and a traditional identification method based on single-factor and single-dimensional features (referred to as single-dimensional method). Their identification results for the four types of ship steady states are as follows: Figure 4 As shown. Based on the verification results of the above examples, it can be seen that the seven hull steady-state characteristic factors used in the embodiments of the present invention, such as the X / Y / Z-axis acceleration characteristics, the X / Y-axis inclination characteristics, and the total atomic number and tri-state atomic number characteristics, have an accuracy rate of 29.7%, 46.8%, 45.2%, 29.4%, 46.8%, 33.5%, and 44.3% respectively when used as single features, which are all far lower than the 98.9% achieved by the multi-factor, multi-feature method in the embodiments of the present invention. Therefore, the hull steady-state identification method provided by the present invention has significant advantages over traditional identification methods.

[0113] Figure 5 The structure diagram of a steady-state identification system based on the multi-factor and multi-dimensional characteristics of a cold atomic absolute gravimeter provided by an embodiment of the present invention is as follows: Figure 5 As shown, a steady-state recognition system based on the multi-factor and multi-dimensional characteristics of a cold atomic absolute gravimeter includes an acquisition module, a processing module, a construction module, and an identification module, wherein:

[0114] an acquisition module, configured to collect historical data of the ship's operation based on the cold atom absolute gravimeter at each steady-state level, the historical data including acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter;

[0115] a processing module, configured to divide the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix;

[0116] A construction module is used to establish a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and to cross-validate the hull steady-state identification model;

[0117] The identification module is used to identify the hull steady state based on the currently collected hull acceleration, inclination and atomic number data according to the cross-validated hull steady state identification model.

[0118] It can be understood that the steady-state identification system based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter provided by the present invention corresponds to the steady-state identification method based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter provided in the aforementioned embodiments. The relevant technical features of the steady-state identification system based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter can refer to the relevant technical features of the steady-state identification method based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter, and will not be repeated here.

[0119] See also Figure 6 , Figure 6 Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, an embodiment of the present invention provides an electronic device 600, including a memory 610, a processor 620, and a computer program 611 stored in the memory 610 and executable on the processor 620. When the processor 620 executes the computer program 611, the following steps are implemented:

[0120] S1, collecting historical data of the ship's operation based on a cold atom absolute gravimeter at each steady-state level, wherein the historical data includes acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter;

[0121] S2, dividing the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix;

[0122] S3, establishing a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and cross-validating the hull steady-state identification model;

[0123] S4, according to the cross-validated hull steady-state identification model, the hull steady-state is identified based on the currently collected hull acceleration, inclination and atomic number data.

[0124] See also Figure 7 , Figure 7 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 7 As shown, this embodiment provides a computer-readable storage medium 700 on which a computer program 711 is stored. When the computer program 711 is executed by a processor, the following steps are implemented:

[0125] S1, collecting historical data of the ship's operation based on a cold atom absolute gravimeter at each steady-state level, wherein the historical data includes acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter;

[0126] S2, dividing the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix;

[0127] S3, establishing a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and cross-validating the hull steady-state identification model;

[0128] S4, according to the cross-validated hull steady-state identification model, the hull steady-state is identified based on the currently collected hull acceleration, inclination and atomic number data.

[0129] The embodiments of the present invention provide a method, system, and storage medium for steady-state identification based on the multi-factor and multi-dimensional characteristics of a cold atomic absolute gravimeter, which have the following advantages:

[0130] 1. The present invention can use the multi-factor characteristics of the cold atomic absolute gravimeter to judge the steady state of the ship, which is more accurate than the traditional single-factor single-dimensional characteristics (such as the single inclination angle characteristic, acceleration characteristic or attitude characteristic at a certain moment);

[0131] 2. This invention groups and distinguishes multiple features, identifying the steady state of the ship by instantly judging data from a specific amount or duration in the past. This amount or duration far exceeds the ship's rolling and settling cycle, making the judgment results more continuous and reliable.

[0132] 3. This invention is the first to introduce the atomic number of the absolute gravity of cold atoms, which is easily affected by the hull posture, as a hull steady-state discrimination feature, thereby enhancing the diversity of the discrimination features and the accuracy of the results.

[0133] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0134] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0138] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0139] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A steady-state identification method based on multi-factor and multi-dimensional characteristics of cold atom absolute gravimeter, characterized in that: The following steps are involved: S1, collecting historical data of the ship's operation based on the cold atom absolute gravimeter at each steady-state level, wherein the historical data includes acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter; S2, dividing the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix; S3, establishing a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and cross-validating the hull steady-state identification model; S4, according to the cross-validated hull steady-state identification model, the hull steady-state is identified based on the currently collected hull acceleration, inclination and atomic number data.

2. The method for steady-state identification based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter according to claim 1, characterized in that: Step S1 includes: Based on the cold atomic absolute gravimeter, the three-axis acceleration data of the X, Y and Z axes of the hull are collected at various steady-state levels; Based on the cold atomic absolute gravimeter, the inclination state of the X and Y axes of the hull at various steady-state levels is collected; According to the interference and selected state output results of cold atoms, the total number of atoms and the number of three-state atoms of the cold atom absolute gravimeter when the hull is operating at various steady-state levels are collected.

3. The method for steady-state identification based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter according to claim 2, characterized in that: Step S2 includes: S201: For data collected at the same steady-state level, each axis acceleration data, each axis tilt state data, total number of atoms, and number of three-state atoms are respectively regarded as a type of single-element feature data, and each type of single-element feature data is divided into multiple feature groups according to a preset dimension to form multiple single-element multi-dimensional steady-state feature matrices; S202, combining all single-element multidimensional steady-state characteristic matrices at the same steady-state level to obtain a multi-element multidimensional steady-state characteristic matrix at a single steady-state level; S203, combining the multi-factor and multi-dimensional steady-state characteristic matrices at all steady-state levels to form a hull steady-state characteristic matrix.

4. The method for steady-state identification based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter according to claim 3, characterized in that: In step S201, each type of single-element feature data is divided into multiple feature groups according to a preset dimension to form multiple single-element multi-dimensional steady-state feature matrices, including: Arrange a certain type of single-factor feature data in columns; Divide the single-element feature data of the current category into multiple feature groups according to the preset number of rows or time periods; Arrange the multiple feature groups obtained by division into rows or columns to form a single-factor multi-dimensional steady-state feature matrix of the current category; Traverse the single-factor feature data of all categories to obtain multiple single-factor multi-dimensional steady-state feature matrices.

5. The method for steady-state identification based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter according to claim 3, characterized in that: In step S201, each type of single-element feature data is divided into a plurality of feature groups according to a preset dimension to form a plurality of single-element multi-dimensional steady-state feature matrices, including: Arrange a certain type of single-factor feature data in rows; Divide the single-element feature data of the current category into multiple feature groups according to the preset number of columns or time periods; Arrange the multiple feature groups obtained by division into rows or columns to form a single-factor multi-dimensional steady-state feature matrix of the current category; Traverse the single-factor feature data of all categories to obtain multiple single-factor multi-dimensional steady-state feature matrices.

6. A steady-state identification method based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter according to any one of claims 3 to 5, characterized in that: Step S1 further includes: collecting hydrological and meteorological characteristic data of the waters where the ship is located, wherein the hydrological and meteorological characteristic data include one or more of heading speed, flow direction and velocity, wind direction and velocity, and surge conditions; Step S201 also includes: For the hydrological and meteorological characteristic data collected at the same steady-state level, the hydrological and meteorological characteristic data are treated as one or more categories of single-element characteristic data according to the number of items of the collected hydrological and meteorological characteristic data; According to the preset dimensions, various types of single-element feature data are divided into multiple feature groups to form a single or multiple single-element multidimensional steady-state feature matrix corresponding to the number of hydrological and meteorological feature data items.

7. A steady-state identification method based on multi-factor and multi-dimensional characteristics of a cold atom absolute gravimeter according to claim 4 or 5, characterized in that: In step S3, the machine learning algorithm is one of a linear discriminant analysis algorithm, a support vector machine algorithm, a random forest algorithm, a neural network algorithm, and a partial least squares algorithm; and the cross-validation method used is K-fold cross-validation, leave-one-out cross-validation, or leave-one-out cross-validation.

8. A steady-state identification system based on multi-factor and multi-dimensional characteristics of cold atom absolute gravimeter, characterized by: include: an acquisition module, configured to collect historical data of the ship's operation based on the cold atom absolute gravimeter at each steady-state level, the historical data including acceleration and inclination of the ship, and atomic number data of the cold atom absolute gravimeter; a processing module, configured to divide the acceleration, inclination and atomic number data into feature groups to form a multi-element and multi-dimensional hull steady-state feature matrix; A construction module is used to establish a hull steady-state identification model based on the hull steady-state characteristic matrix and a machine learning algorithm, and to cross-validate the hull steady-state identification model; The identification module is used to identify the hull steady state based on the currently collected hull acceleration, inclination and atomic number data according to the cross-validated hull steady state identification model.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to implement the steps of the steady-state identification method based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter as described in any one of claims 1 to 7 when executing the computer management program stored in the memory.

10. A computer-readable storage medium, characterized in that A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the steady-state identification method based on the multi-factor and multi-dimensional characteristics of the cold atom absolute gravimeter as described in any one of claims 1 to 7 are implemented.

Images