Motion path feature analysis method and system based on data exploration
Through the combination of data exploration and target feature analysis network, the spacecraft motion path characteristics are extracted, which solves the problem of low accuracy and efficiency of spacecraft path analysis under complex conditions, realizes intelligent path analysis and optimization control, and improves the aerospace Equipment operation efficiency and safety.
Patent Information
- Application Number
- CN202410824862.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-25
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-06-25
AI Technical Summary
Spacecraft path analysis has problems of accuracy and low efficiency under complex conditions, especially due to the high dimensions of state variables, many constraints, strong coupling and uncertainty, it is difficult for the existing technology to achieve efficient path planning and control.
The motion path feature analysis method based on data exploration is adopted. By obtaining multi-dimensional motion data of aerospace equipment, the motion path features are extracted, and the target feature analysis network is used for strategy analysis, and a motion path analysis report is generated to assist in optimization control.
It realizes intelligent spacecraft path analysis under complex conditions, improves the accuracy and safety of the motion path planning and control strategies of aerospace equipment, and improves operational efficiency.
Smart Images

Figure CN119025843A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of aerospace science and technology, and in particular to a motion path feature analysis method and system based on data exploration. Background Art
[0002] In the field of aerospace science and technology, data exploration refers to the use of data analysis and mining techniques to explore and discover valuable information and patterns hidden in massive amounts of data. The aerospace field generates a large amount of data in daily operations and research and development, including telemetry data, image data, experimental data, etc. from satellites, rockets, spacecraft, sensors and other equipment. Through data exploration, researchers can use methods such as data mining, statistical analysis, and machine learning to extract useful information from these data, reveal potential patterns and patterns, and help improve the design, execution, and evaluation process of space missions. Data exploration has important application significance in the field of aerospace science and technology, and can help researchers better understand and use data, and improve work efficiency and research level.
[0003] In the context of data exploration, spacecraft path analysis can enable more accurate and efficient path planning and control. In related technologies, spacecraft path analysis often requires optimizing performance indicators such as fuel / energy consumption and mission time while satisfying complex constraints such as mission environment and spacecraft physical performance. This type of path analysis problem usually includes nonlinear optimal control problems with constraints. Spacecraft path analysis and control have the characteristics of high state variable dimension, multiple constraints, strong coupling and uncertainty, which poses certain challenges in both theoretical and technical implementation.
[0004] Therefore, it is urgent to design a new spacecraft path analysis scheme to improve the accuracy of spacecraft path analysis under complex conditions. Summary of the invention
[0005] In response to the technical problems existing in the prior art, the present invention provides a motion path feature analysis method and system based on data exploration, which is used to realize intelligent spacecraft path analysis under complex conditions, help optimize the motion path planning and control strategy of aerospace equipment, and improve the operating efficiency and safety of aerospace equipment.
[0006] In a first aspect, an embodiment of the present application provides a motion path feature analysis method based on data exploration, the method comprising:
[0007] Acquire multi-dimensional motion data of aerospace equipment in different environments; the multi-dimensional motion data at least includes: the position, motion speed, acceleration, and motion trajectory of the aerospace equipment;
[0008] Extracting motion path features of the aerospace equipment from the multi-dimensional motion data;
[0009] The motion path feature is input into a target feature analysis network, and a strategy analysis is performed on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment; the motion strategy feature at least includes: the correlation feature between the historical motion path of the aerospace equipment and the dynamic control mode adapted to the environment in which the aerospace equipment is located;
[0010] Based on the motion strategy characteristics, a motion path analysis report of the aerospace equipment is generated to assist in optimizing the control of the aerospace equipment.
[0011] In a second aspect, an embodiment of the present application provides a motion path feature analysis system based on data exploration, characterized in that the system includes the following units, wherein:
[0012] An acquisition unit is configured to acquire multi-dimensional motion data of aerospace equipment under different environments; the multi-dimensional motion data at least includes: a location, motion speed, acceleration, and motion trajectory of the aerospace equipment;
[0013] an extraction unit, configured to extract motion path features of the aerospace equipment from the multi-dimensional motion data;
[0014] The analysis unit is configured to input the motion path feature into a target feature analysis network, and perform a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment; the motion strategy feature at least includes: a correlation feature between the historical motion path of the aerospace equipment and a dynamic control mode adapted to the environment in which the aerospace equipment is located;
[0015] The generating unit is configured to generate a motion path analysis report of the aerospace equipment based on the motion strategy characteristics, so as to assist in optimizing the control of the aerospace equipment.
[0016] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:
[0017] at least one processor, memory, and input-output unit;
[0018] The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the motion path feature analysis method based on data exploration of the first aspect.
[0019] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes the motion path feature analysis method based on data exploration of the first aspect.
[0020] The beneficial effect of the present invention is that it provides a motion path feature analysis method and system based on data exploration. In this technical solution, first, the multi-dimensional motion data of aerospace equipment in different environments is obtained; the multi-dimensional motion data at least includes: the position of the aerospace equipment, the motion speed, the acceleration, and the motion trajectory. Then, the motion path characteristics of the aerospace equipment are extracted from the multi-dimensional motion data. Next, the motion path characteristics are input into the target feature analysis network, and the historical motion path of the aerospace equipment is strategically analyzed through the target feature analysis network to obtain the motion strategy characteristics of the aerospace equipment; the motion strategy characteristics at least include: the correlation characteristics between the historical motion path of the aerospace equipment and the dynamic control mode adapted to the environment in which the aerospace equipment is located. Finally, based on the motion strategy characteristics, a motion path analysis report of the aerospace equipment is generated to assist in the optimization control of the aerospace equipment.
[0021] The technical solution of this application, through in-depth exploration and analysis of the multi-dimensional motion data of aerospace equipment, combined with the strategic analysis of the target feature analysis network, can effectively extract key motion path features, reveal the laws and patterns in historical motion paths, and realize intelligent spacecraft path analysis under complex conditions, thereby providing more accurate and scientific support for the dynamic control of aerospace equipment, helping to optimize the motion path planning and control strategies of aerospace equipment, and improving the operating efficiency and safety of aerospace equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 It is a flow chart of a motion path feature analysis method based on data exploration according to an embodiment of the present application;
[0023] Figure 2 It is a structural schematic diagram of a motion path feature analysis system based on data exploration in an embodiment of the present application;
[0024] Figure 3 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application;
[0025] Figure 4 It is a structural schematic diagram of a medium device according to an embodiment of the present application. DETAILED DESCRIPTION
[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0027] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.
[0028] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.
[0029] In the context of data exploration, spacecraft path analysis can enable more accurate and efficient path planning and control. In related technologies, spacecraft path analysis often requires optimizing performance indicators such as fuel / energy consumption and mission time while satisfying complex constraints such as mission environment and spacecraft physical performance. This type of path analysis problem usually includes nonlinear optimal control problems with constraints. Spacecraft path analysis and control have the characteristics of high state variable dimension, multiple constraints, strong coupling and uncertainty, which poses certain challenges in both theoretical and technical implementation.
[0030] The embodiment of the present application provides a method and system for analyzing motion path characteristics based on data exploration. In this technical solution, first, the multi-dimensional motion data of aerospace equipment in different environments is obtained; the multi-dimensional motion data includes at least: the position of the aerospace equipment, the motion speed, the acceleration, and the motion trajectory. Then, the motion path characteristics of the aerospace equipment are extracted from the multi-dimensional motion data. Next, the motion path characteristics are input into the target feature analysis network, and the historical motion path of the aerospace equipment is strategically analyzed through the target feature analysis network to obtain the motion strategy characteristics of the aerospace equipment; the motion strategy characteristics include at least: the correlation characteristics between the historical motion path of the aerospace equipment and the dynamic control mode adapted to the environment in which the aerospace equipment is located. Finally, based on the motion strategy characteristics, a motion path analysis report of the aerospace equipment is generated to assist in the optimization control of the aerospace equipment.
[0031] The technical solution of this application, through in-depth exploration and analysis of the multi-dimensional motion data of aerospace equipment, combined with the strategic analysis of the target feature analysis network, can effectively extract key motion path features, reveal the laws and patterns in historical motion paths, and realize intelligent spacecraft path analysis under complex conditions, thereby providing more accurate and scientific support for the dynamic control of aerospace equipment, helping to optimize the motion path planning and control strategies of aerospace equipment, and improving the operating efficiency and safety of aerospace equipment.
[0032] The motion path feature analysis scheme based on data exploration provided by the embodiment of the present application can also be performed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a special device (such as a special terminal device with a motion path feature analysis system based on data exploration, etc.). The chips introduced in the above embodiments can also be carried in these electronic devices. Alternatively, these electronic devices can also be installed with a service program for executing a motion path feature analysis scheme based on data exploration.
[0033] Figure 1 A schematic diagram of a flow chart of a motion path feature analysis method based on data exploration provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:
[0034] 101, obtain multi-dimensional motion data of aerospace equipment in different environments;
[0035] 102, extracting motion path features of the aerospace equipment from the multi-dimensional motion data;
[0036] 103, inputting the motion path feature into a target feature analysis network, and performing a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain a motion strategy feature of the aerospace equipment; the motion strategy feature at least includes: a correlation feature between the historical motion path of the aerospace equipment and a dynamic control mode adapted to the environment in which the aerospace equipment is located;
[0037] 104. Based on the motion strategy characteristics, a motion path analysis report of the aerospace equipment is generated to assist in optimizing the control of the aerospace equipment.
[0038] In the embodiment of the present application, the multidimensional motion data at least includes: the location of the aerospace equipment, the speed of movement, the acceleration, and the motion trajectory. Specifically, in the embodiment of the present application, the multidimensional motion data includes the following key parameters: First, the location of the aerospace equipment: the current coordinate position information of the aerospace equipment, usually expressed in the form of longitude and latitude, altitude, etc. This parameter can help determine the specific location of the aerospace equipment, which is very important for path planning and position monitoring. Second, the speed of movement: the speed of the aerospace equipment in a specific time, usually expressed as the distance passed per unit time. The change in the speed of movement can affect the motion state and dynamic control scheme of the equipment, which is of great significance to the execution of the aerospace mission. Third, acceleration: the acceleration of the aerospace equipment during the movement process, which describes the speed and direction of the speed change. Acceleration information helps to analyze the motion characteristics of the equipment in a dynamic environment and provide more accurate control and planning basis. Fourth, the motion trajectory: the motion trajectory path information of the aerospace equipment over a period of time can be expressed by a set of coordinate points or a curve. The motion trajectory reflects the actual motion path of the equipment in space, which is crucial to the evaluation and optimization of the motion process. Based on the above parameters and comprehensive analysis of multi-dimensional motion data such as the position, speed, acceleration and trajectory of aerospace equipment, we can fully understand the movement of aerospace equipment in different environments, and provide a data basis and decision-making basis for formulating motion strategies and optimizing control.
[0039] As an optional embodiment, in 101, the following specific methods can be adopted to obtain the multi-dimensional motion data of aerospace equipment in different environments: First, obtain the real-time location information of aerospace equipment through the GPS positioning system, including data such as longitude, latitude and altitude, so as to accurately monitor and record the location of aerospace equipment. Second, use inertial measurement units, such as accelerometers and gyroscopes, to measure data such as acceleration and angular velocity of aerospace equipment in real time to reflect the motion state and changes of the equipment. Use sensors or monitoring devices carried by aerospace equipment to record the motion trajectory of the equipment in space, that is, the coordinate trajectory data of aerospace equipment at different time points. Third, install environmental sensors, such as weather stations, temperature sensors and humidity sensors, to monitor the meteorological and climate information of the environment in which the aerospace equipment is located in real time, and provide support for environmental feature analysis. Fourth, communication data recording. It is used to record the communication data between aerospace equipment and the ground command center, including command transmission, data feedback, etc., to understand the operating status and interaction of the equipment during the communication process.
[0040] The multi-dimensional motion data obtained through the above methods can fully display the motion characteristics and behaviors of aerospace equipment in different environments, and provide an important data basis and reference for subsequent motion path feature analysis and motion strategy optimization. These data will help to better understand the motion behavior of aerospace equipment and provide support for improving equipment operation, improving efficiency and ensuring safety.
[0041] As an optional embodiment, in 102, extracting the motion path features of the aerospace equipment from the multi-dimensional motion data includes the following steps:
[0042] 1021, performing image recognition processing on the environmental image data in the multi-dimensional motion data to obtain the route length and the curvature of the route path of the aerospace equipment in the current environment;
[0043] 1022, extracting real-time route information from the navigation system data of the multi-dimensional motion data; the real-time navigation information at least includes: real-time heading, real-time speed, and real-time position of the aerospace equipment;
[0044] 1023, extracting historical navigation records from the historical navigation data of the multi-dimensional motion data; the historical navigation records are used to analyze historical navigation behaviors and inertial motion laws of aerospace equipment;
[0045] 1024. Construct motion path characteristics of the aerospace equipment based on the route length, route curvature, real-time route information, and historical navigation records of the aerospace equipment; the motion path characteristics are used to represent the navigation state and behavior characteristics of the aerospace equipment in the current environment.
[0046] In this optional embodiment, extracting the motion path features of the aerospace equipment from the multi-dimensional motion data can be performed according to the following steps:
[0047] In 1021, image recognition processing is performed on the environmental image data in the multi-dimensional motion data to identify the environmental information around the aerospace equipment, and features such as the route length and the curvature of the route path are extracted to understand the impact of the current environment on the navigation path. In 1022, real-time route information such as the real-time heading, real-time speed and real-time position of the aerospace equipment is extracted from the navigation system data of the multi-dimensional motion data, and the motion state of the aerospace equipment at the current moment is monitored in real time. In 1023, the historical navigation records of the aerospace equipment are extracted from the historical navigation data of the multi-dimensional motion data, including the past navigation routes, behaviors and inertial motion laws, and the motion behavior patterns of the aerospace equipment are understood through historical data analysis. In 1024, based on the route length, curvature of the route path, real-time route information and historical navigation records of the aerospace equipment, the motion path features of the aerospace equipment are constructed to characterize the navigation state and behavior characteristics of the aerospace equipment in the current environment. These features can help understand the motion habits, environmental adaptability and path planning methods of the aerospace equipment.
[0048] Through the implementation of the above steps, the motion path characteristics of aerospace equipment can be effectively extracted, and the operating status and behavior characteristics of aerospace equipment in different environments can be comprehensively analyzed, providing an important reference for subsequent motion strategy analysis and control optimization. Such analysis helps to improve the path planning, operating efficiency and safety of aerospace equipment, and enhance the execution level and success rate of aerospace missions.
[0049] As an optional embodiment, it is assumed that the target feature analysis network includes at least the following structures: input layer, feature extraction layer, strategy analysis layer, and output layer. The input layer is the first layer of the neural network structure, which is responsible for receiving the original input data and passing it to the next layer. In this scenario, the input layer receives the motion path feature data of the aerospace equipment extracted from the multi-dimensional motion data, and uses these data as the input of the neural network. The feature extraction layer is a key part of the neural network, which is responsible for extracting meaningful features from the input data. In this example, the feature extraction layer processes and analyzes the input motion path feature data of the aerospace equipment, learns the feature information hidden in the data, and converts it into a higher-level representation. The strategy analysis layer performs further analysis and decision-making based on the extracted feature information. In this embodiment, the strategy analysis layer comprehensively considers the motion path feature data of the aerospace equipment, and formulates strategies based on the learned feature information to optimize the motion behavior of the aerospace equipment in different environments. The output layer is the last layer of the neural network structure, which is responsible for generating the final output result. In this scenario, the output layer converts the decision results made by the strategy analysis layer into highly readable information, presents the optimized motion path features, and provides guidance for the motion behavior of the aerospace equipment. Through the above introduction, the structure of the entire target feature analysis network is clear and concise. It receives raw data from the input layer, extracts important features through the feature extraction layer, makes decisions through the strategy analysis layer, and finally displays the optimized results through the output layer. This network structure helps to comprehensively analyze the motion path characteristics of aerospace equipment and provide support for the formulation of reasonable motion strategies and optimized control solutions.
[0050] Based on the above structure, in 103, the motion path feature is input into the target feature analysis network, and the historical motion path of the aerospace equipment is strategically analyzed by the target feature analysis network to obtain the motion strategy feature of the aerospace equipment, including the following steps:
[0051] 1031, receiving the motion path feature of the aerospace equipment as an input feature through the input layer;
[0052] 1032, extracting key information features from the input features through a feature extraction layer and a multi-layer neural network unit to identify multi-dimensional potential regular features in the motion path features; the multi-dimensional potential regular features at least include: path selection regular features, action sequence regular features, action plan regular features, and decision basis regular features;
[0053] 1033, analyzing the motion strategy law of the aerospace equipment according to the multi-dimensional potential law characteristics through the strategy analysis layer to obtain the target strategy of the aerospace equipment;
[0054] 1034. Generate motion strategy features of aerospace equipment based on the target strategy through the output layer; the motion strategy features at least include: path selection strategy features, action sequence strategy features, action plan strategy features, and decision basis strategy features.
[0055] In this optional embodiment, the strategy analysis of the historical motion path of the aerospace equipment is performed through the target feature analysis network to obtain the motion strategy features of the aerospace equipment. The following steps can be performed:
[0056] 1031, receives the motion path features of the aerospace equipment as input features through the input layer, and passes these features to the next layer for processing and analysis.
[0057] 1032, through the feature extraction layer, the multi-layer neural network unit is used to extract the key information features in the input features, and identify the multi-dimensional potential regular features in the motion path features, such as the regular features of path selection, the regular features of action sequence, the regular features of action plan, the regular features of decision basis, etc. These regular features can help understand the behavior patterns and decision basis in the historical motion paths of aerospace equipment.
[0058] 1033, through the strategy analysis layer, the movement strategy laws of aerospace equipment are analyzed according to the multi-dimensional potential law characteristics, and the target strategy of aerospace equipment is summarized from the historical movement path to help understand and predict the future movement behavior of aerospace equipment.
[0059] 1034, through the output layer, based on the obtained target strategy, the motion strategy features of the aerospace equipment are generated, including path selection strategy features, action sequence strategy features, action plan strategy features, decision basis strategy features, etc. These strategy features can provide guidance and reference for the motion planning and decision-making of future aerospace equipment.
[0060] For example, through such a target feature analysis network, the historical motion path data of aerospace equipment can be input into the network, and key features can be extracted through deep learning to analyze the motion strategy of aerospace equipment. In this way, the motion behavior pattern of aerospace equipment can be better understood, its future motion path selection and decision basis can be predicted, and more intelligent and effective support can be provided for the planning and execution of aerospace missions.
[0061] In the embodiment of the present application, further optionally, the network parameters of the target feature analysis network are adjusted by optimizing the loss function; wherein the optimized loss function is expressed as the following formula:
[0062]
[0063] Where S represents the adjustment parameter of the target feature analysis network, n represents the total number of parameter samples of the target feature analysis network, and y i1 represents the parameters to be adjusted of the target feature analysis network, y i2 represents the actual adjustment parameters of the target feature analysis network, represents the parameter adjustment variance distance of the target feature analysis network, Represents the parameter adjustment variance distance mean of the target feature analysis network.
[0064] By optimizing the loss function, the network parameters can be iteratively adjusted to minimize the loss function, thereby improving the performance and accuracy of the target feature analysis network. By continuously optimizing the network parameters, the network can better fit the data, improve generalization ability and accuracy, and thus better analyze the motion path characteristics of aerospace equipment and formulate effective motion strategy characteristics.
[0065] The beneficial effect of this method is to improve the performance and accuracy of the target feature analysis network, so that it can better adapt to the data characteristics of aerospace equipment and provide more accurate motion strategy analysis and prediction capabilities. Optimizing the loss function can help the network learn the laws and characteristics of data more effectively, thereby providing stronger support for the motion strategy analysis and optimization of aerospace equipment and improving the intelligence level of the entire system.
[0066] In the embodiment of the present application, further optionally, in 1033, the motion strategy law of the aerospace equipment is analyzed according to the multi-dimensional potential law characteristics through the strategy analysis layer to obtain the target strategy of the aerospace equipment, including the following steps;
[0067] 10331, cross-validating the multi-dimensional potential regularity characteristics;
[0068] 10332. Select the target strategy that matches the verification condition from the multi-dimensional potential regularity features according to the cross-validation result.
[0069] In the embodiment of the present application, further optionally, when the motion strategy law of aerospace equipment is analyzed according to the multidimensional potential law characteristics by the strategy analysis layer to obtain the target strategy of aerospace equipment, in step 10331, the multidimensional potential law characteristics are cross-validated. Cross-validation is an effective method for evaluating the generalization ability of a model. By dividing the data set into a training set and a validation set, the generalization effect of the model on new data can be verified. In this step, cross-validation of the multidimensional potential law characteristics can help ensure that the obtained target strategy has good generalization ability and applicability. In step 10332, based on the cross-validation results, a target strategy matching the validation conditions is selected from the multidimensional potential law characteristics. By matching the validation conditions, the target strategy that best meets the validation results can be selected, that is, by validating and analyzing the multidimensional law characteristics, the target strategy that best meets and is effective for the motion strategy law of aerospace equipment is finally determined. Through the above steps, the motion strategy law of aerospace equipment can be analyzed more comprehensively and objectively, the accuracy and reliability of the analysis results can be confirmed through cross-validation, and the matching target strategy can be selected based on the validation results. This can improve the credibility and applicability of the analysis results, provide more effective and reliable guidance for the formulation of aerospace equipment motion strategies, and thus enhance the performance and intelligence level of the entire aerospace system.
[0070] For example, in 103, it is assumed that there is a large amount of historical motion path data of aerospace equipment, including features such as path selection, action sequence, action plan, and decision basis. We input these data into the target feature analysis network, and finally obtain the motion strategy features of the aerospace equipment after steps such as feature extraction and strategy analysis. Through this process, we can understand the motion strategy laws and decision basis of aerospace equipment in different situations, thereby providing reference and guidance for the planning and execution of future aerospace missions.
[0071] In this way, strategic analysis of historical motion paths through the target feature analysis network can help aerospace equipment achieve intelligent decision support. The motion strategy characteristics analyzed based on historical data can provide aerospace equipment with more intelligent and accurate decision-making guidance, and improve the efficiency and accuracy of task execution. By analyzing historical motion paths and identifying multi-dimensional potential regular features, it can help optimize the motion planning of aerospace equipment. Understanding regular features such as path selection, action sequence, action plan, and decision-making basis can make motion planning more reasonable and effective, and improve the overall operating efficiency of aerospace equipment. By obtaining the motion strategy characteristics of aerospace equipment, the motion behavior of aerospace equipment can be better guided during the execution of aerospace missions. According to the target strategy obtained by analysis, aerospace equipment can better perform tasks, reduce error rates, improve execution results, and ensure the smooth completion of tasks.
[0072] Through this example, we can see that analyzing the historical motion path of aerospace equipment through the target feature analysis network and obtaining motion strategy characteristics will bring beneficial effects such as intelligent decision support, optimized motion planning, and improved mission execution results, thereby improving the execution efficiency and overall level of aerospace missions.
[0073] As an optional embodiment, after 103, the travel plan data of the aerospace equipment can also be obtained; the travel plan data at least includes: the route to be traveled by the aerospace equipment within a preset time period in the future; based on the route to be traveled, the environment in which the aerospace equipment will be located within a preset time period in the future is predicted to obtain the predicted environmental information of the aerospace equipment; based on the predicted environmental information and the motion strategy characteristics, a motion path adjustment strategy for the aerospace equipment is generated.
[0074] In this optional embodiment, by inputting the motion path characteristics of the aerospace equipment into the target feature analysis network for strategy analysis, after obtaining the motion strategy characteristics of the aerospace equipment, the travel plan data of the aerospace equipment can be further obtained. These travel plan data include the route to be traveled by the aerospace equipment within a preset time in the future, the predicted environmental information, and the motion path adjustment strategy generated based on the predicted environmental information and the motion strategy characteristics.
[0075] For example, it is assumed that the target feature analysis network is used to perform a strategy analysis on the historical motion path of the aerospace equipment, and the motion strategy features of the aerospace equipment are obtained. Then, these features are used to generate the travel plan data of the aerospace equipment. In this process, a time range can be preset to obtain the route to be traveled by the aerospace equipment within this time range, and the future environment of the aerospace equipment can be obtained by predicting the environmental information. Finally, the motion path adjustment strategy of the aerospace equipment is generated by combining the predicted environmental information and the motion strategy features.
[0076] In this way, intelligent path planning can be achieved by obtaining the travel plan data of aerospace equipment. According to the motion strategy characteristics obtained by analyzing the historical motion path and combining the predicted environmental information, a more intelligent and reasonable travel plan can be formulated for aerospace equipment to adapt to future environmental changes. Predicting the route and environmental information of aerospace equipment to be traveled within a preset time in the future helps to improve the accuracy of the prediction. By combining the predicted environmental information and the motion path adjustment strategy generated by the motion strategy characteristics, the future travel of aerospace equipment can be more accurately predicted, and the decision accuracy and execution effect can be improved. Generating a motion path adjustment strategy for aerospace equipment can help optimize the motion path. According to the predicted environmental information and motion strategy characteristics, the motion path of aerospace equipment is adjusted to make it more in line with the actual situation and mission requirements, and the motion efficiency and safety of aerospace equipment are improved. Through this example, it can be seen that the strategy analysis of the historical motion path through the target feature analysis network and the generation of the travel plan data of aerospace equipment will bring beneficial effects such as intelligent path planning, improved prediction accuracy and optimized motion path adjustment, thereby improving the execution efficiency and overall level of aerospace missions.
[0077] As an optional embodiment, in 104, a motion path analysis report of the aerospace equipment is generated based on the motion strategy characteristics to assist in optimizing the control of the aerospace equipment.
[0078] For example, suppose that the historical motion paths of aerospace equipment are strategically analyzed through the target feature analysis network, and the motion strategy features of the aerospace equipment are obtained. In this example, a detailed motion path analysis report can be generated based on these features. The report can include a summary of the motion strategy of the aerospace equipment, key decision basis, recommended action plan, etc. This report can assist in the optimization control of aerospace equipment and provide decision support and guidance.
[0079] In an embodiment of the present application, the motion path analysis report can provide relevant information and data support to help it make more informed decisions. The content such as the summary of motion strategy characteristics and action plan recommendations contained in the report can provide guidance to help it optimize the control of the motion path of aerospace equipment. By analyzing the motion path characteristics in the report, the motion strategy laws and decision-making basis of aerospace equipment can be understood, thereby optimizing the motion path planning. Through the key information and suggestions provided by the report, a more reasonable and effective motion path planning can be formulated to improve the efficiency and accuracy of aerospace equipment movement. By assisting in the optimized control of aerospace equipment, the control efficiency can be improved. Based on the information and suggestions provided by the motion path analysis report, the motion path of aerospace equipment can be more accurately monitored and adjusted to ensure that it moves according to the optimized plan, thereby improving the efficiency and accuracy of mission execution.
[0080] Through this example, we can see that generating a motion path analysis report for aerospace equipment based on motion strategy features can bring beneficial effects such as decision support and guidance, optimize motion path planning, and improve control efficiency, thereby improving the efficiency and quality of aerospace equipment motion control.
[0081] In an embodiment of the present application, a motion path feature analysis method based on data exploration is provided. Through in-depth exploration and analysis of the multi-dimensional motion data of aerospace equipment and combined with the strategy analysis of the target feature analysis network, it is possible to effectively extract key motion path features, reveal the laws and patterns in historical motion paths, and realize intelligent spacecraft path analysis under complex conditions, thereby providing more accurate and scientific support for the dynamic control of aerospace equipment, helping to optimize the motion path planning and control strategies of aerospace equipment, and improving the operating efficiency and safety of aerospace equipment.
[0082] In another embodiment of the present application, a motion path feature analysis system based on data exploration is also provided. Figure 2 The motion path feature analysis system based on data exploration includes the following units:
[0083] An acquisition unit is configured to acquire multi-dimensional motion data of aerospace equipment under different environments; the multi-dimensional motion data at least includes: a location, motion speed, acceleration, and motion trajectory of the aerospace equipment;
[0084] an extraction unit, configured to extract motion path features of the aerospace equipment from the multi-dimensional motion data;
[0085] The analysis unit is configured to input the motion path feature into a target feature analysis network, and perform a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment; the motion strategy feature at least includes: a correlation feature between the historical motion path of the aerospace equipment and a dynamic control mode adapted to the environment in which the aerospace equipment is located;
[0086] The generating unit is configured to generate a motion path analysis report of the aerospace equipment based on the motion strategy characteristics, so as to assist in optimizing the control of the aerospace equipment.
[0087] Further optionally, the extraction unit extracts the motion path features of the aerospace equipment from the multi-dimensional motion data, and is configured to:
[0088] Performing image recognition processing on the environmental image data in the multi-dimensional motion data to obtain the route length and the curvature of the route path of the aerospace equipment in the current environment;
[0089] Extracting real-time route information from the navigation system data of the multi-dimensional motion data; the real-time navigation information at least includes: the real-time heading, real-time speed, and real-time position of the aerospace equipment;
[0090] Extracting historical navigation records from the historical navigation data of the multi-dimensional motion data; the historical navigation records are used to analyze the historical navigation behavior and inertial motion law of aerospace equipment;
[0091] Based on the route length, route curvature, real-time route information and historical navigation records of the aerospace equipment, the motion path characteristics of the aerospace equipment are constructed; the motion path characteristics are used to represent the navigation status and behavior characteristics of the aerospace equipment in the current environment.
[0092] Further optionally, the target feature analysis network includes at least the following structures: an input layer, a feature extraction layer, a strategy analysis layer, and an output layer;
[0093] The analysis unit inputs the motion path feature into a target feature analysis network, and performs a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment, and is configured as follows:
[0094] Through the input layer, receiving the motion path features of the aerospace equipment as input features;
[0095] Through the feature extraction layer, the key information features in the input features are extracted through a multi-layer neural network unit to identify the multi-dimensional potential regular features in the motion path features; the multi-dimensional potential regular features at least include: path selection regular features, action sequence regular features, action plan regular features, and decision basis regular features;
[0096] Through the strategy analysis layer, the motion strategy law of the aerospace equipment is analyzed according to the multi-dimensional potential law characteristics to obtain the target strategy of the aerospace equipment;
[0097] Through the output layer, the motion strategy features of the aerospace equipment are generated based on the target strategy; the motion strategy features at least include: path selection strategy features, action sequence strategy features, action plan strategy features, and decision basis strategy features.
[0098] Wherein, further optionally, the network parameters of the target feature analysis network are adjusted by optimizing the loss function; wherein the optimized loss function is expressed as the following formula:
[0099]
[0100] Where S represents the adjustment parameter of the target feature analysis network, n represents the total number of parameter samples of the target feature analysis network, and y i1represents the parameters to be adjusted of the target feature analysis network, y i2 represents the actual adjustment parameters of the target feature analysis network, represents the parameter adjustment variance distance of the target feature analysis network, Represents the parameter adjustment variance distance mean of the target feature analysis network.
[0101] Further optionally, the analysis unit, through the strategy analysis layer, analyzes the motion strategy law of the aerospace equipment according to the multi-dimensional potential law characteristics to obtain the target strategy of the aerospace equipment, and is configured as follows;
[0102] Cross-validation of the multi-dimensional potential regularity characteristics;
[0103] According to the cross-validation result, the target strategy matching the validation condition is selected from the multi-dimensional potential regularity features.
[0104] Further optionally, after the analysis unit inputs the motion path feature into a target feature analysis network and performs a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment, the analysis unit is further configured to:
[0105] Acquiring travel plan data of the aerospace equipment; the travel plan data at least includes: a route to be traveled by the aerospace equipment within a preset time period in the future;
[0106] Based on the route to be traveled, predict the environment in which the aerospace equipment will be located within a preset time period in the future to obtain predicted environmental information of the aerospace equipment;
[0107] Based on the predicted environmental information and the motion strategy characteristics, a motion path adjustment strategy for the aerospace equipment is generated.
[0108] Among them, further optionally, the analysis unit predicts the environment in which the aerospace equipment will be located within a preset time period in the future based on the route to be traveled to obtain predicted environmental information of the aerospace equipment, and is configured to:
[0109] Extracting a plurality of path feature points from the route to be traveled to construct a path feature sequence to be analyzed;
[0110] Inputting the path feature sequence to be analyzed into the environmental prediction model to analyze the future environmental change law of the aerospace equipment between each path feature point;
[0111] Based on the future environmental change law, the environmental change law of the environment in which the aerospace equipment will be located within a preset time period in the future is predicted to obtain the predicted environmental information.
[0112] The system can implement various steps in the above method embodiment, which will not be expanded here.
[0113] In the embodiment of the present application, through the motion path feature analysis system based on data exploration, combined with the strategy analysis of the target feature analysis network, it is possible to effectively extract key motion path features, reveal the laws and patterns in historical motion paths, and realize intelligent spacecraft path analysis under complex conditions, thereby providing more accurate and scientific support for the dynamic control of aerospace equipment, helping to optimize the motion path planning and control strategies of aerospace equipment, and improving the operating efficiency and safety of aerospace equipment.
[0114] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 5102 and a computer program 511 stored in the memory 510 and executable on the processor 5102. When the processor 5102 executes the computer program 511, the following steps are implemented: obtaining multi-dimensional motion data of aerospace equipment in different environments; the multi-dimensional motion data at least includes: the position, motion speed, acceleration, and motion trajectory of the aerospace equipment; extracting the motion path characteristics of the aerospace equipment from the multi-dimensional motion data; inputting the motion path characteristics into a target feature analysis network, and performing a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy characteristics of the aerospace equipment; the motion strategy characteristics at least include: the correlation characteristics between the historical motion path of the aerospace equipment and the dynamic control mode adapted to the environment in which the aerospace equipment is located; based on the motion strategy characteristics, generating a motion path analysis report of the aerospace equipment to assist in the optimization control of the aerospace equipment.
[0115] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4As shown, this embodiment provides a computer-readable storage medium 600 on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: obtaining multi-dimensional motion data of aerospace equipment in different environments; the multi-dimensional motion data at least includes: the position, motion speed, acceleration, and motion trajectory of the aerospace equipment; extracting the motion path characteristics of the aerospace equipment from the multi-dimensional motion data; inputting the motion path characteristics into a target feature analysis network, and performing a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy characteristics of the aerospace equipment; the motion strategy characteristics at least include: the correlation characteristics between the historical motion path of the aerospace equipment and the dynamic control mode adapted to the environment in which the aerospace equipment is located; based on the motion strategy characteristics, generating a motion path analysis report for the aerospace equipment to assist in the optimal control of the aerospace equipment.
[0116] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0117] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0118] 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 flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 generate 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 flowchart and / or block diagram. 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.
[0119] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions 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.
[0121] 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.
[0122] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A motion path feature analysis method based on data exploration, characterized in that: The method comprises: Acquire multi-dimensional motion data of aerospace equipment in different environments; the multi-dimensional motion data at least includes: the position, motion speed, acceleration, and motion trajectory of the aerospace equipment; Extracting motion path features of the aerospace equipment from the multi-dimensional motion data; The motion path feature is input into a target feature analysis network, and a strategy analysis is performed on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment; the motion strategy feature at least includes: the correlation feature between the historical motion path of the aerospace equipment and the dynamic control mode adapted to the environment in which the aerospace equipment is located; Based on the motion strategy characteristics, a motion path analysis report of the aerospace equipment is generated to assist in optimizing the control of the aerospace equipment.
2. The motion path feature analysis method according to claim 1, characterized in that: The step of extracting the motion path features of the aerospace equipment from the multi-dimensional motion data comprises: Performing image recognition processing on the environmental image data in the multi-dimensional motion data to obtain the route length and the curvature of the route path of the aerospace equipment in the current environment; Extracting real-time route information from the navigation system data of the multi-dimensional motion data; the real-time navigation information at least includes: the real-time heading, real-time speed, and real-time position of the aerospace equipment; Extracting historical navigation records from the historical navigation data of the multi-dimensional motion data; the historical navigation records are used to analyze the historical navigation behavior and inertial motion law of aerospace equipment; Based on the route length, route curvature, real-time route information and historical navigation records of the aerospace equipment, the motion path characteristics of the aerospace equipment are constructed; the motion path characteristics are used to represent the navigation status and behavior characteristics of the aerospace equipment in the current environment.
3. The motion path feature analysis method according to claim 1, characterized in that: The target feature analysis network at least includes the following structures: input layer, feature extraction layer, strategy analysis layer, and output layer; The step of inputting the motion path feature into a target feature analysis network and performing a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment includes: Through the input layer, receiving the motion path features of the aerospace equipment as input features; Through the feature extraction layer, the key information features in the input features are extracted through a multi-layer neural network unit to identify the multi-dimensional potential regular features in the motion path features; the multi-dimensional potential regular features at least include: path selection regular features, action sequence regular features, action plan regular features, and decision basis regular features; Through the strategy analysis layer, the motion strategy law of the aerospace equipment is analyzed according to the multi-dimensional potential law characteristics to obtain the target strategy of the aerospace equipment; Through the output layer, the motion strategy features of the aerospace equipment are generated based on the target strategy; the motion strategy features at least include: path selection strategy features, action sequence strategy features, action plan strategy features, and decision basis strategy features.
4. The motion path feature analysis method according to claim 3, characterized in that: The network parameters of the target feature analysis network are adjusted by optimizing the loss function; wherein the optimized loss function is expressed as the following formula: Where S represents the adjustment parameter of the target feature analysis network, n represents the total number of parameter samples of the target feature analysis network, and y i1 represents the parameters to be adjusted of the target feature analysis network, y i2 represents the actual adjustment parameters of the target feature analysis network, represents the parameter adjustment variance distance of the target feature analysis network, Represents the parameter adjustment variance distance mean of the target feature analysis network.
5. The motion path feature analysis method according to claim 3, characterized in that: The strategy analysis layer analyzes the motion strategy law of the aerospace equipment according to the multi-dimensional potential law characteristics to obtain the target strategy of the aerospace equipment, including: Cross-validation of the multi-dimensional potential regularity characteristics; According to the cross-validation result, the target strategy matching the validation condition is selected from the multi-dimensional potential regularity features.
6. The motion path feature analysis method according to claim 1, characterized in that: After the motion path feature is input into the target feature analysis network, and the historical motion path of the aerospace equipment is strategically analyzed by the target feature analysis network to obtain the motion strategy feature of the aerospace equipment, the method further includes: Acquiring travel plan data of the aerospace equipment; the travel plan data at least includes: a route to be traveled by the aerospace equipment within a preset time period in the future; Predicting the environment in which the aerospace equipment will be located within a preset time period in the future based on the route to be traveled, so as to obtain predicted environmental information of the aerospace equipment; Based on the predicted environmental information and the motion strategy characteristics, a motion path adjustment strategy for the aerospace equipment is generated.
7. The motion path feature analysis method according to claim 6, characterized in that: The predicting of the environment in which the aerospace equipment will be located within a preset time period in the future based on the route to be traveled to obtain predicted environmental information of the aerospace equipment includes: Extracting a plurality of path feature points from the route to be traveled to construct a path feature sequence to be analyzed; Inputting the path feature sequence to be analyzed into the environmental prediction model to analyze the future environmental change law of the aerospace equipment between each path feature point; Based on the future environmental change law, the environmental change law of the environment in which the aerospace equipment will be located within a preset time period in the future is predicted to obtain the predicted environmental information.
8. A motion path feature analysis system based on data exploration, characterized in that: The system comprises the following units, wherein: An acquisition unit is configured to acquire multi-dimensional motion data of aerospace equipment under different environments; the multi-dimensional motion data at least includes: a location, motion speed, acceleration, and motion trajectory of the aerospace equipment; an extraction unit, configured to extract motion path features of the aerospace equipment from the multi-dimensional motion data; The analysis unit is configured to input the motion path feature into a target feature analysis network, and perform a strategy analysis on the historical motion path of the aerospace equipment through the target feature analysis network to obtain the motion strategy feature of the aerospace equipment; the motion strategy feature at least includes: a correlation feature between the historical motion path of the aerospace equipment and a dynamic control mode adapted to the environment in which the aerospace equipment is located; The generating unit is configured to generate a motion path analysis report of the aerospace equipment based on the motion strategy characteristics, so as to assist in optimizing the control of the aerospace equipment.
9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the motion path feature analysis method based on data exploration as described in any one of claims 1-7.
10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the motion path feature analysis method based on data exploration as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Mobile robot repositioning method based on deep learning
CN114858158A
Method and apparatus for generating multi-drone network cooperative operation plan based on reinforcement learning
US20230297859A1
