Outdoor environment dynamic modeling method and system of embedded training simulator
By acquiring multi-source sensor data for time series modeling and field strength parameter conversion, the problem that embedded training simulator cannot accurately reflect real-time environmental changes is solved, and dynamic modeling with high accuracy and adaptability is achieved.
Patent Information
- Application Number
- CN202510874617.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-08-01
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing embedded training simulators cannot accurately reflect real-time environment changes, resulting in dynamic response distortion, and cannot guarantee accuracy, consistency and adaptability.
By acquiring multi-source sensor data, performing time series modeling, converting it into field strength parameters, calculating the motion trajectory adjustment, controlling the mechanical joint response in real time, and establishing the correlation between environmental data and equipment performance.
The embedded training simulator is implemented to seamlessly reflect environmental changes, accurately capture subtle differences, and improve accuracy, consistency and adaptability.
Smart Images
Figure CN120408561A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of training simulators, and in particular, to a method and system for dynamically modeling the outdoor environment of an embedded training simulator. Background Art
[0002] The dynamic modeling of the outdoor environment of an embedded training simulator is a technology that combines real-time simulation, physical engines, environmental perception, and data fusion, and can provide a high-fidelity and dynamically changing virtual outdoor environment for the training system. By simulating dynamic characteristics such as real-world weather changes, terrain changes, moving targets, and sensor interference, the authenticity and effectiveness of training can be improved. However, in the existing methods for dynamically modeling the outdoor environment of embedded training simulators, due to equipment limitations and the unpredictability and complexity of environmental changes, it is impossible to ensure that the embedded training simulator can seamlessly reflect the continuous process of environmental changes and accurately capture and reflect the subtle differences in environmental changes.
[0003] Therefore, the existing modeling of embedded training simulators relies on preset environmental parameters for static modeling, making it difficult to reflect the dynamic characteristics of real-time changes. At the same time, the impact of environmental factors on the mechanical performance of the equipment is not quantified, resulting in distorted dynamic responses of the embedded training simulator and unable to guarantee the accuracy, consistency, adaptability, and predictability of the embedded training simulator. Summary of the Invention
[0004] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a method for dynamically modeling the outdoor environment of an embedded training simulator, including: Obtaining outdoor environment data of the embedded training simulator collected by multi-source sensors; Performing time series modeling on the outdoor environment data to obtain a sequence of dynamic environment parameters; Converting each dynamic environment parameter in the sequence of dynamic environment parameters into a field strength parameter, and calculating the adjustment amount of the movement trajectory of the embedded training simulator based on the field strength parameter; According to the adjustment amount of the movement trajectory, controlling the mechanical joint response of the embedded training simulator in real time, establishing the correlation between the outdoor environment data and the performance parameters of the embedded training simulator, and completing the dynamic modeling of the outdoor environment of the embedded training simulator.
[0005] Preferably, converting the dynamic environment parameter in the sequence of dynamic environment parameters into a field strength parameter includes: Based on historical environmental statistical data, obtaining the reference value range of the outdoor environment data; Using a machine learning model to establish the mapping relationship between the environmental parameters and the equipment performance indicators based on the reference value range; Based on the mapping relationship, converting the dynamic environment parameter into a field strength parameter through a field strength conversion strategy.
[0006] Preferably, the field strength parameter includes an electromagnetic field strength parameter or a mechanical field strength parameter; The calculation method of the field strength conversion strategy is as follows:
[0007] Wherein, is the field strength parameter, is the temperature, is the reference temperature, is the temperature calibration coefficient based on the device characteristics, is the humidity, is the reference humidity, is the humidity calibration coefficient based on the device characteristics, is the wind speed, is the wind speed calibration coefficient based on the device characteristics.
[0008] Preferably, time series modeling is performed on the outdoor environmental data to obtain a dynamic environmental parameter sequence, including: Using a long short-term memory network (LSTM) to extract the long-term and short-term dependence features of the outdoor environmental data; Detecting the periodic change pattern of the outdoor environmental data through an autoregressive integrated moving average model (ARIMA); Generating a dynamic environmental parameter sequence with continuous timestamps based on the long-term and short-term dependence features and the periodic change pattern of the outdoor environmental data.
[0009] Preferably, after obtaining the outdoor environmental data of the embedded training simulator collected by the multi-source sensors and before converting each dynamic environmental parameter in the dynamic environmental parameter sequence into a field strength parameter, the method further includes: Accessing meteorological prediction data to generate the probability distribution of environmental parameters within a future time window; Simulating the device response under multiple extreme scenarios through the Monte Carlo method; After calculating the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter, the method further includes: Combining the device response to update the motion trajectory adjustment amount of the embedded training simulator to obtain the updated motion trajectory adjustment amount.
[0010] Preferably, after obtaining the outdoor environmental data of the embedded training simulator collected by the multi-source sensors, the method further includes: preprocessing the outdoor environmental data; The steps of the preprocessing include: Fusing the outdoor environmental data of the embedded training simulator collected by the multi-source sensors through a spatio-temporal alignment algorithm; Adopting an environmental mutation detection algorithm with a sliding window; An adaptive calibration algorithm based on dynamic parameters compensates for sensor noise and transmission delay to obtain preprocessed outdoor environment data.
[0011] Preferably, the mechanical joint response of the embedded training simulator is controlled in real time according to the amount of movement trajectory adjustment, including: According to the amount of movement trajectory adjustment, combined with the mechanical joint adjustment strategy, obtain the dynamic joint damping coefficient; Based on the dynamic joint damping coefficient, establish a PID control model of mechanical joint angle - environmental parameters; Use the fuzzy logic algorithm to process, based on the PID control model, to obtain the mechanical joint response of the embedded training simulator; The calculation formula of the mechanical joint adjustment strategy is as follows:
[0012] Among them, is the real-time damping coefficient, is the reference damping value, is the temperature change sensitivity coefficient, is the total time, is the current moment.
[0013] Based on the same inventive concept, the present invention also provides an outdoor environment dynamic modeling system for an embedded training simulator, including: An outdoor environment data acquisition module for acquiring outdoor environment data of the embedded training simulator collected by multi-source sensors; An environmental parameter sequence acquisition module for performing time series modeling on the outdoor environment data to obtain a dynamic environmental parameter sequence; A trajectory adjustment amount calculation module for converting each dynamic environmental parameter in the dynamic environmental parameter sequence into a field strength parameter and calculating the movement trajectory adjustment amount of the embedded training simulator based on the field strength parameter; A dynamic modeling module for controlling the mechanical joint response of the embedded training simulator in real time according to the movement trajectory adjustment amount, establishing an association relationship between the outdoor environment data and the performance parameters of the embedded training simulator, and completing the outdoor environment dynamic modeling of the embedded training simulator.
[0014] Preferably, the trajectory adjustment amount calculation module is specifically used for: Based on historical environmental statistical data, obtain the reference value range of outdoor environment data; Use a machine learning model to establish a mapping relationship between environmental parameters and device performance indicators based on the reference value range; Based on the mapping relationship, convert the dynamic environmental parameters into field strength parameters through the field strength conversion strategy.
[0015] Preferably, the field strength parameter includes an electromagnetic field strength parameter or a mechanical field strength parameter; The calculation method of the field strength conversion strategy is as follows:
[0016] where, is the field strength parameter, is the temperature, is the reference temperature, is the temperature calibration coefficient based on the device characteristics, is the humidity, is the reference humidity, is the humidity calibration coefficient based on the device characteristics, is the wind speed, is the wind speed calibration coefficient based on the device characteristics.
[0017] Preferably, the environmental parameter sequence acquisition module is specifically configured to: Extract the long-term and short-term dependence features of the outdoor environmental data by using the long short-term memory network LSTM; Detect the periodic change pattern of the outdoor environmental data through the autoregressive integrated moving average model ARIMA; Generate a dynamic environmental parameter sequence with continuous time stamps based on the long-term and short-term dependence features and the periodic change pattern of the outdoor environmental data.
[0018] Preferably, the system further includes a meteorological prediction module, which is specifically configured to: Access meteorological prediction data and generate the probability distribution of environmental parameters within a future time window; Simulate the device response under multiple extreme scenarios through the Monte Carlo method; The trajectory adjustment amount calculation module is further configured to: Combine the device response to update the motion trajectory adjustment amount of the embedded training simulator to obtain the updated motion trajectory adjustment amount.
[0019] Preferably, the system further includes an outdoor environmental data preprocessing module, which is specifically configured to: Fuse the outdoor environmental data of the embedded training simulator collected by multiple sensors through a spatio-temporal alignment algorithm; Adopt an environmental mutation detection algorithm with a sliding window; Based on an adaptive calibration algorithm with dynamic parameters, compensate for sensor noise and transmission delay to obtain the preprocessed outdoor environmental data.
[0020] Preferably, the dynamic modeling module is specifically configured to: According to the motion trajectory adjustment amount, combine the mechanical joint adjustment strategy to obtain the dynamic joint damping coefficient; Based on the dynamic joint damping coefficient, a PID control model of the mechanical joint angle - environmental parameters is established; Processed by the fuzzy logic algorithm, based on the PID control model, the mechanical joint response of the embedded training simulator is obtained; The calculation formula of the mechanical joint adjustment strategy is as follows:
[0021] Wherein, is the real - time damping coefficient, is the reference damping value, is the temperature change sensitivity coefficient, is the total time, is the current moment.
[0022] Based on the same inventive concept, the present invention also provides an electronic device, including: at least one processor and a memory; the memory and the processor are connected by a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the outdoor environment dynamic modeling method of an embedded training simulator as described above is implemented.
[0023] Based on the same inventive concept, the present invention also provides a readable storage medium, on which an execution program is stored, and when the execution program is executed, the outdoor environment dynamic modeling method of an embedded training simulator as described above is implemented.
[0024] Compared with the closest prior art, the beneficial effects of the present invention are as follows: The present invention provides an outdoor environment dynamic modeling method for an embedded training simulator, including: acquiring outdoor environment data of the embedded training simulator collected by multi - source sensors; performing time - series modeling on the outdoor environment data to obtain a dynamic environment parameter sequence; converting each dynamic environment parameter in the dynamic environment parameter sequence into a field strength parameter, calculating the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter; controlling the mechanical joint response of the embedded training simulator in real - time according to the motion trajectory adjustment amount, establishing an association relationship between the outdoor environment data and the performance parameters of the embedded training simulator, and completing the outdoor environment dynamic modeling of the embedded training simulator. The present invention, through time - series modeling, ensures that the embedded training simulator seamlessly reflects the continuous process of environmental changes; through dynamic environment parameters, accurately captures and reflects the subtle differences in environmental changes; and then comprehensively considers environmental factors and device characteristics to establish a refined mathematical model and an efficient calculation mechanism, balancing the accuracy, consistency, adaptability, and predictability of the embedded training simulator. Description of the Drawings
[0025] Figure 1Schematic flowchart of a method for dynamically modeling the outdoor environment of an embedded training simulator provided by the present invention; Figure 2 Structural diagram of a system for dynamically modeling the outdoor environment of an embedded training simulator provided by the present invention; Figure 3 Schematic diagram of an electronic device provided by the present invention. Detailed implementation manners
[0026] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention, and should not be construed as limiting the present invention.
[0027] Embodiment 1: The present invention provides a method for dynamically modeling the outdoor environment of an embedded training simulator. Specifically, Figure 1 Schematic flowchart of a method for dynamically modeling the outdoor environment of an embedded training simulator provided by an embodiment of the present invention. As shown in the figure, the method includes the following steps: S1: Obtain outdoor environment data of the embedded training simulator collected by multi-source sensors; S2: Perform time series modeling on the outdoor environment data to obtain a sequence of dynamic environment parameters; S3: Convert each dynamic environment parameter in the sequence of dynamic environment parameters into a field strength parameter, and calculate the movement trajectory adjustment amount of the embedded training simulator based on the field strength parameter; S4: Real-time control the mechanical joint response of the embedded training simulator according to the movement trajectory adjustment amount, establish the correlation between the outdoor environment data and the performance parameters of the embedded training simulator, and complete the dynamic modeling of the outdoor environment of the embedded training simulator.
[0028] Through time series modeling, the present invention ensures that the embedded training simulator seamlessly reflects the continuous process of environmental changes; through dynamic environment parameters, it accurately captures and reflects the subtle differences in environmental changes; and then comprehensively considers environmental factors and device characteristics to establish a refined mathematical model and an efficient calculation mechanism, balancing the accuracy, consistency, adaptability, and predictability of the embedded training simulator.
[0029] First, in order to obtain accurate and real-time outdoor environment data, the present invention uses multi-source sensors to collect outdoor environment data of the embedded training simulator. Among them, the multi-source sensors used include but are not limited to: temperature and humidity composite sensors, three-dimensional ultrasonic anemometers, and multi-spectral environmental optical sensors. The collected outdoor environment data includes but is not limited to: environmental data such as temperature, humidity, wind speed, and light intensity.
[0030] After obtaining the outdoor environmental data, in some alternative embodiments, the outdoor environmental data can also be preprocessed to improve the data accuracy. The specific preprocessing steps include: fusing the outdoor environmental data of the embedded training simulator collected by multi-source sensors through a spatio-temporal alignment algorithm; adopting an environmental mutation detection algorithm with a sliding window; and an adaptive calibration algorithm based on dynamic parameters to compensate for sensor noise and transmission delay, so as to obtain the preprocessed outdoor environmental data.
[0031] Among them, fusing the outdoor environmental data through a spatio-temporal alignment algorithm can solve the data delay problem between multi-source sensors. A sliding window with a fixed time window length can be used to detect mutation events, and an anomaly flag is triggered when the data difference between adjacent windows exceeds a preset threshold.
[0032] In some alternative embodiments, after obtaining the outdoor environmental data of the embedded training simulator collected by multi-source sensors, in order to further improve the accuracy of the embedded training simulator, meteorological prediction data can also be accessed to predict future outdoor environmental data. Specifically, access the meteorological prediction data to generate the probability distribution of environmental parameters within a future time window; simulate the device responses under various extreme scenarios through the Monte Carlo method.
[0033] In a specific embodiment, access the Smart Weather API of the meteorological bureau to obtain the short-term forecast for the next 30 minutes and generate a wind speed probability distribution histogram; then randomly sample 100 parameter combinations (temperature, wind speed, humidity, etc.) of the outdoor environmental data, simulate the device responses under various extreme scenarios through the Monte Carlo method, and pre-adjust the possible movement trajectory parameters of the embedded training simulator and the sensitivity thresholds of the multi-source sensors.
[0034] After obtaining the outdoor environmental data, perform time series modeling on the outdoor environmental data to obtain a dynamic environmental parameter sequence. Specifically, use a long short-term memory network (LSTM) to extract the long-term and short-term dependence features of the outdoor environmental data; detect the periodic change patterns of the outdoor environmental data through an autoregressive integrated moving average model (ARIMA); generate a dynamic environmental parameter sequence with continuous timestamps based on the long-term and short-term dependence features and the periodic change patterns of the outdoor environmental data. In the present invention, by using the established time series model, it can be ensured that the embedded training simulator can seamlessly reflect the continuous process of environmental changes.
[0035] After obtaining the dynamic environmental parameter sequence, convert each dynamic environmental parameter in the dynamic environmental parameter sequence into a field strength parameter, and calculate the movement trajectory adjustment amount of the embedded training simulator based on the field strength parameter.
[0036] Convert the dynamic environment parameters in the dynamic environment parameter sequence into field strength parameters, including: obtaining the reference value range of outdoor environment data based on historical environment statistical data; using a machine learning model to establish a mapping relationship between environment parameters and device performance indicators based on the reference value range; and converting the dynamic environment parameters into field strength parameters through a field strength conversion strategy based on the mapping relationship.
[0037] Among them, the field strength parameters include electromagnetic field strength parameters or mechanical field strength parameters; The calculation method of the field strength conversion strategy is as follows:
[0038] Among them, is the field strength parameter, is the temperature, is the reference temperature, is the temperature calibration coefficient based on device characteristics, is the humidity, is the reference humidity, is the humidity calibration coefficient based on device characteristics, is the wind speed, is the wind speed calibration coefficient based on device characteristics.
[0039] In the present invention, the outdoor environment data considered includes temperature, humidity and wind speed. Therefore, the established field strength conversion strategy is a formula related to temperature, humidity and wind speed. It can be understood that those skilled in the art can add other outdoor environment data to the field strength conversion strategy if other outdoor environment data is considered when implementing this modeling method, and no limitation is made here.
[0040] Specifically, statistical analysis can be performed on historical environment data to extract the mean and variance of temperature, humidity, etc. as reference references; a machine learning model is used to establish a mapping relationship between environment parameters and device performance indicators, and based on the mapping relationship, the dynamic environment parameters are converted into field strength parameters through the field strength conversion strategy.
[0041] In some optional implementation manners, the noise and delay problems of multi-source sensors can be further compensated by an adaptive calibration algorithm for dynamic parameters.
[0042] In a specific implementation manner, an embedded training simulator is run in a standard laboratory environment (temperature 25°C ± 0.5°C, humidity 50% ± 3%), and the device performance indicators are recorded as the reference response curve. Furthermore, the specific field strength parameters in this scenario are calculated through the field strength conversion strategy:
[0043] Among them, is the field strength parameter, is temperature, is humidity, is wind speed, the reference temperature is 25 °C, the temperature calibration coefficient based on the device characteristics is 0.78, the reference humidity is 50%, the humidity calibration coefficient based on the device characteristics is 2.15, and the wind speed calibration coefficient based on the device characteristics is / °C.
[0044] When the real-time humidity is, enable the anti-saturation correction strategy for correction. The specific anti-saturation correction strategy is as follows:
[0045] Among them, is the field strength correction parameter, is the field strength parameter, is the humidity, is the anti-saturation correction factor.
[0046] Convert each dynamic environment parameter in the dynamic environment parameter sequence into a field strength parameter to obtain multiple field strength parameters. Calculate the motion trajectory adjustment amount of the embedded training simulator based on the multiple field strength parameters.
[0047] When accessing meteorological prediction data, after calculating the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter, it further includes: combining the device response to update the motion trajectory adjustment amount of the embedded training simulator to obtain the updated motion trajectory adjustment amount.
[0048] After calculating the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter, control the mechanical joint response of the embedded training simulator in real time according to the motion trajectory adjustment amount, establish the correlation relationship between the outdoor environment data and the performance parameters of the embedded training simulator, and complete the outdoor environment dynamic modeling of the embedded training simulator.
[0049] Specifically, controlling the mechanical joint response of the embedded training simulator in real time according to the motion trajectory adjustment amount includes: obtaining the dynamic joint damping coefficient according to the motion trajectory adjustment amount in combination with the mechanical joint adjustment strategy; establishing a PID control model of the mechanical joint angle - environment parameter based on the dynamic joint damping coefficient; and obtaining the mechanical joint response of the embedded training simulator by using the fuzzy logic algorithm and based on the PID control model.
[0050] The calculation formula of the mechanical joint adjustment strategy is as follows:
[0051] Among them, is the real-time damping coefficient, is the reference damping value, is the temperature change sensitivity coefficient, is the total time, is the current moment.
[0052] In some optional embodiments, after obtaining the correlation between the outdoor environment data and the performance parameters of the embedded training simulator, the method further includes: dynamically displaying the correlation between the obtained outdoor environment data and the performance parameters of the embedded training simulator through a visualization interface.
[0053] The content displayed on the visualization interface includes, but is not limited to: a multi-dimensional correlation heat map of the outdoor environment data and the performance parameters of the embedded training simulator; a real-time comparison map of the dynamic response curves at different times; a prediction deviation warning prompt map of the outdoor environment data and the performance parameters of the embedded training simulator.
[0054] Specifically, the temperature, humidity, and wind speed in the outdoor environment data can be mapped to the RGB three-channel space to establish a multi-dimensional correlation heat map of the outdoor environment data and the performance parameters of the embedded training simulator.
[0055] The prediction deviation warning prompt map can be displayed in the following way: the first curve shows the theoretical response of the prediction trajectory, and the second curve shows the feedback value of the actual multi-source sensor; when the distance between the first curve and the second curve continuously exceeds 10% within a preset time threshold, a yellow warning is triggered; when the distance between the first curve and the second curve continuously exceeds 20% within a preset time threshold, a red warning is triggered. It can be understood that the technical personnel can set the specific display content of the visualization interface according to their needs, and no restrictions are imposed here.
[0056] In the dynamic modeling of the outdoor environment of the embedded training simulator, it is necessary to establish a time series model and a real-time data update mechanism to ensure that the simulator can seamlessly reflect the continuous process of environmental changes. However, environmental changes are often unpredictable and complex. How to accurately capture and reflect the subtle differences in environmental changes is a key technical issue. At the same time, under different environmental conditions, the dynamic performance of the simulator should also be consistent, which requires establishing corresponding mathematical models and determining the reference values of environmental changes. In addition, the impact of environmental factors such as temperature and humidity on the equipment also needs to be considered. How to convert these factors into field strength parameters and establish a mathematical model is also an important technical challenge. Finally, how to use meteorological data and large-scale environmental prediction models to enable the simulator to predict future environmental changes and adjust the operating state in advance is also an urgent problem to be solved. In short, in the dynamic modeling of the outdoor environment, how to balance the accuracy, consistency, adaptability, and predictability of the simulator is a complex technical balance that requires comprehensive consideration of various environmental factors and equipment characteristics, and establishing refined mathematical models and efficient computing mechanisms.
[0057] The outdoor environment dynamic modeling method of the embedded training simulator proposed by the present invention determines key environmental factors such as temperature, humidity, and wind speed according to sensor data and environmental prediction technology. Specifically, by establishing a mathematical model, these environmental changes are transmitted to the operation logic of the simulator in real time, and the vibration intensity, movement trajectory, etc. of the simulator are adjusted. At the same time, it ensures that the users of the embedded training simulator can intuitively understand the impact of environmental changes on the device performance through visualization tools; the joints of the embedded training simulator should be closely combined with environmental changes to achieve precise dynamic response. The core system needs to integrate environmental data acquisition, mathematical modeling, and real-time simulation technologies to dynamically adjust the simulator behavior in different scenarios.
[0058] To reflect the coherence of environmental changes over time, it is necessary to establish a time series model and a real-time data update mechanism. Specifically, through high-precision sensors and refined mathematical models, the subtle differences in environmental changes are accurately captured and reflected; the reference values of environmental changes are determined, and corresponding mathematical models are established to ensure that the embedded training simulator maintains consistent dynamic performance under different conditions; by combining meteorological data and large-scale environmental prediction models, the embedded training simulator can predict future environmental changes and adjust its operating state in advance; environmental factors such as temperature and humidity are converted into field strength parameters, and a mathematical model is established to truly reflect the impact of the environment on the device.
[0059] Embodiment 2: Based on the same inventive concept, the present invention also provides an outdoor environment dynamic modeling system 200 for an embedded training simulator. The structure of this system is as Figure 2 shown. This system 200 includes: An outdoor environment data acquisition module 201 for acquiring outdoor environment data of the embedded training simulator collected by multi-source sensors; An environmental parameter sequence acquisition module 202 for performing time series modeling on the outdoor environment data to obtain a dynamic environmental parameter sequence; A trajectory adjustment amount calculation module 203 for converting each dynamic environmental parameter in the dynamic environmental parameter sequence into a field strength parameter and calculating the movement trajectory adjustment amount of the embedded training simulator based on the field strength parameter; A dynamic modeling module 204 for controlling the mechanical joint response of the embedded training simulator in real time according to the movement trajectory adjustment amount, establishing the correlation between the outdoor environment data and the performance parameters of the embedded training simulator, and completing the outdoor environment dynamic modeling of the embedded training simulator.
[0060] Preferably, the trajectory adjustment amount calculation module 203 is specifically used for: Based on historical environmental statistical data, obtaining the reference value range of the outdoor environment data; Using a machine learning model to establish the mapping relationship between the environmental parameters and the device performance indicators based on the reference value range; Based on the mapping relationship, the dynamic environmental parameters are converted into field strength parameters through the field strength conversion strategy.
[0061] Preferably, the field strength parameters include electromagnetic field strength parameters or mechanical field strength parameters; The calculation method of the field strength conversion strategy is as follows:
[0062] Wherein, is the field strength parameter, is the temperature, is the reference temperature, is the temperature calibration coefficient based on the device characteristics, is the humidity, is the reference humidity, is the humidity calibration coefficient based on the device characteristics, is the wind speed, is the wind speed calibration coefficient based on the device characteristics.
[0063] Preferably, the environmental parameter sequence acquisition module 202 is specifically configured to: Use the long short-term memory network LSTM to extract the long-term and short-term dependence features of the outdoor environmental data; Detect the periodic change pattern of the outdoor environmental data through the autoregressive integrated moving average model ARIMA; Generate a dynamic environmental parameter sequence with continuous timestamps based on the long-term and short-term dependence features and periodic change patterns of the outdoor environmental data.
[0064] Preferably, the system further includes a meteorological prediction module, which is specifically configured to: Access meteorological prediction data and generate the probability distribution of environmental parameters within a future time window; Simulate the device responses under multiple extreme scenarios through the Monte Carlo method; The trajectory adjustment amount calculation module is further configured to: Combine the device responses to update the motion trajectory adjustment amount of the embedded training simulator to obtain the updated motion trajectory adjustment amount.
[0065] Preferably, the system further includes an outdoor environmental data preprocessing module, which is specifically configured to: Fuse the outdoor environmental data of the embedded training simulator collected by multi-source sensors through the spatio-temporal alignment algorithm; Adopt the environmental mutation detection algorithm with a sliding window; Based on the adaptive calibration algorithm of dynamic parameters, compensate for sensor noise and transmission delay to obtain the preprocessed outdoor environmental data.
[0066] Preferably, the dynamic modeling module 204 is specifically configured to: According to the adjustment amount of the motion trajectory and combined with the mechanical joint adjustment strategy, obtain the dynamic joint damping coefficient; Based on the dynamic joint damping coefficient, establish a PID control model for the mechanical joint angle - environmental parameters; Adopt fuzzy logic algorithm processing, and based on the PID control model, obtain the mechanical joint response of the embedded training simulator; The calculation formula of the mechanical joint adjustment strategy is as follows:
[0067] Wherein, is the real - time damping coefficient, is the reference damping value, is the temperature change sensitivity coefficient, is the total time, is the current moment.
[0068] Embodiment 3: Based on the same inventive concept, as Figure 3 shown, the present invention also provides an electronic device, which may be a computer device, a single - chip microcomputer device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected through a bus; the memory can be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, and this data can be called and / or modified when the instructions are executed.
[0069] The processor may be a Central Processing Unit (CPU), or may also be other general - purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field - Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in a readable storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of an outdoor environment dynamic modeling method of an embedded training simulator in the above - mentioned embodiment.
[0070] Embodiment 4: Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device-readable storage medium (Memory). The electronic device-readable storage medium is a memory device in the electronic device and is used to store programs and data. It can be understood that the readable storage medium here can include both the built-in storage medium in the electronic device and, of course, the extended storage medium supported by the electronic device. The storage medium provides a storage space, and the operating system of the terminal is stored in this storage space. Moreover, one or more instructions suitable for being loaded and executed by the processor are stored in this storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the storage medium can be loaded and executed by the processor to implement the steps of the outdoor environment dynamic modeling method of an embedded training simulator in the above embodiments.
[0071] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.
[0072] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.
[0073] These computer program instructions can 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 generate a manufactured article including an instruction device, and the instruction device implements the functions in Figure 1 one process or multiple processes and / or blocks Figure 1The functions specified in one or more boxes.
[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one Figure 1 one process or more processes and / or boxes Figure 1 step of the functions specified in one or more boxes.
[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the scope of its protection. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent replacements to the specific implementation manners of the application. However, these changes, modifications or equivalent replacements are all within the scope of the protection of the claims pending for approval of the application.
Claims
1. An outdoor environment dynamic modeling method for an embedded training simulator, characterized in that, Including: Obtain the outdoor environment data of the embedded training simulator collected by multi-source sensors; Perform time series modeling on the outdoor environment data to obtain a dynamic environment parameter sequence; Convert each dynamic environment parameter in the dynamic environment parameter sequence into a field strength parameter, and calculate the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter; According to the motion trajectory adjustment amount, real-time control the mechanical joint response of the embedded training simulator, establish the correlation between the outdoor environment data and the performance parameters of the embedded training simulator, and complete the dynamic modeling of the outdoor environment of the embedded training simulator.
2. The method according to claim 1, characterized in that, The conversion of the dynamic environment parameter in the dynamic environment parameter sequence into a field strength parameter includes: Based on historical environment statistical data, obtain the reference value range of the outdoor environment data; Use a machine learning model to establish a mapping relationship between environmental parameters and device performance indicators based on the reference value range; Based on the mapping relationship, convert the dynamic environment parameter into a field strength parameter through a field strength conversion strategy.
3. The method according to claim 2, characterized in that The field strength parameter includes an electromagnetic field strength parameter or a mechanical field strength parameter; The calculation method of the field strength conversion strategy is as follows: Among them, is the field strength parameter, is the temperature, is the reference temperature, is the temperature calibration coefficient based on the device characteristics, is the humidity, is the reference humidity, is the humidity calibration coefficient based on the device characteristics, is the wind speed, is the wind speed calibration coefficient based on the device characteristics.
4. The method according to claim 1, characterized in that The performing time series modeling on the outdoor environment data to obtain a dynamic environment parameter sequence includes: Adopt a long short-term memory network (LSTM) to extract the long-term and short-term dependence features of the outdoor environment data; Detect the periodic change pattern of the outdoor environment data through an autoregressive integrated moving average model (ARIMA); Generate a dynamic environment parameter sequence with continuous timestamps based on the long-term and short-term dependence features and the periodic change pattern of the outdoor environment data.
5. The method according to claim 1, wherein After obtaining the outdoor environment data of the embedded training simulator collected by multi-source sensors and before converting each dynamic environment parameter in the dynamic environment parameter sequence into a field strength parameter, the method further includes: Access meteorological prediction data to generate the environmental parameter probability distribution within a future time window; Simulate the device response under multiple extreme scenarios through the Monte Carlo method; After calculating the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter, the method further includes: Combine the device response to update the motion trajectory adjustment amount of the embedded training simulator to obtain an updated motion trajectory adjustment amount.
6. The method according to claim 1, characterized in that After obtaining the outdoor environment data of the embedded training simulator collected by multi-source sensors, the method further includes: preprocessing the outdoor environment data; The steps of the preprocessing include: Fuse the outdoor environment data of the embedded training simulator collected by multi-source sensors through a spatio-temporal alignment algorithm; Adopt an environmental mutation detection algorithm with a sliding window; Based on an adaptive calibration algorithm for dynamic parameters, compensate for sensor noise and transmission delay to obtain the preprocessed outdoor environment data.
7. The method according to claim 1, characterized in that, The real-time control of the mechanical joint response of the embedded training simulator according to the motion trajectory adjustment amount includes: According to the motion trajectory adjustment amount, combine with a mechanical joint adjustment strategy to obtain a dynamic joint damping coefficient; Based on the dynamic joint damping coefficient, establish a PID control model of the mechanical joint angle - environmental parameter; Processed by the fuzzy logic algorithm, based on the PID control model, the mechanical joint response of the embedded training simulator is obtained; The calculation formula of the mechanical joint adjustment strategy is as follows: Among them, is the real-time damping coefficient, is the reference damping value, is the temperature change sensitivity coefficient, is the total time, is the current moment.
8. An outdoor environment dynamic modeling system for an embedded training simulator, characterized in that, Including: An outdoor environment data acquisition module, configured to acquire the outdoor environment data of the embedded training simulator collected by multi-source sensors; An environmental parameter sequence acquisition module, configured to perform time series modeling on the outdoor environment data to obtain a dynamic environmental parameter sequence; A trajectory adjustment amount calculation module, configured to convert each dynamic environmental parameter in the dynamic environmental parameter sequence into a field strength parameter, and calculate the motion trajectory adjustment amount of the embedded training simulator based on the field strength parameter; A dynamic modeling module, configured to control the mechanical joint response of the embedded training simulator in real time according to the motion trajectory adjustment amount, establish the association relationship between the outdoor environment data and the performance parameters of the embedded training simulator, and complete the outdoor environment dynamic modeling of the embedded training simulator.
9. An electronic device, characterized in that, Including: At least one processor and a memory; The memory and the processor are connected by a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the outdoor environment dynamic modeling method of the embedded training simulator according to any one of claims 1 to 7 is implemented.
10. A readable storage medium, characterized in that, There is an execution program stored thereon, and when the execution program is executed, the outdoor environment dynamic modeling method of the embedded training simulator according to any one of claims 1 to 7 is implemented.