A method, system, and terminal for determining the envelope of lunar surface drilling and sampling conditions.
By constructing a safe envelope boundary for lunar surface drilling and sampling conditions, and utilizing multidimensional feature extraction and data registration techniques, the problem of the inability to determine lunar surface drilling and sampling conditions in real time in existing technologies was solved, thus enabling the probe to perform safe drilling tasks.
Patent Information
- Application Number
- CN202611613446.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-19
- Publication Date
- 2026-11-17
AI Technical Summary
Existing technology cannot determine whether lunar drilling and sampling conditions are within the safe envelope of ground tests based on real-time telemetry data, which means that the safety of the probe cannot be guaranteed.
By determining the initial telemetry data samples for the lunar drilling simulation experiment, data preprocessing and multidimensional feature extraction were performed. The optimal statistical features and depth observation window were calculated, a safe envelope boundary was constructed, and data registration and feature value calculation were performed on the real-time telemetry data to determine whether the on-orbit feature value was within the safe envelope boundary.
It improves the accuracy of lunar surface drilling and sampling condition assessment, ensures the safe execution of the probe's drilling mission, and provides real-time early warning capabilities for abnormal operating conditions.
Smart Images

Figure CN123115774A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a method, system, terminal, and computer-readable storage medium for determining the envelope of lunar drilling sampling conditions. Background Technology
[0002] After landing at the lunar south pole, the probe will release a flyby spacecraft to conduct drilling, sampling, and in-situ analysis. However, due to the complex lunar surface topography, the physical and mechanical properties of lunar regolith (such as particle size distribution, density, and water ice content) exhibit significant spatial variability. If the lunar regolith conditions encountered during on-orbit drilling exceed the envelope of ground-based tests, it means that the characteristics of the current drilling target exceed the safety boundaries established on the ground, potentially leading to serious consequences such as abnormal loads on the drilling tools, abnormally increased drilling power consumption, decreased sampling success rate, or even damage to the drilling tools. Therefore, during the drilling process, it is necessary to determine whether the current on-orbit conditions are within the safety envelope boundaries established by ground tests, based on real-time telemetry data, to provide ground personnel with early warning capabilities and decision-making basis for abnormal conditions.
[0003] However, existing technologies mostly focus on monitoring a single working condition during the drilling process or identifying faults afterward. They cannot determine whether the current working condition is within the Earth's coverage area based on real-time telemetry data, which leads to the inability to accurately know the lunar drilling and sampling conditions and the inability to guarantee the safety of the probe.
[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention
[0005] The main objective of this invention is to provide a method, system, terminal, and computer-readable storage medium for determining the lunar surface drilling and sampling condition envelope. This aims to solve the problem that existing technologies often focus on monitoring a single condition during the drilling process or identifying faults afterward, and cannot determine whether the current condition is within the Earth's surface envelope based on real-time telemetry data. As a result, the lunar surface drilling and sampling condition cannot be accurately known, and the safety of the probe cannot be guaranteed.
[0006] To achieve the above objectives, the present invention provides a method for determining the envelope of lunar surface drilling and sampling conditions, the method comprising the following steps: A lunar surface drilling simulation experiment was determined, initial telemetry data samples from the lunar surface drilling simulation experiment were obtained, and the initial telemetry data samples were preprocessed to obtain target telemetry sample data. Multidimensional feature extraction is performed on the target telemetry sample data to obtain a multidimensional feature set; Calculate the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and determine the safe envelope boundary based on the optimal statistical features and the optimal depth observation window; Acquire real-time telemetry data, perform data registration and feature value calculation on the real-time telemetry data, and obtain on-orbit feature values; If the on-orbit feature value is determined to be within the safety envelope boundary, the envelope compliance result is output.
[0007] Optionally, the method for determining the lunar surface drilling sampling condition envelope, wherein determining the lunar surface drilling simulation test, obtaining initial telemetry data samples from the lunar surface drilling simulation test, and performing data preprocessing on the initial telemetry data samples to obtain target telemetry sample data, specifically includes: The lunar surface drilling simulation test is determined, wherein the lunar surface drilling simulation test includes a first simulated lunar soil drilling test, a second simulated lunar soil drilling test, and a third simulated lunar soil drilling test; Acquire initial telemetry data samples from the lunar drilling simulation test, wherein the telemetry parameters in the initial telemetry data samples include the current current of the rotary mechanism, the current current of the feed mechanism, the average drilling pressure, and the average torque. The initial telemetry data samples are subjected to outlier removal and sampling alignment to obtain the target telemetry sample data.
[0008] Optionally, the method for determining the lunar surface drilling sampling condition envelope, wherein the step of extracting multi-dimensional features from the target telemetry sample data to obtain a multi-dimensional feature set specifically includes: The total drilling depth during the lunar surface drilling simulation test was obtained, and the total drilling depth was divided into intervals to obtain multiple depth observation intervals. Calculate the feature values corresponding to the target telemetry sample data in each depth observation interval to obtain a multidimensional feature set; The types of the eigenvalues include statistical domain features, time-domain waveform features, frequency domain features, trend and fitting features, and entropy and fractal features.
[0009] Optionally, the method for determining the envelope of lunar surface drilling sampling conditions includes, in part, calculating the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and determining the safe envelope boundary based on the optimal statistical features and the optimal depth observation window; The discrimination score of each feature value in the multidimensional feature set in each depth observation interval is calculated using box plot visualization and one-way ANOVA, and the global mean and global standard deviation corresponding to the discrimination score are calculated. The optimal statistical features and optimal depth observation window corresponding to each telemetry parameter are calculated based on the global mean and the global standard deviation, and a safe envelope boundary is constructed based on the target telemetry sample data, the optimal statistical features, and the optimal depth observation window.
[0010] Optionally, the method for determining the lunar surface drilling sampling condition envelope, wherein acquiring real-time telemetry data, performing data registration processing and feature value calculation on the real-time telemetry data to obtain on-orbit feature values, specifically includes: Acquire real-time telemetry data, current drilling depth, and telemetry data timestamp or frame number, and perform data registration processing on the real-time telemetry data and the current drilling depth according to the telemetry data timestamp or frame number to obtain registered telemetry data; When the current drilling depth reaches the optimal depth observation window, target registration telemetry data where the drilling depth reaches the optimal depth observation window is extracted from the registration telemetry data; Based on the optimal statistical characteristics, feature values are calculated for the target registration telemetry data to obtain on-orbit feature values.
[0011] Optionally, the method for determining the lunar surface drilling sampling condition envelope, wherein acquiring real-time telemetry data, performing data registration processing and feature value calculation on the real-time telemetry data to obtain on-orbit feature values, further includes: The cumulative position ratio corresponding to the on-orbit feature value is calculated using an empirical distribution function, and the centrality score is calculated based on the cumulative position ratio. The absolute probability of the on-orbit feature value is calculated based on frequency statistics, and the absolute probability is normalized to obtain the relative frequency score. The feature discrimination capability of each telemetry parameter in each depth observation interval is calculated based on the cumulative location ratio, the centrality score, and the relative frequency score.
[0012] Optionally, the method for determining the envelope of lunar surface drilling sampling conditions, wherein the step of outputting an envelope compliance result if the on-orbit feature value is determined to be within the safe envelope boundary, specifically includes: The on-orbit feature value corresponding to each telemetry parameter is compared sequentially with the safety envelope boundary; If the on-orbit feature value corresponding to each telemetry parameter is within the safe envelope boundary, then the centrality scores corresponding to each telemetry parameter are summarized to obtain the envelope compliance result.
[0013] Furthermore, to achieve the above objectives, the present invention also provides a system for determining the envelope of lunar surface drilling and sampling conditions, wherein the system for determining the envelope of lunar surface drilling and sampling conditions includes: The data preprocessing module is used to determine the lunar surface drilling simulation experiment, obtain the initial telemetry data sample in the lunar surface drilling simulation experiment, and perform data preprocessing on the initial telemetry data sample to obtain the target telemetry sample data. A multidimensional feature extraction module is used to extract multidimensional features from the target telemetry sample data to obtain a multidimensional feature set. The safe envelope boundary generation module is used to calculate the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and to determine the safe envelope boundary based on the optimal statistical features and the optimal depth observation window. The on-orbit feature value generation module is used to acquire real-time telemetry data, perform data registration processing and feature value calculation on the real-time telemetry data, and obtain on-orbit feature values. The envelope compliance result output module is used to output the envelope compliance result if it is determined that the on-orbit feature value is within the safe envelope boundary.
[0014] In addition, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a lunar surface drilling sampling condition envelope determination program stored in the memory and executable on the processor, wherein when the lunar surface drilling sampling condition envelope determination program is executed by the processor, it implements the steps of the lunar surface drilling sampling condition envelope determination method as described above.
[0015] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program for determining the lunar surface drilling sampling envelope, and when the program for determining the lunar surface drilling sampling envelope is executed by a processor, it implements the steps of the method for determining the lunar surface drilling sampling envelope as described above.
[0016] In this invention, a lunar surface drilling simulation experiment is determined, initial telemetry data samples from the simulation experiment are obtained, and the initial telemetry data samples are preprocessed to obtain target telemetry sample data. Multidimensional feature extraction is performed on the target telemetry sample data to obtain a multidimensional feature set. The optimal statistical feature and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set are calculated, and a safe envelope boundary is determined based on the optimal statistical feature and the optimal depth observation window. Real-time telemetry data is acquired, and data registration and feature value calculation are performed on the real-time telemetry data to obtain on-orbit feature values. If the on-orbit feature value is determined to be within the safe envelope boundary, the envelope compliance result is output. This invention, by extracting multidimensional features from telemetry data to obtain a multidimensional feature set, and then selecting the optimal statistical feature and optimal depth observation window, and generating a safe envelope boundary, can effectively improve the accuracy of lunar surface drilling sampling condition judgment and ensure the normal execution of the probe's lunar regolith drilling mission. Attached Figure Description
[0017] Figure 1 This is a flowchart of a preferred embodiment of the method for determining the envelope of lunar surface drilling and sampling conditions according to the present invention; Figure 2 This is a visual illustration of the feature discrimination capability of a preferred embodiment of the method for determining the envelope of lunar surface drilling sampling conditions of the present invention. Figure 2 The content in the figure is specifically a box plot showing the relationship between the current of the rotary mechanism in the -100 mm depth range and the average current. Figure 3 This is a thermal schematic diagram illustrating the feature discrimination capability of a preferred embodiment of the method for determining the envelope of lunar surface drilling and sampling conditions of the present invention. Figure 3 The content specifically uses nine depth ranges from 10mm to 200mm as examples to illustrate the correspondence between depth segments and feature numbers in the current current of the rotary mechanism. Figure 4 This is a schematic diagram comparing on-orbit current data with typical operating conditions in a preferred embodiment of the method for determining the envelope of lunar surface drilling sampling conditions according to the present invention. Figure 4 (A) in the graph is a probability distribution histogram. Figure 4 (B) in the graph represents the relative probability score function. Figure 4 (C) in the figure represents the empirical CDF plot. Figure 4 (D in the graph represents the centrality score). Figure 5 This is a schematic diagram comparing on-orbit current data with challenging conditions in a preferred embodiment of the method for determining the envelope of lunar surface drilling sampling conditions according to the present invention. Figure 5 (A) in the graph is a probability distribution histogram. Figure 5 (B) in the graph represents the relative probability score function. Figure 5 (C) in the figure represents the empirical CDF plot. Figure 5 (D in the graph represents the centrality score). Figure 6 This is a structural diagram of a preferred embodiment of the lunar surface drilling and sampling condition envelope determination system of the present invention; Figure 7 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0019] After the probe lands at the lunar south pole, it will release a flyby spacecraft to drill and sample the lunar south pole. In two different environments, namely a small cold trap in the sunlit area and a permanently shadowed area, it will conduct multiple drilling, sampling and in-situ analysis of the lunar regolith and water ice in the lunar south pole region.
[0020] In lunar south pole drilling and sampling missions, the complex lunar surface topography leads to significant spatial variability in the physical and mechanical properties of lunar regolith (such as particle size distribution, density, and water ice content). To ensure the success of the drilling and sampling mission, extensive drilling verification tests were conducted during the ground test phase for three simulated lunar regolith conditions: typical, challenging, and extreme. Telemetry parameter response characteristics under different conditions were obtained. However, whether the actual properties of the lunar regolith fall within the envelope of the ground verification during actual in-orbit drilling is a crucial question that must be answered in real time.
[0021] If the lunar soil conditions encountered during on-orbit drilling exceed the envelope of ground tests, it means that the characteristics of the current drilling target exceed the safety boundaries verified on the ground. This could lead to serious consequences such as abnormal loads on the drilling tools, abnormally increased drilling power consumption, decreased sampling success rate, or even damage to the drilling tools. Therefore, during drilling, it is necessary to determine whether the current on-orbit conditions are within the safety envelope boundaries established by ground tests, based on real-time telemetry data. This will provide ground personnel with early warning capabilities and decision-making basis for abnormal conditions.
[0022] In existing technologies, various methods for condition identification and fault diagnosis based on measurement-while-drilling (MWD) data have been developed for engineering drilling, oil and gas drilling, or mining operations in Earth environments. However, these methods differ fundamentally from lunar drilling and sampling missions, as follows: 1. Significantly different application scenarios and media conditions: The extreme low temperature, low gravity, high vacuum, and complex media conditions (a mixture of lunar soil / water ice / rock) at the lunar south pole fundamentally differ from those in conventional soil or rock drilling on Earth. Existing working condition identification thresholds and envelope boundaries in the Earth environment cannot be directly transferred to lunar drilling scenarios.
[0023] 2. Lack of ground-based test envelope construction methods for lunar drilling: Existing technologies mostly focus on single-condition monitoring during drilling or post-fault identification, lacking a systematic approach. In particular, existing technologies have not addressed how to select the optimal feature parameters and the best depth observation window from dozens of candidate statistical features.
[0024] 3. Lack of multi-parameter joint criteria and quantitative envelope conformity assessment indicators: Existing methods usually rely on threshold judgments of a single parameter, making it difficult to comprehensively utilize information from multiple telemetry parameters for integrated judgment. Furthermore, regarding the question of "the position of on-orbit data within the ground envelope," there is a lack of quantitative assessment indicators such as cumulative position ratio, centrality score, and relative frequency score, making it difficult for ground personnel to quantitatively assess the degree of deviation and risk level of the current on-orbit operating conditions.
[0025] 4. Lack of envelope scheme for specific loads and telemetry parameters of the Flyover water-ice drill: The Flyover water-ice drill has specific drilling mechanisms (including rotary mechanism, feed mechanism, and impact mechanism) and types of telemetry parameters (rotation current, feed current, drilling pressure, torque, etc.). Existing technologies cannot be directly applied, and a dedicated envelope judgment scheme needs to be developed for this specific device and mission requirements.
[0026] In summary, existing technologies have significant shortcomings in determining the operational envelope of lunar surface drilling and sampling missions, making it difficult to meet the needs of the spacecraft drilling and sampling mission for real-time interpretation of on-orbit operational conditions and safety early warning.
[0027] Therefore, this invention proposes a method for determining the envelope of lunar surface drilling sampling conditions, to solve the real-time problem of determining whether the on-orbit drilling conditions in lunar remote-operated drilling and extraction missions are within the safe envelope range of ground tests. This method first establishes a drilling telemetry database covering three simulated lunar soil conditions—typical, challenging, and extreme—based on ground simulation test data. The total drilling depth is divided into multiple depth observation intervals, and within each interval, a multidimensional feature set covering five dimensions—statistical domain, time domain waveform, frequency domain, trend and fitting, complexity, and entropy and fractal—is extracted for each telemetry parameter. Through an evaluation method combining box plot visualization and one-way ANOVA, the feature-depth interval combination with optimal condition discrimination and stability is selected for each telemetry parameter, thereby constructing the safe envelope boundary of the ground test.
[0028] During the on-orbit application phase, this invention processes the real-time telemetry data according to the same depth range and feature extraction method to calculate the feature values to be evaluated; it calculates the cumulative position ratio of the on-orbit feature values in the ground reference sample set through an empirical distribution function to evaluate their relative position on the envelope boundary; it also introduces centrality score and relative frequency score to measure the position of the on-orbit data relative to the center region of the ground envelope and the degree of sample support, respectively; finally, it uses a multi-telemetry parameter joint judgment strategy to comprehensively determine whether the on-orbit operating conditions exceed the ground envelope range.
[0029] The technical effects of this invention include: 1. Establishing a systematic method for judging the envelope of lunar drilling and extraction conditions, filling a technical gap in this field; 2. By combining multi-dimensional feature extraction and statistical evaluation, the optimal combination of features and depth intervals can be selected, improving the sensitivity and reliability of condition differentiation; 3. Proposing multi-level quantitative evaluation indicators such as cumulative position ratio, centrality score, and relative frequency score, providing ground personnel with a complete judgment basis from qualitative to quantitative; 4. Adopting a multi-parameter joint judgment strategy avoids the risk of misjudgment by a single parameter, improving the robustness of envelope judgment; 5. This invention can be directly integrated into the ground support system for drilling and extraction missions, realizing real-time monitoring and anomaly early warning of on-orbit drilling and extraction conditions.
[0030] The method for determining the envelope of lunar surface drilling sampling conditions according to a preferred embodiment of the present invention, such as... Figure 1 As shown, the method for determining the envelope of lunar surface drilling sampling conditions includes the following steps: Step S10: Determine the lunar surface drilling simulation test, obtain the initial telemetry data sample in the lunar surface drilling simulation test, and perform data preprocessing on the initial telemetry data sample to obtain the target telemetry sample data.
[0031] The present invention proposes a method for determining the envelope of lunar surface drilling and sampling conditions. The overall technical solution is divided into two major stages: the ground envelope construction stage and the on-orbit real-time judgment stage.
[0032] The ground envelope construction stage includes the following steps: 1. Dataset definition and depth interval division; 2. Multi-dimensional feature extraction; 3. Feature discrimination ability evaluation and optimal feature selection; 4. Envelope boundary establishment.
[0033] The on-orbit real-time judgment phase includes the following steps: 1. On-orbit telemetry data acquisition and preprocessing; 2. On-orbit feature value calculation; 3. Quantitative assessment of envelope conformity (i.e., calculation of cumulative position ratio, centrality score, and relative frequency score); 4. Multi-parameter joint judgment and result output.
[0034] Specifically, a lunar surface drilling simulation test is determined, which includes a first simulated lunar soil drilling test, a second simulated lunar soil drilling test, and a third simulated lunar soil drilling test; initial telemetry data samples are obtained from the lunar surface drilling simulation test, wherein the telemetry parameters in the initial telemetry data samples include the current current of the rotary mechanism, the current current of the feed mechanism, the average drilling pressure, and the average torque; outlier removal and sampling alignment are performed on the initial telemetry data samples to obtain target telemetry sample data.
[0035] The specific implementation process for defining the dataset and partitioning the depth interval is as follows: The dataset is defined as follows: Let P be the set of telemetry parameters generated by the drilling device during a complete drilling process (i.e., the initial telemetry data sample data in this invention), which includes, but is not limited to, the following K key parameters: current current of the rotary mechanism, current current of the feed mechanism, average drilling pressure, and average torque (K=4).
[0036] For the m-th drilling test, each parameter p∈P is a function that varies with the drilling depth z, denoted as p_m(z). The ground test covers three typical simulated lunar soil conditions: typical condition (i.e., the first simulated lunar soil drilling test in this invention, used to simulate the typical lunar soil state in the lunar south polar region), challenging condition (i.e., the second simulated lunar soil drilling test in this invention, used to simulate the lunar soil state containing more coarse particles), and extreme condition (i.e., the third simulated lunar soil drilling test in this invention, used to simulate the extremely complex lunar soil state containing a large number of large-diameter rock particles). The set of conditions is denoted as C={typical, challenging, extreme}.
[0037] Furthermore, multiple repeated drilling tests are needed under each working condition to obtain stable telemetry data samples.
[0038] The data preprocessing process is as follows: 1. Data screening: Using the maximum depth actually reached by the feed mechanism as the standard, the test data under the same simulated lunar soil conditions are screened, and test data with obviously abnormal drilling depths are removed.
[0039] 2. Sampling Alignment: The actual on-orbit telemetry data transmission cycle is about 1.3 seconds. Based on this, the ground simulation data is sampled at equal intervals to ensure that the sampling frequency of the ground data and the on-orbit data is consistent.
[0040] Step S20: Extract multidimensional features from the target telemetry sample data to obtain a multidimensional feature set.
[0041] Specifically, the total drilling depth during the lunar surface drilling simulation test is obtained, and the total drilling depth is divided into intervals to obtain multiple depth observation intervals.
[0042] The process of dividing the depth range is as follows: Considering the vertical distribution differences in lunar soil properties (such as variations in density at different depths), the total drilling depth D_total (typically on the order of 1100 mm) is discretized into multiple equal-depth windows (i.e., multiple depth observation intervals). The depth window size is set to Δd, and the entire process is divided into N depth observation intervals.
[0043] The definition of the i-th depth observation interval I_i is: I_i=[(i-1)×Δd, i×Δd], where i=1, 2,…,N.
[0044] To examine the impact of different observation scales, Δd was set with multiple scales, including 10mm, 25mm, 50mm, 75mm, 100mm, 125mm, 150mm, 175mm, and 200mm, for a total of nine interval sizes. Subsequent feature evaluation analysis determined the optimal depth interval size for each telemetry parameter.
[0045] Calculate the feature values corresponding to the target telemetry sample data in each depth observation interval to obtain a multidimensional feature set; wherein, the types of the feature values include statistical domain features, time domain waveform features, frequency domain features, trend and fitting features, and entropy and fractal features.
[0046] The multi-dimensional feature extraction process is as follows: For each depth observation interval I_i, statistical features of the telemetry parameter p within that interval are calculated. Let T be the feature extraction function. For the m-th experiment, the feature value F_{m, i} of parameter p within the i-th depth observation interval is... T The calculation is as follows: F{m,i} T =T(p_m(z)), z∈I_i.
[0047] Based on M ground test data (where the sample size of working condition c_j is M_j, j=1,2,3), three sets of feature datasets can be obtained under any depth interval I_i, corresponding to the typical, challenging and extreme working conditions respectively.
[0048] Feature System Construction: Taking into account the characteristics of telemetry data, this invention constructs a multi-dimensional, multi-level feature index system, containing 46 features across five dimensions, as detailed below: Table 1: Statistical domain characteristics (numbers 1-15), used to describe the central tendency, dispersion and distribution pattern of the data.
[0049]
[0050] Table 2: Time-domain waveform characteristics (serial numbers 16-30): focusing on the geometry, energy fluctuations, and transient impacts of the quantized signal.
[0051]
[0052] Continued from Table 2:
[0053] Table 3: Frequency domain characteristics (serial numbers 31-36), spectral energy distribution and dominant frequency components of analytical signals based on Fast Fourier Transform (FFT).
[0054]
[0055] Table 4: Trends and Fitting Characteristics (Nos. 37-39): Capturing the Evolution of Signals with Increasing Depth and Autocorrelation.
[0056]
[0057] Table 5: Complexity, Entropy and Fractal Characteristics (Nos. 40-46): Using nonlinear dynamic indicators to measure the degree of chaos and irregularity of signals.
[0058]
[0059] Step S30: Calculate the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and determine the safe envelope boundary based on the optimal statistical features and the optimal depth observation window.
[0060] Specifically, the discrimination score of each feature value in the multidimensional feature set in each depth observation interval is calculated using box plot visualization and one-way ANOVA, and the global mean and global standard deviation corresponding to the discrimination score are calculated.
[0061] The process of evaluating feature discrimination ability and selecting the optimal feature is as follows: 1. For qualitative evaluation, such as Figure 2 As shown, this invention employs a visual box plot, with the depth interval I_i as the horizontal axis unit and the feature value F (i.e., Figure 2 Using the average current in the data as the vertical axis, box plots were drawn for three different operating conditions. The evaluation principle is that a characteristic with good distinguishability should satisfy "small differences within the group and large differences between the groups", that is, the box height is relatively narrow under the same operating condition, while the boxes under different operating conditions are significantly offset on the vertical axis, with no overlapping area or a small overlapping area.
[0062] 2. For quantitative evaluation, this invention employs one-way ANOVA. To quantify the distinguishing ability of each feature for different working conditions, one-way ANOVA is performed on three sets of working condition data within each depth interval I_i, and the F-statistic is calculated. Let Score_{i} T The discriminant score of feature T in the i-th interval is expressed as: Score_{i} T =F_i T ; The larger the F value, the higher the distinguishing power of feature T for the three working conditions and the stronger the statistical significance within the i-th depth interval.
[0063] The optimal statistical features and optimal depth observation window corresponding to each telemetry parameter are calculated based on the global mean and the global standard deviation, and a safe envelope boundary is constructed based on the target telemetry sample data, the optimal statistical features, and the optimal depth observation window.
[0064] The process for selecting the globally optimal feature is as follows: Considering that the F-value of a single depth interval cannot represent the effectiveness of the feature throughout the entire drilling process, in order to screen out features that perform well and stably across the entire depth range, this invention needs to calculate the global mean μ_T and global standard deviation σ_T of the F-value of feature T (i.e., the feature value in this invention) across all N depth intervals, expressed as: μ_T=(1 / N)×Σ_{i=1} {N} Score_{i} T ; σ_T=[(1 / N)×Σ_{i=1} {N} (Score_{i} T -μ_T)²]; The optimal feature should satisfy two conditions simultaneously: 1. Maximize μ_T: This indicates that the feature has the strongest average discriminative power across the entire depth range; 2. Minimize σ_T: This indicates that the discriminative power of the feature fluctuates little with depth and has good robustness.
[0065] Through the above steps, for each telemetry parameter, its corresponding optimal statistical characteristic T and optimal depth observation window N can be selected. For example... Figure 3 As shown, the present invention visualizes the results in the form of a heatmap: the vertical axis corresponds to 46 feature numbers, the horizontal axis represents the divided depth intervals, and the color intensity in each cell maps to the F value, allowing for intuitive observation of high-discrimination features within different depth intervals.
[0066] Furthermore, the process of establishing the envelope boundary is as follows: After completing feature screening, for any telemetry parameter p, its optimal statistical feature T and optimal number of depth intervals N are determined. At this time, the ground test data involved in envelope construction forms a stable reference sample set. If there are a total of m ground tests for constructing the envelope (covering all repeated tests of three working conditions), the reference sample set is denoted as: X={x_1, x_2, ..., x_m}; Where x_m represents the feature value extracted from the m-th ground test under the parameter p, feature T, and depth interval N.
[0067] Further, the envelope boundary is defined as follows: the upper and lower boundaries of the ground reference samples are the envelope boundaries (i.e., the safety envelope boundaries in the present invention), and the expression is: x_min=min(x_1, x_2, ..., x_n); x_max=max(x_1, x_2, ..., x_n); When x_orb<x_min or x_orb>x_max is satisfied, it can be directly determined that the on-orbit feature value exceeds the current ground test feature envelope range.
[0068] Step S40: Acquire real-time telemetry data, perform data registration processing and feature value calculation on the real-time telemetry data, to obtain an on-orbit feature value.
[0069] Specifically, acquire the real-time telemetry data, the current drilling depth, and the timestamp or frame number of the telemetry data, and perform data registration processing on the real-time telemetry data and the current drilling depth according to the timestamp or the frame number of the telemetry data, to obtain registered telemetry data.
[0070] The on-orbit data acquisition and preprocessing process is as follows: In the on-orbit application phase, the data inputs include: 1. Real-time telemetry data during the drilling process: the current current of the rotary mechanism, the current current of the feed mechanism, drilling pressure, torque, etc., which are acquired from the telemetry data server; 2. Current depth data of the feed mechanism: used to determine the depth interval where the current drilling is located; 3. Ground preset parameters: the optimal feature T, optimal depth interval N, and ground reference sample set X corresponding to each telemetry parameter.
[0071] The data registration process is as follows: Align each telemetry parameter with the corresponding drilling depth data in time according to the timestamp or frame number of the telemetry data, to ensure that the telemetry data and depth information used for calculation are data at the same moment or the closest moment.
[0072] When the current drilling depth reaches the optimal depth observation window, target registration telemetry data with the drilling depth reaching the optimal depth observation window is extracted from the registration telemetry data; feature values are calculated on the target registration telemetry data according to the optimal statistical characteristics to obtain on-orbit feature values.
[0073] The process for calculating on-orbit eigenvalues and quantitatively assessing envelope compliance is as follows: In-orbit feature extraction: For in-orbit drilling data, when the drilling depth reaches the depth range corresponding to the preset optimal depth interval N, the corresponding telemetry parameter data is extracted, and the in-orbit feature value is calculated using the pre-determined optimal feature T, as shown in the following expression: x_orb=T(p_orb(z), z∈N); Furthermore, the cumulative position ratio corresponding to the on-orbit feature value is calculated using an empirical distribution function, and the centrality score is calculated based on the cumulative position ratio; the absolute probability of the on-orbit feature value is calculated based on frequency statistics, and the absolute probability is normalized to obtain a relative frequency score; the feature discrimination capability of each telemetry parameter in each depth observation interval is calculated based on the cumulative position ratio, the centrality score, and the relative frequency score.
[0074] The calculation process for the Cumulative Position Ratio is as follows: The cumulative position ratio of the on-orbit eigenvalues is calculated using the Empirical Distribution Function (EDF), and the expression is: (x_orb)=(1 / n)×Σ_{m=1} {n} 1(x_m≤x_orb); Where 1(·) is an indicator function, taking the value 1 if the condition within the parentheses is true, and 0 otherwise; n is the total number of samples in the ground experiment. The range of (x_orb) is [0, 1]. (x_orb)=1 indicates that the on-orbit value is greater than or equal to all ground reference samples and is close to the upper bound of the envelope; (x_orb)=0 indicates that the on-orbit value is less than or equal to all ground reference samples, and is close to the lower bound of the envelope; (x_orb)=0.5 indicates that the on-orbit value is at the median level of the ground reference sample.
[0075] The calculation process for the centrality score is as follows: To measure the position of on-orbit feature values relative to the central region of the sample distribution, a centrality score is introduced, expressed as: C(x_orb) = 1 - 2 × | (x_orb)-0.5|; The equivalent expression is: C(x_orb) = 2 × min( (x_orb), 1- (x_orb)); the centrality score ranges from [0, 1]. When the on-orbit feature value is located at the center of the ground reference sample distribution, C(x_orb) = 1; when the on-orbit feature value is located at the extreme edge, C(x_orb) = 0. This index directly reflects the degree of consistency between on-orbit operating conditions and typical ground test conditions.
[0076] The calculation process for absolute probability is as follows: Since the feature values in this invention are discrete data, the absolute probability of the on-orbit feature values can be directly defined based on frequency statistics: P_abs(x_orb)=(1 / n)×Σ_{m=1} {n} 1(x_m=x_orb); This metric represents the proportion of samples in the ground reference sample that have exactly the same characteristic value as the current on-orbit value. The higher the metric, the better the match between the on-orbit value and the existing ground samples.
[0077] The calculation process for the Relative Frequency Score is as follows: To eliminate the differences in sample frequency magnitudes among different parameters and features, the absolute probability is further normalized, and a relative frequency score is defined, expressed as: R(x_orb)=P_abs(x_orb) / max_{v∈X}[(1 / n)×Σ_{m=1} {n} 1(x_m=v)]; In the formula, the denominator represents the absolute probability of the feature value that appears most frequently in the ground reference sample set. The range of the relative frequency score is [0, 1], and R(x_orb) = 1 indicates that the on-orbit feature value corresponds exactly to the most frequently occurring value in the ground control sample.
[0078] Step S50: If it is determined that the on-orbit feature value is within the safe envelope boundary, then output the envelope compliance result.
[0079] Specifically, the on-orbit feature value corresponding to each telemetry parameter is compared with the safe envelope boundary in sequence; if the on-orbit feature value corresponding to each telemetry parameter is within the safe envelope boundary, the centrality score corresponding to each telemetry parameter is summarized to obtain the envelope compliance result.
[0080] This invention employs a multi-parameter joint judgment strategy, wherein the specific implementation steps of the multi-parameter joint judgment strategy are as follows: This invention sets optimal feature and depth range combinations for each telemetry parameter: This invention systematically evaluates the distinguishing ability of 46 features of four telemetry parameters in each depth range, and the results are as follows: 1. Current current of the rotary mechanism: The optimal features are the mean (depth range 25-100mm) and the average slope (depth range 125-200mm). The mean feature performs best from the small depth range (10mm) to the medium depth range; after entering the large depth range, the distinguishability of the average slope is significantly improved and becomes dominant.
[0081] 2. Current current of the feed mechanism: The optimal characteristics are maximum value (10mm), spectral energy (25-50mm), and slope variance (75-200mm). The variation of these characteristics with the depth range reflects the differences in the force characteristics of the feed mechanism at different drilling stages.
[0082] 3. Average torque: The optimal features are the minimum value and the area under the curve. These two features alternately occupy the top three positions in the 50-200mm depth range and the difference is small. They are the best distinguishing features for this parameter.
[0083] 4. Average drilling pressure: The optimal features are permutation entropy (125–200 mm) and upper quartile (50–100 mm). Due to the high stability of drilling pressure telemetry data, the differences between data under different operating conditions are not as large as those of other telemetry parameters. Therefore, the nonlinear feature based on entropy shows better sensitivity in distinguishing between the three operating conditions.
[0084] The joint judgment rule is as follows: Taking into account the requirements of discrimination, computational complexity, and on-orbit real-time performance, this invention uses a 100mm depth interval as the unified observation window for the four telemetry parameters and constructs a joint judgment scheme: When the drilling depth reaches an integer multiple of 100mm, the optimal eigenvalues corresponding to the four telemetry parameters are calculated simultaneously, and their envelope conformity is evaluated respectively. The specific judgment logic is as follows: 1. Calculate the on-orbit characteristic value x_orb for each parameter. {(k)} (k=1, 2, 3, 4 correspond to rotary current, feed current, drilling pressure, and torque, respectively); 2. Calculate the cumulative position ratio, centrality score, and relative frequency score for each parameter; 3. Determine whether the on-orbit characteristic value of each parameter is within the ground envelope (i.e., determine whether x_min≤x_orb≤x_max); 4. If the on-orbit characteristic value of any of the four parameters exceeds the range, it is determined that the current on-orbit working condition exceeds the ground test envelope, triggering an anomaly warning; 5. If all four parameters are within the envelope, the centrality scores of the four parameters are combined to give a comprehensive compliance assessment.
[0085] Furthermore, the visualization process for envelope determination is as follows: Taking the current average value of the rotary mechanism as an example, after obtaining the average rotary current value below a depth of 0-100mm under on-orbit drilling conditions, the current on-orbit characteristic value is superimposed onto the distribution maps of the three ground conditions (typical / challenging / extreme) for visualization, and the position of the on-orbit value within the ground envelope is marked. In this way, ground personnel can intuitively see the relationship between the on-orbit characteristic value and the reference distributions of the typical, challenging, and extreme conditions, and make quick judgments.
[0086] It is understood that this invention, as one of the core functional modules of the ground support system for drilling missions, runs on the monitoring terminal of the ground control center. The software architecture is divided into three layers: 1. Data access layer: responsible for obtaining real-time telemetry data streams from the telemetry server; 2. Algorithm calculation layer: implementing core algorithms such as feature extraction, envelope comparison, and multi-parameter joint judgment; 3. Display and interaction layer: providing a visual interface to display envelope judgment results, feature values of each parameter, historical trends, and early warning information.
[0087] The software processing flow is as follows: 1. Initialization: Load ground preset parameters, including the optimal feature T, optimal depth interval N, ground reference sample set X, and envelope boundary [x_min, x_max] of each telemetry parameter.
[0088] 2. Data reception: Real-time reception of telemetry data streams during the drilling process, including rotary current, feed current, drilling pressure, torque, and drilling depth.
[0089] 3. Depth range judgment: Based on the current drilling depth, determine whether the preset depth range (such as an integer multiple of 100mm) has been reached.
[0090] 4. Feature Calculation: When the evaluation depth is reached, extract the telemetry data segment within the current depth interval and calculate it according to the preset optimal feature T. Calculate the on-orbit characteristic values of the four parameters.
[0091] 5. Envelope assessment: such as Figure 4 and Figure 5 As shown, each parameter is processed one by one: x_orb is compared with the ground reference sample set X (i.e., the on-orbit feature values); the cumulative position ratio is calculated using the empirical distribution function. (x_orb); calculate the centrality score C(x_orb); calculate the absolute probability P_abs(x_orb) and the relative frequency score R(x_orb).
[0092] 6. Joint Judgment: Executes multi-parameter joint judgment logic. If any parameter exceeds the envelope boundary, a "Out of Envelope" warning is triggered; if all parameters are within the envelope, the overall compliance score is output.
[0093] 7. Results Display: The judgment results are displayed on the visualization interface, including: the current drilling depth and the depth range used; a comparison chart of the current feature values of the four parameters with the envelope boundary; the cumulative position ratio, centrality score, and relative frequency score of each parameter; the joint judgment conclusion ("within the envelope" / "outside the envelope"); if it exceeds the envelope, the abnormal parameter is highlighted.
[0094] 8. Continuous monitoring: As the drilling depth increases, repeat steps (3) to (7) at each evaluation depth node to achieve continuous envelope monitoring of the entire drilling process.
[0095] Based on the above description of the technical solution, the technical effects of the present invention can be summarized as follows: 1. Systematization: This invention establishes a complete technical process from ground envelope construction to real-time on-orbit judgment, covering all aspects of dataset definition, multi-dimensional feature extraction, statistical evaluation and screening, envelope boundary establishment, quantitative compliance assessment, and multi-parameter joint judgment.
[0096] 2. Sensitivity of the multi-dimensional feature system: Through 46 features covering five dimensions, including statistical domain, time domain waveform, frequency domain, trend and fitting, complexity and entropy and fractal, it can capture subtle differences in telemetry data under different working conditions from different perspectives, avoiding information that may be missed by a single feature dimension.
[0097] 3. Automatic Optimal Feature Selection: By combining qualitative evaluation using box plots with quantitative evaluation using ANOVA, the system can automatically select the optimal features and optimal depth ranges for each telemetry parameter, avoiding the subjectivity and bias of relying on experience to select features. The direct benefit of this technology is that different optimal features can be selected for different telemetry parameters, adapting to the data distribution characteristics of different parameters.
[0098] 4. Multi-level quantitative assessment: This invention proposes three complementary quantitative indicators: cumulative position ratio, centrality score, and relative frequency score. These indicators characterize the envelope conformity of on-orbit data from three dimensions: "location, distance from the center, and support received," providing richer interpretation information than a simple binary judgment of "in or out of the envelope." The direct effect of this technical feature is that ground personnel can quantitatively assess the degree of deviation and risk level of on-orbit operating conditions, rather than simply obtaining binary results.
[0099] 5. Robustness of Multi-Parameter Joint Judgment: A four-parameter joint judgment strategy (rotation current + feed current + drilling pressure + torque) is adopted. An abnormality in any parameter triggers an early warning, avoiding false alarms or missed detections that might occur due to sensor noise or local interference from a single parameter. The direct effect of this technical feature is a significant reduction in false alarm and missed alarm rates, improving the reliability of abnormal operating condition detection.
[0100] 6. Depth-Adaptive Monitoring Strategy: By dividing the depth range into multiple scales (10mm to 200mm), different optimal features can be used for judgment at different drilling stages, adapting to the characteristics of lunar regolith sequence changes during drilling. The direct effect of this technical feature is that optimal working condition differentiation capability can be obtained at different depth stages.
[0101] The main innovative points of this invention include: 1. A ground condition envelope construction method for lunar drilling missions was established: This invention does not simply preset fixed thresholds for condition judgment, but rather conducts systematic drilling tests by constructing three representative lunar soil conditions (typical, challenging, and extreme) on the ground, and establishes a telemetry parameter response database. Based on this, through multi-scale depth interval division and multi-dimensional feature extraction, the combination of features and depth intervals with optimal discriminative power and stability is selected to form the ground test safety envelope boundary. This method fully considers the special characteristics of lunar drilling missions (low gravity, complex lunar soil conditions, and specific load structures for water-ice drills), and is fundamentally different from existing drilling condition identification methods under Earth conditions.
[0102] 2. A multi-dimensional feature evaluation system covering 46 features across five dimensions was constructed: This invention innovatively constructs 46 statistical features from five dimensions—statistical domain, time-domain waveform, frequency domain, trend and fitting, complexity, and entropy and fractals—forming a multi-level, multi-angle representation capability for drilling telemetry data. In particular, the introduction of nonlinear dynamic indices such as permutation entropy, sample entropy, and fractal dimension effectively captures the complex physical response characteristics of telemetry signals under extreme conditions. By combining qualitative evaluation using box plots with quantitative evaluation using one-way ANOVA, objective selection of optimal features and optimal depth intervals is achieved, avoiding subjectivity reliant on human experience.
[0103] 3. This invention proposes a three-tiered quantitative envelope conformity assessment index system based on cumulative position ratio, centrality score, and relative frequency score. This invention not only determines whether on-orbit data is within the envelope (binary judgment), but also calculates the cumulative position ratio (relative position within the envelope), centrality score (assessing the degree of deviation from the center), and relative frequency score (assessing the degree of sample support) through an empirical distribution function, forming a three-tiered quantitative assessment system that considers "location - distance from the center - support level." This index system provides ground personnel with a complete interpretation basis from qualitative to quantitative analysis, supporting refined risk level management.
[0104] 4. A joint judgment strategy for four telemetry parameters was established: Based on a systematic analysis of four key telemetry parameters—rotating mechanism current, feed mechanism current, drilling pressure, and torque—this invention determined the optimal combination of characteristics and depth ranges for each parameter, constructing a multi-parameter joint judgment rule. This strategy stipulates that if the on-orbit characteristic value of any parameter exceeds the corresponding envelope range, the current working condition is determined to be outside the ground envelope. This joint judgment strategy effectively overcomes the problem of limited information sources from a single parameter, significantly improving the robustness and reliability of the judgment.
[0105] 5. A closed-loop technical system was constructed, from ground testing to on-orbit application: This invention establishes a complete closed-loop technical system encompassing "ground simulation testing → database construction → multi-dimensional feature extraction → statistical evaluation and screening → envelope boundary establishment → on-orbit data evaluation → multi-parameter joint judgment → result visualization output." This system progresses step-by-step from ground to on-orbit, with each stage closely connected, ensuring both the scientific rigor and sufficiency of the envelope construction and the real-time performance and reliability of on-orbit applications. This complete system fills the technical gap in determining the working condition envelope during lunar drilling and production missions.
[0106] Possible design changes or modifications to this invention are as follows: 1. Simplification and Replacement of Feature System: This invention adopts a five-dimensional feature system with 46 features. Competitors may attempt to replace the feature set defined in this invention with other signal processing methods (such as wavelet analysis, Empirical Mode Decomposition (EMD), deep learning automatic feature extraction, etc.). However, such alternatives essentially still follow the technical route of "feature extraction → optimal feature selection → envelope construction" and should be within the scope of protection of this invention.
[0107] 2. Replacement of Evaluation Indicators: Competitors may use other statistical testing methods (such as Kruskal-Wallis nonparametric tests, feature importance ranking of machine learning classifiers, etc.) to replace the one-way ANOVA in this invention for feature selection; or use other probability distribution models to replace the empirical distribution function. Overall, as long as the basic idea of "constructing a reference distribution based on ground test data → quantitatively evaluating the conformity of on-orbit data" is followed, it should fall within the scope of protection of this invention.
[0108] 3. Addition or reduction of telemetry parameters: This invention targets four specific telemetry parameters. Competitors may add or remove telemetry parameter types based on different drilling tool configurations. However, the core idea of the multi-parameter joint judgment strategy—combining multiple independent information sources for redundant judgment—is not limited by the specific number of parameters. The key protection lies in the "multi-parameter joint" judgment architecture.
[0109] 4. Variation in Depth Ranges: This invention examines nine depth ranges from 10mm to 200mm. Competitors may use different range sizes or adaptive range division strategies. However, the fundamental framework of "discretizing the drilling depth into observation windows and extracting features within those windows for judgment" should not be altered.
[0110] 5. Expansion of Application Scenarios: Although this invention is geared towards lunar drilling and sampling, the method can be extended to drilling and sampling missions on other planets or asteroids, automated drilling operations in extreme Earth environments, etc. Any application of this invention that involves determining the working condition envelope during the drilling process and employs the technical approach of "constructing the envelope through ground tests → multi-dimensional feature evaluation and screening → multi-parameter joint judgment" should be considered an extension of the invention's application.
[0111] Furthermore, such as Figure 6 As shown, based on the above-mentioned method for determining the envelope of lunar surface drilling sampling conditions, the present invention also provides a system for determining the envelope of lunar surface drilling sampling conditions, wherein the system for determining the envelope of lunar surface drilling sampling conditions includes: The data preprocessing module 51 is used to determine the lunar surface drilling simulation test, obtain the initial telemetry data sample in the lunar surface drilling simulation test, and perform data preprocessing on the initial telemetry data sample to obtain the target telemetry sample data. The multidimensional feature extraction module 52 is used to extract multidimensional features from the target telemetry sample data to obtain a multidimensional feature set; The safe envelope boundary generation module 53 is used to calculate the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and to determine the safe envelope boundary based on the optimal statistical features and the optimal depth observation window. The on-orbit feature value generation module 54 is used to acquire real-time telemetry data, perform data registration processing and feature value calculation on the real-time telemetry data, and obtain on-orbit feature values. The envelope compliance result output module 55 is used to output the envelope compliance result if it is determined that the on-orbit feature value is within the safe envelope boundary.
[0112] Furthermore, such as Figure 7 As shown, based on the above-mentioned method and system for determining the envelope of lunar surface drilling sampling conditions, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 7 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0113] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, SmartMediaCard (SMC), SecureDigital (SD) card, or FlashCard. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a lunar drilling sampling condition envelope determination program 40, which can be executed by the processor 10 to implement the lunar drilling sampling condition envelope determination method of this application.
[0114] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the method for determining the lunar surface drilling sampling condition envelope.
[0115] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display 30 is used to display information on the terminal and to display a visual user interface.
[0116] In one embodiment, when the processor 10 executes the lunar drilling sampling condition envelope determination program 40 in the memory 20, it implements the steps of the lunar drilling sampling condition envelope determination method as described above.
[0117] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program for determining the envelope of lunar drilling sampling conditions, and when the program for determining the envelope of lunar drilling sampling conditions is executed by a processor, it implements the steps of the method for determining the envelope of lunar drilling sampling conditions as described above.
[0118] In summary, this invention provides a method, system, terminal, and storage medium for determining the envelope of lunar surface drilling sampling conditions. The method includes: determining a lunar surface drilling simulation experiment; acquiring initial telemetry data samples from the lunar surface drilling simulation experiment; preprocessing the initial telemetry data samples to obtain target telemetry sample data; extracting multidimensional features from the target telemetry sample data to obtain a multidimensional feature set; calculating the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and determining a safe envelope boundary based on the optimal statistical features and the optimal depth observation window; acquiring real-time telemetry data; performing data registration and feature value calculation on the real-time telemetry data to obtain on-orbit feature values; and outputting an envelope compliance result if the on-orbit feature value is determined to be within the safe envelope boundary. This invention extracts multidimensional features from telemetry data to obtain a multidimensional feature set, then selects the optimal statistical features and the optimal depth observation window, and generates a safe envelope boundary. This can effectively improve the accuracy of lunar surface drilling and sampling condition judgment and ensure the normal execution of the probe's lunar soil drilling mission.
[0119] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.
[0120] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.
[0121] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.
Claims
1. A method for determining the envelope of lunar surface drilling and sampling conditions, characterized in that, The method for determining the envelope of lunar surface drilling sampling conditions includes: A lunar surface drilling simulation experiment was determined, initial telemetry data samples from the lunar surface drilling simulation experiment were obtained, and the initial telemetry data samples were preprocessed to obtain target telemetry sample data. Multidimensional feature extraction is performed on the target telemetry sample data to obtain a multidimensional feature set; Calculate the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and determine the safe envelope boundary based on the optimal statistical features and the optimal depth observation window; Acquire real-time telemetry data, perform data registration and feature value calculation on the real-time telemetry data, and obtain on-orbit feature values; If the on-orbit feature value is determined to be within the safety envelope boundary, the envelope compliance result is output.
2. The method for determining the envelope of lunar surface drilling and sampling conditions according to claim 1, characterized in that, The process of determining the lunar surface drilling simulation experiment, acquiring initial telemetry data samples from the lunar surface drilling simulation experiment, and preprocessing the initial telemetry data samples to obtain target telemetry sample data specifically includes: The lunar surface drilling simulation test is determined, wherein the lunar surface drilling simulation test includes a first simulated lunar soil drilling test, a second simulated lunar soil drilling test, and a third simulated lunar soil drilling test; Acquire initial telemetry data samples from the lunar drilling simulation test, wherein the telemetry parameters in the initial telemetry data samples include the current current of the rotary mechanism, the current current of the feed mechanism, the average drilling pressure, and the average torque. The initial telemetry data samples are subjected to outlier removal and sampling alignment to obtain the target telemetry sample data.
3. The method for determining the envelope of lunar surface drilling and sampling conditions according to claim 1, characterized in that, The step of extracting multidimensional features from the target telemetry sample data to obtain a multidimensional feature set specifically includes: The total drilling depth during the lunar surface drilling simulation test was obtained, and the total drilling depth was divided into intervals to obtain multiple depth observation intervals. Calculate the feature values corresponding to the target telemetry sample data in each depth observation interval to obtain a multidimensional feature set; The types of the eigenvalues include statistical domain features, time-domain waveform features, frequency domain features, trend and fitting features, and entropy and fractal features.
4. The method for determining the envelope of lunar surface drilling and sampling conditions according to claim 3, characterized in that, The calculation of the optimal statistical feature and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and the determination of the safe envelope boundary based on the optimal statistical feature and the optimal depth observation window, specifically includes: The discrimination score of each feature value in the multidimensional feature set in each depth observation interval is calculated using box plot visualization and one-way ANOVA, and the global mean and global standard deviation corresponding to the discrimination score are calculated. The optimal statistical features and optimal depth observation window corresponding to each telemetry parameter are calculated based on the global mean and the global standard deviation, and a safe envelope boundary is constructed based on the target telemetry sample data, the optimal statistical features, and the optimal depth observation window.
5. The method for determining the envelope of lunar surface drilling and sampling conditions according to claim 1, characterized in that, The process of acquiring real-time telemetry data, performing data registration and feature value calculation on the real-time telemetry data to obtain on-orbit feature values specifically includes: Acquire real-time telemetry data, current drilling depth, and telemetry data timestamp or frame number, and perform data registration processing on the real-time telemetry data and the current drilling depth according to the telemetry data timestamp or frame number to obtain registered telemetry data; When the current drilling depth reaches the optimal depth observation window, target registration telemetry data where the drilling depth reaches the optimal depth observation window is extracted from the registration telemetry data; Based on the optimal statistical characteristics, feature values are calculated for the target registration telemetry data to obtain on-orbit feature values.
6. The method for determining the envelope of lunar surface drilling and sampling conditions according to claim 3, characterized in that, The process of acquiring real-time telemetry data, performing data registration and feature value calculation on the real-time telemetry data to obtain on-orbit feature values, further includes: The cumulative position ratio corresponding to the on-orbit feature value is calculated using an empirical distribution function, and the centrality score is calculated based on the cumulative position ratio. The absolute probability of the on-orbit feature value is calculated based on frequency statistics, and the absolute probability is normalized to obtain the relative frequency score. The feature discrimination capability of each telemetry parameter in each depth observation interval is calculated based on the cumulative location ratio, the centrality score, and the relative frequency score.
7. The method for determining the envelope of lunar surface drilling and sampling conditions according to claim 6, characterized in that, If the on-orbit feature value is determined to be within the safety envelope boundary, then the envelope compliance result is output, specifically including: The on-orbit feature value corresponding to each telemetry parameter is compared sequentially with the safety envelope boundary; If the on-orbit feature value corresponding to each telemetry parameter is within the safe envelope boundary, then the centrality scores corresponding to each telemetry parameter are summarized to obtain the envelope compliance result.
8. A system for determining the envelope of lunar surface drilling and sampling conditions, characterized in that, The system for determining the envelope of lunar surface drilling sampling conditions includes: The data preprocessing module is used to determine the lunar surface drilling simulation experiment, obtain the initial telemetry data sample in the lunar surface drilling simulation experiment, and perform data preprocessing on the initial telemetry data sample to obtain the target telemetry sample data. A multidimensional feature extraction module is used to extract multidimensional features from the target telemetry sample data to obtain a multidimensional feature set. The safe envelope boundary generation module is used to calculate the optimal statistical features and optimal depth observation window corresponding to each telemetry parameter in the multidimensional feature set, and to determine the safe envelope boundary based on the optimal statistical features and the optimal depth observation window. The on-orbit feature value generation module is used to acquire real-time telemetry data, perform data registration processing and feature value calculation on the real-time telemetry data, and obtain on-orbit feature values. The envelope compliance result output module is used to output the envelope compliance result if it is determined that the on-orbit feature value is within the safe envelope boundary.
9. A terminal, characterized in that, The terminal includes: a memory, a processor, and a lunar surface drilling sampling condition envelope determination program stored in the memory and executable on the processor. When the lunar surface drilling sampling condition envelope determination program is executed by the processor, it implements the steps of the lunar surface drilling sampling condition envelope determination method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for determining the lunar surface drilling sampling envelope. When the program for determining the lunar surface drilling sampling envelope is executed by a processor, it implements the steps of the method for determining the lunar surface drilling sampling envelope as described in any one of claims 1-7.
