Intelligent optimization method and system for trenchless track under complex stratum condition

Abstract

The present application relates to the technical field of pipeline construction, and more particularly to a non-excavation trajectory intelligent optimization method and system under complex stratum conditions. By obtaining three-dimensional geological stratification data, soil mechanical parameter distribution data and obstacle spatial position data in the black soil area, the black soil layer is identified and constraint conditions are set for spatial constraint domain division to obtain a feasible space. An initial trajectory is generated in the feasible space, and the path length, curvature change rate and disturbance are calculated. An evaluation function is constructed, and the optimized trajectory is obtained based on the hierarchical constraint weight correction gradient iteration optimization. The optimized trajectory is superimposed with the geological data to calculate the adaptation degree of each soil layer section. According to the adaptation degree, the process parameter combination is distributed to generate control instructions to drive the non-excavation crossing equipment to lay the pipeline along the optimized trajectory. The present application realizes intelligent protection of the soil structure in the black soil area, effectively reduces construction disturbance, and improves the accuracy and safety of pipeline crossing.

Description

Technical Field

[0001] This invention relates to the field of pipeline construction technology, and in particular to a method and system for intelligent optimization of trenchless trajectories under complex geological conditions. Background Technology

[0002] In pipeline engineering practices across black soil regions, existing technologies generally rely on surface surveys and empirical route planning. The conventional approach is as follows: first, the distribution range and basic physical and mechanical properties of the black soil layer are obtained through borehole sampling. Then, combined with the topographic map of the construction area and pipeline routing requirements, engineering technicians manually formulate a crossing route based on experience. This route typically prioritizes avoiding surface structures and known underground pipelines, but lacks a systematic consideration of the spatial heterogeneity within the black soil layer. Before construction, the advance angle of the trenchless equipment and mud parameters are adjusted to adapt to the preset route, ultimately completing the pipeline laying. This process can meet basic construction requirements under normal geological conditions.

[0003] The high organic matter content, strong collapsibility, and seasonal freeze-thaw cycles unique to black soil regions lead to a drastically non-uniform spatial distribution of soil mechanical parameters. Existing methods rely solely on a limited number of discrete sampling points for path planning, failing to quantify the degree of disturbance caused when the path traverses different soil regions. For example, in organic-rich areas or freeze-thaw sensitive zones, mechanical propulsion may induce local soil instability, leading to pipeline deformation or surface subsidence, but traditional experience-based judgments are insufficient to identify such risks in advance. The path optimization process is highly dependent on human experience, lacking quantitative analysis of the spatial coupling relationship between trajectory geometry (such as the rate of curvature change) and soil mechanical parameters. When the path needs to avoid obstacles or adapt to complex geological interfaces, manual adjustments often focus only on minimizing path length, ignoring the additional stress concentration caused by abrupt curvature changes. This increases the probability of pipeline failure due to uneven stress distribution in non-uniform soil layers. These shortcomings result in challenges such as low construction efficiency, significant environmental disturbance, and insufficient long-term service reliability for pipeline engineering in black soil regions. Summary of the Invention

[0004] This invention provides a method and system for intelligent optimization of trenchless trajectories under complex geological conditions, which can solve the problems in the prior art.

[0005] A first aspect of this invention provides a method for intelligent optimization of trenchless trajectories under complex geological conditions, comprising:

[0006] To obtain three-dimensional geological stratification data, soil mechanical parameter distribution data, and obstacle spatial location data of underground space in the black soil region;

[0007] The spatial distribution range of black soil layer in three-dimensional geological stratification data is identified. Constraints are set for black soil layer based on organic matter content, collapsibility coefficient and seasonal freeze-thaw depth. Spatial constraint domain is divided in combination with obstacle spatial location data to obtain feasible space.

[0008] An initial trajectory is generated within the feasible space. The path length and rate of curvature change are calculated based on the spatial geometry of the initial trajectory. The disturbance is calculated based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters.

[0009] An evaluation function is constructed based on the disturbance amount, path length, and rate of curvature change. Soil mechanical parameters at each node of the initial trajectory are extracted to establish hierarchical constraint weights. The gradient of the evaluation function is corrected based on the hierarchical constraint weights, and the initial trajectory is iteratively optimized to obtain the optimized trajectory.

[0010] The optimized trajectory is spatially overlaid with three-dimensional geological stratification data to identify the interaction positions between the optimized trajectory and each soil layer, calculate the fit of the optimized trajectory in each soil layer segment, and obtain the fit result.

[0011] Based on the adaptation results, process parameter combinations are assigned to different spatial segments of the optimized trajectory, control commands are generated, and trenchless crossing equipment is driven to lay pipelines along the optimized trajectory based on the control commands.

[0012] The spatial distribution range of the black soil layer in the three-dimensional geological stratification data was identified. Constraints were set for the black soil layer based on organic matter content, collapsibility coefficient, and seasonal freeze-thaw depth. The spatial constraint domain was divided in conjunction with the spatial location data of obstacles, resulting in the following feasible space:

[0013] Soil types of each soil layer are extracted from three-dimensional geological stratification data. The spatial distribution range of the soil type black soil is identified. The distribution data of soil mechanical parameters are spatially matched with the spatial distribution range of black soil to obtain the distribution of organic matter content and collapsibility coefficient.

[0014] The distribution of organic matter content and collapsibility coefficient were coupled to obtain the coupled risk index distribution. Based on the coupled risk index distribution, the spatial coordinate range of the black soil layer was divided into spatial constraint domains, resulting in prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains.

[0015] Based on the construction time point, the seasonal freeze-thaw depth is queried from the preset freeze-thaw depth database, and allowable and restricted crossing depth constraints are set for the allowable crossing constraint domain and the restricted crossing constraint domain, respectively.

[0016] The spatial location data of obstacles are spatially superimposed with the allowable crossing constraint domain and the restricted crossing constraint domain, and the overlapping area is removed. Vertical boundary constraints are set in the allowable crossing constraint domain and the restricted crossing constraint domain according to the allowable crossing burial depth constraint condition and the restricted crossing burial depth constraint condition, respectively, to obtain the feasible space.

[0017] The coupled calculation of organic matter content distribution and collapsibility coefficient distribution yields the coupled risk index distribution. Based on the coupled risk index distribution, the spatial coordinate range of the black soil layer is divided into spatial constraint domains, resulting in prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains, including:

[0018] The organic matter content and collapsibility coefficient values ​​of each spatial location point are extracted from the organic matter content distribution and collapsibility coefficient distribution. The coupling risk index value of each spatial location point is obtained by nonlinear coupling calculation of the organic matter content and collapsibility coefficient values.

[0019] The coupling risk index values ​​at each spatial location point are spatially interpolated to obtain the coupling risk index distribution, and the spatial gradient of the coupling risk index distribution is calculated to obtain the spatial gradient field.

[0020] Gradient abrupt change locations are extracted from the spatial gradient field, and these locations are connected to form the boundary line of the constrained domain. The spatial coordinate range of the black soil layer is then divided into multiple spatial partitions based on the boundary line of the constrained domain.

[0021] Cluster analysis is performed on the coupling risk index values ​​within each spatial partition to obtain risk clustering results. Based on the risk clustering results, the risk concentration index of each spatial partition is calculated. Based on the risk concentration index, each spatial partition is divided into prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains.

[0022] An initial trajectory is generated within the feasible space. Based on the spatial geometry of the initial trajectory, the path length and rate of change of curvature are calculated. The disturbance is calculated based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters, including:

[0023] Obtain the starting and ending coordinates of the pipeline crossing project, and arrange multiple intermediate control points between the starting and ending coordinates within the feasible space. Connect the starting and ending coordinates sequentially through the intermediate control points to generate the initial trajectory.

[0024] The initial trajectory is discretized to obtain the three-dimensional coordinates of each sampling point. The spatial distance between the three-dimensional coordinates of adjacent sampling points is calculated and summed to obtain the path length of the initial trajectory.

[0025] The curvature value of each sampling point is obtained by calculating the change in tangent direction at the three-dimensional coordinates of each sampling point, and the curvature change rate of the initial trajectory is obtained by performing a difference operation on the curvature values ​​of adjacent sampling points.

[0026] Based on the three-dimensional coordinates of each sampling point, the shear strength and compression modulus of the corresponding location in the soil mechanical parameter distribution data are extracted. The curvature value of each sampling point is weighted with the shear strength and compression modulus of the corresponding location to obtain the soil disturbance at each sampling point. The soil disturbance at each sampling point is integrated along the path length of the initial trajectory to obtain the disturbance of the initial trajectory.

[0027] An evaluation function is constructed based on the disturbance amount, path length, and rate of curvature change. Soil mechanical parameters at each node of the initial trajectory are extracted to establish hierarchical constraint weights. The gradient of the evaluation function is corrected based on these hierarchical constraint weights, and the initial trajectory is iteratively optimized to obtain the optimized trajectory, which includes:

[0028] We assign weight coefficients to the disturbance amount, path length, and rate of curvature change, and then sum them up to construct an evaluation function.

[0029] Extract the node coordinates of each node position of the initial trajectory, and extract the soil mechanical parameters of each node position of the initial trajectory from the soil mechanical parameter distribution data based on the node coordinates. The soil mechanical parameters include shear strength and compression modulus. Calculate the reciprocal of shear strength and the reciprocal of compression modulus, perform normalization processing, and then perform weighted summation to establish the layered constraint weights of each node position.

[0030] Calculate the gradient vector of the evaluation function with respect to the coordinates of each node, multiply the hierarchical constraint weights of each node position with the gradient vector of the corresponding node coordinates to obtain the corrected gradient vector, and adjust the coordinates of each node according to the corrected gradient vector to obtain the updated node coordinates.

[0031] The constrained node coordinates are obtained by updating the node coordinates to fit within the feasible space.

[0032] The evaluation function is recalculated based on the coordinates of the constraint nodes to obtain the current evaluation function value. It is then determined whether the difference between the current evaluation function value and the previous evaluation function value is less than the preset convergence threshold. If it is less than the preset convergence threshold, the coordinates of the constraint nodes are connected to obtain the optimized trajectory. Otherwise, the coordinates of the constraint nodes are used as the current node coordinates and the iteration optimization continues.

[0033] The optimized trajectory is spatially overlaid with 3D geological stratification data to identify the interaction positions between the optimized trajectory and each soil layer. The fit degree of the optimized trajectory in each soil layer segment is calculated, and the fit results include:

[0034] Extract the three-dimensional coordinates of each sampling point on the optimized trajectory, and spatially overlay the three-dimensional coordinates of each sampling point on the optimized trajectory with the three-dimensional geological stratification data to determine the soil layer type of each sampling point;

[0035] By statistically analyzing the crossing length and crossing angle of the optimized trajectory in each soil layer type, the interaction position between the optimized trajectory and each soil layer can be obtained.

[0036] Extract the shear strength and compression modulus from the soil mechanical parameter distribution data corresponding to the interaction position between the optimized trajectory and each soil layer, extract the curvature value at the interaction position between the optimized trajectory and each soil layer, and calculate the angle between the crossing direction and the soil layer division based on the crossing angle of the optimized trajectory in each soil layer.

[0037] The local fit is calculated based on shear strength, compression modulus, curvature value and included angle. The local fit is weighted and accumulated according to the crossing length to calculate the fit of the optimized trajectory in each soil layer segment.

[0038] The adaptation degree of the optimized trajectory in each soil layer is coupled with the geological environmental carrying capacity of the corresponding location to obtain a comprehensive adaptation index. The comprehensive adaptation index is then summarized to obtain the adaptation result.

[0039] Based on the adaptation results, process parameter combinations are assigned to different spatial segments of the optimized trajectory, control commands are generated, and the trenchless crossing equipment is driven to lay pipelines along the optimized trajectory based on the control commands, including:

[0040] Extract the comprehensive adaptation index of the optimized trajectory in each soil layer from the adaptation results, and establish the process control coefficient of the optimized trajectory in each soil layer based on the comprehensive adaptation index.

[0041] Extract the soil mechanical parameters corresponding to each soil layer of the optimized trajectory, determine the standard process parameters of the optimized trajectory in each soil layer based on the soil mechanical parameters, and couple the process control coefficient with the standard process parameters to obtain the basic process parameters of the optimized trajectory in each soil layer.

[0042] The corrected process parameters are obtained by dynamically correcting the foundation process parameters based on the rate of curvature change of the optimized trajectory in each soil layer.

[0043] The gradient of the change of the modified process parameters in the adjacent soil layer segment at the soil layer interface is calculated for the optimized trajectory. The transition process parameters and the length of the transition region at the soil layer interface are generated based on the gradient. The modified process parameters, the transition process parameters and the length of the transition region are combined to obtain the process parameter combination.

[0044] The process parameters are combined with the spatial coordinates of the optimized trajectory to generate control commands. These commands are then transmitted to the trenchless crossing equipment, which is used to lay the pipeline along the optimized trajectory.

[0045] A second aspect of the present invention provides a trenchless trajectory intelligent optimization system under complex geological conditions, comprising:

[0046] The data acquisition unit is used to acquire three-dimensional geological stratification data, soil mechanical parameter distribution data, and obstacle spatial location data of the underground space in the black soil region.

[0047] Spatial division units are used to identify the spatial distribution range of black soil layers in three-dimensional geological stratification data. Constraints are set for black soil layers based on organic matter content, collapsibility coefficient and seasonal freeze-thaw depth. Spatial constraint domains are divided in combination with obstacle spatial location data to obtain feasible space.

[0048] The trajectory generation unit is used to generate an initial trajectory within the feasible space, calculate the path length and rate of curvature change based on the spatial geometry of the initial trajectory, and calculate the disturbance amount based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters.

[0049] The weight correction unit is used to construct an evaluation function based on the disturbance amount, path length and curvature change rate, extract the soil mechanical parameters of each node position of the initial trajectory to establish hierarchical constraint weights, correct the gradient of the evaluation function based on the hierarchical constraint weights and iteratively optimize the initial trajectory to obtain the optimized trajectory.

[0050] The adaptation evaluation unit is used to spatially overlay the optimized trajectory with three-dimensional geological stratification data, identify the interaction positions between the optimized trajectory and each soil layer, calculate the adaptation degree of the optimized trajectory in each soil layer segment, and obtain the adaptation result.

[0051] The command and control unit is used to allocate process parameter combinations to different spatial segments of the optimized trajectory based on the adaptation results, generate control commands, and drive the trenchless crossing equipment to lay pipelines along the optimized trajectory based on the control commands.

[0052] A third aspect of the present invention provides an electronic device, comprising:

[0053] processor;

[0054] Memory used to store processor-executable instructions;

[0055] The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0056] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0057] Compared with existing technologies, this method significantly reduces the disturbance and damage to the soil structure in black soil regions. By setting constraints based on the organic matter content, collapsibility coefficient, and seasonal freeze-thaw depth of the black soil layer, and combining obstacle spatial data to delineate feasible spaces, the pipeline trajectory automatically avoids highly sensitive black soil areas, preventing black soil layer compaction, organic matter loss, and freeze-thaw cycle damage caused by blind crossings in traditional construction. The disturbance calculation is directly related to the distribution of soil mechanical parameters, ensuring that the trajectory optimization process always prioritizes minimizing soil disturbance. The mechanical properties of different soil layers are converted into weighting factors, automatically adjusting the curvature and burial depth of the trajectory in soft soil layers, hard soil layers, or freeze-thaw interfaces, optimizing the path length and curvature change rate while ensuring structural safety. This layered adaptive optimization mechanism avoids the risks of local over-bending or excessive crossing of weak soil layers caused by single-parameter optimization. The fit calculation results accurately match the process parameter combinations for each spatial segment. By clearly identifying the interfaces between the pipeline and each soil layer, process parameters such as drilling speed, mud pressure, and pullback force are allocated accordingly, ensuring that the most suitable construction strategy is adopted for each crossing section. Control commands directly drive trenchless equipment to operate along the optimized trajectory, realizing closed-loop intelligent control from geological perception to construction execution, significantly improving crossing accuracy and construction efficiency. Attached Figure Description

[0058] Figure 1 This is a flowchart illustrating the intelligent optimization method for non-excavation trajectory under complex geological conditions according to an embodiment of the present invention.

[0059] Figure 2 This is a flowchart of trajectory iterative optimization based on hierarchical constraints and gradient correction in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0062] Figure 1 This is a flowchart illustrating the intelligent optimization method for non-excavation trajectories under complex geological conditions according to an embodiment of the present invention.

[0063] Intelligent optimization methods for trenchless trajectories under complex geological conditions include:

[0064] To obtain three-dimensional geological stratification data, soil mechanical parameter distribution data, and obstacle spatial location data of underground space in the black soil region;

[0065] The spatial distribution range of black soil layer in three-dimensional geological stratification data is identified. Constraints are set for black soil layer based on organic matter content, collapsibility coefficient and seasonal freeze-thaw depth. Spatial constraint domain is divided in combination with obstacle spatial location data to obtain feasible space.

[0066] An initial trajectory is generated within the feasible space. The path length and rate of curvature change are calculated based on the spatial geometry of the initial trajectory. The disturbance is calculated based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters.

[0067] An evaluation function is constructed based on the disturbance amount, path length, and rate of curvature change. Soil mechanical parameters at each node of the initial trajectory are extracted to establish hierarchical constraint weights. The gradient of the evaluation function is corrected based on the hierarchical constraint weights, and the initial trajectory is iteratively optimized to obtain the optimized trajectory.

[0068] The optimized trajectory is spatially overlaid with three-dimensional geological stratification data to identify the interaction positions between the optimized trajectory and each soil layer, calculate the fit of the optimized trajectory in each soil layer segment, and obtain the fit result.

[0069] Based on the adaptation results, process parameter combinations are assigned to different spatial segments of the optimized trajectory, control commands are generated, and trenchless crossing equipment is driven to lay pipelines along the optimized trajectory based on the control commands.

[0070] The spatial distribution range of the black soil layer in the three-dimensional geological stratification data was identified. Constraints were set for the black soil layer based on organic matter content, collapsibility coefficient, and seasonal freeze-thaw depth. The spatial constraint domain was divided in conjunction with the spatial location data of obstacles, resulting in the following feasible space:

[0071] Soil types of each soil layer are extracted from three-dimensional geological stratification data. The spatial distribution range of the soil type black soil is identified. The distribution data of soil mechanical parameters are spatially matched with the spatial distribution range of black soil to obtain the distribution of organic matter content and collapsibility coefficient.

[0072] The distribution of organic matter content and collapsibility coefficient were coupled to obtain the coupled risk index distribution. Based on the coupled risk index distribution, the spatial coordinate range of the black soil layer was divided into spatial constraint domains, resulting in prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains.

[0073] Based on the construction time point, the seasonal freeze-thaw depth is queried from the preset freeze-thaw depth database, and allowable and restricted crossing depth constraints are set for the allowable crossing constraint domain and the restricted crossing constraint domain, respectively.

[0074] The spatial location data of obstacles are spatially superimposed with the allowable crossing constraint domain and the restricted crossing constraint domain, and the overlapping area is removed. Vertical boundary constraints are set in the allowable crossing constraint domain and the restricted crossing constraint domain according to the allowable crossing burial depth constraint condition and the restricted crossing burial depth constraint condition, respectively, to obtain the feasible space.

[0075] Soil type identifiers for each soil layer were extracted from 3D geological stratification data. Based on geological classification codes, the stratified records of underground space were scanned layer by layer. The soil type identifiers were compared with the classification characteristics of black soil layers to identify the entire spatial distribution range of soil layers classified as black soil. Black soil layers typically exhibit characteristics such as high organic matter content and a dark humus layer, which can be distinguished in geological stratification data through soil layer codes or lithological description fields. After identifying the spatial range of black soil layers, the distribution data of soil mechanical parameters was spatially matched with the spatial distribution range of black soil layers. Specifically, the 3D coordinate boundaries of the black soil layers were used as the clipping domain, and the distribution of organic matter content and collapsibility coefficient falling within this range was extracted from the soil mechanical parameter distribution data. Organic matter content reflects the ecological sensitivity of black soil layers; higher organic matter content indicates a more fragile soil structure and poorer recovery ability after disturbance. The collapsibility coefficient characterizes the tendency of soil to subside and deform under external forces or water immersion conditions; a higher collapsibility coefficient indicates a higher potential risk of damage to surface and underground structures from pipeline construction.

[0076] The distribution of organic matter content and collapsibility coefficient were coupled and calculated to obtain the coupled risk index distribution. The core idea of ​​the coupled calculation is to weightedly superimpose the spatial distributions of the two types of parameters in the same coordinate system to comprehensively reflect the overall risk level of each spatial location in the black soil layer. Let the organic matter content at a certain spatial location within the black soil layer be... The collapsibility coefficient is Then the coupling risk index at that location It can be represented as ,in and These are the dimensionless values ​​of organic matter content and collapsibility coefficient after normalization, respectively. and These are the corresponding weighting coefficients, and their sum is 1. The weight values ​​are determined based on engineering experience and regional geological characteristics. A coupling risk index distribution field is formed by calculating the coupling risk index point-by-point across the entire spatial coordinates of the black soil layer. Based on the coupling risk index distribution, the spatial coordinate range of the black soil layer is divided into three levels of spatial constraint domains: when... Exceeding the preset high-risk threshold When this space is designated as a prohibited crossing constraint region, it means that the pipeline trajectory must absolutely not enter this region; when Between low risk threshold With high risk threshold When the pipeline is between these two points, the corresponding area is designated as a restricted crossing constraint region, indicating that the pipeline can conditionally cross under specific process conditions; when... Below At this point, the corresponding area is designated as a permissible crossing constraint domain, indicating that the area is suitable for pipeline crossing construction at the geological risk level. The spatial boundary of the Level 3 constraint domain is stored in the form of a 3D polygon or voxel mesh for subsequent trajectory planning.

[0077] The seasonal freeze-thaw depth is retrieved from a pre-defined freeze-thaw depth database based on the construction time point. This database is constructed based on the geographical location of the construction area, historical meteorological data, and soil thermophysical parameters, storing statistical and extreme values ​​of freeze-thaw depth for each region by month or season. The query retrieves the seasonal freeze-thaw depth under the current construction conditions by using the month or season corresponding to the construction time point as an index, combined with the geographical coordinates of the construction area. Seasonal freeze-thaw depth characterizes the maximum depth at which soil below the surface freezes or thaws. If a pipeline crosses within this freeze-thaw influence depth, it will face the dual threats of frost heave and thaw settlement deformation. Therefore, freeze-thaw depth is a key parameter for determining the burial depth constraint conditions for crossing. For the allowable crossing constraint domain, allowable crossing burial depth constraints are set: the burial depth of the pipeline trajectory within this domain. Must meet ,in To allow for a safety margin in the crossing zone, the value is determined by comprehensively considering the soil's thermal conductivity and the pipe's outer diameter. For the restricted crossing zone, since the soil's collapsibility and organic matter content are at a moderate risk level, a more stringent constraint on the crossing depth is set: the burial depth of the pipe trajectory within this zone... Must meet ,in This means that the safety margin for limiting the crossing area is greater, in order to further reduce the risk of freeze-thaw cycles affecting the pipeline structure.

[0078] The spatial location data of obstacles is spatially overlaid with the permissible and restricted crossing constraint domains to identify overlapping areas between the space occupied by obstacles and these two types of constraint domains. These overlapping areas are then removed from the corresponding constraint domains. Obstacles include existing underground pipelines, structure foundations, groundwater bodies, and cultural relic protection areas, and their spatial location data is expressed in three-dimensional coordinate volumes or buffer zones. The spatial overlay operation uses three-dimensional Boolean subtraction to trim the obstacle buffer volume from the permissible and restricted crossing constraint domains one by one, obtaining the effective constraint domain after removing the influence of obstacles. The buffer zone radius is determined based on the obstacle type and the disturbance range of pipeline construction. For highly sensitive obstacles such as pressure pipelines, the buffer zone radius should be appropriately increased to ensure safe construction distances.

[0079] After removing overlapping obstacle areas, vertical boundary constraints are set within the permissible and restricted crossing constraint domains, respectively, based on the permissible and restricted crossing depth constraints. These vertical boundary constraints use the spatial coordinates of each constraint domain as a reference, defining the minimum and maximum burial depth surfaces for the pipeline trajectory in the vertical direction, forming a vertically feasible interval. The minimum burial depth surface is determined by the sum of the freeze-thaw depth and the safety margin, while the maximum burial depth surface is determined by comprehensively considering factors such as the maximum drilling capacity of trenchless equipment, the groundwater level depth, and the drillability of the underlying rock strata. A three-dimensional intersection operation is performed between the horizontal ranges of the permissible and restricted crossing constraint domains and their respective vertical feasible intervals to obtain the feasible space. The feasible space is expressed as a set of three-dimensional voxels or parameterized boundary surfaces, and all spatial locations within it satisfy organic matter protection constraints, collapsibility risk constraints, freeze-thaw depth constraints, and obstacle safety distance constraints, providing a compliant spatial search domain for subsequent initial trajectory generation and trajectory optimization.

[0080] The coupled calculation of organic matter content distribution and collapsibility coefficient distribution yields the coupled risk index distribution. Based on the coupled risk index distribution, the spatial coordinate range of the black soil layer is divided into spatial constraint domains, resulting in prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains, including:

[0081] The organic matter content and collapsibility coefficient values ​​of each spatial location point are extracted from the organic matter content distribution and collapsibility coefficient distribution. The coupling risk index value of each spatial location point is obtained by nonlinear coupling calculation of the organic matter content and collapsibility coefficient values.

[0082] The coupling risk index values ​​at each spatial location point are spatially interpolated to obtain the coupling risk index distribution, and the spatial gradient of the coupling risk index distribution is calculated to obtain the spatial gradient field.

[0083] Gradient abrupt change locations are extracted from the spatial gradient field, and these locations are connected to form the boundary line of the constrained domain. The spatial coordinate range of the black soil layer is then divided into multiple spatial partitions based on the boundary line of the constrained domain.

[0084] Cluster analysis is performed on the coupling risk index values ​​within each spatial partition to obtain risk clustering results. Based on the risk clustering results, the risk concentration index of each spatial partition is calculated. Based on the risk concentration index, each spatial partition is divided into prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains.

[0085] From the distribution data of organic matter content and collapsibility coefficient, the values ​​of organic matter content and collapsibility coefficient corresponding to each spatial location point are extracted one by one. Since the dimensions and numerical ranges of the two types of indicators differ, direct superposition would lead to dimensional inconsistencies. Therefore, before coupling calculations, the two types of values ​​need to be normalized separately, mapping them to a unified dimensionless interval to ensure the rationality of subsequent coupling calculations. After normalization, a nonlinear coupling method is used to calculate the coupling risk index value for each spatial location point. The significance of nonlinear coupling lies in the fact that the influence of organic matter content and collapsibility coefficient on the risk of traversing black soil areas is not a simple linear superposition; there is an interactive reinforcing effect between the two—when the organic matter content is high, the soil's water-holding capacity increases, further exacerbating collapsibility. Therefore, the coupling risk index should reflect this nonlinear superposition characteristic. Specifically, the coupling risk index... The calculation method is as follows ,in This is the normalized value of organic matter content. This is the normalized value of the collapsibility coefficient. , These are the weighting coefficients for the two types of indicators, respectively. , For their respective nonlinear exponents, The coefficient of the interaction term is used to characterize the coupling enhancement effect between the two types of indicators. , and The values ​​are determined based on field exploration data and historical engineering cases, and are usually... , This is to reflect the nonlinear amplification characteristics of high-risk areas.

[0086] After obtaining the coupled risk index values ​​at each spatial location, due to the uneven spatial distribution of the measured sampling points, spatial interpolation is required to convert the discrete data into a continuous coupled risk index distribution field. Kriging interpolation is the preferred interpolation method, as it can utilize spatial autocorrelation structures to provide unbiased optimal estimates for unsampled locations, making it suitable for the spatial continuity characteristics of geological parameters. After interpolation, spatial gradient calculations are performed on the coupled risk index distribution field to obtain the spatial gradient field. The spatial gradient field reflects the rate and direction of change of the coupled risk index in three-dimensional space. Locations with larger gradient values ​​correspond to regions where the risk index changes abruptly, i.e., the boundaries of transition zones between different risk levels. Gradient calculations are performed separately in three coordinate directions to ensure that the abrupt risk changes in the horizontal and vertical directions are captured, which is particularly important for the depth-related heterogeneity of the stratigraphic structure in the black soil region.

[0087] Gradient abrupt change locations are extracted from the spatial gradient field; these are the sets of spatial points whose gradient magnitudes exceed a set threshold. The gradient abrupt change threshold is determined based on the statistical distribution characteristics of the overall gradient field, typically using the upper quartile of the gradient magnitude distribution as the initial threshold, and adjusted appropriately based on engineering experience. After extracting the gradient abrupt change locations, these spatial points are connected to form the boundary lines of the constrained domain. The boundary line connection process employs a spatial topology tracing algorithm, tracing paths along the spatial continuity of the gradient abrupt change points to ensure the formation of closed or semi-closed boundary curves. For boundaries in three-dimensional space, the boundary lines are actually a set of spatial surfaces; their projection onto the horizontal section forms a two-dimensional boundary profile, while on the vertical section, they represent the variation of risk zones at different depths. Based on the boundary lines of the constrained domain, the three-dimensional spatial coordinate range of the black soil layer is divided into multiple spatial zones. The coupling risk index values ​​within each spatial zone are relatively homogeneous, while the risk levels between different zones differ significantly.

[0088] Cluster analysis was performed on the coupled risk index values ​​within each spatial partition to objectively identify the natural grouping of risk levels. A density-based spatial clustering method was employed, which does not require pre-specifying the number of clusters, adaptively discovers the clustering patterns of risk indices within each partition, and exhibits good robustness to outliers. After clustering, the risk clustering results for each spatial partition were obtained, i.e., the risk index values ​​within each partition were assigned to several risk level clusters. Based on this, the risk concentration index for each spatial partition was calculated. Risk Concentration Index Defined as the first The proportion of sample points in high-risk clusters within a spatial partition to the total number of sample points in that partition, i.e. ,in For the first The number of location points within a partition that belong to high-risk clusters. For the first The total number of locations within a zone. The risk concentration index comprehensively reflects the proportion of high-risk areas within a spatial zone; a higher value indicates a more concentrated overall risk within that zone.

[0089] Based on the risk concentration index, each spatial partition is divided into three types of constraint domains. When Exceeding the high-risk threshold At that time, the corresponding zone was designated as a prohibited crossing constraint area. This area has high organic matter content and strong collapsibility; pipeline crossing would cause irreversible structural disturbance to the black soil layer, and the probability of ground instability during construction is extremely high. Therefore, this area was completely excluded during the trajectory planning stage. Between low risk threshold With high risk threshold During this period, the corresponding zone is designated as a restricted crossing constraint region. Within this region, the risk level is moderate, and the pipeline trajectory can cross under specific process conditions, but must meet burial depth constraints. and safety margin The requirements are met, and targeted disturbance reduction measures are adopted in the subsequent process parameter allocation stage. When Below the low risk threshold At that time, the corresponding zone was designated as a permitted crossing constraint area, where the soil risk was low, and the pipeline trajectory could meet the burial depth constraints. and safety margin Under the premise of free planning, the selection of process parameters has great flexibility.

[0090] The spatial boundary information of the three types of constraint domains is fused and stored with the original 3D geological stratification data to form a complete spatial constraint domain dataset, which can be directly called upon in the subsequent feasible space generation and trajectory optimization stages. The prohibited crossing constraint domain is treated as a hard exclusion area when delineating the feasible space, the restricted crossing constraint domain is treated as a conditional soft constraint area, and the allowed crossing constraint domain is used as a preferred trajectory path. This three-level constraint domain division mechanism directly transforms the geological risk assessment results into spatial constraints for trajectory planning, realizing a quantitative mapping from geological exploration data to engineering decisions. It effectively avoids the problem of unreasonable crossing paths caused by relying on experience judgment in traditional trenchless construction, and provides scientifically reliable spatial boundary conditions for the subsequent generation of optimized trajectories.

[0091] An initial trajectory is generated within the feasible space. Based on the spatial geometry of the initial trajectory, the path length and rate of change of curvature are calculated. The disturbance is calculated based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters, including:

[0092] Obtain the starting and ending coordinates of the pipeline crossing project, and arrange multiple intermediate control points between the starting and ending coordinates within the feasible space. Connect the starting and ending coordinates sequentially through the intermediate control points to generate the initial trajectory.

[0093] The initial trajectory is discretized to obtain the three-dimensional coordinates of each sampling point. The spatial distance between the three-dimensional coordinates of adjacent sampling points is calculated and summed to obtain the path length of the initial trajectory.

[0094] The curvature value of each sampling point is obtained by calculating the change in tangent direction at the three-dimensional coordinates of each sampling point, and the curvature change rate of the initial trajectory is obtained by performing a difference operation on the curvature values ​​of adjacent sampling points.

[0095] Based on the three-dimensional coordinates of each sampling point, the shear strength and compression modulus of the corresponding location in the soil mechanical parameter distribution data are extracted. The curvature value of each sampling point is weighted with the shear strength and compression modulus of the corresponding location to obtain the soil disturbance at each sampling point. The soil disturbance at each sampling point is integrated along the path length of the initial trajectory to obtain the disturbance of the initial trajectory.

[0096] Obtaining the coordinates of the starting and ending points of the pipeline crossing project is a prerequisite for generating the initial trajectory. These coordinates are determined during the engineering survey phase and typically correspond to the three-dimensional spatial coordinates of the pipeline entry and exit points, including planar position and elevation information. Within the feasible space, multiple intermediate control points are arranged between the starting and ending coordinates. The number and location of these control points are determined comprehensively based on the geometry of the feasible space, geological strata distribution characteristics, and the spatial distribution of obstacles. Intermediate control points are evenly distributed within the feasible space or densely arranged in areas of dense geological variation to ensure that the generated initial trajectory remains within the feasible space throughout the entire crossing process. By sequentially connecting the starting and ending coordinates through the intermediate control points, a continuous and smooth initial trajectory is generated using cubic spline interpolation or B-spline curve fitting. This ensures that the trajectory has continuous first and second derivatives at each control point, thereby guaranteeing that the geometric smoothness of the trajectory meets the construction requirements of trenchless crossing equipment.

[0097] Discretizing the initial trajectory is a fundamental operation for subsequent calculations of path length, rate of curvature change, and disturbance. Sampling is performed along the initial trajectory at equal arc length intervals or equal parametric intervals, resulting in a series of three-dimensional coordinate sequences of sampling points. The selection of the sampling interval must balance computational accuracy and efficiency; in sections with complex geological variations or high curvature, the sampling interval should be appropriately reduced to improve local computational accuracy. Let the first... The three-dimensional coordinates of each sampling point are Adjacent sampling points and Spatial distance between Calculated using the Euclidean distance formula, i.e. The path length of the initial trajectory is obtained by sequentially summing the spatial distances of all adjacent sampling points. ,Right now ,in Total number of sampling points. Path length. It directly reflects the actual laying length of the pipeline during its underground crossing. The shorter the path length, the smaller the workload and the lower the construction risk. Therefore, path length is one of the important geometric indicators for evaluating the quality of the initial trajectory.

[0098] The calculation of the rate of curvature change reflects the degree of curvature of the initial trajectory in space and its changing trend along the trajectory direction. At each sampling point, the tangent direction vector is calculated based on the three-dimensional coordinates of three adjacent sampling points. The tangent direction vector is obtained by normalizing the coordinate differences between adjacent sampling points. Let the... The tangent unit vector at each sampling point is The change in the tangent direction between adjacent sampling points can be measured by the cosine of the angle between the two tangent vectors, and then the arc length interval between adjacent sampling points can be used to calculate the first... curvature value at each sampling point Curvature value The physical meaning of curvature is the angle of rotation of the trajectory along the inward tangent direction per unit arc length at that point; a larger curvature value indicates a more pronounced curvature at that point. After obtaining the curvature value sequence for each sampling point, a difference operation is performed on the curvature values ​​of adjacent sampling points, i.e., calculation... Then divide by the corresponding arc length interval to obtain the rate of change of curvature at each sampling point. Rate of change of curvature It describes the rate of change of the curvature along the path direction. An excessive rate of curvature change means that there is a sharp turn in the trajectory, which will generate a large additional stress on the drill bit guide mechanism and the pipeline body of the trenchless crossing equipment. Therefore, the rate of curvature change is a key parameter that constrains the geometry of the trajectory.

[0099] Calculating soil disturbance requires combining the geometric characteristics of the trajectory with the mechanical properties of the soil along the route. Based on the three-dimensional coordinates of each sampling point, the shear strength and compression modulus at the corresponding locations are extracted from the soil mechanical parameter distribution data. Shear strength reflects the soil's ability to resist shear failure, while compression modulus reflects the soil's deformation stiffness under compression conditions. Both together determine the degree of disturbance to the surrounding soil caused by the trenchless tunneling equipment during its advancement. Soil with lower shear strength is more prone to shear failure under drilling disturbance, while soil with lower compression modulus deforms more under lateral compression. Both situations exacerbate the damage to the original structure of the black soil layer. Let the first... The shear strength at each sampling point is Compression modulus is The curvature value is The amount of soil disturbance at that sampling point It is obtained through weighted calculation, that is ,in and These are the weighting coefficients for the reciprocals of shear strength and compression modulus, respectively, in the calculation of disturbance. Both are determined based on the engineering geological characteristics of the soil in the black soil region. The physical meaning of this weighted calculation method is that: the greater the curvature value, the greater the lateral force exerted on the soil by the equipment at that point; the lower the shear strength or the smaller the compression modulus, the weaker the soil's resistance to that lateral force, and therefore the greater the overall disturbance.

[0100] The soil disturbance at each sampling point was obtained. Then, the total disturbance of the initial trajectory is obtained by integrating the path length along the initial trajectory. Within the framework of discretization, integration is implemented using numerical integration methods, i.e. ,in For the first The sampling point and the first The arc length interval between each sampling point. Overall perturbation. This comprehensive indicator reflects the cumulative disturbance caused by the initial trajectory to the black soil region along the entire traverse path, and is a core indicator for evaluating the trajectory's impact on the black soil region's ecological environment. In areas where the black soil layer is rich in organic matter and has a sensitive soil structure, even with small local curvature, if the shear strength and compression modulus of that section are low, the disturbance to the overall soil mass will be significant. The contribution will still be significantly larger. This calculation mechanism can effectively guide the subsequent trajectory optimization process to actively avoid the spatial areas most sensitive to disturbance of the black soil layer, thereby achieving the goal of harmlessness in the pipeline crossing process.

[0101] Path length rate of change of curvature and overall disturbance These three indicators together constitute a quantitative description of the overall performance of the initial trajectory, providing a complete input data foundation for subsequent construction of the evaluation function and iterative optimization.

[0102] like Figure 2 As shown, Figure 2 This is a flowchart of trajectory iterative optimization based on hierarchical constraints and gradient correction in an embodiment of the present invention.

[0103] An evaluation function is constructed based on the disturbance amount, path length, and rate of curvature change. Soil mechanical parameters at each node of the initial trajectory are extracted to establish hierarchical constraint weights. The gradient of the evaluation function is corrected based on these hierarchical constraint weights, and the initial trajectory is iteratively optimized to obtain the optimized trajectory, which includes:

[0104] We assign weight coefficients to the disturbance amount, path length, and rate of curvature change, and then sum them up to construct an evaluation function.

[0105] Extract the node coordinates of each node position of the initial trajectory, and extract the soil mechanical parameters of each node position of the initial trajectory from the soil mechanical parameter distribution data based on the node coordinates. The soil mechanical parameters include shear strength and compression modulus. Calculate the reciprocal of shear strength and the reciprocal of compression modulus, perform normalization processing, and then perform weighted summation to establish the layered constraint weights of each node position.

[0106] Calculate the gradient vector of the evaluation function with respect to the coordinates of each node, multiply the hierarchical constraint weights of each node position with the gradient vector of the corresponding node coordinates to obtain the corrected gradient vector, and adjust the coordinates of each node according to the corrected gradient vector to obtain the updated node coordinates.

[0107] The constrained node coordinates are obtained by updating the node coordinates to fit within the feasible space.

[0108] The evaluation function is recalculated based on the coordinates of the constraint nodes to obtain the current evaluation function value. It is then determined whether the difference between the current evaluation function value and the previous evaluation function value is less than the preset convergence threshold. If it is less than the preset convergence threshold, the coordinates of the constraint nodes are connected to obtain the optimized trajectory. Otherwise, the coordinates of the constraint nodes are used as the current node coordinates and the iteration optimization continues.

[0109] The evaluation function is constructed based on three indicators: disturbance amount, path length, and rate of curvature change. A comprehensive quantification is achieved by assigning weight coefficients to each indicator and then summing them using weighted averages. Let the weight coefficient for the disturbance amount be... The weighting coefficient for path length is The weighting coefficient for the rate of change of curvature is Then the evaluation function Represented as ,in This represents the mean or cumulative rate of curvature change of all sampling points on the initial trajectory, depending on the requirements for trajectory smoothness in the engineering scenario. The three weighting coefficients satisfy... All values ​​are greater than zero to ensure that the evaluation function remains sensitive to all three indicators. In the black soil region crossing scenario, the disturbance amount corresponds to the degree of damage to the black soil structure caused by pipeline construction, and its weight coefficient is usually assigned a high value to prioritize the protection of the ecological integrity of the black soil layer; the path length weight coefficient reflects the engineering economic constraints; and the curvature change rate weight coefficient reflects the mechanical feasibility requirements of trenchless equipment at trajectory turns.

[0110] The establishment of layered constraint weights depends on the soil mechanical parameters at each node location. After extracting the three-dimensional coordinates of each node in the initial trajectory, the shear strength at that node is obtained through spatial interpolation or by directly querying the soil mechanical parameter distribution data. and compressive modulus Because soil layers with lower shear strength are more prone to shear failure under construction disturbance, and soil layers with lower compression modulus are more prone to compressive deformation under stress, using the reciprocal of both as the basis for weight calculation allows the weight value to automatically increase at locations with weak mechanical properties, thereby imposing stronger constraints on trajectory nodes in subsequent gradient correction. The reciprocal of shear strength... and the reciprocal of the compressive modulus Normalization was performed separately to obtain the dimensionless reciprocal of the normalized shear strength. and the reciprocal of the normalized compressibility modulus The normalization process employs a max-min normalization method, using the maximum and minimum values ​​of the corresponding quantities across all nodes as the upper and lower bounds of the normalization to ensure that all indicators are of the same numerical magnitude. After normalization, the weighting coefficient for the reciprocal of the shear strength is set as follows: The weighting factor for the reciprocal of the compressibility modulus is ,and Then the first Hierarchical constraint weights at each node Represented as The larger the weight value, the weaker the mechanical properties of the soil layer where the node is located. In the iterative optimization process, it is necessary to impose stricter restrictions on the movement step size of the node to prevent excessive disturbance of the fragile soil layer by trajectory adjustment.

[0111] The gradient vector is calculated for the evaluation function. Expand the partial derivatives with respect to the coordinates of each node. Let the th... The coordinate vector of each node is Then the gradient vector of the evaluation function for the coordinates of that node. This describes the direction and rate of change of the evaluation function value with respect to the node position at the current node coordinates. The gradient vector can be calculated using the numerical difference method, that is, applying a small perturbation to each coordinate component separately. Calculate the change in the evaluation function value, then divide by Obtain the partial derivative components in the corresponding directions. Combine the partial derivatives in the three coordinate directions to obtain the complete gradient vector. After obtaining the gradient vector, combine it with the hierarchical constraint weights at that node. Multiplying them together yields the corrected gradient vector. The physical meaning of correcting the gradient vector is as follows: for nodes in soil layers with weak mechanical properties, by amplifying the magnitude of the gradient vector, the equivalent step size of the node during gradient descent updates is relatively increased, thereby driving the optimization process to more actively move the node away from high-risk areas; while for nodes in stable soil layers, the weight value is smaller, the gradient correction magnitude is relatively mild, and the trajectory is allowed to make a larger range of path adjustments in this area to reduce the path length or rate of curvature change.

[0112] The node coordinates are updated based on the corrected gradient vector, following a gradient descent approach. Let the iteration step size be... Then the updated node coordinates Depend on Calculated step size. The choice of step size has a significant impact on iterative convergence. An excessively large step size may cause nodes to oscillate near the feasible space boundary, while an excessively small step size will result in slow convergence. In practical applications, an adaptive step size strategy can be adopted, dynamically adjusting the step size based on the change in the evaluation function value between adjacent iterations. This is done to balance convergence speed and stability. After the coordinate update is completed, the updated node coordinates are obtained. However, the updated coordinates may exceed the boundary of the feasible space, requiring further constraint projection processing.

[0113] The process of updating node coordinates to fit within the feasible space is called constraint projection. For nodes outside the feasible space boundary, they are projected onto the feasible space boundary along the nearest distance direction, ensuring that they exactly satisfy the spatial constraints. If the updated node coordinates are already within the feasible space, no projection is needed; they are directly used as the constraint node coordinates. The feasible space boundary is determined by the spatial constraint domain partitioning results in the previous steps, including the restricted crossing domain boundary delineated based on the coupling risk index within the black soil layer, the obstacle safety distance boundary, and the burial depth constraint below the ground surface. The constraint projection operation ensures that the coordinates of all nodes are strictly within the feasible space after each iteration, thereby ensuring that the optimized trajectory always meets the engineering safety requirements.

[0114] The evaluation function is recalculated based on the coordinates of the constraint nodes to obtain the evaluation function value for the current iteration. .Will The evaluation function value compared to the previous iteration Calculate the difference, and then calculate the absolute value of the difference. .like Less than the preset convergence threshold If the iteration has converged, the coordinates of the current constraint nodes are connected sequentially to form a continuous spatial curve, which is the output result of the optimized trajectory. Not less than If the current constraint node coordinates are not met, the current constraint node coordinates will be used as the initial node coordinates for the next iteration. The entire process of gradient calculation, gradient correction, coordinate update, and constraint projection will be re-executed until the convergence condition is met. Convergence threshold. The threshold setting should be determined comprehensively based on engineering accuracy requirements and computational resource constraints. A threshold that is too small will prolong the number of iterations, while a threshold that is too large may lead to insufficient optimization results. In practical engineering, a maximum number of iterations is usually set as an additional termination condition; when the number of iterations reaches the upper limit... If the convergence condition is still not met, the connection result of the constraint node coordinates in the current round is taken as the approximate optimized trajectory output, and an early warning is triggered for manual review by engineers. After the above complete iterative optimization process, the final optimized trajectory, under the premise of satisfying the feasible space constraints, comprehensively minimizes the disturbance of the black soil layer, path length, and rate of curvature change. It also protects the mechanically weak soil layer area through the layered constraint weight mechanism, providing a high-quality trajectory basis for subsequent process parameter allocation.

[0115] The optimized trajectory is spatially overlaid with 3D geological stratification data to identify the interaction positions between the optimized trajectory and each soil layer. The fit degree of the optimized trajectory in each soil layer segment is calculated, and the fit results include:

[0116] Extract the three-dimensional coordinates of each sampling point on the optimized trajectory, and spatially overlay the three-dimensional coordinates of each sampling point on the optimized trajectory with the three-dimensional geological stratification data to determine the soil layer type of each sampling point;

[0117] By statistically analyzing the crossing length and crossing angle of the optimized trajectory in each soil layer type, the interaction position between the optimized trajectory and each soil layer can be obtained.

[0118] Extract the shear strength and compression modulus from the soil mechanical parameter distribution data corresponding to the interaction position between the optimized trajectory and each soil layer, extract the curvature value at the interaction position between the optimized trajectory and each soil layer, and calculate the angle between the crossing direction and the soil layer division based on the crossing angle of the optimized trajectory in each soil layer.

[0119] The local fit is calculated based on shear strength, compression modulus, curvature value and included angle. The local fit is weighted and accumulated according to the crossing length to calculate the fit of the optimized trajectory in each soil layer segment.

[0120] The adaptation degree of the optimized trajectory in each soil layer is coupled with the geological environmental carrying capacity of the corresponding location to obtain a comprehensive adaptation index. The comprehensive adaptation index is then summarized to obtain the adaptation result.

[0121] Extracting the 3D coordinates of each sampling point on the optimized trajectory and spatially overlaying these coordinates with 3D geological stratification data is a fundamental step in calculating the fit. The 3D geological stratification data is stored in the form of voxel grids or irregular tetrahedral grids, with each grid cell carrying a corresponding soil layer type label. The 3D coordinates of each sampling point on the optimized trajectory are mapped one by one into the geological grid. The soil layer type of each sampling point is determined by its affiliation in the voxels, including black soil, sub-clay, gravel, and bedrock. For sampling points that fall near the interface between two layers, nearest neighbor interpolation is used to assign them to the nearest soil layer cell, avoiding errors in layer classification due to floating-point precision issues. After completing the point-by-point layer classification, adjacent sampling points in the same layer are aggregated along the trajectory direction to form several continuous soil layer crossing segments. Each segment records the starting and ending sampling point indices, the soil layer type, and the spatial extension direction of the segment.

[0122] When calculating the crossing length and angle of the optimized trajectory in various soil types, the crossing length is taken as the cumulative value of the arc length interval between adjacent sampling points within the crossing segment of that soil layer, reflecting the actual extension distance of the pipeline in that soil layer. The crossing angle is calculated based on the angle between the average tangent direction vector of the crossing segment and the normal vector of the corresponding soil layer surface. The surface normal vector is obtained by interpolating the local normal vector of the upper interface of that soil layer in the three-dimensional geological stratification data. The crossing angle... Defined as the complementary angle between the tangent direction vector and the surface normal vector, i.e., the actual incident angle between the tangent direction and the surface, its value range is... ,in This indicates that the pipe passes through the floor vertically. This indicates that the pipeline extends parallel to the plane. The size of the crossing angle directly affects the range of construction disturbance and the stress state of the pipeline, and is an important input for subsequent fit calculations.

[0123] When extracting the shear strength and compression modulus corresponding to the interaction positions between the optimized trajectory and each soil layer, spatial interpolation is performed from the soil mechanical parameter distribution data according to the three-dimensional coordinates of the sampling points. The distance-weighted inverse proportional interpolation method is used to obtain the shear strength of each point. and compressive modulus subscript Indicates the first Representative parameter values ​​for each soil layer crossing segment are obtained, and the arithmetic mean of the corresponding parameters at all sampling points within that segment is taken. Simultaneously, the curvature values ​​of the optimized trajectory at each soil layer interaction location are extracted. The average curvature of each sampling point within the crossing segment is taken as the representative curvature of that segment. The above four indicators—shear strength—are considered. Compression modulus curvature value and crossing angle — Together they constitute the set of input parameters for calculating local fitness.

[0124] Local adaptation Reflecting the pipeline trajectory in the first The degree of compatibility between the soil layer and geological conditions within the crossing section is comprehensively considered, taking into account the soil's ability to withstand construction disturbance, the additional stress on the soil layer due to pipeline bending, and the rationality of the crossing direction. Higher shear strength indicates stronger resistance to shear failure and better adaptability to construction; a larger compression modulus results in smaller deformation of the soil under pipeline load, further enhancing adaptability; a smaller curvature value indicates lower pipeline bending in that section, less lateral compression of the soil layer, and better adaptability; and a crossing angle closer to a reasonable range (generally, engineering experience indicates...) is also important. to The better the local fit (between the optimal incident angles), the better the fit. Based on the above analysis, the local fit... Constructed as follows: based on shear strength and compressive modulus The sum of normalized values ​​is used as the contribution term to soil bearing capacity, with curvature value as the factor. The normalized reciprocal is used as a bending adaptation contribution term, based on the crossing angle. The rationality score is used as a contribution item for direction adaptation, and the weighted sum of the three items is obtained. ,Right now ,in , , These are the dimensionless values ​​of the corresponding parameters after normalization in the global scope. For the scoring function of the crossing angle, , , , The weighting coefficients for each contribution item satisfy the following conditions: . The construction method is as follows: when A higher score is given when the score falls within a preset reasonable range, and the score decreases linearly or non-linearly according to the degree of deviation when the score deviates from the reasonable range. This ensures that the influence of the crossing angle on the local fit is continuously differentiable, which facilitates subsequent optimization and iteration.

[0125] The local fit is weighted and accumulated according to the crossing length to calculate the overall fit of the optimized trajectory in each soil layer segment. Let the first... The length of each soil layer crossing section is Then the weighted fit of this soil layer segment is Then, for all soil layer crossing sections Normalizing by the total crossing length yields the fit distribution of the entire optimized trajectory across each soil layer. The physical significance of weighting by crossing length lies in the fact that the longer the pipeline extends through a certain soil layer, the greater the impact of the geological conditions of that soil layer on the overall construction quality. Therefore, it should be given a higher weight to avoid the potential impact of simply passing through a high-risk soil layer without equalizing it.

[0126] The fit of the optimized trajectory in each soil layer is coupled with the geological carrying capacity of the corresponding location to obtain a comprehensive fit index. The geological carrying capacity comprehensively reflects the soil layer's self-recovery ability after construction disturbance, the impact of groundwater occurrence on soil stability, and the degree to which the soil layer thickness ensures long-term pipeline support. It is determined by the geological carrying capacity evaluation values ​​pre-stored in the three-dimensional geological stratification data. Direct reading. Coupled computation uses a product form, i.e. ,in The coupling index is used to adjust the intensity of the influence of geological environment carrying capacity on the comprehensive adaptation index. When it is linearly coupled, when More severe penalties are imposed on areas with lower load-bearing capacity. At times, the impact of bearing capacity is weakened. In construction scenarios in black soil regions, due to the high organic matter content, loose structure, and sensitivity to disturbance of the black soil layer, it is usually... The value is greater than 1 to strengthen the constraint on the comprehensive adaptation index of the black soil layer crossing section, and to ensure that the crossing scheme of the optimized trajectory in the black soil layer meets the harmlessness requirements.

[0127] Summarize the comprehensive compatibility indexes of each soil layer crossing section This results in a complete adaptation process. The adaptation results are stored in structured data format, including the start and end locations of each soil layer crossing segment, the soil layer type, and the crossing length. Crossing angle Local adaptation Weighted fit Geological environment carrying capacity evaluation value and comprehensive adaptation indicators For soil crossing sections where the comprehensive compatibility index is lower than the preset threshold, they are marked as insufficient compatibility areas. In the subsequent process parameter allocation stage, reinforced support parameter combinations will be prioritized for these areas to ensure the safety of pipeline laying and the synergistic achievement of the ecological protection goals of the black soil region.

[0128] Based on the adaptation results, process parameter combinations are assigned to different spatial segments of the optimized trajectory, control commands are generated, and the trenchless crossing equipment is driven to lay pipelines along the optimized trajectory based on the control commands, including:

[0129] Extract the comprehensive adaptation index of the optimized trajectory in each soil layer from the adaptation results, and establish the process control coefficient of the optimized trajectory in each soil layer based on the comprehensive adaptation index.

[0130] Extract the soil mechanical parameters corresponding to each soil layer of the optimized trajectory, determine the standard process parameters of the optimized trajectory in each soil layer based on the soil mechanical parameters, and couple the process control coefficient with the standard process parameters to obtain the basic process parameters of the optimized trajectory in each soil layer.

[0131] The corrected process parameters are obtained by dynamically correcting the foundation process parameters based on the rate of curvature change of the optimized trajectory in each soil layer.

[0132] The gradient of the change of the modified process parameters in the adjacent soil layer segment at the soil layer interface is calculated for the optimized trajectory. The transition process parameters and the length of the transition region at the soil layer interface are generated based on the gradient. The modified process parameters, the transition process parameters and the length of the transition region are combined to obtain the process parameter combination.

[0133] The process parameters are combined with the spatial coordinates of the optimized trajectory to generate control commands. These commands are then transmitted to the trenchless crossing equipment, which is used to lay the pipeline along the optimized trajectory.

[0134] After completing the fitness assessment of the optimized trajectory, the comprehensive fitness index of each soil layer crossing segment is extracted from the fitness results. Based on this, process control coefficients for each soil layer are established. Comprehensive adaptation indexes. This comprehensively reflects the degree of matching between the trajectory and the geological environment. A higher value indicates a more harmonious relationship between the trajectory and geological conditions, resulting in relatively lower construction difficulty; conversely, a lower value requires more precise configuration of process parameters. Mapped to process control coefficient Using a piecewise linear mapping relationship, when When the preset high-adaptation threshold is exceeded, Take the smaller value to maintain the normal construction intensity; when When the value is below the preset low adaptation threshold, Take the larger value to trigger the strengthening process configuration; within the middle range Follow Linear interpolation is used to determine the mapping mechanism. This mechanism directly transforms the geological compatibility assessment results into quantifiable data for process control, avoiding the uncertainty caused by relying on human experience.

[0135] After obtaining the process control coefficient, the soil mechanical parameters corresponding to each soil layer segment are extracted simultaneously from the adaptation results, including the average representative shear strength of that segment. and mean compressive modulus Using these two parameters as core inputs, and based on the technical specifications for trenchless tunneling, standard technical parameters for each soil layer are determined. These standard technical parameters include drilling thrust. Mud pump pressure and drilling speed Three core quantities. Among them, drilling thrust. and Positive correlation; greater thrust is required in soil layers with high shear strength to overcome ground resistance; mud pump pressure and The inverse positive correlation indicates that soft soil layers with lower compression modulus require higher mud pressure to maintain borehole stability; drilling speed Then take into account and The reciprocal of the product is set to appropriately reduce the velocity in soft strata to prevent borehole collapse. The process control coefficient is... The basic process parameters are obtained by coupling calculations with the three standard process parameters mentioned above. , and The coupling method is to multiply the standard process parameters by the control coefficient, that is, the basic process parameters are equal to the standard process parameters multiplied by the control coefficient. The product of these parameters allows for the quantitative control of standard parameters by the geological adaptation assessment results.

[0136] After the basic process parameters are determined, dynamic adjustments are needed to address the impact of trajectory curvature changes on the construction process. The rate of curvature change at sampling points within each soil layer segment is extracted from the optimized trajectory. Calculate the mean of the rate of change of curvature in this segment. This serves as a representative indicator of the curvature change intensity in this section. A trajectory segment with a large rate of curvature change means the pipeline needs to complete a significant directional deflection within a short distance, placing higher demands on the equipment's turning capability and the pressure-bearing capacity of the borehole wall. A curvature correction factor is introduced. Its value is determined by After normalization, the result is obtained by mapping to a linear or nonlinear function. The larger the rate of curvature change, the larger the correction factor. Curvature correction is applied to the basic process parameters: in trajectory segments with a large rate of curvature change, the drilling speed correction value is appropriately reduced. This extends the construction time per unit length and ensures steering accuracy; at the same time, the mud pump pressure correction value is appropriately increased. To maintain sufficient borehole wall support pressure in the curved section; drilling thrust correction value Then, adjust the parameters upwards appropriately based on the increase in friction of the curved section. The three parameters obtained after curvature correction are... , , These are the corrected process parameters for each soil layer, which can more accurately reflect the actual requirements of the trajectory geometry for the construction process.

[0137] At the interface between soil layers, the modified process parameters for adjacent soil layers often differ significantly. Directly switching between these parameters would impact the trenchless drilling equipment and could potentially cause borehole instability at the interface. Therefore, it is necessary to calculate the gradient of the modified process parameters between adjacent soil layers. It is defined as the ratio of the absolute value of the difference in corresponding process parameters between adjacent segments to the preset reference length of the transition region. Gradient variation The larger the value, the more drastic the parameter jump, and the longer the required transition region. The longer the transition region, the better, ensuring a smooth transition between parameters. (Transition region length) The length of the transition zone is determined by the combined fit index at the geological interface and the gradient change: when the strata properties on both sides of the interface differ significantly (large difference in the comprehensive fit index), the length of the transition zone is correspondingly extended; when the strata properties on both sides are similar, the length of the transition zone can be appropriately shortened. Within the transition zone, each process parameter is smoothly transitioned from the corrected process parameters of the previous soil layer to the corrected process parameters of the next soil layer using cubic spline interpolation, generating a transition process parameter sequence. The modified process parameters for each soil layer, the transition process parameters at the soil layer interface, and the corresponding transition zone length are combined to form a complete set of process parameters, achieving a continuous and smooth distribution of process parameters across the entire trajectory range.

[0138] Control commands are generated by associating and encoding the combination of process parameters with the spatial coordinates of the optimized trajectory. The core of this associative encoding is to use the three-dimensional coordinates of each node on the optimized trajectory as index keys, binding and storing the drilling thrust, mud pump pressure, drilling speed, and area type (normal section or transition section) at the corresponding location in a structured data format. The control commands include location trigger conditions: when the real-time positioning information of the trenchless tunneling equipment matches the preset coordinates in the command, the corresponding combination of process parameters is automatically loaded and executed. The control commands also include anomaly response logic: when the measured drilling resistance exceeds a preset range, an adaptive parameter adjustment process is triggered, increasing the thrust or adjusting the mud pump pressure by a preset step size based on the current process parameters until the drilling status returns to normal. The encoded control commands are transmitted to the control unit of the trenchless tunneling equipment, driving the equipment to strictly advance along the optimized trajectory and complete the pipeline laying operation according to the preset combination of process parameters for each spatial segment, thereby achieving precise and harmless tunneling through the underground space of the black soil region.

[0139] A second aspect of the present invention provides a trenchless trajectory intelligent optimization system under complex geological conditions, comprising:

[0140] The data acquisition unit is used to acquire three-dimensional geological stratification data, soil mechanical parameter distribution data, and obstacle spatial location data of the underground space in the black soil region.

[0141] Spatial division units are used to identify the spatial distribution range of black soil layers in three-dimensional geological stratification data. Constraints are set for black soil layers based on organic matter content, collapsibility coefficient and seasonal freeze-thaw depth. Spatial constraint domains are divided in combination with obstacle spatial location data to obtain feasible space.

[0142] The trajectory generation unit is used to generate an initial trajectory within the feasible space, calculate the path length and rate of change of curvature based on the spatial geometry of the initial trajectory, and calculate the disturbance amount based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters.

[0143] The weight correction unit is used to construct an evaluation function based on the disturbance amount, path length and curvature change rate, extract the soil mechanical parameters of each node position of the initial trajectory to establish hierarchical constraint weights, correct the gradient of the evaluation function based on the hierarchical constraint weights and iteratively optimize the initial trajectory to obtain the optimized trajectory.

[0144] The adaptation evaluation unit is used to spatially overlay the optimized trajectory with three-dimensional geological stratification data, identify the interaction positions between the optimized trajectory and each soil layer, calculate the adaptation degree of the optimized trajectory in each soil layer segment, and obtain the adaptation result.

[0145] The command and control unit is used to allocate process parameter combinations to different spatial segments of the optimized trajectory based on the adaptation results, generate control commands, and drive the trenchless crossing equipment to lay pipelines along the optimized trajectory based on the control commands.

[0146] A third aspect of the present invention provides an electronic device, comprising:

[0147] processor;

[0148] Memory used to store processor-executable instructions;

[0149] The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0150] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0151] This invention can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the invention.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A non-excavation trajectory intelligent optimization method under complex geological conditions, characterized in that, include: To obtain three-dimensional geological stratification data, soil mechanical parameter distribution data, and obstacle spatial location data of the underground space in the black soil region; The spatial distribution range of the black soil layer in the three-dimensional geological stratification data is identified. Constraints are set for the black soil layer based on organic matter content, collapsibility coefficient and seasonal freeze-thaw depth. The spatial constraint domain is divided in combination with the spatial location data of obstacles to obtain the feasible space. An initial trajectory is generated within the feasible space. The path length and rate of curvature change are calculated based on the spatial geometry of the initial trajectory. The disturbance is calculated based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters. An evaluation function is constructed based on the disturbance amount, path length, and curvature change rate. Soil mechanical parameters at each node of the initial trajectory are extracted to establish layered constraint weights. The gradient of the evaluation function is corrected based on the layered constraint weights, and the initial trajectory is iteratively optimized to obtain the optimized trajectory. The optimized trajectory is spatially overlaid with three-dimensional geological stratification data to identify the interaction positions between the optimized trajectory and each soil layer, calculate the fit of the optimized trajectory in each soil layer segment, and obtain the fit result. Based on the adaptation results, process parameter combinations are assigned to different spatial segments of the optimized trajectory, control commands are generated, and trenchless crossing equipment is driven to lay pipelines along the optimized trajectory based on the control commands.

2. The method according to claim 1, characterized in that, The spatial distribution range of the black soil layer in the three-dimensional geological stratification data was identified. Constraints were set for the black soil layer based on organic matter content, collapsibility coefficient, and seasonal freeze-thaw depth. The spatial constraint domain was divided in conjunction with the spatial location data of obstacles, resulting in the following feasible space: Soil types of each soil layer are extracted from three-dimensional geological stratification data. The spatial distribution range of the soil layer type black soil is identified. The distribution data of soil mechanical parameters are spatially matched with the spatial distribution range of black soil to obtain the distribution of organic matter content and collapsibility coefficient. The distribution of organic matter content and collapsibility coefficient were coupled to obtain the coupled risk index distribution. Based on the coupled risk index distribution, the spatial coordinate range of the black soil layer was divided into spatial constraint domains, resulting in prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains. Based on the construction time point, the seasonal freeze-thaw depth is queried from the preset freeze-thaw depth database, and allowable and restricted crossing depth constraints are set for the allowable crossing constraint domain and the restricted crossing constraint domain, respectively. The spatial location data of obstacles are spatially superimposed with the allowable crossing constraint domain and the restricted crossing constraint domain, and the overlapping area is removed. Vertical boundary constraints are set in the allowable crossing constraint domain and the restricted crossing constraint domain according to the allowable crossing burial depth constraint condition and the restricted crossing burial depth constraint condition, respectively, to obtain the feasible space.

3. The method according to claim 2, characterized in that, The coupled calculation of organic matter content distribution and collapsibility coefficient distribution yields the coupled risk index distribution. Based on the coupled risk index distribution, the spatial coordinate range of the black soil layer is divided into spatial constraint domains, resulting in prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains, including: The organic matter content and collapsibility coefficient values ​​of each spatial location point are extracted from the organic matter content distribution and collapsibility coefficient distribution. The coupling risk index value of each spatial location point is obtained by nonlinear coupling calculation of the organic matter content and collapsibility coefficient values. The coupling risk index values ​​at each spatial location point are spatially interpolated to obtain the coupling risk index distribution, and the spatial gradient of the coupling risk index distribution is calculated to obtain the spatial gradient field. Gradient abrupt change locations are extracted from the spatial gradient field, and these locations are connected to form the boundary line of the constrained domain. The spatial coordinate range of the black soil layer is then divided into multiple spatial partitions based on the boundary line of the constrained domain. Cluster analysis is performed on the coupling risk index values ​​within each spatial partition to obtain risk clustering results. Based on the risk clustering results, the risk concentration index of each spatial partition is calculated. Based on the risk concentration index, each spatial partition is divided into prohibited crossing constraint domains, restricted crossing constraint domains, and permitted crossing constraint domains.

4. The method according to claim 1, characterized in that, An initial trajectory is generated within the feasible space. Based on the spatial geometry of the initial trajectory, the path length and rate of change of curvature are calculated. The disturbance is calculated based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters, including: Obtain the starting and ending coordinates of the pipeline crossing project, and arrange multiple intermediate control points between the starting and ending coordinates within the feasible space. Connect the starting and ending coordinates sequentially through the intermediate control points to generate the initial trajectory. The initial trajectory is discretized to obtain the three-dimensional coordinates of each sampling point. The spatial distance between the three-dimensional coordinates of adjacent sampling points is calculated and summed to obtain the path length of the initial trajectory. The curvature value of each sampling point is obtained by calculating the change in tangent direction at the three-dimensional coordinates of each sampling point, and the curvature change rate of the initial trajectory is obtained by performing a difference operation on the curvature values ​​of adjacent sampling points. Based on the three-dimensional coordinates of each sampling point, the shear strength and compression modulus of the corresponding location in the soil mechanical parameter distribution data are extracted. The curvature value of each sampling point is weighted with the shear strength and compression modulus of the corresponding location to obtain the soil disturbance at each sampling point. The soil disturbance at each sampling point is integrated along the path length of the initial trajectory to obtain the disturbance of the initial trajectory.

5. The method according to claim 1, characterized in that, An evaluation function is constructed based on the disturbance amount, path length, and rate of curvature change. Soil mechanical parameters at each node of the initial trajectory are extracted to establish hierarchical constraint weights. The gradient of the evaluation function is corrected based on these hierarchical constraint weights, and the initial trajectory is iteratively optimized to obtain the optimized trajectory, which includes: We assign weight coefficients to the disturbance amount, path length, and rate of curvature change, and then sum them up to construct an evaluation function. Extract the node coordinates of each node position of the initial trajectory, and extract the soil mechanical parameters of each node position of the initial trajectory from the soil mechanical parameter distribution data based on the node coordinates. The soil mechanical parameters include shear strength and compression modulus. Calculate the reciprocal of shear strength and the reciprocal of compression modulus, perform normalization processing, and then perform weighted summation to establish the layered constraint weights of each node position. Calculate the gradient vector of the evaluation function with respect to the coordinates of each node, multiply the hierarchical constraint weights of each node position with the gradient vector of the corresponding node coordinates to obtain the corrected gradient vector, and adjust the coordinates of each node according to the corrected gradient vector to obtain the updated node coordinates. The constrained node coordinates are obtained by updating the node coordinates to fit within the feasible space. The evaluation function is recalculated based on the coordinates of the constraint nodes to obtain the current evaluation function value. It is then determined whether the difference between the current evaluation function value and the previous evaluation function value is less than the preset convergence threshold. If it is less than the preset convergence threshold, the coordinates of the constraint nodes are connected to obtain the optimized trajectory. Otherwise, the coordinates of the constraint nodes are used as the current node coordinates and the iteration optimization continues.

6. The method according to claim 1, characterized in that, The optimized trajectory is spatially overlaid with 3D geological stratification data to identify the interaction positions between the optimized trajectory and each soil layer. The fit degree of the optimized trajectory in each soil layer segment is calculated, and the fit results include: Extract the three-dimensional coordinates of each sampling point on the optimized trajectory, and spatially overlay the three-dimensional coordinates of each sampling point on the optimized trajectory with the three-dimensional geological stratification data to determine the soil layer type of each sampling point; By statistically analyzing the crossing length and crossing angle of the optimized trajectory in each soil layer type, the interaction position between the optimized trajectory and each soil layer can be obtained. Extract the shear strength and compression modulus from the soil mechanical parameter distribution data corresponding to the interaction position between the optimized trajectory and each soil layer, extract the curvature value at the interaction position between the optimized trajectory and each soil layer, and calculate the angle between the crossing direction and the soil layer division based on the crossing angle of the optimized trajectory in each soil layer. The local fit is calculated based on shear strength, compression modulus, curvature value and included angle. The local fit is weighted and accumulated according to the crossing length to calculate the fit of the optimized trajectory in each soil layer segment. The adaptation degree of the optimized trajectory in each soil layer is coupled with the geological environmental carrying capacity of the corresponding location to obtain a comprehensive adaptation index. The comprehensive adaptation index is then summarized to obtain the adaptation result.

7. The method according to claim 1, characterized in that, Based on the adaptation results, process parameter combinations are assigned to different spatial segments of the optimized trajectory, control commands are generated, and the trenchless crossing equipment is driven to lay pipelines along the optimized trajectory based on the control commands, including: Extract the comprehensive adaptation index of the optimized trajectory in each soil layer from the adaptation results, and establish the process control coefficient of the optimized trajectory in each soil layer based on the comprehensive adaptation index. Extract the soil mechanical parameters corresponding to each soil layer of the optimized trajectory, determine the standard process parameters of the optimized trajectory in each soil layer based on the soil mechanical parameters, and couple the process control coefficient with the standard process parameters to obtain the basic process parameters of the optimized trajectory in each soil layer. The corrected process parameters are obtained by dynamically correcting the foundation process parameters based on the rate of curvature change of the optimized trajectory in each soil layer. The gradient of the change of the modified process parameters in the adjacent soil layer segment at the soil layer interface is calculated for the optimized trajectory. The transition process parameters and the length of the transition region at the soil layer interface are generated based on the gradient. The modified process parameters, the transition process parameters and the length of the transition region are combined to obtain the process parameter combination. The process parameters are combined with the spatial coordinates of the optimized trajectory to generate control commands. These commands are then transmitted to the trenchless crossing equipment, which is used to lay the pipeline along the optimized trajectory.

8. A non-excavation trajectory intelligent optimization system for complex geological conditions, used to implement the method as described in any one of claims 1-7, characterized in that, include: The data acquisition unit is used to acquire three-dimensional geological stratification data, soil mechanical parameter distribution data, and obstacle spatial location data of the underground space in the black soil region. Spatial division units are used to identify the spatial distribution range of black soil layers in three-dimensional geological stratification data. Constraints are set for black soil layers based on organic matter content, collapsibility coefficient and seasonal freeze-thaw depth. Spatial constraint domains are divided in combination with obstacle spatial location data to obtain feasible space. The trajectory generation unit is used to generate an initial trajectory within the feasible space, calculate the path length and rate of curvature change based on the spatial geometry of the initial trajectory, and calculate the disturbance amount based on the spatial relationship between the initial trajectory and the distribution data of soil mechanical parameters. The weight correction unit is used to construct an evaluation function based on the disturbance amount, path length and curvature change rate, extract the soil mechanical parameters of each node position of the initial trajectory to establish hierarchical constraint weights, correct the gradient of the evaluation function based on the hierarchical constraint weights and iteratively optimize the initial trajectory to obtain the optimized trajectory. The adaptation evaluation unit is used to spatially overlay the optimized trajectory with three-dimensional geological stratification data, identify the interaction positions between the optimized trajectory and each soil layer, calculate the adaptation degree of the optimized trajectory in each soil layer segment, and obtain the adaptation result. The command and control unit is used to allocate process parameter combinations to different spatial segments of the optimized trajectory based on the adaptation results, generate control commands, and drive the trenchless crossing equipment to lay pipelines along the optimized trajectory based on the control commands.

9. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images