A method for selecting the axis orientation of an underground powerhouse using knowledge graphs and block theory, and a readable storage medium.

Abstract

This invention discloses a method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory, along with a readable storage medium. The method includes: S1, constructing a knowledge graph for the underground powerhouse axis: using factors for selecting the axis direction of the underground powerhouse, determining the characteristic indicators of entity objects, collecting and processing the entity attribute database, and mapping the entity attribute data and entity relationships to knowledge graph nodes and edges to establish the knowledge graph. S2, organizing the underground powerhouse area survey data, setting sub-entities and attribute data for each entity object, and obtaining the entity objects and attributes of the underground powerhouse axis using the knowledge graph. S3, combining block theory to select a suitable axis direction for the underground powerhouse. This addresses the problem that traditional layout schemes in existing technologies mainly rely on manual experience and professional knowledge, lacking a systematic and scientific method to support the decision-making process, thus improving decision-making efficiency.

Description

Technical Field

[0001] This invention belongs to the field of underground powerhouse layout in hydropower projects. Specifically, it is a readable storage medium for a method of selecting the axial direction of underground powerhouses in hydropower projects using knowledge graphs and block theory. Background Technology

[0002] In the surveying, design, and construction phases of hydropower projects, the selection of the layout of the hub is a very important and crucial task. Among them, the selection and determination of the axis direction of the underground powerhouse is very important. Once the axis direction of the powerhouse is determined, the layout of the hub is basically determined, which facilitates the overall progress of subsequent work in the hydropower project.

[0003] Currently, the selection of the axis orientation of underground powerhouses is primarily based on engineering geological conditions, geological structure, and geostress factors, following regulatory requirements and expert experience. This involves analyzing the layout conditions of the project to reduce the impact of geostress and adverse geological structures on the stability of the surrounding rock of the underground powerhouse caverns, thereby improving the stability of the surrounding rock and ensuring the safety and efficiency of the project. However, current methods for selecting the axis orientation of underground powerhouses mainly rely on manual experience and professional knowledge, which has some shortcomings and limitations. They lack a systematic and scientific approach to support the decision-making process and improve efficiency, and may introduce issues of subjectivity and uncertainty in decision-making.

[0004] A knowledge graph is a structured graphical model used to organize and represent knowledge. Based on entities (such as people, places, and events) and the relationships between them, it presents the semantic connections of knowledge. By integrating information from different data sources and knowledge domains into a unified semantic network, knowledge graphs enable machines to better understand and reason about knowledge relationships, thus supporting tasks such as natural language processing, data analysis, and intelligent decision-making. Using knowledge graphs, suitable axial directions for underground power plants can be identified based on engineering geological conditions, and block theory can be used to further identify axial directions for underground power plants with higher safety factors. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a readable storage medium for a method of selecting the axis direction of an underground powerhouse using knowledge graphs and block theory. This addresses the issues in existing technologies where traditional layout schemes rely primarily on human experience and expertise, lacking a systematic and scientific approach to support the decision-making process, thereby improving decision-making efficiency.

[0006] This invention is implemented as follows: a method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory, comprising the following steps:

[0007] S1. Construct a knowledge graph of the underground plant axis: Use the selection factors of the underground plant axis direction to determine the characteristic indicators of the entity objects, collect and process the entity attribute database, map the entity attribute data and entity relationships to knowledge graph nodes and edges, and establish a knowledge graph.

[0008] S2, sort out the survey data of the underground powerhouse area, set sub-entities and attribute data of each entity object, and use knowledge graph to obtain the entity objects and attributes of the underground powerhouse axis;

[0009] S3, combining block theory, select a suitable axial direction for the underground powerhouse.

[0010] The construction of the knowledge graph relating the axial directions of the underground powerhouse in S1 includes the following steps:

[0011] S1-1: Identify the entities that are the selection factors for the axis of the underground factory building, collect entity objects and attribute information, and construct a knowledge graph database.

[0012] S1-2 establishes relationships between entities using entity object transfer rules, combines an object database, optimizes entity relationship weights using expert weighting, and constructs a knowledge graph.

[0013] In S1-1, the knowledge graph entities include the maximum principal stress A in the underground powerhouse area, the structural surface B, the fracture structural surface C, and the axis of the underground powerhouse D. The attribute information includes the entity object name, object type, and object data.

[0014] The underground powerhouse area has been selected based on the regional engineering geological conditions. Entity A, representing the maximum principal stress in the underground powerhouse area, is the key entity, with the maximum principal stress as its objective and the direction of the maximum principal stress as its attribute factor. Entity B, representing the structural surface, is the primary entity, primarily consisting of structural surfaces of small faults and densely fractured zones with limited data. The entity is further subdivided into sub-entities based on the number of structural surface groups, with the orientation of the structural surface as its attribute factor. Entity C, representing the fractured structural surface, is the secondary entity, including fractured composite structural surfaces. The entity is further subdivided into sub-entities based on the number of fractured structural surface groups, with the orientation of the fractured structural surface as its attribute factor. Entity D, representing the underground powerhouse axis, is the target entity, with the orientation of the underground powerhouse axis as its attribute factor.

[0015] The attribute factors of the entity objects A, B, C and D are all quadrant angles or azimuth angles. The object type is the quadrant or azimuth to which the object belongs. The object data is located in NE0~90° and NW270~360°. The object data is a self-defined direction interval value. The entity object attribute value is set every 5° or 10° to construct the object database.

[0016] The knowledge graph entity relationships in S1-2 include three types: AD, BD, and CD. The relationship between entity A (maximum principal stress) and entity D (factory axis) is the angle between the factory axis direction and the direction of the maximum principal stress in the surrounding rock, which is no greater than 30°. The relationships between entity B (structural surface) and entity C (fracture structure surface) and entity D (factory axis) are both the angle between the factory axis and the direction of the main structural line, which is no less than 60°.

[0017] In S1-2, the expert weighting method optimizes the weights. This involves experts determining the entity path weights based on the geological conditions of the specific application project to optimize the shortest path retrieval algorithm. Experts assign weight values ​​w to the importance of entities A, B, and C relative to the target entity. A w B w C The target entity that does not affect the overall factory axis direction selection is determined by setting the sum of the weights of the three entities to a specific fixed value, assigning a separate entity weight value to each sub-entity factor, determining the starting entity based on the entity weight value, and using the shortest path algorithm to optimize the relationship weights to obtain the target entity D object;

[0018] The formula for optimizing weights using the expert weighting method is illustrated below:

[0019] w(i,D)=g ij ·f(i,D)

[0020]

[0021] Where w(i,D) is the combined weight between entity object i and target entity object D; g ij f(i,D) represents the weights of entity objects A, B, and C and their sub-entity objects assigned by the expert; f(i,D) represents the relationship weight between entity object i and target entity object D.

[0022] In step S2, based on the geological survey results of the engineering area, the entity objects of the maximum principal stress, structural surface, and fracture surface are obtained. Sub-entity groups of structural surface and fracture surface are selected, and attribute values ​​and entity weight values ​​of 5-degree or 10-degree entity objects are set. The knowledge graph is used to obtain suggested values ​​for the axial direction interval of the underground powerhouse. In step S3, based on the underground powerhouse model data and survey geological data, the Unwedge program is used to establish the powerhouse excavation model. The fracture surface combination of step S1 is selected, and based on the rock mass physical and mechanical parameters, the axial direction values ​​of the underground powerhouse obtained in step S2 are analyzed at intervals of 5 degrees or 10 degrees. The minimum safety factor within each direction range of the powerhouse axis is analyzed, and the axial direction corresponding to the larger value in the minimum safety factor column is taken as the appropriate value.

[0023] A computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the above-described method.

[0024] A computer device includes a memory, a processor, and a program stored in the memory and executable thereon, the program being executed by the processor to implement the steps of the method described above.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. This invention, by employing a knowledge graph-based method for underground powerhouse layout, can enhance designers' and decision-makers' understanding of key factors in engineering geological conditions and provide precise and automated decision support, enabling the quantitative selection of suitable underground powerhouse axis directions.

[0027] 2. By combining knowledge graphs with block theory, this invention can significantly consider safety risks, improve the identification and management of risks in the design phase of underground powerhouse axis direction, and help improve the scientificity, operability and reliability of layout schemes, thereby improving the construction quality and engineering benefits of underground powerhouses. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the overall process of the present invention.

[0029] Figure 2 This is a schematic diagram of the structural surface data in this embodiment.

[0030] Figure 3 This is a schematic diagram of the crack structure surface data in this embodiment.

[0031] Figure 4 This is a schematic diagram showing the safety factor results of the fractured composite block in this embodiment. Detailed Implementation

[0032] To make the objectives, construction scheme, technical route, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0033] The present invention employs a knowledge graph and block theory for selecting the axis direction of underground powerhouses, such as... Figure 1 As shown, this method includes the following steps:

[0034] Step S1: Construct a knowledge graph of the underground factory axis. This involves using the selection factors of the underground factory axis direction to determine the characteristic indicators of the entity objects, collecting and processing the entity attribute database, mapping the entity attribute data and entity relationships to knowledge graph nodes and edges, and establishing the knowledge graph.

[0035] Preferably, constructing a knowledge graph relating the axial directions of underground powerhouses includes the following steps:

[0036] Step S1-1: Organize the entities that are the selection factors for the underground factory axis, collect entity objects and attribute information, and construct a knowledge graph database.

[0037] Preferably, the knowledge graph entities include the maximum principal stress A in the underground powerhouse area, the structural surface B, the fractured structural surface C, and the underground powerhouse axis D, and the attribute information includes the entity object name, object type, and object data.

[0038] Preferably, the location of the underground powerhouse has been selected based on the regional engineering geological conditions. The entity with the maximum principal stress, A, is the key entity; its object is the maximum principal stress in the underground powerhouse area, and its attribute factor is the direction of the maximum principal stress. The structural surface entity B is the main entity; its object is primarily composed of structural surfaces with limited data, such as small faults and densely fractured zones. The entity is further subdivided into sub-entities based on the number of structural surface groups, and its attribute factor is the orientation of the structural surface. The fractured structural surface entity C is the secondary entity; its object includes fractured composite structural surfaces. The entity is further subdivided into sub-entities based on the number of fractured structural surface groups, and its attribute factor is the orientation of the fractured structural surface. The underground powerhouse axis entity D is the target entity; its attribute factor is the orientation of the underground powerhouse axis.

[0039] Preferably, the attribute factors of entity objects A, B, C and D are all quadrant angles or azimuth angles, the object type is the quadrant or azimuth to which the object belongs, the object data is located in NE0~90° and NW270~360°, the object data is a self-defined direction interval value, and the entity object attribute value is self-defined every 5° or 10° to construct the object database.

[0040] Step S1-2: Establish relationships between entities using entity object transfer rules, combine with the object database, optimize entity relationship weights using expert weighting method, and construct a knowledge graph.

[0041] Preferably, the knowledge graph entity relationships in this method have three types: AD, BD, and CD. Specifically, the relationship between entity A (maximum principal stress) and entity D (factory building axis) is such that the angle between the factory building axis direction and the direction of the maximum principal stress in the surrounding rock should not exceed 30°. The relationships between structural plane entities B and C and entity D (factory building axis) are such that the factory building axis should ideally have a large angle with the direction of the main structural line, not less than 60°.

[0042] Preferably, the expert weighting method optimizes the weights. This involves experts determining the entity path weights based on the geological conditions of the specific application project to optimize the shortest path retrieval algorithm. Experts assign weight values ​​w to entities A, B, and C relative to the target entity. A w B w C Without affecting the overall factory axis direction selection, the target entity is determined to have a specific fixed value for the sum of the weights of the three entities. The entity weight value is assigned to each sub-entity factor. The starting entity is determined based on the entity weight value. The shortest path algorithm is used to optimize the relationship weights and obtain the target entity D object.

[0043] The expert weighting method optimization formula is illustrated below:

[0044] w(i,D)=g ij ·f(i,D)

[0045]

[0046] Where w(i,D) is the combined weight between entity object i and target entity object D; g ij f(i,D) represents the weights of entity objects A, B, and C and their sub-entity objects assigned by the expert; f(i,D) represents the relationship weight between entity object i and target entity object D.

[0047] Step S2 involves organizing the survey data of the underground powerhouse area, defining the sub-entities and attribute data of each entity, and using a knowledge graph to obtain the entity objects and attributes of the underground powerhouse axis. Specifically, based on the geological survey results of the engineering area, entity objects representing the maximum principal stress, structural surfaces, and fracture surfaces are obtained. Sub-entity groups for structural surfaces and fracture surfaces are selected, and attribute values ​​and weight values ​​for 5-degree or 10-degree entities are set. The knowledge graph is then used to obtain suggested values ​​for the axial direction intervals of the underground powerhouse.

[0048] Step S3: Combining block theory, further select a suitable axial direction for the underground powerhouse. The attitude, extension length, and distribution of fractured structural surfaces are highly random, and they will randomly combine and cut to form blocks, which has a certain impact on the safety of the underground powerhouse area. In this step, based on the underground powerhouse model data and geological survey data, the Unwedge program is used to establish a powerhouse excavation model. The fractured structural surface combination in Step A is selected, and based on the rock mass physical and mechanical parameters, the axial direction values ​​of the underground powerhouse obtained in Step B are analyzed at intervals of 5 degrees or 10 degrees to determine the minimum safety factor within each direction of the powerhouse axis. The axial direction corresponding to the larger value in the minimum safety factor column is taken as the suitable value.

[0049] Through the following embodiments, combined with Figure 1 The technical solution of the present invention will be described in detail below.

[0050] In this embodiment, the initial proposed location of the underground powerhouse hub of a pumped storage power station is at the tail end of the waterway system. The excavation dimensions of the underground powerhouse are 163.5×24.5×54.5m. According to the geological survey of the underground powerhouse area, the maximum principal stress direction is NE58~73°, and the powerhouse area belongs to a medium stress field. The structural plane mainly develops 14 faults and 1 group of densely fractured zones, with the main orientations being NW320~330° and NE10~15°. Figure 2 The fracture structure exhibits numerous orientations, primarily consisting of four groups: NW, NNE, NEE, and NWW. The fracture dip angles are predominantly steep, with a few gently dipping fractures found locally. The strikes mainly include NW 320–350°, NE 0–15°, NE 80–85°, and NW 270–280°. Figure 3 ).

[0051] This embodiment constructs a knowledge graph, autonomously sets the object attribute value to 10°, sets the entity object to the entity object with the maximum principal stress A, constructs structural surface entities B1 and B2, and a fracture structural surface C, and assigns an entity object weight of g. A =5,g B1 =g B2 =2, g C =1, entity relation weights f(A,D)=0.5, f(B,D)=0.4, f(C,D)=0.1, construct a knowledge graph. Input the entity object with the maximum principal stress A (NE58~73°), construct the structural surface entities B1 (oriented with NW320~330°), B2 (NE10~15°), and the crack structural surface C (NW320~350°), and obtain the suitable orientation of the factory axis entity object D. The suitable orientation of the object is NE30~40°, NE40~50°, NE50~60°, NE60~70°, NE70~80°, that is, NE30~80°.

[0052] Based on the suitable axial alignment range of the underground powerhouse according to the knowledge graph, and considering safety factors, three sets of fracture combinations were selected: fracture J1: NW320~350°NE<40~65°; fracture J2: NE0~15°SE<50~80°; and gently dipping fracture J3: NW330~350°NE<12~30°. An excavation model of the powerhouse was established using the Unwedge program, with the following mechanical parameters: φ=19.3°, C=0t / ㎡, and rock unit weight of 2.67t / m³. 3 The unit weight of water is 1 t / m³ 3 The safety factor for the factory building axis is calculated within the NE30-80° range (e.g., ...). Figure 4 The results show that when the axial direction of the factory building is 50-60°, the minimum safety factor is relatively large, which is more practically significant in the optimization selection of the axial direction of underground factory buildings.

[0053] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented, in whole or in part, as a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0054] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several algorithm optimizations, improvements and modifications can be made without departing from the principle of the present invention, and these optimizations, improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory, characterized in that, Includes the following steps: S1. Constructing a knowledge graph of the underground plant's axis: This involves using factors for selecting the direction of the underground plant's axis to determine the characteristic indicators of entity objects, collecting and processing the entity attribute database, mapping the entity attribute data and entity relationships to knowledge graph nodes and edges, and establishing the knowledge graph. This includes the following steps: S1-1: Identify and analyze the entities that are key factors in selecting the underground powerhouse axis, collect entity object and attribute information, and construct a knowledge graph database. The knowledge graph entities include the maximum principal stress A, structural plane B, fracture structural plane C, and the underground powerhouse axis D in the underground powerhouse area. Attribute information includes entity object name, object type, and object data. The underground powerhouse location has been selected based on the regional engineering geological conditions. The maximum principal stress A entity is the key entity, representing the maximum principal stress in the underground powerhouse area, with the attribute factor being the direction of the maximum principal stress. The structural plane B entity is the primary entity, primarily identifying structural planes with limited data, such as small faults and densely fractured zones. Entities are subdivided into sub-entities based on the number of structural plane groups, with the attribute factor being the orientation of the structural plane. The fracture structural plane C entity is a secondary entity, including fracture combination structural planes, subdivided into sub-entities based on the number of fracture structural plane groups, with the attribute factor being the orientation of the fracture structural plane. The underground powerhouse axis D entity is the target entity, with the attribute factor being the orientation of the underground powerhouse axis. S1-2: Establish relationships between entities using entity object transfer rules, combine with object database, optimize entity relationship weights using expert weighting method, and construct knowledge graph; S2, sort out the survey data of the underground powerhouse area, set sub-entities and attribute data of each entity object, and use knowledge graph to obtain the entity objects and attributes of the underground powerhouse axis; S3, combining block theory, select a suitable axial direction for the underground powerhouse.

2. The method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory as described in claim 1, characterized in that, The attribute factors of the entity objects A, B, C and D are all quadrant angles or azimuth angles. The object type is the quadrant or azimuth to which the object belongs. The object data is located in NE0~90° and NW270~360°. The object data is a self-defined direction interval value. The entity object attribute value is set every 5° or 10° to construct the object database.

3. The method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory as described in claim 1 or 2, characterized in that, The knowledge graph entity relationships in S1-2 include three types: AD, BD, and CD. The relationship between entity A (maximum principal stress) and entity D (factory axis) is the angle between the factory axis direction and the direction of the maximum principal stress in the surrounding rock, which is no greater than 30°. The relationships between entity B (structural surface) and entity C (fracture structure surface) and entity D (factory axis) are both the angle between the factory axis and the direction of the main structural line, which is no less than 60°.

4. The method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory as described in claim 3, is characterized in that... In S1-2, the expert weighting method optimizes the weights. This involves experts determining the entity path weights based on the geological conditions of the specific application project to optimize the shortest path retrieval algorithm. Experts assign weight values ​​w to the importance of entities A, B, and C relative to the target entity. A w B w C The target entity that does not affect the overall factory axis direction selection is determined by setting the sum of the weights of the three entities to a specific fixed value, assigning a separate entity weight value to each sub-entity factor, determining the starting entity based on the entity weight value, and using the shortest path algorithm to optimize the relationship weights to obtain the target entity D object; The formula for optimizing weights using the expert weighting method is illustrated below: w(i,D)=g ij ·f(i,D) Where w(i,D) is the combined weight between entity object i and target entity object D; g ij f(i,D) represents the weights of entity objects A, B, and C and their sub-entity objects assigned by the expert; f(i,D) represents the relationship weight between entity object i and target entity object D.

5. The method for selecting the axis direction of an underground powerhouse using knowledge graphs and block theory as described in claim 1, characterized in that, In step S2, based on the geological survey results of the engineering area, the entity objects of the maximum principal stress, structural surface, and fracture surface are obtained. Sub-entity groups of structural surface and fracture surface are selected, and attribute values ​​and entity weight values ​​of 5-degree or 10-degree entity objects are set. The knowledge graph is used to obtain suggested values ​​for the axial direction interval of the underground powerhouse. In step S3, based on the underground powerhouse model data and survey geological data, the Unwedge program is used to establish the powerhouse excavation model. The fracture surface combination of step S1 is selected, and based on the rock mass physical and mechanical parameters, the axial direction values ​​of the underground powerhouse obtained in step S2 are analyzed at intervals of 5 degrees or 10 degrees. The minimum safety factor within each direction range of the powerhouse axis is analyzed, and the axial direction corresponding to the larger value in the minimum safety factor column is taken as the appropriate value.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method as described in any one of claims 1-5.

7. A computer device, characterized in that, The computer device includes a memory, a processor, and a program stored in and executable on the memory, the program being executed by the processor to implement the steps of the method as described in any one of claims 1-5.

Images