Rock slope support model construction scheme generation method

Abstract

The invention relates to the technical field of computer aided design, and provides a rock slope support model construction scheme generation method comprising the following steps: S1, obtaining a slope support model; s2, marking a connecting piece; s3, generating a construction step scheme; the scheme generation model is a GPT model; s4, verifying feasibility; s5, performing progress simulation; and S6, single-point anomaly detection is carried out. According to the method, the construction step scheme is generated based on the GPT model, automatic preliminary generation of the construction step scheme can be effectively realized by means of the AI technology, a large amount of labor cost is saved, and the situation that the construction period is delayed due to later scheme modification caused by negligence factors of arrangement personnel is effectively avoided; and on the basis, the communication and management cost in the construction progress arrangement process is greatly reduced, and automation and intelligence of large-depth and large-area development of slope supporting engineering are effectively assisted.

Description

Technical Field

[0001] The invention relates to a method for generating a rock slope support model construction plan, and belongs to the technical field of computer-aided design. Background Art

[0002] To ensure the safety of the structure construction under the slope and the surrounding environment, the measures of retaining, reinforcing and protecting the sidewalls of the slope and the surrounding environment are collectively called slope support. Slope support engineering is a systematic engineering with multiple complex factors interacting with each other. It is both a structural engineering and a geotechnical engineering.

[0003] At present, slope support projects are developing in the direction of large depth and large area, with some projects exceeding 100 meters in length, width and depth, high project cost and large number of projects. However, due to its complex technology, wide scope, many changing factors and frequent accidents, it has become the most challenging technical difficulty in construction projects.

[0004] With the development of BIM theory and technology, the application of information models is constantly expanding to the entire engineering industry. Using BIM technology, on the one hand, model visualization is achieved, and on the other hand, the design process and design information are integrated. At the same time, there is collaborative design, and technical designers of various disciplines can all participate.

[0005] However, because slope support projects are developing in the direction of greater depth and larger area, the manpower cost required for their design work is getting higher and higher. At the same time, the communication and management costs in the design process are also getting higher and higher, which is difficult for general enterprises to bear.

[0006] In the prior art, after the rock slope support model is designed, the construction steps are arranged by professionals such as project managers according to the slope support model. When arranging, it is necessary to consider both the reasonableness of the construction difficulty and the reasonableness of the schedule. At least 80% of the workload of these arrangements is tedious work directly set according to simple rules. The labor cost is high and unnecessary. In addition, due to the tediousness, it is often delayed due to the negligence of the arrangers causing the plan to be modified later. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a method for generating a construction plan for a rock slope support model. The method for generating a construction plan for a rock slope support model generates a construction step plan based on the GPT model. It can effectively realize the automatic preliminary generation of the construction step plan with the help of AI technology, save a lot of manpower costs, and effectively avoid delays in the construction period due to late modification of the plan due to negligence of the arrangement personnel.

[0008] The problem of the inability to effectively organize the generation rules in the design of complex construction step plans.

[0009] The present invention is achieved through the following technical solutions.

[0010] The present invention provides a method for generating a rock slope support model construction plan, comprising the following steps: S1. Obtaining a slope support model: obtaining a slope support model containing geological information at a target location from a path selected by a user; S2. Marking connectors: Analyze the slope support model, separate the connectors from the slope support model, mark the separated connectors, mark the unseparated parts as structural parts, and then put the connectors back into the slope support model to obtain a marked slope support model; S3. Generate a construction step plan: input the marked slope support model into a plan generation model to obtain a construction step plan in text form or rich text form; the plan generation model is a GPT model; S4, feasibility check: Check the construction step plan step by step to determine whether there are steps in the construction step plan that exceed the possible upper limit. If so, return directly to step S3 with an error message; S5. Progress simulation: Calculate the time consumption of the construction step plan step by step to form a construction progress plan; S6. Single-point anomaly detection: Perform single-point anomaly detection on the time consumption of each step in the construction progress plan to determine whether the time consumption of any step exceeds the preset value relative to the time consumption of other steps. If so, mark it as an abnormality and return to step S3. If not, output the construction step plan and construction progress plan.

[0011] The preset value in step S6 is set by the user within the range of 2.3 to 2.8.

[0012] In step S5, random climate is generated and the influence of the generated random climate on the time consumption is added to the calculation.

[0013] The random climate includes light rain, moderate rain, heavy rain, rainstorm, strong wind, high temperature, heavy snow, blizzard, haze, and freezing.

[0014] In step S5, a random event is generated and the influence of the generated random event on the time consumption is added to the calculation.

[0015] The random events include water outage, power outage, traffic interruption, personal accident, underground obstacle handling, fire, and landslide.

[0016] The scheme generation model is trained by using the slope support model and the corresponding construction step scheme in the historical data as training data.

[0017] The possible upper limit in step S4 is preset by the user and includes the range of construction steps and corresponding parameters.

[0018] The possible upper limit is stored as an XML file in a key-value manner.

[0019] The beneficial effects of the present invention are as follows: by generating construction step plans based on the GPT model, the automatic preliminary generation of construction step plans can be effectively realized with the help of AI technology, thereby saving a large amount of manpower costs, and effectively avoiding delays in construction period due to late modification of plans caused by negligence of scheduling personnel. Based on this, the communication and management costs in the construction schedule scheduling process are greatly reduced, and the automation and intelligence of slope support projects in the direction of greater depth and larger area are effectively assisted. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of a process of at least one embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The following division of various embodiments is for the convenience of description and should not constitute any limitation on the specific implementation of the present invention. Various embodiments can be combined and referenced with each other without contradiction.

[0022] A first embodiment of the present invention relates to Figure 1 A method for generating a rock slope support model construction plan is shown, comprising the following steps: S1. Obtaining a slope support model: obtaining a slope support model containing geological information at a target location from a path selected by a user; S2. Marking connectors: Analyze the slope support model, separate the connectors from the slope support model, mark the separated connectors, mark the unseparated parts as structural parts, and then put the connectors back into the slope support model to obtain a marked slope support model; S3. Generate a construction step plan: input the marked slope support model into a plan generation model to obtain a construction step plan in text form or rich text form; the plan generation model is a GPT model; S4, feasibility check: Check the construction step plan step by step to determine whether there are steps in the construction step plan that exceed the possible upper limit. If so, return directly to step S3 with an error message; S5. Progress simulation: Calculate the time consumption of the construction step plan step by step to form a construction progress plan; S6. Single-point anomaly detection: Perform single-point anomaly detection on the time consumption of each step in the construction progress plan to determine whether the time consumption of any step exceeds the preset value relative to the time consumption of other steps. If so, mark it as an abnormality and return to step S3. If not, output the construction step plan and construction progress plan.

[0023] The GPT (Generative Pre-Trained Transformer) model is a text-generating deep learning model based on the Internet and trained with available data. The input of the GPT model is easy to customize, or even does not need to be customized. The key points of using the GPT model are two: first, the input form is not limited, and it can be used to take the three-dimensional model (slope support model) as input; second, its output is text, which is consistent with the form of the construction step plan.

[0024] The second implementation of the present application is substantially equivalent to the first implementation, mainly in that, in step S5, a random climate is generated and the influence of the generated random climate on the time consumption is added to the calculation.

[0025] Furthermore, random climate includes light rain, moderate rain, heavy rain, rainstorm, strong wind, high temperature, heavy snow, blizzard, haze, and freezing.

[0026] Furthermore, in step S5, a random event is generated and the influence of the generated random event on the time consumption is added to the calculation.

[0027] Furthermore, random events include water outage, power outage, traffic disruption, personal accidents, underground obstacle handling, fire, and landslide.

[0028] The third embodiment of the present application is substantially equivalent to the first embodiment, mainly in that the preset value in step S6 is set by the user within the range of 2.3 to 2.8, thereby ensuring that the workload of no construction step significantly exceeds the normal range.

[0029] Furthermore, the solution generation model is trained using the slope support model and the corresponding construction step scheme in the historical data as training data, thereby ensuring the pertinence and professionalism of the solution generation model.

[0030] Furthermore, the possible upper limit in step S4 is preset by the user and includes the range of construction steps and corresponding parameters.

[0031] Furthermore, the upper limit may be stored as an XML file using a key-value method.

[0032] Those skilled in the art will appreciate that the above-mentioned embodiments are specific examples for implementing the present invention, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A method for generating a construction plan for a rock slope support model, characterized in that: The following steps are involved: S1. Obtaining a slope support model: obtaining a slope support model containing geological information at a target location from a path selected by a user; S2. Marking connectors: Analyze the slope support model, separate the connectors from the slope support model, mark the separated connectors, mark the unseparated parts as structural parts, and then put the connectors back into the slope support model to obtain a marked slope support model; S3. Generate a construction step plan: input the marked slope support model into a plan generation model to obtain a construction step plan in text form or rich text form; the plan generation model is a GPT model; S4, feasibility check: Check the construction step plan step by step to determine whether there are steps in the construction step plan that exceed the possible upper limit. If so, return directly to step S3 with an error message; S5. Progress simulation: Calculate the time consumption of the construction step plan step by step to form a construction progress plan; S6. Single-point anomaly detection: Perform single-point anomaly detection on the time consumption of each step in the construction progress plan to determine whether the time consumption of any step exceeds the preset value relative to the time consumption of other steps. If so, mark it as an abnormality and return to step S3. If not, output the construction step plan and construction progress plan.

2. The method for generating a rock slope support model construction plan according to claim 1, characterized in that: The preset value in step S6 is set by the user within the range of 2.3 to 2.

8.

3. The method for generating a rock slope support model construction plan according to claim 1, characterized in that: In step S5, random climate is generated and the influence of the generated random climate on the time consumption is added to the calculation.

4. The method for generating a rock slope support model construction plan according to claim 3, characterized in that: The random climate includes light rain, moderate rain, heavy rain, rainstorm, strong wind, high temperature, heavy snow, blizzard, haze, and freezing.

5. The method for generating a rock slope support model construction plan according to claim 1, characterized in that: In step S5, a random event is generated and the influence of the generated random event on the time consumption is added to the calculation.

6. The method for generating a rock slope support model construction plan according to claim 5, characterized in that: The random events include water outage, power outage, traffic interruption, personal accident, underground obstacle handling, fire, and landslide.

7. The method for generating a rock slope support model construction plan according to claim 1, characterized in that: The scheme generation model is trained by using the slope support model and the corresponding construction step scheme in the historical data as training data.

8. The method for generating a rock slope support model construction plan according to claim 1, characterized in that: The possible upper limit in step S4 is preset by the user and includes the range of construction steps and corresponding parameters.

9. The method for generating a rock slope support model construction plan according to claim 8, characterized in that: The possible upper limit is stored as an XML file in a key-value manner.

Images