CN117853077B

CN117853077B - Piling process management method, device, equipment and storage medium

Info

Publication number: CN117853077B
Application number: CN202410260423.0A
Authority: CN
Inventors: 杜振兴; 陈明; 王丽; 罗少攀
Original assignee: China Construction Third Bureau Group South China Co Ltd
Current assignee: China Construction Third Bureau Group South China Co Ltd
Priority date: 2024-03-07
Filing date: 2024-03-07
Publication date: 2024-07-19
Anticipated expiration: 2044-03-07
Also published as: CN117853077A

Abstract

The invention discloses a piling process management method, a piling process management device, piling process management equipment and a piling process storage medium, wherein the piling process management method comprises the following steps: when a piling model is built in a building area to be piled, the building area is taken as a reference to be outwards expanded into a survey area; encoding geological data in the survey area into a first sub-vector; encoding weather information in the survey area into a second sub-vector; encoding pile parameters in the pile model into a third sub-vector; splicing the first sub-vector, the second sub-vector and the third sub-vector into a target vector; clustering the sample models into a plurality of clusters according to accidents occurring during piling of the historical reference sample models; searching a cluster to which the piling model belongs according to the target vector to serve as a target cluster; generating management information for piling in a building area by taking accidents occurring in a coping target cluster as targets; the management information is displayed when the pile model is loaded. The simulation reality is improved, effective reference is provided for the management of the actual piling process, and the security of the piling process is improved.

Description

Piling process management method, device, equipment and storage medium

Technical Field

The present invention relates to the field of building design technology, and in particular, to a method, an apparatus, a device, and a storage medium for managing a pile driving process.

Background

In the fields of architecture, engineering, civil engineering, etc., designers and constructors often use BIM (Building Information Management, building information model) to assist in designing and constructing a building.

At present, when piling, designers and constructors can construct a three-dimensional piling model in advance by using BIM to simulate the piling situation, but the piling model mainly reflects some measurement data and design data, so that the piling situation under ideal situation is simulated, the reality is lower, the reference value for the management of the actual piling process is lower, various accidents are easy to occur, and the piling safety is lower.

Disclosure of Invention

The invention provides a piling process management method, a piling process management device, piling process management equipment and a piling process storage medium, so as to solve the problem of how to improve the authenticity of simulated piling in BIM, thereby improving the piling safety.

According to an aspect of the present invention, there is provided a pile driving process management method applied to a building information model platform, the method comprising:

When a piling model is built in a building area to be piled, the building area is taken as a reference to be outwards expanded into a survey area;

Encoding geological data in the survey area into a first sub-vector;

encoding weather information in the survey area as a second sub-vector;

encoding pile parameters in the pile model into a third sub-vector;

splicing the first sub-vector, the second sub-vector and the third sub-vector into a target vector;

clustering the sample models into a plurality of clusters according to accidents occurring during piling of the historical reference sample models;

searching a cluster to which the piling model belongs according to the target vector to serve as a target cluster;

Generating management information for piling in the building area by taking accidents occurring in the target cluster as targets;

and displaying the management information when the pile driving model is loaded.

According to another aspect of the present invention, there is provided a pile driving process management apparatus for use with a building information model platform, the apparatus comprising:

the survey area generating module is used for expanding the building area to be piled into a survey area outwards by taking the building area as a reference when a piling model is constructed on the building area to be piled;

a first sub-vector encoding module for encoding geological data in the survey area into a first sub-vector;

a second sub-vector encoding module for encoding weather information in the survey area into a second sub-vector;

a third sub-vector encoding module for encoding pile parameters in the pile model into a third sub-vector;

The target vector splicing module is used for splicing the first sub-vector, the second sub-vector and the third sub-vector into a target vector;

The sample clustering module is used for clustering the sample models into a plurality of clusters according to accidents occurring during piling of the historical reference sample models;

The cluster searching module is used for searching a cluster to which the piling model belongs according to the target vector and taking the cluster as a target cluster;

The management information generation module is used for generating management information for piling in the building area by taking accidents occurring in the target cluster as targets;

And the management information display module is used for displaying the management information when the pile driving model is loaded.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of managing a pile driving process according to any one of the embodiments of the invention.

According to another aspect of the invention there is provided a computer readable storage medium storing a computer program for causing a processor to perform the method of managing a pile driving process according to any one of the embodiments of the invention.

The embodiment is applied to a building information model platform, and when a pile driving model is built in a building area to be driven, the building area is taken as a reference to be outwards expanded into a survey area; encoding geological data in the survey area into a first sub-vector; encoding weather information in the survey area into a second sub-vector; encoding pile parameters in the pile model into a third sub-vector; splicing the first sub-vector, the second sub-vector and the third sub-vector into a target vector; clustering the sample models into a plurality of clusters according to accidents occurring during piling of the historical reference sample models; searching a cluster to which the piling model belongs according to the target vector to serve as a target cluster; generating management information for piling in a building area by taking accidents occurring in a coping target cluster as targets; the management information is displayed when the pile model is loaded. According to the embodiment, the characteristics of piling are represented in the dimensions of surrounding environment, short-time weather and piling operation, the characteristics of piling are enriched, the history piling situation is fitted, the possible occurrence story is predicted, corresponding management information is given in the piling process, so that the piling is as close to the actual situation as possible, the simulation authenticity is improved, effective references are provided for the actual piling process management, coping is carried out in advance, the probability of various accidents is reduced, and the safety of the piling process is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method of managing a pile driving process according to a first embodiment of the present invention;

FIG. 2 is a schematic illustration of a building area and survey area provided in accordance with a first embodiment of the present invention;

FIG. 3 is an exemplary diagram of a grid adjacency provided in accordance with one embodiment of the present invention;

Fig. 4 is a schematic structural view of a pile driving process management device according to a second embodiment of the present invention;

Fig. 5 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein are capable of being practiced otherwise than as specifically illustrated and described. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a pile driving process management method according to a first embodiment of the present invention, where the method is applied to a building information model platform, and includes the following steps:

step 101, when constructing a pile model of a building area to be piled, the building area is used as a reference to be outwards expanded into a survey area.

In this embodiment, as shown in fig. 2, an electronic map may be loaded, and a design drawing is imported on the electronic map, so that a piling point 201 is marked on the electronic map, where the piling point is a position waiting for piling.

Typically, the number of piling points 201 is two or more, and all are gathered in a certain area, so that for convenience of representation, a minimum circumscribing rectangle with right direction can be generated for the piling points 201 as the building area 202 to be piled.

By righting, it is meant that the four sides of the building area 202 (not distinguishing the width and height) are oriented to the east, south, west and north, respectively.

When a three-dimensional pile model is built for each pile driving point in the BIM, a certain range can be extended outwards by taking the building area 202 as a reference to obtain a survey area 203, and the survey area 203 is the surrounding environment of the building area 202, so that the pile driving has obvious influence.

In a specific implementation, the distance from the center point of the building area to each side may be measured, multiplied by a preset magnification factor (e.g., 2.5, etc.), to obtain a new distance, and the new distance used to construct the survey area.

Step 102, geological data in the survey area is encoded into a first sub-vector.

In general, one dimension that has a relatively significant impact on pile driving is the address, and in this embodiment, address data of the survey area may be collected and vectorized to encode it into a first sub-vector.

In particular implementations, remote sensing image data acquired over or to the survey area may be acquired in historical or real-time using tools such as an automatic aircraft.

And performing semantic segmentation on the remote sensing image data by using a deep learning model such as FCN (Fully Convolutional Networks, full convolution network), segNet (Semantic Segmentation Networks, semantic segmentation network) and the like to obtain semantic information of each pixel point.

Further, the semantic information generally refers to categories, and the granularity of the categories may be classified according to actual situations, for coarse granularity, water, buildings, soil, rocks, plants, for fine granularity, rivers, lakes, roofs, pavement, bushes, trees, etc., which is not limited in this embodiment.

As shown in fig. 2, the telemetry image data is divided into a plurality of grids 204, the grids 204 are generally square with designated sides, and for decision making, the plurality of grids 204 cover the survey area 203, i.e., all grids 204 comprise a larger extent than the survey area 203 and include the survey area 203, and particularly a portion of the grids 204 comprise an extent that overlaps the building area 202 and a portion of the grids 204 comprise an extent that overlaps the survey area 203.

Each grid is traversed and compared to the survey area, and if the traversed current grid is located in the survey area (including the case where the current grid intersects the survey area, i.e., the edges of the grid overlap the edges of the survey area and the grid does not exceed the survey area), other grids adjacent to the current grid are determined.

Illustratively, as shown in fig. 3, each grid is set to a logical distance, and if the smallest logical distance between a certain grid and the current grid O is less than or equal to a preset distance threshold (e.g., 1), the grid may be considered to be adjacent to the current grid O.

Semantic information of all pixel points in the current grid and other grids is input into a pre-trained gradient lifting decision tree (Gradient Boosting Decision Tree, GBDT) to make a decision, and the earth surface attribute of the current grid is obtained.

GBDT is an alternative decision tree algorithm by constructing a set of weak learners (trees) and accumulating the results of multiple decision trees as the final prediction output.

The earth's surface properties refer to information observable by the earth's surface and related to pile driving, including waters, soil, gravel and rock, and the like.

In addition, formation properties acquired at various subsurface depths (e.g., acquisition of the subsurface properties once every 50cm interval) in a survey area (either in real-time borehole or the like) may be acquired, such as soft earth, sand, silt formations, boulders, hard clays, mudstones, limestone karst cave formations, granite hard rock formations, and the like.

The earth's surface properties and the formation properties are arranged in order to form geological data of the survey area, and the geological data is encoded into a first sub-vector using a one-hot (independent heating) or the like method.

Step 103, the weather information in the investigation region is encoded into a second sub-vector.

In general, one dimension with obvious influence on pile driving is weather, and in this embodiment, weather information in a short period of a survey area can be collected and vectorized, so that the weather information is encoded into a second sub-vector.

In a specific implementation, weather with obvious geological influence is mainly temperature and rainfall, so that on one hand, a first temperature value and a first rainfall recorded in a survey area in a plurality of historical time periods (such as days) can be inquired, and on the other hand, a second temperature value and a second rainfall predicted in a plurality of future time periods (such as days) of the survey area can be inquired.

And forming weather information in the investigation region by arranging the first temperature value, the second temperature value, the first rainfall and the second rainfall in sequence, and encoding the weather information into a second sub-vector by using a one-hot method and the like.

Step 104, encoding pile parameters in the pile model into a third sub-vector.

In this embodiment, some important pile parameters, such as pile depth, pile radius, pile material, pile driver type, etc., may be selected from the pile model, and these pile parameters are sequentially arranged and vectorized, and encoded into a third subvector by using one-hot or other methods.

Step 105, stitching the first sub-vector, the second sub-vector and the third sub-vector to form a target vector.

In this embodiment, the first sub-vector, the second sub-vector and the third sub-vector may be spliced to obtain the target vector, so that the target vector represents the feature of pile driving integrity.

And 106, clustering the sample models into a plurality of clusters according to accidents occurring during piling of the historical reference sample models.

In this embodiment, a pile model in which pile driving has been completed in history may be queried, and as a sample model, the sample model may be clustered into a plurality of clusters using accidents occurring when the history reference sample model is used for pile driving, so that the clusters embody the same or similar accidents when pile driving of the same category is embodied.

In one embodiment of the present invention, step 106 may include the steps of:

Step 1061, a sample model and a sample vector are obtained.

In this embodiment, a sample model and its associated sample vector may be read from historical data, where the sample model is a pile model that historically simulates pile driving, thereby referencing pile driving as a reference, and the sample vector is a target vector generated for the sample model.

In this embodiment, after pile driving is completed, the current pile driving model and its target vector may be used as the sample model and its sample vector for the subsequent cluster.

Step 1062, training the plurality of sets using the sample vectors, respectively.

In this embodiment, the same clustering algorithm may be invoked, different clustering parameters may be adjusted, and sample vectors are used to cluster sample models to obtain multiple sets, where one set is a result of one-time clustering, each set has multiple clusters, the sample models are divided into clusters, and the clusters in each set include the sample models.

Because the clustering parameters are different, the number of clusters in each set is different, so that the distribution condition of sample models in the clusters in each set is different.

In a preferred embodiment of the present invention, step 1062 may further include the sub-steps of:

sub-step 10621, initializing a plurality of sets.

In this embodiment, the cluster parameter that is adjusted is the number of clusters, and then, in the initial stage, multiple sets may be initialized, and each set iterates on the sample model separately for multiple rounds, so as to implement clustering of the sample model.

And each set is provided with a set value, wherein the set value is the number of clusters in the set.

Further, the aggregate value may be an average value at a predetermined interval (e.g., 1 or 2) over a wide range (e.g., [5, 30 ]).

Sub-step 10622, generating a number of clusters of aggregate values in each aggregate.

In clustering in the respective sets, a plurality of clusters may be initialized so that the number of clusters is a set value, wherein each cluster has a center point, which may be set randomly at the beginning, or points as far as possible from each other may be selected as the center points, or the like, which is not limited in this embodiment.

Sub-step 10623, in each set, calculates a distance between a sample vector of each sample model and the center point.

In each cluster of each set, the sample model is taken as a point, the sample vector of the sample model is taken as the dimension of the point, and the distance between the sample vector of each sample model and the center point is calculated by using Euclidean distance, cosine distance and the like.

Sub-step 10624, in each set, the sample models are partitioned into clusters with the smallest distance.

And traversing each sample model in each cluster of each set, comparing the distances between the sample model and each cluster, and dividing the sample model into the cluster with the smallest distance in the round of iteration.

Sub-step 10625, in each set, updates the center point using the average of the sample vectors of all sample models within each cluster.

In each cluster of each set, the average value of the sample vectors of all the sample models is updated to the value of the center point.

Sub-step 10626, in each set, determining whether the center point in each cluster changes during updating; if so, sub-step 10627 is performed, and if not, sub-step 10622-sub-step 10626 is performed back.

Sub-step 10627, determining clusters within the set complete training.

In each set, for the same cluster, a difference (e.g., a distance) between a value of a center point before update and a value after update may be calculated, if the difference is small (e.g., the distance is less than or equal to a certain threshold), the center point may be considered unchanged at the time of update, and if the difference is large (e.g., the distance is greater than a certain threshold), the center point may be considered changed at the time of update.

If the center points in the clusters in the same set are unchanged during updating, the convergence of the clusters in the set can be confirmed, and the clusters in the set complete training.

If the center points in each cluster in the same set change during updating, it can be confirmed that the clusters in the set do not converge, and the next iteration is performed, and sub-steps 10622-10626 are re-performed until each cluster in the set converges.

Step 1063, inquiring accident information of accident records generated during pile driving according to the sample model.

When the historical reference sample model is used for actual piling, different accidents can occur, such as pile position deviation, pile body inclination, pile body necking, hole collapse, exceeding of the sediment thickness, floating of a reinforcement cage, pipe water inflow, pipe clamping, pipe burying, pile breaking, pile casing periphery water leakage, low pile body concrete strength and the like, and at the end of piling, designers and constructors can record accident information.

In this embodiment, each sample model may be traversed to query accident information referencing accident records that occur when the sample model is piled.

Step 1064, in each set, calculating the adaptation degree between the cluster and the single accident according to the accident information.

In this embodiment, one of the targets for clustering the sample models is that the piling situation (i.e., surrounding environment, short-term weather, piling operation) of the sample models in each cluster is the same or similar, and that the accident that occurs is single, i.e., the accident in each cluster is the same or similar.

In each set, accident information of sample models in each cluster can be traversed, natural language processing can be carried out on the accident information, and therefore the adaptation degree between the clusters and the single accident can be calculated according to the accident information.

In one example, in each set, the type of accident, the grade of the accident, is read from the accident information of each sample model, for example, for pile body inclination (type), the angle of pile body inclination may be divided into a plurality of inclination ranges, each inclination range representing one grade.

In each cluster, the duty ratio of the sample models under each category in all sample models is counted, namely, the number of the sample models under each category is counted, the number of all sample models is counted, the ratio of the number of the sample models under each category to the number of all sample models is calculated, and the duty ratio of the sample models under each category in all sample models is obtained.

The duty cycles of the sample models at all sample models for each category are compared.

The sample models under the category with the highest duty ratio are divided into a first model group, and the sample models except the first model group are divided into a second model group.

In the first model population, a first degree of dispersion is calculated for the scale using an algorithm such as standard deviation.

The second degree of discretization is calculated for the number of sample models in the second model population using standard deviation or the like.

And adding the product of the duty ratio of the first model group and the first weight, the product of the reciprocal of the first discrete degree and the second weight and the product of the reciprocal of the second discrete degree and the third weight to obtain the adaptation degree between the cluster and the single accident, wherein the first weight, the second weight and the third weight can be adjusted according to experience and belong to super-parameters.

In this example, the degree of fit between clusters and single incidents is expressed as follows:

；

Wherein, Is the firstThe degree of fit between clusters and single incidents,Is the first in the clusterThe number of sample models under the category of the incident,For the number of categories for all incidents in the cluster,In order to take the maximum value it is,For the number of sample models under the category of all incidents in the cluster,To a first degree of discretization,To a second degree of discretization,As a first weight to be used,As a result of the second weight being set,Is a third weight.

Further, in the case that pile driving conditions (i.e., surrounding environment, short weather, pile driving operation) of the sample models in each cluster are the same or similar, if a single accident occurs, the ratio of the accident of a certain class is obviously higher than that of the accident of other classes, the classes of the accidents should be the same or similar in consideration of the classification level with a certain man-made subjectivity, and the accidents of other classes should be sporadic accidents with randomness, basically normal distribution and lower in second discrete degree.

Step 1065, fusing all the adaptation degrees into cluster quality values of the sets in each set.

In the same cluster, the adaptation degree of all clusters can be fused into the cluster quality value of the set in a linear (such as weighted summation) or nonlinear mode, and the cluster quality value is the quantized representation of the quality of the clusters in the set.

In one example, in each set, all the adaptation degrees are substituted into the following formula to calculate, and obtain the cluster quality value of the set:

；

Wherein, For the cluster quality value of the set,Is the first in the collectionThe degree of adaptation of the individual clusters,For the number of clusters in the set,、And (3) withAre all the coefficients of the two-dimensional space,Is a natural number, wherein,、And (3) withAll can be adjusted according to experience, and belongs to super parameters.

In this example, the cluster quality value contains two items, one of which is an average value calculated for the degree of fit of all clusters, and the cluster quality value of the set is mainly in positive correlation with the average value of the degree of fit of all clusters, i.e. the larger the average value of the degree of fit of all clusters is, the larger the cluster quality value of the set is, whereas the smaller the average value of the degree of fit of all clusters is, the smaller the cluster quality value of the set is.

The other term is a constraint term, the number of the classes of accidents is limited in a statistically available range, the number of the accidents is basically in a certain numerical range, the sporadic accidents are divided into one cluster to avoid overfitting, the number of the clusters can be used as the constraint term of the adaptation degree of the set, if the number is in the numerical range, the numerical value of the constraint term is higher, and if the number is too small and too large, the numerical value of the constraint term is lower.

Step 1066, determining that the cluster in the set with the highest cluster quality value is valid.

And comparing the cluster quality values of the sets, confirming that the clusters in the set with the highest cluster quality value are effective, performing subsequent processing by using the clusters in the set with the highest cluster quality value, and filtering the set with the non-highest cluster quality value.

And 107, searching a cluster to which the piling model belongs according to the target vector to serve as a target cluster.

For the current piling model, the target vector of the current piling model can be compared with each cluster, and the cluster to which the piling model belongs is confirmed and is recorded as the target cluster.

In a specific implementation, the distance between the target vector and the center point of each cluster can be calculated in the modes of Euclidean distance, cosine distance and the like, and k (k is a positive integer, such as 3) clusters with the highest distance between people and the clusters are clusters to which the piling model belongs and serve as target clusters.

Step 108, aiming at coping with accidents occurring in the target cluster, generating management information for the piling process of the building area.

In practical application, the piling process comprises a plurality of nodes, and each node has corresponding design and construction specifications.

In one example, the process of piling includes the following nodes:

1. Early preparation:

The position and the number of piling are determined according to the design requirements and engineering requirements. The construction site is surveyed and measured, the construction accuracy and safety are ensured, and corresponding materials and equipment such as pile drivers, reinforcing steel bars, concrete and the like are prepared.

2. Pile foundation preparation:

And cleaning a construction area, removing barriers, and ensuring that soil or water areas around the pile foundation are cleaned. If necessary, a foundation treatment such as excavation of pits, reinforcement of soft foundations, etc. is performed.

3. Positioning and elevation control:

The position and elevation of the pile site are accurately measured and marked using measuring instruments and tools.

4. Pile driver installation and commissioning:

and selecting a proper pile driver, and installing and debugging according to design requirements and types of piles. Pile drivers typically include vibratory hammers, counter-hammers, or hydraulic presses. And according to the characteristics and the operation method of the selected pile machine, ensuring the firm installation of the pile machine, and testing and adjusting.

5. Piling is started:

According to design requirements, reasonable piling methods and technologies are adopted, and piles (such as reinforced concrete piles, steel pipe piles and the like) are gradually driven into the ground or water by operating a pile driver. In the piling process, the vertical position and the perpendicularity of the pile are ensured to meet the requirements by adjusting and monitoring according to actual conditions.

6. Acceptance and recording:

Quality inspection of the driven pile is performed, including checking the perpendicularity, length, strength, etc. of the pile. Meanwhile, relevant piling data are recorded, and the relevant piling data comprise information such as the position, depth and verticality of each pile, so that construction of subsequent procedures can be used and traced.

In this embodiment, an accident that may occur (i.e., the type of accident with the highest proportion in the target cluster) may be selected from the target clusters, the manner of handling the accident may be queried from the accident information recorded by the accident when piling with reference to the sample model, the node that may occur the accident may be found in the process of piling in the building area, and the manner of handling the accident may be marked at the node to obtain the management information.

And step 109, displaying management information when the pile driving model is loaded.

When the BIM renders the pile driving model for a designer and/or constructor to browse, management information can be displayed at the same time for the designer and/or constructor to reference.

Example two

Fig. 4 is a schematic structural diagram of a management device for pile driving process according to a second embodiment of the present invention. As shown in fig. 4, the device is applied to a building information model platform and comprises the following modules:

A survey area generating module 401, configured to, when constructing a pile model for a building area to be piled, outwardly expand into a survey area with the building area as a reference;

A first sub-vector encoding module 402 for encoding geological data in the survey area into a first sub-vector;

a second sub-vector encoding module 403, configured to encode weather information in the survey area into a second sub-vector;

A third sub-vector encoding module 404 for encoding pile parameters in the pile model into a third sub-vector;

A target vector stitching module 405, configured to stitch the first sub-vector, the second sub-vector, and the third sub-vector into a target vector;

A sample clustering module 406, configured to cluster a historical reference sample model into a plurality of clusters according to an accident occurring when the sample model is piled;

The cluster searching module 407 is configured to search a cluster to which the piling model belongs according to the target vector, as a target cluster;

A management information generating module 408, configured to generate management information for piling a pile in the building area with a view to coping with an accident occurring in the target cluster;

And the management information display module 409 is used for displaying the management information when the pile model is loaded.

In a preferred embodiment of the present invention, the first sub-vector encoding module 402 is further configured to:

Acquiring remote sensing image data acquired from the survey area;

executing semantic segmentation on the remote sensing image data to obtain semantic information of each pixel point;

dividing the remote sensing image data into a plurality of grids; a plurality of the grids covering the survey area;

If the current grid is located in the survey area, determining other grids adjacent to the current grid;

Inputting semantic information of the current grid and all pixel points in other grids into a pre-trained gradient lifting decision tree for decision making, so as to obtain the earth surface attribute of the current grid; the surface attributes include water, soil, gravel and rock;

acquiring stratum attributes acquired at each subsurface depth in the survey area;

the earth surface attributes and the formation attributes are organized into geological data of the survey area, and the geological data is encoded into a first sub-vector.

In a preferred embodiment of the present invention, the second sub-vector encoding module 403 is further configured to:

inquiring a first temperature value and a first rainfall recorded by the survey area in a plurality of historical time periods;

querying a second temperature value and a second rainfall predicted by the survey area in a plurality of future time periods;

and forming weather information in the investigation region by the first temperature value, the second temperature value, the first rainfall and the second rainfall, and encoding the weather information into a second sub-vector.

In a preferred embodiment of the present invention, the sample clustering module 406 is further configured to:

Obtaining a sample model and a sample vector; the sample model is a piling model of historical reference piling, and the sample vector is a target vector generated for the sample model;

Training a plurality of sets respectively by using the sample vectors, wherein clusters in each set comprise the sample model, and the number of clusters in each set is different;

Inquiring accident information of accident records generated when the sample model is piled;

Calculating the adaptation degree between the clusters and single accidents according to the accident information in each set;

fusing all the adaptation degrees into cluster quality values of the sets in each set;

determining that the cluster in the set with the highest cluster quality value is valid.

Initializing a plurality of sets; set values are set in each set;

Generating clusters with the quantity of the set values in each set; each of the clusters has a center point;

calculating, in each of the sets, a distance between the sample vector of each of the sample models and the center point;

In each of the sets, grouping the sample models into the clusters having the smallest distance;

updating the center point in each of the sets using an average of the sample vectors of all of the sample models within each of the clusters;

Judging whether the central point in each cluster changes in updating or not in each set; if yes, determining that the clusters in the set complete training; and if not, returning to execute the calculation of the distance between the sample vector of each sample model and the central point in each set.

reading the category of the accident and the grade of the accident from the accident information of each sample model in each set;

in each cluster, counting the duty ratio of the sample model under each category to all the sample models;

dividing the sample model under the category with the highest duty ratio into a first model group, and dividing the sample model except the first model group into a second model group;

Calculating a first degree of discretization for the class in the first model population;

calculating a second degree of discretization for the number of sample models in the second model population;

And adding the product of the duty ratio of the first model group and a first weight, the product of the reciprocal of the first discrete degree and a second weight and the product of the reciprocal of the second discrete degree and a third weight to obtain the adaptation degree between the cluster and the single accident.

Substituting all the adaptation degrees into the following formulas in each set to calculate and obtain the clustering quality value of the set:

；

Wherein, For the cluster quality value of the set,Is the first in the collectionThe degree of adaptation of the individual clusters,For the number of clusters in the set,、And (3) withAre coefficients.

The piling process management device provided by the embodiment of the invention can execute the piling process management method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the piling process management method.

Example III

Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the pile driving process management method.

In some embodiments, the pile driving process management method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more of the steps of the pile driving process management method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the pile driving process management method in any other suitable way (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

Example IV

Embodiments of the present invention also provide a computer program product comprising a computer program which, when executed by a processor, implements a method of managing a pile driving process as provided by any of the embodiments of the present invention.

Computer program product in the implementation, the computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of pile driving process management, for application to a building information model platform, the method comprising:

Encoding geological data in the survey area into a first sub-vector;

encoding weather information in the survey area as a second sub-vector;

encoding pile parameters in the pile model into a third sub-vector;

Displaying the management information when loading the pile model;

the method for clustering the sample model into a plurality of clusters according to the accident occurring when piling the historical reference sample model comprises the following steps:

Determining that the cluster in the set with the highest cluster quality value is valid;

the training of the plurality of sets using the sample vectors, respectively, includes:

Initializing a plurality of sets; set values are set in each set;

judging whether the central point in each cluster changes in updating or not in each set; if not, determining that the clusters in the set complete training; if yes, returning to execute the calculation of the distance between the sample vector of each sample model and the central point in each set.

2. The method of claim 1, wherein the encoding the geological data in the survey area into a first sub-vector comprises:

Acquiring remote sensing image data acquired from the survey area;

3. The method of claim 1, wherein the encoding the weather information in the survey area as a second sub-vector comprises:

4. The method of claim 1, wherein said calculating, in each of said sets, a degree of fit between said cluster and a single one of said incidents from said incident information comprises:

5. The method of claim 1, wherein said fusing all of said fitness levels in each of said sets to cluster quality values for said sets comprises:

；

6. A pile driving process management device for use with a building information model platform, the device comprising:

the management information display module is used for displaying the management information when the pile driving model is loaded;

Wherein, the sample clustering module is further configured to:

The sample clustering module is further configured to:

Initializing a plurality of sets; set values are set in each set;

7. An electronic device, the electronic device comprising:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the pile driving procedure management method of any one of claims 1-5.

8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for causing a processor to implement the pile driving process management method according to any one of claims 1-5 when executed.